HTTPie)',\n ]\n\n\noptions_highlighter = OptionsHighlighter()\n\n\ndef unpack_argument(\n argument: Argument,\n) -> Tuple[Text, Text]:\n opt1 = opt2 = ''\n\n style = None\n if argument.aliases:\n if len(argument.aliases) >= 2:\n opt2, opt1 = argument.aliases\n else:\n (opt1,) = argument.aliases\n else:\n opt1 = argument.metavar\n style = STYLE_USAGE_REGULAR\n\n return Text(opt1, style=style), Text(opt2)\n\n\ndef to_usage(\n spec: ParserSpec,\n *,\n program_name: Optional[str] = None,\n whitelist: AbstractSet[str] = frozenset()\n) -> RenderableType:\n shown_arguments = [\n argument\n for group in spec.groups\n for argument in group.arguments\n if (not argument.aliases or whitelist.intersection(argument.aliases))\n ]\n\n # Sort the shown_arguments so that --dash options are\n # shown first\n shown_arguments.sort(key=lambda argument: argument.aliases, reverse=True)\n\n text = Text(program_name or spec.program, style=STYLE_BOLD)\n for argument in shown_arguments:\n text.append(' ')\n\n is_whitelisted = whitelist.intersection(argument.aliases)\n if argument.aliases:\n name = '/'.join(sorted(argument.aliases, key=len))\n else:\n name = argument.metavar\n\n nargs = argument.configuration.get('nargs')\n if nargs is Qualifiers.OPTIONAL:\n text.append('[' + name + ']', style=STYLE_USAGE_OPTIONAL)\n elif nargs is Qualifiers.ZERO_OR_MORE:\n text.append(\n '[' + name + ' ...]',\n style=STYLE_USAGE_OPTIONAL,\n )\n else:\n text.append(\n name,\n style=STYLE_USAGE_ERROR\n if is_whitelisted\n else STYLE_USAGE_REGULAR,\n )\n\n raw_form = argument.serialize()\n if raw_form.get('choices'):\n text.append(' ')\n text.append(\n '{' + ', '.join(raw_form['choices']) + '}',\n style=STYLE_USAGE_MISSING,\n )\n\n return text\n\n\n# This part is loosely based on the rich-click's help message\n# generation.\ndef to_help_message(\n spec: ParserSpec,\n) -> Iterable[RenderableType]:\n yield Padding(\n options_highlighter(spec.description),\n LEFT_INDENT_2,\n )\n\n yield Padding(\n Text('Usage', style=STYLE_SWITCH),\n LEFT_INDENT_2,\n )\n yield Padding(to_usage(spec), LEFT_INDENT_3)\n\n group_rows = {}\n for group in spec.groups:\n options_rows = []\n\n for argument in group.arguments:\n if argument.is_hidden:\n continue\n\n opt1, opt2 = unpack_argument(argument)\n if opt2:\n opt1.append('/')\n opt1.append(opt2)\n\n # Column for a metavar, if we have one\n metavar = Text(style=STYLE_METAVAR)\n metavar.append(argument.configuration.get('metavar', ''))\n\n if opt1 == metavar:\n metavar = Text('')\n\n raw_form = argument.serialize()\n desc = raw_form.get('short_description', '')\n if raw_form.get('choices'):\n desc += ' (choices: '\n desc += textwrap.shorten(\n ', '.join(raw_form.get('choices')),\n MAX_CHOICE_CHARS,\n )\n desc += ')'\n\n rows = [\n Padding(\n options_highlighter(opt1),\n LEFT_PADDING_2,\n ),\n metavar,\n options_highlighter(desc),\n ]\n\n options_rows.append(rows)\n if argument.configuration.get('nested_options'):\n options_rows.extend(\n [\n (\n Padding(\n Text(\n key,\n style=STYLE_USAGE_OPTIONAL,\n ),\n LEFT_PADDING_4,\n ),\n value,\n dec,\n )\n for key, value, dec in argument.nested_options\n ]\n )\n\n group_rows[group.name] = options_rows\n\n options_table = Table(highlight=False, box=None, show_header=False)\n for group_name, options_rows in group_rows.items():\n options_table.add_row(Text(), Text(), Text())\n options_table.add_row(\n Text(group_name, style=STYLE_SWITCH),\n Text(),\n Text(),\n )\n options_table.add_row(Text(), Text(), Text())\n for row in options_rows:\n options_table.add_row(*row)\n\n yield Padding(\n Text('Options', style=STYLE_SWITCH),\n LEFT_INDENT_2,\n )\n yield Padding(options_table, LEFT_PADDING_2)\n yield Padding(\n Text('More Information', style=STYLE_SWITCH),\n LEFT_INDENT_2,\n )\n yield Padding(\n MORE_INFO_COMMANDS.rstrip('\\n'),\n LEFT_PADDING_3\n )\n yield Padding(\n spec.epilog.rstrip('\\n'),\n LEFT_INDENT_BOTTOM_3,\n )\n\n\n\nFile: httpie/output/ui/man_pages.py\n\n\"\"\"Logic for checking and displaying man pages.\"\"\"\n\nimport subprocess\nimport os\nfrom httpie.context import Environment\n\n\nMAN_COMMAND = 'man'\nNO_MAN_PAGES = os.getenv('HTTPIE_NO_MAN_PAGES', False)\n\n# On some systems, HTTP(n) might exist, but we are only interested in HTTP(1).\n# For more information on man page sections: <https://unix.stackexchange.com/a/138643>\nMAN_PAGE_SECTION = '1'\n\n\ndef is_available(program: str) -> bool:\n \"\"\"\n Check whether `program`'s man pages are available on this system.\n\n \"\"\"\n if NO_MAN_PAGES or os.system == 'nt':\n return False\n try:\n process = subprocess.run(\n [MAN_COMMAND, MAN_PAGE_SECTION, program],\n shell=False,\n stdout=subprocess.DEVNULL,\n stderr=subprocess.DEVNULL\n )\n except Exception:\n # There might be some errors outside the process, e.g\n # a permission error to execute something that is not an\n # executable.\n return False\n else:\n return process.returncode == 0\n\n\ndef display_for(env: Environment, program: str) -> None:\n \"\"\"\n Open the system man page for the given command (http/https/httpie).\n\n \"\"\"\n subprocess.run(\n [MAN_COMMAND, MAN_PAGE_SECTION, program],\n stdout=env.stdout,\n stderr=env.stderr\n )\n\n\n\nFile: httpie/output/ui/rich_palette.py\n\nfrom collections import ChainMap\nfrom typing import TYPE_CHECKING, Any, Optional\n\nif TYPE_CHECKING:\n from rich.theme import Theme\n\nfrom httpie.output.ui.palette import GenericColor, PieStyle, Styles, ColorString, _StyledGenericColor # noqa\n\nRICH_BOLD = ColorString('bold')\n\n# Rich-specific color code declarations\n# <https://github.com/Textualize/rich/blob/fcd684dd3a482977cab620e71ccaebb94bf13ac9/rich/default_styles.py>\nCUSTOM_STYLES = {\n 'progress.description': RICH_BOLD | GenericColor.WHITE,\n 'progress.data.speed': RICH_BOLD | GenericColor.GREEN,\n 'progress.percentage': RICH_BOLD | GenericColor.AQUA,\n 'progress.download': RICH_BOLD | GenericColor.AQUA,\n 'progress.remaining': RICH_BOLD | GenericColor.ORANGE,\n 'bar.complete': RICH_BOLD | GenericColor.PURPLE,\n 'bar.finished': RICH_BOLD | GenericColor.GREEN,\n 'bar.pulse': RICH_BOLD | GenericColor.PURPLE,\n 'option': RICH_BOLD | GenericColor.PINK,\n}\n\n\nclass _GenericColorCaster(dict):\n \"\"\"\n Translate GenericColor to a regular string on the attribute access\n phase.\n \"\"\"\n\n def _translate(self, key: Any) -> Any:\n if isinstance(key, GenericColor):\n return key.name.lower()\n else:\n return key\n\n def __getitem__(self, key: Any) -> Any:\n return super().__getitem__(self._translate(key))\n\n def get(self, key: Any) -> Any:\n return super().get(self._translate(key))\n\n\ndef _make_rich_color_theme(style_name: Optional[str] = None) -> 'Theme':\n from rich.style import Style\n from rich.theme import Theme\n\n try:\n PieStyle(style_name)\n except ValueError:\n style = Styles.ANSI\n else:\n style = Styles.PIE\n\n theme = Theme()\n for color, color_set in ChainMap(\n GenericColor.__members__, CUSTOM_STYLES\n ).items():\n if isinstance(color_set, _StyledGenericColor):\n properties = dict.fromkeys(color_set.styles, True)\n color_set = color_set.color\n else:\n properties = {}\n\n theme.styles[color.lower()] = Style(\n color=color_set.apply_style(style, style_name=style_name),\n **properties,\n )\n\n # E.g translate GenericColor.BLUE into blue on key access\n theme.styles = _GenericColorCaster(theme.styles)\n return theme\n\n\n\nFile: httpie/output/ui/rich_progress.py\n\nfrom dataclasses import dataclass\nfrom typing import TYPE_CHECKING, Optional\n\nfrom httpie.context import Environment\n\nif TYPE_CHECKING:\n from rich.console import Console\n\n\n@dataclass\nclass BaseDisplay:\n env: Environment\n\n def start(\n self, *, total: Optional[float], at: float, description: str\n ) -> None:\n ...\n\n def update(self, steps: float) -> None:\n ...\n\n def stop(self, time_spent: float) -> None:\n ...\n\n @property\n def console(self) -> 'Console':\n \"\"\"Returns the default console to be used with displays (stderr).\"\"\"\n return self.env.rich_error_console\n\n def _print_summary(\n self, is_finished: bool, observed_steps: int, time_spent: float\n ):\n from rich import filesize\n\n if is_finished:\n verb = 'Done'\n else:\n verb = 'Interrupted'\n\n total_size = filesize.decimal(observed_steps)\n avg_speed = filesize.decimal(observed_steps / time_spent)\n\n minutes, seconds = divmod(time_spent, 60)\n hours, minutes = divmod(int(minutes), 60)\n if hours:\n total_time = f'{hours:d}:{minutes:02d}:{seconds:0.5f}'\n else:\n total_time = f'{minutes:02d}:{seconds:0.5f}'\n\n self.console.print(\n f'[progress.description]{verb}. {total_size} in {total_time} ({avg_speed}/s)'\n )\n\n\nclass DummyDisplay(BaseDisplay):\n \"\"\"\n A dummy display object to be used when the progress bars,\n spinners etc. are disabled globally (or during tests).\n \"\"\"\n\n\nclass StatusDisplay(BaseDisplay):\n def start(\n self, *, total: Optional[float], at: float, description: str\n ) -> None:\n self.observed = at\n self.description = (\n f'[progress.description]{description}[/progress.description]'\n )\n\n self.status = self.console.status(self.description, spinner='line')\n self.status.start()\n\n def update(self, steps: float) -> None:\n from rich import filesize\n\n self.observed += steps\n\n observed_amount, observed_unit = filesize.decimal(\n self.observed\n ).split()\n self.status.update(\n status=f'{self.description} [progress.download]{observed_amount}/? {observed_unit}[/progress.download]'\n )\n\n def stop(self, time_spent: float) -> None:\n self.status.stop()\n self.console.print(self.description)\n if time_spent:\n self._print_summary(\n is_finished=True,\n observed_steps=self.observed,\n time_spent=time_spent,\n )\n\n\nclass ProgressDisplay(BaseDisplay):\n def start(\n self, *, total: Optional[float], at: float, description: str\n ) -> None:\n from rich.progress import (\n Progress,\n BarColumn,\n DownloadColumn,\n TimeRemainingColumn,\n TransferSpeedColumn,\n )\n\n assert total is not None\n self.console.print(f'[progress.description]{description}')\n self.progress_bar = Progress(\n '[',\n BarColumn(),\n ']',\n '[progress.percentage]{task.percentage:>3.0f}%',\n '(',\n DownloadColumn(),\n ')',\n TimeRemainingColumn(),\n TransferSpeedColumn(),\n console=self.console,\n transient=True,\n )\n self.progress_bar.start()\n self.transfer_task = self.progress_bar.add_task(\n description, completed=at, total=total\n )\n\n def update(self, steps: float) -> None:\n self.progress_bar.advance(self.transfer_task, steps)\n\n def stop(self, time_spent: Optional[float]) -> None:\n self.progress_bar.stop()\n\n if time_spent:\n [task] = self.progress_bar.tasks\n self._print_summary(\n is_finished=task.finished,\n observed_steps=task.completed,\n time_spent=time_spent,\n )\n\n\n\nFile: httpie/output/lexers/metadata.py\n\nimport pygments\n\nfrom httpie.models import ELAPSED_TIME_LABEL\nfrom httpie.output.lexers.common import precise\n\nSPEED_TOKENS = {\n 0.45: pygments.token.Number.SPEED.FAST,\n 1.00: pygments.token.Number.SPEED.AVG,\n 2.50: pygments.token.Number.SPEED.SLOW,\n}\n\n\ndef speed_based_token(lexer, match, ctx):\n try:\n value = float(match.group())\n except ValueError:\n return pygments.token.Number\n\n for limit, token in SPEED_TOKENS.items():\n if value <= limit:\n break\n else:\n token = pygments.token.Number.SPEED.VERY_SLOW\n\n response_type = precise(\n lexer,\n token,\n pygments.token.Number\n )\n yield match.start(), response_type, match.group()\n\n\nclass MetadataLexer(pygments.lexer.RegexLexer):\n \"\"\"Simple HTTPie metadata lexer.\"\"\"\n\n tokens = {\n 'root': [\n (\n fr'({ELAPSED_TIME_LABEL})( *)(:)( *)(\\d+\\.\\d+)(s)', pygments.lexer.bygroups(\n pygments.token.Name.Decorator, # Name\n pygments.token.Text,\n pygments.token.Operator, # Colon\n pygments.token.Text,\n speed_based_token,\n pygments.token.Name.Builtin # Value\n )\n ),\n # Generic item\n (\n r'(.*?)( *)(:)( *)(.+)', pygments.lexer.bygroups(\n pygments.token.Name.Decorator, # Name\n pygments.token.Text,\n pygments.token.Operator, # Colon\n pygments.token.Text,\n pygments.token.Text # Value\n )\n ),\n ]\n }\n\n\n\nFile: httpie/output/lexers/__init__.py\n\n\n\n\nFile: httpie/output/lexers/common.py\n\ndef precise(lexer, precise_token, parent_token):\n # Due to a pygments bug*, custom tokens will look bad\n # on outside styles. Until it is fixed on upstream, we'll\n # convey whether the client is using pie style or not\n # through precise option and return more precise tokens\n # depending on it's value.\n #\n # [0]: https://github.com/pygments/pygments/issues/1986\n if precise_token is None or not lexer.options.get(\"precise\"):\n return parent_token\n else:\n return precise_token\n\n\n\nFile: httpie/output/lexers/http.py\n\nimport re\nimport pygments\nfrom httpie.output.lexers.common import precise\n\nRE_STATUS_LINE = re.compile(r'(\\d{3})( +)?(.+)?')\n\nSTATUS_TYPES = {\n '1': pygments.token.Number.HTTP.INFO,\n '2': pygments.token.Number.HTTP.OK,\n '3': pygments.token.Number.HTTP.REDIRECT,\n '4': pygments.token.Number.HTTP.CLIENT_ERR,\n '5': pygments.token.Number.HTTP.SERVER_ERR,\n}\n\nRESPONSE_TYPES = {\n 'GET': pygments.token.Name.Function.HTTP.GET,\n 'HEAD': pygments.token.Name.Function.HTTP.HEAD,\n 'POST': pygments.token.Name.Function.HTTP.POST,\n 'PUT': pygments.token.Name.Function.HTTP.PUT,\n 'PATCH': pygments.token.Name.Function.HTTP.PATCH,\n 'DELETE': pygments.token.Name.Function.HTTP.DELETE,\n}\n\n\ndef http_response_type(lexer, match, ctx):\n status_match = RE_STATUS_LINE.match(match.group())\n if status_match is None:\n return None\n\n status_code, text, reason = status_match.groups()\n status_type = precise(\n lexer,\n STATUS_TYPES.get(status_code[0]),\n pygments.token.Number\n )\n\n groups = pygments.lexer.bygroups(\n status_type,\n pygments.token.Text,\n status_type\n )\n yield from groups(lexer, status_match, ctx)\n\n\ndef request_method(lexer, match, ctx):\n response_type = precise(\n lexer,\n RESPONSE_TYPES.get(match.group()),\n pygments.token.Name.Function\n )\n yield match.start(), response_type, match.group()\n\n\nclass SimplifiedHTTPLexer(pygments.lexer.RegexLexer):\n \"\"\"Simplified HTTP lexer for Pygments.\n\n It only operates on headers and provides a stronger contrast between\n their names and values than the original one bundled with Pygments\n (:class:`pygments.lexers.text import HttpLexer`), especially when\n Solarized color scheme is used.\n\n \"\"\"\n name = 'HTTP'\n aliases = ['http']\n filenames = ['*.http']\n tokens = {\n 'root': [\n # Request-Line\n (r'([A-Z]+)( +)([^ ]+)( +)(HTTP)(/)(\\d+\\.\\d+)',\n pygments.lexer.bygroups(\n request_method,\n pygments.token.Text,\n pygments.token.Name.Namespace,\n pygments.token.Text,\n pygments.token.Keyword.Reserved,\n pygments.token.Operator,\n pygments.token.Number\n )),\n # Response Status-Line\n (r'(HTTP)(/)(\\d+\\.\\d+)( +)(.+)',\n pygments.lexer.bygroups(\n pygments.token.Keyword.Reserved, # 'HTTP'\n pygments.token.Operator, # '/'\n pygments.token.Number, # Version\n pygments.token.Text,\n http_response_type, # Status code and Reason\n )),\n # Header\n (r'(.*?)( *)(:)( *)(.+)', pygments.lexer.bygroups(\n pygments.token.Name.Attribute, # Name\n pygments.token.Text,\n pygments.token.Operator, # Colon\n pygments.token.Text,\n pygments.token.String # Value\n ))\n ]\n }\n\n\n\nFile: httpie/output/lexers/json.py\n\nimport re\n\nfrom pygments.lexer import bygroups, using, RegexLexer\nfrom pygments.lexers.data import JsonLexer\nfrom pygments.token import Token\n\nPREFIX_TOKEN = Token.Error\nPREFIX_REGEX = r'[^{\\[\"]+'\n\n\nclass EnhancedJsonLexer(RegexLexer):\n \"\"\"\n Enhanced JSON lexer for Pygments.\n\n It adds support for eventual data prefixing the actual JSON body.\n\n \"\"\"\n name = 'JSON'\n flags = re.IGNORECASE | re.DOTALL\n tokens = {\n 'root': [\n # Eventual non-JSON data prefix followed by actual JSON body.\n # FIX: data prefix + number (integer or float) is not correctly handled.\n (\n fr'({PREFIX_REGEX})' + r'((?:[{\\[\"]|true|false|null).+)',\n bygroups(PREFIX_TOKEN, using(JsonLexer))\n ),\n # JSON body.\n (r'.+', using(JsonLexer)),\n ],\n }\n\n\n\nFile: httpie/output/formatters/xml.py\n\nfrom typing import TYPE_CHECKING, Optional\n\nfrom ...encoding import UTF8\nfrom ...plugins import FormatterPlugin\n\nif TYPE_CHECKING:\n from xml.dom.minidom import Document\n\n\nXML_DECLARATION_OPEN = '<?xml'\nXML_DECLARATION_CLOSE = '?>'\n\n\ndef parse_xml(data: str) -> 'Document':\n \"\"\"Parse given XML `data` string into an appropriate :class:`~xml.dom.minidom.Document` object.\"\"\"\n from defusedxml.minidom import parseString\n return parseString(data)\n\n\ndef parse_declaration(raw_body: str) -> Optional[str]:\n body = raw_body.strip()\n # XMLDecl ::= '<?xml' DECL_CONTENT '?>'\n if body.startswith(XML_DECLARATION_OPEN):\n end = body.find(XML_DECLARATION_CLOSE)\n if end != -1:\n return body[:end + len(XML_DECLARATION_CLOSE)]\n\n\ndef pretty_xml(document: 'Document',\n declaration: Optional[str] = None,\n encoding: Optional[str] = UTF8,\n indent: int = 2) -> str:\n \"\"\"Render the given :class:`~xml.dom.minidom.Document` `document` into a prettified string.\"\"\"\n kwargs = {\n 'encoding': encoding or UTF8,\n 'indent': ' ' * indent,\n }\n body = document.toprettyxml(**kwargs).decode(kwargs['encoding'])\n\n # Remove blank lines automatically added by `toprettyxml()`.\n lines = [line for line in body.splitlines() if line.strip()]\n\n # xml.dom automatically adds the declaration, even if\n # it is not present in the actual body. Remove it.\n if len(lines) >= 1 and parse_declaration(lines[0]):\n lines.pop(0)\n if declaration:\n lines.insert(0, declaration)\n\n return '\\n'.join(lines)\n\n\nclass XMLFormatter(FormatterPlugin):\n\n def __init__(self, **kwargs):\n super().__init__(**kwargs)\n self.enabled = self.format_options['xml']['format']\n\n def format_body(self, body: str, mime: str):\n if 'xml' not in mime:\n return body\n\n from xml.parsers.expat import ExpatError\n from defusedxml.common import DefusedXmlException\n\n declaration = parse_declaration(body)\n try:\n parsed_body = parse_xml(body)\n except ExpatError:\n pass # Invalid XML, ignore.\n except DefusedXmlException:\n pass # Unsafe XML, ignore.\n else:\n body = pretty_xml(parsed_body,\n encoding=parsed_body.encoding,\n indent=self.format_options['xml']['indent'],\n declaration=declaration)\n\n return body\n\n\n\nFile: httpie/output/formatters/__init__.py\n\n\n\n\nFile: httpie/output/formatters/headers.py\n\nfrom ...plugins import FormatterPlugin\n\n\nclass HeadersFormatter(FormatterPlugin):\n\n def __init__(self, **kwargs):\n super().__init__(**kwargs)\n self.enabled = self.format_options['headers']['sort']\n\n def format_headers(self, headers: str) -> str:\n \"\"\"\n Sorts headers by name while retaining relative\n order of multiple headers with the same name.\n\n \"\"\"\n lines = headers.splitlines()\n headers = sorted(lines[1:], key=lambda h: h.split(':')[0])\n return '\\r\\n'.join(lines[:1] + headers)\n\n\n\nFile: httpie/output/formatters/json.py\n\nimport json\n\nfrom ...plugins import FormatterPlugin\n\n\nclass JSONFormatter(FormatterPlugin):\n\n def __init__(self, **kwargs):\n super().__init__(**kwargs)\n self.enabled = self.format_options['json']['format']\n\n def format_body(self, body: str, mime: str) -> str:\n maybe_json = [\n 'json',\n 'javascript',\n 'text',\n ]\n if (self.kwargs['explicit_json']\n or any(token in mime for token in maybe_json)):\n from ..utils import load_prefixed_json\n try:\n data_prefix, json_obj = load_prefixed_json(body)\n except ValueError:\n pass # Invalid JSON, ignore.\n else:\n # Indent, sort keys by name, and avoid\n # unicode escapes to improve readability.\n body = data_prefix + json.dumps(\n obj=json_obj,\n sort_keys=self.format_options['json']['sort_keys'],\n ensure_ascii=False,\n indent=self.format_options['json']['indent']\n )\n return body\n\n\n\nFile: httpie/output/formatters/colors.py\n\nimport json\nfrom typing import Optional, Type, Tuple\n\nimport pygments.formatters\nimport pygments.lexer\nimport pygments.lexers\nimport pygments.style\nimport pygments.styles\nimport pygments.token\nfrom pygments.formatters.terminal import TerminalFormatter\nfrom pygments.formatters.terminal256 import Terminal256Formatter\nfrom pygments.lexer import Lexer\nfrom pygments.lexers.data import JsonLexer\nfrom pygments.lexers.special import TextLexer\nfrom pygments.lexers.text import HttpLexer as PygmentsHttpLexer\nfrom pygments.util import ClassNotFound\n\nfrom ..lexers.json import EnhancedJsonLexer\nfrom ..lexers.metadata import MetadataLexer\nfrom ..ui.palette import AUTO_STYLE, SHADE_TO_PIE_STYLE, PieColor, ColorString, get_color\nfrom ...context import Environment\nfrom ...plugins import FormatterPlugin\n\n\nDEFAULT_STYLE = AUTO_STYLE\nSOLARIZED_STYLE = 'solarized' # Bundled here\nPYGMENTS_BOLD = ColorString('bold')\nPYGMENTS_ITALIC = ColorString('italic')\n\nBUNDLED_STYLES = {\n SOLARIZED_STYLE,\n AUTO_STYLE\n}\n\n\ndef get_available_styles():\n return sorted(BUNDLED_STYLES | set(pygments.styles.get_all_styles()))\n\n\nclass ColorFormatter(FormatterPlugin):\n \"\"\"\n Colorize using Pygments\n\n This processor that applies syntax highlighting to the headers,\n and also to the body if its content type is recognized.\n\n \"\"\"\n group_name = 'colors'\n metadata_lexer = MetadataLexer()\n\n def __init__(\n self,\n env: Environment,\n explicit_json=False,\n color_scheme=DEFAULT_STYLE,\n **kwargs\n ):\n super().__init__(**kwargs)\n\n if not env.colors:\n self.enabled = False\n return\n\n use_auto_style = color_scheme == AUTO_STYLE\n has_256_colors = env.colors == 256\n if use_auto_style or not has_256_colors:\n http_lexer = PygmentsHttpLexer()\n body_formatter = header_formatter = TerminalFormatter()\n precise = False\n else:\n from ..lexers.http import SimplifiedHTTPLexer\n header_formatter, body_formatter, precise = self.get_formatters(color_scheme)\n http_lexer = SimplifiedHTTPLexer(precise=precise)\n\n self.explicit_json = explicit_json # --json\n self.header_formatter = header_formatter\n self.body_formatter = body_formatter\n self.http_lexer = http_lexer\n self.metadata_lexer = MetadataLexer(precise=precise)\n\n def format_headers(self, headers: str) -> str:\n return pygments.highlight(\n code=headers,\n lexer=self.http_lexer,\n formatter=self.header_formatter,\n ).strip()\n\n def format_body(self, body: str, mime: str) -> str:\n lexer = self.get_lexer_for_body(mime, body)\n if lexer:\n body = pygments.highlight(\n code=body,\n lexer=lexer,\n formatter=self.body_formatter,\n )\n return body\n\n def format_metadata(self, metadata: str) -> str:\n return pygments.highlight(\n code=metadata,\n lexer=self.metadata_lexer,\n formatter=self.header_formatter,\n ).strip()\n\n def get_lexer_for_body(\n self, mime: str,\n body: str\n ) -> Optional[Type[Lexer]]:\n return get_lexer(\n mime=mime,\n explicit_json=self.explicit_json,\n body=body,\n )\n\n def get_formatters(self, color_scheme: str) -> Tuple[\n pygments.formatter.Formatter,\n pygments.formatter.Formatter,\n bool\n ]:\n if color_scheme in PIE_STYLES:\n header_style, body_style = PIE_STYLES[color_scheme]\n precise = True\n else:\n header_style = self.get_style_class(color_scheme)\n body_style = header_style\n precise = False\n\n return (\n Terminal256Formatter(style=header_style),\n Terminal256Formatter(style=body_style),\n precise\n )\n\n @staticmethod\n def get_style_class(color_scheme: str) -> Type[pygments.style.Style]:\n try:\n return pygments.styles.get_style_by_name(color_scheme)\n except ClassNotFound:\n return Solarized256Style\n\n\ndef get_lexer(\n mime: str,\n explicit_json=False,\n body=''\n) -> Optional[Type[Lexer]]:\n # Build candidate mime type and lexer names.\n mime_types, lexer_names = [mime], []\n type_, subtype = mime.split('/', 1)\n if '+' not in subtype:\n lexer_names.append(subtype)\n else:\n subtype_name, subtype_suffix = subtype.split('+', 1)\n lexer_names.extend([subtype_name, subtype_suffix])\n mime_types.extend([\n f'{type_}/{subtype_name}',\n f'{type_}/{subtype_suffix}',\n ])\n\n # As a last resort, if no lexer feels responsible, and\n # the subtype contains 'json', take the JSON lexer\n if 'json' in subtype:\n lexer_names.append('json')\n\n # Try to resolve the right lexer.\n lexer = None\n for mime_type in mime_types:\n try:\n lexer = pygments.lexers.get_lexer_for_mimetype(mime_type)\n break\n except ClassNotFound:\n pass\n else:\n for name in lexer_names:\n try:\n lexer = pygments.lexers.get_lexer_by_name(name)\n except ClassNotFound:\n pass\n\n if explicit_json and body and (not lexer or isinstance(lexer, TextLexer)):\n # JSON response with an incorrect Content-Type?\n try:\n json.loads(body) # FIXME: the body also gets parsed in json.py\n except ValueError:\n pass # Nope\n else:\n lexer = pygments.lexers.get_lexer_by_name('json')\n\n # Use our own JSON lexer: it supports JSON bodies preceded by non-JSON data\n # as well as legit JSON bodies.\n if isinstance(lexer, JsonLexer):\n lexer = EnhancedJsonLexer()\n\n return lexer\n\n\nclass Solarized256Style(pygments.style.Style):\n \"\"\"\n solarized256\n ------------\n\n A Pygments style inspired by Solarized's 256 color mode.\n\n :copyright: (c) 2011 by Hank Gay, (c) 2012 by John Mastro.\n :license: BSD, see LICENSE for more details.\n\n \"\"\"\n BASE03 = \"#1c1c1c\"\n BASE02 = \"#262626\"\n BASE01 = \"#4e4e4e\"\n BASE00 = \"#585858\"\n BASE0 = \"#808080\"\n BASE1 = \"#8a8a8a\"\n BASE2 = \"#d7d7af\"\n BASE3 = \"#ffffd7\"\n YELLOW = \"#af8700\"\n ORANGE = \"#d75f00\"\n RED = \"#af0000\"\n MAGENTA = \"#af005f\"\n VIOLET = \"#5f5faf\"\n BLUE = \"#0087ff\"\n CYAN = \"#00afaf\"\n GREEN = \"#5f8700\"\n\n background_color = BASE03\n styles = {\n pygments.token.Keyword: GREEN,\n pygments.token.Keyword.Constant: ORANGE,\n pygments.token.Keyword.Declaration: BLUE,\n pygments.token.Keyword.Namespace: ORANGE,\n pygments.token.Keyword.Reserved: BLUE,\n pygments.token.Keyword.Type: RED,\n pygments.token.Name.Attribute: BASE1,\n pygments.token.Name.Builtin: BLUE,\n pygments.token.Name.Builtin.Pseudo: BLUE,\n pygments.token.Name.Class: BLUE,\n pygments.token.Name.Constant: ORANGE,\n pygments.token.Name.Decorator: BLUE,\n pygments.token.Name.Entity: ORANGE,\n pygments.token.Name.Exception: YELLOW,\n pygments.token.Name.Function: BLUE,\n pygments.token.Name.Tag: BLUE,\n pygments.token.Name.Variable: BLUE,\n pygments.token.String: CYAN,\n pygments.token.String.Backtick: BASE01,\n pygments.token.String.Char: CYAN,\n pygments.token.String.Doc: CYAN,\n pygments.token.String.Escape: RED,\n pygments.token.String.Heredoc: CYAN,\n pygments.token.String.Regex: RED,\n pygments.token.Number: CYAN,\n pygments.token.Operator: BASE1,\n pygments.token.Operator.Word: GREEN,\n pygments.token.Comment: BASE01,\n pygments.token.Comment.Preproc: GREEN,\n pygments.token.Comment.Special: GREEN,\n pygments.token.Generic.Deleted: CYAN,\n pygments.token.Generic.Emph: PYGMENTS_ITALIC,\n pygments.token.Generic.Error: RED,\n pygments.token.Generic.Heading: ORANGE,\n pygments.token.Generic.Inserted: GREEN,\n pygments.token.Generic.Strong: PYGMENTS_BOLD,\n pygments.token.Generic.Subheading: ORANGE,\n pygments.token.Token: BASE1,\n pygments.token.Token.Other: ORANGE,\n }\n\n\nPIE_HEADER_STYLE = {\n # HTTP line / Headers / Etc.\n pygments.token.Name.Namespace: PYGMENTS_BOLD | PieColor.PRIMARY,\n pygments.token.Keyword.Reserved: PYGMENTS_BOLD | PieColor.GREY,\n pygments.token.Operator: PYGMENTS_BOLD | PieColor.GREY,\n pygments.token.Number: PYGMENTS_BOLD | PieColor.GREY,\n pygments.token.Name.Function.Magic: PYGMENTS_BOLD | PieColor.GREEN,\n pygments.token.Name.Exception: PYGMENTS_BOLD | PieColor.GREEN,\n pygments.token.Name.Attribute: PieColor.BLUE,\n pygments.token.String: PieColor.PRIMARY,\n\n # HTTP Methods\n pygments.token.Name.Function: PYGMENTS_BOLD | PieColor.GREY,\n pygments.token.Name.Function.HTTP.GET: PYGMENTS_BOLD | PieColor.GREEN,\n pygments.token.Name.Function.HTTP.HEAD: PYGMENTS_BOLD | PieColor.GREEN,\n pygments.token.Name.Function.HTTP.POST: PYGMENTS_BOLD | PieColor.YELLOW,\n pygments.token.Name.Function.HTTP.PUT: PYGMENTS_BOLD | PieColor.ORANGE,\n pygments.token.Name.Function.HTTP.PATCH: PYGMENTS_BOLD | PieColor.ORANGE,\n pygments.token.Name.Function.HTTP.DELETE: PYGMENTS_BOLD | PieColor.RED,\n\n # HTTP status codes\n pygments.token.Number.HTTP.INFO: PYGMENTS_BOLD | PieColor.AQUA,\n pygments.token.Number.HTTP.OK: PYGMENTS_BOLD | PieColor.GREEN,\n pygments.token.Number.HTTP.REDIRECT: PYGMENTS_BOLD | PieColor.YELLOW,\n pygments.token.Number.HTTP.CLIENT_ERR: PYGMENTS_BOLD | PieColor.ORANGE,\n pygments.token.Number.HTTP.SERVER_ERR: PYGMENTS_BOLD | PieColor.RED,\n\n # Metadata\n pygments.token.Name.Decorator: PieColor.GREY,\n pygments.token.Number.SPEED.FAST: PYGMENTS_BOLD | PieColor.GREEN,\n pygments.token.Number.SPEED.AVG: PYGMENTS_BOLD | PieColor.YELLOW,\n pygments.token.Number.SPEED.SLOW: PYGMENTS_BOLD | PieColor.ORANGE,\n pygments.token.Number.SPEED.VERY_SLOW: PYGMENTS_BOLD | PieColor.RED,\n}\n\nPIE_BODY_STYLE = {\n # {}[]:\n pygments.token.Punctuation: PieColor.GREY,\n\n # Keys\n pygments.token.Name.Tag: PieColor.PINK,\n\n # Values\n pygments.token.Literal.String: PieColor.GREEN,\n pygments.token.Literal.String.Double: PieColor.GREEN,\n pygments.token.Literal.Number: PieColor.AQUA,\n pygments.token.Keyword: PieColor.ORANGE,\n\n # Other stuff\n pygments.token.Text: PieColor.PRIMARY,\n pygments.token.Name.Attribute: PieColor.PRIMARY,\n pygments.token.Name.Builtin: PieColor.BLUE,\n pygments.token.Name.Builtin.Pseudo: PieColor.BLUE,\n pygments.token.Name.Class: PieColor.BLUE,\n pygments.token.Name.Constant: PieColor.ORANGE,\n pygments.token.Name.Decorator: PieColor.BLUE,\n pygments.token.Name.Entity: PieColor.ORANGE,\n pygments.token.Name.Exception: PieColor.YELLOW,\n pygments.token.Name.Function: PieColor.BLUE,\n pygments.token.Name.Variable: PieColor.BLUE,\n pygments.token.String: PieColor.AQUA,\n pygments.token.String.Backtick: PieColor.SECONDARY,\n pygments.token.String.Char: PieColor.AQUA,\n pygments.token.String.Doc: PieColor.AQUA,\n pygments.token.String.Escape: PieColor.RED,\n pygments.token.String.Heredoc: PieColor.AQUA,\n pygments.token.String.Regex: PieColor.RED,\n pygments.token.Number: PieColor.AQUA,\n pygments.token.Operator: PieColor.PRIMARY,\n pygments.token.Operator.Word: PieColor.GREEN,\n pygments.token.Comment: PieColor.SECONDARY,\n pygments.token.Comment.Preproc: PieColor.GREEN,\n pygments.token.Comment.Special: PieColor.GREEN,\n pygments.token.Generic.Deleted: PieColor.AQUA,\n pygments.token.Generic.Emph: PYGMENTS_ITALIC,\n pygments.token.Generic.Error: PieColor.RED,\n pygments.token.Generic.Heading: PieColor.ORANGE,\n pygments.token.Generic.Inserted: PieColor.GREEN,\n pygments.token.Generic.Strong: PYGMENTS_BOLD,\n pygments.token.Generic.Subheading: PieColor.ORANGE,\n pygments.token.Token: PieColor.PRIMARY,\n pygments.token.Token.Other: PieColor.ORANGE,\n}\n\n\ndef make_style(name, raw_styles, shade):\n def format_value(value):\n return ' '.join(\n get_color(part, shade) or part\n for part in value.split()\n )\n\n bases = (pygments.style.Style,)\n data = {\n 'styles': {\n key: format_value(value)\n for key, value in raw_styles.items()\n }\n }\n return type(name, bases, data)\n\n\ndef make_styles():\n styles = {}\n\n for shade, name in SHADE_TO_PIE_STYLE.items():\n styles[name] = [\n make_style(name, style_map, shade)\n for style_name, style_map in [\n (f'Pie{name}HeaderStyle', PIE_HEADER_STYLE),\n (f'Pie{name}BodyStyle', PIE_BODY_STYLE),\n ]\n ]\n\n return styles\n\n\nPIE_STYLES = make_styles()\nPIE_STYLE_NAMES = list(PIE_STYLES.keys())\nBUNDLED_STYLES |= PIE_STYLES.keys()\n\n\n\nFile: httpie/legacy/v3_2_0_session_header_format.py\n\nfrom typing import Any, Type, List, Dict, TYPE_CHECKING\n\nif TYPE_CHECKING:\n from httpie.sessions import Session\n\n\nOLD_HEADER_STORE_WARNING = '''\\\nOutdated layout detected for the current session. Please consider updating it,\nin order to use the latest features regarding the header layout.\n\nFor fixing the current session:\n\n $ httpie cli sessions upgrade {hostname} {session_id}\n'''\n\nOLD_HEADER_STORE_WARNING_FOR_NAMED_SESSIONS = '''\\\n\nFor fixing all named sessions:\n\n $ httpie cli sessions upgrade-all\n'''\n\nOLD_HEADER_STORE_LINK = '\\nSee $INSERT_LINK for more information.'\n\n\ndef pre_process(session: 'Session', headers: Any) -> List[Dict[str, Any]]:\n \"\"\"Serialize the headers into a unified form and issue a warning if\n the session file is using the old layout.\"\"\"\n\n is_old_style = isinstance(headers, dict)\n if is_old_style:\n normalized_headers = list(headers.items())\n else:\n normalized_headers = [\n (item['name'], item['value'])\n for item in headers\n ]\n\n if is_old_style:\n warning = OLD_HEADER_STORE_WARNING.format(hostname=session.bound_host, session_id=session.session_id)\n if not session.is_anonymous:\n warning += OLD_HEADER_STORE_WARNING_FOR_NAMED_SESSIONS\n warning += OLD_HEADER_STORE_LINK\n session.warn_legacy_usage(warning)\n\n return normalized_headers\n\n\ndef post_process(\n normalized_headers: List[Dict[str, Any]],\n *,\n original_type: Type[Any]\n) -> Any:\n \"\"\"Deserialize given header store into the original form it was\n used in.\"\"\"\n\n if issubclass(original_type, dict):\n # For the legacy behavior, preserve the last value.\n return {\n item['name']: item['value']\n for item in normalized_headers\n }\n else:\n return normalized_headers\n\n\ndef fix_layout(session: 'Session', *args, **kwargs) -> None:\n from httpie.sessions import materialize_headers\n\n if not isinstance(session['headers'], dict):\n return None\n\n session['headers'] = materialize_headers(session['headers'])\n\n\n\nFile: httpie/legacy/v3_1_0_session_cookie_format.py\n\nimport argparse\nfrom typing import Any, Type, List, Dict, TYPE_CHECKING\n\nif TYPE_CHECKING:\n from httpie.sessions import Session\n\n\nINSECURE_COOKIE_JAR_WARNING = '''\\\nOutdated layout detected for the current session. Please consider updating it,\nin order to not get affected by potential security problems.\n\nFor fixing the current session:\n\n With binding all cookies to the current host (secure):\n $ httpie cli sessions upgrade --bind-cookies {hostname} {session_id}\n\n Without binding cookies (leaving them as is) (insecure):\n $ httpie cli sessions upgrade {hostname} {session_id}\n'''\n\n\nINSECURE_COOKIE_JAR_WARNING_FOR_NAMED_SESSIONS = '''\\\n\nFor fixing all named sessions:\n\n With binding all cookies to the current host (secure):\n $ httpie cli sessions upgrade-all --bind-cookies\n\n Without binding cookies (leaving them as is) (insecure):\n $ httpie cli sessions upgrade-all\n'''\n\nINSECURE_COOKIE_SECURITY_LINK = '\\nSee https://pie.co/docs/security for more information.'\n\n\ndef pre_process(session: 'Session', cookies: Any) -> List[Dict[str, Any]]:\n \"\"\"Load the given cookies to the cookie jar while maintaining\n support for the old cookie layout.\"\"\"\n\n is_old_style = isinstance(cookies, dict)\n if is_old_style:\n normalized_cookies = [\n {\n 'name': key,\n **value\n }\n for key, value in cookies.items()\n ]\n else:\n normalized_cookies = cookies\n\n should_issue_warning = is_old_style and any(\n cookie.get('domain', '') == ''\n for cookie in normalized_cookies\n )\n\n if should_issue_warning:\n warning = INSECURE_COOKIE_JAR_WARNING.format(hostname=session.bound_host, session_id=session.session_id)\n if not session.is_anonymous:\n warning += INSECURE_COOKIE_JAR_WARNING_FOR_NAMED_SESSIONS\n warning += INSECURE_COOKIE_SECURITY_LINK\n session.warn_legacy_usage(warning)\n\n return normalized_cookies\n\n\ndef post_process(\n normalized_cookies: List[Dict[str, Any]],\n *,\n original_type: Type[Any]\n) -> Any:\n \"\"\"Convert the cookies to their original format for\n maximum compatibility.\"\"\"\n\n if issubclass(original_type, dict):\n return {\n cookie.pop('name'): cookie\n for cookie in normalized_cookies\n }\n else:\n return normalized_cookies\n\n\ndef fix_layout(session: 'Session', hostname: str, args: argparse.Namespace) -> None:\n if not isinstance(session['cookies'], dict):\n return None\n\n session['cookies'] = [\n {\n 'name': key,\n **value\n }\n for key, value in session['cookies'].items()\n ]\n for cookie in session.cookies:\n if cookie.domain == '':\n if args.bind_cookies:\n cookie.domain = hostname\n else:\n cookie._rest['is_explicit_none'] = True\n\n\n\nFile: httpie/legacy/__init__.py\n\n\n\n\nFile: httpie/cli/argtypes.py\n\nimport argparse\nimport getpass\nimport os\nimport sys\nfrom copy import deepcopy\nfrom typing import List, Optional, Union\n\nfrom .constants import DEFAULT_FORMAT_OPTIONS, SEPARATOR_CREDENTIALS\nfrom ..sessions import VALID_SESSION_NAME_PATTERN\n\n\nclass KeyValueArg:\n \"\"\"Base key-value pair parsed from CLI.\"\"\"\n\n def __init__(self, key: str, value: Optional[str], sep: str, orig: str):\n self.key = key\n self.value = value\n self.sep = sep\n self.orig = orig\n\n def __eq__(self, other: 'KeyValueArg'):\n return self.__dict__ == other.__dict__\n\n def __repr__(self):\n return repr(self.__dict__)\n\n\nclass SessionNameValidator:\n\n def __init__(self, error_message: str):\n self.error_message = error_message\n\n def __call__(self, value: str) -> str:\n # Session name can be a path or just a name.\n if (os.path.sep not in value\n and not VALID_SESSION_NAME_PATTERN.search(value)):\n raise argparse.ArgumentError(None, self.error_message)\n return value\n\n\nclass Escaped(str):\n \"\"\"Represents an escaped character.\"\"\"\n\n def __repr__(self):\n return f\"Escaped({repr(str(self))})\"\n\n\nclass KeyValueArgType:\n \"\"\"A key-value pair argument type used with `argparse`.\n\n Parses a key-value arg and constructs a `KeyValueArg` instance.\n Used for headers, form data, and other key-value pair types.\n\n \"\"\"\n\n key_value_class = KeyValueArg\n\n def __init__(self, *separators: str):\n self.separators = separators\n self.special_characters = set()\n for separator in separators:\n self.special_characters.update(separator)\n\n def __call__(self, s: str) -> KeyValueArg:\n \"\"\"Parse raw string arg and return `self.key_value_class` instance.\n\n The best of `self.separators` is determined (first found, longest).\n Back slash escaped characters aren't considered as separators\n (or parts thereof). Literal back slash characters have to be escaped\n as well (r'\\\\').\n\n \"\"\"\n tokens = self.tokenize(s)\n\n # Sorting by length ensures that the longest one will be\n # chosen as it will overwrite any shorter ones starting\n # at the same position in the `found` dictionary.\n separators = sorted(self.separators, key=len)\n\n for i, token in enumerate(tokens):\n\n if isinstance(token, Escaped):\n continue\n\n found = {}\n for sep in separators:\n pos = token.find(sep)\n if pos != -1:\n found[pos] = sep\n\n if found:\n # Starting first, longest separator found.\n sep = found[min(found.keys())]\n\n key, value = token.split(sep, 1)\n\n # Any preceding tokens are part of the key.\n key = ''.join(tokens[:i]) + key\n\n # Any following tokens are part of the value.\n value += ''.join(tokens[i + 1:])\n\n break\n\n else:\n raise argparse.ArgumentTypeError(f'{s!r} is not a valid value')\n\n return self.key_value_class(key=key, value=value, sep=sep, orig=s)\n\n def tokenize(self, s: str) -> List[Union[str, Escaped]]:\n r\"\"\"Tokenize the raw arg string\n\n There are only two token types - strings and escaped characters:\n\n >>> KeyValueArgType('=').tokenize(r'foo\\=bar\\\\baz')\n ['foo', Escaped('='), 'bar\\\\\\\\baz']\n\n \"\"\"\n tokens = ['']\n characters = iter(s)\n for char in characters:\n if char == '\\\\':\n char = next(characters, '')\n if char not in self.special_characters:\n tokens[-1] += '\\\\' + char\n else:\n tokens.extend([Escaped(char), ''])\n else:\n tokens[-1] += char\n return tokens\n\n\nclass PromptMixin:\n def _prompt_password(self, prompt: str) -> str:\n prompt_text = f'http: {prompt}: '\n try:\n return self._getpass(prompt_text)\n except (EOFError, KeyboardInterrupt):\n sys.stderr.write('\\n')\n sys.exit(0)\n\n @staticmethod\n def _getpass(prompt):\n # To allow easy mocking.\n return getpass.getpass(str(prompt))\n\n\nclass SSLCredentials(PromptMixin):\n \"\"\"Represents the passphrase for the certificate's key.\"\"\"\n\n def __init__(self, value: Optional[str]) -> None:\n self.value = value\n\n def prompt_password(self, key_file: str) -> None:\n self.value = self._prompt_password(f'passphrase for {key_file}')\n\n\nclass AuthCredentials(KeyValueArg, PromptMixin):\n \"\"\"Represents parsed credentials.\"\"\"\n\n def has_password(self) -> bool:\n return self.value is not None\n\n def prompt_password(self, host: str) -> None:\n self.value = self._prompt_password(f'password for {self.key}@{host}:')\n\n\nclass AuthCredentialsArgType(KeyValueArgType):\n \"\"\"A key-value arg type that parses credentials.\"\"\"\n\n key_value_class = AuthCredentials\n\n def __call__(self, s):\n \"\"\"Parse credentials from `s`.\n\n (\"username\" or \"username:password\").\n\n \"\"\"\n try:\n return super().__call__(s)\n except argparse.ArgumentTypeError:\n # No password provided, will prompt for it later.\n return self.key_value_class(\n key=s,\n value=None,\n sep=SEPARATOR_CREDENTIALS,\n orig=s\n )\n\n\nparse_auth = AuthCredentialsArgType(SEPARATOR_CREDENTIALS)\n\n\ndef readable_file_arg(filename):\n try:\n with open(filename, 'rb'):\n return filename\n except OSError as ex:\n raise argparse.ArgumentTypeError(f'{ex.filename}: {ex.strerror}')\n\n\ndef parse_format_options(s: str, defaults: Optional[dict]) -> dict:\n \"\"\"\n Parse `s` and update `defaults` with the parsed values.\n\n >>> parse_format_options(\n ... defaults={'json': {'indent': 4, 'sort_keys': True}},\n ... s='json.indent:2,json.sort_keys:False',\n ... )\n {'json': {'indent': 2, 'sort_keys': False}}\n\n \"\"\"\n value_map = {\n 'true': True,\n 'false': False,\n }\n options = deepcopy(defaults or {})\n for option in s.split(','):\n try:\n path, value = option.lower().split(':')\n section, key = path.split('.')\n except ValueError:\n raise argparse.ArgumentTypeError(f'invalid option {option!r}')\n\n if value in value_map:\n parsed_value = value_map[value]\n else:\n if value.isnumeric():\n parsed_value = int(value)\n else:\n parsed_value = value\n\n if defaults is None:\n options.setdefault(section, {})\n else:\n try:\n default_value = defaults[section][key]\n except KeyError:\n raise argparse.ArgumentTypeError(\n f'invalid key {path!r}')\n\n default_type, parsed_type = type(default_value), type(parsed_value)\n if parsed_type is not default_type:\n raise argparse.ArgumentTypeError(\n 'invalid value'\n f' {value!r} in {option!r}'\n f' (expected {default_type.__name__}'\n f' got {parsed_type.__name__})'\n )\n\n options[section][key] = parsed_value\n\n return options\n\n\nPARSED_DEFAULT_FORMAT_OPTIONS = parse_format_options(\n s=','.join(DEFAULT_FORMAT_OPTIONS),\n defaults=None,\n)\n\n\ndef response_charset_type(encoding: str) -> str:\n try:\n ''.encode(encoding)\n except LookupError:\n raise argparse.ArgumentTypeError(\n f'{encoding!r} is not a supported encoding')\n return encoding\n\n\ndef response_mime_type(mime_type: str) -> str:\n if mime_type.count('/') != 1:\n raise argparse.ArgumentTypeError(\n f'{mime_type!r} doesn’t look like a mime type; use type/subtype')\n return mime_type\n\n\n\nFile: httpie/cli/options.py\n\nimport argparse\nimport textwrap\nimport typing\nfrom dataclasses import dataclass, field\nfrom enum import Enum, auto\nfrom typing import Any, Optional, Dict, List, Tuple, Type, TypeVar\n\nfrom httpie.cli.argparser import HTTPieArgumentParser\nfrom httpie.cli.utils import Manual, LazyChoices\n\n\nclass Qualifiers(Enum):\n OPTIONAL = auto()\n ZERO_OR_MORE = auto()\n ONE_OR_MORE = auto()\n SUPPRESS = auto()\n\n\ndef map_qualifiers(\n configuration: Dict[str, Any], qualifier_map: Dict[Qualifiers, Any]\n) -> Dict[str, Any]:\n return {\n key: qualifier_map[value] if isinstance(value, Qualifiers) else value\n for key, value in configuration.items()\n }\n\n\ndef drop_keys(\n configuration: Dict[str, Any], key_blacklist: Tuple[str, ...]\n):\n return {\n key: value\n for key, value in configuration.items()\n if key not in key_blacklist\n }\n\n\nPARSER_SPEC_VERSION = '0.0.1a0'\n\n\n@dataclass\nclass ParserSpec:\n program: str\n description: Optional[str] = None\n epilog: Optional[str] = None\n groups: List['Group'] = field(default_factory=list)\n man_page_hint: Optional[str] = None\n source_file: Optional[str] = None\n\n def finalize(self) -> 'ParserSpec':\n if self.description:\n self.description = textwrap.dedent(self.description)\n if self.epilog:\n self.epilog = textwrap.dedent(self.epilog)\n for group in self.groups:\n group.finalize()\n return self\n\n def add_group(self, name: str, **kwargs) -> 'Group':\n group = Group(name, **kwargs)\n self.groups.append(group)\n return group\n\n def serialize(self) -> Dict[str, Any]:\n return {\n 'name': self.program,\n 'description': self.description,\n 'groups': [group.serialize() for group in self.groups],\n }\n\n\n@dataclass\nclass Group:\n name: str\n description: str = ''\n is_mutually_exclusive: bool = False\n arguments: List['Argument'] = field(default_factory=list)\n\n def finalize(self) -> None:\n if self.description:\n self.description = textwrap.dedent(self.description)\n\n def add_argument(self, *args, **kwargs):\n argument = Argument(list(args), kwargs.copy())\n argument.post_init()\n self.arguments.append(argument)\n return argument\n\n def serialize(self) -> Dict[str, Any]:\n return {\n 'name': self.name,\n 'description': self.description or None,\n 'is_mutually_exclusive': self.is_mutually_exclusive,\n 'args': [argument.serialize() for argument in self.arguments],\n }\n\n\nclass Argument(typing.NamedTuple):\n aliases: List[str]\n configuration: Dict[str, Any]\n\n def post_init(self):\n \"\"\"Run a bunch of post-init hooks.\"\"\"\n # If there is a short help, then create the longer version from it.\n short_help = self.configuration.get('short_help')\n if (\n short_help\n and 'help' not in self.configuration\n and self.configuration.get('action') != 'lazy_choices'\n ):\n self.configuration['help'] = f'\\n{short_help}\\n\\n'\n\n def serialize(self, *, isolation_mode: bool = False) -> Dict[str, Any]:\n configuration = self.configuration.copy()\n\n # Unpack the dynamically computed choices, since we\n # will need to store the actual values somewhere.\n action = configuration.pop('action', None)\n short_help = configuration.pop('short_help', None)\n nested_options = configuration.pop('nested_options', None)\n\n if action == 'lazy_choices':\n choices = LazyChoices(\n self.aliases,\n **{'dest': None, **configuration},\n isolation_mode=isolation_mode\n )\n configuration['choices'] = list(choices.load())\n configuration['help'] = choices.help\n\n result = {}\n if self.aliases:\n result['options'] = self.aliases.copy()\n else:\n result['options'] = [configuration['metavar']]\n result['is_positional'] = True\n\n qualifiers = JSON_QUALIFIER_TO_OPTIONS[configuration.get('nargs', Qualifiers.SUPPRESS)]\n result.update(qualifiers)\n\n description = configuration.get('help')\n if description and description is not Qualifiers.SUPPRESS:\n result['short_description'] = short_help\n result['description'] = description\n\n if nested_options:\n result['nested_options'] = nested_options\n\n python_type = configuration.get('type')\n if python_type is not None:\n if hasattr(python_type, '__name__'):\n type_name = python_type.__name__\n else:\n type_name = type(python_type).__name__\n\n result['python_type_name'] = type_name\n\n result.update({\n key: value\n for key, value in configuration.items()\n if key in JSON_DIRECT_MIRROR_OPTIONS\n if value is not Qualifiers.SUPPRESS\n })\n\n return result\n\n @property\n def is_positional(self):\n return len(self.aliases) == 0\n\n @property\n def is_hidden(self):\n return self.configuration.get('help') is Qualifiers.SUPPRESS\n\n def __getattr__(self, attribute_name):\n if attribute_name in self.configuration:\n return self.configuration[attribute_name]\n else:\n raise AttributeError(attribute_name)\n\n\nParserType = TypeVar('ParserType', bound=Type[argparse.ArgumentParser])\n\nARGPARSE_QUALIFIER_MAP = {\n Qualifiers.OPTIONAL: argparse.OPTIONAL,\n Qualifiers.SUPPRESS: argparse.SUPPRESS,\n Qualifiers.ZERO_OR_MORE: argparse.ZERO_OR_MORE,\n Qualifiers.ONE_OR_MORE: argparse.ONE_OR_MORE\n}\nARGPARSE_IGNORE_KEYS = ('short_help', 'nested_options')\n\n\ndef to_argparse(\n abstract_options: ParserSpec,\n parser_type: ParserType = HTTPieArgumentParser,\n) -> ParserType:\n concrete_parser = parser_type(\n prog=abstract_options.program,\n description=abstract_options.description,\n epilog=abstract_options.epilog,\n )\n concrete_parser.spec = abstract_options\n concrete_parser.register('action', 'lazy_choices', LazyChoices)\n concrete_parser.register('action', 'manual', Manual)\n\n for abstract_group in abstract_options.groups:\n concrete_group = concrete_parser.add_argument_group(\n title=abstract_group.name, description=abstract_group.description\n )\n if abstract_group.is_mutually_exclusive:\n concrete_group = concrete_group.add_mutually_exclusive_group(required=False)\n\n for abstract_argument in abstract_group.arguments:\n concrete_group.add_argument(\n *abstract_argument.aliases,\n **drop_keys(map_qualifiers(\n abstract_argument.configuration, ARGPARSE_QUALIFIER_MAP\n ), ARGPARSE_IGNORE_KEYS)\n )\n\n return concrete_parser\n\n\nJSON_DIRECT_MIRROR_OPTIONS = (\n 'choices',\n 'metavar'\n)\n\n\nJSON_QUALIFIER_TO_OPTIONS = {\n Qualifiers.OPTIONAL: {'is_optional': True},\n Qualifiers.ZERO_OR_MORE: {'is_optional': True, 'is_variadic': True},\n Qualifiers.ONE_OR_MORE: {'is_optional': False, 'is_variadic': True},\n Qualifiers.SUPPRESS: {}\n}\n\n\ndef to_data(abstract_options: ParserSpec) -> Dict[str, Any]:\n return {'version': PARSER_SPEC_VERSION, 'spec': abstract_options.serialize()}\n\n\ndef parser_to_parser_spec(parser: argparse.ArgumentParser, **kwargs) -> ParserSpec:\n \"\"\"Take an existing argparse parser, and create a spec from it.\"\"\"\n return ParserSpec(\n program=parser.prog,\n description=parser.description,\n epilog=parser.epilog,\n **kwargs\n )\n\n\n\nFile: httpie/cli/requestitems.py\n\nimport os\nimport functools\nfrom typing import Callable, Dict, IO, List, Optional, Tuple, Union\n\nfrom .argtypes import KeyValueArg\nfrom .constants import (\n SEPARATORS_GROUP_MULTIPART, SEPARATOR_DATA_EMBED_FILE_CONTENTS,\n SEPARATOR_DATA_EMBED_RAW_JSON_FILE, SEPARATOR_GROUP_NESTED_JSON_ITEMS,\n SEPARATOR_DATA_RAW_JSON, SEPARATOR_DATA_STRING, SEPARATOR_FILE_UPLOAD,\n SEPARATOR_FILE_UPLOAD_TYPE, SEPARATOR_HEADER, SEPARATOR_HEADER_EMPTY,\n SEPARATOR_HEADER_EMBED, SEPARATOR_QUERY_PARAM,\n SEPARATOR_QUERY_EMBED_FILE, RequestType\n)\nfrom .dicts import (\n BaseMultiDict, MultipartRequestDataDict, RequestDataDict,\n RequestFilesDict, HTTPHeadersDict, RequestJSONDataDict,\n RequestQueryParamsDict,\n)\nfrom .exceptions import ParseError\nfrom .nested_json import interpret_nested_json\nfrom ..utils import get_content_type, load_json_preserve_order_and_dupe_keys, split_iterable\n\n\nclass RequestItems:\n\n def __init__(self, request_type: Optional[RequestType] = None):\n self.headers = HTTPHeadersDict()\n self.request_type = request_type\n self.is_json = request_type is None or request_type is RequestType.JSON\n self.data = RequestJSONDataDict() if self.is_json else RequestDataDict()\n self.files = RequestFilesDict()\n self.params = RequestQueryParamsDict()\n # To preserve the order of fields in file upload multipart requests.\n self.multipart_data = MultipartRequestDataDict()\n\n @classmethod\n def from_args(\n cls,\n request_item_args: List[KeyValueArg],\n request_type: Optional[RequestType] = None,\n ) -> 'RequestItems':\n instance = cls(request_type=request_type)\n rules: Dict[str, Tuple[Callable, dict]] = {\n SEPARATOR_HEADER: (\n process_header_arg,\n instance.headers,\n ),\n SEPARATOR_HEADER_EMPTY: (\n process_empty_header_arg,\n instance.headers,\n ),\n SEPARATOR_HEADER_EMBED: (\n process_embed_header_arg,\n instance.headers,\n ),\n SEPARATOR_QUERY_PARAM: (\n process_query_param_arg,\n instance.params,\n ),\n SEPARATOR_QUERY_EMBED_FILE: (\n process_embed_query_param_arg,\n instance.params,\n ),\n SEPARATOR_FILE_UPLOAD: (\n process_file_upload_arg,\n instance.files,\n ),\n SEPARATOR_DATA_STRING: (\n process_data_item_arg,\n instance.data,\n ),\n SEPARATOR_DATA_EMBED_FILE_CONTENTS: (\n process_data_embed_file_contents_arg,\n instance.data,\n ),\n SEPARATOR_GROUP_NESTED_JSON_ITEMS: (\n process_data_nested_json_embed_args,\n instance.data,\n ),\n SEPARATOR_DATA_RAW_JSON: (\n convert_json_value_to_form_if_needed(\n in_json_mode=instance.is_json,\n processor=process_data_raw_json_embed_arg\n ),\n instance.data,\n ),\n SEPARATOR_DATA_EMBED_RAW_JSON_FILE: (\n convert_json_value_to_form_if_needed(\n in_json_mode=instance.is_json,\n processor=process_data_embed_raw_json_file_arg,\n ),\n instance.data,\n ),\n }\n\n if instance.is_json:\n json_item_args, request_item_args = split_iterable(\n iterable=request_item_args,\n key=lambda arg: arg.sep in SEPARATOR_GROUP_NESTED_JSON_ITEMS\n )\n if json_item_args:\n pairs = [(arg.key, rules[arg.sep][0](arg)) for arg in json_item_args]\n processor_func, target_dict = rules[SEPARATOR_GROUP_NESTED_JSON_ITEMS]\n value = processor_func(pairs)\n target_dict.update(value)\n\n # Then handle all other items.\n for arg in request_item_args:\n processor_func, target_dict = rules[arg.sep]\n value = processor_func(arg)\n\n if arg.sep in SEPARATORS_GROUP_MULTIPART:\n instance.multipart_data[arg.key] = value\n\n if isinstance(target_dict, BaseMultiDict):\n target_dict.add(arg.key, value)\n else:\n target_dict[arg.key] = value\n\n return instance\n\n\nJSONType = Union[str, bool, int, list, dict]\n\n\ndef process_header_arg(arg: KeyValueArg) -> Optional[str]:\n return arg.value or None\n\n\ndef process_embed_header_arg(arg: KeyValueArg) -> str:\n return load_text_file(arg).rstrip('\\n')\n\n\ndef process_empty_header_arg(arg: KeyValueArg) -> str:\n if not arg.value:\n return arg.value\n raise ParseError(\n f'Invalid item {arg.orig!r} (to specify an empty header use `Header;`)'\n )\n\n\ndef process_query_param_arg(arg: KeyValueArg) -> str:\n return arg.value\n\n\ndef process_embed_query_param_arg(arg: KeyValueArg) -> str:\n return load_text_file(arg).rstrip('\\n')\n\n\ndef process_file_upload_arg(arg: KeyValueArg) -> Tuple[str, IO, str]:\n parts = arg.value.split(SEPARATOR_FILE_UPLOAD_TYPE)\n filename = parts[0]\n mime_type = parts[1] if len(parts) > 1 else None\n try:\n f = open(os.path.expanduser(filename), 'rb')\n except OSError as e:\n raise ParseError(f'{arg.orig!r}: {e}')\n return (\n os.path.basename(filename),\n f,\n mime_type or get_content_type(filename),\n )\n\n\ndef convert_json_value_to_form_if_needed(in_json_mode: bool, processor: Callable[[KeyValueArg], JSONType]) -> Callable[[], str]:\n \"\"\"\n We allow primitive values to be passed to forms via JSON key/value syntax.\n\n But complex values lead to an error because there’s no clear way to serialize them.\n\n \"\"\"\n if in_json_mode:\n return processor\n\n @functools.wraps(processor)\n def wrapper(*args, **kwargs) -> str:\n try:\n output = processor(*args, **kwargs)\n except ParseError:\n output = None\n if isinstance(output, (str, int, float)):\n return str(output)\n else:\n raise ParseError('Cannot use complex JSON value types with --form/--multipart.')\n\n return wrapper\n\n\ndef process_data_item_arg(arg: KeyValueArg) -> str:\n return arg.value\n\n\ndef process_data_embed_file_contents_arg(arg: KeyValueArg) -> str:\n return load_text_file(arg)\n\n\ndef process_data_embed_raw_json_file_arg(arg: KeyValueArg) -> JSONType:\n contents = load_text_file(arg)\n value = load_json(arg, contents)\n return value\n\n\ndef process_data_raw_json_embed_arg(arg: KeyValueArg) -> JSONType:\n value = load_json(arg, arg.value)\n return value\n\n\ndef process_data_nested_json_embed_args(pairs) -> Dict[str, JSONType]:\n return interpret_nested_json(pairs)\n\n\ndef load_text_file(item: KeyValueArg) -> str:\n path = item.value\n try:\n with open(os.path.expanduser(path), 'rb') as f:\n return f.read().decode()\n except OSError as e:\n raise ParseError(f'{item.orig!r}: {e}')\n except UnicodeDecodeError:\n raise ParseError(\n f'{item.orig!r}: cannot embed the content of {item.value!r},'\n ' not a UTF-8 or ASCII-encoded text file'\n )\n\n\ndef load_json(arg: KeyValueArg, contents: str) -> JSONType:\n try:\n return load_json_preserve_order_and_dupe_keys(contents)\n except ValueError as e:\n raise ParseError(f'{arg.orig!r}: {e}')\n\n\n\nFile: httpie/cli/constants.py\n\n\"\"\"Parsing and processing of CLI input (args, auth credentials, files, stdin).\n\n\"\"\"\nimport enum\nimport re\n\n\nURL_SCHEME_RE = re.compile(r'^[a-z][a-z0-9.+-]*://', re.IGNORECASE)\n\nHTTP_POST = 'POST'\nHTTP_GET = 'GET'\nHTTP_OPTIONS = 'OPTIONS'\n\n# Various separators used in args\nSEPARATOR_HEADER = ':'\nSEPARATOR_HEADER_EMPTY = ';'\nSEPARATOR_CREDENTIALS = ':'\nSEPARATOR_PROXY = ':'\nSEPARATOR_HEADER_EMBED = ':@'\nSEPARATOR_DATA_STRING = '='\nSEPARATOR_DATA_RAW_JSON = ':='\nSEPARATOR_FILE_UPLOAD = '@'\nSEPARATOR_FILE_UPLOAD_TYPE = ';type=' # in already parsed file upload path only\nSEPARATOR_DATA_EMBED_FILE_CONTENTS = '=@'\nSEPARATOR_DATA_EMBED_RAW_JSON_FILE = ':=@'\nSEPARATOR_QUERY_PARAM = '=='\nSEPARATOR_QUERY_EMBED_FILE = '==@'\n\n# Separators that become request data\nSEPARATOR_GROUP_DATA_ITEMS = frozenset({\n SEPARATOR_DATA_STRING,\n SEPARATOR_DATA_RAW_JSON,\n SEPARATOR_FILE_UPLOAD,\n SEPARATOR_DATA_EMBED_FILE_CONTENTS,\n SEPARATOR_DATA_EMBED_RAW_JSON_FILE\n})\n\nSEPARATORS_GROUP_MULTIPART = frozenset({\n SEPARATOR_DATA_STRING,\n SEPARATOR_DATA_EMBED_FILE_CONTENTS,\n SEPARATOR_FILE_UPLOAD,\n})\n\n# Separators for items whose value is a filename to be embedded\nSEPARATOR_GROUP_DATA_EMBED_ITEMS = frozenset({\n SEPARATOR_HEADER_EMBED,\n SEPARATOR_QUERY_EMBED_FILE,\n SEPARATOR_DATA_EMBED_FILE_CONTENTS,\n SEPARATOR_DATA_EMBED_RAW_JSON_FILE,\n})\n\n# Separators for nested JSON items\nSEPARATOR_GROUP_NESTED_JSON_ITEMS = frozenset([\n SEPARATOR_DATA_STRING,\n SEPARATOR_DATA_RAW_JSON,\n SEPARATOR_DATA_EMBED_FILE_CONTENTS,\n SEPARATOR_DATA_EMBED_RAW_JSON_FILE,\n])\n\n# Separators allowed in ITEM arguments\nSEPARATOR_GROUP_ALL_ITEMS = frozenset({\n SEPARATOR_HEADER,\n SEPARATOR_HEADER_EMPTY,\n SEPARATOR_HEADER_EMBED,\n SEPARATOR_QUERY_PARAM,\n SEPARATOR_QUERY_EMBED_FILE,\n SEPARATOR_DATA_STRING,\n SEPARATOR_DATA_RAW_JSON,\n SEPARATOR_FILE_UPLOAD,\n SEPARATOR_DATA_EMBED_FILE_CONTENTS,\n SEPARATOR_DATA_EMBED_RAW_JSON_FILE,\n})\n\n# Output options\nOUT_REQ_HEAD = 'H'\nOUT_REQ_BODY = 'B'\nOUT_RESP_HEAD = 'h'\nOUT_RESP_BODY = 'b'\nOUT_RESP_META = 'm'\n\nBASE_OUTPUT_OPTIONS = frozenset({\n OUT_REQ_HEAD,\n OUT_REQ_BODY,\n OUT_RESP_HEAD,\n OUT_RESP_BODY,\n})\n\nOUTPUT_OPTIONS = frozenset({\n *BASE_OUTPUT_OPTIONS,\n OUT_RESP_META,\n})\n\n# Pretty\n\n\nclass PrettyOptions(enum.Enum):\n STDOUT_TTY_ONLY = enum.auto()\n\n\nPRETTY_MAP = {\n 'all': ['format', 'colors'],\n 'colors': ['colors'],\n 'format': ['format'],\n 'none': []\n}\nPRETTY_STDOUT_TTY_ONLY = PrettyOptions.STDOUT_TTY_ONLY\n\n\nDEFAULT_FORMAT_OPTIONS = [\n 'headers.sort:true',\n 'json.format:true',\n 'json.indent:4',\n 'json.sort_keys:true',\n 'xml.format:true',\n 'xml.indent:2',\n]\nSORTED_FORMAT_OPTIONS = [\n 'headers.sort:true',\n 'json.sort_keys:true',\n]\nSORTED_FORMAT_OPTIONS_STRING = ','.join(SORTED_FORMAT_OPTIONS)\nUNSORTED_FORMAT_OPTIONS_STRING = ','.join(\n option.replace('true', 'false') for option in SORTED_FORMAT_OPTIONS)\n\n# Defaults\nOUTPUT_OPTIONS_DEFAULT = OUT_RESP_HEAD + OUT_RESP_BODY\nOUTPUT_OPTIONS_DEFAULT_STDOUT_REDIRECTED = OUT_RESP_BODY\nOUTPUT_OPTIONS_DEFAULT_OFFLINE = OUT_REQ_HEAD + OUT_REQ_BODY\n\n\nclass RequestType(enum.Enum):\n FORM = enum.auto()\n MULTIPART = enum.auto()\n JSON = enum.auto()\n\n\n\nFile: httpie/cli/__init__.py\n\n\n\n\nFile: httpie/cli/utils.py\n\nimport argparse\nfrom typing import Any, Callable, Generic, Iterator, Iterable, Optional, TypeVar\n\nT = TypeVar('T')\n\n\nclass Manual(argparse.Action):\n def __init__(\n self,\n option_strings,\n dest=argparse.SUPPRESS,\n default=argparse.SUPPRESS,\n help=None\n ):\n super().__init__(\n option_strings=option_strings,\n dest=dest,\n default=default,\n nargs=0,\n help=help\n )\n\n def __call__(self, parser, namespace, values, option_string=None):\n parser.print_manual()\n parser.exit()\n\n\nclass LazyChoices(argparse.Action, Generic[T]):\n def __init__(\n self,\n *args,\n getter: Callable[[], Iterable[T]],\n help_formatter: Optional[Callable[[T, bool], str]] = None,\n sort: bool = False,\n cache: bool = True,\n isolation_mode: bool = False,\n **kwargs\n ) -> None:\n self.getter = getter\n self.help_formatter = help_formatter\n self.sort = sort\n self.cache = cache\n self.isolation_mode = isolation_mode\n self._help: Optional[str] = None\n self._obj: Optional[Iterable[T]] = None\n super().__init__(*args, **kwargs)\n self.choices = self\n\n def load(self) -> T:\n if self._obj is None or not self.cache:\n self._obj = self.getter()\n\n assert self._obj is not None\n return self._obj\n\n @property\n def help(self) -> str:\n if self._help is None and self.help_formatter is not None:\n self._help = self.help_formatter(\n self.load(),\n isolation_mode=self.isolation_mode\n )\n return self._help\n\n @help.setter\n def help(self, value: Any) -> None:\n self._help = value\n\n def __contains__(self, item: Any) -> bool:\n return item in self.load()\n\n def __iter__(self) -> Iterator[T]:\n if self.sort:\n return iter(sorted(self.load()))\n else:\n return iter(self.load())\n\n def __call__(self, parser, namespace, values, option_string=None):\n setattr(namespace, self.dest, values)\n\n\n\nFile: httpie/cli/definition.py\n\nfrom __future__ import annotations\n\nimport os\nimport textwrap\nfrom argparse import FileType\n\nfrom httpie import __doc__, __version__\nfrom httpie.cli.argtypes import (KeyValueArgType, SessionNameValidator,\n SSLCredentials, readable_file_arg,\n response_charset_type, response_mime_type)\nfrom httpie.cli.constants import (BASE_OUTPUT_OPTIONS, DEFAULT_FORMAT_OPTIONS,\n OUT_REQ_BODY, OUT_REQ_HEAD, OUT_RESP_BODY,\n OUT_RESP_HEAD, OUT_RESP_META, OUTPUT_OPTIONS,\n OUTPUT_OPTIONS_DEFAULT, PRETTY_MAP,\n PRETTY_STDOUT_TTY_ONLY,\n SEPARATOR_GROUP_ALL_ITEMS, SEPARATOR_PROXY,\n SORTED_FORMAT_OPTIONS_STRING,\n UNSORTED_FORMAT_OPTIONS_STRING, RequestType)\nfrom httpie.cli.options import ParserSpec, Qualifiers, to_argparse\nfrom httpie.output.formatters.colors import (AUTO_STYLE, DEFAULT_STYLE, BUNDLED_STYLES,\n get_available_styles)\nfrom httpie.plugins.builtin import BuiltinAuthPlugin\nfrom httpie.plugins.registry import plugin_manager\nfrom httpie.ssl_ import AVAILABLE_SSL_VERSION_ARG_MAPPING, DEFAULT_SSL_CIPHERS_STRING\n\n\n# Man pages are static (built when making a release).\n# We use this check to not include generated, system-specific information there (e.g., default --ciphers).\nIS_MAN_PAGE = bool(os.environ.get('HTTPIE_BUILDING_MAN_PAGES'))\n\n\noptions = ParserSpec(\n 'http',\n description=f'{__doc__.strip()} <https://httpie.io>',\n epilog=\"\"\"\n For every --OPTION there is also a --no-OPTION that reverts OPTION\n to its default value.\n\n Suggestions and bug reports are greatly appreciated:\n https://github.com/httpie/cli/issues\n \"\"\",\n source_file=__file__\n)\n\n#######################################################################\n# Positional arguments.\n#######################################################################\n\npositional_arguments = options.add_group(\n 'Positional arguments',\n description=\"\"\"\n These arguments come after any flags and in the order they are listed here.\n Only URL is required.\n \"\"\",\n)\n\npositional_arguments.add_argument(\n dest='method',\n metavar='METHOD',\n nargs=Qualifiers.OPTIONAL,\n default=None,\n short_help='The HTTP method to be used for the request (GET, POST, PUT, DELETE, ...).',\n help=\"\"\"\n The HTTP method to be used for the request (GET, POST, PUT, DELETE, ...).\n\n This argument can be omitted in which case HTTPie will use POST if there\n is some data to be sent, otherwise GET:\n\n $ http example.org # => GET\n $ http example.org hello=world # => POST\n\n \"\"\",\n)\npositional_arguments.add_argument(\n dest='url',\n metavar='URL',\n short_help='The request URL.',\n help=\"\"\"\n The request URL. Scheme defaults to 'http://' if the URL\n does not include one. (You can override this with: --default-scheme=http/https)\n\n You can also use a shorthand for localhost\n\n $ http :3000 # => http://localhost:3000\n $ http :/foo # => http://localhost/foo\n\n \"\"\",\n)\npositional_arguments.add_argument(\n dest='request_items',\n metavar='REQUEST_ITEM',\n nargs=Qualifiers.ZERO_OR_MORE,\n default=None,\n type=KeyValueArgType(*SEPARATOR_GROUP_ALL_ITEMS),\n short_help=(\n 'HTTPie’s request items syntax for specifying HTTP headers, JSON/Form'\n 'data, files, and URL parameters.'\n ),\n nested_options=[\n ('HTTP Headers', 'Name:Value', 'Arbitrary HTTP header, e.g X-API-Token:123'),\n ('URL Parameters', 'name==value', 'Querystring parameter to the URL, e.g limit==50'),\n ('Data Fields', 'field=value', 'Data fields to be serialized as JSON (default) or Form Data (with --form)'),\n ('Raw JSON Fields', 'field:=json', 'Data field for real JSON types.'),\n ('File upload Fields', 'field@/dir/file', 'Path field for uploading a file.'),\n ],\n help=r\"\"\"\n Optional key-value pairs to be included in the request. The separator used\n determines the type:\n\n ':' HTTP headers:\n\n Referer:https://httpie.io Cookie:foo=bar User-Agent:bacon/1.0\n\n '==' URL parameters to be appended to the request URI:\n\n search==httpie\n\n '=' Data fields to be serialized into a JSON object (with --json, -j)\n or form data (with --form, -f):\n\n name=HTTPie language=Python description='CLI HTTP client'\n\n ':=' Non-string JSON data fields (only with --json, -j):\n\n awesome:=true amount:=42 colors:='[\"red\", \"green\", \"blue\"]'\n\n '@' Form file fields (only with --form or --multipart):\n\n cv@~/Documents/CV.pdf\n cv@'~/Documents/CV.pdf;type=application/pdf'\n\n '=@' A data field like '=', but takes a file path and embeds its content:\n\n essay=@Documents/essay.txt\n\n ':=@' A raw JSON field like ':=', but takes a file path and embeds its content:\n\n package:=@./package.json\n\n You can use a backslash to escape a colliding separator in the field name:\n\n field-name-with\\:colon=value\n\n \"\"\",\n)\n\n#######################################################################\n# Content type.\n#######################################################################\n\ncontent_types = options.add_group('Predefined content types')\n\ncontent_types.add_argument(\n '--json',\n '-j',\n action='store_const',\n const=RequestType.JSON,\n dest='request_type',\n short_help='(default) Serialize data items from the command line as a JSON object.',\n help=\"\"\"\n (default) Data items from the command line are serialized as a JSON object.\n The Content-Type and Accept headers are set to application/json\n (if not specified).\n\n \"\"\",\n)\ncontent_types.add_argument(\n '--form',\n '-f',\n action='store_const',\n const=RequestType.FORM,\n dest='request_type',\n short_help='Serialize data items from the command line as form field data.',\n help=\"\"\"\n Data items from the command line are serialized as form fields.\n\n The Content-Type is set to application/x-www-form-urlencoded (if not\n specified). The presence of any file fields results in a\n multipart/form-data request.\n\n \"\"\",\n)\ncontent_types.add_argument(\n '--multipart',\n action='store_const',\n const=RequestType.MULTIPART,\n dest='request_type',\n short_help=(\n 'Similar to --form, but always sends a multipart/form-data '\n 'request (i.e., even without files).'\n )\n)\ncontent_types.add_argument(\n '--boundary',\n short_help=(\n 'Specify a custom boundary string for multipart/form-data requests. '\n 'Only has effect only together with --form.'\n )\n)\ncontent_types.add_argument(\n '--raw',\n short_help='Pass raw request data without extra processing.',\n help=\"\"\"\n This option allows you to pass raw request data without extra processing\n (as opposed to the structured request items syntax):\n\n $ http --raw='data' pie.dev/post\n\n You can achieve the same by piping the data via stdin:\n\n $ echo data | http pie.dev/post\n\n Or have HTTPie load the raw data from a file:\n\n $ http pie.dev/post @data.txt\n\n\n \"\"\",\n)\n\n#######################################################################\n# Content processing.\n#######################################################################\n\nprocessing_options = options.add_group('Content processing options')\n\nprocessing_options.add_argument(\n '--compress',\n '-x',\n action='count',\n default=0,\n short_help='Compress the content with Deflate algorithm.',\n help=\"\"\"\n Content compressed (encoded) with Deflate algorithm.\n The Content-Encoding header is set to deflate.\n\n Compression is skipped if it appears that compression ratio is\n negative. Compression can be forced by repeating the argument.\n\n \"\"\",\n)\n\n\n#######################################################################\n# Output processing\n#######################################################################\n\n\ndef format_style_help(available_styles, *, isolation_mode: bool = False):\n text = \"\"\"\n Output coloring style (default is \"{default}\"). It can be one of:\n\n {available_styles}\n \"\"\"\n if isolation_mode:\n text += '\\n\\n'\n text += 'For finding out all available styles in your system, try:\\n\\n'\n text += ' $ http --style\\n'\n text += textwrap.dedent(\"\"\"\n The \"{auto_style}\" style follows your terminal's ANSI color styles.\n For non-{auto_style} styles to work properly, please make sure that the\n $TERM environment variable is set to \"xterm-256color\" or similar\n (e.g., via `export TERM=xterm-256color' in your ~/.bashrc).\n \"\"\")\n\n if isolation_mode:\n available_styles = sorted(BUNDLED_STYLES)\n\n available_styles_text = '\\n'.join(\n f' {line.strip()}'\n for line in textwrap.wrap(', '.join(available_styles), 60)\n ).strip()\n return text.format(\n default=DEFAULT_STYLE,\n available_styles=available_styles_text,\n auto_style=AUTO_STYLE,\n )\n\n\n_sorted_kwargs = {\n 'action': 'append_const',\n 'const': SORTED_FORMAT_OPTIONS_STRING,\n 'dest': 'format_options',\n}\n_unsorted_kwargs = {\n 'action': 'append_const',\n 'const': UNSORTED_FORMAT_OPTIONS_STRING,\n 'dest': 'format_options',\n}\n\noutput_processing = options.add_group('Output processing')\n\noutput_processing.add_argument(\n '--pretty',\n dest='prettify',\n default=PRETTY_STDOUT_TTY_ONLY,\n choices=sorted(PRETTY_MAP.keys()),\n short_help='Control the processing of console outputs.',\n help=\"\"\"\n Controls output processing. The value can be \"none\" to not prettify\n the output (default for redirected output), \"all\" to apply both colors\n and formatting (default for terminal output), \"colors\", or \"format\".\n\n \"\"\",\n)\noutput_processing.add_argument(\n '--style',\n '-s',\n dest='style',\n metavar='STYLE',\n default=DEFAULT_STYLE,\n action='lazy_choices',\n getter=get_available_styles,\n short_help=f'Output coloring style (default is \"{DEFAULT_STYLE}\").',\n help_formatter=format_style_help,\n)\n\n# The closest approx. of the documented resetting to default via --no-<option>.\n# We hide them from the doc because they act only as low-level aliases here.\noutput_processing.add_argument(\n '--no-unsorted', **_sorted_kwargs, help=Qualifiers.SUPPRESS\n)\noutput_processing.add_argument(\n '--no-sorted', **_unsorted_kwargs, help=Qualifiers.SUPPRESS\n)\n\noutput_processing.add_argument(\n '--unsorted',\n **_unsorted_kwargs,\n short_help='Disables all sorting while formatting output.',\n help=f\"\"\"\n Disables all sorting while formatting output. It is a shortcut for:\n\n --format-options={UNSORTED_FORMAT_OPTIONS_STRING}\n\n \"\"\",\n)\noutput_processing.add_argument(\n '--sorted',\n **_sorted_kwargs,\n short_help='Re-enables all sorting options while formatting output.',\n help=f\"\"\"\n Re-enables all sorting options while formatting output. It is a shortcut for:\n\n --format-options={SORTED_FORMAT_OPTIONS_STRING}\n\n \"\"\",\n)\noutput_processing.add_argument(\n '--response-charset',\n metavar='ENCODING',\n type=response_charset_type,\n short_help='Override the response encoding for terminal display purposes.',\n help=\"\"\"\n Override the response encoding for terminal display purposes, e.g.:\n\n --response-charset=utf8\n --response-charset=big5\n\n \"\"\",\n)\noutput_processing.add_argument(\n '--response-mime',\n metavar='MIME_TYPE',\n type=response_mime_type,\n short_help='Override the response mime type for coloring and formatting for the terminal.',\n help=\"\"\"\n Override the response mime type for coloring and formatting for the terminal, e.g.:\n\n --response-mime=application/json\n --response-mime=text/xml\n\n \"\"\",\n)\noutput_processing.add_argument(\n '--format-options',\n action='append',\n short_help='Controls output formatting.',\n help=\"\"\"\n Controls output formatting. Only relevant when formatting is enabled\n through (explicit or implied) --pretty=all or --pretty=format.\n The following are the default options:\n\n {option_list}\n\n You may use this option multiple times, as well as specify multiple\n comma-separated options at the same time. For example, this modifies the\n settings to disable the sorting of JSON keys, and sets the indent size to 2:\n\n --format-options json.sort_keys:false,json.indent:2\n\n This is something you will typically put into your config file.\n\n \"\"\".format(\n option_list='\\n'.join(\n f' {option}' for option in DEFAULT_FORMAT_OPTIONS\n ).strip()\n ),\n)\n\n#######################################################################\n# Output options\n#######################################################################\n\noutput_options = options.add_group('Output options')\n\noutput_options.add_argument(\n '--print',\n '-p',\n dest='output_options',\n metavar='WHAT',\n short_help='Options to specify what the console output should contain.',\n help=f\"\"\"\n String specifying what the output should contain:\n\n '{OUT_REQ_HEAD}' request headers\n '{OUT_REQ_BODY}' request body\n '{OUT_RESP_HEAD}' response headers\n '{OUT_RESP_BODY}' response body\n '{OUT_RESP_META}' response metadata\n\n The default behaviour is '{OUTPUT_OPTIONS_DEFAULT}' (i.e., the response\n headers and body is printed), if standard output is not redirected.\n If the output is piped to another program or to a file, then only the\n response body is printed by default.\n\n \"\"\",\n)\noutput_options.add_argument(\n '--headers',\n '-h',\n dest='output_options',\n action='store_const',\n const=OUT_RESP_HEAD,\n short_help='Print only the response headers.',\n help=f\"\"\"\n Print only the response headers. Shortcut for --print={OUT_RESP_HEAD}.\n\n \"\"\",\n)\noutput_options.add_argument(\n '--meta',\n '-m',\n dest='output_options',\n action='store_const',\n const=OUT_RESP_META,\n short_help='Print only the response metadata.',\n help=f\"\"\"\n Print only the response metadata. Shortcut for --print={OUT_RESP_META}.\n\n \"\"\",\n)\noutput_options.add_argument(\n '--body',\n '-b',\n dest='output_options',\n action='store_const',\n const=OUT_RESP_BODY,\n short_help='Print only the response body.',\n help=f\"\"\"\n Print only the response body. Shortcut for --print={OUT_RESP_BODY}.\n\n \"\"\",\n)\n\noutput_options.add_argument(\n '--verbose',\n '-v',\n dest='verbose',\n action='count',\n default=0,\n short_help='Make output more verbose.',\n help=f\"\"\"\n Verbose output. For the level one (with single `-v`/`--verbose`), print\n the whole request as well as the response. Also print any intermediary\n requests/responses (such as redirects). For the second level and higher,\n print these as well as the response metadata.\n\n Level one is a shortcut for: --all --print={''.join(sorted(BASE_OUTPUT_OPTIONS))}\n Level two is a shortcut for: --all --print={''.join(sorted(OUTPUT_OPTIONS))}\n \"\"\",\n)\noutput_options.add_argument(\n '--all',\n default=False,\n action='store_true',\n short_help='Show any intermediary requests/responses.',\n help=\"\"\"\n By default, only the final request/response is shown. Use this flag to show\n any intermediary requests/responses as well. Intermediary requests include\n followed redirects (with --follow), the first unauthorized request when\n Digest auth is used (--auth=digest), etc.\n\n \"\"\",\n)\noutput_options.add_argument(\n '--history-print',\n '-P',\n dest='output_options_history',\n metavar='WHAT',\n help=Qualifiers.SUPPRESS,\n)\noutput_options.add_argument(\n '--stream',\n '-S',\n action='store_true',\n default=False,\n short_help='Always stream the response body by line, i.e., behave like `tail -f`.',\n help=\"\"\"\n Always stream the response body by line, i.e., behave like `tail -f'.\n\n Without --stream and with --pretty (either set or implied),\n HTTPie fetches the whole response before it outputs the processed data.\n\n Set this option when you want to continuously display a prettified\n long-lived response, such as one from the Twitter streaming API.\n\n It is useful also without --pretty: It ensures that the output is flushed\n more often and in smaller chunks.\n\n \"\"\",\n)\noutput_options.add_argument(\n '--output',\n '-o',\n type=FileType('a+b'),\n dest='output_file',\n metavar='FILE',\n short_help='Save output to FILE instead of stdout.',\n help=\"\"\"\n Save output to FILE instead of stdout. If --download is also set, then only\n the response body is saved to FILE. Other parts of the HTTP exchange are\n printed to stderr.\n\n \"\"\",\n)\n\noutput_options.add_argument(\n '--download',\n '-d',\n action='store_true',\n default=False,\n short_help='Download the body to a file instead of printing it to stdout.',\n help=\"\"\"\n Do not print the response body to stdout. Rather, download it and store it\n in a file. The filename is guessed unless specified with --output\n [filename]. This action is similar to the default behaviour of wget.\n\n \"\"\",\n)\noutput_options.add_argument(\n '--continue',\n '-c',\n dest='download_resume',\n action='store_true',\n default=False,\n short_help='Resume an interrupted download (--output needs to be specified).',\n help=\"\"\"\n Resume an interrupted download. Note that the --output option needs to be\n specified as well.\n\n \"\"\",\n)\noutput_options.add_argument(\n '--quiet',\n '-q',\n action='count',\n default=0,\n short_help='Do not print to stdout or stderr, except for errors and warnings when provided once.',\n help=\"\"\"\n Do not print to stdout or stderr, except for errors and warnings when provided once.\n Provide twice to suppress warnings as well.\n stdout is still redirected if --output is specified.\n Flag doesn't affect behaviour of download beyond not printing to terminal.\n\n \"\"\",\n)\n\n#######################################################################\n# Sessions\n#######################################################################\n\nsession_name_validator = SessionNameValidator(\n 'Session name contains invalid characters.'\n)\n\nsessions = options.add_group('Sessions', is_mutually_exclusive=True)\n\nsessions.add_argument(\n '--session',\n metavar='SESSION_NAME_OR_PATH',\n type=session_name_validator,\n short_help='Create, or reuse and update a session.',\n help=\"\"\"\n Create, or reuse and update a session. Within a session, custom headers,\n auth credential, as well as any cookies sent by the server persist between\n requests.\n\n Session files are stored in:\n\n [HTTPIE_CONFIG_DIR]/<HOST>/<SESSION_NAME>.json.\n\n See the following page to find out your default HTTPIE_CONFIG_DIR:\n\n https://httpie.io/docs/cli/config-file-directory\n \"\"\",\n)\nsessions.add_argument(\n '--session-read-only',\n metavar='SESSION_NAME_OR_PATH',\n type=session_name_validator,\n short_help='Create or read a session without updating it',\n help=\"\"\"\n Create or read a session without updating it form the request/response\n exchange.\n\n \"\"\",\n)\n\n\n#######################################################################\n# Authentication\n#######################################################################\n\n\ndef format_auth_help(auth_plugins_mapping, *, isolation_mode: bool = False):\n text = \"\"\"\n The authentication mechanism to be used. Defaults to \"{default}\".\n\n {auth_types}\n \"\"\"\n\n auth_plugins = list(auth_plugins_mapping.values())\n if isolation_mode:\n auth_plugins = [\n auth_plugin\n for auth_plugin in auth_plugins\n if issubclass(auth_plugin, BuiltinAuthPlugin)\n ]\n text += '\\n'\n text += 'To see all available auth types on your system, including ones installed via plugins, run:\\n\\n'\n text += ' $ http --auth-type'\n\n auth_types = '\\n\\n '.join(\n '\"{type}\": {name}{package}{description}'.format(\n type=plugin.auth_type,\n name=plugin.name,\n package=(\n ''\n if issubclass(plugin, BuiltinAuthPlugin)\n else f' (provided by {plugin.package_name})'\n ),\n description=(\n ''\n if not plugin.description\n else '\\n '\n + ('\\n '.join(textwrap.wrap(plugin.description)))\n ),\n )\n for plugin in auth_plugins\n )\n\n return text.format(\n default=auth_plugins[0].auth_type,\n auth_types=auth_types,\n )\n\n\nauthentication = options.add_group('Authentication')\n\nauthentication.add_argument(\n '--auth',\n '-a',\n default=None,\n metavar='USER[:PASS] | TOKEN',\n short_help='Credentials for the selected (-A) authentication method.',\n help=\"\"\"\n For username/password based authentication mechanisms (e.g\n basic auth or digest auth) if only the username is provided\n (-a username), HTTPie will prompt for the password.\n\n \"\"\",\n)\nauthentication.add_argument(\n '--auth-type',\n '-A',\n action='lazy_choices',\n default=None,\n getter=plugin_manager.get_auth_plugin_mapping,\n sort=True,\n cache=False,\n short_help='The authentication mechanism to be used.',\n help_formatter=format_auth_help,\n)\nauthentication.add_argument(\n '--ignore-netrc',\n default=False,\n action='store_true',\n short_help='Ignore credentials from .netrc.'\n)\n\n#######################################################################\n# Network\n#######################################################################\n\nnetwork = options.add_group('Network')\n\nnetwork.add_argument(\n '--offline',\n default=False,\n action='store_true',\n short_help='Build the request and print it but don’t actually send it.'\n)\nnetwork.add_argument(\n '--proxy',\n default=[],\n action='append',\n metavar='PROTOCOL:PROXY_URL',\n type=KeyValueArgType(SEPARATOR_PROXY),\n short_help='String mapping of protocol to the URL of the proxy.',\n help=\"\"\"\n String mapping protocol to the URL of the proxy\n (e.g. http:http://foo.bar:3128). You can specify multiple proxies with\n different protocols. The environment variables $ALL_PROXY, $HTTP_PROXY,\n and $HTTPS_proxy are supported as well.\n\n \"\"\",\n)\nnetwork.add_argument(\n '--follow',\n '-F',\n default=False,\n action='store_true',\n short_help='Follow 30x Location redirects.'\n)\n\nnetwork.add_argument(\n '--max-redirects',\n type=int,\n default=30,\n short_help='The maximum number of redirects that should be followed (with --follow).',\n help=\"\"\"\n By default, requests have a limit of 30 redirects (works with --follow).\n\n \"\"\",\n)\nnetwork.add_argument(\n '--max-headers',\n type=int,\n default=0,\n short_help=(\n 'The maximum number of response headers to be read before '\n 'giving up (default 0, i.e., no limit).'\n )\n)\n\nnetwork.add_argument(\n '--timeout',\n type=float,\n default=0,\n metavar='SECONDS',\n short_help='The connection timeout of the request in seconds.',\n help=\"\"\"\n The connection timeout of the request in seconds.\n The default value is 0, i.e., there is no timeout limit.\n This is not a time limit on the entire response download;\n rather, an error is reported if the server has not issued a response for\n timeout seconds (more precisely, if no bytes have been received on\n the underlying socket for timeout seconds).\n\n \"\"\",\n)\nnetwork.add_argument(\n '--check-status',\n default=False,\n action='store_true',\n short_help='Exit with an error status code if the server replies with an error.',\n help=\"\"\"\n By default, HTTPie exits with 0 when no network or other fatal errors\n occur. This flag instructs HTTPie to also check the HTTP status code and\n exit with an error if the status indicates one.\n\n When the server replies with a 4xx (Client Error) or 5xx (Server Error)\n status code, HTTPie exits with 4 or 5 respectively. If the response is a\n 3xx (Redirect) and --follow hasn't been set, then the exit status is 3.\n Also an error message is written to stderr if stdout is redirected.\n\n \"\"\",\n)\nnetwork.add_argument(\n '--path-as-is',\n default=False,\n action='store_true',\n short_help='Bypass dot segment (/../ or /./) URL squashing.'\n)\nnetwork.add_argument(\n '--chunked',\n default=False,\n action='store_true',\n short_help=(\n 'Enable streaming via chunked transfer encoding. '\n 'The Transfer-Encoding header is set to chunked.'\n )\n)\n\n#######################################################################\n# SSL\n#######################################################################\n\nssl = options.add_group('SSL')\n\nssl.add_argument(\n '--verify',\n default='yes',\n short_help='If \"no\", skip SSL verification. If a file path, use it as a CA bundle.',\n help=\"\"\"\n Set to \"no\" (or \"false\") to skip checking the host's SSL certificate.\n Defaults to \"yes\" (\"true\"). You can also pass the path to a CA_BUNDLE file\n for private certs. (Or you can set the REQUESTS_CA_BUNDLE environment\n variable instead.)\n \"\"\",\n)\nssl.add_argument(\n '--ssl',\n dest='ssl_version',\n choices=sorted(AVAILABLE_SSL_VERSION_ARG_MAPPING.keys()),\n short_help='The desired protocol version to used.',\n help=\"\"\"\n The desired protocol version to use. This will default to\n SSL v2.3 which will negotiate the highest protocol that both\n the server and your installation of OpenSSL support. Available protocols\n may vary depending on OpenSSL installation (only the supported ones\n are shown here).\n\n \"\"\",\n)\n\nCIPHERS_CURRENT_DEFAULTS = (\n \"\"\"\n See `http --help` for the default ciphers list on you system.\n\n \"\"\"\n if IS_MAN_PAGE else\n f\"\"\"\n By default, the following ciphers are used on your system:\n\n {DEFAULT_SSL_CIPHERS_STRING}\n\n \"\"\"\n)\nssl.add_argument(\n '--ciphers',\n short_help='A string in the OpenSSL cipher list format.',\n help=f\"\"\"\n\n A string in the OpenSSL cipher list format.\n\n {CIPHERS_CURRENT_DEFAULTS}\n\n \"\"\"\n)\nssl.add_argument(\n '--cert',\n default=None,\n type=readable_file_arg,\n short_help='Specifies a local cert to use as the client-side SSL certificate.',\n help=\"\"\"\n You can specify a local cert to use as client side SSL certificate.\n This file may either contain both private key and certificate or you may\n specify --cert-key separately.\n\n \"\"\",\n)\nssl.add_argument(\n '--cert-key',\n default=None,\n type=readable_file_arg,\n short_help='The private key to use with SSL. Only needed if --cert is given.',\n help=\"\"\"\n The private key to use with SSL. Only needed if --cert is given and the\n certificate file does not contain the private key.\n\n \"\"\",\n)\n\nssl.add_argument(\n '--cert-key-pass',\n default=None,\n type=SSLCredentials,\n short_help='The passphrase to be used to with the given private key.',\n help=\"\"\"\n The passphrase to be used to with the given private key. Only needed if --cert-key\n is given and the key file requires a passphrase.\n If not provided, you’ll be prompted interactively.\n \"\"\"\n)\n\n#######################################################################\n# Troubleshooting\n#######################################################################\n\ntroubleshooting = options.add_group('Troubleshooting')\ntroubleshooting.add_argument(\n '--ignore-stdin',\n '-I',\n action='store_true',\n default=False,\n short_help='Do not attempt to read stdin'\n)\ntroubleshooting.add_argument(\n '--help',\n action='help',\n default=Qualifiers.SUPPRESS,\n short_help='Show this help message and exit.',\n)\ntroubleshooting.add_argument(\n '--manual',\n action='manual',\n default=Qualifiers.SUPPRESS,\n short_help='Show the full manual.',\n)\ntroubleshooting.add_argument(\n '--version',\n action='version',\n version=__version__,\n short_help='Show version and exit.',\n)\ntroubleshooting.add_argument(\n '--traceback',\n action='store_true',\n default=False,\n short_help='Prints the exception traceback should one occur.',\n)\ntroubleshooting.add_argument(\n '--default-scheme',\n default='http',\n short_help='The default scheme to use if not specified in the URL.'\n)\ntroubleshooting.add_argument(\n '--debug',\n action='store_true',\n default=False,\n short_help='Print useful diagnostic information for bug reports.',\n help=\"\"\"\n Prints the exception traceback should one occur, as well as other\n information useful for debugging HTTPie itself and for reporting bugs.\n\n \"\"\",\n)\n\n#######################################################################\n# Finalization\n#######################################################################\n\noptions.finalize()\nparser = to_argparse(options)\n\n\n\nFile: httpie/cli/exceptions.py\n\nclass ParseError(Exception):\n pass\n\n\n\nFile: httpie/cli/argparser.py\n\nimport argparse\nimport errno\nimport os\nimport re\nimport sys\nfrom argparse import RawDescriptionHelpFormatter\nfrom textwrap import dedent\nfrom urllib.parse import urlsplit\n\nfrom requests.utils import get_netrc_auth\n\nfrom .argtypes import (\n AuthCredentials, SSLCredentials, KeyValueArgType,\n PARSED_DEFAULT_FORMAT_OPTIONS,\n parse_auth,\n parse_format_options,\n)\nfrom .constants import (\n HTTP_GET, HTTP_POST, BASE_OUTPUT_OPTIONS, OUTPUT_OPTIONS, OUTPUT_OPTIONS_DEFAULT,\n OUTPUT_OPTIONS_DEFAULT_OFFLINE, OUTPUT_OPTIONS_DEFAULT_STDOUT_REDIRECTED,\n OUT_RESP_BODY, PRETTY_MAP, PRETTY_STDOUT_TTY_ONLY, RequestType,\n SEPARATOR_CREDENTIALS,\n SEPARATOR_GROUP_ALL_ITEMS, SEPARATOR_GROUP_DATA_ITEMS, URL_SCHEME_RE,\n)\nfrom .exceptions import ParseError\nfrom .requestitems import RequestItems\nfrom ..context import Environment\nfrom ..plugins.registry import plugin_manager\nfrom ..utils import ExplicitNullAuth, get_content_type\n\n\nclass HTTPieHelpFormatter(RawDescriptionHelpFormatter):\n \"\"\"A nicer help formatter.\n\n Help for arguments can be indented and contain new lines.\n It will be de-dented and arguments in the help\n will be separated by a blank line for better readability.\n\n\n \"\"\"\n\n def __init__(self, max_help_position=6, *args, **kwargs):\n # A smaller indent for args help.\n kwargs['max_help_position'] = max_help_position\n super().__init__(*args, **kwargs)\n\n def _split_lines(self, text, width):\n text = dedent(text).strip() + '\\n\\n'\n return text.splitlines()\n\n def add_usage(self, usage, actions, groups, prefix=None):\n # Only display the positional arguments\n displayed_actions = [\n action\n for action in actions\n if not action.option_strings\n ]\n\n _, exception, _ = sys.exc_info()\n if (\n isinstance(exception, argparse.ArgumentError)\n and len(exception.args) >= 1\n and isinstance(exception.args[0], argparse.Action)\n ):\n # add_usage path is also taken when you pass an invalid option,\n # e.g --style=invalid. If something like that happens, we want\n # to include to action that caused to the invalid usage into\n # the list of actions we are displaying.\n displayed_actions.insert(0, exception.args[0])\n\n super().add_usage(\n usage,\n displayed_actions,\n groups,\n prefix=\"usage:\\n \"\n )\n\n\n# TODO: refactor and design type-annotated data structures\n# for raw args + parsed args and keep things immutable.\nclass BaseHTTPieArgumentParser(argparse.ArgumentParser):\n def __init__(self, *args, **kwargs):\n super().__init__(*args, **kwargs)\n self.env = None\n self.args = None\n self.has_stdin_data = False\n self.has_input_data = False\n\n # noinspection PyMethodOverriding\n def parse_args(\n self,\n env: Environment,\n args=None,\n namespace=None\n ) -> argparse.Namespace:\n self.env = env\n self.args, no_options = self.parse_known_args(args, namespace)\n if self.args.debug:\n self.args.traceback = True\n self.has_stdin_data = (\n self.env.stdin\n and not getattr(self.args, 'ignore_stdin', False)\n and not self.env.stdin_isatty\n )\n self.has_input_data = self.has_stdin_data or getattr(self.args, 'raw', None) is not None\n return self.args\n\n # noinspection PyShadowingBuiltins\n def _print_message(self, message, file=None):\n # Sneak in our stderr/stdout.\n if hasattr(self, 'root'):\n env = self.root.env\n else:\n env = self.env\n\n if env is not None:\n file = {\n sys.stdout: env.stdout,\n sys.stderr: env.stderr,\n None: env.stderr\n }.get(file, file)\n\n if not hasattr(file, 'buffer') and isinstance(message, str):\n message = message.encode(env.stdout_encoding)\n super()._print_message(message, file)\n\n\nclass HTTPieManagerArgumentParser(BaseHTTPieArgumentParser):\n def parse_known_args(self, args=None, namespace=None):\n try:\n return super().parse_known_args(args, namespace)\n except SystemExit as exc:\n if not hasattr(self, 'root') and exc.code == 2: # Argument Parser Error\n raise argparse.ArgumentError(None, None)\n raise\n\n\nclass HTTPieArgumentParser(BaseHTTPieArgumentParser):\n \"\"\"Adds additional logic to `argparse.ArgumentParser`.\n\n Handles all input (CLI args, file args, stdin), applies defaults,\n and performs extra validation.\n\n \"\"\"\n\n def __init__(self, *args, formatter_class=HTTPieHelpFormatter, **kwargs):\n kwargs.setdefault('add_help', False)\n super().__init__(*args, formatter_class=formatter_class, **kwargs)\n\n # noinspection PyMethodOverriding\n def parse_args(\n self,\n env: Environment,\n args=None,\n namespace=None\n ) -> argparse.Namespace:\n self.env = env\n self.env.args = namespace = namespace or argparse.Namespace()\n self.args, no_options = super().parse_known_args(args, namespace)\n if self.args.debug:\n self.args.traceback = True\n self.has_stdin_data = (\n self.env.stdin\n and not self.args.ignore_stdin\n and not self.env.stdin_isatty\n )\n self.has_input_data = self.has_stdin_data or self.args.raw is not None\n # Arguments processing and environment setup.\n self._apply_no_options(no_options)\n self._process_request_type()\n self._process_download_options()\n self._setup_standard_streams()\n self._process_output_options()\n self._process_pretty_options()\n self._process_format_options()\n self._guess_method()\n self._parse_items()\n self._process_url()\n self._process_auth()\n self._process_ssl_cert()\n\n if self.args.raw is not None:\n self._body_from_input(self.args.raw)\n elif self.has_stdin_data:\n self._body_from_file(self.env.stdin)\n\n if self.args.compress:\n # TODO: allow --compress with --chunked / --multipart\n if self.args.chunked:\n self.error('cannot combine --compress and --chunked')\n if self.args.multipart:\n self.error('cannot combine --compress and --multipart')\n\n return self.args\n\n def _process_request_type(self):\n request_type = self.args.request_type\n self.args.json = request_type is RequestType.JSON\n self.args.multipart = request_type is RequestType.MULTIPART\n self.args.form = request_type in {\n RequestType.FORM,\n RequestType.MULTIPART,\n }\n\n def _process_url(self):\n if self.args.url.startswith('://'):\n # Paste URL & add space shortcut: `http ://pie.dev` → `http://pie.dev`\n self.args.url = self.args.url[3:]\n if not URL_SCHEME_RE.match(self.args.url):\n if os.path.basename(self.env.program_name) == 'https':\n scheme = 'https://'\n else:\n scheme = self.args.default_scheme + '://'\n\n # See if we're using curl style shorthand for localhost (:3000/foo)\n shorthand = re.match(r'^:(?!:)(\\d*)(/?.*)$', self.args.url)\n if shorthand:\n port = shorthand.group(1)\n rest = shorthand.group(2)\n self.args.url = scheme + 'localhost'\n if port:\n self.args.url += ':' + port\n self.args.url += rest\n else:\n self.args.url = scheme + self.args.url\n\n def _setup_standard_streams(self):\n \"\"\"\n Modify `env.stdout` and `env.stdout_isatty` based on args, if needed.\n\n \"\"\"\n\n self.args.output_file_specified = bool(self.args.output_file)\n if self.args.download:\n # FIXME: Come up with a cleaner solution.\n if not self.args.output_file and not self.env.stdout_isatty:\n # Use stdout as the download output file.\n self.args.output_file = self.env.stdout\n # With `--download`, we write everything that would normally go to\n # `stdout` to `stderr` instead. Let's replace the stream so that\n # we don't have to use many `if`s throughout the codebase.\n # The response body will be treated separately.\n self.env.stdout = self.env.stderr\n self.env.stdout_isatty = self.env.stderr_isatty\n\n elif self.args.output_file:\n # When not `--download`ing, then `--output` simply replaces\n # `stdout`. The file is opened for appending, which isn't what\n # we want in this case.\n self.args.output_file.seek(0)\n try:\n self.args.output_file.truncate()\n except OSError as e:\n if e.errno == errno.EINVAL:\n # E.g. /dev/null on Linux.\n pass\n else:\n raise\n self.env.stdout = self.args.output_file\n self.env.stdout_isatty = False\n\n if self.args.quiet:\n self.env.quiet = self.args.quiet\n self.env.stderr = self.env.devnull\n if not (self.args.output_file_specified and not self.args.download):\n self.env.stdout = self.env.devnull\n self.env.apply_warnings_filter()\n\n def _process_ssl_cert(self):\n from httpie.ssl_ import _is_key_file_encrypted\n\n if self.args.cert_key_pass is None:\n self.args.cert_key_pass = SSLCredentials(None)\n\n if (\n self.args.cert_key is not None\n and self.args.cert_key_pass.value is None\n and _is_key_file_encrypted(self.args.cert_key)\n ):\n self.args.cert_key_pass.prompt_password(self.args.cert_key)\n\n def _process_auth(self):\n # TODO: refactor & simplify this method.\n self.args.auth_plugin = None\n default_auth_plugin = plugin_manager.get_auth_plugins()[0]\n auth_type_set = self.args.auth_type is not None\n url = urlsplit(self.args.url)\n\n if self.args.auth is None and not auth_type_set:\n if url.username is not None:\n # Handle http://username:password@hostname/\n username = url.username\n password = url.password or ''\n self.args.auth = AuthCredentials(\n key=username,\n value=password,\n sep=SEPARATOR_CREDENTIALS,\n orig=SEPARATOR_CREDENTIALS.join([username, password])\n )\n\n if self.args.auth is not None or auth_type_set:\n if not self.args.auth_type:\n self.args.auth_type = default_auth_plugin.auth_type\n plugin = plugin_manager.get_auth_plugin(self.args.auth_type)()\n\n if (not self.args.ignore_netrc\n and self.args.auth is None\n and plugin.netrc_parse):\n # Only host needed, so it’s OK URL not finalized.\n netrc_credentials = get_netrc_auth(self.args.url)\n if netrc_credentials:\n self.args.auth = AuthCredentials(\n key=netrc_credentials[0],\n value=netrc_credentials[1],\n sep=SEPARATOR_CREDENTIALS,\n orig=SEPARATOR_CREDENTIALS.join(netrc_credentials)\n )\n\n if plugin.auth_require and self.args.auth is None:\n self.error('--auth required')\n\n plugin.raw_auth = self.args.auth\n self.args.auth_plugin = plugin\n already_parsed = isinstance(self.args.auth, AuthCredentials)\n\n if self.args.auth is None or not plugin.auth_parse:\n self.args.auth = plugin.get_auth()\n else:\n if already_parsed:\n # from the URL\n credentials = self.args.auth\n else:\n credentials = parse_auth(self.args.auth)\n\n if (not credentials.has_password()\n and plugin.prompt_password):\n if self.args.ignore_stdin:\n # Non-tty stdin read by now\n self.error(\n 'Unable to prompt for passwords because'\n ' --ignore-stdin is set.'\n )\n credentials.prompt_password(url.netloc)\n\n if (credentials.key and credentials.value):\n plugin.raw_auth = credentials.key + \":\" + credentials.value\n\n self.args.auth = plugin.get_auth(\n username=credentials.key,\n password=credentials.value,\n )\n if not self.args.auth and self.args.ignore_netrc:\n # Set a no-op auth to force requests to ignore .netrc\n # <https://github.com/psf/requests/issues/2773#issuecomment-174312831>\n self.args.auth = ExplicitNullAuth()\n\n def _apply_no_options(self, no_options):\n \"\"\"For every `--no-OPTION` in `no_options`, set `args.OPTION` to\n its default value. This allows for un-setting of options, e.g.,\n specified in config.\n\n \"\"\"\n invalid = []\n\n for option in no_options:\n if not option.startswith('--no-'):\n invalid.append(option)\n continue\n\n # --no-option => --option\n inverted = '--' + option[5:]\n for action in self._actions:\n if inverted in action.option_strings:\n setattr(self.args, action.dest, action.default)\n break\n else:\n invalid.append(option)\n\n if invalid:\n self.error(f'unrecognized arguments: {\" \".join(invalid)}')\n\n def _body_from_file(self, fd):\n \"\"\"Read the data from a file-like object.\n\n Bytes are always read.\n\n \"\"\"\n self._ensure_one_data_source(self.args.data, self.args.files)\n self.args.data = getattr(fd, 'buffer', fd)\n\n def _body_from_input(self, data):\n \"\"\"Read the data from the CLI.\n\n \"\"\"\n self._ensure_one_data_source(self.has_stdin_data, self.args.data,\n self.args.files)\n self.args.data = data.encode()\n\n def _ensure_one_data_source(self, *other_sources):\n \"\"\"There can only be one source of input request data.\n\n \"\"\"\n if any(other_sources):\n self.error('Request body (from stdin, --raw or a file) and request '\n 'data (key=value) cannot be mixed. Pass '\n '--ignore-stdin to let key/value take priority. '\n 'See https://httpie.io/docs#scripting for details.')\n\n def _guess_method(self):\n \"\"\"Set `args.method` if not specified to either POST or GET\n based on whether the request has data or not.\n\n \"\"\"\n if self.args.method is None:\n # Invoked as `http URL'.\n assert not self.args.request_items\n if self.has_input_data:\n self.args.method = HTTP_POST\n else:\n self.args.method = HTTP_GET\n\n # FIXME: False positive, e.g., \"localhost\" matches but is a valid URL.\n elif not re.match('^[a-zA-Z]+$', self.args.method):\n # Invoked as `http URL item+'. The URL is now in `args.method`\n # and the first ITEM is now incorrectly in `args.url`.\n try:\n # Parse the URL as an ITEM and store it as the first ITEM arg.\n self.args.request_items.insert(0, KeyValueArgType(\n *SEPARATOR_GROUP_ALL_ITEMS).__call__(self.args.url))\n\n except argparse.ArgumentTypeError as e:\n if self.args.traceback:\n raise\n self.error(e.args[0])\n\n else:\n # Set the URL correctly\n self.args.url = self.args.method\n # Infer the method\n has_data = (\n self.has_input_data\n or any(\n item.sep in SEPARATOR_GROUP_DATA_ITEMS\n for item in self.args.request_items)\n )\n self.args.method = HTTP_POST if has_data else HTTP_GET\n\n def _parse_items(self):\n \"\"\"\n Parse `args.request_items` into `args.headers`, `args.data`,\n `args.params`, and `args.files`.\n\n \"\"\"\n try:\n request_items = RequestItems.from_args(\n request_item_args=self.args.request_items,\n request_type=self.args.request_type,\n )\n except ParseError as e:\n if self.args.traceback:\n raise\n self.error(e.args[0])\n else:\n self.args.headers = request_items.headers\n self.args.data = request_items.data\n self.args.files = request_items.files\n self.args.params = request_items.params\n self.args.multipart_data = request_items.multipart_data\n\n if self.args.files and not self.args.form:\n # `http url @/path/to/file`\n request_file = None\n for key, file in self.args.files.items():\n if key != '':\n self.error(\n 'Invalid file fields (perhaps you meant --form?):'\n f' {\",\".join(self.args.files.keys())}')\n if request_file is not None:\n self.error(\"Can't read request from multiple files\")\n request_file = file\n\n fn, fd, ct = request_file\n self.args.files = {}\n\n self._body_from_file(fd)\n\n if 'Content-Type' not in self.args.headers:\n content_type = get_content_type(fn)\n if content_type:\n self.args.headers['Content-Type'] = content_type\n\n def _process_output_options(self):\n \"\"\"Apply defaults to output options, or validate the provided ones.\n\n The default output options are stdout-type-sensitive.\n\n \"\"\"\n\n def check_options(value, option):\n unknown = set(value) - OUTPUT_OPTIONS\n if unknown:\n self.error(f'Unknown output options: {option}={\",\".join(unknown)}')\n\n if self.args.verbose:\n self.args.all = True\n\n if self.args.output_options is None:\n if self.args.verbose >= 2:\n self.args.output_options = ''.join(OUTPUT_OPTIONS)\n elif self.args.verbose == 1:\n self.args.output_options = ''.join(BASE_OUTPUT_OPTIONS)\n elif self.args.offline:\n self.args.output_options = OUTPUT_OPTIONS_DEFAULT_OFFLINE\n elif not self.env.stdout_isatty:\n self.args.output_options = OUTPUT_OPTIONS_DEFAULT_STDOUT_REDIRECTED\n else:\n self.args.output_options = OUTPUT_OPTIONS_DEFAULT\n\n if self.args.output_options_history is None:\n self.args.output_options_history = self.args.output_options\n\n check_options(self.args.output_options, '--print')\n check_options(self.args.output_options_history, '--history-print')\n\n if self.args.download and OUT_RESP_BODY in self.args.output_options:\n # Response body is always downloaded with --download and it goes\n # through a different routine, so we remove it.\n self.args.output_options = str(\n set(self.args.output_options) - set(OUT_RESP_BODY))\n\n def _process_pretty_options(self):\n if self.args.prettify == PRETTY_STDOUT_TTY_ONLY:\n self.args.prettify = PRETTY_MAP[\n 'all' if self.env.stdout_isatty else 'none']\n elif (self.args.prettify and self.env.is_windows\n and self.args.output_file):\n self.error('Only terminal output can be colorized on Windows.')\n else:\n # noinspection PyTypeChecker\n self.args.prettify = PRETTY_MAP[self.args.prettify]\n\n def _process_download_options(self):\n if self.args.offline:\n self.args.download = False\n self.args.download_resume = False\n return\n if not self.args.download:\n if self.args.download_resume:\n self.error('--continue only works with --download')\n if self.args.download_resume and not (\n self.args.download and self.args.output_file):\n self.error('--continue requires --output to be specified')\n\n def _process_format_options(self):\n format_options = self.args.format_options or []\n parsed_options = PARSED_DEFAULT_FORMAT_OPTIONS\n for options_group in format_options:\n parsed_options = parse_format_options(options_group, defaults=parsed_options)\n self.args.format_options = parsed_options\n\n def print_manual(self):\n from httpie.output.ui import man_pages\n\n if man_pages.is_available(self.env.program_name):\n man_pages.display_for(self.env, self.env.program_name)\n return None\n\n text = self.format_help()\n with self.env.rich_console.pager():\n self.env.rich_console.print(\n text,\n highlight=False\n )\n\n def print_usage(self, file):\n from rich.text import Text\n from httpie.output.ui import rich_help\n\n whitelist = set()\n _, exception, _ = sys.exc_info()\n if (\n isinstance(exception, argparse.ArgumentError)\n and len(exception.args) >= 1\n and isinstance(exception.args[0], argparse.Action)\n and exception.args[0].option_strings\n ):\n # add_usage path is also taken when you pass an invalid option,\n # e.g --style=invalid. If something like that happens, we want\n # to include to action that caused to the invalid usage into\n # the list of actions we are displaying.\n whitelist.add(exception.args[0].option_strings[0])\n\n usage_text = Text('usage', style='bold')\n usage_text.append(':\\n ')\n usage_text.append(rich_help.to_usage(self.spec, whitelist=whitelist))\n self.env.rich_error_console.print(usage_text)\n\n def error(self, message):\n \"\"\"Prints a usage message incorporating the message to stderr and\n exits.\"\"\"\n self.print_usage(sys.stderr)\n self.env.rich_error_console.print(\n dedent(\n f'''\n [bold]error[/bold]:\n {message}\n\n [bold]for more information[/bold]:\n run '{self.prog} --help' or visit https://httpie.io/docs/cli\n '''.rstrip()\n )\n )\n self.exit(2)\n\n\n\nFile: httpie/cli/dicts.py\n\nfrom collections import OrderedDict\n\nfrom multidict import MultiDict, CIMultiDict\n\n\nclass BaseMultiDict(MultiDict):\n \"\"\"\n Base class for all MultiDicts.\n \"\"\"\n\n\nclass HTTPHeadersDict(CIMultiDict, BaseMultiDict):\n \"\"\"\n Headers are case-insensitive and multiple values are supported\n through the `add()` API.\n \"\"\"\n\n def add(self, key, value):\n \"\"\"\n Add or update a new header.\n\n If the given `value` is `None`, then all the previous\n values will be overwritten and the value will be set\n to `None`.\n \"\"\"\n if value is None:\n self[key] = value\n return None\n\n # If the previous value for the given header is `None`\n # then discard it since we are explicitly giving a new\n # value for it.\n if key in self and self.getone(key) is None:\n self.popone(key)\n\n super().add(key, value)\n\n def remove_item(self, key, value):\n \"\"\"\n Remove a (key, value) pair from the dict.\n \"\"\"\n existing_values = self.popall(key)\n existing_values.remove(value)\n\n for value in existing_values:\n self.add(key, value)\n\n\nclass RequestJSONDataDict(OrderedDict):\n pass\n\n\nclass MultiValueOrderedDict(OrderedDict):\n \"\"\"Multi-value dict for URL parameters and form data.\"\"\"\n\n def __setitem__(self, key, value):\n \"\"\"\n If `key` is assigned more than once, `self[key]` holds a\n `list` of all the values.\n\n This allows having multiple fields with the same name in form\n data and URL params.\n\n \"\"\"\n assert not isinstance(value, list)\n if key not in self:\n super().__setitem__(key, value)\n else:\n if not isinstance(self[key], list):\n super().__setitem__(key, [self[key]])\n self[key].append(value)\n\n def items(self):\n for key, values in super().items():\n if not isinstance(values, list):\n values = [values]\n for value in values:\n yield key, value\n\n\nclass RequestQueryParamsDict(MultiValueOrderedDict):\n pass\n\n\nclass RequestDataDict(MultiValueOrderedDict):\n pass\n\n\nclass MultipartRequestDataDict(MultiValueOrderedDict):\n pass\n\n\nclass RequestFilesDict(RequestDataDict):\n pass\n\n\n\nFile: httpie/cli/nested_json/interpret.py\n\nfrom typing import Type, Union, Any, Iterable, Tuple\n\nfrom .parse import parse, assert_cant_happen\nfrom .errors import NestedJSONSyntaxError\nfrom .tokens import EMPTY_STRING, TokenKind, Token, PathAction, Path, NestedJSONArray\n\n\n__all__ = [\n 'interpret_nested_json',\n 'unwrap_top_level_list_if_needed',\n]\n\nJSONType = Type[Union[dict, list, int, float, str]]\nJSON_TYPE_MAPPING = {\n dict: 'object',\n list: 'array',\n int: 'number',\n float: 'number',\n str: 'string',\n}\n\n\ndef interpret_nested_json(pairs: Iterable[Tuple[str, str]]) -> dict:\n context = None\n for key, value in pairs:\n context = interpret(context, key, value)\n return wrap_with_dict(context)\n\n\ndef interpret(context: Any, key: str, value: Any) -> Any:\n cursor = context\n paths = list(parse(key))\n paths.append(Path(PathAction.SET, value))\n\n # noinspection PyShadowingNames\n def type_check(index: int, path: Path, expected_type: JSONType):\n if not isinstance(cursor, expected_type):\n if path.tokens:\n pseudo_token = Token(\n kind=TokenKind.PSEUDO,\n value='',\n start=path.tokens[0].start,\n end=path.tokens[-1].end,\n )\n else:\n pseudo_token = None\n cursor_type = JSON_TYPE_MAPPING.get(type(cursor), type(cursor).__name__)\n required_type = JSON_TYPE_MAPPING[expected_type]\n message = f'Cannot perform {path.kind.to_string()!r} based access on '\n message += repr(''.join(path.reconstruct() for path in paths[:index]))\n message += f' which has a type of {cursor_type!r} but this operation'\n message += f' requires a type of {required_type!r}.'\n raise NestedJSONSyntaxError(\n source=key,\n token=pseudo_token,\n message=message,\n message_kind='Type',\n )\n\n def object_for(kind: PathAction) -> Any:\n if kind is PathAction.KEY:\n return {}\n elif kind in {PathAction.INDEX, PathAction.APPEND}:\n return []\n else:\n assert_cant_happen()\n\n for index, (path, next_path) in enumerate(zip(paths, paths[1:])):\n # If there is no context yet, set it.\n if cursor is None:\n context = cursor = object_for(path.kind)\n if path.kind is PathAction.KEY:\n type_check(index, path, dict)\n if next_path.kind is PathAction.SET:\n cursor[path.accessor] = next_path.accessor\n break\n cursor = cursor.setdefault(path.accessor, object_for(next_path.kind))\n elif path.kind is PathAction.INDEX:\n type_check(index, path, list)\n if path.accessor < 0:\n raise NestedJSONSyntaxError(\n source=key,\n token=path.tokens[1],\n message='Negative indexes are not supported.',\n message_kind='Value',\n )\n cursor.extend([None] * (path.accessor - len(cursor) + 1))\n if next_path.kind is PathAction.SET:\n cursor[path.accessor] = next_path.accessor\n break\n if cursor[path.accessor] is None:\n cursor[path.accessor] = object_for(next_path.kind)\n cursor = cursor[path.accessor]\n elif path.kind is PathAction.APPEND:\n type_check(index, path, list)\n if next_path.kind is PathAction.SET:\n cursor.append(next_path.accessor)\n break\n cursor.append(object_for(next_path.kind))\n cursor = cursor[-1]\n else:\n assert_cant_happen()\n\n return context\n\n\ndef wrap_with_dict(context):\n if context is None:\n return {}\n elif isinstance(context, list):\n return {\n EMPTY_STRING: NestedJSONArray(context),\n }\n else:\n assert isinstance(context, dict)\n return context\n\n\ndef unwrap_top_level_list_if_needed(data: dict):\n \"\"\"\n Propagate the top-level list, if that’s what we got.\n\n \"\"\"\n if len(data) == 1:\n key, value = list(data.items())[0]\n if isinstance(value, NestedJSONArray):\n assert key == EMPTY_STRING\n return value\n return data\n\n\n\nFile: httpie/cli/nested_json/__init__.py\n\n\"\"\"\nA library for parsing the HTTPie nested JSON key syntax and constructing the resulting objects.\n\n<https://httpie.io/docs/cli/nested-json>\n\nIt has no dependencies.\n\n\"\"\"\nfrom .interpret import interpret_nested_json, unwrap_top_level_list_if_needed\nfrom .errors import NestedJSONSyntaxError\nfrom .tokens import EMPTY_STRING, NestedJSONArray\n\n\n__all__ = [\n 'interpret_nested_json',\n 'unwrap_top_level_list_if_needed',\n 'EMPTY_STRING',\n 'NestedJSONArray',\n 'NestedJSONSyntaxError'\n]\n\n\n\nFile: httpie/cli/nested_json/tokens.py\n\nfrom enum import Enum, auto\nfrom typing import NamedTuple, Union, Optional, List\n\nEMPTY_STRING = ''\nHIGHLIGHTER = '^'\nOPEN_BRACKET = '['\nCLOSE_BRACKET = ']'\nBACKSLASH = '\\\\'\n\n\nclass TokenKind(Enum):\n TEXT = auto()\n NUMBER = auto()\n LEFT_BRACKET = auto()\n RIGHT_BRACKET = auto()\n PSEUDO = auto() # Not a real token, use when representing location only.\n\n def to_name(self) -> str:\n for key, value in OPERATORS.items():\n if value is self:\n return repr(key)\n else:\n return 'a ' + self.name.lower()\n\n\nOPERATORS = {\n OPEN_BRACKET: TokenKind.LEFT_BRACKET,\n CLOSE_BRACKET: TokenKind.RIGHT_BRACKET,\n}\nSPECIAL_CHARS = OPERATORS.keys() | {BACKSLASH}\nLITERAL_TOKENS = [\n TokenKind.TEXT,\n TokenKind.NUMBER,\n]\n\n\nclass Token(NamedTuple):\n kind: TokenKind\n value: Union[str, int]\n start: int\n end: int\n\n\nclass PathAction(Enum):\n KEY = auto()\n INDEX = auto()\n APPEND = auto()\n # Pseudo action, used by the interpreter\n SET = auto()\n\n def to_string(self) -> str:\n return self.name.lower()\n\n\nclass Path:\n def __init__(\n self,\n kind: PathAction,\n accessor: Optional[Union[str, int]] = None,\n tokens: Optional[List[Token]] = None,\n is_root: bool = False,\n ):\n self.kind = kind\n self.accessor = accessor\n self.tokens = tokens or []\n self.is_root = is_root\n\n def reconstruct(self) -> str:\n if self.kind is PathAction.KEY:\n if self.is_root:\n return str(self.accessor)\n return OPEN_BRACKET + self.accessor + CLOSE_BRACKET\n elif self.kind is PathAction.INDEX:\n return OPEN_BRACKET + str(self.accessor) + CLOSE_BRACKET\n elif self.kind is PathAction.APPEND:\n return OPEN_BRACKET + CLOSE_BRACKET\n\n\nclass NestedJSONArray(list):\n \"\"\"Denotes a top-level JSON array.\"\"\"\n\n\n\nFile: httpie/cli/nested_json/errors.py\n\nfrom typing import Optional\n\nfrom .tokens import Token, HIGHLIGHTER\n\n\nclass NestedJSONSyntaxError(ValueError):\n def __init__(\n self,\n source: str,\n token: Optional[Token],\n message: str,\n message_kind: str = 'Syntax',\n ) -> None:\n self.source = source\n self.token = token\n self.message = message\n self.message_kind = message_kind\n\n def __str__(self):\n lines = [f'HTTPie {self.message_kind} Error: {self.message}']\n if self.token is not None:\n lines.append(self.source)\n lines.append(\n ' ' * self.token.start\n + HIGHLIGHTER * (self.token.end - self.token.start)\n )\n return '\\n'.join(lines)\n\n\n\nFile: httpie/cli/nested_json/parse.py\n\nfrom typing import Iterator\n\nfrom .errors import NestedJSONSyntaxError\nfrom .tokens import (\n EMPTY_STRING,\n BACKSLASH,\n TokenKind,\n OPERATORS,\n SPECIAL_CHARS,\n LITERAL_TOKENS,\n Token,\n PathAction,\n Path,\n)\n\n\n__all__ = [\n 'parse',\n 'assert_cant_happen',\n]\n\n\ndef parse(source: str) -> Iterator[Path]:\n \"\"\"\n start: root_path path*\n root_path: (literal | index_path | append_path)\n literal: TEXT | NUMBER\n\n path:\n key_path\n | index_path\n | append_path\n key_path: LEFT_BRACKET TEXT RIGHT_BRACKET\n index_path: LEFT_BRACKET NUMBER RIGHT_BRACKET\n append_path: LEFT_BRACKET RIGHT_BRACKET\n\n \"\"\"\n\n tokens = list(tokenize(source))\n cursor = 0\n\n def can_advance():\n return cursor < len(tokens)\n\n # noinspection PyShadowingNames\n def expect(*kinds):\n nonlocal cursor\n assert kinds\n if can_advance():\n token = tokens[cursor]\n cursor += 1\n if token.kind in kinds:\n return token\n elif tokens:\n token = tokens[-1]._replace(\n start=tokens[-1].end + 0,\n end=tokens[-1].end + 1,\n )\n else:\n token = None\n if len(kinds) == 1:\n suffix = kinds[0].to_name()\n else:\n suffix = ', '.join(kind.to_name() for kind in kinds[:-1])\n suffix += ' or ' + kinds[-1].to_name()\n message = f'Expecting {suffix}'\n raise NestedJSONSyntaxError(source, token, message)\n\n # noinspection PyShadowingNames\n def parse_root():\n tokens = []\n if not can_advance():\n return Path(\n kind=PathAction.KEY,\n accessor=EMPTY_STRING,\n is_root=True\n )\n # (literal | index_path | append_path)?\n token = expect(*LITERAL_TOKENS, TokenKind.LEFT_BRACKET)\n tokens.append(token)\n if token.kind in LITERAL_TOKENS:\n action = PathAction.KEY\n value = str(token.value)\n elif token.kind is TokenKind.LEFT_BRACKET:\n token = expect(TokenKind.NUMBER, TokenKind.RIGHT_BRACKET)\n tokens.append(token)\n if token.kind is TokenKind.NUMBER:\n action = PathAction.INDEX\n value = token.value\n tokens.append(expect(TokenKind.RIGHT_BRACKET))\n elif token.kind is TokenKind.RIGHT_BRACKET:\n action = PathAction.APPEND\n value = None\n else:\n assert_cant_happen()\n else:\n assert_cant_happen()\n # noinspection PyUnboundLocalVariable\n return Path(\n kind=action,\n accessor=value,\n tokens=tokens,\n is_root=True\n )\n\n yield parse_root()\n\n # path*\n while can_advance():\n path_tokens = [expect(TokenKind.LEFT_BRACKET)]\n token = expect(TokenKind.TEXT, TokenKind.NUMBER, TokenKind.RIGHT_BRACKET)\n path_tokens.append(token)\n if token.kind is TokenKind.RIGHT_BRACKET:\n path = Path(PathAction.APPEND, tokens=path_tokens)\n elif token.kind is TokenKind.TEXT:\n path = Path(PathAction.KEY, token.value, tokens=path_tokens)\n path_tokens.append(expect(TokenKind.RIGHT_BRACKET))\n elif token.kind is TokenKind.NUMBER:\n path = Path(PathAction.INDEX, token.value, tokens=path_tokens)\n path_tokens.append(expect(TokenKind.RIGHT_BRACKET))\n else:\n assert_cant_happen()\n # noinspection PyUnboundLocalVariable\n yield path\n\n\ndef tokenize(source: str) -> Iterator[Token]:\n cursor = 0\n backslashes = 0\n buffer = []\n\n def send_buffer() -> Iterator[Token]:\n nonlocal backslashes\n if not buffer:\n return None\n\n value = ''.join(buffer)\n kind = TokenKind.TEXT\n if not backslashes:\n for variation, kind in [\n (int, TokenKind.NUMBER),\n (check_escaped_int, TokenKind.TEXT),\n ]:\n try:\n value = variation(value)\n except ValueError:\n continue\n else:\n break\n yield Token(\n kind=kind,\n value=value,\n start=cursor - (len(buffer) + backslashes),\n end=cursor,\n )\n buffer.clear()\n backslashes = 0\n\n def can_advance() -> bool:\n return cursor < len(source)\n\n while can_advance():\n index = source[cursor]\n if index in OPERATORS:\n yield from send_buffer()\n yield Token(OPERATORS[index], index, cursor, cursor + 1)\n elif index == BACKSLASH and can_advance():\n if source[cursor + 1] in SPECIAL_CHARS:\n backslashes += 1\n else:\n buffer.append(index)\n buffer.append(source[cursor + 1])\n cursor += 1\n else:\n buffer.append(index)\n cursor += 1\n\n yield from send_buffer()\n\n\ndef check_escaped_int(value: str) -> str:\n if not value.startswith(BACKSLASH):\n raise ValueError('Not an escaped int')\n try:\n int(value[1:])\n except ValueError as exc:\n raise ValueError('Not an escaped int') from exc\n else:\n return value[1:]\n\n\ndef assert_cant_happen():\n raise ValueError('Unexpected value')\n\n\n\nFile: httpie/manager/compat.py\n\nimport sys\nimport shutil\nimport subprocess\n\nfrom contextlib import suppress\nfrom typing import List, Optional\nfrom httpie.compat import is_frozen\n\n\nclass PipError(Exception):\n \"\"\"An exception that occurs when pip exits with an error status code.\"\"\"\n\n def __init__(self, stdout, stderr):\n self.stdout = stdout\n self.stderr = stderr\n\n\ndef _discover_system_pip() -> List[str]:\n # When we are running inside of a frozen binary, we need the system\n # pip to install plugins since there is no way for us to execute any\n # code outside of the HTTPie.\n #\n # We explicitly depend on system pip, so the SystemError should not\n # be executed (except for broken installations).\n def _check_pip_version(pip_location: Optional[str]) -> bool:\n if not pip_location:\n return False\n\n with suppress(subprocess.CalledProcessError):\n stdout = subprocess.check_output([pip_location, \"--version\"], text=True)\n return \"python 3\" in stdout\n\n targets = [\n \"pip\",\n \"pip3\"\n ]\n for target in targets:\n pip_location = shutil.which(target)\n if _check_pip_version(pip_location):\n return pip_location\n\n raise SystemError(\"Couldn't find 'pip' executable. Please ensure that pip in your system is available.\")\n\n\ndef _run_pip_subprocess(pip_executable: List[str], args: List[str]) -> bytes:\n\n cmd = [*pip_executable, *args]\n try:\n process = subprocess.run(\n cmd,\n check=True,\n shell=False,\n stdout=subprocess.PIPE,\n stderr=subprocess.PIPE\n )\n except subprocess.CalledProcessError as error:\n raise PipError(error.stdout, error.stderr) from error\n else:\n return process.stdout\n\n\ndef run_pip(args: List[str]) -> bytes:\n if is_frozen:\n pip_executable = [_discover_system_pip()]\n else:\n pip_executable = [sys.executable, '-m', 'pip']\n\n return _run_pip_subprocess(pip_executable, args)\n\n\n\nFile: httpie/manager/__init__.py\n\n\n\n\nFile: httpie/manager/core.py\n\nimport argparse\nfrom typing import Optional\n\nfrom httpie.context import Environment\nfrom httpie.status import ExitStatus\nfrom httpie.manager.cli import missing_subcommand, parser\nfrom httpie.manager.tasks import CLI_TASKS\n\nMSG_COMMAND_CONFUSION = '''\\\nThis command is only for managing HTTPie plugins.\nTo send a request, please use the http/https commands:\n\n $ http {args}\n\n $ https {args}\n'''\n\n# noinspection PyStringFormat\nMSG_NAKED_INVOCATION = f'''\\\n{missing_subcommand()}\n\n{MSG_COMMAND_CONFUSION}\n'''.rstrip(\"\\n\").format(args='POST pie.dev/post hello=world')\n\n\ndef dispatch_cli_task(env: Environment, action: Optional[str], args: argparse.Namespace) -> ExitStatus:\n if action is None:\n parser.error(missing_subcommand('cli'))\n\n return CLI_TASKS[action](env, args)\n\n\ndef program(args: argparse.Namespace, env: Environment) -> ExitStatus:\n if args.action is None:\n parser.error(MSG_NAKED_INVOCATION)\n\n if args.action == 'plugins':\n return dispatch_cli_task(env, args.action, args)\n elif args.action == 'cli':\n return dispatch_cli_task(env, args.cli_action, args)\n\n return ExitStatus.SUCCESS\n\n\n\nFile: httpie/manager/cli.py\n\nfrom textwrap import dedent\nfrom httpie.cli.argparser import HTTPieManagerArgumentParser\nfrom httpie.cli.options import Qualifiers, ARGPARSE_QUALIFIER_MAP, map_qualifiers, parser_to_parser_spec\nfrom httpie import __version__\n\nCLI_SESSION_UPGRADE_FLAGS = [\n {\n 'flags': ['--bind-cookies'],\n 'action': 'store_true',\n 'default': False,\n 'help': 'Bind domainless cookies to the host that session belongs.'\n }\n]\n\nCOMMANDS = {\n 'cli': {\n 'help': 'Manage HTTPie for Terminal',\n 'export-args': [\n 'Export available options for the CLI',\n {\n 'flags': ['-f', '--format'],\n 'choices': ['json'],\n 'help': 'Format to export in.',\n 'default': 'json'\n }\n ],\n 'check-updates': [\n 'Check for updates'\n ],\n 'sessions': {\n 'help': 'Manage HTTPie sessions',\n 'upgrade': [\n 'Upgrade the given HTTPie session with the latest '\n 'layout. A list of changes between different session versions '\n 'can be found in the official documentation.',\n {\n 'dest': 'hostname',\n 'metavar': 'HOSTNAME',\n 'help': 'The host this session belongs.'\n },\n {\n 'dest': 'session',\n 'metavar': 'SESSION_NAME_OR_PATH',\n 'help': 'The name or the path for the session that will be upgraded.'\n },\n *CLI_SESSION_UPGRADE_FLAGS\n ],\n 'upgrade-all': [\n 'Upgrade all named sessions with the latest layout. A list of '\n 'changes between different session versions can be found in the official '\n 'documentation.',\n *CLI_SESSION_UPGRADE_FLAGS\n ],\n }\n }\n}\n\n\nCOMMANDS['plugins'] = COMMANDS['cli']['plugins'] = {\n 'help': 'Manage HTTPie plugins.',\n 'install': [\n 'Install the given targets from PyPI '\n 'or from a local paths.',\n {\n 'dest': 'targets',\n 'metavar': 'TARGET',\n 'nargs': Qualifiers.ONE_OR_MORE,\n 'help': 'targets to install'\n }\n ],\n 'upgrade': [\n 'Upgrade the given plugins',\n {\n 'dest': 'targets',\n 'metavar': 'TARGET',\n 'nargs': Qualifiers.ONE_OR_MORE,\n 'help': 'targets to upgrade'\n }\n ],\n 'uninstall': [\n 'Uninstall the given HTTPie plugins.',\n {\n 'dest': 'targets',\n 'metavar': 'TARGET',\n 'nargs': Qualifiers.ONE_OR_MORE,\n 'help': 'targets to install'\n }\n ],\n 'list': [\n 'List all installed HTTPie plugins.'\n ],\n}\n\n\ndef missing_subcommand(*args) -> str:\n base = COMMANDS\n for arg in args:\n base = base[arg]\n\n assert isinstance(base, dict)\n subcommands = ', '.join(map(repr, base.keys()))\n return f'Please specify one of these: {subcommands}'\n\n\ndef generate_subparsers(root, parent_parser, definitions, spec):\n action_dest = '_'.join(parent_parser.prog.split()[1:] + ['action'])\n actions = parent_parser.add_subparsers(\n dest=action_dest\n )\n for command, properties in definitions.items():\n is_subparser = isinstance(properties, dict)\n properties = properties.copy()\n\n descr = properties.pop('help', None) if is_subparser else properties.pop(0)\n command_parser = actions.add_parser(command, description=descr)\n command_parser.root = root\n if is_subparser:\n generate_subparsers(root, command_parser, properties, spec)\n continue\n\n group = spec.add_group(parent_parser.prog + ' ' + command, description=descr)\n for argument in properties:\n argument = argument.copy()\n flags = argument.pop('flags', [])\n command_parser.add_argument(*flags, **map_qualifiers(argument, ARGPARSE_QUALIFIER_MAP))\n group.add_argument(*flags, **argument)\n\n\nparser = HTTPieManagerArgumentParser(\n prog='httpie',\n description=dedent(\n '''\n Managing interface for the HTTPie itself. <https://httpie.io/docs#manager>\n\n Be aware that you might be looking for http/https commands for sending\n HTTP requests. This command is only available for managing the HTTTPie\n plugins and the configuration around it.\n '''\n ),\n)\n\nparser.add_argument(\n '--debug',\n action='store_true',\n default=False,\n help='''\n Prints the exception traceback should one occur, as well as other\n information useful for debugging HTTPie itself and for reporting bugs.\n\n '''\n)\n\nparser.add_argument(\n '--traceback',\n action='store_true',\n default=False,\n help='''\n Prints the exception traceback should one occur.\n\n '''\n)\n\nparser.add_argument(\n '--version',\n action='version',\n version=__version__,\n help='''\n Show version and exit.\n\n '''\n)\n\nman_page_hint = '''\nIf you are looking for the man pages of http/https commands, try one of the following:\n $ man http\n $ man https\n\n'''\n\noptions = parser_to_parser_spec(parser, man_page_hint=man_page_hint, source_file=__file__)\ngenerate_subparsers(parser, parser, COMMANDS, options)\n\n\n\nFile: httpie/manager/__main__.py\n\nimport argparse\nimport sys\n\nfrom typing import List, Union\n\nfrom httpie.context import Environment\nfrom httpie.status import ExitStatus\nfrom httpie.manager.cli import parser\nfrom httpie.manager.core import MSG_COMMAND_CONFUSION, program as main_program\n\n\ndef is_http_command(args: List[Union[str, bytes]], env: Environment) -> bool:\n \"\"\"Check whether http/https parser can parse the arguments.\"\"\"\n\n from httpie.cli.definition import parser as http_parser\n from httpie.manager.cli import COMMANDS\n\n # If the user already selected a top-level sub-command, never\n # show the http/https version. E.g httpie plugins pie.dev/post\n if len(args) >= 1 and args[0] in COMMANDS:\n return False\n\n with env.as_silent():\n try:\n http_parser.parse_args(env=env, args=args)\n except (Exception, SystemExit):\n return False\n else:\n return True\n\n\ndef main(args: List[Union[str, bytes]] = sys.argv, env: Environment = Environment()) -> ExitStatus:\n from httpie.core import raw_main\n\n try:\n return raw_main(\n parser=parser,\n main_program=main_program,\n args=args,\n env=env,\n use_default_options=False,\n )\n except argparse.ArgumentError:\n program_args = args[1:]\n if is_http_command(program_args, env):\n env.stderr.write(MSG_COMMAND_CONFUSION.format(args=' '.join(program_args)) + \"\\n\")\n\n return ExitStatus.ERROR\n\n\ndef program():\n try:\n exit_status = main()\n except KeyboardInterrupt:\n exit_status = ExitStatus.ERROR_CTRL_C\n\n return exit_status\n\n\nif __name__ == '__main__': # pragma: nocover\n sys.exit(program())\n\n\n\nFile: httpie/manager/tasks/plugins.py\n\nimport argparse\nimport os\nimport textwrap\nimport re\nimport shutil\nfrom collections import defaultdict\nfrom contextlib import suppress\nfrom pathlib import Path\nfrom typing import List, Optional, Tuple\n\nfrom httpie.manager.compat import PipError, run_pip\nfrom httpie.manager.cli import parser, missing_subcommand\nfrom httpie.compat import get_dist_name, importlib_metadata\nfrom httpie.context import Environment\nfrom httpie.status import ExitStatus\nfrom httpie.utils import get_site_paths\n\nPEP_503 = re.compile(r\"[-_.]+\")\n\n\nclass PluginInstaller:\n\n def __init__(self, env: Environment, debug: bool = False) -> None:\n self.env = env\n self.dir = env.config.plugins_dir\n self.debug = debug\n\n self.setup_plugins_dir()\n\n def setup_plugins_dir(self) -> None:\n try:\n self.dir.mkdir(\n exist_ok=True,\n parents=True\n )\n except OSError:\n self.env.stderr.write(\n f'Couldn\\'t create \"{self.dir!s}\"'\n ' directory for plugin installation.'\n ' Please re-check the permissions for that directory,'\n ' and if needed, allow write-access.'\n )\n raise\n\n def fail(\n self,\n command: str,\n target: Optional[str] = None,\n reason: Optional[str] = None\n ) -> ExitStatus:\n message = f'Can\\'t {command}'\n if target:\n message += f' {target!r}'\n if reason:\n message += f': {reason}'\n\n self.env.stderr.write(message + '\\n')\n return ExitStatus.ERROR\n\n def _install(self, targets: List[str], mode='install') -> Tuple[\n bytes, ExitStatus\n ]:\n pip_args = [\n 'install',\n '--prefer-binary',\n f'--prefix={self.dir}',\n '--no-warn-script-location',\n ]\n if mode == 'upgrade':\n pip_args.append('--upgrade')\n pip_args.extend(targets)\n\n try:\n stdout = run_pip(pip_args)\n except PipError as pip_error:\n error = pip_error\n stdout = pip_error.stdout\n else:\n error = None\n\n self.env.stdout.write(stdout.decode())\n\n if error:\n reason = None\n if error.stderr:\n stderr = error.stderr.decode()\n\n if self.debug:\n self.env.stderr.write('Command failed: ')\n self.env.stderr.write('pip ' + ' '.join(pip_args) + '\\n')\n self.env.stderr.write(textwrap.indent(' ', stderr))\n\n last_line = stderr.strip().splitlines()[-1]\n severity, _, message = last_line.partition(': ')\n if severity == 'ERROR':\n reason = message\n\n stdout = error.stdout\n exit_status = self.fail(mode, ', '.join(targets), reason)\n else:\n exit_status = ExitStatus.SUCCESS\n\n return stdout, exit_status\n\n def install(self, targets: List[str]) -> ExitStatus:\n self.env.stdout.write(f\"Installing {', '.join(targets)}...\\n\")\n self.env.stdout.flush()\n _, exit_status = self._install(targets)\n return exit_status\n\n def _clear_metadata(self, targets: List[str]) -> None:\n # Due to an outstanding pip problem[0], we have to get rid of\n # existing metadata for old versions manually.\n # [0]: https://github.com/pypa/pip/issues/10727\n result_deps = defaultdict(list)\n for site_dir in get_site_paths(self.dir):\n for child in site_dir.iterdir():\n if child.suffix in {'.dist-info', '.egg-info'}:\n name, _, version = child.stem.rpartition('-')\n result_deps[name].append((version, child))\n\n for target in targets:\n name, _, version = target.rpartition('-')\n name = PEP_503.sub(\"-\", name).lower().replace('-', '_')\n if name not in result_deps:\n continue\n\n for result_version, meta_path in result_deps[name]:\n if version != result_version:\n shutil.rmtree(meta_path)\n\n def upgrade(self, targets: List[str]) -> ExitStatus:\n self.env.stdout.write(f\"Upgrading {', '.join(targets)}...\\n\")\n self.env.stdout.flush()\n\n raw_stdout, exit_status = self._install(\n targets,\n mode='upgrade'\n )\n if not raw_stdout:\n return exit_status\n\n stdout = raw_stdout.decode()\n installation_line = stdout.splitlines()[-1]\n if installation_line.startswith('Successfully installed'):\n self._clear_metadata(installation_line.split()[2:])\n\n def _uninstall(self, target: str) -> Optional[ExitStatus]:\n try:\n distribution = importlib_metadata.distribution(target)\n except importlib_metadata.PackageNotFoundError:\n return self.fail('uninstall', target, 'package is not installed')\n\n base_dir = Path(distribution.locate_file('.')).resolve()\n if self.dir not in base_dir.parents:\n # If the package is installed somewhere else (e.g on the site packages\n # of the real python interpreter), than that means this package is not\n # installed through us.\n return self.fail('uninstall', target,\n 'package is not installed through httpie plugins'\n ' interface')\n\n files = distribution.files\n if files is None:\n return self.fail('uninstall', target, 'couldn\\'t locate the package')\n\n # TODO: Consider handling failures here (e.g if it fails,\n # just revert the operation and leave the site-packages\n # in a proper shape).\n for file in files:\n with suppress(FileNotFoundError):\n os.unlink(distribution.locate_file(file))\n\n metadata_path = getattr(distribution, '_path', None)\n if (\n metadata_path\n and metadata_path.exists()\n and not any(metadata_path.iterdir())\n ):\n metadata_path.rmdir()\n\n self.env.stdout.write(f'Successfully uninstalled {target}\\n')\n\n def uninstall(self, targets: List[str]) -> ExitStatus:\n # Unfortunately uninstall doesn't work with custom pip schemes. See:\n # - https://github.com/pypa/pip/issues/5595\n # - https://github.com/pypa/pip/issues/4575\n # so we have to implement our own uninstalling logic. Which works\n # on top of the importlib_metadata.\n\n exit_code = ExitStatus.SUCCESS\n for target in targets:\n exit_code |= self._uninstall(target) or ExitStatus.SUCCESS\n return ExitStatus(exit_code)\n\n def list(self) -> None:\n from httpie.plugins.registry import plugin_manager\n\n known_plugins = defaultdict(list)\n\n for entry_point in plugin_manager.iter_entry_points(self.dir):\n ep_info = (entry_point.group, entry_point.name)\n ep_name = get_dist_name(entry_point) or entry_point.module\n known_plugins[ep_name].append(ep_info)\n\n for plugin, entry_points in known_plugins.items():\n self.env.stdout.write(plugin)\n\n version = importlib_metadata.version(plugin)\n if version is not None:\n self.env.stdout.write(f' ({version})')\n self.env.stdout.write('\\n')\n\n for group, entry_point in sorted(entry_points):\n self.env.stdout.write(f' {entry_point} ({group})\\n')\n\n def run(\n self,\n action: Optional[str],\n args: argparse.Namespace,\n ) -> ExitStatus:\n from httpie.plugins.manager import enable_plugins\n\n if action is None:\n parser.error(missing_subcommand('plugins'))\n\n with enable_plugins(self.dir):\n if action == 'install':\n status = self.install(args.targets)\n elif action == 'upgrade':\n status = self.upgrade(args.targets)\n elif action == 'uninstall':\n status = self.uninstall(args.targets)\n elif action == 'list':\n status = self.list()\n\n return status or ExitStatus.SUCCESS\n\n\ndef cli_plugins(env: Environment, args: argparse.Namespace) -> ExitStatus:\n plugins = PluginInstaller(env, debug=args.debug)\n\n try:\n action = args.cli_plugins_action\n except AttributeError:\n action = args.plugins_action\n\n return plugins.run(action, args)\n\n\n\nFile: httpie/manager/tasks/sessions.py\n\nimport argparse\n\nfrom httpie.sessions import SESSIONS_DIR_NAME, get_httpie_session\nfrom httpie.status import ExitStatus\nfrom httpie.context import Environment\nfrom httpie.legacy import v3_1_0_session_cookie_format, v3_2_0_session_header_format\nfrom httpie.manager.cli import missing_subcommand, parser\nfrom httpie.utils import is_version_greater\n\n\nFIXERS_TO_VERSIONS = {\n '3.1.0': v3_1_0_session_cookie_format.fix_layout,\n '3.2.0': v3_2_0_session_header_format.fix_layout,\n}\n\n\ndef cli_sessions(env: Environment, args: argparse.Namespace) -> ExitStatus:\n action = args.cli_sessions_action\n if action is None:\n parser.error(missing_subcommand('cli', 'sessions'))\n\n if action == 'upgrade':\n return cli_upgrade_session(env, args)\n elif action == 'upgrade-all':\n return cli_upgrade_all_sessions(env, args)\n else:\n raise ValueError(f'Unexpected action: {action}')\n\n\ndef upgrade_session(env: Environment, args: argparse.Namespace, hostname: str, session_name: str):\n session = get_httpie_session(\n env=env,\n config_dir=env.config.directory,\n session_name=session_name,\n host=hostname,\n url=hostname,\n suppress_legacy_warnings=True\n )\n\n session_name = session.path.stem\n if session.is_new():\n env.log_error(f'{session_name!r} @ {hostname!r} does not exist.')\n return ExitStatus.ERROR\n\n fixers = [\n fixer\n for version, fixer in FIXERS_TO_VERSIONS.items()\n if is_version_greater(version, session.version)\n ]\n\n if len(fixers) == 0:\n env.stdout.write(f'{session_name!r} @ {hostname!r} is already up to date.\\n')\n return ExitStatus.SUCCESS\n\n for fixer in fixers:\n fixer(session, hostname, args)\n\n session.save(bump_version=True)\n env.stdout.write(f'Upgraded {session_name!r} @ {hostname!r} to v{session.version}\\n')\n return ExitStatus.SUCCESS\n\n\ndef cli_upgrade_session(env: Environment, args: argparse.Namespace) -> ExitStatus:\n return upgrade_session(\n env,\n args=args,\n hostname=args.hostname,\n session_name=args.session\n )\n\n\ndef cli_upgrade_all_sessions(env: Environment, args: argparse.Namespace) -> ExitStatus:\n session_dir_path = env.config_dir / SESSIONS_DIR_NAME\n\n status = ExitStatus.SUCCESS\n for host_path in session_dir_path.iterdir():\n hostname = host_path.name\n for session_path in host_path.glob(\"*.json\"):\n session_name = session_path.stem\n status |= upgrade_session(\n env,\n args=args,\n hostname=hostname,\n session_name=session_name\n )\n return status\n\n\n\nFile: httpie/manager/tasks/export_args.py\n\nimport argparse\nimport json\n\nfrom httpie.cli.definition import options\nfrom httpie.cli.options import to_data\nfrom httpie.output.writer import write_raw_data\nfrom httpie.status import ExitStatus\nfrom httpie.context import Environment\n\n\nFORMAT_TO_CONTENT_TYPE = {\n 'json': 'application/json'\n}\n\n\ndef cli_export_args(env: Environment, args: argparse.Namespace) -> ExitStatus:\n if args.format == 'json':\n data = json.dumps(to_data(options))\n else:\n raise NotImplementedError(f'Unexpected format value: {args.format}')\n\n write_raw_data(\n env,\n data,\n stream_kwargs={'mime_overwrite': FORMAT_TO_CONTENT_TYPE[args.format]},\n )\n return ExitStatus.SUCCESS\n\n\n\nFile: httpie/manager/tasks/__init__.py\n\nfrom httpie.manager.tasks.sessions import cli_sessions\nfrom httpie.manager.tasks.export_args import cli_export_args\nfrom httpie.manager.tasks.plugins import cli_plugins\nfrom httpie.manager.tasks.check_updates import cli_check_updates\n\nCLI_TASKS = {\n 'sessions': cli_sessions,\n 'export-args': cli_export_args,\n 'plugins': cli_plugins,\n 'check-updates': cli_check_updates\n}\n\n\n\nFile: httpie/manager/tasks/check_updates.py\n\nimport argparse\nfrom httpie.context import Environment\nfrom httpie.status import ExitStatus\nfrom httpie.internal.update_warnings import fetch_updates, get_update_status\n\n\ndef cli_check_updates(env: Environment, args: argparse.Namespace) -> ExitStatus:\n fetch_updates(env, lazy=False)\n env.stdout.write(get_update_status(env))\n return ExitStatus.SUCCESS\n\n\n\nFile: extras/packaging/linux/build.py\n\nimport stat\nimport subprocess\nfrom pathlib import Path\nfrom typing import Iterator, Tuple\n\nBUILD_DIR = Path(__file__).parent\nHTTPIE_DIR = BUILD_DIR.parent.parent.parent\n\nEXTRAS_DIR = HTTPIE_DIR / 'extras'\nMAN_PAGES_DIR = EXTRAS_DIR / 'man'\n\nSCRIPT_DIR = BUILD_DIR / Path('scripts')\nHOOKS_DIR = SCRIPT_DIR / 'hooks'\n\nDIST_DIR = BUILD_DIR / 'dist'\n\nTARGET_SCRIPTS = {\n SCRIPT_DIR / 'http_cli.py': [],\n SCRIPT_DIR / 'httpie_cli.py': ['--hidden-import=pip'],\n}\n\n\ndef build_binaries() -> Iterator[Tuple[str, Path]]:\n for target_script, extra_args in TARGET_SCRIPTS.items():\n subprocess.check_call(\n [\n 'pyinstaller',\n '--onefile',\n '--noupx',\n '-p',\n HTTPIE_DIR,\n '--additional-hooks-dir',\n HOOKS_DIR,\n *extra_args,\n target_script,\n ]\n )\n\n for executable_path in DIST_DIR.iterdir():\n if executable_path.suffix:\n continue\n stat_r = executable_path.stat()\n executable_path.chmod(stat_r.st_mode | stat.S_IEXEC)\n yield executable_path.stem, executable_path\n\n\ndef build_packages(http_binary: Path, httpie_binary: Path) -> None:\n import httpie\n\n # Mapping of src_file -> dst_file\n files = [\n (http_binary, '/usr/bin/http'),\n (http_binary, '/usr/bin/https'),\n (httpie_binary, '/usr/bin/httpie'),\n ]\n files.extend(\n (man_page, f'/usr/share/man/man1/{man_page.name}')\n for man_page in MAN_PAGES_DIR.glob('*.1')\n )\n\n # A list of additional dependencies\n deps = [\n 'python3 >= 3.7',\n 'python3-pip'\n ]\n\n processed_deps = [\n f'--depends={dep}'\n for dep in deps\n ]\n processed_files = [\n '='.join([str(src.resolve()), dst]) for src, dst in files\n ]\n for target in ['deb', 'rpm']:\n subprocess.check_call(\n [\n 'fpm',\n '--force',\n '-s',\n 'dir',\n '-t',\n target,\n '--name',\n 'httpie',\n '--version',\n httpie.__version__,\n '--description',\n httpie.__doc__.strip(),\n '--license',\n httpie.__licence__,\n *processed_deps,\n *processed_files,\n ],\n cwd=DIST_DIR,\n )\n\n\ndef main():\n binaries = dict(build_binaries())\n build_packages(binaries['http_cli'], binaries['httpie_cli'])\n\n # Rename http_cli/httpie_cli to http/httpie\n binaries['http_cli'].rename(DIST_DIR / 'http')\n binaries['httpie_cli'].rename(DIST_DIR / 'httpie')\n\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: extras/packaging/linux/scripts/httpie_cli.py\n\nfrom httpie.manager.__main__ import main\n\nif __name__ == '__main__':\n import sys\n sys.exit(main())\n\n\n\nFile: extras/packaging/linux/scripts/http_cli.py\n\nfrom httpie.__main__ import main\n\nif __name__ == '__main__':\n import sys\n sys.exit(main())\n\n\n\nFile: extras/packaging/linux/scripts/hooks/hook-pip.py\n\nfrom pathlib import Path\nfrom PyInstaller.utils.hooks import collect_all\n\ndef hook(hook_api):\n for pkg in [\n 'pip',\n 'setuptools',\n 'distutils',\n 'pkg_resources'\n ]:\n datas, binaries, hiddenimports = collect_all(pkg)\n hook_api.add_datas(datas)\n hook_api.add_binaries(binaries)\n hook_api.add_imports(*hiddenimports)\n\n\n\nFile: extras/profiling/run.py\n\n\"\"\"\nRun the HTTPie benchmark suite with multiple environments.\n\nThis script is configured in a way that, it will create\ntwo (or more) isolated environments and compare the *last\ncommit* of this repository with it's master.\n\n> If you didn't commit yet, it won't be showing results.\n\nYou can also pass --fresh, which would test the *last\ncommit* of this repository with a fresh copy of HTTPie\nitself. This way even if you don't have an up-to-date\nmaster branch, you can still compare it with the upstream's\nmaster.\n\nYou can also pass --complex to add 2 additional environments,\nwhich would include additional dependencies like pyOpenSSL.\n\nExamples:\n\n # Run everything as usual, and compare last commit with master\n $ python extras/profiling/run.py\n\n # Include complex environments\n $ python extras/profiling/run.py --complex\n\n # Compare against a fresh copy\n $ python extras/profiling/run.py --fresh\n\n # Compare against a custom branch of a custom repo\n $ python extras/profiling/run.py --target-repo my_repo --target-branch my_branch\n\n # Debug changes made on this script (only run benchmarks once)\n $ python extras/profiling/run.py --debug\n\"\"\"\n\nimport dataclasses\nimport shlex\nimport subprocess\nimport sys\nimport tempfile\nimport venv\nfrom argparse import ArgumentParser, FileType\nfrom contextlib import contextmanager\nfrom dataclasses import dataclass\nfrom pathlib import Path\nfrom typing import (IO, Dict, Generator, Iterable, List, Optional,\n Tuple)\n\nBENCHMARK_SCRIPT = Path(__file__).parent / 'benchmarks.py'\nCURRENT_REPO = Path(__file__).parent.parent.parent\n\nGITHUB_URL = 'https://github.com/httpie/cli.git'\nTARGET_BRANCH = 'master'\n\n# Additional dependencies for --complex\nADDITIONAL_DEPS = ('pyOpenSSL',)\n\n\ndef call(*args, **kwargs):\n kwargs.setdefault('stdout', subprocess.DEVNULL)\n return subprocess.check_call(*args, **kwargs)\n\n\nclass Environment:\n \"\"\"\n Each environment defines how to create an isolated instance\n where we could install HTTPie and run benchmarks without any\n environmental factors.\n \"\"\"\n\n @contextmanager\n def on_repo(self) -> Generator[Tuple[Path, Dict[str, str]], None, None]:\n \"\"\"\n Return the path to the python interpreter and the\n environment variables (e.g HTTPIE_COMMAND) to be\n used on the benchmarks.\n \"\"\"\n raise NotImplementedError\n\n\n@dataclass\nclass HTTPieEnvironment(Environment):\n repo_url: str\n branch: Optional[str] = None\n dependencies: Iterable[str] = ()\n\n @contextmanager\n def on_repo(self) -> Generator[Path, None, None]:\n with tempfile.TemporaryDirectory() as directory_path:\n directory = Path(directory_path)\n\n # Clone the repo\n repo_path = directory / 'httpie'\n call(\n ['git', 'clone', self.repo_url, repo_path],\n stderr=subprocess.DEVNULL,\n )\n\n if self.branch is not None:\n call(\n ['git', 'checkout', self.branch],\n cwd=repo_path,\n stderr=subprocess.DEVNULL,\n )\n\n # Prepare the environment\n venv_path = directory / '.venv'\n venv.create(venv_path, with_pip=True)\n\n # Install basic dependencies\n python = venv_path / 'bin' / 'python'\n call(\n [\n python,\n '-m',\n 'pip',\n 'install',\n 'wheel',\n 'pyperf==2.3.0',\n *self.dependencies,\n ]\n )\n\n # Create a wheel distribution of HTTPie\n call([python, 'setup.py', 'bdist_wheel'], cwd=repo_path)\n\n # Install httpie\n distribution_path = next((repo_path / 'dist').iterdir())\n call(\n [python, '-m', 'pip', 'install', distribution_path],\n cwd=repo_path,\n )\n\n http = venv_path / 'bin' / 'http'\n yield python, {'HTTPIE_COMMAND': shlex.join([str(python), str(http)])}\n\n\n@dataclass\nclass LocalCommandEnvironment(Environment):\n local_command: str\n\n @contextmanager\n def on_repo(self) -> Generator[Path, None, None]:\n yield sys.executable, {'HTTPIE_COMMAND': self.local_command}\n\n\ndef dump_results(\n results: List[str],\n file: IO[str],\n min_speed: Optional[str] = None\n) -> None:\n for result in results:\n lines = result.strip().splitlines()\n if min_speed is not None and \"hidden\" in lines[-1]:\n lines[-1] = (\n 'Some benchmarks were hidden from this list '\n 'because their timings did not change in a '\n 'significant way (change was within the error '\n 'margin ±{margin}%).'\n ).format(margin=min_speed)\n result = '\\n'.join(lines)\n\n print(result, file=file)\n print(\"\\n---\\n\", file=file)\n\n\ndef compare(*args, directory: Path, min_speed: Optional[str] = None):\n compare_args = ['pyperf', 'compare_to', '--table', '--table-format=md', *args]\n if min_speed:\n compare_args.extend(['--min-speed', min_speed])\n return subprocess.check_output(\n compare_args,\n cwd=directory,\n text=True,\n )\n\n\ndef run(\n configs: List[Dict[str, Environment]],\n file: IO[str],\n debug: bool = False,\n min_speed: Optional[str] = None,\n) -> None:\n result_directory = Path(tempfile.mkdtemp())\n results = []\n\n current = 1\n total = sum(1 for config in configs for _ in config.items())\n\n def iterate(env_name, status):\n print(\n f'Iteration: {env_name} ({current}/{total}) ({status})' + ' ' * 10,\n end='\\r',\n flush=True,\n )\n\n for config in configs:\n for env_name, env in config.items():\n iterate(env_name, 'setting up')\n with env.on_repo() as (python, env_vars):\n iterate(env_name, 'running benchmarks')\n args = [python, BENCHMARK_SCRIPT, '-o', env_name]\n if debug:\n args.append('--debug-single-value')\n call(\n args,\n cwd=result_directory,\n env=env_vars,\n )\n current += 1\n\n results.append(compare(\n *config.keys(),\n directory=result_directory,\n min_speed=min_speed\n ))\n\n dump_results(results, file=file, min_speed=min_speed)\n print('Results are available at:', result_directory)\n\n\ndef main() -> None:\n parser = ArgumentParser()\n parser.add_argument('--local-repo', default=CURRENT_REPO)\n parser.add_argument('--local-branch', default=None)\n parser.add_argument('--target-repo', default=CURRENT_REPO)\n parser.add_argument('--target-branch', default=TARGET_BRANCH)\n parser.add_argument(\n '--fresh',\n action='store_const',\n const=GITHUB_URL,\n dest='target_repo',\n help='Clone the target repo from upstream GitHub URL',\n )\n parser.add_argument(\n '--complex',\n action='store_true',\n help='Add a second run, with a complex python environment.',\n )\n parser.add_argument(\n '--local-bin',\n help='Run the suite with the given local binary in addition to'\n ' existing runners. (E.g --local-bin $(command -v xh))',\n )\n parser.add_argument(\n '--file',\n type=FileType('w'),\n default=sys.stdout,\n help='File to print the actual results',\n )\n parser.add_argument(\n '--min-speed',\n help='Minimum of speed in percent to consider that a '\n 'benchmark is significant'\n )\n parser.add_argument(\n '--debug',\n action='store_true',\n )\n\n options = parser.parse_args()\n\n configs = []\n\n base_config = {\n options.target_branch: HTTPieEnvironment(options.target_repo, options.target_branch),\n 'this_branch': HTTPieEnvironment(options.local_repo, options.local_branch),\n }\n configs.append(base_config)\n\n if options.complex:\n complex_config = {\n env_name\n + '-complex': dataclasses.replace(env, dependencies=ADDITIONAL_DEPS)\n for env_name, env in base_config.items()\n }\n configs.append(complex_config)\n\n if options.local_bin:\n base_config['binary'] = LocalCommandEnvironment(options.local_bin)\n\n run(configs, file=options.file, debug=options.debug, min_speed=options.min_speed)\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: extras/profiling/benchmarks.py\n\n\"\"\"\nThis file is the declaration of benchmarks for HTTPie. It\nis also used to run them with the current environment.\n\nEach instance of BaseRunner class will be an individual\nbenchmark. And if run without any arguments, this file\nwill execute every benchmark instance and report the\ntimings.\n\nThe benchmarks are run through 'pyperf', which allows to\ndo get very precise results. For micro-benchmarks like startup,\nplease run `pyperf system tune` to get even more accurate results.\n\nExamples:\n\n # Run everything as usual, the default is that we do 3 warm-up runs\n # and 5 actual runs.\n $ python extras/profiling/benchmarks.py\n\n # For retrieving results faster, pass --fast\n $ python extras/profiling/benchmarks.py --fast\n\n # For verify everything works as expected, pass --debug-single-value.\n # It will only run everything once, so the resuls are not reliable. But\n # very useful when iterating on a benchmark\n $ python extras/profiling/benchmarks.py --debug-single-value\n\n # If you want to run with a custom HTTPie command (for example with\n # and HTTPie instance installed in another virtual environment),\n # pass HTTPIE_COMMAND variable.\n $ HTTPIE_COMMAND=\"/my/python /my/httpie\" python extras/profiling/benchmarks.py\n\"\"\"\n\nfrom __future__ import annotations\n\nimport os\nimport shlex\nimport subprocess\nimport sys\nimport threading\nfrom contextlib import ExitStack, contextmanager\nfrom dataclasses import dataclass, field\nfrom functools import cached_property, partial\nfrom http.server import HTTPServer, SimpleHTTPRequestHandler\nfrom tempfile import TemporaryDirectory\nfrom typing import ClassVar, Final, List\n\nimport pyperf\n\n# For download benchmarks, define a set of files.\n# file: (block_size, count) => total_size = block_size * count\nPREDEFINED_FILES: Final = {'3G': (3 * 1024 ** 2, 1024)}\n\n\nclass QuietSimpleHTTPServer(SimpleHTTPRequestHandler):\n def log_message(self, *args, **kwargs):\n pass\n\n\n@contextmanager\ndef start_server():\n \"\"\"Create a server to serve local files. It will create the\n PREDEFINED_FILES through dd.\"\"\"\n with TemporaryDirectory() as directory:\n for file_name, (block_size, count) in PREDEFINED_FILES.items():\n subprocess.check_call(\n [\n 'dd',\n 'if=/dev/zero',\n f'of={file_name}',\n f'bs={block_size}',\n f'count={count}',\n ],\n cwd=directory,\n stdout=subprocess.DEVNULL,\n stderr=subprocess.DEVNULL,\n )\n\n handler = partial(QuietSimpleHTTPServer, directory=directory)\n server = HTTPServer(('localhost', 0), handler)\n\n thread = threading.Thread(target=server.serve_forever)\n thread.start()\n yield '{}:{}'.format(*server.socket.getsockname())\n server.shutdown()\n thread.join(timeout=0.5)\n\n\n@dataclass\nclass Context:\n benchmarks: ClassVar[List[BaseRunner]] = []\n stack: ExitStack = field(default_factory=ExitStack)\n runner: pyperf.Runner = field(default_factory=pyperf.Runner)\n\n def run(self) -> pyperf.BenchmarkSuite:\n results = [benchmark.run(self) for benchmark in self.benchmarks]\n return pyperf.BenchmarkSuite(results)\n\n @property\n def cmd(self) -> List[str]:\n if cmd := os.getenv('HTTPIE_COMMAND'):\n return shlex.split(cmd)\n\n http = os.path.join(os.path.dirname(sys.executable), 'http')\n assert os.path.exists(http)\n return [sys.executable, http]\n\n @cached_property\n def server(self) -> str:\n return self.stack.enter_context(start_server())\n\n def __enter__(self):\n return self\n\n def __exit__(self, *exc_info):\n self.stack.close()\n\n\n@dataclass\nclass BaseRunner:\n \"\"\"\n An individual benchmark case. By default it has the category\n (e.g like startup or download) and a name.\n \"\"\"\n\n category: str\n title: str\n\n def __post_init__(self):\n Context.benchmarks.append(self)\n\n def run(self, context: Context) -> pyperf.Benchmark:\n raise NotImplementedError\n\n @property\n def name(self) -> str:\n return f'{self.title} ({self.category})'\n\n\n@dataclass\nclass CommandRunner(BaseRunner):\n \"\"\"\n Run a single command, and benchmark it.\n \"\"\"\n\n args: List[str]\n\n def run(self, context: Context) -> pyperf.Benchmark:\n return context.runner.bench_command(self.name, [*context.cmd, *self.args])\n\n\n@dataclass\nclass DownloadRunner(BaseRunner):\n \"\"\"\n Benchmark downloading a single file from the\n remote server.\n \"\"\"\n\n file_name: str\n\n def run(self, context: Context) -> pyperf.Benchmark:\n return context.runner.bench_command(\n self.name,\n [\n *context.cmd,\n '--download',\n 'GET',\n f'{context.server}/{self.file_name}',\n ],\n )\n\n\nCommandRunner('startup', '`http --version`', ['--version'])\nCommandRunner('startup', '`http --offline pie.dev/get`', ['--offline', 'pie.dev/get'])\nfor pretty in ['all', 'none']:\n CommandRunner(\n 'startup',\n f'`http --pretty={pretty} pie.dev/stream/1000`',\n [\n '--print=HBhb',\n f'--pretty={pretty}',\n 'httpbin.org/stream/1000'\n ]\n )\nDownloadRunner('download', '`http --download :/big_file.txt` (3GB)', '3G')\n\n\ndef main() -> None:\n # PyPerf will bring it's own argument parser, so configure the script.\n # The somewhat fast and also precise enough configuration is this. We run\n # benchmarks 3 times to warm up (e.g especially for download benchmark, this\n # is important). And then 5 actual runs where we record.\n sys.argv.extend(\n ['--worker', '--loops=1', '--warmup=3', '--values=5', '--processes=2']\n )\n\n with Context() as context:\n context.run()\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: extras/scripts/generate_man_pages.py\n\nimport os\nimport re\nfrom contextlib import contextmanager\nfrom pathlib import Path\nfrom typing import Optional, Iterator, Iterable\n\n\n# So that httpie.cli.definition can provide man-page-specific output. Must be set before importing httpie.\nos.environ['HTTPIE_BUILDING_MAN_PAGES'] = '1'\n\nimport httpie\nfrom httpie.cli.definition import options as core_options, IS_MAN_PAGE\nfrom httpie.cli.options import ParserSpec\nfrom httpie.manager.cli import options as manager_options\nfrom httpie.output.ui.rich_help import OptionsHighlighter, to_usage\nfrom httpie.output.ui.rich_utils import render_as_string\n\n\nassert IS_MAN_PAGE, 'CLI definition does not understand we’re building man pages'\n\n# Escape certain characters, so they are rendered properly on all terminals.\n# <https://man7.org/linux/man-pages/man7/groff_char.7.html>\nESCAPE_MAP = {\n '\"': '\\[dq]',\n \"'\": '\\[aq]',\n '~': '\\(ti',\n '’': \"\\(ga\",\n '\\\\': '\\e',\n}\nESCAPE_MAP = {ord(key): value for key, value in ESCAPE_MAP.items()}\n\nEXTRAS_DIR = Path(__file__).parent.parent\nMAN_PAGE_PATH = EXTRAS_DIR / 'man'\nPROJECT_ROOT = EXTRAS_DIR.parent\n\nOPTION_HIGHLIGHT_RE = re.compile(\n OptionsHighlighter.highlights[0]\n)\n\n\nclass ManPageBuilder:\n def __init__(self):\n self.source = []\n\n def title_line(\n self,\n full_name: str,\n program_name: str,\n program_version: str,\n last_edit_date: str,\n ) -> None:\n self.source.append(\n f'.TH {program_name} 1 \"{last_edit_date}\" '\n f'\"{full_name} {program_version}\" \"{full_name} Manual\"'\n )\n\n def set_name(self, program_name: str) -> None:\n with self.section('NAME'):\n self.write(program_name)\n\n def write(self, text: str, *, bold: bool = False) -> None:\n if bold:\n text = '.B ' + text\n self.source.append(text)\n\n def separate(self) -> None:\n self.source.append('.PP')\n\n def format_desc(self, desc: str) -> str:\n description = _escape_and_dedent(desc)\n description = OPTION_HIGHLIGHT_RE.sub(\n # Boldify the option part, but don't remove the prefix (start of the match).\n lambda match: match[1] + self.boldify(match['option']),\n description\n )\n return description\n\n def add_comment(self, comment: str) -> None:\n self.source.append(f'.\\\\\" {comment}')\n\n def add_options(self, options: Iterable[str], *, metavar: Optional[str] = None) -> None:\n text = \", \".join(map(self.boldify, options))\n if metavar:\n text += f' {self.underline(metavar)}'\n self.write(f'.IP \"{text}\"')\n\n def build(self) -> str:\n return '\\n'.join(self.source)\n\n @contextmanager\n def section(self, section_name: str) -> Iterator[None]:\n self.write(f'.SH {section_name}')\n self.in_section = True\n yield\n self.in_section = False\n\n def underline(self, text: str) -> str:\n return r'\\fI\\,{}\\/\\fR'.format(text)\n\n def boldify(self, text: str) -> str:\n return r'\\fB\\,{}\\/\\fR'.format(text)\n\n\ndef _escape_and_dedent(text: str) -> str:\n lines = []\n for should_act, line in enumerate(text.splitlines()):\n # Only dedent after the first line.\n if should_act:\n if line.startswith(' '):\n line = line[4:]\n\n lines.append(line)\n return '\\n'.join(lines).translate(ESCAPE_MAP)\n\n\ndef to_man_page(program_name: str, spec: ParserSpec, *, is_top_level_cmd: bool = False) -> str:\n builder = ManPageBuilder()\n builder.add_comment(\n f\"This file is auto-generated from the parser declaration \"\n + (f\"in {Path(spec.source_file).relative_to(PROJECT_ROOT)} \" if spec.source_file else \"\")\n + f\"by {Path(__file__).relative_to(PROJECT_ROOT)}.\"\n )\n\n builder.title_line(\n full_name='HTTPie',\n program_name=program_name,\n program_version=httpie.__version__,\n last_edit_date=httpie.__date__,\n )\n builder.set_name(program_name)\n\n with builder.section('SYNOPSIS'):\n # `http` and `https` are commands that can be directly used, so they can have\n # a valid usage. But `httpie` is a top-level command with multiple sub commands,\n # so for the synopsis we'll only reference the `httpie` name.\n if is_top_level_cmd:\n synopsis = program_name\n else:\n synopsis = render_as_string(to_usage(spec, program_name=program_name))\n builder.write(synopsis)\n\n with builder.section('DESCRIPTION'):\n builder.write(spec.description)\n if spec.man_page_hint:\n builder.write(spec.man_page_hint)\n\n for index, group in enumerate(spec.groups, 1):\n with builder.section(group.name):\n if group.description:\n builder.write(group.description)\n\n for argument in group.arguments:\n if argument.is_hidden:\n continue\n\n raw_arg = argument.serialize(isolation_mode=True)\n\n metavar = raw_arg.get('metavar')\n if raw_arg.get('is_positional'):\n # In case of positional arguments, metavar is always equal\n # to the list of options (e.g `METHOD`).\n metavar = None\n builder.add_options(raw_arg['options'], metavar=metavar)\n\n desc = builder.format_desc(raw_arg.get('description', ''))\n builder.write('\\n' + desc + '\\n')\n\n builder.separate()\n\n if spec.epilog:\n with builder.section('SEE ALSO'):\n builder.write(builder.format_desc(spec.epilog))\n\n return builder.build()\n\n\ndef main() -> None:\n for program_name, spec, config in [\n ('http', core_options, {}),\n ('https', core_options, {}),\n ('httpie', manager_options, {'is_top_level_cmd': True}),\n ]:\n with open((MAN_PAGE_PATH / program_name).with_suffix('.1'), 'w') as stream:\n stream.write(to_man_page(program_name, spec, **config))\n\n\nif __name__ == '__main__':\n main()\n\n\n"},"repo_readme":{"kind":"string","value":"<h2 align=\"center\">\n <a href=\"https://httpie.io\" target=\"blank_\">\n <img height=\"100\" alt=\"HTTPie\" src=\"https://raw.githubusercontent.com/httpie/cli/master/docs/httpie-logo.svg\" />\n </a>\n <br>\n HTTPie CLI: human-friendly HTTP client for the API era\n</h2>\n\n<div align=\"center\">\n\n[](https://httpie.io/product)\n[](https://httpie.io/app)\n[](https://httpie.io/cli)\n[](https://twitter.com/httpie)\n[](https://httpie.io/discord)\n\n</div>\n\n\n<div align=\"center\">\n\n[](https://httpie.org/docs/cli)\n[](https://pypi.python.org/pypi/httpie)\n[](https://github.com/httpie/cli/actions)\n[](https://codecov.io/gh/httpie/cli)\n[](https://www.pepy.tech/projects/httpie)\n\n</div>\n\nHTTPie (pronounced _aitch-tee-tee-pie_) is a command-line HTTP client.\nIts goal is to make CLI interaction with web services as human-friendly as possible.\nHTTPie is designed for testing, debugging, and generally interacting with APIs & HTTP servers.\nThe `http` & `https` commands allow for creating and sending arbitrary HTTP requests.\nThey use simple and natural syntax and provide formatted and colorized output.\n\n<div align=\"center\">\n\n<img src=\"https://raw.githubusercontent.com/httpie/cli/master/docs/httpie-animation.gif\" alt=\"HTTPie in action\" width=\"100%\"/>\n\n\n</div>\n\n\n\n\n## We lost 54k GitHub stars\n\nPlease note we recently accidentally made this repo private for a moment, and GitHub deleted our community that took a decade to build. Read the full story here: https://httpie.io/blog/stardust\n\n\n\n\n## Getting started\n\n- [Installation instructions →](https://httpie.io/docs#installation)\n- [Full documentation →](https://httpie.io/docs)\n\n## Features\n\n- Expressive and intuitive syntax\n- Formatted and colorized terminal output\n- Built-in JSON support\n- Forms and file uploads\n- HTTPS, proxies, and authentication\n- Arbitrary request data\n- Custom headers\n- Persistent sessions\n- `wget`-like downloads\n\n[See all features →](https://httpie.io/docs)\n\n## Examples\n\nHello World:\n\n```bash\nhttps httpie.io/hello\n```\n\nCustom [HTTP method](https://httpie.io/docs#http-method), [HTTP headers](https://httpie.io/docs#http-headers) and [JSON](https://httpie.io/docs#json) data:\n\n```bash\nhttp PUT pie.dev/put X-API-Token:123 name=John\n```\n\nBuild and print a request without sending it using [offline mode](https://httpie.io/docs/cli/offline-mode):\n\n```bash\nhttp --offline pie.dev/post hello=offline\n```\n\nUse [GitHub API](https://developer.github.com/v3/issues/comments/#create-a-comment) to post a comment on an [Issue](https://github.com/httpie/cli/issues/83) with [authentication](https://httpie.io/docs#authentication):\n\n```bash\nhttp -a USERNAME POST https://api.github.com/repos/httpie/cli/issues/83/comments body='HTTPie is awesome! :heart:'\n```\n\n[See more examples →](https://httpie.io/docs#examples)\n\n## Community & support\n\n- Visit the [HTTPie website](https://httpie.io) for full documentation and useful links.\n- Join our [Discord server](https://httpie.io/discord) is to ask questions, discuss features, and for general API chat.\n- Tweet at [@httpie](https://twitter.com/httpie) on Twitter.\n- Use [StackOverflow](https://stackoverflow.com/questions/tagged/httpie) to ask questions and include a `httpie` tag.\n- Create [GitHub Issues](https://github.com/httpie/cli/issues) for bug reports and feature requests.\n- Subscribe to the [HTTPie newsletter](https://httpie.io) for occasional updates.\n\n## Contributing\n\nHave a look through existing [Issues](https://github.com/httpie/cli/issues) and [Pull Requests](https://github.com/httpie/cli/pulls) that you could help with. If you'd like to request a feature or report a bug, please [create a GitHub Issue](https://github.com/httpie/cli/issues) using one of the templates provided.\n\n[See contribution guide →](https://github.com/httpie/cli/blob/master/CONTRIBUTING.md)\n"}}},{"rowIdx":153,"cells":{"repo_name":{"kind":"string","value":"linux-insides"},"repo_commit":{"kind":"string","value":"0995b4bc531fcf29b4431ecf0e29aa86e66838f4"},"repo_content":{"kind":"string","value":"File: Scripts/get_all_links.py\n\n#!/usr/bin/env python\n\nfrom __future__ import print_function\nfrom socket import timeout\n\nimport os\nimport sys\nimport codecs\nimport re\n\nimport markdown\n\ntry:\n # compatible for python2\n from urllib2 import urlopen\n from urllib2 import HTTPError\n from urllib2 import URLError\nexcept ImportError:\n # compatible for python3\n from urllib.request import urlopen\n from urllib.error import HTTPError\n from urllib.error import URLError\n\ndef check_live_url(url):\n\n result = False\n try:\n ret = urlopen(url, timeout=2)\n result = (ret.code == 200)\n except HTTPError as e:\n print(e, file=sys.stderr)\n except URLError as e:\n print(e, file=sys.stderr)\n except timeout as e:\n print(e, file=sys.stderr)\n except Exception as e:\n print(e, file=sys.stderr)\n\n return result\n\n\ndef main(path):\n\n filenames = []\n for (dirpath, dnames, fnames) in os.walk(path):\n for fname in fnames:\n if fname.endswith('.md'):\n filenames.append(os.sep.join([dirpath, fname]))\n\n urls = []\n\n for filename in filenames:\n fd = codecs.open(filename, mode=\"r\", encoding=\"utf-8\")\n for line in fd.readlines():\n refs = re.findall(r'(?<=<a href=\")[^\"]*', markdown.markdown(line))\n for ref in refs:\n if ref not in urls:\n urls.append(ref)\n fd.close()\n\n for url in urls:\n if not url.startswith(\"http\"):\n print(\"markdown file name: \" + url)\n continue\n if check_live_url(url):\n print(url)\n else:\n print(url, file=sys.stderr)\n\n\nif __name__ == '__main__':\n\n if len(sys.argv) == 2:\n main(sys.argv[1])\n else:\n print(\"Choose one path as argument one\")\n\n\n"},"repo_readme":{"kind":"string","value":"linux-insides\n===============\n\nA book-in-progress about the linux kernel and its insides.\n\n**The goal is simple** - to share my modest knowledge about the insides of the linux kernel and help people who are interested in linux kernel insides, and other low-level subject matter. Feel free to go through the book [Start here](https://github.com/0xAX/linux-insides/blob/master/SUMMARY.md)\n\n**Questions/Suggestions**: Feel free about any questions or suggestions by pinging me at twitter [@0xAX](https://twitter.com/0xAX), adding an [issue](https://github.com/0xAX/linux-insides/issues/new) or just drop me an [email](mailto:anotherworldofworld@gmail.com).\n\nGenerating eBooks and PDFs - [documentation](https://github.com/GitbookIO/gitbook/blob/master/docs/ebook.md)\n\n# Mailing List\n\nWe have a Google Group mailing list for learning the kernel source code. Here are some instructions about how to use it.\n\n#### Join\n\nSend an email with any subject/content to `kernelhacking+subscribe@googlegroups.com`. Then you will receive a confirmation email. Reply it with any content and then you are done.\n\n> If you have Google account, you can also open the [archive page](https://groups.google.com/forum/#!forum/kernelhacking) and click **Apply to join group**. You will be approved automatically.\n\n#### Send emails to mailing list\n\nJust send emails to `kernelhacking@googlegroups.com`. The basic usage is the same as other mailing lists powered by mailman.\n\n#### Archives\n\nhttps://groups.google.com/forum/#!forum/kernelhacking\n\nOn other languages\n-------------------\n\n * [Brazilian Portuguese](https://github.com/mauri870/linux-insides)\n * [Chinese](https://github.com/MintCN/linux-insides-zh)\n * [Japanese](https://github.com/tkmru/linux-insides-ja)\n * [Korean](https://github.com/junsooo/linux-insides-ko)\n * [Russian](https://github.com/proninyaroslav/linux-insides-ru)\n * [Spanish](https://github.com/leolas95/linux-insides)\n * [Turkish](https://github.com/ayyucedemirbas/linux-insides_Turkish)\n\nDocker\n------\n\nIn order to run your own copy of the book with gitbook within a local container:\n\n1. Enable Docker experimental features with vim or another text editor\n ```bash\n sudo vim /usr/lib/systemd/system/docker.service\n ```\n\n Then add --experimental=true to the end of the ExecStart=/usr/bin/dockerd -H fd:// line and save.\n\n Eg: *ExecStart=/usr/bin/dockerd -H fd:// --experimental=true*\n\n Then, you need to reload and restart the Docker daemon:\n ```bash\n systemctl daemon-reload\n systemctl restart docker.service\n ```\n\n2. Run docker image\n ```bash\n make run\n ```\n\n3. Open your local copy of linux insides book under this url\n http://localhost:4000 or run `make browse`\n\n\nContributions \n--------------\n\nFeel free to create issues or pull-requests if you have any problems.\n\n**Please read [CONTRIBUTING.md](https://github.com/0xAX/linux-insides/blob/master/CONTRIBUTING.md) before pushing any changes.**\n\n\n\nAuthor\n---------------\n\n[@0xAX](https://twitter.com/0xAX)\n\nLICENSE\n-------------\n\nLicensed [BY-NC-SA Creative Commons](http://creativecommons.org/licenses/by-nc-sa/4.0/).\n"}}},{"rowIdx":154,"cells":{"repo_name":{"kind":"string","value":"examples"},"repo_commit":{"kind":"string","value":"26de41904319c7094afc53a3ee809de47112d387"},"repo_content":{"kind":"string","value":""},"repo_readme":{"kind":"string","value":"# PyTorch Examples\n\n\n\nhttps://pytorch.org/examples/\n\n`pytorch/examples` is a repository showcasing examples of using [PyTorch](https://github.com/pytorch/pytorch). The goal is to have curated, short, few/no dependencies _high quality_ examples that are substantially different from each other that can be emulated in your existing work.\n\n- For tutorials: https://github.com/pytorch/tutorials\n- For changes to pytorch.org: https://github.com/pytorch/pytorch.github.io\n- For a general model hub: https://pytorch.org/hub/ or https://huggingface.co/models\n- For recipes on how to run PyTorch in production: https://github.com/facebookresearch/recipes\n- For general Q&A and support: https://discuss.pytorch.org/\n\n## Available models\n\n- [Image classification (MNIST) using Convnets](./mnist/README.md)\n- [Word-level Language Modeling using RNN and Transformer](./word_language_model/README.md)\n- [Training Imagenet Classifiers with Popular Networks](./imagenet/README.md)\n- [Generative Adversarial Networks (DCGAN)](./dcgan/README.md)\n- [Variational Auto-Encoders](./vae/README.md)\n- [Superresolution using an efficient sub-pixel convolutional neural network](./super_resolution/README.md)\n- [Hogwild training of shared ConvNets across multiple processes on MNIST](mnist_hogwild)\n- [Training a CartPole to balance in OpenAI Gym with actor-critic](./reinforcement_learning/README.md)\n- [Natural Language Inference (SNLI) with GloVe vectors, LSTMs, and torchtext](snli)\n- [Time sequence prediction - use an LSTM to learn Sine waves](./time_sequence_prediction/README.md)\n- [Implement the Neural Style Transfer algorithm on images](./fast_neural_style/README.md)\n- [Reinforcement Learning with Actor Critic and REINFORCE algorithms on OpenAI gym](./reinforcement_learning/README.md)\n- [PyTorch Module Transformations using fx](./fx/README.md)\n- Distributed PyTorch examples with [Distributed Data Parallel](./distributed/ddp/README.md) and [RPC](./distributed/rpc)\n- [Several examples illustrating the C++ Frontend](cpp)\n- [Image Classification Using Forward-Forward](./mnist_forward_forward/README.md)\n- [Language Translation using Transformers](./language_translation/README.md)\n\n\n\nAdditionally, a list of good examples hosted in their own repositories:\n\n- [Neural Machine Translation using sequence-to-sequence RNN with attention (OpenNMT)](https://github.com/OpenNMT/OpenNMT-py)\n\n## Contributing\n\nIf you'd like to contribute your own example or fix a bug please make sure to take a look at [CONTRIBUTING.md](CONTRIBUTING.md).\n"}}},{"rowIdx":155,"cells":{"repo_name":{"kind":"string","value":"localGPT"},"repo_commit":{"kind":"string","value":"a1dea3becb8b1ae28a87369b1636c4c4a4501c27"},"repo_content":{"kind":"string","value":"File: localGPT_UI.py\n\nimport torch\nimport subprocess\nimport streamlit as st\nfrom run_localGPT import load_model\nfrom langchain.vectorstores import Chroma\nfrom constants import CHROMA_SETTINGS, EMBEDDING_MODEL_NAME, PERSIST_DIRECTORY, MODEL_ID, MODEL_BASENAME\nfrom langchain.embeddings import HuggingFaceInstructEmbeddings\nfrom langchain.chains import RetrievalQA\nfrom streamlit_extras.add_vertical_space import add_vertical_space\nfrom langchain.prompts import PromptTemplate\nfrom langchain.memory import ConversationBufferMemory\n\n\ndef model_memory():\n # Adding history to the model.\n template = \"\"\"Use the following pieces of context to answer the question at the end. If you don't know the answer,\\\n just say that you don't know, don't try to make up an answer.\n\n {context}\n\n {history}\n Question: {question}\n Helpful Answer:\"\"\"\n\n prompt = PromptTemplate(input_variables=[\"history\", \"context\", \"question\"], template=template)\n memory = ConversationBufferMemory(input_key=\"question\", memory_key=\"history\")\n\n return prompt, memory\n\n\n# Sidebar contents\nwith st.sidebar:\n st.title(\"🤗💬 Converse with your Data\")\n st.markdown(\n \"\"\"\n ## About\n This app is an LLM-powered chatbot built using:\n - [Streamlit](https://streamlit.io/)\n - [LangChain](https://python.langchain.com/)\n - [LocalGPT](https://github.com/PromtEngineer/localGPT) \n \n \"\"\"\n )\n add_vertical_space(5)\n st.write(\"Made with ❤️ by [Prompt Engineer](https://youtube.com/@engineerprompt)\")\n\n\nif torch.backends.mps.is_available():\n DEVICE_TYPE = \"mps\"\nelif torch.cuda.is_available():\n DEVICE_TYPE = \"cuda\"\nelse:\n DEVICE_TYPE = \"cpu\"\n\n\n# if \"result\" not in st.session_state:\n# # Run the document ingestion process.\n# run_langest_commands = [\"python\", \"ingest.py\"]\n# run_langest_commands.append(\"--device_type\")\n# run_langest_commands.append(DEVICE_TYPE)\n\n# result = subprocess.run(run_langest_commands, capture_output=True)\n# st.session_state.result = result\n\n# Define the retreiver\n# load the vectorstore\nif \"EMBEDDINGS\" not in st.session_state:\n EMBEDDINGS = HuggingFaceInstructEmbeddings(model_name=EMBEDDING_MODEL_NAME, model_kwargs={\"device\": DEVICE_TYPE})\n st.session_state.EMBEDDINGS = EMBEDDINGS\n\nif \"DB\" not in st.session_state:\n DB = Chroma(\n persist_directory=PERSIST_DIRECTORY,\n embedding_function=st.session_state.EMBEDDINGS,\n client_settings=CHROMA_SETTINGS,\n )\n st.session_state.DB = DB\n\nif \"RETRIEVER\" not in st.session_state:\n RETRIEVER = DB.as_retriever()\n st.session_state.RETRIEVER = RETRIEVER\n\nif \"LLM\" not in st.session_state:\n LLM = load_model(device_type=DEVICE_TYPE, model_id=MODEL_ID, model_basename=MODEL_BASENAME)\n st.session_state[\"LLM\"] = LLM\n\n\nif \"QA\" not in st.session_state:\n prompt, memory = model_memory()\n\n QA = RetrievalQA.from_chain_type(\n llm=LLM,\n chain_type=\"stuff\",\n retriever=RETRIEVER,\n return_source_documents=True,\n chain_type_kwargs={\"prompt\": prompt, \"memory\": memory},\n )\n st.session_state[\"QA\"] = QA\n\nst.title(\"LocalGPT App 💬\")\n# Create a text input box for the user\nprompt = st.text_input(\"Input your prompt here\")\n# while True:\n\n# If the user hits enter\nif prompt:\n # Then pass the prompt to the LLM\n response = st.session_state[\"QA\"](prompt)\n answer, docs = response[\"result\"], response[\"source_documents\"]\n # ...and write it out to the screen\n st.write(answer)\n\n # With a streamlit expander\n with st.expander(\"Document Similarity Search\"):\n # Find the relevant pages\n search = st.session_state.DB.similarity_search_with_score(prompt)\n # Write out the first\n for i, doc in enumerate(search):\n # print(doc)\n st.write(f\"Source Document # {i+1} : {doc[0].metadata['source'].split('/')[-1]}\")\n st.write(doc[0].page_content)\n st.write(\"--------------------------------\")\n\n\n\nFile: crawl.py\n\nimport os\nimport shutil\nimport click\nimport subprocess\n\nfrom constants import (\n DOCUMENT_MAP,\n SOURCE_DIRECTORY\n)\n\ndef logToFile(logentry):\n file1 = open(\"crawl.log\",\"a\")\n file1.write(logentry + \"\\n\")\n file1.close()\n print(logentry + \"\\n\")\n\n@click.command()\n@click.option(\n \"--device_type\",\n default=\"cuda\",\n type=click.Choice(\n [\n \"cpu\",\n \"cuda\",\n \"ipu\",\n \"xpu\",\n \"mkldnn\",\n \"opengl\",\n \"opencl\",\n \"ideep\",\n \"hip\",\n \"ve\",\n \"fpga\",\n \"ort\",\n \"xla\",\n \"lazy\",\n \"vulkan\",\n \"mps\",\n \"meta\",\n \"hpu\",\n \"mtia\",\n ],\n ),\n help=\"Device to run on. (Default is cuda)\",\n)\n@click.option(\n \"--landing_directory\",\n default=\"./LANDING_DOCUMENTS\"\n)\n@click.option(\n \"--processed_directory\",\n default=\"./PROCESSED_DOCUMENTS\"\n)\n@click.option(\n \"--error_directory\",\n default=\"./ERROR_DOCUMENTS\"\n)\n@click.option(\n \"--unsupported_directory\",\n default=\"./UNSUPPORTED_DOCUMENTS\"\n)\n\ndef main(device_type, landing_directory, processed_directory, error_directory, unsupported_directory):\n paths = []\n\n os.makedirs(processed_directory, exist_ok=True)\n os.makedirs(error_directory, exist_ok=True)\n os.makedirs(unsupported_directory, exist_ok=True)\n\n for root, _, files in os.walk(landing_directory):\n for file_name in files:\n file_extension = os.path.splitext(file_name)[1]\n short_filename = os.path.basename(file_name)\n\n if not os.path.isdir(root + \"/\" + file_name):\n if file_extension in DOCUMENT_MAP.keys():\n shutil.move(root + \"/\" + file_name, SOURCE_DIRECTORY+ \"/\" + short_filename)\n logToFile(\"START: \" + root + \"/\" + short_filename)\n process = subprocess.Popen(\"python ingest.py --device_type=\" + device_type, shell=True, stdout=subprocess.PIPE)\n process.wait()\n if process.returncode > 0:\n shutil.move(SOURCE_DIRECTORY + \"/\" + short_filename, error_directory + \"/\" + short_filename)\n logToFile(\"ERROR: \" + root + \"/\" + short_filename)\n else:\n logToFile(\"VALID: \" + root + \"/\" + short_filename)\n shutil.move(SOURCE_DIRECTORY + \"/\" + short_filename, processed_directory+ \"/\" + short_filename)\n else:\n shutil.move(root + \"/\" + file_name, unsupported_directory+ \"/\" + short_filename)\n\nif __name__ == \"__main__\":\n main()\n\n\n\nFile: ingest.py\n\nimport logging\nimport os\nfrom concurrent.futures import ProcessPoolExecutor, ThreadPoolExecutor, as_completed\n\nimport click\nimport torch\nfrom langchain.docstore.document import Document\nfrom langchain.text_splitter import Language, RecursiveCharacterTextSplitter\nfrom langchain.vectorstores import Chroma\nfrom utils import get_embeddings\n\nfrom constants import (\n CHROMA_SETTINGS,\n DOCUMENT_MAP,\n EMBEDDING_MODEL_NAME,\n INGEST_THREADS,\n PERSIST_DIRECTORY,\n SOURCE_DIRECTORY,\n)\n\n\ndef file_log(logentry):\n file1 = open(\"file_ingest.log\", \"a\")\n file1.write(logentry + \"\\n\")\n file1.close()\n print(logentry + \"\\n\")\n\n\ndef load_single_document(file_path: str) -> Document:\n # Loads a single document from a file path\n try:\n file_extension = os.path.splitext(file_path)[1]\n loader_class = DOCUMENT_MAP.get(file_extension)\n if loader_class:\n file_log(file_path + \" loaded.\")\n loader = loader_class(file_path)\n else:\n file_log(file_path + \" document type is undefined.\")\n raise ValueError(\"Document type is undefined\")\n return loader.load()[0]\n except Exception as ex:\n file_log(\"%s loading error: \\n%s\" % (file_path, ex))\n return None\n\n\ndef load_document_batch(filepaths):\n logging.info(\"Loading document batch\")\n # create a thread pool\n with ThreadPoolExecutor(len(filepaths)) as exe:\n # load files\n futures = [exe.submit(load_single_document, name) for name in filepaths]\n # collect data\n if futures is None:\n file_log(name + \" failed to submit\")\n return None\n else:\n data_list = [future.result() for future in futures]\n # return data and file paths\n return (data_list, filepaths)\n\n\ndef load_documents(source_dir: str) -> list[Document]:\n # Loads all documents from the source documents directory, including nested folders\n paths = []\n for root, _, files in os.walk(source_dir):\n for file_name in files:\n print(\"Importing: \" + file_name)\n file_extension = os.path.splitext(file_name)[1]\n source_file_path = os.path.join(root, file_name)\n if file_extension in DOCUMENT_MAP.keys():\n paths.append(source_file_path)\n\n # Have at least one worker and at most INGEST_THREADS workers\n n_workers = min(INGEST_THREADS, max(len(paths), 1))\n chunksize = round(len(paths) / n_workers)\n docs = []\n with ProcessPoolExecutor(n_workers) as executor:\n futures = []\n # split the load operations into chunks\n for i in range(0, len(paths), chunksize):\n # select a chunk of filenames\n filepaths = paths[i : (i + chunksize)]\n # submit the task\n try:\n future = executor.submit(load_document_batch, filepaths)\n except Exception as ex:\n file_log(\"executor task failed: %s\" % (ex))\n future = None\n if future is not None:\n futures.append(future)\n # process all results\n for future in as_completed(futures):\n # open the file and load the data\n try:\n contents, _ = future.result()\n docs.extend(contents)\n except Exception as ex:\n file_log(\"Exception: %s\" % (ex))\n\n return docs\n\n\ndef split_documents(documents: list[Document]) -> tuple[list[Document], list[Document]]:\n # Splits documents for correct Text Splitter\n text_docs, python_docs = [], []\n for doc in documents:\n if doc is not None:\n file_extension = os.path.splitext(doc.metadata[\"source\"])[1]\n if file_extension == \".py\":\n python_docs.append(doc)\n else:\n text_docs.append(doc)\n return text_docs, python_docs\n\n\n@click.command()\n@click.option(\n \"--device_type\",\n default=\"cuda\" if torch.cuda.is_available() else \"cpu\",\n type=click.Choice(\n [\n \"cpu\",\n \"cuda\",\n \"ipu\",\n \"xpu\",\n \"mkldnn\",\n \"opengl\",\n \"opencl\",\n \"ideep\",\n \"hip\",\n \"ve\",\n \"fpga\",\n \"ort\",\n \"xla\",\n \"lazy\",\n \"vulkan\",\n \"mps\",\n \"meta\",\n \"hpu\",\n \"mtia\",\n ],\n ),\n help=\"Device to run on. (Default is cuda)\",\n)\ndef main(device_type):\n # Load documents and split in chunks\n logging.info(f\"Loading documents from {SOURCE_DIRECTORY}\")\n documents = load_documents(SOURCE_DIRECTORY)\n text_documents, python_documents = split_documents(documents)\n text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)\n python_splitter = RecursiveCharacterTextSplitter.from_language(\n language=Language.PYTHON, chunk_size=880, chunk_overlap=200\n )\n texts = text_splitter.split_documents(text_documents)\n texts.extend(python_splitter.split_documents(python_documents))\n logging.info(f\"Loaded {len(documents)} documents from {SOURCE_DIRECTORY}\")\n logging.info(f\"Split into {len(texts)} chunks of text\")\n\n \"\"\"\n (1) Chooses an appropriate langchain library based on the enbedding model name. Matching code is contained within fun_localGPT.py.\n \n (2) Provides additional arguments for instructor and BGE models to improve results, pursuant to the instructions contained on\n their respective huggingface repository, project page or github repository.\n \"\"\"\n\n embeddings = get_embeddings(device_type)\n\n logging.info(f\"Loaded embeddings from {EMBEDDING_MODEL_NAME}\")\n\n db = Chroma.from_documents(\n texts,\n embeddings,\n persist_directory=PERSIST_DIRECTORY,\n client_settings=CHROMA_SETTINGS,\n )\n\n\nif __name__ == \"__main__\":\n logging.basicConfig(\n format=\"%(asctime)s - %(levelname)s - %(filename)s:%(lineno)s - %(message)s\", level=logging.INFO\n )\n main()\n\n\n\nFile: prompt_template_utils.py\n\n\"\"\"\nThis file implements prompt template for llama based models. \nModify the prompt template based on the model you select. \nThis seems to have significant impact on the output of the LLM.\n\"\"\"\n\nfrom langchain.memory import ConversationBufferMemory\nfrom langchain.prompts import PromptTemplate\n\n# this is specific to Llama-2.\n\nsystem_prompt = \"\"\"You are a helpful assistant, you will use the provided context to answer user questions.\nRead the given context before answering questions and think step by step. If you can not answer a user question based on \nthe provided context, inform the user. Do not use any other information for answering user. Provide a detailed answer to the question.\"\"\"\n\n\ndef get_prompt_template(system_prompt=system_prompt, promptTemplate_type=None, history=False):\n if promptTemplate_type == \"llama\":\n B_INST, E_INST = \"[INST]\", \"[/INST]\"\n B_SYS, E_SYS = \"<<SYS>>\\n\", \"\\n<</SYS>>\\n\\n\"\n SYSTEM_PROMPT = B_SYS + system_prompt + E_SYS\n if history:\n instruction = \"\"\"\n Context: {history} \\n {context}\n User: {question}\"\"\"\n\n prompt_template = B_INST + SYSTEM_PROMPT + instruction + E_INST\n prompt = PromptTemplate(input_variables=[\"history\", \"context\", \"question\"], template=prompt_template)\n else:\n instruction = \"\"\"\n Context: {context}\n User: {question}\"\"\"\n\n prompt_template = B_INST + SYSTEM_PROMPT + instruction + E_INST\n prompt = PromptTemplate(input_variables=[\"context\", \"question\"], template=prompt_template)\n\n elif promptTemplate_type == \"llama3\":\n\n B_INST, E_INST = \"<|start_header_id|>user<|end_header_id|>\", \"<|eot_id|>\"\n B_SYS, E_SYS = \"<|begin_of_text|><|start_header_id|>system<|end_header_id|> \", \"<|eot_id|>\"\n ASSISTANT_INST = \"<|start_header_id|>assistant<|end_header_id|>\"\n SYSTEM_PROMPT = B_SYS + system_prompt + E_SYS\n if history:\n instruction = \"\"\"\n Context: {history} \\n {context}\n User: {question}\"\"\"\n\n prompt_template = SYSTEM_PROMPT + B_INST + instruction + ASSISTANT_INST\n prompt = PromptTemplate(input_variables=[\"history\", \"context\", \"question\"], template=prompt_template)\n else:\n instruction = \"\"\"\n Context: {context}\n User: {question}\"\"\"\n\n prompt_template = SYSTEM_PROMPT + B_INST + instruction + ASSISTANT_INST\n prompt = PromptTemplate(input_variables=[\"context\", \"question\"], template=prompt_template)\n\n elif promptTemplate_type == \"mistral\":\n B_INST, E_INST = \"<s>[INST] \", \" [/INST]\"\n if history:\n prompt_template = (\n B_INST\n + system_prompt\n + \"\"\"\n \n Context: {history} \\n {context}\n User: {question}\"\"\"\n + E_INST\n )\n prompt = PromptTemplate(input_variables=[\"history\", \"context\", \"question\"], template=prompt_template)\n else:\n prompt_template = (\n B_INST\n + system_prompt\n + \"\"\"\n \n Context: {context}\n User: {question}\"\"\"\n + E_INST\n )\n prompt = PromptTemplate(input_variables=[\"context\", \"question\"], template=prompt_template)\n else:\n # change this based on the model you have selected.\n if history:\n prompt_template = (\n system_prompt\n + \"\"\"\n \n Context: {history} \\n {context}\n User: {question}\n Answer:\"\"\"\n )\n prompt = PromptTemplate(input_variables=[\"history\", \"context\", \"question\"], template=prompt_template)\n else:\n prompt_template = (\n system_prompt\n + \"\"\"\n \n Context: {context}\n User: {question}\n Answer:\"\"\"\n )\n prompt = PromptTemplate(input_variables=[\"context\", \"question\"], template=prompt_template)\n\n memory = ConversationBufferMemory(input_key=\"question\", memory_key=\"history\")\n\n print(f\"Here is the prompt used: {prompt}\")\n\n return (\n prompt,\n memory,\n )\n\n\n\nFile: run_localGPT.py\n\nimport os\nimport logging\nimport click\nimport torch\nimport utils\nfrom langchain.chains import RetrievalQA\nfrom langchain.embeddings import HuggingFaceInstructEmbeddings\nfrom langchain.llms import HuggingFacePipeline\nfrom langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler # for streaming response\nfrom langchain.callbacks.manager import CallbackManager\n\ncallback_manager = CallbackManager([StreamingStdOutCallbackHandler()])\n\nfrom prompt_template_utils import get_prompt_template\nfrom utils import get_embeddings\n\n# from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler\nfrom langchain.vectorstores import Chroma\nfrom transformers import (\n GenerationConfig,\n pipeline,\n)\n\nfrom load_models import (\n load_quantized_model_awq,\n load_quantized_model_gguf_ggml,\n load_quantized_model_qptq,\n load_full_model,\n)\n\nfrom constants import (\n EMBEDDING_MODEL_NAME,\n PERSIST_DIRECTORY,\n MODEL_ID,\n MODEL_BASENAME,\n MAX_NEW_TOKENS,\n MODELS_PATH,\n CHROMA_SETTINGS,\n)\n\n\ndef load_model(device_type, model_id, model_basename=None, LOGGING=logging):\n \"\"\"\n Select a model for text generation using the HuggingFace library.\n If you are running this for the first time, it will download a model for you.\n subsequent runs will use the model from the disk.\n\n Args:\n device_type (str): Type of device to use, e.g., \"cuda\" for GPU or \"cpu\" for CPU.\n model_id (str): Identifier of the model to load from HuggingFace's model hub.\n model_basename (str, optional): Basename of the model if using quantized models.\n Defaults to None.\n\n Returns:\n HuggingFacePipeline: A pipeline object for text generation using the loaded model.\n\n Raises:\n ValueError: If an unsupported model or device type is provided.\n \"\"\"\n logging.info(f\"Loading Model: {model_id}, on: {device_type}\")\n logging.info(\"This action can take a few minutes!\")\n\n if model_basename is not None:\n if \".gguf\" in model_basename.lower():\n llm = load_quantized_model_gguf_ggml(model_id, model_basename, device_type, LOGGING)\n return llm\n elif \".ggml\" in model_basename.lower():\n model, tokenizer = load_quantized_model_gguf_ggml(model_id, model_basename, device_type, LOGGING)\n elif \".awq\" in model_basename.lower():\n model, tokenizer = load_quantized_model_awq(model_id, LOGGING)\n else:\n model, tokenizer = load_quantized_model_qptq(model_id, model_basename, device_type, LOGGING)\n else:\n model, tokenizer = load_full_model(model_id, model_basename, device_type, LOGGING)\n\n # Load configuration from the model to avoid warnings\n generation_config = GenerationConfig.from_pretrained(model_id)\n # see here for details:\n # https://huggingface.co/docs/transformers/\n # main_classes/text_generation#transformers.GenerationConfig.from_pretrained.returns\n\n # Create a pipeline for text generation\n pipe = pipeline(\n \"text-generation\",\n model=model,\n tokenizer=tokenizer,\n max_length=MAX_NEW_TOKENS,\n temperature=0.2,\n # top_p=0.95,\n repetition_penalty=1.15,\n generation_config=generation_config,\n )\n\n local_llm = HuggingFacePipeline(pipeline=pipe)\n logging.info(\"Local LLM Loaded\")\n\n return local_llm\n\n\ndef retrieval_qa_pipline(device_type, use_history, promptTemplate_type=\"llama\"):\n \"\"\"\n Initializes and returns a retrieval-based Question Answering (QA) pipeline.\n\n This function sets up a QA system that retrieves relevant information using embeddings\n from the HuggingFace library. It then answers questions based on the retrieved information.\n\n Parameters:\n - device_type (str): Specifies the type of device where the model will run, e.g., 'cpu', 'cuda', etc.\n - use_history (bool): Flag to determine whether to use chat history or not.\n\n Returns:\n - RetrievalQA: An initialized retrieval-based QA system.\n\n Notes:\n - The function uses embeddings from the HuggingFace library, either instruction-based or regular.\n - The Chroma class is used to load a vector store containing pre-computed embeddings.\n - The retriever fetches relevant documents or data based on a query.\n - The prompt and memory, obtained from the `get_prompt_template` function, might be used in the QA system.\n - The model is loaded onto the specified device using its ID and basename.\n - The QA system retrieves relevant documents using the retriever and then answers questions based on those documents.\n \"\"\"\n\n \"\"\"\n (1) Chooses an appropriate langchain library based on the enbedding model name. Matching code is contained within ingest.py.\n \n (2) Provides additional arguments for instructor and BGE models to improve results, pursuant to the instructions contained on\n their respective huggingface repository, project page or github repository.\n \"\"\"\n\n embeddings = get_embeddings(device_type)\n\n logging.info(f\"Loaded embeddings from {EMBEDDING_MODEL_NAME}\")\n\n # load the vectorstore\n db = Chroma(persist_directory=PERSIST_DIRECTORY, embedding_function=embeddings, client_settings=CHROMA_SETTINGS)\n retriever = db.as_retriever()\n\n # get the prompt template and memory if set by the user.\n prompt, memory = get_prompt_template(promptTemplate_type=promptTemplate_type, history=use_history)\n\n # load the llm pipeline\n llm = load_model(device_type, model_id=MODEL_ID, model_basename=MODEL_BASENAME, LOGGING=logging)\n\n if use_history:\n qa = RetrievalQA.from_chain_type(\n llm=llm,\n chain_type=\"stuff\", # try other chains types as well. refine, map_reduce, map_rerank\n retriever=retriever,\n return_source_documents=True, # verbose=True,\n callbacks=callback_manager,\n chain_type_kwargs={\"prompt\": prompt, \"memory\": memory},\n )\n else:\n qa = RetrievalQA.from_chain_type(\n llm=llm,\n chain_type=\"stuff\", # try other chains types as well. refine, map_reduce, map_rerank\n retriever=retriever,\n return_source_documents=True, # verbose=True,\n callbacks=callback_manager,\n chain_type_kwargs={\n \"prompt\": prompt,\n },\n )\n\n return qa\n\n\n# chose device typ to run on as well as to show source documents.\n@click.command()\n@click.option(\n \"--device_type\",\n default=\"cuda\" if torch.cuda.is_available() else \"cpu\",\n type=click.Choice(\n [\n \"cpu\",\n \"cuda\",\n \"ipu\",\n \"xpu\",\n \"mkldnn\",\n \"opengl\",\n \"opencl\",\n \"ideep\",\n \"hip\",\n \"ve\",\n \"fpga\",\n \"ort\",\n \"xla\",\n \"lazy\",\n \"vulkan\",\n \"mps\",\n \"meta\",\n \"hpu\",\n \"mtia\",\n ],\n ),\n help=\"Device to run on. (Default is cuda)\",\n)\n@click.option(\n \"--show_sources\",\n \"-s\",\n is_flag=True,\n help=\"Show sources along with answers (Default is False)\",\n)\n@click.option(\n \"--use_history\",\n \"-h\",\n is_flag=True,\n help=\"Use history (Default is False)\",\n)\n@click.option(\n \"--model_type\",\n default=\"llama3\",\n type=click.Choice(\n [\"llama3\", \"llama\", \"mistral\", \"non_llama\"],\n ),\n help=\"model type, llama3, llama, mistral or non_llama\",\n)\n@click.option(\n \"--save_qa\",\n is_flag=True,\n help=\"whether to save Q&A pairs to a CSV file (Default is False)\",\n)\ndef main(device_type, show_sources, use_history, model_type, save_qa):\n \"\"\"\n Implements the main information retrieval task for a localGPT.\n\n This function sets up the QA system by loading the necessary embeddings, vectorstore, and LLM model.\n It then enters an interactive loop where the user can input queries and receive answers. Optionally,\n the source documents used to derive the answers can also be displayed.\n\n Parameters:\n - device_type (str): Specifies the type of device where the model will run, e.g., 'cpu', 'mps', 'cuda', etc.\n - show_sources (bool): Flag to determine whether to display the source documents used for answering.\n - use_history (bool): Flag to determine whether to use chat history or not.\n\n Notes:\n - Logging information includes the device type, whether source documents are displayed, and the use of history.\n - If the models directory does not exist, it creates a new one to store models.\n - The user can exit the interactive loop by entering \"exit\".\n - The source documents are displayed if the show_sources flag is set to True.\n\n \"\"\"\n\n logging.info(f\"Running on: {device_type}\")\n logging.info(f\"Display Source Documents set to: {show_sources}\")\n logging.info(f\"Use history set to: {use_history}\")\n\n # check if models directory do not exist, create a new one and store models here.\n if not os.path.exists(MODELS_PATH):\n os.mkdir(MODELS_PATH)\n\n qa = retrieval_qa_pipline(device_type, use_history, promptTemplate_type=model_type)\n # Interactive questions and answers\n while True:\n query = input(\"\\nEnter a query: \")\n if query == \"exit\":\n break\n # Get the answer from the chain\n res = qa(query)\n answer, docs = res[\"result\"], res[\"source_documents\"]\n\n # Print the result\n print(\"\\n\\n> Question:\")\n print(query)\n print(\"\\n> Answer:\")\n print(answer)\n\n if show_sources: # this is a flag that you can set to disable showing answers.\n # # Print the relevant sources used for the answer\n print(\"----------------------------------SOURCE DOCUMENTS---------------------------\")\n for document in docs:\n print(\"\\n> \" + document.metadata[\"source\"] + \":\")\n print(document.page_content)\n print(\"----------------------------------SOURCE DOCUMENTS---------------------------\")\n\n # Log the Q&A to CSV only if save_qa is True\n if save_qa:\n utils.log_to_csv(query, answer)\n\n\nif __name__ == \"__main__\":\n logging.basicConfig(\n format=\"%(asctime)s - %(levelname)s - %(filename)s:%(lineno)s - %(message)s\", level=logging.INFO\n )\n main()\n\n\n\nFile: constants.py\n\nimport os\n\n# from dotenv import load_dotenv\nfrom chromadb.config import Settings\n\n# https://python.langchain.com/en/latest/modules/indexes/document_loaders/examples/excel.html?highlight=xlsx#microsoft-excel\nfrom langchain.document_loaders import CSVLoader, PDFMinerLoader, TextLoader, UnstructuredExcelLoader, Docx2txtLoader\nfrom langchain.document_loaders import UnstructuredFileLoader, UnstructuredMarkdownLoader\nfrom langchain.document_loaders import UnstructuredHTMLLoader\n\n\n# load_dotenv()\nROOT_DIRECTORY = os.path.dirname(os.path.realpath(__file__))\n\n# Define the folder for storing database\nSOURCE_DIRECTORY = f\"{ROOT_DIRECTORY}/SOURCE_DOCUMENTS\"\n\nPERSIST_DIRECTORY = f\"{ROOT_DIRECTORY}/DB\"\n\nMODELS_PATH = \"./models\"\n\n# Can be changed to a specific number\nINGEST_THREADS = os.cpu_count() or 8\n\n# Define the Chroma settings\nCHROMA_SETTINGS = Settings(\n anonymized_telemetry=False,\n is_persistent=True,\n)\n\n# Context Window and Max New Tokens\nCONTEXT_WINDOW_SIZE = 8096\nMAX_NEW_TOKENS = CONTEXT_WINDOW_SIZE # int(CONTEXT_WINDOW_SIZE/4)\n\n#### If you get a \"not enough space in the buffer\" error, you should reduce the values below, start with half of the original values and keep halving the value until the error stops appearing\n\nN_GPU_LAYERS = 100 # Llama-2-70B has 83 layers\nN_BATCH = 512\n\n### From experimenting with the Llama-2-7B-Chat-GGML model on 8GB VRAM, these values work:\n# N_GPU_LAYERS = 20\n# N_BATCH = 512\n\n\n# https://python.langchain.com/en/latest/_modules/langchain/document_loaders/excel.html#UnstructuredExcelLoader\nDOCUMENT_MAP = {\n \".html\": UnstructuredHTMLLoader,\n \".txt\": TextLoader,\n \".md\": UnstructuredMarkdownLoader,\n \".py\": TextLoader,\n # \".pdf\": PDFMinerLoader,\n \".pdf\": UnstructuredFileLoader,\n \".csv\": CSVLoader,\n \".xls\": UnstructuredExcelLoader,\n \".xlsx\": UnstructuredExcelLoader,\n \".docx\": Docx2txtLoader,\n \".doc\": Docx2txtLoader,\n}\n\n# Default Instructor Model\nEMBEDDING_MODEL_NAME = \"hkunlp/instructor-large\" # Uses 1.5 GB of VRAM (High Accuracy with lower VRAM usage)\n\n####\n#### OTHER EMBEDDING MODEL OPTIONS\n####\n\n# EMBEDDING_MODEL_NAME = \"hkunlp/instructor-xl\" # Uses 5 GB of VRAM (Most Accurate of all models)\n# EMBEDDING_MODEL_NAME = \"intfloat/e5-large-v2\" # Uses 1.5 GB of VRAM (A little less accurate than instructor-large)\n# EMBEDDING_MODEL_NAME = \"intfloat/e5-base-v2\" # Uses 0.5 GB of VRAM (A good model for lower VRAM GPUs)\n# EMBEDDING_MODEL_NAME = \"all-MiniLM-L6-v2\" # Uses 0.2 GB of VRAM (Less accurate but fastest - only requires 150mb of vram)\n\n####\n#### MULTILINGUAL EMBEDDING MODELS\n####\n\n# EMBEDDING_MODEL_NAME = \"intfloat/multilingual-e5-large\" # Uses 2.5 GB of VRAM\n# EMBEDDING_MODEL_NAME = \"intfloat/multilingual-e5-base\" # Uses 1.2 GB of VRAM\n\n\n#### SELECT AN OPEN SOURCE LLM (LARGE LANGUAGE MODEL)\n# Select the Model ID and model_basename\n# load the LLM for generating Natural Language responses\n\n#### GPU VRAM Memory required for LLM Models (ONLY) by Billion Parameter value (B Model)\n#### Does not include VRAM used by Embedding Models - which use an additional 2GB-7GB of VRAM depending on the model.\n####\n#### (B Model) (float32) (float16) (GPTQ 8bit) (GPTQ 4bit)\n#### 7b 28 GB 14 GB 7 GB - 9 GB 3.5 GB - 5 GB\n#### 13b 52 GB 26 GB 13 GB - 15 GB 6.5 GB - 8 GB\n#### 32b 130 GB 65 GB 32.5 GB - 35 GB 16.25 GB - 19 GB\n#### 65b 260.8 GB 130.4 GB 65.2 GB - 67 GB 32.6 GB - - 35 GB\n\n# MODEL_ID = \"TheBloke/Llama-2-7B-Chat-GGML\"\n# MODEL_BASENAME = \"llama-2-7b-chat.ggmlv3.q4_0.bin\"\n\n####\n#### (FOR GGUF MODELS)\n####\n\n# MODEL_ID = \"TheBloke/Llama-2-13b-Chat-GGUF\"\n# MODEL_BASENAME = \"llama-2-13b-chat.Q4_K_M.gguf\"\n\n# MODEL_ID = \"TheBloke/Llama-2-7b-Chat-GGUF\"\n# MODEL_BASENAME = \"llama-2-7b-chat.Q4_K_M.gguf\"\n\n# MODEL_ID = \"QuantFactory/Meta-Llama-3-8B-Instruct-GGUF\"\n# MODEL_BASENAME = \"Meta-Llama-3-8B-Instruct.Q4_K_M.gguf\"\n\n# LLAMA 3 # use for Apple Silicon\nMODEL_ID = \"meta-llama/Meta-Llama-3-8B-Instruct\"\nMODEL_BASENAME = None\n\n# LLAMA 3 # use for NVIDIA GPUs\n# MODEL_ID = \"unsloth/llama-3-8b-bnb-4bit\"\n# MODEL_BASENAME = None\n\n# MODEL_ID = \"TheBloke/Mistral-7B-Instruct-v0.1-GGUF\"\n# MODEL_BASENAME = \"mistral-7b-instruct-v0.1.Q8_0.gguf\"\n\n# MODEL_ID = \"TheBloke/Llama-2-70b-Chat-GGUF\"\n# MODEL_BASENAME = \"llama-2-70b-chat.Q4_K_M.gguf\"\n\n####\n#### (FOR HF MODELS)\n####\n\n# MODEL_ID = \"NousResearch/Llama-2-7b-chat-hf\"\n# MODEL_BASENAME = None\n# MODEL_ID = \"TheBloke/vicuna-7B-1.1-HF\"\n# MODEL_BASENAME = None\n# MODEL_ID = \"TheBloke/Wizard-Vicuna-7B-Uncensored-HF\"\n# MODEL_ID = \"TheBloke/guanaco-7B-HF\"\n# MODEL_ID = 'NousResearch/Nous-Hermes-13b' # Requires ~ 23GB VRAM. Using STransformers\n# alongside will 100% create OOM on 24GB cards.\n# llm = load_model(device_type, model_id=model_id)\n\n####\n#### (FOR GPTQ QUANTIZED) Select a llm model based on your GPU and VRAM GB. Does not include Embedding Models VRAM usage.\n####\n\n##### 48GB VRAM Graphics Cards (RTX 6000, RTX A6000 and other 48GB VRAM GPUs) #####\n\n### 65b GPTQ LLM Models for 48GB GPUs (*** With best embedding model: hkunlp/instructor-xl ***)\n# MODEL_ID = \"TheBloke/guanaco-65B-GPTQ\"\n# MODEL_BASENAME = \"model.safetensors\"\n# MODEL_ID = \"TheBloke/Airoboros-65B-GPT4-2.0-GPTQ\"\n# MODEL_BASENAME = \"model.safetensors\"\n# MODEL_ID = \"TheBloke/gpt4-alpaca-lora_mlp-65B-GPTQ\"\n# MODEL_BASENAME = \"model.safetensors\"\n# MODEL_ID = \"TheBloke/Upstage-Llama1-65B-Instruct-GPTQ\"\n# MODEL_BASENAME = \"model.safetensors\"\n\n##### 24GB VRAM Graphics Cards (RTX 3090 - RTX 4090 (35% Faster) - RTX A5000 - RTX A5500) #####\n\n### 13b GPTQ Models for 24GB GPUs (*** With best embedding model: hkunlp/instructor-xl ***)\n# MODEL_ID = \"TheBloke/Wizard-Vicuna-13B-Uncensored-GPTQ\"\n# MODEL_BASENAME = \"Wizard-Vicuna-13B-Uncensored-GPTQ-4bit-128g.compat.no-act-order.safetensors\"\n# MODEL_ID = \"TheBloke/vicuna-13B-v1.5-GPTQ\"\n# MODEL_BASENAME = \"model.safetensors\"\n# MODEL_ID = \"TheBloke/Nous-Hermes-13B-GPTQ\"\n# MODEL_BASENAME = \"nous-hermes-13b-GPTQ-4bit-128g.no-act.order\"\n# MODEL_ID = \"TheBloke/WizardLM-13B-V1.2-GPTQ\"\n# MODEL_BASENAME = \"gptq_model-4bit-128g.safetensors\n\n### 30b GPTQ Models for 24GB GPUs (*** Requires using intfloat/e5-base-v2 instead of hkunlp/instructor-large as embedding model ***)\n# MODEL_ID = \"TheBloke/Wizard-Vicuna-30B-Uncensored-GPTQ\"\n# MODEL_BASENAME = \"Wizard-Vicuna-30B-Uncensored-GPTQ-4bit--1g.act.order.safetensors\"\n# MODEL_ID = \"TheBloke/WizardLM-30B-Uncensored-GPTQ\"\n# MODEL_BASENAME = \"WizardLM-30B-Uncensored-GPTQ-4bit.act-order.safetensors\"\n\n##### 8-10GB VRAM Graphics Cards (RTX 3080 - RTX 3080 Ti - RTX 3070 Ti - 3060 Ti - RTX 2000 Series, Quadro RTX 4000, 5000, 6000) #####\n### (*** Requires using intfloat/e5-small-v2 instead of hkunlp/instructor-large as embedding model ***)\n\n### 7b GPTQ Models for 8GB GPUs\n# MODEL_ID = \"TheBloke/Wizard-Vicuna-7B-Uncensored-GPTQ\"\n# MODEL_BASENAME = \"Wizard-Vicuna-7B-Uncensored-GPTQ-4bit-128g.no-act.order.safetensors\"\n# MODEL_ID = \"TheBloke/WizardLM-7B-uncensored-GPTQ\"\n# MODEL_BASENAME = \"WizardLM-7B-uncensored-GPTQ-4bit-128g.compat.no-act-order.safetensors\"\n# MODEL_ID = \"TheBloke/wizardLM-7B-GPTQ\"\n# MODEL_BASENAME = \"wizardLM-7B-GPTQ-4bit.compat.no-act-order.safetensors\"\n\n####\n#### (FOR GGML) (Quantized cpu+gpu+mps) models - check if they support llama.cpp\n####\n\n# MODEL_ID = \"TheBloke/wizard-vicuna-13B-GGML\"\n# MODEL_BASENAME = \"wizard-vicuna-13B.ggmlv3.q4_0.bin\"\n# MODEL_BASENAME = \"wizard-vicuna-13B.ggmlv3.q6_K.bin\"\n# MODEL_BASENAME = \"wizard-vicuna-13B.ggmlv3.q2_K.bin\"\n# MODEL_ID = \"TheBloke/orca_mini_3B-GGML\"\n# MODEL_BASENAME = \"orca-mini-3b.ggmlv3.q4_0.bin\"\n\n####\n#### (FOR AWQ QUANTIZED) Select a llm model based on your GPU and VRAM GB. Does not include Embedding Models VRAM usage.\n### (*** MODEL_BASENAME is not actually used but have to contain .awq so the correct model loading is used ***)\n### (*** Compute capability 7.5 (sm75) and CUDA Toolkit 11.8+ are required ***)\n####\n# MODEL_ID = \"TheBloke/Llama-2-7B-Chat-AWQ\"\n# MODEL_BASENAME = \"model.safetensors.awq\"\n\n\n\nFile: run_localGPT_API.py\n\nimport logging\nimport os\nimport shutil\nimport subprocess\nimport argparse\n\nimport torch\nfrom flask import Flask, jsonify, request\nfrom langchain.chains import RetrievalQA\nfrom langchain.embeddings import HuggingFaceInstructEmbeddings\n\n# from langchain.embeddings import HuggingFaceEmbeddings\nfrom run_localGPT import load_model\nfrom prompt_template_utils import get_prompt_template\n\n# from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler\nfrom langchain.vectorstores import Chroma\nfrom werkzeug.utils import secure_filename\n\nfrom constants import CHROMA_SETTINGS, EMBEDDING_MODEL_NAME, PERSIST_DIRECTORY, MODEL_ID, MODEL_BASENAME\n\n# API queue addition\nfrom threading import Lock\n\nrequest_lock = Lock()\n\n\nif torch.backends.mps.is_available():\n DEVICE_TYPE = \"mps\"\nelif torch.cuda.is_available():\n DEVICE_TYPE = \"cuda\"\nelse:\n DEVICE_TYPE = \"cpu\"\n\nSHOW_SOURCES = True\nlogging.info(f\"Running on: {DEVICE_TYPE}\")\nlogging.info(f\"Display Source Documents set to: {SHOW_SOURCES}\")\n\nEMBEDDINGS = HuggingFaceInstructEmbeddings(model_name=EMBEDDING_MODEL_NAME, model_kwargs={\"device\": DEVICE_TYPE})\n\n# uncomment the following line if you used HuggingFaceEmbeddings in the ingest.py\n# EMBEDDINGS = HuggingFaceEmbeddings(model_name=EMBEDDING_MODEL_NAME)\n# if os.path.exists(PERSIST_DIRECTORY):\n# try:\n# shutil.rmtree(PERSIST_DIRECTORY)\n# except OSError as e:\n# print(f\"Error: {e.filename} - {e.strerror}.\")\n# else:\n# print(\"The directory does not exist\")\n\n# run_langest_commands = [\"python\", \"ingest.py\"]\n# if DEVICE_TYPE == \"cpu\":\n# run_langest_commands.append(\"--device_type\")\n# run_langest_commands.append(DEVICE_TYPE)\n\n# result = subprocess.run(run_langest_commands, capture_output=True)\n# if result.returncode != 0:\n# raise FileNotFoundError(\n# \"No files were found inside SOURCE_DOCUMENTS, please put a starter file inside before starting the API!\"\n# )\n\n# load the vectorstore\nDB = Chroma(\n persist_directory=PERSIST_DIRECTORY,\n embedding_function=EMBEDDINGS,\n client_settings=CHROMA_SETTINGS,\n)\n\nRETRIEVER = DB.as_retriever()\n\nLLM = load_model(device_type=DEVICE_TYPE, model_id=MODEL_ID, model_basename=MODEL_BASENAME)\nprompt, memory = get_prompt_template(promptTemplate_type=\"llama\", history=False)\n\nQA = RetrievalQA.from_chain_type(\n llm=LLM,\n chain_type=\"stuff\",\n retriever=RETRIEVER,\n return_source_documents=SHOW_SOURCES,\n chain_type_kwargs={\n \"prompt\": prompt,\n },\n)\n\napp = Flask(__name__)\n\n\n@app.route(\"/api/delete_source\", methods=[\"GET\"])\ndef delete_source_route():\n folder_name = \"SOURCE_DOCUMENTS\"\n\n if os.path.exists(folder_name):\n shutil.rmtree(folder_name)\n\n os.makedirs(folder_name)\n\n return jsonify({\"message\": f\"Folder '{folder_name}' successfully deleted and recreated.\"})\n\n\n@app.route(\"/api/save_document\", methods=[\"GET\", \"POST\"])\ndef save_document_route():\n if \"document\" not in request.files:\n return \"No document part\", 400\n file = request.files[\"document\"]\n if file.filename == \"\":\n return \"No selected file\", 400\n if file:\n filename = secure_filename(file.filename)\n folder_path = \"SOURCE_DOCUMENTS\"\n if not os.path.exists(folder_path):\n os.makedirs(folder_path)\n file_path = os.path.join(folder_path, filename)\n file.save(file_path)\n return \"File saved successfully\", 200\n\n\n@app.route(\"/api/run_ingest\", methods=[\"GET\"])\ndef run_ingest_route():\n global DB\n global RETRIEVER\n global QA\n try:\n if os.path.exists(PERSIST_DIRECTORY):\n try:\n shutil.rmtree(PERSIST_DIRECTORY)\n except OSError as e:\n print(f\"Error: {e.filename} - {e.strerror}.\")\n else:\n print(\"The directory does not exist\")\n\n run_langest_commands = [\"python\", \"ingest.py\"]\n if DEVICE_TYPE == \"cpu\":\n run_langest_commands.append(\"--device_type\")\n run_langest_commands.append(DEVICE_TYPE)\n\n result = subprocess.run(run_langest_commands, capture_output=True)\n if result.returncode != 0:\n return \"Script execution failed: {}\".format(result.stderr.decode(\"utf-8\")), 500\n # load the vectorstore\n DB = Chroma(\n persist_directory=PERSIST_DIRECTORY,\n embedding_function=EMBEDDINGS,\n client_settings=CHROMA_SETTINGS,\n )\n RETRIEVER = DB.as_retriever()\n prompt, memory = get_prompt_template(promptTemplate_type=\"llama\", history=False)\n\n QA = RetrievalQA.from_chain_type(\n llm=LLM,\n chain_type=\"stuff\",\n retriever=RETRIEVER,\n return_source_documents=SHOW_SOURCES,\n chain_type_kwargs={\n \"prompt\": prompt,\n },\n )\n return \"Script executed successfully: {}\".format(result.stdout.decode(\"utf-8\")), 200\n except Exception as e:\n return f\"Error occurred: {str(e)}\", 500\n\n\n@app.route(\"/api/prompt_route\", methods=[\"GET\", \"POST\"])\ndef prompt_route():\n global QA\n global request_lock # Make sure to use the global lock instance\n user_prompt = request.form.get(\"user_prompt\")\n if user_prompt:\n # Acquire the lock before processing the prompt\n with request_lock:\n # print(f'User Prompt: {user_prompt}') \n # Get the answer from the chain\n res = QA(user_prompt)\n answer, docs = res[\"result\"], res[\"source_documents\"]\n\n prompt_response_dict = {\n \"Prompt\": user_prompt,\n \"Answer\": answer,\n }\n\n prompt_response_dict[\"Sources\"] = []\n for document in docs:\n prompt_response_dict[\"Sources\"].append(\n (os.path.basename(str(document.metadata[\"source\"])), str(document.page_content))\n )\n\n return jsonify(prompt_response_dict), 200\n else:\n return \"No user prompt received\", 400\n\n\nif __name__ == \"__main__\":\n parser = argparse.ArgumentParser()\n parser.add_argument(\"--port\", type=int, default=5110, help=\"Port to run the API on. Defaults to 5110.\")\n parser.add_argument(\n \"--host\",\n type=str,\n default=\"127.0.0.1\",\n help=\"Host to run the UI on. Defaults to 127.0.0.1. \"\n \"Set to 0.0.0.0 to make the UI externally \"\n \"accessible from other devices.\",\n )\n args = parser.parse_args()\n\n logging.basicConfig(\n format=\"%(asctime)s - %(levelname)s - %(filename)s:%(lineno)s - %(message)s\", level=logging.INFO\n )\n app.run(debug=False, host=args.host, port=args.port)\n\n\n\nFile: utils.py\n\nimport os\nimport csv\nfrom datetime import datetime\nfrom constants import EMBEDDING_MODEL_NAME\nfrom langchain.embeddings import HuggingFaceInstructEmbeddings\nfrom langchain.embeddings import HuggingFaceBgeEmbeddings\nfrom langchain.embeddings import HuggingFaceEmbeddings\n\n\ndef log_to_csv(question, answer):\n\n log_dir, log_file = \"local_chat_history\", \"qa_log.csv\"\n # Ensure log directory exists, create if not\n if not os.path.exists(log_dir):\n os.makedirs(log_dir)\n\n # Construct the full file path\n log_path = os.path.join(log_dir, log_file)\n\n # Check if file exists, if not create and write headers\n if not os.path.isfile(log_path):\n with open(log_path, mode=\"w\", newline=\"\", encoding=\"utf-8\") as file:\n writer = csv.writer(file)\n writer.writerow([\"timestamp\", \"question\", \"answer\"])\n\n # Append the log entry\n with open(log_path, mode=\"a\", newline=\"\", encoding=\"utf-8\") as file:\n writer = csv.writer(file)\n timestamp = datetime.now().strftime(\"%Y-%m-%d %H:%M:%S\")\n writer.writerow([timestamp, question, answer])\n\n\ndef get_embeddings(device_type=\"cuda\"):\n if \"instructor\" in EMBEDDING_MODEL_NAME:\n return HuggingFaceInstructEmbeddings(\n model_name=EMBEDDING_MODEL_NAME,\n model_kwargs={\"device\": device_type},\n embed_instruction=\"Represent the document for retrieval:\",\n query_instruction=\"Represent the question for retrieving supporting documents:\",\n )\n\n elif \"bge\" in EMBEDDING_MODEL_NAME:\n return HuggingFaceBgeEmbeddings(\n model_name=EMBEDDING_MODEL_NAME,\n model_kwargs={\"device\": device_type},\n query_instruction=\"Represent this sentence for searching relevant passages:\",\n )\n\n else:\n return HuggingFaceEmbeddings(\n model_name=EMBEDDING_MODEL_NAME,\n model_kwargs={\"device\": device_type},\n )\n\n\n\nFile: load_models.py\n\nimport sys\n\nimport torch\n\nif sys.platform != \"darwin\":\n from auto_gptq import AutoGPTQForCausalLM\n\nfrom huggingface_hub import hf_hub_download\nfrom langchain.llms import LlamaCpp\nfrom transformers import AutoModelForCausalLM, AutoTokenizer, LlamaForCausalLM, LlamaTokenizer, BitsAndBytesConfig\n\nfrom constants import CONTEXT_WINDOW_SIZE, MAX_NEW_TOKENS, MODELS_PATH, N_BATCH, N_GPU_LAYERS\n\n\ndef load_quantized_model_gguf_ggml(model_id, model_basename, device_type, logging):\n \"\"\"\n Load a GGUF/GGML quantized model using LlamaCpp.\n\n This function attempts to load a GGUF/GGML quantized model using the LlamaCpp library.\n If the model is of type GGML, and newer version of LLAMA-CPP is used which does not support GGML,\n it logs a message indicating that LLAMA-CPP has dropped support for GGML.\n\n Parameters:\n - model_id (str): The identifier for the model on HuggingFace Hub.\n - model_basename (str): The base name of the model file.\n - device_type (str): The type of device where the model will run, e.g., 'mps', 'cuda', etc.\n - logging (logging.Logger): Logger instance for logging messages.\n\n Returns:\n - LlamaCpp: An instance of the LlamaCpp model if successful, otherwise None.\n\n Notes:\n - The function uses the `hf_hub_download` function to download the model from the HuggingFace Hub.\n - The number of GPU layers is set based on the device type.\n \"\"\"\n\n try:\n logging.info(\"Using Llamacpp for GGUF/GGML quantized models\")\n model_path = hf_hub_download(\n repo_id=model_id,\n filename=model_basename,\n resume_download=True,\n cache_dir=MODELS_PATH,\n )\n kwargs = {\n \"model_path\": model_path,\n \"n_ctx\": CONTEXT_WINDOW_SIZE,\n \"max_tokens\": MAX_NEW_TOKENS,\n \"n_batch\": N_BATCH, # set this based on your GPU & CPU RAM\n }\n if device_type.lower() == \"mps\":\n kwargs[\"n_gpu_layers\"] = 1\n if device_type.lower() == \"cuda\":\n kwargs[\"n_gpu_layers\"] = N_GPU_LAYERS # set this based on your GPU\n\n return LlamaCpp(**kwargs)\n except TypeError:\n if \"ggml\" in model_basename:\n logging.INFO(\"If you were using GGML model, LLAMA-CPP Dropped Support, Use GGUF Instead\")\n return None\n\n\ndef load_quantized_model_qptq(model_id, model_basename, device_type, logging):\n \"\"\"\n Load a GPTQ quantized model using AutoGPTQForCausalLM.\n\n This function loads a quantized model that ends with GPTQ and may have variations\n of .no-act.order or .safetensors in their HuggingFace repo.\n It will not work for Macs, as AutoGPTQ only supports Linux and Windows:\n - Nvidia CUDA (Windows and Linux)\n - AMD ROCm (Linux only)\n - CPU QiGen (Linux only, new and experimental)\n\n Parameters:\n - model_id (str): The identifier for the model on HuggingFace Hub.\n - model_basename (str): The base name of the model file.\n - device_type (str): The type of device where the model will run.\n - logging (logging.Logger): Logger instance for logging messages.\n\n Returns:\n - model (AutoGPTQForCausalLM): The loaded quantized model.\n - tokenizer (AutoTokenizer): The tokenizer associated with the model.\n\n Notes:\n - The function checks for the \".safetensors\" ending in the model_basename and removes it if present.\n \"\"\"\n\n if sys.platform == \"darwin\":\n logging.INFO(\"GPTQ models will NOT work on Mac devices. Please choose a different model.\")\n return None, None\n\n # The code supports all huggingface models that ends with GPTQ and have some variation\n # of .no-act.order or .safetensors in their HF repo.\n logging.info(\"Using AutoGPTQForCausalLM for quantized models\")\n\n if \".safetensors\" in model_basename:\n # Remove the \".safetensors\" ending if present\n model_basename = model_basename.replace(\".safetensors\", \"\")\n\n tokenizer = AutoTokenizer.from_pretrained(model_id, use_fast=True)\n logging.info(\"Tokenizer loaded\")\n\n model = AutoGPTQForCausalLM.from_quantized(\n model_id,\n model_basename=model_basename,\n use_safetensors=True,\n trust_remote_code=True,\n device_map=\"auto\",\n use_triton=False,\n quantize_config=None,\n )\n return model, tokenizer\n\n\ndef load_full_model(model_id, model_basename, device_type, logging):\n \"\"\"\n Load a full model using either LlamaTokenizer or AutoModelForCausalLM.\n\n This function loads a full model based on the specified device type.\n If the device type is 'mps' or 'cpu', it uses LlamaTokenizer and LlamaForCausalLM.\n Otherwise, it uses AutoModelForCausalLM.\n\n Parameters:\n - model_id (str): The identifier for the model on HuggingFace Hub.\n - model_basename (str): The base name of the model file.\n - device_type (str): The type of device where the model will run.\n - logging (logging.Logger): Logger instance for logging messages.\n\n Returns:\n - model (Union[LlamaForCausalLM, AutoModelForCausalLM]): The loaded model.\n - tokenizer (Union[LlamaTokenizer, AutoTokenizer]): The tokenizer associated with the model.\n\n Notes:\n - The function uses the `from_pretrained` method to load both the model and the tokenizer.\n - Additional settings are provided for NVIDIA GPUs, such as loading in 4-bit and setting the compute dtype.\n \"\"\"\n\n if device_type.lower() in [\"mps\", \"cpu\"]:\n logging.info(\"Using AutoModelForCausalLM\")\n # tokenizer = LlamaTokenizer.from_pretrained(model_id, cache_dir=\"./models/\")\n # model = LlamaForCausalLM.from_pretrained(model_id, cache_dir=\"./models/\")\n\n model = AutoModelForCausalLM.from_pretrained(model_id,\n # quantization_config=quantization_config,\n # low_cpu_mem_usage=True,\n # torch_dtype=\"auto\",\n torch_dtype=torch.bfloat16,\n device_map=\"auto\",\n cache_dir=\"./models/\")\n\n tokenizer = AutoTokenizer.from_pretrained(model_id, cache_dir=\"./models/\")\n else:\n logging.info(\"Using AutoModelForCausalLM for full models\")\n tokenizer = AutoTokenizer.from_pretrained(model_id, cache_dir=\"./models/\")\n logging.info(\"Tokenizer loaded\")\n bnb_config = BitsAndBytesConfig(\n load_in_4bit=True,\n bnb_4bit_use_double_quant=True,\n bnb_4bit_quant_type=\"nf4\",\n bnb_4bit_compute_dtype=torch.float16\n )\n model = AutoModelForCausalLM.from_pretrained(\n model_id,\n device_map=\"auto\",\n torch_dtype=torch.float16,\n low_cpu_mem_usage=True,\n cache_dir=MODELS_PATH,\n trust_remote_code=True, # set these if you are using NVIDIA GPU\n quantization_config=bnb_config\n # load_in_4bit=True,\n # bnb_4bit_quant_type=\"nf4\",\n # bnb_4bit_compute_dtype=torch.float16,\n # max_memory={0: \"15GB\"}, # Uncomment this line with you encounter CUDA out of memory errors\n )\n\n model.tie_weights()\n return model, tokenizer\n\n\ndef load_quantized_model_awq(model_id, logging):\n \"\"\"\n Load a AWQ quantized model using AutoModelForCausalLM.\n\n This function loads a quantized model that ends with AWQ.\n It will not work for Macs as AutoAWQ currently only supports Nvidia GPUs.\n\n Parameters:\n - model_id (str): The identifier for the model on HuggingFace Hub.\n - logging (logging.Logger): Logger instance for logging messages.\n\n Returns:\n - model (AutoModelForCausalLM): The loaded quantized model.\n - tokenizer (AutoTokenizer): The tokenizer associated with the model.\n\n \"\"\"\n\n if sys.platform == \"darwin\":\n logging.INFO(\"AWQ models will NOT work on Mac devices. Please choose a different model.\")\n return None, None\n\n # The code supports all huggingface models that ends with AWQ.\n logging.info(\"Using AutoModelForCausalLM for AWQ quantized models\")\n\n tokenizer = AutoTokenizer.from_pretrained(model_id, use_fast=True)\n logging.info(\"Tokenizer loaded\")\n\n model = AutoModelForCausalLM.from_pretrained(\n model_id,\n use_safetensors=True,\n trust_remote_code=True,\n device_map=\"auto\",\n )\n return model, tokenizer\n\n\n\nFile: localGPTUI/localGPTUI.py\n\nimport argparse\nimport os\nimport sys\nimport tempfile\n\nimport requests\nfrom flask import Flask, render_template, request\nfrom werkzeug.utils import secure_filename\n\nsys.path.append(os.path.join(os.path.dirname(__file__), \"..\"))\n\napp = Flask(__name__)\napp.secret_key = \"LeafmanZSecretKey\"\n\nAPI_HOST = \"http://localhost:5110/api\"\n\n\n# PAGES #\n@app.route(\"/\", methods=[\"GET\", \"POST\"])\ndef home_page():\n if request.method == \"POST\":\n if \"user_prompt\" in request.form:\n user_prompt = request.form[\"user_prompt\"]\n print(f\"User Prompt: {user_prompt}\")\n\n main_prompt_url = f\"{API_HOST}/prompt_route\"\n response = requests.post(main_prompt_url, data={\"user_prompt\": user_prompt})\n print(response.status_code) # print HTTP response status code for debugging\n if response.status_code == 200:\n # print(response.json()) # Print the JSON data from the response\n return render_template(\"home.html\", show_response_modal=True, response_dict=response.json())\n elif \"documents\" in request.files:\n delete_source_url = f\"{API_HOST}/delete_source\" # URL of the /api/delete_source endpoint\n if request.form.get(\"action\") == \"reset\":\n response = requests.get(delete_source_url)\n\n save_document_url = f\"{API_HOST}/save_document\"\n run_ingest_url = f\"{API_HOST}/run_ingest\" # URL of the /api/run_ingest endpoint\n files = request.files.getlist(\"documents\")\n for file in files:\n print(file.filename)\n filename = secure_filename(file.filename)\n with tempfile.SpooledTemporaryFile() as f:\n f.write(file.read())\n f.seek(0)\n response = requests.post(save_document_url, files={\"document\": (filename, f)})\n print(response.status_code) # print HTTP response status code for debugging\n # Make a GET request to the /api/run_ingest endpoint\n response = requests.get(run_ingest_url)\n print(response.status_code) # print HTTP response status code for debugging\n\n # Display the form for GET request\n return render_template(\n \"home.html\",\n show_response_modal=False,\n response_dict={\"Prompt\": \"None\", \"Answer\": \"None\", \"Sources\": [(\"ewf\", \"wef\")]},\n )\n\n\nif __name__ == \"__main__\":\n parser = argparse.ArgumentParser()\n parser.add_argument(\"--port\", type=int, default=5111, help=\"Port to run the UI on. Defaults to 5111.\")\n parser.add_argument(\n \"--host\",\n type=str,\n default=\"127.0.0.1\",\n help=\"Host to run the UI on. Defaults to 127.0.0.1. \"\n \"Set to 0.0.0.0 to make the UI externally \"\n \"accessible from other devices.\",\n )\n args = parser.parse_args()\n app.run(debug=False, host=args.host, port=args.port)\n\n\n"},"repo_readme":{"kind":"string","value":"# LocalGPT: Secure, Local Conversations with Your Documents 🌐\n\n\n[](https://github.com/PromtEngineer/localGPT/stargazers)\n[](https://github.com/PromtEngineer/localGPT/network/members)\n[](https://github.com/PromtEngineer/localGPT/issues)\n[](https://github.com/PromtEngineer/localGPT/pulls)\n[](https://github.com/PromtEngineer/localGPT/blob/main/LICENSE)\n\n🚨🚨 You can run localGPT on a pre-configured [Virtual Machine](https://bit.ly/localGPT). Make sure to use the code: PromptEngineering to get 50% off. I will get a small commision!\n\n**LocalGPT** is an open-source initiative that allows you to converse with your documents without compromising your privacy. With everything running locally, you can be assured that no data ever leaves your computer. Dive into the world of secure, local document interactions with LocalGPT.\n\n## Features 🌟\n- **Utmost Privacy**: Your data remains on your computer, ensuring 100% security.\n- **Versatile Model Support**: Seamlessly integrate a variety of open-source models, including HF, GPTQ, GGML, and GGUF.\n- **Diverse Embeddings**: Choose from a range of open-source embeddings.\n- **Reuse Your LLM**: Once downloaded, reuse your LLM without the need for repeated downloads.\n- **Chat History**: Remembers your previous conversations (in a session).\n- **API**: LocalGPT has an API that you can use for building RAG Applications.\n- **Graphical Interface**: LocalGPT comes with two GUIs, one uses the API and the other is standalone (based on streamlit).\n- **GPU, CPU & MPS Support**: Supports multiple platforms out of the box, Chat with your data using `CUDA`, `CPU` or `MPS` and more!\n\n## Dive Deeper with Our Videos 🎥\n- [Detailed code-walkthrough](https://youtu.be/MlyoObdIHyo)\n- [Llama-2 with LocalGPT](https://youtu.be/lbFmceo4D5E)\n- [Adding Chat History](https://youtu.be/d7otIM_MCZs)\n- [LocalGPT - Updated (09/17/2023)](https://youtu.be/G_prHSKX9d4)\n\n## Technical Details 🛠️\nBy selecting the right local models and the power of `LangChain` you can run the entire RAG pipeline locally, without any data leaving your environment, and with reasonable performance.\n\n- `ingest.py` uses `LangChain` tools to parse the document and create embeddings locally using `InstructorEmbeddings`. It then stores the result in a local vector database using `Chroma` vector store.\n- `run_localGPT.py` uses a local LLM to understand questions and create answers. The context for the answers is extracted from the local vector store using a similarity search to locate the right piece of context from the docs.\n- You can replace this local LLM with any other LLM from the HuggingFace. Make sure whatever LLM you select is in the HF format.\n\nThis project was inspired by the original [privateGPT](https://github.com/imartinez/privateGPT).\n\n## Built Using 🧩\n- [LangChain](https://github.com/hwchase17/langchain)\n- [HuggingFace LLMs](https://huggingface.co/models)\n- [InstructorEmbeddings](https://instructor-embedding.github.io/)\n- [LLAMACPP](https://github.com/abetlen/llama-cpp-python)\n- [ChromaDB](https://www.trychroma.com/)\n- [Streamlit](https://streamlit.io/)\n\n# Environment Setup 🌍\n\n1. 📥 Clone the repo using git:\n\n```shell\ngit clone https://github.com/PromtEngineer/localGPT.git\n```\n\n2. 🐍 Install [conda](https://www.anaconda.com/download) for virtual environment management. Create and activate a new virtual environment.\n\n```shell\nconda create -n localGPT python=3.10.0\nconda activate localGPT\n```\n\n3. 🛠️ Install the dependencies using pip\n\nTo set up your environment to run the code, first install all requirements:\n\n```shell\npip install -r requirements.txt\n```\n\n***Installing LLAMA-CPP :***\n\nLocalGPT uses [LlamaCpp-Python](https://github.com/abetlen/llama-cpp-python) for GGML (you will need llama-cpp-python <=0.1.76) and GGUF (llama-cpp-python >=0.1.83) models.\n\n\nIf you want to use BLAS or Metal with [llama-cpp](https://github.com/abetlen/llama-cpp-python#installation-with-openblas--cublas--clblast--metal) you can set appropriate flags:\n\nFor `NVIDIA` GPUs support, use `cuBLAS`\n\n```shell\n# Example: cuBLAS\nCMAKE_ARGS=\"-DLLAMA_CUBLAS=on\" FORCE_CMAKE=1 pip install llama-cpp-python --no-cache-dir\n```\n\nFor Apple Metal (`M1/M2`) support, use\n\n```shell\n# Example: METAL\nCMAKE_ARGS=\"-DLLAMA_METAL=on\" FORCE_CMAKE=1 pip install llama-cpp-python --no-cache-dir\n```\nFor more details, please refer to [llama-cpp](https://github.com/abetlen/llama-cpp-python#installation-with-openblas--cublas--clblast--metal)\n\n## Docker 🐳\n\nInstalling the required packages for GPU inference on NVIDIA GPUs, like gcc 11 and CUDA 11, may cause conflicts with other packages in your system.\nAs an alternative to Conda, you can use Docker with the provided Dockerfile.\nIt includes CUDA, your system just needs Docker, BuildKit, your NVIDIA GPU driver and the NVIDIA container toolkit.\nBuild as `docker build -t localgpt .`, requires BuildKit.\nDocker BuildKit does not support GPU during *docker build* time right now, only during *docker run*.\nRun as `docker run -it --mount src=\"$HOME/.cache\",target=/root/.cache,type=bind --gpus=all localgpt`.\n\n## Test dataset\n\nFor testing, this repository comes with [Constitution of USA](https://constitutioncenter.org/media/files/constitution.pdf) as an example file to use.\n\n## Ingesting your OWN Data.\nPut your files in the `SOURCE_DOCUMENTS` folder. You can put multiple folders within the `SOURCE_DOCUMENTS` folder and the code will recursively read your files.\n\n### Support file formats:\nLocalGPT currently supports the following file formats. LocalGPT uses `LangChain` for loading these file formats. The code in `constants.py` uses a `DOCUMENT_MAP` dictionary to map a file format to the corresponding loader. In order to add support for another file format, simply add this dictionary with the file format and the corresponding loader from [LangChain](https://python.langchain.com/docs/modules/data_connection/document_loaders/).\n\n```shell\nDOCUMENT_MAP = {\n \".txt\": TextLoader,\n \".md\": TextLoader,\n \".py\": TextLoader,\n \".pdf\": PDFMinerLoader,\n \".csv\": CSVLoader,\n \".xls\": UnstructuredExcelLoader,\n \".xlsx\": UnstructuredExcelLoader,\n \".docx\": Docx2txtLoader,\n \".doc\": Docx2txtLoader,\n}\n```\n\n### Ingest\n\nRun the following command to ingest all the data.\n\nIf you have `cuda` setup on your system.\n\n```shell\npython ingest.py\n```\nYou will see an output like this:\n<img width=\"1110\" alt=\"Screenshot 2023-09-14 at 3 36 27 PM\" src=\"https://github.com/PromtEngineer/localGPT/assets/134474669/c9274e9a-842c-49b9-8d95-606c3d80011f\">\n\n\nUse the device type argument to specify a given device.\nTo run on `cpu`\n\n```sh\npython ingest.py --device_type cpu\n```\n\nTo run on `M1/M2`\n\n```sh\npython ingest.py --device_type mps\n```\n\nUse help for a full list of supported devices.\n\n```sh\npython ingest.py --help\n```\n\nThis will create a new folder called `DB` and use it for the newly created vector store. You can ingest as many documents as you want, and all will be accumulated in the local embeddings database.\nIf you want to start from an empty database, delete the `DB` and reingest your documents.\n\nNote: When you run this for the first time, it will need internet access to download the embedding model (default: `Instructor Embedding`). In the subsequent runs, no data will leave your local environment and you can ingest data without internet connection.\n\n## Ask questions to your documents, locally!\n\nIn order to chat with your documents, run the following command (by default, it will run on `cuda`).\n\n```shell\npython run_localGPT.py\n```\nYou can also specify the device type just like `ingest.py`\n\n```shell\npython run_localGPT.py --device_type mps # to run on Apple silicon\n```\n\nThis will load the ingested vector store and embedding model. You will be presented with a prompt:\n\n```shell\n> Enter a query:\n```\n\nAfter typing your question, hit enter. LocalGPT will take some time based on your hardware. You will get a response like this below.\n<img width=\"1312\" alt=\"Screenshot 2023-09-14 at 3 33 19 PM\" src=\"https://github.com/PromtEngineer/localGPT/assets/134474669/a7268de9-ade0-420b-a00b-ed12207dbe41\">\n\nOnce the answer is generated, you can then ask another question without re-running the script, just wait for the prompt again.\n\n\n***Note:*** When you run this for the first time, it will need internet connection to download the LLM (default: `TheBloke/Llama-2-7b-Chat-GGUF`). After that you can turn off your internet connection, and the script inference would still work. No data gets out of your local environment.\n\nType `exit` to finish the script.\n\n### Extra Options with run_localGPT.py\n\nYou can use the `--show_sources` flag with `run_localGPT.py` to show which chunks were retrieved by the embedding model. By default, it will show 4 different sources/chunks. You can change the number of sources/chunks\n\n```shell\npython run_localGPT.py --show_sources\n```\n\nAnother option is to enable chat history. ***Note***: This is disabled by default and can be enabled by using the `--use_history` flag. The context window is limited so keep in mind enabling history will use it and might overflow.\n\n```shell\npython run_localGPT.py --use_history\n```\n\nYou can store user questions and model responses with flag `--save_qa` into a csv file `/local_chat_history/qa_log.csv`. Every interaction will be stored. \n\n```shell\npython run_localGPT.py --save_qa\n```\n\n# Run the Graphical User Interface\n\n1. Open `constants.py` in an editor of your choice and depending on choice add the LLM you want to use. By default, the following model will be used:\n\n ```shell\n MODEL_ID = \"TheBloke/Llama-2-7b-Chat-GGUF\"\n MODEL_BASENAME = \"llama-2-7b-chat.Q4_K_M.gguf\"\n ```\n\n3. Open up a terminal and activate your python environment that contains the dependencies installed from requirements.txt.\n\n4. Navigate to the `/LOCALGPT` directory.\n\n5. Run the following command `python run_localGPT_API.py`. The API should being to run.\n\n6. Wait until everything has loaded in. You should see something like `INFO:werkzeug:Press CTRL+C to quit`.\n\n7. Open up a second terminal and activate the same python environment.\n\n8. Navigate to the `/LOCALGPT/localGPTUI` directory.\n\n9. Run the command `python localGPTUI.py`.\n\n10. Open up a web browser and go the address `http://localhost:5111/`.\n\n\n# How to select different LLM models?\n\nTo change the models you will need to set both `MODEL_ID` and `MODEL_BASENAME`.\n\n1. Open up `constants.py` in the editor of your choice.\n2. Change the `MODEL_ID` and `MODEL_BASENAME`. If you are using a quantized model (`GGML`, `GPTQ`, `GGUF`), you will need to provide `MODEL_BASENAME`. For unquantized models, set `MODEL_BASENAME` to `NONE`\n5. There are a number of example models from HuggingFace that have already been tested to be run with the original trained model (ending with HF or have a .bin in its \"Files and versions\"), and quantized models (ending with GPTQ or have a .no-act-order or .safetensors in its \"Files and versions\").\n6. For models that end with HF or have a .bin inside its \"Files and versions\" on its HuggingFace page.\n\n - Make sure you have a `MODEL_ID` selected. For example -> `MODEL_ID = \"TheBloke/guanaco-7B-HF\"`\n - Go to the [HuggingFace Repo](https://huggingface.co/TheBloke/guanaco-7B-HF)\n\n7. For models that contain GPTQ in its name and or have a .no-act-order or .safetensors extension inside its \"Files and versions on its HuggingFace page.\n\n - Make sure you have a `MODEL_ID` selected. For example -> model_id = `\"TheBloke/wizardLM-7B-GPTQ\"`\n - Got to the corresponding [HuggingFace Repo](https://huggingface.co/TheBloke/wizardLM-7B-GPTQ) and select \"Files and versions\".\n - Pick one of the model names and set it as `MODEL_BASENAME`. For example -> `MODEL_BASENAME = \"wizardLM-7B-GPTQ-4bit.compat.no-act-order.safetensors\"`\n\n8. Follow the same steps for `GGUF` and `GGML` models.\n\n# GPU and VRAM Requirements\n\nBelow is the VRAM requirement for different models depending on their size (Billions of parameters). The estimates in the table does not include VRAM used by the Embedding models - which use an additional 2GB-7GB of VRAM depending on the model.\n\n| Mode Size (B) | float32 | float16 | GPTQ 8bit | GPTQ 4bit |\n| ------- | --------- | --------- | -------------- | ------------------ |\n| 7B | 28 GB | 14 GB | 7 GB - 9 GB | 3.5 GB - 5 GB |\n| 13B | 52 GB | 26 GB | 13 GB - 15 GB | 6.5 GB - 8 GB |\n| 32B | 130 GB | 65 GB | 32.5 GB - 35 GB| 16.25 GB - 19 GB |\n| 65B | 260.8 GB | 130.4 GB | 65.2 GB - 67 GB| 32.6 GB - 35 GB |\n\n\n# System Requirements\n\n## Python Version\n\nTo use this software, you must have Python 3.10 or later installed. Earlier versions of Python will not compile.\n\n## C++ Compiler\n\nIf you encounter an error while building a wheel during the `pip install` process, you may need to install a C++ compiler on your computer.\n\n### For Windows 10/11\n\nTo install a C++ compiler on Windows 10/11, follow these steps:\n\n1. Install Visual Studio 2022.\n2. Make sure the following components are selected:\n - Universal Windows Platform development\n - C++ CMake tools for Windows\n3. Download the MinGW installer from the [MinGW website](https://sourceforge.net/projects/mingw/).\n4. Run the installer and select the \"gcc\" component.\n\n### NVIDIA Driver's Issues:\n\nFollow this [page](https://linuxconfig.org/how-to-install-the-nvidia-drivers-on-ubuntu-22-04) to install NVIDIA Drivers.\n\n## Star History\n\n[](https://star-history.com/#PromtEngineer/localGPT&Date)\n\n# Disclaimer\n\nThis is a test project to validate the feasibility of a fully local solution for question answering using LLMs and Vector embeddings. It is not production ready, and it is not meant to be used in production. Vicuna-7B is based on the Llama model so that has the original Llama license.\n\n# Common Errors\n\n - [Torch not compatible with CUDA enabled](https://github.com/pytorch/pytorch/issues/30664)\n\n - Get CUDA version\n ```shell\n nvcc --version\n ```\n ```shell\n nvidia-smi\n ```\n - Try installing PyTorch depending on your CUDA version\n ```shell\n conda install -c pytorch torchvision cudatoolkit=10.1 pytorch\n ```\n - If it doesn't work, try reinstalling\n ```shell\n pip uninstall torch\n pip cache purge\n pip install torch -f https://download.pytorch.org/whl/torch_stable.html\n ```\n\n- [ERROR: pip's dependency resolver does not currently take into account all the packages that are installed](https://stackoverflow.com/questions/72672196/error-pips-dependency-resolver-does-not-currently-take-into-account-all-the-pa/76604141#76604141)\n ```shell\n pip install h5py\n pip install typing-extensions\n pip install wheel\n ```\n- [Failed to import transformers](https://github.com/huggingface/transformers/issues/11262)\n - Try re-install\n ```shell\n conda uninstall tokenizers, transformers\n pip install transformers\n ```\n"}}},{"rowIdx":156,"cells":{"repo_name":{"kind":"string","value":"Python-100-Days"},"repo_commit":{"kind":"string","value":"bf24146944745bb25c66c82307fd218abd179c6a"},"repo_content":{"kind":"string","value":"File: Day31-35/code/josephu.py\n\ndef main():\n persons = [True] * 30\n counter = 0\n index = 0\n number = 0\n while counter < 15:\n if persons[index]:\n number += 1\n if number == 9:\n persons[index] = False\n number = 0\n counter += 1\n index += 1\n index %= len(persons)\n for person in persons:\n\t print('基' if person else '非', end='')\n print()\n\n\nif __name__ == '__main__':\n main()\n\n\n\n\nFile: Day31-35/code/dayofyear.py\n\nimport sys\nimport mycal\n\n\ndef main():\n if len(sys.argv) != 4:\n print('Not enough arguments')\n return \n year = int(sys.argv[1])\n month = int(sys.argv[2])\n day = int(sys.argv[3])\n total = 0\n for m in range(1, month):\n total += mycal.get_days(year, m)\n total += day\n print(f'{year}年{month}月{day}日是{year}年的第{total}天')\n\n\nif __name__ == '__main__':\n main()\n\n\n\n\nFile: Day31-35/code/guess.py\n\n#!/usr/bin/python3\n# coding: utf-8\nfrom random import randint\n\n\ndef main():\n answer = randint(1, 100)\n while True:\n number = int(input('请输入: '))\n if number < answer:\n print('大一点')\n elif number > answer:\n print('小一点')\n else:\n print('恭喜你猜对了!')\n break\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day31-35/code/mycal.py\n\n#!/usr/bin/python3\nfrom datetime import datetime\n\nimport sys\n\n\ndef is_leap(year):\n return year % 4 == 0 and year % 100 != 0 or year % 400 == 0\n\n\ndef main():\n if len(sys.argv) == 3:\n month = int(sys.argv[1])\n year = int(sys.argv[2])\n else:\n now = datetime.now()\n date = now.date\n month = now.month\n year = now.year\n m, y = (month, year) if month >= 3 else (month + 12, year - 1)\n c, y = y // 100, y % 100\n w = (y + y // 4 + c // 4 - 2 * c + 26 * (m + 1) // 10) % 7\n month_words = [\n 'January', 'February', 'March', 'April', 'May', 'June',\n 'July', 'August', 'September', 'October', 'November', 'December'\n ]\n print(f'{month_words[month - 1]} {year}'.center(20))\n print('Su Mo Tu We Th Fr Sa')\n print(' ' * 3 * w, end='')\n days = [\n [31, 28, 31, 30, 31, 30, 31, 31, 30, 31, 30, 31],\n [31, 29, 31, 30, 31, 30, 31, 31, 30, 31, 30, 31]\n ][is_leap(year)][month - 1] \n for day in range(1, days + 1):\n print(str(day).rjust(2), end=' ')\n w += 1\n if w == 7:\n print()\n w = 0\n print()\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day31-35/code/homework01.py\n\n# 经典递归求解问题:\n# 1. 迷宫寻路\n# 2. 汉诺塔(梵塔)\n# 3. 骑士周游\n# 4. 八皇后\n\n\ndef f(n: int, m=1) -> int:\n if n == 0 or n == 1:\n return m\n return f(n - 1, n * m)\n\n\ndef sum(n: int) -> int:\n if n == 1:\n return 1\n return n + sum(n - 1)\n\n\ndef steps(n: int, m={}) -> int:\n if n < 0:\n return 0\n elif n == 0:\n return 1\n else:\n try:\n return m[n]\n except:\n m[n] = steps(n - 1) + steps(n - 2) + steps(n - 3)\n return m[n]\n\n\ndef list_depth(items: list) -> int:\n max_depth = 1 if isinstance(items, list) else 0\n if max_depth:\n for item in items:\n if isinstance(item, list):\n max_depth = max(max_depth, list_depth(item) + 1)\n return max_depth\n\n\n\ndef main():\n mylist = [1, ['a', ['b', ['c']]],[100, [200, 300, [400, [500, [600, [700]]]]]]] \n thylist = [[], [[[]]], [[], []]]\n print(list_depth(mylist))\n print(list_depth(thylist))\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day16-20/code/example19.py\n\n\"\"\"\n扩展性系统性能\n- 垂直扩展 - 增加单节点处理能力\n- 水平扩展 - 将单节点变成多节点（读写分离/分布式集群）\n并发编程 - 加速程序执行 / 改善用户体验\n耗时间的任务都尽可能独立的执行，不要阻塞代码的其他部分\n- 多线程\n1. 创建Thread对象指定target和args属性并通过start方法启动线程\n2. 继承Thread类并重写run方法来定义线程执行的任务\n3. 创建线程池对象ThreadPoolExecutor并通过submit来提交要执行的任务\n第3种方式可以通过Future对象的result方法在将来获得线程的执行结果\n也可以通过done方法判定线程是否执行结束\n- 多进程\n- 异步I/O\n\"\"\"\nimport glob\nimport os\nimport time\n\nfrom concurrent.futures import ThreadPoolExecutor\nfrom threading import Thread\n\nfrom PIL import Image\n\n\n# class ThumbnailThread(Thread):\n\n# def __init__(self, infile):\n# self.infile = infile\n# super().__init__()\n\n# def run(self):\n# file, ext = os.path.splitext(self.infile)\n# filename = file[file.rfind('/') + 1:]\n# for size in (32, 64, 128):\n# outfile = f'thumbnails/{filename}_{size}_{size}.png'\n# image = Image.open(self.infile)\n# image.thumbnail((size, size))\n# image.save(outfile, format='PNG')\n\n\ndef gen_thumbnail(infile):\n file, ext = os.path.splitext(infile)\n filename = file[file.rfind('/') + 1:]\n for size in (32, 64, 128):\n outfile = f'thumbnails/{filename}_{size}_{size}.png'\n image = Image.open(infile)\n image.thumbnail((size, size))\n image.save(outfile, format='PNG')\n\n\n# def main():\n# start = time.time()\n# threads = []\n# for infile in glob.glob('images/*'):\n# # t = Thread(target=gen_thumbnail, args=(infile, ))\n# t = ThumbnailThread(infile)\n# t.start()\n# threads.append(t)\n# for t in threads:\n# t.join()\n# end = time.time()\n# print(f'耗时: {end - start}秒')\n\n\ndef main():\n pool = ThreadPoolExecutor(max_workers=30)\n futures = []\n start = time.time()\n for infile in glob.glob('images/*'):\n # submit方法是非阻塞式的方法 \n # 即便工作线程数已经用完，submit方法也会接受提交的任务 \n future = pool.submit(gen_thumbnail, infile)\n futures.append(future)\n for future in futures:\n # result方法是一个阻塞式的方法 如果线程还没有结束\n # 暂时取不到线程的执行结果 代码就会在此处阻塞\n future.result()\n end = time.time()\n print(f'耗时: {end - start}秒')\n # shutdown也是非阻塞式的方法 但是如果已经提交的任务还没有执行完\n # 线程池是不会停止工作的 shutdown之后再提交任务就不会执行而且会产生异常\n pool.shutdown()\n\n\nif __name__ == '__main__':\n main()\n\n\n\n\n\n\n\n\n\n\nFile: Day16-20/code/example09.py\n\n\"\"\"\n装饰器 - 装饰器中放置的通常都是横切关注（cross-concern）功能\n所谓横切关注功能就是很多地方都会用到但跟正常业务又逻辑没有必然联系的功能\n装饰器实际上是实现了设计模式中的代理模式 - AOP（面向切面编程）\n\"\"\"\nfrom functools import wraps\nfrom random import randint\nfrom time import time, sleep\n\nimport pymysql\n\n\ndef record(output):\n\n def decorate(func):\n\n @wraps(func)\n def wrapper(*args, **kwargs):\n start = time()\n ret_value = func(*args, **kwargs)\n output(func.__name__, time() - start)\n return ret_value\n\n return wrapper\n\n return decorate\n\n\ndef output_to_console(fname, duration):\n print('%s: %.3f秒' % (fname, duration))\n\n\ndef output_to_file(fname, duration):\n with open('log.txt', 'a') as file_stream:\n file_stream.write('%s: %.3f秒\\n' % (fname, duration))\n\n\ndef output_to_db(fname, duration):\n con = pymysql.connect(host='localhost', port=3306,\n database='test', charset='utf8',\n user='root', password='123456',\n autocommit=True)\n try:\n with con.cursor() as cursor:\n cursor.execute('insert into tb_record values (default, %s, %s)',\n (fname, '%.3f' % duration))\n finally:\n con.close()\n\n\n@record(output_to_console)\ndef random_delay(min, max):\n sleep(randint(min, max))\n\n\ndef main():\n for _ in range(3):\n # print(random_delay.__name__)\n random_delay(3, 5)\n # for _ in range(3):\n # # 取消掉装饰器\n # random_delay.__wrapped__(3, 5)\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day16-20/code/example18.py\n\n\"\"\"\n元 - meta\n元数据 - 描述数据的数据 - metadata\n元类 - 描述类的类 - metaclass - 继承自type\n\"\"\"\nimport threading\n\n\nclass SingletonMeta(type):\n \"\"\"自定义元类\"\"\"\n\n def __init__(cls, *args, **kwargs):\n cls.__instance = None\n cls.lock = threading.Lock()\n super().__init__(*args, **kwargs)\n\n def __call__(cls, *args, **kwargs):\n if cls.__instance is None:\n with cls.lock:\n if cls.__instance is None:\n cls.__instance = super().__call__(*args, **kwargs)\n return cls.__instance\n\n\nclass President(metaclass=SingletonMeta):\n \"\"\"总统(单例类)\"\"\"\n\n def __init__(self, name, country):\n self.name = name\n self.country = country\n\n def __str__(self):\n return f'{self.country}: {self.name}'\n\n\ndef main():\n \"\"\"主函数\"\"\"\n p1 = President('特朗普', '美国')\n p2 = President('奥巴马', '美国')\n p3 = President.__call__('克林顿', '美国')\n print(p1 == p2)\n print(p1 == p3)\n print(p1, p2, p3, sep='\\n')\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day16-20/code/example08.py\n\n\"\"\"\n加密和解密\n对称加密 - 加密和解密是同一个密钥 - DES / AES\n非对称加密 - 加密和解密是不同的密钥 - RSA\npip install pycrypto\n\"\"\"\nimport base64\n\nfrom hashlib import md5\n\nfrom Crypto.Cipher import AES\nfrom Crypto import Random\nfrom Crypto.PublicKey import RSA\n\n# # AES加密的密钥（长度32个字节）\n# key = md5(b'1qaz2wsx').hexdigest()\n# # AES加密的初始向量（随机生成）\n# iv = Random.new().read(AES.block_size)\n\n\ndef main():\n \"\"\"主函数\"\"\"\n # 生成密钥对\n key_pair = RSA.generate(1024)\n # 导入公钥\n pub_key = RSA.importKey(key_pair.publickey().exportKey())\n # 导入私钥\n pri_key = RSA.importKey(key_pair.exportKey())\n message1 = 'hello, world!'\n # 加密数据\n data = pub_key.encrypt(message1.encode(), None)\n # 对加密数据进行BASE64编码\n message2 = base64.b64encode(data[0])\n print(message2)\n # 对加密数据进行BASE64解码\n data = base64.b64decode(message2)\n # 解密数据\n message3 = pri_key.decrypt(data)\n print(message3.decode())\n # # AES - 对称加密\n # str1 = '我爱你们！'\n # cipher = AES.new(key, AES.MODE_CFB, iv)\n # # 加密\n # str2 = cipher.encrypt(str1)\n # print(str2)\n # # 解密\n # cipher = AES.new(key, AES.MODE_CFB, iv)\n # str3 = cipher.decrypt(str2)\n # print(str3.decode())\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day16-20/code/test_example01.py\n\n\"\"\"\n单元测试 - 针对程序中最小的功能模块（函数和方法）的测试\n测试方法：\n- 白盒测试：程序自己写的测试\n- 黑盒测试：测试人员或QA，不知道代码实现细节，只关注功能\n编写Python单元测试 - 定义类继承TestCase，写测试方法(test_开头)\n执行单元测试：\n- unittest.main()\n- python3 -m unittest test_example01.py\n第三方库 - nose2 / pytest\npip install pytest pytest-cov\npytest -v --cov\n------------------------------\npip install nose2 cov-core\nnose2 -v -C\n\"\"\"\nfrom unittest import TestCase\n\nfrom example01 import seq_search, bin_search\n\n\nclass TestExample01(TestCase):\n \"\"\"测试查找函数的测试用例\"\"\"\n\n # 执行每个测试函数之前要执行的方法\n def setUp(self):\n self.data1 = [35, 97, 12, 68, 55, 73, 81, 40]\n self.data2 = [12, 35, 40, 55, 68, 73, 81, 97]\n\n # 执行每个测试函数之后要执行的方法\n def tearDown(self):\n pass\n\n def test_seq_search(self):\n \"\"\"测试顺序查找\"\"\"\n self.assertEqual(0, seq_search(self.data1, 35))\n self.assertEqual(2, seq_search(self.data1, 12))\n self.assertEqual(6, seq_search(self.data1, 81))\n self.assertEqual(7, seq_search(self.data1, 40))\n self.assertEqual(-1, seq_search(self.data1, 99))\n self.assertEqual(-1, seq_search(self.data1, 7))\n\n def test_bin_search(self):\n \"\"\"测试二分查找\"\"\"\n self.assertEqual(1, bin_search(self.data2, 35))\n self.assertEqual(0, bin_search(self.data2, 12))\n self.assertEqual(6, bin_search(self.data2, 81))\n self.assertEqual(2, bin_search(self.data2, 40))\n self.assertEqual(7, bin_search(self.data2, 97))\n self.assertEqual(-1, bin_search(self.data2, 7))\n self.assertEqual(-1, bin_search(self.data2, 99))\n\n\n\nFile: Day16-20/code/example23.py\n\n\"\"\"\n协程（coroutine）- 可以在需要时进行切换的相互协作的子程序\n\"\"\"\nimport asyncio\n\nfrom example15 import is_prime\n\n\ndef num_generator(m, n):\n \"\"\"指定范围的数字生成器\"\"\"\n yield from range(m, n + 1)\n\n\nasync def prime_filter(m, n):\n \"\"\"素数过滤器\"\"\"\n primes = []\n for i in num_generator(m, n):\n if is_prime(i):\n print('Prime =>', i)\n primes.append(i)\n\n await asyncio.sleep(0.001)\n return tuple(primes)\n\n\nasync def square_mapper(m, n):\n \"\"\"平方映射器\"\"\"\n squares = []\n for i in num_generator(m, n):\n print('Square =>', i * i)\n squares.append(i * i)\n\n await asyncio.sleep(0.001)\n return squares\n\n\ndef main():\n \"\"\"主函数\"\"\"\n loop = asyncio.get_event_loop()\n future = asyncio.gather(prime_filter(2, 100), square_mapper(1, 100))\n future.add_done_callback(lambda x: print(x.result()))\n loop.run_until_complete(future)\n loop.close()\n\n\nif __name__ == '__main__':\n\tmain()\n\n\n\nFile: Day16-20/code/example17.py\n\n\"\"\"\n多重继承 - 一个类有两个或者两个以上的父类\nMRO - 方法解析顺序 - Method Resolution Order\n当出现菱形继承（钻石继承）的时候，子类到底继承哪个父类的方法\nPython 2.x - 深度优先搜索\nPython 3.x - C3算法 - 类似于广度优先搜索\n\"\"\"\nclass A():\n\n def say_hello(self):\n print('Hello, A')\n\n\nclass B(A):\n pass\n\n\nclass C(A):\n\n def say_hello(self):\n print('Hello, C')\n\n\nclass D(B, C):\n pass\n\n\nclass SetOnceMappingMixin():\n \"\"\"自定义混入类\"\"\"\n __slots__ = ()\n\n def __setitem__(self, key, value):\n if key in self:\n raise KeyError(str(key) + ' already set')\n return super().__setitem__(key, value)\n\n\nclass SetOnceDict(SetOnceMappingMixin, dict):\n \"\"\"自定义字典\"\"\"\n pass\n\n\ndef main():\n print(D.mro())\n # print(D.__mro__)\n D().say_hello()\n print(SetOnceDict.__mro__)\n my_dict= SetOnceDict()\n my_dict['username'] = 'jackfrued'\n my_dict['username'] = 'hellokitty'\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day16-20/code/example07.py\n\n\"\"\"\n哈希摘要 - 数字签名/指纹 - 单向哈希函数（没有反函数不可逆）\n应用领域：\n1. 数据库中的用户敏感信息保存成哈希摘要\n2. 给数据生成签名验证数据没有被恶意篡改\n3. 云存储服务的秒传功能（去重功能）\n\"\"\"\n\n\nclass StreamHasher():\n \"\"\"摘要生成器\"\"\"\n\n def __init__(self, algorithm='md5', size=4096):\n \"\"\"初始化方法\n @params:\n algorithm - 哈希摘要算法\n size - 每次读取数据的大小\n \"\"\"\n self.size = size\n cls = getattr(__import__('hashlib'), algorithm.lower())\n self.hasher = cls()\n \n\n def digest(self, file_stream):\n \"\"\"生成十六进制的摘要字符串\"\"\"\n # data = file_stream.read(self.size)\n # while data:\n # self.hasher.update(data)\n # data = file_stream.read(self.size)\n for data in iter(lambda: file_stream.read(self.size), b''):\n self.hasher.update(data)\n return self.hasher.hexdigest()\n\n def __call__(self, file_stream):\n return self.digest(file_stream)\n\n\ndef main():\n \"\"\"主函数\"\"\"\n hasher1 = StreamHasher()\n hasher2 = StreamHasher('sha1')\n hasher3 = StreamHasher('sha256')\n with open('Python-3.7.2.tar.xz', 'rb') as file_stream:\n print(hasher1.digest(file_stream))\n file_stream.seek(0, 0)\n print(hasher2.digest(file_stream))\n file_stream.seek(0, 0)\n print(hasher3(file_stream))\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day16-20/code/example13.py\n\nfrom example12 import EmployeeFactory\n\n\ndef main():\n \"\"\"主函数\"\"\"\n emps = [\n EmployeeFactory.create('M', '曹操'), \n EmployeeFactory.create('P', '荀彧', 120),\n EmployeeFactory.create('P', '郭嘉', 85), \n EmployeeFactory.create('S', '典韦', 123000),\n ]\n for emp in emps:\n print('%s: %.2f元' % (emp.name, emp.get_salary()))\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day16-20/code/example03.py\n\n\"\"\"\n函数递归调用 - 函数直接或者间接的调用了自身\n1. 收敛条件\n2. 递归公式\n\nn! = n * (n-1)!\nf(n) = f(n-1) + f(n-2)\n1 1 2 3 5 8 13 21 34 55 ...\n\"\"\"\nfrom contextlib import contextmanager\nfrom time import perf_counter\n\n\ndef fac(num):\n \"\"\"求阶乘\"\"\"\n assert num >= 0\n if num in (0, 1):\n return 1\n return num * fac(num - 1)\n\n\ndef fib2(num):\n \"\"\"普通函数\"\"\"\n a, b = 1, 1\n for _ in range(num - 1):\n a, b = b, a + b\n return a\n\n\ndef fib3(num):\n \"\"\"生成器\"\"\"\n a, b = 0, 1\n for _ in range(num):\n a, b = b, a + b\n yield a\n\n\n# 动态规划 - 保存可能进行重复运算的中间结果（空间换时间）\ndef fib(num, results={}):\n \"\"\"斐波拉切数\"\"\"\n assert num > 0\n if num in (1, 2):\n return 1\n try:\n return results[num]\n except KeyError:\n results[num] = fib(num - 1) + fib(num - 2)\n return results[num]\n\n\n@contextmanager\ndef timer():\n try:\n start = perf_counter()\n yield\n finally:\n end = perf_counter()\n print(f'{end - start}秒')\n\n\ndef main():\n \"\"\"主函数\"\"\"\n # for val in fib3(20):\n # print(val)\n # gen = fib3(20)\n # for _ in range(10):\n # print(next(gen))\n for num in range(1, 121):\n with timer():\n print(f'{num}: {fib(num)}')\n # print(fac(5))\n # print(fac(-5))\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day16-20/code/example12.py\n\n\"\"\"\n面向对象的三大支柱：封装、继承、多态\n面向对象的设计原则：SOLID原则\n面向对象的设计模式：GoF设计模式（单例、工厂、代理、策略、迭代器）\n月薪结算系统 - 部门经理每月15000 程序员每小时200 销售员1800底薪加销售额5%提成\n\"\"\"\nfrom abc import ABCMeta, abstractmethod\n\n\nclass Employee(metaclass=ABCMeta):\n \"\"\"员工(抽象类)\"\"\"\n\n def __init__(self, name):\n self.name = name\n\n @abstractmethod\n def get_salary(self):\n \"\"\"结算月薪(抽象方法)\"\"\"\n pass\n\n\nclass Manager(Employee):\n \"\"\"部门经理\"\"\"\n\n def get_salary(self):\n return 15000.0\n\n\nclass Programmer(Employee):\n \"\"\"程序员\"\"\"\n\n def __init__(self, name, working_hour=0):\n self.working_hour = working_hour\n super().__init__(name)\n\n def get_salary(self):\n return 200.0 * self.working_hour\n\n\nclass Salesman(Employee):\n \"\"\"销售员\"\"\"\n\n def __init__(self, name, sales=0.0):\n self.sales = sales\n super().__init__(name)\n\n def get_salary(self):\n return 1800.0 + self.sales * 0.05\n\n\nclass EmployeeFactory():\n \"\"\"创建员工的工厂（工厂模式 - 通过工厂实现对象使用者和对象之间的解耦合）\"\"\"\n\n @staticmethod\n def create(emp_type, *args, **kwargs):\n \"\"\"创建员工\"\"\"\n emp_type = emp_type.upper()\n emp = None\n if emp_type == 'M':\n emp = Manager(*args, **kwargs)\n elif emp_type == 'P':\n emp = Programmer(*args, **kwargs)\n elif emp_type == 'S':\n emp = Salesman(*args, **kwargs)\n return emp\n\n\n\nFile: Day16-20/code/example02.py\n\n\"\"\"\n排序 - 冒泡排序、选择排序、归并排序、快速排序\n冒泡排序 - O(n ** 2)：两两比较，大的下沉\n35, 97, 12, 68, 55, 73, 81, 40\n35, 12, 68, 55, 73, 81, 40, [97]\n12, 35, 55, 68, 73, 40, [81]\n12, 35, 55, 68, 40, [73]\n...\n选择排序 - O(n ** 2)：每次从剩下元素中选择最小\n-----------------------------------------\n归并排序 - O(n * log_2 n) - 高级排序算法\n35, 97, 12, 68, 55, 73, 81, 40\n[35, 97, 12, 68], [55, 73, 81, 40]\n[35, 97], [12, 68], [55, 73], [81, 40]\n[35], [97], [12], [68], [55], [73], [81], [40]\n[35, 97], [12, 68], [55, 73], [40, 81]\n[12, 35, 68, 97], [40, 55, 73, 81]\n[12, 35, 40, 55, 68, 73, 81, 97]\n-----------------------------------------\n快速排序 - 以枢轴为界将列表中的元素划分为两个部分，左边都比枢轴小，右边都比枢轴大\n35, 97, 12, 68, 55, 73, 81, 40\n35, 12, [40], 68, 55, 73, 81, 97\n[12], 35, [40], 68, 55, 73, 81, [97]\n[12], 35, [40], 55, [68], 73, 81, [97]\n[12], 35, [40], 55, [68], 73, [81], [97]\n\"\"\"\n\n\nclass Person(object):\n \"\"\"人\"\"\"\n\n def __init__(self, name, age):\n self.name = name\n self.age = age\n\n # def __gt__(self, other):\n # return self.name > other.name\n\n def __str__(self):\n return f'{self.name}: {self.age}'\n\n def __repr__(self):\n return self.__str__()\n\n\ndef select_sort(origin_items, comp=lambda x, y: x < y):\n \"\"\"简单选择排序\"\"\"\n items = origin_items[:]\n for i in range(len(items) - 1):\n min_index = i\n for j in range(i + 1, len(items)):\n if comp(items[j], items[min_index]):\n min_index = j\n items[i], items[min_index] = items[min_index], items[i]\n return items\n\n\n# 函数的设计要尽量做到无副作用（不影响调用者）\n# 9 1 2 3 4 5 6 7 8\n# 9 2 3 4 5 6 7 8 1\n# *前面的参数叫位置参数，传参时只需要对号入座即可\n# *后面的参数叫命名关键字参数，传参时必须给出参数名和参数值\n# *args - 可变参数 - 元组\n# **kwargs - 关键字参数 - 字典\ndef bubble_sort(origin_items, *, comp=lambda x, y: x > y):\n \"\"\"冒泡排序\"\"\"\n items = origin_items[:]\n for i in range(1, len(items)):\n swapped = False\n for j in range(i - 1, len(items) - i):\n if comp(items[j], items[j + 1]):\n items[j], items[j + 1] = items[j + 1], items[j]\n swapped = True\n if swapped:\n swapped = False\n for j in range(len(items) - i - 1, i - 1, -1):\n if comp(items[j - 1], items[j]):\n items[j], items[j - 1] = items[j - 1], items[j]\n swapped = True\n if not swapped:\n break\n return items\n\n\ndef merge_sort(items, comp=lambda x, y: x <= y):\n \"\"\"归并排序\"\"\"\n if len(items) < 2:\n return items[:]\n mid = len(items) // 2\n left = merge_sort(items[:mid], comp)\n right = merge_sort(items[mid:], comp)\n return merge(left, right, comp)\n\n\ndef merge(items1, items2, comp=lambda x, y: x <= y):\n \"\"\"合并（将两个有序列表合并成一个新的有序列表）\"\"\"\n items = []\n index1, index2 = 0, 0\n while index1 < len(items1) and index2 < len(items2):\n if comp(items1[index1], items2[index2]):\n items.append(items1[index1])\n index1 += 1\n else:\n items.append(items2[index2])\n index2 += 1\n items += items1[index1:]\n items += items2[index2:]\n return items\n\n\ndef quick_sort(origin_items, comp=lambda x, y: x <= y):\n \"\"\"快速排序\"\"\"\n items = origin_items[:]\n _quick_sort(items, 0, len(items) - 1, comp)\n return items\n\n\ndef _quick_sort(items, start, end, comp):\n \"\"\"递归调用划分和排序\"\"\"\n if start < end:\n pos = _partition(items, start, end, comp)\n _quick_sort(items, start, pos - 1, comp)\n _quick_sort(items, pos + 1, end, comp)\n\n\ndef _partition(items, start, end, comp):\n \"\"\"划分\"\"\"\n pivot = items[end]\n i = start - 1\n for j in range(start, end):\n if comp(items[j], pivot):\n i += 1\n items[i], items[j] = items[j], items[i]\n items[i + 1], items[end] = items[end], items[i + 1]\n return i + 1\n\n\ndef main():\n \"\"\"主函数\"\"\"\n items = [35, 97, 12, 68, 55, 73, 81, 40]\n # print(bubble_sort(items))\n # print(select_sort(items))\n # print(merge_sort(items))\n print(quick_sort(items))\n items2 = [\n Person('Wang', 25), Person('Luo', 39),\n Person('Zhang', 50), Person('He', 20)\n ]\n # print(bubble_sort(items2, comp=lambda p1, p2: p1.age > p2.age))\n # print(select_sort(items2, comp=lambda p1, p2: p1.name < p2.name))\n # print(merge_sort(items2, comp=lambda p1, p2: p1.age <= p2.age))\n print(quick_sort(items2, comp=lambda p1, p2: p1.age <= p2.age))\n items3 = ['apple', 'orange', 'watermelon', 'durian', 'pear']\n # print(bubble_sort(items3))\n # print(bubble_sort(items3, comp=lambda x, y: len(x) > len(y)))\n # print(merge_sort(items3))\n print(merge_sort(items3))\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day16-20/code/example22.py\n\n\"\"\"\n多进程和进程池的使用\n多线程因为GIL的存在不能够发挥CPU的多核特性\n对于计算密集型任务应该考虑使用多进程\ntime python3 example22.py\nreal 0m11.512s\nuser 0m39.319s\nsys 0m0.169s\n\"\"\"\nimport concurrent.futures\nimport math\n\nPRIMES = [\n 1116281,\n 1297337,\n 104395303,\n 472882027,\n 533000389,\n 817504243,\n 982451653,\n 112272535095293,\n 112582705942171,\n 112272535095293,\n 115280095190773,\n 115797848077099,\n 1099726899285419\n] * 5\n\n\ndef is_prime(n):\n \"\"\"判断素数\"\"\"\n if n % 2 == 0:\n return False\n\n sqrt_n = int(math.floor(math.sqrt(n)))\n for i in range(3, sqrt_n + 1, 2):\n if n % i == 0:\n return False\n return True\n\n\ndef main():\n \"\"\"主函数\"\"\"\n with concurrent.futures.ProcessPoolExecutor() as executor:\n for number, prime in zip(PRIMES, executor.map(is_prime, PRIMES)):\n print('%d is prime: %s' % (number, prime))\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day16-20/code/example16.py\n\n\"\"\"\n魔术方法\n如果要把自定义对象放到set或者用作dict的键\n那么必须要重写__hash__和__eq__两个魔术方法\n前者用来计算对象的哈希码，后者用来判断两个对象是否相同\n哈希码不同的对象一定是不同的对象，但哈希码相同未必是相同的对象（哈希码冲撞）\n所以在哈希码相同的时候还要通过__eq__来判定对象是否相同\n\"\"\"\n\n\nclass Student():\n __slots__ = ('stuid', 'name', 'gender')\n\n def __init__(self, stuid, name):\n self.stuid = stuid\n self.name = name\n\n def __hash__(self):\n return hash(self.stuid) + hash(self.name)\n\n def __eq__(self, other):\n return self.stuid == other.stuid and \\\n self.name == other.name\n\n def __str__(self):\n return f'{self.stuid}: {self.name}'\n\n def __repr__(self):\n return self.__str__()\n\n\nclass School():\n\n def __init__(self, name):\n self.name = name\n self.students = {}\n\n def __setitem__(self, key, student):\n self.students[key] = student\n\n def __getitem__(self, key):\n return self.students[key]\n\n\ndef main():\n # students = set()\n # students.add(Student(1001, '王大锤'))\n # students.add(Student(1001, '王大锤'))\n # students.add(Student(1001, '白元芳'))\n # print(len(students))\n # print(students)\n stu = Student(1234, '骆昊')\n stu.gender = 'Male'\n # stu.birth = '1980-11-28'\n print(stu.name, stu.birth)\n school = School('千锋教育')\n school[1001] = Student(1001, '王大锤')\n school[1002] = Student(1002, '白元芳')\n school[1003] = Student(1003, '白洁')\n print(school[1002])\n print(school[1003])\n\n\nif __name__ == '__main__':\n main()\n\n\n\n\nFile: Day16-20/code/example06.py\n\n\"\"\"\n编码和解码 - BASE64\n0-9A-Za-z+/\n1100 0101 1001 0011 0111 0110\n00110001 00011001 00001101 00110110\nbase64\nb64encode / b64decode\n-------------------------------------\n序列化和反序列化\n序列化 - 将对象变成字节序列(bytes)或者字符序列(str) - 串行化/腌咸菜\n反序列化 - 把字节序列或者字符序列还原成对象\nPython标准库对序列化的支持：\njson - 字符形式的序列化\npickle - 字节形式的序列化\ndumps / loads\n\"\"\"\nimport base64\nimport json\nimport redis\n\nfrom example02 import Person\n\n\nclass PersonJsonEncoder(json.JSONEncoder):\n\n def default(self, o):\n return o.__dict__\n\n\ndef main():\n cli = redis.StrictRedis(host='120.77.222.217', port=6379, \n password='123123')\n data = base64.b64decode(cli.get('guido'))\n with open('guido2.jpg', 'wb') as file_stream:\n file_stream.write(data)\n # with open('guido.jpg', 'rb') as file_stream:\n # result = base64.b64encode(file_stream.read())\n # cli.set('guido', result)\n # persons = [\n # Person('骆昊', 39), Person('王大锤', 18),\n # Person('白元芳', 25), Person('狄仁杰', 37)\n # ]\n # persons = json.loads(cli.get('persons'))\n # print(persons)\n # cli.set('persons', json.dumps(persons, cls=PersonJsonEncoder))\n\n\nif __name__ == '__main__':\n main()\n\n\n\n\nFile: Day16-20/code/example11.py\n\n\"\"\"\n变量的作用域以及Python搜索变量的顺序\nLEGB: Local --> Embedded --> Global --> Built-in\nglobal - 声明或定义全局变量（要么直接使用现有的全局作用域的变量，要么定义一个变量放到全局作用域）\nnonlocal - 声明使用嵌套作用域的变量（如果嵌套作用域没有对应的变量直接报错）\n\"\"\"\nx = 100\n\n\ndef foo():\n global x\n x = 200\n\n def bar():\n x = 300\n print(x)\n\n bar()\n print(x)\n\n\nfoo()\nprint(x)\n\n\n\nFile: Day16-20/code/example01.py\n\n\"\"\"\n查找 - 顺序查找和二分查找\n算法：解决问题的方法（步骤）\n评价一个算法的好坏主要有两个指标：渐近时间复杂度和渐近空间复杂度，通常一个算法很难做到时间复杂度和空间复杂度都很低（因为时间和空间是不可调和的矛盾）\n表示渐近时间复杂度通常使用大O标记\nO(c)：常量时间复杂度 - 哈希存储 / 布隆过滤器\nO(log_2 n)：对数时间复杂度 - 折半查找\nO(n)：线性时间复杂度 - 顺序查找\nO(n * log_2 n)：- 对数线性时间复杂度 - 高级排序算法（归并排序、快速排序）\nO(n ** 2)：平方时间复杂度 - 简单排序算法（冒泡排序、选择排序、插入排序）\nO(n ** 3)：立方时间复杂度 - Floyd算法 / 矩阵乘法运算\n也称为多项式时间复杂度\nO(2 ** n)：几何级数时间复杂度 - 汉诺塔\nO(3 ** n)：几何级数时间复杂度\n也称为指数时间复杂度\nO(n!)：阶乘时间复杂度 - 旅行经销商问题 - NP\n\"\"\"\nfrom math import log2, factorial\nfrom matplotlib import pyplot\n\nimport numpy\n\n\ndef seq_search(items: list, elem) -> int:\n \"\"\"顺序查找\"\"\"\n for index, item in enumerate(items):\n if elem == item:\n return index\n return -1\n\n\ndef bin_search(items, elem):\n \"\"\"二分查找\"\"\"\n start, end = 0, len(items) - 1\n while start <= end:\n mid = (start + end) // 2\n if elem > items[mid]:\n start = mid + 1\n elif elem < items[mid]:\n end = mid - 1\n else:\n return mid\n return -1\n\n\ndef main():\n \"\"\"主函数（程序入口）\"\"\"\n num = 6\n styles = ['r-.', 'g-*', 'b-o', 'y-x', 'c-^', 'm-+', 'k-d']\n legends = ['对数', '线性', '线性对数', '平方', '立方', '几何级数', '阶乘']\n x_data = [x for x in range(1, num + 1)]\n y_data1 = [log2(y) for y in range(1, num + 1)]\n y_data2 = [y for y in range(1, num + 1)]\n y_data3 = [y * log2(y) for y in range(1, num + 1)]\n y_data4 = [y ** 2 for y in range(1, num + 1)]\n y_data5 = [y ** 3 for y in range(1, num + 1)]\n y_data6 = [3 ** y for y in range(1, num + 1)]\n y_data7 = [factorial(y) for y in range(1, num + 1)]\n y_datas = [y_data1, y_data2, y_data3, y_data4, y_data5, y_data6, y_data7]\n for index, y_data in enumerate(y_datas):\n pyplot.plot(x_data, y_data, styles[index])\n pyplot.legend(legends)\n pyplot.xticks(numpy.arange(1, 7, step=1))\n pyplot.yticks(numpy.arange(0, 751, step=50))\n pyplot.show()\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day16-20/code/example21.py\n\n\"\"\"\n多个线程竞争一个资源 - 保护临界资源 - 锁（Lock/RLock）\n多个线程竞争多个资源（线程数>资源数） - 信号量（Semaphore）\n多个线程的调度 - 暂停线程执行/唤醒等待中的线程 - Condition\n\"\"\"\nfrom concurrent.futures import ThreadPoolExecutor\nfrom random import randint\nfrom time import sleep\n\nimport threading\n\n\nclass Account():\n \"\"\"银行账户\"\"\"\n\n def __init__(self, balance=0):\n self.balance = balance\n lock = threading.Lock()\n self.condition = threading.Condition(lock)\n\n def withdraw(self, money):\n \"\"\"取钱\"\"\"\n with self.condition:\n while money > self.balance:\n self.condition.wait()\n new_balance = self.balance - money\n sleep(0.001)\n self.balance = new_balance\n\n def deposit(self, money):\n \"\"\"存钱\"\"\"\n with self.condition:\n new_balance = self.balance + money\n sleep(0.001)\n self.balance = new_balance\n self.condition.notify_all()\n\n\ndef add_money(account):\n while True:\n money = randint(5, 10)\n account.deposit(money)\n print(threading.current_thread().name,\n ':', money, '====>', account.balance)\n sleep(0.5)\n\n\ndef sub_money(account):\n while True:\n money = randint(10, 30)\n account.withdraw(money)\n print(threading.current_thread().name,\n ':', money, '<====', account.balance)\n sleep(1)\n\n\ndef main():\n account = Account()\n with ThreadPoolExecutor(max_workers=10) as pool:\n for _ in range(5):\n pool.submit(add_money, account)\n pool.submit(sub_money, account)\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day16-20/code/example15.py\n\n\"\"\"\n迭代器 - __iter__ / __next__\nitertools - 生成可迭代序列的工具模块\n\"\"\"\nimport itertools\n\nfrom math import sqrt\n\n\ndef is_prime(num):\n \"\"\"判断素数\"\"\"\n for factor in range(2, int(sqrt(num)) + 1):\n if num % factor == 0:\n return False\n return True\n\n\nclass PrimeIter(object):\n \"\"\"素数迭代器\"\"\"\n\n def __init__(self, min_value, max_value):\n assert 2 <= min_value <= max_value\n self.min_value = min_value - 1\n self.max_value = max_value\n\n def __iter__(self):\n return self\n\n def __next__(self):\n self.min_value += 1\n while self.min_value <= self.max_value:\n if is_prime(self.min_value):\n return self.min_value\n self.min_value += 1\n raise StopIteration()\n\n\nclass FibIter(object):\n \"\"\"斐波那契数迭代器\"\"\"\n \n def __init__(self, num):\n self.num = num\n self.a, self.b = 0, 1\n self.idx = 0\n \n def __iter__(self):\n return self\n\n def __next__(self):\n if self.idx < self.num:\n self.a, self.b = self.b, self.a + self.b\n self.idx += 1\n return self.a\n raise StopIteration()\n\n\ndef main():\n # for val in itertools.permutations('ABCD'):\n # print(val)\n # for val in itertools.combinations('ABCDE', 3):\n # print(val)\n # for val in itertools.product('黑红梅方', range(1, 14)):\n # print(val)\n # fib_iter = FibIter(20)\n # print('===>', next(fib_iter))\n # print('===>', next(fib_iter))\n # for val in fib_iter:\n # print(val)\n prime_iter = PrimeIter(2, 100000)\n for val in prime_iter:\n print(val)\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day16-20/code/example05.py\n\n\"\"\"\n递归回溯法：叫称为试探法，按选优条件向前搜索，当搜索到某一步，\n发现原先选择并不优或达不到目标时，就退回一步重新选择。\n经典问题：骑士巡逻\n\"\"\"\nimport os\nimport sys\nimport time\n\nSIZE = 5\ntotal = 0\n\n\ndef print_board(board):\n # os.system('clear')\n for row in board:\n for col in row:\n print(str(col).center(4), end='')\n print()\n\n\ndef patrol(board, row, col, step=1):\n if row >= 0 and row < SIZE and \\\n col >= 0 and col < SIZE and \\\n board[row][col] == 0:\n board[row][col] = step\n if step == SIZE * SIZE:\n global total\n total += 1\n print(f'第{total}种走法: ')\n print_board(board)\n patrol(board, row - 2, col - 1, step + 1)\n patrol(board, row - 1, col - 2, step + 1)\n patrol(board, row + 1, col - 2, step + 1)\n patrol(board, row + 2, col - 1, step + 1)\n patrol(board, row + 2, col + 1, step + 1)\n patrol(board, row + 1, col + 2, step + 1)\n patrol(board, row - 1, col + 2, step + 1)\n patrol(board, row - 2, col + 1, step + 1)\n board[row][col] = 0\n\n\ndef main():\n board = [[0] * SIZE for _ in range(SIZE)]\n patrol(board, SIZE - 1, SIZE - 1)\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day16-20/code/example20.py\n\n\"\"\"\n线程间通信（共享数据）非常简单因为可以共享同一个进程的内存\n进程间通信（共享数据）比较麻烦因为操作系统会保护分配给进程的内存\n要实现多进程间的通信通常可以用系统管道、套接字、三方服务来实现\nmultiprocessing.Queue\n守护线程 - daemon thread\n守护进程 - firewalld / httpd / mysqld\n在系统停机的时候不保留的进程 - 不会因为进程还没有执行结束而阻碍系统停止\n\"\"\"\nfrom threading import Thread\nfrom time import sleep\n\n\ndef output(content):\n while True:\n print(content, end='')\n\n\ndef main():\n Thread(target=output, args=('Ping', ), daemon=True).start()\n Thread(target=output, args=('Pong', ), daemon=True).start()\n sleep(5)\n print('bye!')\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day16-20/code/example14.py\n\n\"\"\"\n面向对象\n枚举 - 一个变量的值只有有限个选择，最适合的类型就是枚举\n通过枚举我们可以定义符号常量，符号常量优于字面常量\n\"\"\"\nfrom enum import Enum, unique\n\nimport random\n\n\n@unique\nclass Suite(Enum):\n \"\"\"花色（枚举）\"\"\"\n SPADE, HEART, CLUB, DIAMOND = range(4)\n\n def __lt__(self, other):\n return self.value < other.value\n\n\nclass Card():\n \"\"\"牌\"\"\"\n \n def __init__(self, suite, face):\n self.suite = suite\n self.face = face\n\n def __repr__(self):\n return self.__str__()\n\n def __str__(self):\n suites = ('♠️', '♥️', '♣️', '♦️')\n faces = ('', 'A', '2', '3', '4', '5', '6', \n '7', '8', '9', '10', 'J', 'Q', 'K')\n return f'{suites[self.suite.value]} {faces[self.face]}'\n\n\nclass Poker():\n \"\"\"扑克\"\"\"\n \n def __init__(self):\n self.index = 0\n self.cards = [Card(suite, face)\n for suite in Suite\n for face in range(1, 14)]\n\n def shuffle(self):\n \"\"\"洗牌\"\"\"\n self.index = 0\n random.shuffle(self.cards)\n\n def deal(self):\n \"\"\"发牌\"\"\"\n card = self.cards[self.index]\n self.index += 1\n return card\n\n @property\n def has_more(self):\n \"\"\"是否有更多的牌\"\"\"\n return self.index < len(self.cards)\n\n\nclass Player():\n \"\"\"玩家\"\"\"\n\n def __init__(self, name):\n self.name = name\n self.cards = []\n\n def get_card(self, card):\n \"\"\"摸牌\"\"\"\n self.cards.append(card)\n\n def arrange(self):\n \"\"\"整理手上的牌\"\"\"\n self.cards.sort(key=lambda card: (card.suite, card.face))\n\n\ndef main():\n \"\"\"主函数\"\"\"\n poker = Poker()\n poker.shuffle()\n players = [\n Player('东邪'), Player('西毒'), \n Player('南帝'), Player('北丐')\n ]\n while poker.has_more:\n for player in players:\n player.get_card(poker.deal())\n for player in players:\n player.arrange()\n print(player.name, end=': ')\n print(player.cards)\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day16-20/code/example04.py\n\n\"\"\"\n贪婪法：在对问题求解时，总是做出在当前看来是最好的选择，\n不追求最优解，快速找到满意解。\n\"\"\"\nclass Thing(object):\n \"\"\"物品\"\"\"\n\n def __init__(self, name, price, weight):\n self.name = name\n self.price = price\n self.weight = weight\n\n @property\n def value(self):\n \"\"\"价格重量比\"\"\"\n return self.price / self.weight\n\n\ndef input_thing():\n \"\"\"输入物品信息\"\"\"\n name_str, price_str, weight_str = input().split()\n return name_str, int(price_str), int(weight_str)\n\n\ndef main():\n \"\"\"主函数\"\"\"\n max_weight, num_of_things = map(int, input().split())\n all_things = []\n for _ in range(num_of_things):\n all_things.append(Thing(*input_thing()))\n all_things.sort(key=lambda x: x.value, reverse=True)\n total_weight = 0\n total_price = 0\n for thing in all_things:\n if total_weight + thing.weight <= max_weight:\n print(f'小偷拿走了{thing.name}')\n total_weight += thing.weight\n total_price += thing.price\n print(f'总价值: {total_price}美元')\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day16-20/code/example10.py\n\n\"\"\"\n装饰类的装饰器 - 单例模式 - 一个类只能创建出唯一的对象\n上下文语法：\n__enter__ / __exit__\n\"\"\"\nimport threading\n\nfrom functools import wraps\n\n\ndef singleton(cls):\n \"\"\"单例装饰器\"\"\"\n instances = {}\n lock = threading.Lock()\n\n @wraps(cls)\n def wrapper(*args, **kwargs):\n if cls not in instances:\n with lock:\n if cls not in instances:\n instances[cls] = cls(*args, **kwargs)\n return instances[cls]\n\n return wrapper\n\n\n@singleton\nclass President():\n\n def __init__(self, name, country):\n self.name = name\n self.country = country\n\n def __str__(self):\n return f'{self.country}: {self.name}'\n\n\ndef main():\n print(President.__name__)\n p1 = President('特朗普', '美国')\n p2 = President('奥巴马', '美国')\n print(p1 == p2)\n print(p1)\n print(p2)\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day16-20/code/example24.py\n\n\"\"\"\naiohttp - 异步HTTP网络访问\n异步I/O（异步编程）- 只使用一个线程（单线程）来处理用户请求\n用户请求一旦被接纳，剩下的都是I/O操作，通过多路I/O复用也可以达到并发的效果\n这种做法与多线程相比可以让CPU利用率更高，因为没有线程切换的开销\nRedis/Node.js - 单线程 + 异步I/O\nCelery - 将要执行的耗时间的任务异步化处理\n异步I/O事件循环 - uvloop\n\"\"\"\nimport asyncio\nimport re\n\nimport aiohttp\n\n\nasync def fetch(session, url):\n async with session.get(url, ssl=False) as resp:\n return await resp.text()\n\n\nasync def main():\n pattern = re.compile(r'\\<title\\>(?P<title>.*)\\<\\/title\\>')\n urls = ('https://www.python.org/',\n 'https://git-scm.com/',\n 'https://www.jd.com/',\n 'https://www.taobao.com/',\n 'https://www.douban.com/')\n async with aiohttp.ClientSession() as session:\n for url in urls:\n html = await fetch(session, url)\n print(pattern.search(html).group('title'))\n\n\nif __name__ == '__main__':\n loop = asyncio.get_event_loop()\n loop.run_until_complete(main())\n loop.close()\n\n\n\nFile: Day16-20/code/test_example02.py\n\nfrom unittest import TestCase\n\nfrom example02 import select_sort, merge\n\n\nclass TestExample02(TestCase):\n \"\"\"测试排序函数的测试用例\"\"\"\n\n def setUp(self):\n self.data1 = [35, 97, 12, 68, 55, 73, 81, 40]\n self.items1 = [12, 35, 68, 97]\n self.items2 = [40, 55, 73, 81]\n\n def test_merge(self):\n items = merge(self.items1, self.items2)\n for i in range(len(items) - 1):\n self.assertLessEqual(items[i], items[i + 1])\n\n def test_select_sort(self):\n \"\"\"测试顺序查找\"\"\"\n items = select_sort(self.data1)\n for i in range(len(items) - 1):\n self.assertLessEqual(items[i], items[i + 1])\n \n\n\nFile: Day36-45/code/contact/main.py\n\n\"\"\"\n-- 创建名为address的数据库\ncreate database address default charset utf8;\n\n-- 切换到address数据库\nuse address;\n\n-- 创建联系人表tb_contacter\ncreate table tb_contacter\n(\nconid int auto_increment comment '编号',\nconname varchar(31) not null comment '姓名',\ncontel varchar(15) default '' comment '电话',\nconemail varchar(255) default'' comment '邮箱',\nprimary key (conid)\n);\n\"\"\"\nimport pymysql\n\nINSERT_CONTACTER = \"\"\"\ninsert into tb_contacter (conname, contel, conemail) \nvalues (%s, %s, %s)\n\"\"\"\nDELETE_CONTACTER = \"\"\"\ndelete from tb_contacter where conid=%s\n\"\"\"\nUPDATE_CONTACTER = \"\"\"\nupdate tb_contacter set conname=%s, contel=%s, conemail=%s \nwhere conid=%s\n\"\"\"\nSELECT_CONTACTERS = \"\"\"\nselect conid as id, conname as name, contel as tel, conemail as email \nfrom tb_contacter limit %s offset %s\n\"\"\"\nSELECT_CONTACTERS_BY_NAME = \"\"\"\nselect conid as id, conname as name, contel as tel, conemail as email \nfrom tb_contacter where conname like %s\n\"\"\"\nCOUNT_CONTACTERS = \"\"\"\nselect count(conid) as total from tb_contacter\n\"\"\"\n\n\nclass Contacter(object):\n\n def __init__(self, id, name, tel, email):\n self.id = id\n self.name = name\n self.tel = tel\n self.email = email\n\n\ndef input_contacter_info():\n name = input('姓名: ')\n tel = input('手机: ')\n email = input('邮箱: ')\n return name, tel, email\n\n\ndef add_new_contacter(con):\n name, tel, email = input_contacter_info()\n try:\n with con.cursor() as cursor:\n if cursor.execute(INSERT_CONTACTER,\n (name, tel, email)) == 1:\n print('添加联系人成功!')\n except pymysql.MySQLError as err:\n print(err)\n print('添加联系人失败!')\n\n\ndef delete_contacter(con, contacter):\n try:\n with con.cursor() as cursor:\n if cursor.execute(DELETE_CONTACTER, (contacter.id, )) == 1:\n print('联系人已经删除!')\n except pymysql.MySQLError as err:\n print(err)\n print('删除联系人失败!')\n\n\ndef edit_contacter_info(con, contacter):\n name, tel, email = input_contacter_info()\n contacter.name = name or contacter.name\n contacter.tel = tel or contacter.tel\n contacter.email = email or contacter.email\n try:\n with con.cursor() as cursor:\n if cursor.execute(UPDATE_CONTACTER,\n (contacter.name, contacter.tel,\n contacter.email, contacter.id)) == 1:\n print('联系人信息已经更新!')\n except pymysql.MySQLError as err:\n print(err)\n print('更新联系人信息失败!')\n\n\ndef show_contacter_detail(con, contacter):\n print('姓名:', contacter.name)\n print('手机号:', contacter.tel)\n print('邮箱:', contacter.email)\n choice = input('是否编辑联系人信息?(yes|no)')\n if choice == 'yes':\n edit_contacter_info(con, contacter)\n else:\n choice = input('是否删除联系人信息?(yes|no)')\n if choice == 'yes':\n delete_contacter(con, contacter)\n\n\ndef show_search_result(con, cursor):\n contacters_list = []\n for index, row in enumerate(cursor.fetchall()):\n contacter = Contacter(**row)\n contacters_list.append(contacter)\n print('[%d]: %s' % (index, contacter.name))\n if len(contacters_list) > 0:\n choice = input('是否查看联系人详情?(yes|no)')\n if choice.lower() == 'yes':\n index = int(input('请输入编号: '))\n if 0 <= index < cursor.rowcount:\n show_contacter_detail(con, contacters_list[index])\n\n\ndef find_all_contacters(con):\n page, size = 1, 5\n try:\n with con.cursor() as cursor:\n cursor.execute(COUNT_CONTACTERS)\n total = cursor.fetchone()['total']\n while True:\n cursor.execute(SELECT_CONTACTERS,\n (size, (page - 1) * size))\n show_search_result(con, cursor)\n if page * size < total:\n choice = input('继续查看下一页?(yes|no)')\n if choice.lower() == 'yes':\n page += 1\n else:\n break\n else:\n print('没有下一页记录!')\n break\n except pymysql.MySQLError as err:\n print(err)\n\n\ndef find_contacters_by_name(con):\n name = input('联系人姓名: ')\n try:\n with con.cursor() as cursor:\n cursor.execute(SELECT_CONTACTERS_BY_NAME,\n ('%' + name + '%', ))\n show_search_result(con, cursor)\n except pymysql.MySQLError as err:\n print(err)\n\n\ndef find_contacters(con):\n while True:\n print('1. 查看所有联系人')\n print('2. 搜索联系人')\n print('3. 退出查找')\n choice = int(input('请输入: '))\n if choice == 1:\n find_all_contacters(con)\n elif choice == 2:\n find_contacters_by_name(con)\n elif choice == 3:\n break\n\n\ndef main():\n con = pymysql.connect(host='1.2.3.4', port=3306,\n user='yourname', passwd='yourpass',\n db='address', charset='utf8',\n autocommit=True,\n cursorclass=pymysql.cursors.DictCursor)\n while True:\n print('=====通讯录=====')\n print('1. 新建联系人')\n print('2. 查找联系人')\n print('3. 退出系统')\n print('===============')\n choice = int(input('请选择: '))\n if choice == 1:\n add_new_contacter(con)\n elif choice == 2:\n find_contacters(con)\n elif choice == 3:\n con.close()\n print('谢谢使用, 再见！')\n break\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day46-60/code/hellodjango/manage.py\n\n#!/usr/bin/env python\n\"\"\"Django's command-line utility for administrative tasks.\"\"\"\nimport os\nimport sys\n\n\ndef main():\n os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'hellodjango.settings')\n try:\n from django.core.management import execute_from_command_line\n except ImportError as exc:\n raise ImportError(\n \"Couldn't import Django. Are you sure it's installed and \"\n \"available on your PYTHONPATH environment variable? Did you \"\n \"forget to activate a virtual environment?\"\n ) from exc\n execute_from_command_line(sys.argv)\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day46-60/code/hellodjango/first/models.py\n\nfrom django.db import models\n\n# Create your models here.\n\n\n\nFile: Day46-60/code/hellodjango/first/__init__.py\n\n\n\n\nFile: Day46-60/code/hellodjango/first/apps.py\n\nfrom django.apps import AppConfig\n\n\nclass FirstConfig(AppConfig):\n name = 'first'\n\n\n\nFile: Day46-60/code/hellodjango/first/admin.py\n\nfrom django.contrib import admin\n\n# Register your models here.\n\n\n\nFile: Day46-60/code/hellodjango/first/tests.py\n\nfrom django.test import TestCase\n\n# Create your tests here.\n\n\n\nFile: Day46-60/code/hellodjango/first/views.py\n\nfrom random import sample\n\nfrom django.shortcuts import render\n\n\ndef show_index(request):\n fruits = [\n 'Apple', 'Orange', 'Pitaya', 'Durian', 'Waxberry', 'Blueberry',\n 'Grape', 'Peach', 'Pear', 'Banana', 'Watermelon', 'Mango'\n ]\n return render(request, 'index.html', {'fruits': sample(fruits, 3)})\n\n\n\nFile: Day46-60/code/hellodjango/first/migrations/__init__.py\n\n\n\n\nFile: Day46-60/code/hellodjango/hellodjango/__init__.py\n\n\n\n\nFile: Day46-60/code/hellodjango/hellodjango/settings.py\n\n\"\"\"\nDjango settings for hellodjango project.\n\nGenerated by 'django-admin startproject' using Django 2.2.13.\n\nFor more information on this file, see\nhttps://docs.djangoproject.com/en/2.2/topics/settings/\n\nFor the full list of settings and their values, see\nhttps://docs.djangoproject.com/en/2.2/ref/settings/\n\"\"\"\n\nimport os\n\n# Build paths inside the project like this: os.path.join(BASE_DIR, ...)\nBASE_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))\n\n\n# Quick-start development settings - unsuitable for production\n# See https://docs.djangoproject.com/en/2.2/howto/deployment/checklist/\n\n# SECURITY WARNING: keep the secret key used in production secret!\nSECRET_KEY = 'x)q$(0m0^ttqii@^zn^9bdbh&%l$)wzjm=nv&_y+^y9e!37=-z'\n\n# SECURITY WARNING: don't run with debug turned on in production!\nDEBUG = True\n\nALLOWED_HOSTS = []\n\n\n# Application definition\n\nINSTALLED_APPS = [\n 'django.contrib.admin',\n 'django.contrib.auth',\n 'django.contrib.contenttypes',\n 'django.contrib.sessions',\n 'django.contrib.messages',\n 'django.contrib.staticfiles',\n]\n\nMIDDLEWARE = [\n 'django.middleware.security.SecurityMiddleware',\n 'django.contrib.sessions.middleware.SessionMiddleware',\n 'django.middleware.common.CommonMiddleware',\n 'django.middleware.csrf.CsrfViewMiddleware',\n 'django.contrib.auth.middleware.AuthenticationMiddleware',\n 'django.contrib.messages.middleware.MessageMiddleware',\n 'django.middleware.clickjacking.XFrameOptionsMiddleware',\n]\n\nROOT_URLCONF = 'hellodjango.urls'\n\nTEMPLATES = [\n {\n 'BACKEND': 'django.template.backends.django.DjangoTemplates',\n 'DIRS': [os.path.join(BASE_DIR, 'templates')],\n 'APP_DIRS': True,\n 'OPTIONS': {\n 'context_processors': [\n 'django.template.context_processors.debug',\n 'django.template.context_processors.request',\n 'django.contrib.auth.context_processors.auth',\n 'django.contrib.messages.context_processors.messages',\n ],\n },\n },\n]\n\nWSGI_APPLICATION = 'hellodjango.wsgi.application'\n\n\n# Database\n# https://docs.djangoproject.com/en/2.2/ref/settings/#databases\n\nDATABASES = {\n 'default': {\n 'ENGINE': 'django.db.backends.sqlite3',\n 'NAME': os.path.join(BASE_DIR, 'db.sqlite3'),\n }\n}\n\n\n# Password validation\n# https://docs.djangoproject.com/en/2.2/ref/settings/#auth-password-validators\n\nAUTH_PASSWORD_VALIDATORS = [\n {\n 'NAME': 'django.contrib.auth.password_validation.UserAttributeSimilarityValidator',\n },\n {\n 'NAME': 'django.contrib.auth.password_validation.MinimumLengthValidator',\n },\n {\n 'NAME': 'django.contrib.auth.password_validation.CommonPasswordValidator',\n },\n {\n 'NAME': 'django.contrib.auth.password_validation.NumericPasswordValidator',\n },\n]\n\n\n# Internationalization\n# https://docs.djangoproject.com/en/2.2/topics/i18n/\n\nLANGUAGE_CODE = 'en-us'\n\nTIME_ZONE = 'UTC'\n\nUSE_I18N = True\n\nUSE_L10N = True\n\nUSE_TZ = True\n\n\n# Static files (CSS, JavaScript, Images)\n# https://docs.djangoproject.com/en/2.2/howto/static-files/\n\nSTATIC_URL = '/static/'\n\n\n\nFile: Day46-60/code/hellodjango/hellodjango/urls.py\n\n\"\"\"hellodjango URL Configuration\n\nThe `urlpatterns` list routes URLs to views. For more information please see:\n https://docs.djangoproject.com/en/2.2/topics/http/urls/\nExamples:\nFunction views\n 1. Add an import: from my_app import views\n 2. Add a URL to urlpatterns: path('', views.home, name='home')\nClass-based views\n 1. Add an import: from other_app.views import Home\n 2. Add a URL to urlpatterns: path('', Home.as_view(), name='home')\nIncluding another URLconf\n 1. Import the include() function: from django.urls import include, path\n 2. Add a URL to urlpatterns: path('blog/', include('blog.urls'))\n\"\"\"\nfrom django.contrib import admin\nfrom django.urls import path\n\nfrom first.views import show_index\n\nurlpatterns = [\n path('admin/', admin.site.urls),\n path('hello/', show_index),\n]\n\n\n\nFile: Day46-60/code/hellodjango/hellodjango/wsgi.py\n\n\"\"\"\nWSGI config for hellodjango project.\n\nIt exposes the WSGI callable as a module-level variable named ``application``.\n\nFor more information on this file, see\nhttps://docs.djangoproject.com/en/2.2/howto/deployment/wsgi/\n\"\"\"\n\nimport os\n\nfrom django.core.wsgi import get_wsgi_application\n\nos.environ.setdefault('DJANGO_SETTINGS_MODULE', 'hellodjango.settings')\n\napplication = get_wsgi_application()\n\n\n\nFile: 番外篇/code/test03.py\n\nfrom random import randint, sample\n\n# 初始化备选红色球\nred_balls = [x for x in range(1, 34)]\n# 选出六个红色球\nselected_balls = sample(red_balls, 6)\n# 对红色球进行排序\nselected_balls.sort()\n# 添加一个蓝色球\nselected_balls.append(randint(1, 16))\n# 输出选中的随机号码\nfor index, ball in enumerate(selected_balls):\n print('%02d' % ball, end=' ')\n if index == len(selected_balls) - 2:\n print('|', end=' ')\nprint()\n\n\nFile: 番外篇/code/test02.py\n\nprint(sum(range(1, 101)))\n\n\nFile: 番外篇/code/test.py\n\ndef merge(items1, items2):\n items3 = []\n index1, index2 = 0, 0\n while index1 < len(items) and index2 < len(items2):\n if items[index1] < items2[index2]:\n items3.append(items1[index1])\n index1 += 1\n else:\n items3.append(items2[index2])\n index2 += 1\n\n\n\nFile: 番外篇/code/test01.py\n\nprint('hello, world!')\n\n\nFile: 公开课/文档/第05次公开课-算法入门系列1-周而复始/code/example03.py\n\na, b = 0, 1\nfor num in range(1, 101):\n a, b = b, a + b\n print(f'{num}: {a}')\n\n\n\n\nFile: 公开课/文档/第05次公开课-算法入门系列1-周而复始/code/example02.py\n\nnums = []\nfor i in range(100000):\n nums.insert(0, i)\nprint(nums)\n\n\n\nFile: 公开课/文档/第05次公开课-算法入门系列1-周而复始/code/example06.py\n\nimport re\n\nimport PyPDF2\n\nwith open('Python_Tricks_encrypted.pdf', 'rb') as pdf_file_stream:\n reader = PyPDF2.PdfFileReader(pdf_file_stream)\n with open('dictionary.txt', 'r') as txt_file_stream:\n file_iter = iter(lambda: txt_file_stream.readline(), '')\n for word in file_iter:\n word = re.sub(r'\\s', '', word)\n if reader.decrypt(word):\n print(word)\n break\n\n\n\n\nFile: 公开课/文档/第05次公开课-算法入门系列1-周而复始/code/example01.py\n\nnums = []\nfor i in range(100000):\n nums.append(i)\nnums.reverse()\nprint(nums)\n\n\n\nFile: 公开课/文档/第05次公开课-算法入门系列1-周而复始/code/example05.py\n\n\"\"\"\n公鸡5元一只，母鸡3元一只，小鸡1元三只，用100元买一百只鸡，问公鸡、母鸡、小鸡各有多少只？\n\"\"\"\nfor x in range(21):\n for y in range(34):\n z = 100 - x - y\n if z % 3 == 0 and 5 * x + 3 * y + z // 3 == 100:\n print(x, y, z)\n\n\n\n\nFile: 公开课/文档/第05次公开课-算法入门系列1-周而复始/code/example04.py\n\nfrom functools import lru_cache\n\n\n@lru_cache()\ndef fib(num):\n if num in (1, 2):\n return 1\n return fib(num - 1) + fib(num - 2)\n\n\nfor num in range(1, 101):\n print(f'{num}: {fib(num)}')\n\n\n\nFile: 公开课/文档/第04次公开课-好玩的Python/code/example01.py\n\nfrom PIL import Image, ImageFilter\n\n\nchiling = Image.open('resources/chiling.jpg')\nwidth, height = chiling.size\nchiling.show()\nchiling.transpose(Image.FLIP_LEFT_RIGHT).show()\nchiling.filter(ImageFilter.GaussianBlur(4)).show()\nchiling.filter(ImageFilter.EMBOSS).show()\nchiling.thumbnail((width // 4, height // 4))\nchiling.show()\n\n\n\nFile: 公开课/文档/年薪50W+的Python程序员如何写代码/code/Python/opencourse/part01/example09.py\n\nimport copy\n\n\nclass PrototypeMeta(type):\n\n def __init__(cls, *args, **kwargs):\n super().__init__(*args, **kwargs)\n cls.clone = lambda self, is_deep=True: \\\n copy.deepcopy(self) if is_deep else copy.copy(self)\n\n\nclass Student(metaclass=PrototypeMeta):\n pass\n\n\nstu1 = Student()\nstu2 = stu1.clone()\nprint(stu1 == stu2)\nprint(id(stu1), id(stu2))\n\n\n\nFile: 公开课/文档/年薪50W+的Python程序员如何写代码/code/Python/opencourse/part01/example08.py\n\nfrom functools import wraps\nfrom threading import RLock\n\n\ndef singleton(cls):\n instances = {}\n lock = RLock()\n\n @wraps(cls)\n def wrapper(*args, **kwargs):\n if cls not in instances:\n with lock:\n if cls not in instances:\n instances[cls] = cls(*args, **kwargs)\n return instances[cls]\n\n\n@singleton\nclass President:\n pass\n\n\nPresident = President.__wrapped__\n\n\n\nFile: 公开课/文档/年薪50W+的Python程序员如何写代码/code/Python/opencourse/part01/example07.py\n\nfrom functools import lru_cache\n\n\n@lru_cache()\ndef fib(num):\n if num in (1, 2):\n return 1\n return fib(num - 1) + fib(num - 2)\n\n\nfor n in range(1, 121):\n print(f'{n}: {fib(n)}')\n\n\n\nFile: 公开课/文档/年薪50W+的Python程序员如何写代码/code/Python/opencourse/part01/example03.py\n\nvalues = [True] * 10\nprint(values)\nnumbers = [x for x in range(1, 11)]\nprint(numbers)\n\n\n\nFile: 公开课/文档/年薪50W+的Python程序员如何写代码/code/Python/opencourse/part01/example02.py\n\nprint(sum(range(1, 101)))\n\n\n\nFile: 公开课/文档/年薪50W+的Python程序员如何写代码/code/Python/opencourse/part01/example06.py\n\n# 一行代码实现求阶乘函数\nfac = lambda x: __import__('functools').reduce(int.__mul__, range(1, x + 1), 1)\nprint(fac(5))\n\n# 一行代码实现求最大公约数函数\ngcd = lambda x, y: y % x and gcd(y % x, x) or x\nprint(gcd(15, 27))\n\n# 一行代码实现判断素数的函数\nis_prime = lambda x: x > 1 and not [f for f in range(2, int(x ** 0.5) + 1) if x % f == 0]\nfor num in range(2, 100):\n if is_prime(num):\n print(num, end=' ')\nprint()\n\n# 一行代码实现快速排序\nquick_sort = lambda items: len(items) and quick_sort([x for x in items[1:] if x < items[0]]) \\\n + [items[0]] + quick_sort([x for x in items[1:] if x > items[0]]) \\\n or items\nitems = [57, 12, 35, 68, 99, 81, 70, 22]\nprint(quick_sort(items))\n\n# 生成FizzBuzz列表\n# 1 2 Fizz 4 Buzz 6 ... 14 ... FizzBuzz 16 ... 100\nprint(['Fizz'[x % 3 * 4:] + 'Buzz'[x % 5 * 4:] or x for x in range(1, 101)])\n\n\n\nFile: 公开课/文档/年薪50W+的Python程序员如何写代码/code/Python/opencourse/part01/example01.py\n\nprint('hello, world')\n\n\n\nFile: 公开课/文档/年薪50W+的Python程序员如何写代码/code/Python/opencourse/part01/example05.py\n\nfrom http.server import HTTPServer, SimpleHTTPRequestHandler\n\n\nclass RequestHandler(SimpleHTTPRequestHandler):\n\n def do_GET(self):\n self.send_response(200)\n self.end_headers()\n self.wfile.write('<h1>goodbye, world</h1>'.encode())\n\n\nserver = HTTPServer(('', 8000), RequestHandler)\nserver.serve_forever()\n\n\n\nFile: 公开课/文档/年薪50W+的Python程序员如何写代码/code/Python/opencourse/part01/example04.py\n\nfrom random import randint, sample\n\n\ndef generate():\n \"\"\"生成一组随机号码\"\"\"\n red_balls = [x for x in range(1, 34)]\n selected_balls = sample(red_balls, 6)\n selected_balls.sort()\n selected_balls.append(randint(1, 16))\n return selected_balls\n\n\ndef display(balls):\n \"\"\"输出一组双色球号码\"\"\"\n for index, ball in enumerate(balls):\n print(f'{ball:0>2d}', end=' ')\n if index == len(balls) - 2:\n print('|', end=' ')\n print()\n\n\nnum = int(input('机选几注: '))\nfor _ in range(num):\n display(generate())\n\n\n\nFile: 公开课/文档/年薪50W+的Python程序员如何写代码/code/Python/opencourse/part01/example10.py\n\nimport random\nimport time\n\nimport requests\nfrom bs4 import BeautifulSoup\n\nfor page in range(10):\n resp = requests.get(\n url=f'https://movie.douban.com/top250?start={25 * page}',\n headers={'User-Agent': 'BaiduSpider'}\n )\n soup = BeautifulSoup(resp.text, \"lxml\")\n for elem in soup.select('a > span.title:nth-child(1)'):\n print(elem.text)\n time.sleep(random.random() * 5)\n\n\n\nFile: 公开课/文档/年薪50W+的Python程序员如何写代码/code/Python/opencourse/part02/idiom04.py\n\nfruits = ['orange', 'grape', 'pitaya', 'blueberry']\n\n# index = 0\n# for fruit in fruits:\n# print(index, ':', fruit)\n# index += 1\n\nfor index, fruit in enumerate(fruits):\n print(index, ':', fruit)\n\n\n\nFile: 公开课/文档/年薪50W+的Python程序员如何写代码/code/Python/opencourse/part02/idiom05.py\n\ndata = [7, 20, 3, 15, 11]\n\n# result = []\n# for i in data:\n# if i > 10:\n# result.append(i * 3)\n\nresult = [num * 3 for num in data if num > 10]\nprint(result)\n\n\n\nFile: 公开课/文档/年薪50W+的Python程序员如何写代码/code/Python/opencourse/part02/idiom01.py\n\nname = 'jackfrued'\nfruits = ['apple', 'orange', 'grape']\nowners = {'name': '骆昊', 'age': 40, 'gender': True}\n\n# if name != '' and len(fruits) > 0 and len(owners.keys()) > 0:\n# print('Jackfrued love fruits.')\n\nif name and fruits and owners:\n print('Jackfrued love fruits.')\n\n\n\nFile: 公开课/文档/年薪50W+的Python程序员如何写代码/code/Python/opencourse/part02/idiom06.py\n\ndata = {'x': '5'}\n\n# if 'x' in data and isinstance(data['x'], (str, int, float)) \\\n# and data['x'].isdigit():\n# value = int(data['x'])\n# print(value)\n# else:\n# value = None\n\ntry:\n value = int(data['x'])\n print(value)\nexcept (KeyError, TypeError, ValueError):\n value = None\n\n\n\nFile: 公开课/文档/年薪50W+的Python程序员如何写代码/code/Python/opencourse/part02/idiom02.py\n\na, b = 5, 10\n\n# temp = a\n# a = b\n# b = a\n\na, b = b, a\nprint(f'a = {a}, b = {b}')\n\n\n\nFile: 公开课/文档/年薪50W+的Python程序员如何写代码/code/Python/opencourse/part02/idiom03.py\n\nchars = ['j', 'a', 'c', 'k', 'f', 'r', 'u', 'e', 'd']\n\n# name = ''\n# for char in chars:\n# name += char\n\nname = ''.join(chars)\nprint(name)\n\n\n\nFile: 公开课/文档/年薪50W+的Python程序员如何写代码/code/Python/opencourse/part04/example.py\n\nimport cProfile\n\n\n# @profile\ndef is_prime(num):\n for factor in range(2, int(num ** 0.5) + 1):\n if num % factor == 0:\n return False\n return True\n\n\nclass PrimeIter:\n\n def __init__(self, total):\n self.counter = 0\n self.current = 1\n self.total = total\n\n def __iter__(self):\n return self\n\n def __next__(self):\n if self.counter < self.total:\n self.current += 1\n while not is_prime(self.current):\n self.current += 1\n self.counter += 1\n return self.current\n raise StopIteration()\n\n\n@profile\ndef eat_memory():\n items = []\n for _ in range(1000000):\n items.append(object())\n return items\n\n\ndef main():\n eat_memory()\n # list(PrimeIter(1000))\n # cProfile.run('list(PrimeIter(10000))')\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: 公开课/文档/年薪50W+的Python程序员如何写代码/code/Python/opencourse/part03/example.py\n\n\"\"\"\n扑克\n\"\"\"\nimport enum\nimport random\n\n\n@enum.unique\nclass Suite(enum.Enum):\n \"\"\"花色(枚举)\"\"\"\n SPADE, HEART, CLUB, DIAMOND = range(4)\n\n\nclass Card:\n \"\"\"牌\"\"\"\n\n def __init__(self, suite, face):\n self.suite = suite\n self.face = face\n\n def __repr__(self):\n suites = '♠♥♣♦'\n faces = ['', 'A', '2', '3', '4', '5', '6', '7', '8', '9', '10', 'J', 'Q', 'K']\n return f'{suites[self.suite.value]}{faces[self.face]}'\n\n\nclass Poker:\n \"\"\"扑克\"\"\"\n\n def __init__(self):\n self.cards = [Card(suite, face) for suite in Suite\n for face in range(1, 14)]\n self.current = 0\n\n def shuffle(self):\n \"\"\"洗牌\"\"\"\n self.current = 0\n random.shuffle(self.cards)\n\n def deal(self):\n \"\"\"发牌\"\"\"\n card = self.cards[self.current]\n self.current += 1\n return card\n\n @property\n def has_next(self):\n \"\"\"还有没有牌可以发\"\"\"\n return self.current < len(self.cards)\n\n\ndef main():\n \"\"\"主函数（程序入口）\"\"\"\n poker = Poker()\n poker.shuffle()\n print(poker.cards)\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: 公开课/文档/第06次公开课-算法入门系列2-在水一方/code/example03.py\n\n\"\"\"\n迷宫寻路\n\"\"\"\nimport random\nimport sys\n\nWALL = -1\nROAD = 0\n\nROWS = 10\nCOLS = 10\n\n\ndef find_way(maze, i=0, j=0, step=1):\n \"\"\"走迷宫\"\"\"\n if 0 <= i < ROWS and 0 <= j < COLS and maze[i][j] == 0:\n maze[i][j] = step\n if i == ROWS - 1 and j == COLS - 1:\n print('=' * 20)\n display(maze)\n sys.exit(0)\n find_way(maze, i + 1, j, step + 1)\n find_way(maze, i, j + 1, step + 1)\n find_way(maze, i - 1, j, step + 1)\n find_way(maze, i, j - 1, step + 1)\n maze[i][j] = ROAD\n\n\ndef reset(maze):\n \"\"\"重置迷宫\"\"\"\n for i in range(ROWS):\n for j in range(COLS):\n num = random.randint(1, 10)\n maze[i][j] = WALL if num > 7 else ROAD\n maze[0][0] = maze[ROWS - 1][COLS - 1] = ROAD\n\n\ndef display(maze):\n \"\"\"显示迷宫\"\"\"\n for row in maze:\n for col in row:\n if col == -1:\n print('■', end=' ')\n elif col == 0:\n print('□', end=' ')\n else:\n print(f'{col}'.ljust(2), end='')\n print()\n\n\ndef main():\n \"\"\"主函数\"\"\"\n maze = [[0] * COLS for _ in range(ROWS)]\n reset(maze)\n display(maze)\n find_way(maze)\n print('没有出路!!!')\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: 公开课/文档/第06次公开课-算法入门系列2-在水一方/code/example02.py\n\ndef climb(num):\n a, b, c = 1, 2, 4\n for _ in range(num - 1):\n a, b, c = b, c, a + b + c\n return a\n\n\ndef main():\n n = int(input('台阶数量: '))\n print(climb(n))\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: 公开课/文档/第06次公开课-算法入门系列2-在水一方/code/example01.py\n\nimport sys\n\n\ndef fac(num):\n if num == 0:\n return 1\n return num * fac(num - 1)\n\n\ndef main():\n print(fac(59996))\n\n\nif __name__ == '__main__':\n sys.setrecursionlimit(60000)\n main()\n# for i in range(1000):\n# print(f'{i}:'.rjust(3), fac(i))\n\n\n\n\nFile: 公开课/文档/第06次公开课-算法入门系列2-在水一方/code/example05.py\n\nsize = 25\n\nfor i in range(size):\n for j in range(size):\n if i % 2 == 1 or j % 2 == 1:\n print('■', end='')\n else:\n print('□', end='')\n print()\n \n\n\n\nFile: 公开课/文档/第06次公开课-算法入门系列2-在水一方/code/example04.py\n\n\"\"\"\n骑士巡逻\n\"\"\"\nimport sys\n\nSIZE = 8\n\n\ndef display(board):\n \"\"\"显示棋盘\"\"\"\n for row in board:\n for col in row:\n print(f'{col}'.rjust(2, '0'), end=' ')\n print()\n\n\ndef patrol(board, i=0, j=0, step=1):\n \"\"\"巡逻\"\"\"\n if 0 <= i < SIZE and 0 <= j < SIZE and board[i][j] == 0:\n board[i][j] = step\n if step == SIZE * SIZE:\n display(board)\n sys.exit(0)\n patrol(board, i + 1, j + 2, step + 1)\n patrol(board, i + 2, j + 1, step + 1)\n patrol(board, i + 2, j - 1, step + 1)\n patrol(board, i + 1, j - 2, step + 1)\n patrol(board, i - 1, j - 2, step + 1)\n patrol(board, i - 2, j - 1, step + 1)\n patrol(board, i - 2, j + 1, step + 1)\n patrol(board, i - 1, j + 2, step + 1)\n board[i][j] = 0\n\n\ndef main():\n \"\"\"主函数\"\"\"\n board = [[0] * SIZE for _ in range(SIZE)]\n patrol(board)\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day01-15/code/Day07/lottery.py\n\n\"\"\"\n双色球随机选号程序\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-06\n\"\"\"\n\nfrom random import randrange, randint, sample\n\n\ndef display(balls):\n \"\"\"\n 输出列表中的双色球号码\n \"\"\"\n for index, ball in enumerate(balls):\n if index == len(balls) - 1:\n print('|', end=' ')\n print('%02d' % ball, end=' ')\n print()\n\n\ndef random_select():\n \"\"\"\n 随机选择一组号码\n \"\"\"\n red_balls = [x for x in range(1, 34)]\n selected_balls = []\n for _ in range(6):\n index = randrange(len(red_balls))\n selected_balls.append(red_balls[index])\n del red_balls[index]\n # 上面的for循环也可以写成下面这行代码\n # sample函数是random模块下的函数\n # selected_balls = sample(red_balls, 6)\n selected_balls.sort()\n selected_balls.append(randint(1, 16))\n return selected_balls\n\n\ndef main():\n n = int(input('机选几注: '))\n for _ in range(n):\n display(random_select())\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day01-15/code/Day07/marquee.py\n\n\"\"\"\n输入学生考试成绩计算平均分\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-06\n\"\"\"\n\nimport os\nimport time\n\n\ndef main():\n str = 'Welcome to 1000 Phone Chengdu Campus '\n while True:\n print(str)\n time.sleep(0.2)\n str = str[1:] + str[0:1]\n # for Windows use os.system('cls') instead\n os.system('clear')\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day01-15/code/Day07/tuple.py\n\n\"\"\"\n元组的定义和使用\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-06\n\"\"\"\n\n\ndef main():\n # 定义元组\n t = ('骆昊', 38, True, '四川成都')\n print(t)\n # 获取元组中的元素\n print(t[0])\n print(t[1])\n print(t[2])\n print(t[3])\n # 遍历元组中的值\n for member in t:\n print(member)\n # 重新给元组赋值\n # t[0] = '王大锤' # TypeError\n # 变量t重新引用了新的元组 原来的元组被垃圾回收\n t = ('王大锤', 20, True, '云南昆明')\n print(t)\n # 元组和列表的转换\n person = list(t)\n print(person)\n person[0] = '李小龙'\n person[1] = 25\n print(person)\n fruits_list = ['apple', 'banana', 'orange']\n fruits_tuple = tuple(fruits_list)\n print(fruits_tuple)\n print(fruits_tuple[1])\n\n\nif __name__ == '__main__':\n main()\n\n\nFile: Day01-15/code/Day07/list3.py\n\n\"\"\"\n生成列表\n- 用range创建数字列表\n- 生成表达式\n- 生成器\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-06\n\"\"\"\n\n\n# 生成Fibonacci序列的生成器\ndef fib(n):\n a, b = 0, 1\n for _ in range(n):\n a, b = b, a + b\n yield a\n\n\ndef main():\n # 用range创建数值列表\n list1 = list(range(1, 11))\n print(list1)\n # 生成表达式\n list2 = [x * x for x in range(1, 11)]\n print(list2)\n list3 = [m + n for m in 'ABCDEFG' for n in '12345']\n print(list3)\n print(len(list3))\n # 生成器(节省空间但生成下一个元素时需要花费时间)\n gen = (m + n for m in 'ABCDEFG' for n in '12345')\n print(gen)\n for elem in gen:\n print(elem, end=' ')\n print()\n gen = fib(20)\n print(gen)\n for elem in gen:\n print(elem, end=' ')\n print()\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day01-15/code/Day07/tic-tac-toe.py\n\n\"\"\"\n井字棋游戏\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-06\n\"\"\"\n\nimport os\n\n\n\ndef print_board(board):\n print(board['TL'] + '|' + board['TM'] + '|' + board['TR'])\n print('-+-+-')\n print(board['ML'] + '|' + board['MM'] + '|' + board['MR'])\n print('-+-+-')\n print(board['BL'] + '|' + board['BM'] + '|' + board['BR'])\n\n\ndef main():\n init_board = {\n 'TL': ' ', 'TM': ' ', 'TR': ' ',\n 'ML': ' ', 'MM': ' ', 'MR': ' ',\n 'BL': ' ', 'BM': ' ', 'BR': ' '\n }\n begin = True\n while begin:\n curr_board = init_board.copy()\n begin = False\n turn = 'x'\n counter = 0\n os.system('clear')\n print_board(curr_board)\n while counter < 9:\n move = input('轮到%s走棋, 请输入位置: ' % turn)\n if curr_board[move] == ' ':\n counter += 1\n curr_board[move] = turn\n if turn == 'x':\n turn = 'o'\n else:\n turn = 'x'\n os.system('clear')\n print_board(curr_board)\n choice = input('再玩一局?(yes|no)')\n begin = choice == 'yes'\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day01-15/code/Day07/avgscore.py\n\n\"\"\"\n输入学生考试成绩计算平均分\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-06\n\"\"\"\n\n\ndef main():\n number = int(input('请输入学生人数: '))\n names = [None] * number\n scores = [None] * number\n for index in range(len(names)):\n names[index] = input('请输入第%d个学生的名字: ' % (index + 1))\n scores[index] = float(input('请输入第%d个学生的成绩: ' % (index + 1)))\n total = 0\n for index in range(len(names)):\n print('%s: %.1f分' % (names[index], scores[index]))\n total += scores[index]\n print('平均成绩是: %.1f分' % (total / number))\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day01-15/code/Day07/dict1.py\n\n\"\"\"\n定义和使用字典\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-06\n\"\"\"\n\n\ndef main():\n scores = {'骆昊': 95, '白元芳': 78, '狄仁杰': 82}\n print(scores['骆昊'])\n print(scores['狄仁杰'])\n for elem in scores:\n print('%s\\t--->\\t%d' % (elem, scores[elem]))\n scores['白元芳'] = 65\n scores['诸葛王朗'] = 71\n scores.update(冷面=67, 方启鹤=85)\n print(scores)\n if '武则天' in scores:\n print(scores['武则天'])\n print(scores.get('武则天'))\n print(scores.get('武则天', 60))\n print(scores.popitem())\n print(scores.popitem())\n print(scores.pop('骆昊', 100))\n scores.clear()\n print(scores)\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day01-15/code/Day07/set1.py\n\n\"\"\"\n定义和使用集合\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-06\n\"\"\"\n\n\ndef main():\n set1 = {1, 2, 3, 3, 3, 2}\n print(set1)\n print('Length =', len(set1))\n set2 = set(range(1, 10))\n print(set2)\n set1.add(4)\n set1.add(5)\n set2.update([11, 12])\n print(set1)\n print(set2)\n set2.discard(5)\n # remove的元素如果不存在会引发KeyError\n if 4 in set2:\n set2.remove(4)\n print(set2)\n # 遍历集合容器\n for elem in set2:\n print(elem ** 2, end=' ')\n print()\n # 将元组转换成集合\n set3 = set((1, 2, 3, 3, 2, 1))\n print(set3.pop())\n print(set3)\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day01-15/code/Day07/list2.py\n\n\"\"\"\n列表常用操作\n- 列表连接\n- 获取长度\n- 遍历列表\n- 列表切片\n- 列表排序\n- 列表反转\n- 查找元素\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-06\n\"\"\"\n\n\ndef main():\n fruits = ['grape', 'apple', 'strawberry', 'waxberry']\n fruits += ['pitaya', 'pear', 'mango']\n # 循环遍历列表元素\n for fruit in fruits:\n print(fruit.title(), end=' ')\n print()\n # 列表切片\n fruits2 = fruits[1:4]\n print(fruits2)\n # fruit3 = fruits # 没有复制列表只创建了新的引用\n fruits3 = fruits[:]\n print(fruits3)\n fruits4 = fruits[-3:-1]\n print(fruits4)\n fruits5 = fruits[::-1]\n print(fruits5)\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day01-15/code/Day07/set2.py\n\n\"\"\"\n集合的常用操作\n- 交集\n- 并集\n- 差集\n- 子集\n- 超集\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-06\n\"\"\"\n\n\ndef main():\n set1 = set(range(1, 7))\n print(set1)\n set2 = set(range(2, 11, 2))\n print(set2)\n set3 = set(range(1, 5))\n print(set1 & set2)\n # print(set1.intersection(set2))\n print(set1 | set2)\n # print(set1.union(set2))\n print(set1 - set2)\n # print(set1.difference(set2))\n print(set1 ^ set2)\n # print(set1.symmetric_difference(set2))\n print(set2 <= set1)\n # print(set2.issubset(set1))\n print(set3 <= set1)\n # print(set3.issubset(set1))\n print(set1 >= set2)\n # print(set1.issuperset(set2))\n print(set1 >= set3)\n # print(set1.issuperset(set3))\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day01-15/code/Day07/findmax.py\n\n\"\"\"\n找出列表中最大或最小的元素\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-06\n\"\"\"\n\n\ndef main():\n fruits = ['grape', 'apple', 'strawberry', 'waxberry', 'pitaya']\n # 直接使用内置的max和min函数找出列表中最大和最小元素\n # print(max(fruits))\n # print(min(fruits))\n max_value = min_value = fruits[0]\n for index in range(1, len(fruits)):\n if fruits[index] > max_value:\n max_value = fruits[index]\n elif fruits[index] < min_value:\n min_value = fruits[index]\n print('Max:', max_value)\n print('Min:', min_value)\n\n\nif __name__ == '__main__':\n main()\n# 想一想如果最大的元素有两个要找出第二大的又该怎么做 \n\n\n\nFile: Day01-15/code/Day07/list1.py\n\n\"\"\"\n定义和使用列表\n- 用下标访问元素\n- 添加元素\n- 删除元素\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-06\n\"\"\"\n\n\ndef main():\n fruits = ['grape', '@pple', 'strawberry', 'waxberry']\n print(fruits)\n # 通过下标访问元素\n print(fruits[0])\n print(fruits[1])\n print(fruits[-1])\n print(fruits[-2])\n # print(fruits[-5]) # IndexError\n # print(fruits[4]) # IndexError\n fruits[1] = 'apple'\n print(fruits)\n # 添加元素\n fruits.append('pitaya')\n fruits.insert(0, 'banana')\n print(fruits)\n # 删除元素\n del fruits[1]\n fruits.pop()\n fruits.pop(0)\n fruits.remove('apple')\n print(fruits)\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day01-15/code/Day07/dict2.py\n\n\"\"\"\n字典的常用操作\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-06\n\"\"\"\n\n\ndef main():\n stu = {'name': '骆昊', 'age': 38, 'gender': True}\n print(stu)\n print(stu.keys())\n print(stu.values())\n print(stu.items())\n for elem in stu.items():\n print(elem)\n print(elem[0], elem[1])\n if 'age' in stu:\n stu['age'] = 20\n print(stu)\n stu.setdefault('score', 60)\n print(stu)\n stu.setdefault('score', 100)\n print(stu)\n stu['score'] = 100\n print(stu)\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day01-15/code/Day07/yanghui.py\n\n\"\"\"\n输出10行的杨辉三角 - 二项式的n次方展开系数\n1\n1 1\n1 2 1\n1 3 3 1\n1 4 6 4 1\n... ... ...\n\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-06\n\"\"\"\n\n\ndef main():\n num = int(input('Number of rows: '))\n yh = [[]] * num\n for row in range(len(yh)):\n yh[row] = [None] * (row + 1)\n for col in range(len(yh[row])):\n if col == 0 or col == row:\n yh[row][col] = 1\n else:\n yh[row][col] = yh[row - 1][col] + yh[row - 1][col - 1]\n print(yh[row][col], end='\\t')\n print()\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day01-15/code/Day07/fibonacci.py\n\n\"\"\"\n生成斐波拉切数列\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-06\n\"\"\"\n\n\ndef main():\n f = [1 , 1]\n for i in range(2, 20):\n f += [f[i - 1] + f[i - 2]]\n # f.append(f[i - 1] + f[i - 2])\n for val in f:\n print(val, end=' ')\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day01-15/code/Day07/scoretable.py\n\n\"\"\"\n学生考试成绩表\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-06\n\"\"\"\n\n\ndef main():\n names = ['关羽', '张飞', '赵云', '马超', '黄忠']\n subjs = ['语文', '数学', '英语']\n scores = [[0] * 3] * 5\n for row, name in enumerate(names):\n print('请输入%s的成绩' % name)\n for col, subj in enumerate(subjs):\n scores[row][col] = float(input(subj + ': '))\n print(scores)\n# for row, name in enumerate(names):\n# print('请输入%s的成绩' % name)\n# scores[row] = [None] * len(subjs)\n# for col, subj in enumerate(subjs):\n# score = float(input(subj + ': '))\n# scores[row][col] = score\n# print(scores)\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day01-15/code/Day09/rational.py\n\n\"\"\"\n运算符重载 - 自定义分数类\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-12\n\"\"\"\n\nfrom math import gcd\n\n\nclass Rational(object):\n\n def __init__(self, num, den=1):\n if den == 0:\n raise ValueError('分母不能为0')\n self._num = num\n self._den = den\n self.normalize()\n\n def simplify(self):\n x = abs(self._num)\n y = abs(self._den)\n factor = gcd(x, y)\n if factor > 1:\n self._num //= factor\n self._den //= factor\n return self\n\n def normalize(self):\n if self._den < 0:\n self._den = -self._den\n self._num = -self._num\n return self\n\n def __add__(self, other):\n new_num = self._num * other._den + other._num * self._den\n new_den = self._den * other._den\n return Rational(new_num, new_den).simplify().normalize()\n\n def __sub__(self, other):\n new_num = self._num * other._den - other._num * self._den\n new_den = self._den * other._den\n return Rational(new_num, new_den).simplify().normalize()\n\n def __mul__(self, other):\n new_num = self._num * other._num\n new_den = self._den * other._den\n return Rational(new_num, new_den).simplify().normalize()\n\n def __truediv__(self, other):\n new_num = self._num * other._den\n new_den = self._den * other._num\n return Rational(new_num, new_den).simplify().normalize()\n\n def __str__(self):\n if self._num == 0:\n return '0'\n elif self._den == 1:\n return str(self._num)\n else:\n return '(%d/%d)' % (self._num, self._den)\n\n\nif __name__ == '__main__':\n r1 = Rational(2, 3)\n print(r1)\n r2 = Rational(6, -8)\n print(r2)\n print(r2.simplify())\n print('%s + %s = %s' % (r1, r2, r1 + r2))\n print('%s - %s = %s' % (r1, r2, r1 - r2))\n print('%s * %s = %s' % (r1, r2, r1 * r2))\n print('%s / %s = %s' % (r1, r2, r1 / r2))\n\n\n\nFile: Day01-15/code/Day09/pet.py\n\nfrom abc import ABCMeta, abstractmethod\n\n\nclass Pet(object, metaclass=ABCMeta):\n\n def __init__(self, nickname):\n self._nickname = nickname\n\n @abstractmethod\n def make_voice(self):\n pass\n\n\nclass Dog(Pet):\n\n def make_voice(self):\n print('%s: 汪汪汪...' % self._nickname)\n\n\nclass Cat(Pet):\n\n def make_voice(self):\n print('%s: 喵...喵...' % self._nickname)\n\n\ndef main():\n pets = [Dog('旺财'), Cat('凯蒂'), Dog('大黄')]\n for pet in pets:\n pet.make_voice()\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day01-15/code/Day09/diamond.py\n\n\"\"\"\n多重继承\n- 菱形继承(钻石继承)\n- C3算法(替代DFS的算法)\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-12\n\"\"\"\n\n\nclass A(object):\n\n def foo(self):\n print('foo of A')\n\n\nclass B(A):\n pass\n\n\nclass C(A):\n\n def foo(self):\n print('foo fo C')\n\n\nclass D(B, C):\n pass\n\n\nclass E(D):\n\n def foo(self):\n print('foo in E')\n super().foo()\n super(B, self).foo()\n super(C, self).foo()\n\n\nif __name__ == '__main__':\n d = D()\n d.foo()\n e = E()\n e.foo()\n\n\n\nFile: Day01-15/code/Day09/clock.py\n\nfrom time import time, localtime, sleep\n\n\nclass Clock(object):\n \"\"\"数字时钟\"\"\"\n\n def __init__(self, hour=0, minute=0, second=0):\n self._hour = hour\n self._minute = minute\n self._second = second\n\n @classmethod\n def now(cls):\n ctime = localtime(time())\n return cls(ctime.tm_hour, ctime.tm_min, ctime.tm_sec)\n\n def run(self):\n \"\"\"走字\"\"\"\n self._second += 1\n if self._second == 60:\n self._second = 0\n self._minute += 1\n if self._minute == 60:\n self._minute = 0\n self._hour += 1\n if self._hour == 24:\n self._hour = 0\n\n def show(self):\n \"\"\"显示时间\"\"\"\n return '%02d:%02d:%02d' % \\\n (self._hour, self._minute, self._second)\n\n\ndef main():\n clock = Clock.now()\n while True:\n print(clock.show())\n sleep(1)\n clock.run()\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day01-15/code/Day09/car1.py\n\n\"\"\"\n属性的使用\n- 访问器/修改器/删除器\n- 使用__slots__对属性加以限制\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-12\n\"\"\"\n\n\nclass Car(object):\n\n __slots__ = ('_brand', '_max_speed')\n\n def __init__(self, brand, max_speed):\n self._brand = brand\n self._max_speed = max_speed\n\n @property\n def brand(self):\n return self._brand\n\n @brand.setter\n def brand(self, brand):\n self._brand = brand\n\n @brand.deleter\n def brand(self):\n del self._brand\n\n @property\n def max_speed(self):\n return self._max_speed\n\n @max_speed.setter\n def max_speed(self, max_speed):\n if max_speed < 0:\n raise ValueError('Invalid max speed for car')\n self._max_speed = max_speed\n\n def __str__(self):\n return 'Car: [品牌=%s, 最高时速=%d]' % (self._brand, self._max_speed)\n\n\ncar = Car('QQ', 120)\nprint(car)\n# ValueError\n# car.max_speed = -100\ncar.max_speed = 320\ncar.brand = \"Benz\"\n# 使用__slots__属性限制后下面的代码将产生异常\n# car.current_speed = 80\nprint(car)\n# 如果提供了删除器可以执行下面的代码\n# del car.brand\n# 属性的实现\nprint(Car.brand)\nprint(Car.brand.fget)\nprint(Car.brand.fset)\nprint(Car.brand.fdel)\n# 通过上面的代码帮助学生理解之前提到的包装器的概念\n# Python中有很多类似的语法糖后面还会出现这样的东西\n\n\n\nFile: Day01-15/code/Day09/multi.py\n\n\"\"\"\n多重继承\n- 通过多重继承可以给一个类的对象具备多方面的能力\n- 这样在设计类的时候可以避免设计太多层次的复杂的继承关系\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-12\n\"\"\"\n\n\nclass Father(object):\n\n def __init__(self, name):\n self._name = name\n\n def gamble(self):\n print('%s在打麻将.' % self._name)\n\n def eat(self):\n print('%s在大吃大喝.' % self._name)\n\n\nclass Monk(object):\n\n def __init__(self, name):\n self._name = name\n\n def eat(self):\n print('%s在吃斋.' % self._name)\n\n def chant(self):\n print('%s在念经.' % self._name)\n\n\nclass Musician(object):\n\n def __init__(self, name):\n self._name = name\n\n def eat(self):\n print('%s在细嚼慢咽.' % self._name)\n\n def play_piano(self):\n print('%s在弹钢琴.' % self._name)\n\n\n# 试一试下面的代码看看有什么区别\n# class Son(Monk, Father, Musician):\n# class Son(Musician, Father, Monk):\n\n\nclass Son(Father, Monk, Musician):\n\n def __init__(self, name):\n Father.__init__(self, name)\n Monk.__init__(self, name)\n Musician.__init__(self, name)\n\n\nson = Son('王大锤')\nson.gamble()\n# 调用继承自Father的eat方法\nson.eat()\nson.chant()\nson.play_piano()\n\n\n\nFile: Day01-15/code/Day09/association.py\n\n\"\"\"\n对象之间的关联关系\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-12\n\"\"\"\n\nfrom math import sqrt\n\n\nclass Point(object):\n\n def __init__(self, x=0, y=0):\n self._x = x\n self._y = y\n\n def move_to(self, x, y):\n self._x = x\n self._y = y\n\n def move_by(self, dx, dy):\n self._x += dx\n self._y += dy\n\n def distance_to(self, other):\n dx = self._x - other._x\n dy = self._y - other._y\n return sqrt(dx ** 2 + dy ** 2)\n\n def __str__(self):\n return '(%s, %s)' % (str(self._x), str(self._y))\n\n\nclass Line(object):\n\n def __init__(self, start=Point(0, 0), end=Point(0, 0)):\n self._start = start\n self._end = end\n\n @property\n def start(self):\n return self._start\n\n @start.setter\n def start(self, start):\n self._start = start\n\n @property\n def end(self):\n return self.end\n\n @end.setter\n def end(self, end):\n self._end = end\n\n @property\n def length(self):\n return self._start.distance_to(self._end)\n\n\nif __name__ == '__main__':\n p1 = Point(3, 5)\n print(p1)\n p2 = Point(-2, -1.5)\n print(p2)\n line = Line(p1, p2)\n print(line.length)\n line.start.move_to(2, 1)\n line.end = Point(1, 2)\n print(line.length)\n\n\n\nFile: Day01-15/code/Day09/dependency.py\n\n\"\"\"\n对象之间的依赖关系和运算符重载\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-12\n\"\"\"\n\n\nclass Car(object):\n\n def __init__(self, brand, max_speed):\n self._brand = brand\n self._max_speed = max_speed\n self._current_speed = 0\n\n @property\n def brand(self):\n return self._brand\n\n def accelerate(self, delta):\n self._current_speed += delta\n if self._current_speed > self._max_speed:\n self._current_speed = self._max_speed\n\n def brake(self):\n self._current_speed = 0\n\n def __str__(self):\n return '%s当前时速%d' % (self._brand, self._current_speed)\n\n\nclass Student(object):\n\n def __init__(self, name, age):\n self._name = name\n self._age = age\n\n @property\n def name(self):\n return self._name\n\n # 学生和车之间存在依赖关系 - 学生使用了汽车\n def drive(self, car):\n print('%s驾驶着%s欢快的行驶在去西天的路上' % (self._name, car._brand))\n car.accelerate(30)\n print(car)\n car.accelerate(50)\n print(car)\n car.accelerate(50)\n print(car)\n\n def study(self, course_name):\n print('%s正在学习%s.' % (self._name, course_name))\n\n def watch_av(self):\n if self._age < 18:\n print('%s只能观看《熊出没》.' % self._name)\n else:\n print('%s正在观看岛国爱情动作片.' % self._name)\n\n # 重载大于(>)运算符\n def __gt__(self, other):\n return self._age > other._age\n\n # 重载小于(<)运算符\n def __lt__(self, other):\n return self._age < other._age\n\n\nif __name__ == '__main__':\n stu1 = Student('骆昊', 38)\n stu1.study('Python程序设计')\n stu1.watch_av()\n stu2 = Student('王大锤', 15)\n stu2.study('思想品德')\n stu2.watch_av()\n car = Car('QQ', 120)\n stu2.drive(car)\n print(stu1 > stu2)\n print(stu1 < stu2)\n\n\n\nFile: Day01-15/code/Day09/triangle.py\n\n\"\"\"\n实例方法和类方法的应用\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-12\n\"\"\"\n\nfrom math import sqrt\n\n\nclass Triangle(object):\n\n def __init__(self, a, b, c):\n self._a = a\n self._b = b\n self._c = c\n\n # 静态方法\n @staticmethod\n def is_valid(a, b, c):\n return a + b > c and b + c > a and c + a > b\n\n # 实例方法\n def perimeter(self):\n return self._a + self._b + self._c\n\n # 实例方法\n def area(self):\n p = self.perimeter() / 2\n return sqrt(p * (p - self._a) * (p - self._b) * (p - self._c))\n\n\nif __name__ == '__main__':\n # 用字符串的split方法将字符串拆分成一个列表\n # 再通过map函数对列表中的每个字符串进行映射处理成小数\n a, b, c = map(float, input('请输入三条边: ').split())\n # 先判断给定长度的三条边能否构成三角形\n # 如果能才创建三角形对象\n if Triangle.is_valid(a, b, c):\n tri = Triangle(a, b, c)\n print('周长:', tri.perimeter())\n print('面积:', tri.area())\n # 如果传入对象作为方法参数也可以通过类调用实例方法\n # print('周长:', Triangle.perimeter(tri))\n # print('面积:', Triangle.area(tri))\n # 看看下面的代码就知道其实二者本质上是一致的\n # print(type(tri.perimeter))\n # print(type(Triangle.perimeter))\n else:\n print('不能构成三角形.')\n\n\n\nFile: Day01-15/code/Day09/employee.py\n\n\"\"\"\n抽象类 / 方法重写 / 多态\n实现一个工资结算系统 公司有三种类型的员工\n- 部门经理固定月薪12000元/月\n- 程序员按本月工作小时数每小时100元\n- 销售员1500元/月的底薪加上本月销售额5%的提成\n输入员工的信息 输出每位员工的月薪信息\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-12\n\"\"\"\n\nfrom abc import ABCMeta, abstractmethod\n\n\nclass Employee(object, metaclass=ABCMeta):\n\n def __init__(self, name):\n self._name = name\n\n @property\n def name(self):\n return self._name\n\n @abstractmethod\n def get_salary(self):\n pass\n\n\nclass Manager(Employee):\n\n # 想一想: 如果不定义构造方法会怎么样\n def __init__(self, name):\n # 想一想: 如果不调用父类构造器会怎么样\n super().__init__(name)\n\n def get_salary(self):\n return 12000\n\n\nclass Programmer(Employee):\n\n def __init__(self, name):\n super().__init__(name)\n\n def set_working_hour(self, working_hour):\n self._working_hour = working_hour\n\n def get_salary(self):\n return 100 * self._working_hour\n\n\nclass Salesman(Employee):\n\n def __init__(self, name):\n super().__init__(name)\n\n def set_sales(self, sales):\n self._sales = sales\n\n def get_salary(self):\n return 1500 + self._sales * 0.05\n\n\nif __name__ == '__main__':\n emps = [Manager('武则天'), Programmer('狄仁杰'), Salesman('白元芳')]\n for emp in emps:\n if isinstance(emp, Programmer):\n working_hour = int(input('请输入%s本月工作时间: ' % emp.name))\n emp.set_working_hour(working_hour)\n elif isinstance(emp, Salesman):\n sales = float(input('请输入%s本月销售额: ' % emp.name))\n emp.set_sales(sales)\n print('%s本月月薪为: ￥%.2f元' % (emp.name, emp.get_salary()))\n\n\n\nFile: Day01-15/code/Day09/car2.py\n\n\"\"\"\n属性的使用\n- 使用已有方法定义访问器/修改器/删除器\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-12\n\"\"\"\n\n\nclass Car(object):\n\n def __init__(self, brand, max_speed):\n self.set_brand(brand)\n self.set_max_speed(max_speed)\n\n def get_brand(self):\n return self._brand\n\n def set_brand(self, brand):\n self._brand = brand\n\n def get_max_speed(self):\n return self._max_speed\n\n def set_max_speed(self, max_speed):\n if max_speed < 0:\n raise ValueError('Invalid max speed for car')\n self._max_speed = max_speed\n\n def __str__(self):\n return 'Car: [品牌=%s, 最高时速=%d]' % (self._brand, self._max_speed)\n\n # 用已有的修改器和访问器定义属性\n brand = property(get_brand, set_brand)\n max_speed = property(get_max_speed, set_max_speed)\n\n\ncar = Car('QQ', 120)\nprint(car)\n# ValueError\n# car.max_speed = -100\ncar.max_speed = 320\ncar.brand = \"Benz\"\nprint(car)\nprint(Car.brand)\nprint(Car.brand.fget)\nprint(Car.brand.fset)\n\n\n\nFile: Day01-15/code/Day09/shape.py\n\n\"\"\"\n继承的应用\n- 抽象类\n- 抽象方法\n- 方法重写\n- 多态\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-12\n\"\"\"\n\nfrom abc import ABCMeta, abstractmethod\nfrom math import pi\n\n\nclass Shape(object, metaclass=ABCMeta):\n\n @abstractmethod\n def perimeter(self):\n pass\n\n @abstractmethod\n def area(self):\n pass\n\n\nclass Circle(Shape):\n\n def __init__(self, radius):\n self._radius = radius\n\n def perimeter(self):\n return 2 * pi * self._radius\n\n def area(self):\n return pi * self._radius ** 2\n\n def __str__(self):\n return '我是一个圆'\n\n\nclass Rect(Shape):\n\n def __init__(self, width, height):\n self._width = width\n self._height = height\n\n def perimeter(self):\n return 2 * (self._width + self._height)\n\n def area(self):\n return self._width * self._height\n\n def __str__(self):\n return '我是一个矩形'\n\n\nif __name__ == '__main__':\n shapes = [Circle(5), Circle(3.2), Rect(3.2, 6.3)]\n for shape in shapes:\n print(shape)\n print('周长:', shape.perimeter())\n print('面积:', shape.area())\n\n\n\nFile: Day01-15/code/Day08/circle.py\n\n\"\"\"\n练习\n修一个游泳池 半径(以米为单位)在程序运行时输入 游泳池外修一条3米宽的过道\n过道的外侧修一圈围墙 已知过道的造价为25元每平米 围墙的造价为32.5元每米\n输出围墙和过道的总造价分别是多少钱(精确到小数点后2位)\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-08\n\"\"\"\n\nimport math\n\n\nclass Circle(object):\n\n def __init__(self, radius):\n self._radius = radius\n\n @property\n def radius(self):\n return self._radius\n\n @radius.setter\n def radius(self, radius):\n self._radius = radius if radius > 0 else 0\n\n @property\n def perimeter(self):\n return 2 * math.pi * self._radius\n\n @property\n def area(self):\n return math.pi * self._radius * self._radius\n\n\nif __name__ == '__main__': \n radius = float(input('请输入游泳池的半径: '))\n small = Circle(radius)\n big = Circle(radius + 3)\n print('围墙的造价为: ￥%.1f元' % (big.perimeter * 115))\n print('过道的造价为: ￥%.1f元' % ((big.area - small.area) * 65))\n\n\n\nFile: Day01-15/code/Day08/guess.py\n\n\"\"\"\n面向对象版本的猜数字游戏\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-08\n\"\"\"\n\nfrom random import randint\n\n\nclass GuessMachine(object):\n\n def __init__(self):\n self._answer = None\n self._counter = None\n self._hint = None\n\n def reset(self):\n self._answer = randint(1, 100)\n self._counter = 0\n self._hint = None\n\n def guess(self, your_answer):\n self._counter += 1\n if your_answer > self._answer:\n self._hint = '小一点'\n elif your_answer < self._answer:\n self._hint = '大一点'\n else:\n self._hint = '恭喜你猜对了'\n return True\n return False\n\n @property\n def counter(self):\n return self._counter\n\n @property\n def hint(self):\n return self._hint\n\n\nif __name__ == '__main__':\n gm = GuessMachine()\n play_again = True\n while play_again:\n game_over = False\n gm.reset()\n while not game_over:\n your_answer = int(input('请输入: '))\n game_over = gm.guess(your_answer)\n print(gm.hint)\n if gm.counter > 7:\n print('智商余额不足!')\n play_again = input('再玩一次?(yes|no)') == 'yes'\n\n\n\nFile: Day01-15/code/Day08/hack.py\n\n\"\"\"\n另一种创建类的方式\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-08\n\"\"\"\n\n\ndef bar(self, name):\n self._name = name\n\n\ndef foo(self, course_name):\n print('%s正在学习%s.' % (self._name, course_name))\n\n\ndef main():\n Student = type('Student', (object,), dict(__init__=bar, study=foo))\n stu1 = Student('骆昊')\n stu1.study('Python程序设计')\n\n\nif __name__ == '__main__':\n main() \n\n\n\nFile: Day01-15/code/Day08/clock.py\n\n\"\"\"\n定义和使用时钟类\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-08\n\"\"\"\n\nimport time\nimport os\n\n\nclass Clock(object):\n\n # Python中的函数是没有重载的概念的\n # 因为Python中函数的参数没有类型而且支持缺省参数和可变参数\n # 用关键字参数让构造器可以传入任意多个参数来实现其他语言中的构造器重载\n def __init__(self, **kw):\n if 'hour' in kw and 'minute' in kw and 'second' in kw:\n self._hour = kw['hour']\n self._minute = kw['minute']\n self._second = kw['second']\n else:\n tm = time.localtime(time.time())\n self._hour = tm.tm_hour\n self._minute = tm.tm_min\n self._second = tm.tm_sec\n\n def run(self):\n self._second += 1\n if self._second == 60:\n self._second = 0\n self._minute += 1\n if self._minute == 60:\n self._minute = 0\n self._hour += 1\n if self._hour == 24:\n self._hour = 0\n\n def show(self):\n return '%02d:%02d:%02d' % (self._hour, self._minute, self._second)\n\n\nif __name__ == '__main__':\n # clock = Clock(hour=10, minute=5, second=58)\n clock = Clock()\n while True:\n os.system('clear')\n print(clock.show())\n time.sleep(1)\n clock.run()\n\n\n\nFile: Day01-15/code/Day08/access.py\n\nclass Test:\n\n def __init__(self, foo):\n self.__foo = foo\n\n def __bar(self):\n print(self.__foo)\n print('__bar')\n\n\ndef main():\n test = Test('hello')\n test._Test__bar()\n print(test._Test__foo)\n\n\nif __name__ == \"__main__\":\n main()\n\n\n\nFile: Day01-15/code/Day08/rect.py\n\n\"\"\"\n定义和使用矩形类\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-08\n\"\"\"\n\n\nclass Rect(object):\n \"\"\"矩形类\"\"\"\n\n def __init__(self, width=0, height=0):\n \"\"\"初始化方法\"\"\"\n self.__width = width\n self.__height = height\n\n def perimeter(self):\n \"\"\"计算周长\"\"\"\n return (self.__width + self.__height) * 2\n\n def area(self):\n \"\"\"计算面积\"\"\"\n return self.__width * self.__height\n\n def __str__(self):\n \"\"\"矩形对象的字符串表达式\"\"\"\n return '矩形[%f,%f]' % (self.__width, self.__height)\n\n def __del__(self):\n \"\"\"析构器\"\"\"\n print('销毁矩形对象')\n\n\nif __name__ == '__main__':\n rect1 = Rect()\n print(rect1)\n print(rect1.perimeter())\n print(rect1.area())\n rect2 = Rect(3.5, 4.5)\n print(rect2)\n print(rect2.perimeter())\n print(rect2.area())\n\n\n\nFile: Day01-15/code/Day08/student.py\n\n\"\"\"\n定义和使用学生类\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-08\n\"\"\"\n\n\ndef _foo():\n print('test')\n\n\nclass Student(object):\n\n # __init__是一个特殊方法用于在创建对象时进行初始化操作\n # 通过这个方法我们可以为学生对象绑定name和age两个属性\n def __init__(self, name, age):\n self.name = name\n self.age = age\n\n def study(self, course_name):\n print('%s正在学习%s.' % (self.name, course_name))\n\n # PEP 8要求标识符的名字用全小写多个单词用下划线连接\n # 但是很多程序员和公司更倾向于使用驼峰命名法(驼峰标识)\n def watch_av(self):\n if self.age < 18:\n print('%s只能观看《熊出没》.' % self.name)\n else:\n print('%s正在观看岛国大电影.' % self.name)\n\n\ndef main():\n stu1 = Student('骆昊', 38)\n stu1.study('Python程序设计')\n stu1.watch_av()\n stu2 = Student('王大锤', 15)\n stu2.study('思想品德')\n stu2.watch_av()\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day01-15/code/Day06/function6.py\n\n\"\"\"\n作用域问题\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-05\n\"\"\"\n\n\n# 局部作用域\ndef foo1():\n a = 5\n\n\nfoo1()\n# print(a) # NameError\n\n# 全局作用域\nb = 10\n\n\ndef foo2():\n print(b)\n\n\nfoo2()\n\n\ndef foo3():\n b = 100 # 局部变量\n print(b)\n\n\nfoo3()\nprint(b)\n\n\ndef foo4():\n global b\n b = 200 # 全局变量\n print(b)\n\n\nfoo4()\nprint(b)\n\n\n\nFile: Day01-15/code/Day06/function2.py\n\n\"\"\"\n函数的定义和使用 - 求最大公约数和最小公倍数\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-05\n\"\"\"\n\n\ndef gcd(x, y):\n if x > y:\n (x, y) = (y, x)\n for factor in range(x, 1, -1):\n if x % factor == 0 and y % factor == 0:\n return factor\n return 1\n\n\ndef lcm(x, y):\n return x * y // gcd(x, y)\n\n\nprint(gcd(15, 27))\nprint(lcm(15, 27))\n\n\n\nFile: Day01-15/code/Day06/function3.py\n\n\"\"\"\nPython的内置函数\n- 数学相关: abs / divmod / pow / round / min / max / sum\n- 序列相关: len / range / next / filter / map / sorted / slice / reversed\n- 类型转换: chr / ord / str / bool / int / float / complex / bin / oct / hex\n- 数据结构: dict / list / set / tuple\n- 其他函数: all / any / id / input / open / print / type\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-05\n\"\"\"\n\n\ndef myfilter(mystr):\n return len(mystr) == 6\n\n\n# help()\nprint(chr(0x9a86))\nprint(hex(ord('骆')))\nprint(abs(-1.2345))\nprint(round(-1.2345))\nprint(pow(1.2345, 5))\nfruits = ['orange', 'peach', 'durian', 'watermelon']\nprint(fruits[slice(1, 3)])\nfruits2 = list(filter(myfilter, fruits))\nprint(fruits)\nprint(fruits2)\n\n\n\nFile: Day01-15/code/Day06/function4.py\n\n\"\"\"\nPython常用模块\n- 运行时服务相关模块: copy / pickle / sys / ...\n- 数学相关模块: decimal / math / random / ...\n- 字符串处理模块: codecs / re / ...\n- 文件处理相关模块: shutil / gzip / ...\n- 操作系统服务相关模块: datetime / os / time / logging / io / ...\n- 进程和线程相关模块: multiprocessing / threading / queue\n- 网络应用相关模块: ftplib / http / smtplib / urllib / ...\n- Web编程相关模块: cgi / webbrowser\n- 数据处理和编码模块: base64 / csv / html.parser / json / xml / ...\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-05\n\"\"\"\n\nimport time\nimport shutil\nimport os\n\nseconds = time.time()\nprint(seconds)\nlocaltime = time.localtime(seconds)\nprint(localtime)\nprint(localtime.tm_year)\nprint(localtime.tm_mon)\nprint(localtime.tm_mday)\nasctime = time.asctime(localtime)\nprint(asctime)\nstrtime = time.strftime('%Y-%m-%d %H:%M:%S', localtime)\nprint(strtime)\nmydate = time.strptime('2018-1-1', '%Y-%m-%d')\nprint(mydate)\n\nshutil.copy('/Users/Hao/hello.py', '/Users/Hao/Desktop/first.py')\nos.system('ls -l')\nos.chdir('/Users/Hao')\nos.system('ls -l')\nos.mkdir('test')\n\n\n\nFile: Day01-15/code/Day06/function5.py\n\n\"\"\"\n函数的参数\n- 位置参数\n- 可变参数\n- 关键字参数\n- 命名关键字参数\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-05\n\"\"\"\n\n\n# 参数默认值\ndef f1(a, b=5, c=10):\n return a + b * 2 + c * 3\n\n\nprint(f1(1, 2, 3))\nprint(f1(100, 200))\nprint(f1(100))\nprint(f1(c=2, b=3, a=1))\n\n\n# 可变参数\ndef f2(*args):\n sum = 0\n for num in args:\n sum += num\n return sum\n\n\nprint(f2(1, 2, 3))\nprint(f2(1, 2, 3, 4, 5))\nprint(f2())\n\n\n# 关键字参数\ndef f3(**kw):\n if 'name' in kw:\n print('欢迎你%s!' % kw['name'])\n elif 'tel' in kw:\n print('你的联系电话是: %s!' % kw['tel'])\n else:\n print('没找到你的个人信息!')\n\n\nparam = {'name': '骆昊', 'age': 38}\nf3(**param)\nf3(name='骆昊', age=38, tel='13866778899')\nf3(user='骆昊', age=38, tel='13866778899')\nf3(user='骆昊', age=38, mobile='13866778899')\n\n\n\nFile: Day01-15/code/Day06/function1.py\n\n\"\"\"\n函数的定义和使用 - 计算组合数C(7,3)\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-05\n\"\"\"\n\n\n# 将求阶乘的功能封装成一个函数\ndef factorial(n):\n result = 1\n for num in range(1, n + 1):\n result *= num\n return result\n\n\nprint(factorial(7) // factorial(3) // factorial(4))\n\n\n\nFile: Day01-15/code/Day01/hello.py\n\n\"\"\"\n第一个Python程序 - hello, world!\n向伟大的Dennis M. Ritchie先生致敬\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-02-26\n\n请将该文件命名为hello.py\n\n使用Windows的小伙伴可以在命令行提示下通过下面的命令运行该程序\npython hello.py\n\n对于使用Linux或macOS的小伙伴可以打开终端并键入下面的命令来运行程序\npython3 hello.py\n\"\"\"\n\nprint('hello, world!')\n# print(\"你好,世界！\")\nprint('你好', '世界')\nprint('hello', 'world', sep=', ', end='!')\nprint('goodbye, world', end='!\\n')\n\n\n\nFile: Day01-15/code/Day01/flag.py\n\n\"\"\"\n用Python的turtle模块绘制国旗\n\"\"\"\nimport turtle\n\n\ndef draw_rectangle(x, y, width, height):\n \"\"\"绘制矩形\"\"\"\n turtle.goto(x, y)\n turtle.pencolor('red')\n turtle.fillcolor('red')\n turtle.begin_fill()\n for i in range(2):\n turtle.forward(width)\n turtle.left(90)\n turtle.forward(height)\n turtle.left(90)\n turtle.end_fill()\n\n\ndef draw_star(x, y, radius):\n \"\"\"绘制五角星\"\"\"\n turtle.setpos(x, y)\n pos1 = turtle.pos()\n turtle.circle(-radius, 72)\n pos2 = turtle.pos()\n turtle.circle(-radius, 72)\n pos3 = turtle.pos()\n turtle.circle(-radius, 72)\n pos4 = turtle.pos()\n turtle.circle(-radius, 72)\n pos5 = turtle.pos()\n turtle.color('yellow', 'yellow')\n turtle.begin_fill()\n turtle.goto(pos3)\n turtle.goto(pos1)\n turtle.goto(pos4)\n turtle.goto(pos2)\n turtle.goto(pos5)\n turtle.end_fill()\n\n\ndef main():\n \"\"\"主程序\"\"\"\n turtle.speed(12)\n turtle.penup()\n x, y = -270, -180\n # 画国旗主体\n width, height = 540, 360\n draw_rectangle(x, y, width, height)\n # 画大星星\n pice = 22\n center_x, center_y = x + 5 * pice, y + height - pice * 5\n turtle.goto(center_x, center_y)\n turtle.left(90)\n turtle.forward(pice * 3)\n turtle.right(90)\n draw_star(turtle.xcor(), turtle.ycor(), pice * 3)\n x_poses, y_poses = [10, 12, 12, 10], [2, 4, 7, 9]\n # 画小星星\n for x_pos, y_pos in zip(x_poses, y_poses):\n turtle.goto(x + x_pos * pice, y + height - y_pos * pice)\n turtle.left(turtle.towards(center_x, center_y) - turtle.heading())\n turtle.forward(pice)\n turtle.right(90)\n draw_star(turtle.xcor(), turtle.ycor(), pice)\n # 隐藏海龟\n turtle.ht()\n # 显示绘图窗口\n turtle.mainloop()\n\n\nif __name__ == '__main__':\n main()\n\n\nFile: Day01-15/code/Day01/peppa_pig.py\n\n\"\"\"\n绘制小猪佩奇\n\"\"\"\nfrom turtle import *\n\n\ndef nose(x,y):\n \"\"\"画鼻子\"\"\"\n penup()\n # 将海龟移动到指定的坐标\n goto(x,y)\n pendown()\n # 设置海龟的方向（0-东、90-北、180-西、270-南）\n setheading(-30)\n begin_fill()\n a = 0.4\n for i in range(120):\n if 0 <= i < 30 or 60 <= i <90:\n a = a + 0.08\n # 向左转3度\n left(3)\n # 向前走\n forward(a)\n else:\n a = a - 0.08\n left(3)\n forward(a)\n end_fill()\n penup()\n setheading(90)\n forward(25)\n setheading(0)\n forward(10)\n pendown()\n # 设置画笔的颜色(红, 绿, 蓝)\n pencolor(255, 155, 192)\n setheading(10)\n begin_fill()\n circle(5)\n color(160, 82, 45)\n end_fill()\n penup()\n setheading(0)\n forward(20)\n pendown()\n pencolor(255, 155, 192)\n setheading(10)\n begin_fill()\n circle(5)\n color(160, 82, 45)\n end_fill()\n\n\ndef head(x, y):\n \"\"\"画头\"\"\"\n color((255, 155, 192), \"pink\")\n penup()\n goto(x,y)\n setheading(0)\n pendown()\n begin_fill()\n setheading(180)\n circle(300, -30)\n circle(100, -60)\n circle(80, -100)\n circle(150, -20)\n circle(60, -95)\n setheading(161)\n circle(-300, 15)\n penup()\n goto(-100, 100)\n pendown()\n setheading(-30)\n a = 0.4\n for i in range(60):\n if 0<= i < 30 or 60 <= i < 90:\n a = a + 0.08\n lt(3) #向左转3度\n fd(a) #向前走a的步长\n else:\n a = a - 0.08\n lt(3)\n fd(a)\n end_fill()\n\n\ndef ears(x,y):\n \"\"\"画耳朵\"\"\"\n color((255, 155, 192), \"pink\")\n penup()\n goto(x, y)\n pendown()\n begin_fill()\n setheading(100)\n circle(-50, 50)\n circle(-10, 120)\n circle(-50, 54)\n end_fill()\n penup()\n setheading(90)\n forward(-12)\n setheading(0)\n forward(30)\n pendown()\n begin_fill()\n setheading(100)\n circle(-50, 50)\n circle(-10, 120)\n circle(-50, 56)\n end_fill()\n\n\ndef eyes(x,y):\n \"\"\"画眼睛\"\"\"\n color((255, 155, 192), \"white\")\n penup()\n setheading(90)\n forward(-20)\n setheading(0)\n forward(-95)\n pendown()\n begin_fill()\n circle(15)\n end_fill()\n color(\"black\")\n penup()\n setheading(90)\n forward(12)\n setheading(0)\n forward(-3)\n pendown()\n begin_fill()\n circle(3)\n end_fill()\n color((255, 155, 192), \"white\")\n penup()\n seth(90)\n forward(-25)\n seth(0)\n forward(40)\n pendown()\n begin_fill()\n circle(15)\n end_fill()\n color(\"black\")\n penup()\n setheading(90)\n forward(12)\n setheading(0)\n forward(-3)\n pendown()\n begin_fill()\n circle(3)\n end_fill()\n\n\ndef cheek(x,y):\n \"\"\"画脸颊\"\"\"\n color((255, 155, 192))\n penup()\n goto(x,y)\n pendown()\n setheading(0)\n begin_fill()\n circle(30)\n end_fill()\n\n\ndef mouth(x,y):\n \"\"\"画嘴巴\"\"\"\n color(239, 69, 19)\n penup()\n goto(x, y)\n pendown()\n setheading(-80)\n circle(30, 40)\n circle(40, 80)\n\n\ndef setting():\n \"\"\"设置参数\"\"\"\n pensize(4)\n # 隐藏海龟\n hideturtle()\n colormode(255)\n color((255, 155, 192), \"pink\")\n setup(840, 500)\n speed(10)\n\n\ndef main():\n \"\"\"主函数\"\"\"\n setting() \n nose(-100, 100)\n head(-69, 167)\n ears(0, 160)\n eyes(0, 140)\n cheek(80, 10)\n mouth(-20, 30)\n done()\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day01-15/code/Day12/str2.py\n\n\"\"\"\n字符串常用操作 - 实现字符串倒转的方法\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-19\n\"\"\"\n\nfrom io import StringIO\n\n\ndef reverse_str1(str):\n return str[::-1]\n\n\ndef reverse_str2(str):\n if len(str) <= 1:\n return str\n return reverse_str2(str[1:]) + str[0:1]\n\n\ndef reverse_str3(str):\n # StringIO对象是Python中的可变字符串\n # 不应该使用不变字符串做字符串连接操作 因为会产生很多无用字符串对象\n rstr = StringIO()\n str_len = len(str)\n for index in range(str_len - 1, -1, -1):\n rstr.write(str[index])\n return rstr.getvalue()\n\n\ndef reverse_str4(str):\n return ''.join(str[index] for index in range(len(str) - 1, -1, -1))\n\n\ndef reverse_str5(str):\n # 将字符串处理成列表\n str_list = list(str)\n str_len = len(str)\n # 使用zip函数将两个序列合并成一个产生元组的迭代器\n # 每次正好可以取到一前一后两个下标来实现元素的交换\n for i, j in zip(range(str_len // 2), range(str_len - 1, str_len // 2, -1)):\n str_list[i], str_list[j] = str_list[j], str_list[i]\n # 将列表元素连接成字符串\n return ''.join(str_list)\n\n\nif __name__ == '__main__':\n str = 'I love Python'\n print(reverse_str1(str))\n print(str)\n print(reverse_str2(str))\n print(str)\n print(reverse_str3(str))\n print(str)\n print(reverse_str4(str))\n print(str)\n print(reverse_str5(str))\n print(str)\n\n\n\nFile: Day01-15/code/Day12/test4.py\n\nimport re\n\n\ndef main():\n # 创建正则表达式对象 使用了前瞻和回顾来保证手机号前后不应该出现数字\n pattern = re.compile(r'(?<=\\D)(1[38]\\d{9}|14[57]\\d{8}|15[0-35-9]\\d{8}|17[678]\\d{8})(?=\\D)')\n sentence = '''\n 重要的事情说8130123456789遍，我的手机号是13512346789这个靓号，\n 不是15600998765，也是110或119，王大锤的手机号才是15600998765。\n '''\n # 查找所有匹配并保存到一个列表中\n mylist = re.findall(pattern, sentence)\n print(mylist)\n print('--------华丽的分隔线--------')\n # 通过迭代器取出匹配对象并获得匹配的内容\n for temp in pattern.finditer(sentence):\n print(temp.group())\n print('--------华丽的分隔线--------')\n # 通过search函数指定搜索位置找出所有匹配\n m = pattern.search(sentence)\n while m:\n print(m.group())\n m = pattern.search(sentence, m.end())\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day01-15/code/Day12/test5.py\n\n\"\"\"\n不良内容过滤\n\"\"\"\nimport re\n\n\ndef main():\n sentence = '你丫是傻叉吗? 我操你大爷的. Fuck you.'\n purified = re.sub('[操肏艹]|fuck|shit|傻[比屄逼叉缺吊屌]|煞笔',\n '*', sentence, flags=re.IGNORECASE)\n print(purified)\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day01-15/code/Day12/test3.py\n\n\"\"\"\n验证输入用户名和QQ号是否有效并给出对应的提示信息\n\n要求：\n用户名必须由字母、数字或下划线构成且长度在6~20个字符之间\nQQ号是5~12的数字且首位不能为0\n\"\"\"\n\nimport re\n\n\ndef main():\n username = input('请输入用户名: ')\n qq = input('请输入QQ号: ')\n m1 = re.match(r'^[0-9a-zA-Z_]{6,20}$', username)\n if not m1:\n print('请输入有效的用户名.')\n m2 = re.match(r'^[1-9]\\d{4,11}$', qq)\n if not m2:\n print('请输入有效的QQ号.')\n if m1 and m2:\n print('你输入的信息是有效的!')\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day01-15/code/Day12/str1.py\n\n\"\"\"\n字符串常用操作\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-19\n\"\"\"\n\nimport pyperclip\n\n# 转义字符\nprint('My brother\\'s name is \\'007\\'')\n# 原始字符串\nprint(r'My brother\\'s name is \\'007\\'')\n\nstr = 'hello123world'\nprint('he' in str)\nprint('her' in str)\n# 字符串是否只包含字母\nprint(str.isalpha())\n# 字符串是否只包含字母和数字\nprint(str.isalnum())\n# 字符串是否只包含数字\nprint(str.isdecimal())\n\nprint(str[0:5].isalpha())\nprint(str[5:8].isdecimal())\n\nlist = ['床前明月光', '疑是地上霜', '举头望明月', '低头思故乡']\nprint('-'.join(list))\nsentence = 'You go your way I will go mine'\nwords_list = sentence.split()\nprint(words_list)\nemail = ' jackfrued@126.com '\nprint(email)\nprint(email.strip())\nprint(email.lstrip())\n\n# 将文本放入系统剪切板中\npyperclip.copy('老虎不发猫你当我病危呀')\n# 从系统剪切板获得文本\n# print(pyperclip.paste())\n\n\n\nFile: Day01-15/code/Day15/word1.py\n\n\"\"\"\n创建Word文件\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-26\n\"\"\"\n\n\nFile: Day01-15/code/Day15/pdf1.py\n\n\"\"\"\n创建PDF文件\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-26\n\"\"\"\n\n\nFile: Day01-15/code/Day15/excel1.py\n\n\"\"\"\n创建Excel文件\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-26\n\"\"\"\nfrom openpyxl import Workbook\nfrom openpyxl.worksheet.table import Table, TableStyleInfo\n\nworkbook = Workbook()\nsheet = workbook.active\ndata = [\n [1001, '白元芳', '男', '13123456789'],\n [1002, '白洁', '女', '13233445566']\n]\nsheet.append(['学号', '姓名', '性别', '电话'])\nfor row in data:\n sheet.append(row)\ntab = Table(displayName=\"Table1\", ref=\"A1:E5\")\n\ntab.tableStyleInfo = TableStyleInfo(\n name=\"TableStyleMedium9\", showFirstColumn=False,\n showLastColumn=False, showRowStripes=True, showColumnStripes=True)\nsheet.add_table(tab)\nworkbook.save('./res/全班学生数据.xlsx')\n\n\n\nFile: Day01-15/code/Day15/excel2.py\n\n\"\"\"\n读取Excel文件\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-26\n\"\"\"\n\nfrom openpyxl import load_workbook\nfrom openpyxl import Workbook\n\nworkbook = load_workbook('./res/学生明细表.xlsx')\nprint(workbook.sheetnames)\nsheet = workbook[workbook.sheetnames[0]]\nprint(sheet.title)\nfor row in range(2, 7):\n for col in range(65, 70):\n cell_index = chr(col) + str(row)\n print(sheet[cell_index].value, end='\\t')\n print()\n\n\n\nFile: Day01-15/code/Day15/pdf2.py\n\n\"\"\"\n读取PDF文件\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-26\n\"\"\"\n\nfrom PyPDF2 import PdfFileReader\n\nwith open('./res/Python课程大纲.pdf', 'rb') as f:\n reader = PdfFileReader(f, strict=False)\n print(reader.numPages)\n if reader.isEncrypted:\n reader.decrypt('')\n current_page = reader.getPage(5)\n print(current_page)\n print(current_page.extractText())\n\n\n\nFile: Day01-15/code/Day15/pillow1.py\n\n\"\"\"\n使用pillow操作图像\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-26\n\"\"\"\nfrom PIL import Image\n\nimg = Image.open('./res/guido.jpg')\nprint(img.size)\nprint(img.format)\nprint(img.format_description)\nimg.save('./res/guido.png')\n\nimg2 = Image.open('./res/guido.png')\nimg3 = img2.crop((335, 435, 430, 615))\nfor x in range(4):\n for y in range(5):\n img2.paste(img3, (95 * y , 180 * x))\nimg2.resize((img.size[0] // 2, img.size[1] // 2))\nimg2.rotate(90)\nimg2.save('./res/guido2.png')\n\n\n\nFile: Day01-15/code/Day15/word2.py\n\n\"\"\"\n读取Word文件\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-26\n\"\"\"\n\nfrom docx import Document\n\ndoc = Document('./res/用函数还是用复杂的表达式.docx')\nprint(len(doc.paragraphs))\nprint(doc.paragraphs[0].text)\n# print(doc.paragraphs[1].runs[0].text)\n\ncontent = []\nfor para in doc.paragraphs:\n content.append(para.text)\nprint(''.join(content))\n\n\n\nFile: Day01-15/code/Day14/fileclient.py\n\nfrom socket import socket\nfrom json import loads\nfrom base64 import b64decode\n\n\ndef main():\n client = socket()\n client.connect(('192.168.1.2', 5566))\n # 定义一个保存二进制数据的对象\n in_data = bytes()\n # 由于不知道服务器发送的数据有多大每次接收1024字节\n data = client.recv(1024)\n while data:\n # 将收到的数据拼接起来\n in_data += data\n data = client.recv(1024)\n # 将收到的二进制数据解码成JSON字符串并转换成字典\n # loads函数的作用就是将JSON字符串转成字典对象\n my_dict = loads(in_data.decode('utf-8'))\n filename = my_dict['filename']\n filedata = my_dict['filedata'].encode('utf-8')\n with open('/Users/Hao/' + filename, 'wb') as f:\n # 将base64格式的数据解码成二进制数据并写入文件\n f.write(b64decode(filedata))\n print('图片已保存.')\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day01-15/code/Day14/chatserver.py\n\nfrom socket import socket\nfrom threading import Thread\n\n\ndef main():\n\n class ClientHandler(Thread):\n\n def __init__(self, client):\n super().__init__()\n self._client = client\n\n def run(self):\n try:\n while True:\n try:\n data = self._client.recv(1024)\n if data.decode('utf-8') == 'byebye':\n clients.remove(self._client)\n self._client.close()\n break\n else:\n for client in clients:\n client.send(data)\n except Exception as e:\n print(e)\n clients.remove(self._client)\n break\n except Exception as e:\n print(e)\n\n server = socket()\n server.bind(('10.7.189.118', 12345))\n server.listen(512)\n clients = []\n while True:\n curr_client, addr = server.accept()\n print(addr[0], '连接到服务器.')\n clients.append(curr_client)\n ClientHandler(curr_client).start()\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day01-15/code/Day14/fileserver.py\n\nfrom socket import socket, SOCK_STREAM, AF_INET\nfrom base64 import b64encode\nfrom json import dumps\nfrom threading import Thread\n\n\ndef main():\n\n # 自定义线程类\n class FileTransferHandler(Thread):\n\n def __init__(self, cclient):\n super().__init__()\n self.cclient = cclient\n\n def run(self):\n my_dict = {}\n my_dict['filename'] = 'guido.jpg'\n # JSON是纯文本不能携带二进制数据\n # 所以图片的二进制数据要处理成base64编码\n my_dict['filedata'] = data\n # 通过dumps函数将字典处理成JSON字符串\n json_str = dumps(my_dict)\n # 发送JSON字符串\n self.cclient.send(json_str.encode('utf-8'))\n self.cclient.close()\n\n # 1.创建套接字对象并指定使用哪种传输服务\n server = socket()\n # 2.绑定IP地址和端口(区分不同的服务)\n server.bind(('192.168.1.2', 5566))\n # 3.开启监听 - 监听客户端连接到服务器\n server.listen(512)\n print('服务器启动开始监听...')\n with open('guido.jpg', 'rb') as f:\n # 将二进制数据处理成base64再解码成字符串\n data = b64encode(f.read()).decode('utf-8')\n while True:\n client, addr = server.accept()\n # 用一个字典(键值对)来保存要发送的各种数据\n # 待会可以将字典处理成JSON格式在网络上传递\n FileTransferHandler(client).start()\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day01-15/code/Day14/socket4.py\n\n\"\"\"\n套接字 - 基于UDP协议创建Echo客户端\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-22\n\"\"\"\n\nfrom socket import *\n\nclient = socket(AF_INET, SOCK_DGRAM)\nwhile True:\n data_str = input('请输入: ')\n client.sendto(data_str.encode('utf-8'), ('localhost', 6789))\n data, addr = client.recvfrom(1024)\n data_str = data.decode('utf-8')\n print('服务器回应:', data_str)\n if data_str == 'bye':\n break\nclient.close()\n\n\n\nFile: Day01-15/code/Day14/mmdownloader.py\n\nfrom time import time\nfrom threading import Thread\n\nimport requests\n\n\nclass DownloadHanlder(Thread):\n\n def __init__(self, url):\n super().__init__()\n self.url = url\n\n def run(self):\n filename = self.url[self.url.rfind('/') + 1:]\n resp = requests.get(self.url)\n with open('/Users/Hao/Downloads/' + filename, 'wb') as f:\n f.write(resp.content)\n\n\ndef main():\n # 通过requests模块的get函数获取网络资源\n resp = requests.get(\n 'http://api.tianapi.com/meinv/?key=772a81a51ae5c780251b1f98ea431b84&num=10')\n # 将服务器返回的JSON格式的数据解析为字典\n data_model = resp.json()\n for mm_dict in data_model['newslist']:\n url = mm_dict['picUrl']\n # 通过多线程的方式实现图片下载\n DownloadHanlder(url).start()\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day01-15/code/Day14/chatclient.py\n\nfrom socket import socket\nfrom threading import Thread\n\n\ndef main():\n\n class RefreshScreenThread(Thread):\n\n def __init__(self, client):\n super().__init__()\n self._client = client\n\n def run(self):\n while running:\n data = self._client.recv(1024)\n print(data.decode('utf-8'))\n\n nickname = input('请输入你的昵称: ')\n myclient = socket()\n myclient.connect(('10.7.189.118', 12345))\n running = True\n RefreshScreenThread(myclient).start()\n while running:\n content = input('请发言: ')\n if content == 'byebye':\n myclient.send(content.encode('utf-8'))\n running = False\n else:\n msg = nickname + ': ' + content\n myclient.send(msg.encode('utf-8'))\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day01-15/code/Day14/socket5.py\n\n\"\"\"\n使用socketserver模块创建时间服务器\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-22\n\"\"\"\nfrom socketserver import TCPServer, StreamRequestHandler\nfrom time import *\n\n\nclass EchoRequestHandler(StreamRequestHandler):\n\n def handle(self):\n currtime = localtime(time())\n timestr = strftime('%Y-%m-%d %H:%M:%S', currtime)\n self.wfile.write(timestr.encode('utf-8'))\n\n\nserver = TCPServer(('localhost', 6789), EchoRequestHandler)\nserver.serve_forever()\n\n\n\nFile: Day01-15/code/Day14/socket1.py\n\n\"\"\"\n套接字 - 基于TCP协议创建时间服务器\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-22\n\"\"\"\n\nfrom socket import *\nfrom time import *\n\nserver = socket(AF_INET, SOCK_STREAM)\nserver.bind(('localhost', 6789))\nserver.listen()\nprint('服务器已经启动正在监听客户端连接.')\nwhile True:\n client, addr = server.accept()\n print('客户端%s:%d连接成功.' % (addr[0], addr[1]))\n currtime = localtime(time())\n timestr = strftime('%Y-%m-%d %H:%M:%S', currtime)\n client.send(timestr.encode('utf-8'))\n client.close()\nserver.close()\n\n\n\nFile: Day01-15/code/Day14/timeserver.py\n\nfrom socket import socket, SOCK_STREAM, AF_INET\nfrom datetime import datetime\n\n\ndef main():\n # 1.创建套接字对象并指定使用哪种传输服务\n # family=AF_INET - IPv4地址\n # family=AF_INET6 - IPv6地址\n # type=SOCK_STREAM - TCP套接字\n # type=SOCK_DGRAM - UDP套接字\n # type=SOCK_RAW - 原始套接字\n server = socket(family=AF_INET, type=SOCK_STREAM)\n # 2.绑定IP地址和端口(区分不同的服务)\n server.bind(('192.168.1.2', 6789))\n # 3.开启监听 - 监听客户端连接到服务器\n server.listen(512)\n print('服务器启动开始监听...')\n # 4.通过循环接收客户端的连接并作出相应的处理(提供服务)\n while True:\n # accept方法是一个阻塞方法如果没有客户端连接到服务器\n # 这个方法就会阻塞代码不会向下执行\n # accept方法返回元组其中的第一个元素是客户端对象\n # 第二个元素是客户端的地址(由IP和端口两部分构成)\n client, addr = server.accept()\n print(str(addr) + '连接到了服务器.')\n # 5.发送数据\n client.send(str(datetime.now()).encode('utf-8'))\n # 6.断开连接\n client.close()\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day01-15/code/Day14/socket2.py\n\n\"\"\"\n套接字 - 基于TCP协议创建时间客户端\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-22\n\"\"\"\n\nfrom socket import *\n\nclient = socket(AF_INET, SOCK_STREAM)\nclient.connect(('localhost', 6789))\nwhile True:\n data = client.recv(1024)\n if not data:\n break\n print(data.decode('utf-8'))\nclient.close()\n\n\n\nFile: Day01-15/code/Day14/socket3.py\n\n\"\"\"\n套接字 - 基于UDP协议Echo服务器\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-22\n\"\"\"\nfrom socket import *\nfrom time import *\n\nserver = socket(AF_INET, SOCK_DGRAM)\nserver.bind(('localhost', 6789))\nwhile True:\n data, addr = server.recvfrom(1024)\n server.sendto(data, addr)\nserver.close()\n\n\n\nFile: Day01-15/code/Day14/timeclient.py\n\nfrom socket import socket\n\n\ndef main():\n client = socket()\n client.connect(('10.7.152.69', 6789))\n print(client.recv(1024).decode('utf-8'))\n client.close()\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day01-15/code/Day13/multithread4.py\n\n\"\"\"\n使用多线程的情况 - 耗时间的任务在独立的线程中执行\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-20\n\"\"\"\n\nimport time\nimport tkinter\nimport tkinter.messagebox\nfrom threading import Thread\n\n\ndef main():\n\n class DownloadTaskHandler(Thread):\n\n def run(self):\n # 模拟下载任务需要花费10秒钟时间\n time.sleep(10)\n tkinter.messagebox.showinfo('提示', '下载完成!')\n # 启用下载按钮\n button1.config(state=tkinter.NORMAL)\n\n def download():\n # 禁用下载按钮\n button1.config(state=tkinter.DISABLED)\n # 通过daemon参数将线程设置为守护线程(主程序退出就不再保留执行)\n DownloadTaskHandler(daemon=True).start()\n\n def show_about():\n tkinter.messagebox.showinfo('关于', '作者: 骆昊(v1.0)')\n\n top = tkinter.Tk()\n top.title('单线程')\n top.geometry('200x150')\n top.wm_attributes('-topmost', 1)\n\n panel = tkinter.Frame(top)\n button1 = tkinter.Button(panel, text='下载', command=download)\n button1.pack(side='left')\n button2 = tkinter.Button(panel, text='关于', command=show_about)\n button2.pack(side='right')\n panel.pack(side='bottom')\n\n tkinter.mainloop()\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day01-15/code/Day13/singlethread1.py\n\n\"\"\"\n不使用多线程的情况 - 模拟多个下载任务\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-20\n\"\"\"\n\nfrom random import randint\nfrom time import time, sleep\n\n\ndef download_task(filename):\n print('开始下载%s...' % filename)\n time_to_download = randint(5, 10)\n sleep(time_to_download)\n print('下载完成! 耗费了%d秒' % time_to_download)\n\n\ndef main():\n start = time()\n download_task('Python从入门到住院.pdf')\n download_task('Peking Hot.avi')\n end = time()\n print('总共耗费了%.2f秒.' % (end - start))\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day01-15/code/Day13/multithread1.py\n\n\"\"\"\n使用多线程的情况 - 模拟多个下载任务\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-20\n\"\"\"\n\nfrom random import randint\nfrom time import time, sleep\nimport atexit\nimport _thread\n\n\ndef download_task(filename):\n print('开始下载%s...' % filename)\n time_to_download = randint(5, 10)\n print('剩余时间%d秒.' % time_to_download)\n sleep(time_to_download)\n print('%s下载完成!' % filename)\n\n\ndef shutdown_hook(start):\n end = time()\n print('总共耗费了%.3f秒.' % (end - start))\n\n\ndef main():\n start = time()\n # 将多个下载任务放到多个线程中执行\n thread1 = _thread.start_new_thread(download_task, ('Python从入门到住院.pdf',))\n thread2 = _thread.start_new_thread(download_task, ('Peking Hot.avi',))\n # 注册关机钩子在程序执行结束前计算执行时间\n atexit.register(shutdown_hook, start)\n\n\nif __name__ == '__main__':\n main()\n\n# 执行这里的代码会引发致命错误(不要被这个词吓到) 因为主线程结束后下载线程再想执行就会出问题\n# 需要说明一下 由于_thread模块属于比较底层的线程操作而且不支持守护线程的概念\n# 在实际开发中会有诸多不便 因此我们推荐使用threading模块提供的高级操作进行多线程编程\n\n\n\nFile: Day01-15/code/Day13/generator1.py\n\n\"\"\"\n生成器 - 生成器语法\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-21\n\"\"\"\n\nseq = [x * x for x in range(10)]\nprint(seq)\n\ngen = (x * x for x in range(10))\nprint(gen)\nfor x in gen:\n print(x)\n\nnum = 10\ngen = (x ** y for x, y in zip(range(1, num), range(num - 1, 0, -1)))\nprint(gen)\nn = 1\nwhile n < num:\n print(next(gen))\n n += 1\n\n\n\nFile: Day01-15/code/Day13/multithread5.py\n\n\"\"\"\n多个线程共享数据 - 没有锁的情况\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-20\n\"\"\"\n\nfrom time import sleep\nfrom threading import Thread, Lock\n\n\nclass Account(object):\n\n def __init__(self):\n self._balance = 0\n self._lock = Lock()\n\n def deposit(self, money):\n # 先获取锁才能执行后续的代码\n self._lock.acquire()\n try:\n new_balance = self._balance + money\n sleep(0.01)\n self._balance = new_balance\n finally:\n # 这段代码放在finally中保证释放锁的操作一定要执行\n self._lock.release()\n\n @property\n def balance(self):\n return self._balance\n\n\nclass AddMoneyThread(Thread):\n\n def __init__(self, account, money):\n super().__init__()\n self._account = account\n self._money = money\n\n def run(self):\n self._account.deposit(self._money)\n\n\ndef main():\n account = Account()\n threads = []\n # 创建100个存款的线程向同一个账户中存钱\n for _ in range(100):\n t = AddMoneyThread(account, 1)\n threads.append(t)\n t.start()\n # 等所有存款的线程都执行完毕∫\n for t in threads:\n t.join()\n print('账户余额为: ￥%d元' % account.balance)\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day01-15/code/Day13/multiprocess1.py\n\n\"\"\"\n使用Process类创建多个进程\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-20\n\"\"\"\n\n# 通过下面程序的执行结果可以证实 父进程在创建子进程时复制了进程及其数据结构\n# 每个进程都有自己独立的内存空间 所以进程之间共享数据只能通过IPC的方式\n\n\nfrom multiprocessing import Process, Queue, current_process\nfrom time import sleep\n\n\ndef sub_task(content, counts):\n print(f'PID: {current_process().pid}')\n counter = 0\n while counter < counts:\n counter += 1\n print(f'{counter}: {content}')\n sleep(0.01)\n\n\ndef main():\n number = random.randrange(5, 10)\n Process(target=sub_task, args=('Ping', number)).start()\n Process(target=sub_task, args=('Pong', number)).start()\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day01-15/code/Day13/asyncio1.py\n\n\"\"\"\n异步I/O操作 - asyncio模块\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-21\n\"\"\"\n\nimport asyncio\nimport threading\n# import time\n\n\n@asyncio.coroutine\ndef hello():\n print('%s: hello, world!' % threading.current_thread())\n # 休眠不会阻塞主线程因为使用了异步I/O操作\n # 注意有yield from才会等待休眠操作执行完成\n yield from asyncio.sleep(2)\n # asyncio.sleep(1)\n # time.sleep(1)\n print('%s: goodbye, world!' % threading.current_thread())\n\n\nloop = asyncio.get_event_loop()\ntasks = [hello(), hello()]\n# 等待两个异步I/O操作执行结束\nloop.run_until_complete(asyncio.wait(tasks))\nprint('game over!')\nloop.close()\n\n\n\nFile: Day01-15/code/Day13/coroutine1.py\n\n\"\"\"\n使用协程 - 模拟快递中心派发快递\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-21\n\"\"\"\n\nfrom time import sleep\nfrom random import random\n\n\ndef build_deliver_man(man_id):\n total = 0\n while True:\n total += 1\n print('%d号快递员准备接今天的第%d单.' % (man_id, total))\n pkg = yield\n print('%d号快递员收到编号为%s的包裹.' % (man_id, pkg))\n sleep(random() * 3)\n\n\ndef package_center(deliver_man, max_per_day):\n num = 1\n deliver_man.send(None)\n # next(deliver_man)\n while num <= max_per_day:\n package_id = 'PKG-%d' % num\n deliver_man.send(package_id)\n num += 1\n sleep(0.1)\n deliver_man.close()\n print('今天的包裹派送完毕!')\n\n\ndm = build_deliver_man(1)\npackage_center(dm, 10)\n\n# 两个函数虽然没有调用关系但是创建快递员的函数作为一个协程协助了快递中心函数完成任务\n# 想一想如果有多个快递员的时候应该如何处理\n\n\n\nFile: Day01-15/code/Day13/multiprocess4.py\n\nfrom time import time\n\n\ndef main():\n total = 0\n number_list = [x for x in range(1, 100000001)]\n start = time()\n for number in number_list:\n total += number\n print(total)\n end = time()\n print('Execution time: %.3fs' % (end - start))\n\n\nif __name__ == '__main__':\n main()\n\n\nFile: Day01-15/code/Day13/test2.py\n\nimport time\nfrom threading import Thread, Lock\n\n\nclass Account(object):\n\n def __init__(self, balance=0):\n self._balance = balance\n self._lock = Lock()\n\n @property\n def balance(self):\n return self._balance\n\n def deposit(self, money):\n # 当多个线程同时访问一个资源的时候 就有可能因为竞争资源导致资源的状态错误\n # 被多个线程访问的资源我们通常称之为临界资源 对临界资源的访问需要加上保护\n if money > 0:\n self._lock.acquire()\n try:\n new_balance = self._balance + money\n time.sleep(0.01)\n self._balance = new_balance\n finally:\n self._lock.release()\n\n\nclass AddMoneyThread(Thread):\n\n def __init__(self, account):\n super().__init__()\n self._account = account\n\n def run(self):\n self._account.deposit(1)\n\n\ndef main():\n account = Account(1000)\n tlist = []\n for _ in range(100):\n t = AddMoneyThread(account)\n tlist.append(t)\n t.start()\n for t in tlist:\n t.join()\n print('账户余额: %d元' % account.balance)\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day01-15/code/Day13/asyncio2.py\n\n\"\"\"\n异步I/O操作 - async和await\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-21\n\"\"\"\nimport asyncio\nimport threading\n\n\n# 通过async修饰的函数不再是普通函数而是一个协程\n# 注意async和await将在Python 3.7中作为关键字出现\nasync def hello():\n print('%s: hello, world!' % threading.current_thread())\n await asyncio.sleep(2)\n print('%s: goodbye, world!' % threading.current_thread())\n\n\nloop = asyncio.get_event_loop()\ntasks = [hello(), hello()]\n# 等待两个异步I/O操作执行结束\nloop.run_until_complete(asyncio.wait(tasks))\nloop.close()\n\n\n\nFile: Day01-15/code/Day13/coroutine2.py\n\n\"\"\"\n使用协程 - 查看协程的状态\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-21\n\"\"\"\n\nfrom time import sleep\nfrom inspect import getgeneratorstate\n\n\ndef build_deliver_man(man_id):\n total = 0\n while True:\n total += 1\n print('%d号快递员准备接今天的第%d单.' % (man_id, total))\n pkg = yield\n print('%d号快递员收到编号为%s的包裹.' % (man_id, pkg))\n sleep(0.5)\n\n\ndef package_center(deliver_man, max_per_day):\n num = 1\n # 创建状态(GEN_CREATED) - 等待开始执行\n print(getgeneratorstate(deliver_man))\n deliver_man.send(None)\n # 挂起状态(GEN_SUSPENDED) - 在yield表达式处暂停\n print(getgeneratorstate(deliver_man))\n # next(deliver_man)\n while num <= max_per_day:\n package_id = 'PKG-%d' % num\n deliver_man.send(package_id)\n num += 1\n deliver_man.close()\n # 结束状态(GEN_CLOSED) - 执行完毕\n print(getgeneratorstate(deliver_man))\n print('今天的包裹派送完毕!')\n\n\ndm = build_deliver_man(1)\npackage_center(dm, 10)\n\n\n\nFile: Day01-15/code/Day13/multiprocess3.py\n\n\"\"\"\n创建进程调用其他程序\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-20\n\"\"\"\n\nimport subprocess\nimport sys\n\ndef main():\n # 通过sys.argv获取命令行参数\n if len(sys.argv) > 1:\n # 第一个命令行参数是程序本身所以从第二个开始取\n for index in range(1, len(sys.argv)):\n try:\n # 通过subprocess模块的call函数启动子进程\n status = subprocess.call(sys.argv[index])\n except FileNotFoundError:\n print('不能执行%s命令' % sys.argv[index])\n else:\n print('请使用命令行参数指定要执行的进程')\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day01-15/code/Day13/test3.py\n\nfrom random import randint\nfrom threading import Thread\nfrom time import sleep\n\nimport pygame\n\n\nclass Color(object):\n BLACK = (0, 0, 0)\n WHITE = (255, 255, 255)\n GRAY = (242, 242, 242)\n\n @staticmethod\n def random_color():\n r = randint(0, 255)\n g = randint(0, 255)\n b = randint(0, 255)\n return r, g, b\n\n\nclass Car(object):\n\n def __init__(self, x, y, color):\n self._x = x\n self._y = y\n self._color = color\n\n def move(self):\n if self._x + 80 < 950:\n self._x += randint(1, 10)\n\n def draw(self, screen):\n pygame.draw.rect(screen, self._color,\n (self._x, self._y, 80, 40), 0)\n\n\ndef main():\n\n class BackgroundTask(Thread):\n\n def run(self):\n while True:\n screen.fill(Color.GRAY)\n pygame.draw.line(screen, Color.BLACK, (130, 0), (130, 600), 4)\n pygame.draw.line(screen, Color.BLACK, (950, 0), (950, 600), 4)\n for car in cars:\n car.draw(screen)\n pygame.display.flip()\n sleep(0.05)\n for car in cars:\n car.move()\n\n cars = []\n for index in range(5):\n temp = Car(50, 50 + 120 * index, Color.random_color())\n cars.append(temp)\n pygame.init()\n screen = pygame.display.set_mode((1000, 600))\n BackgroundTask(daemon=True).start()\n running = True\n while running:\n for event in pygame.event.get():\n if event.type == pygame.QUIT:\n running = False\n pygame.quit()\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day01-15/code/Day13/asyncio3.py\n\n\"\"\"\n异步I/O操作 - asyncio模块\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-21\n\"\"\"\nimport asyncio\n\n\nasync def wget(host):\n print('wget %s...' % host)\n connect = asyncio.open_connection(host, 80)\n # 异步方式等待连接结果\n reader, writer = await connect\n header = 'GET / HTTP/1.0\\r\\nHost: %s\\r\\n\\r\\n' % host\n writer.write(header.encode('utf-8'))\n # 异步I/O方式执行写操作\n await writer.drain()\n while True:\n # 异步I/O方式执行读操作\n line = await reader.readline()\n if line == b'\\r\\n':\n break\n print('%s header > %s' % (host, line.decode('utf-8').rstrip()))\n writer.close()\n\n\nloop = asyncio.get_event_loop()\n# 通过生成式语法创建一个装了三个协程的列表\nhosts_list = ['www.sina.com.cn', 'www.sohu.com', 'www.163.com']\ntasks = [wget(host) for host in hosts_list]\n# 下面的方法将异步I/O操作放入EventLoop直到执行完毕\nloop.run_until_complete(asyncio.wait(tasks))\nloop.close()\n\n\n\nFile: Day01-15/code/Day13/multiprocess2.py\n\n\"\"\"\n实现进程间的通信\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-20\n\"\"\"\nimport multiprocessing\nimport os\n\n\ndef sub_task(queue):\n print('子进程进程号:', os.getpid())\n counter = 0\n while counter < 1000:\n queue.put('Pong')\n counter += 1\n\n\nif __name__ == '__main__':\n print('当前进程号:', os.getpid())\n queue = multiprocessing.Queue()\n p = multiprocessing.Process(target=sub_task, args=(queue,))\n p.start()\n counter = 0\n while counter < 1000:\n queue.put('Ping')\n counter += 1\n p.join()\n print('子任务已经完成.')\n for _ in range(2000):\n print(queue.get(), end='')\n\n\n\nFile: Day01-15/code/Day13/multithread2.py\n\n\"\"\"\n使用多线程的情况 - 模拟多个下载任务\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-20\n\"\"\"\n\nfrom random import randint\nfrom threading import Thread\nfrom time import time, sleep\n\n\ndef download_task(filename):\n print('开始下载%s...' % filename)\n time_to_download = randint(5, 10)\n sleep(time_to_download)\n print('%s下载完成! 耗费了%d秒' % (filename, time_to_download))\n\n\ndef main():\n start = time()\n thread1 = Thread(target=download_task, args=('Python从入门到住院.pdf',))\n thread1.start()\n thread2 = Thread(target=download_task, args=('Peking Hot.avi',))\n thread2.start()\n thread1.join()\n thread2.join()\n end = time()\n print('总共耗费了%.3f秒' % (end - start))\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day01-15/code/Day13/generator2.py\n\n\"\"\"\n生成器 - 使用yield关键字\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-21\n\"\"\"\n\n\ndef fib(num):\n n, a, b = 0, 0, 1\n while n < num:\n yield b\n a, b = b, a + b\n n += 1\n\n\nfor x in fib(20):\n print(x)\n\n\n\nFile: Day01-15/code/Day13/multithread6.py\n\n\"\"\"\n多个线程共享数据 - 有锁的情况\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-20\n\"\"\"\n\nimport time\nimport threading\n\n\nclass Account(object):\n\n def __init__(self):\n self._balance = 0\n self._lock = threading.Lock()\n\n def deposit(self, money):\n # 获得锁后代码才能继续执行\n self._lock.acquire()\n try:\n new_balance = self._balance + money\n time.sleep(0.01)\n self._balance = new_balance\n finally:\n # 操作完成后一定要记着释放锁\n self._lock.release()\n\n @property\n def balance(self):\n return self._balance\n\n\nif __name__ == '__main__':\n account = Account()\n # 创建100个存款的线程向同一个账户中存钱\n for _ in range(100):\n threading.Thread(target=account.deposit, args=(1,)).start()\n # 等所有存款的线程都执行完毕\n time.sleep(2)\n print('账户余额为: ￥%d元' % account.balance)\n\n# 想一想结果为什么不是我们期望的100元\n\n\n\nFile: Day01-15/code/Day13/singlethread2.py\n\n\"\"\"\n不使用多线程的情况 - 耗时间的任务阻塞主事件循环\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-20\n\"\"\"\n\nimport time\nimport tkinter\nimport tkinter.messagebox\n\n\ndef download():\n # 模拟下载任务需要花费10秒钟时间\n time.sleep(10)\n tkinter.messagebox.showinfo('提示', '下载完成!')\n\n\ndef show_about():\n tkinter.messagebox.showinfo('关于', '作者: 骆昊(v1.0)')\n\n\ndef main():\n top = tkinter.Tk()\n top.title('单线程')\n top.geometry('200x150')\n top.wm_attributes('-topmost', True)\n\n panel = tkinter.Frame(top)\n button1 = tkinter.Button(panel, text='下载', command=download)\n button1.pack(side='left')\n button2 = tkinter.Button(panel, text='关于', command=show_about)\n button2.pack(side='right')\n panel.pack(side='bottom')\n\n tkinter.mainloop()\n\n\nif __name__ == '__main__':\n main()\n\n\n# 在不使用多线程的情况下 一旦点击下载按钮 由于该操作需要花费10秒中的时间\n# 整个主消息循环也会被阻塞10秒钟无法响应其他的事件\n# 事实上 对于没有因果关系的子任务 这种顺序执行的方式并不合理\n\n\n\nFile: Day01-15/code/Day13/multithread3.py\n\n\"\"\"\n使用多线程的情况 - 模拟多个下载任务\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-20\n\"\"\"\n\nfrom random import randint\nfrom time import time, sleep\nimport threading\n\n\nclass DownloadTask(threading.Thread):\n\n def __init__(self, filename):\n super().__init__()\n self._filename = filename\n\n def run(self):\n print('开始下载%s...' % self._filename)\n time_to_download = randint(5, 10)\n print('剩余时间%d秒.' % time_to_download)\n sleep(time_to_download)\n print('%s下载完成!' % self._filename)\n\n\ndef main():\n start = time()\n # 将多个下载任务放到多个线程中执行\n # 通过自定义的线程类创建线程对象 线程启动后会回调执行run方法\n thread1 = DownloadTask('Python从入门到住院.pdf')\n thread1.start()\n thread2 = DownloadTask('Peking Hot.avi')\n thread2.start()\n thread1.join()\n thread2.join()\n end = time()\n print('总共耗费了%.3f秒' % (end - start))\n\n\nif __name__ == '__main__':\n main()\n\n# 请注意通过threading.Thread创建的线程默认是非守护线程\n\n\n\nFile: Day01-15/code/Day04/for2.py\n\n\"\"\"\n用for循环实现1~100之间的偶数求和\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-01\n\"\"\"\n\nsum = 0\nfor x in range(2, 101, 2):\n sum += x\nprint(sum)\n\n\n\nFile: Day01-15/code/Day04/for6.py\n\n\"\"\"\n打印各种三角形图案\n\n*\n**\n***\n****\n*****\n\n *\n **\n ***\n ****\n*****\n\n *\n ***\n *****\n *******\n*********\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-01\n\"\"\"\n\nrow = int(input('请输入行数: '))\nfor i in range(row):\n for _ in range(i + 1):\n print('*', end='')\n print()\n\nfor i in range(row):\n for j in range(row):\n if j < row - i - 1:\n print(' ', end='')\n else:\n print('*', end='')\n print()\n\nfor i in range(row):\n for _ in range(row - i - 1):\n print(' ', end='')\n for _ in range(2 * i + 1):\n print('*', end='')\n print()\n\n\n\nFile: Day01-15/code/Day04/while1.py\n\n\"\"\"\n用while循环实现1~100求和\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-01\n\"\"\"\n\nsum = 0\nnum = 1\nwhile num <= 100:\n sum += num\n num += 1\nprint(sum)\n\n\n\nFile: Day01-15/code/Day04/for3.py\n\n\"\"\"\n输入非负整数n计算n!\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-01\n\"\"\"\n\nn = int(input('n = '))\nresult = 1\nfor x in range(1, n + 1):\n result *= x\nprint('%d! = %d' % (n, result))\n\n\n\nFile: Day01-15/code/Day04/while2.py\n\n\"\"\"\n用while循环实现1~100之间的偶数求和\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-01\n\"\"\"\n\nsum, num = 0, 2\nwhile num <= 100:\n sum += num\n num += 2\nprint(sum)\n\n\n\nFile: Day01-15/code/Day04/for4.py\n\n\"\"\"\n输入一个正整数判断它是不是素数\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-01\n\"\"\"\nfrom math import sqrt\n\nnum = int(input('请输入一个正整数: '))\nend = int(sqrt(num))\nis_prime = True\nfor x in range(2, end + 1):\n if num % x == 0:\n is_prime = False\n break\nif is_prime and num != 1:\n print('%d是素数' % num)\nelse:\n print('%d不是素数' % num)\n\n\n\nFile: Day01-15/code/Day04/for1.py\n\n\"\"\"\n用for循环实现1~100求和\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-01\n\"\"\"\n\nsum = 0\nfor x in range(1, 101):\n sum += x\nprint(sum)\n\n\n\nFile: Day01-15/code/Day04/for5.py\n\n\"\"\"\n输入两个正整数计算最大公约数和最小公倍数\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-01\n\"\"\"\n\nx = int(input('x = '))\ny = int(input('y = '))\nif x > y:\n (x, y) = (y, x)\nfor factor in range(x, 0, -1):\n if x % factor == 0 and y % factor == 0:\n print('%d和%d的最大公约数是%d' % (x, y, factor))\n print('%d和%d的最小公倍数是%d' % (x, y, x * y // factor))\n break\n\n\n\nFile: Day01-15/code/Day03/tax.py\n\n\"\"\"\n输入月收入和五险一金计算个人所得税\n说明：写这段代码时新的个人所得税计算方式还没有颁布\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-02-28\n\"\"\"\n\nsalary = float(input('本月收入: '))\ninsurance = float(input('五险一金: '))\ndiff = salary - insurance - 3500\nif diff <= 0:\n rate = 0\n deduction = 0\nelif diff < 1500:\n rate = 0.03\n deduction = 0\nelif diff < 4500:\n rate = 0.1\n deduction = 105\nelif diff < 9000:\n rate = 0.2\n deduction = 555\nelif diff < 35000:\n rate = 0.25\n deduction = 1005\nelif diff < 55000:\n rate = 0.3\n deduction = 2755\nelif diff < 80000:\n rate = 0.35\n deduction = 5505\nelse:\n rate = 0.45\n deduction = 13505\ntax = abs(diff * rate - deduction)\nprint('个人所得税: ￥%.2f元' % tax)\nprint('实际到手收入: ￥%.2f元' % (diff + 3500 - tax))\n\n\n\nFile: Day01-15/code/Day03/conversion.py\n\n\"\"\"\n英制单位英寸和公制单位厘米互换\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-02-28\n\"\"\"\n\nvalue = float(input('请输入长度: '))\nunit = input('请输入单位: ')\nif unit == 'in' or unit == '英寸':\n print('%f英寸 = %f厘米' % (value, value * 2.54))\nelif unit == 'cm' or unit == '厘米':\n print('%f厘米 = %f英寸' % (value, value / 2.54))\nelse:\n print('请输入有效的单位')\n\n\n\nFile: Day01-15/code/Day03/rolldice.py\n\n\"\"\"\n掷骰子决定做什么事情\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-02-28\n\"\"\"\nfrom random import randint\n\nface = randint(1, 6)\nif face == 1:\n result = '唱首歌'\nelif face == 2:\n result = '跳个舞'\nelif face == 3:\n result = '学狗叫'\nelif face == 4:\n result = '做俯卧撑'\nelif face == 5:\n result = '念绕口令'\nelse:\n result = '讲冷笑话'\nprint(result)\n\n\n\nFile: Day01-15/code/Day03/triangle.py\n\n\"\"\"\n判断输入的边长能否构成三角形\n如果能则计算出三角形的周长和面积\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-02-28\n\"\"\"\nimport math\n\na = float(input('a = '))\nb = float(input('b = '))\nc = float(input('c = '))\nif a + b > c and a + c > b and b + c > a:\n print('周长: %f' % (a + b + c))\n p = (a + b + c) / 2\n area = math.sqrt(p * (p - a) * (p - b) * (p - c))\n print('面积: %f' % (area))\nelse:\n print('不能构成三角形')\n\n\n\nFile: Day01-15/code/Day03/verify.py\n\n\"\"\"\n用户身份验证\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-02-28\n\"\"\"\n# import getpass\n# from getpass import getpass\n# from getpass import *\n\nusername = input('请输入用户名: ')\npassword = input('请输入口令: ')\n# 输入口令的时候终端中没有回显\n# password = getpass.getpass('请输入口令: ')\nif username == 'admin' and password == '123456':\n print('身份验证成功!')\nelse:\n print('身份验证失败!')\n\n\n\nFile: Day01-15/code/Day03/piecewise.py\n\n\"\"\"\n分段函数求值\n 3x - 5 (x > 1)\nf(x) = x + 2 (-1 <= x <= 1)\n 5x + 3 (x < -1)\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-02-28\n\"\"\"\n\nx = float(input('x = '))\nif x > 1:\n y = 3 * x - 5\nelif x >= -1:\n y = x + 2\nelse:\n y = 5 * x + 3\nprint('f(%.2f) = %.2f' % (x, y))\n\n\n\nFile: Day01-15/code/Day03/grade.py\n\n\"\"\"\n百分制成绩转等级制成绩\n90分以上，输出A\n80分~89分，输出B\n70分~79分，输出C\n60分~69分，输出D\n60分以下，输出E\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-02-28\n\"\"\"\n\nscore = float(input('请输入成绩: '))\nif score >= 90:\n grade = 'A'\nelif score >= 80:\n grade = 'B'\nelif score >= 70:\n grade = 'C'\nelif score >= 60:\n grade = 'D'\nelse:\n grade = 'E'\nprint('对应的等级是:', grade)\n\n\n\nFile: Day01-15/code/Day02/variable2.py\n\n\"\"\"\n将input函数输入的数据保存在变量中并进行操作\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-02-27\n\"\"\"\n\na = int(input('a = '))\nb = int(input('b = '))\nprint(a + b)\nprint(a - b)\nprint(a * b)\nprint(a / b)\nprint(a // b)\nprint(a % b)\nprint(a ** b)\n\n\n\nFile: Day01-15/code/Day02/leap.py\n\n\"\"\"\n输入年份 如果是闰年输出True 否则输出False\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-02-27\n\"\"\"\n\nyear = int(input('请输入年份: '))\n# 如果代码太长写成一行不便于阅读 可以使用\\或()折行\nis_leap = (year % 4 == 0 and year % 100 != 0 or\n year % 400 == 0)\nprint(is_leap)\n\n\n\nFile: Day01-15/code/Day02/variable3.py\n\n\"\"\"\n格式化输出\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-02-27\n\"\"\"\n\na = int(input('a = '))\nb = int(input('b = '))\nprint('%d + %d = %d' % (a, b, a + b))\nprint('%d - %d = %d' % (a, b, a - b))\nprint('%d * %d = %d' % (a, b, a * b))\nprint('%d / %d = %f' % (a, b, a / b))\nprint('%d // %d = %d' % (a, b, a // b))\nprint('%d %% %d = %d' % (a, b, a % b))\nprint('%d ** %d = %d' % (a, b, a ** b))\n\n\n\nFile: Day01-15/code/Day02/circle.py\n\n\"\"\"\n输入半径计算圆的周长和面积\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-02-27\n\"\"\"\nimport math\n\nradius = float(input('请输入圆的半径: '))\nperimeter = 2 * math.pi * radius\narea = math.pi * radius * radius\nprint('周长: %.2f' % perimeter)\nprint('面积: %.2f' % area)\n\n\n\nFile: Day01-15/code/Day02/operator.py\n\n\"\"\"\n运算符的使用\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-02-27\n\"\"\"\n\na = 5\nb = 10\nc = 3\nd = 4\ne = 5\na += b\na -= c\na *= d\na /= e\nprint(\"a = \", a)\n\nflag1 = 3 > 2\nflag2 = 2 < 1\nflag3 = flag1 and flag2\nflag4 = flag1 or flag2\nflag5 = not flag1\nprint(\"flag1 = \", flag1)\nprint(\"flag2 = \", flag2)\nprint(\"flag3 = \", flag3)\nprint(\"flag4 = \", flag4)\nprint(\"flag5 = \", flag5)\nprint(flag1 is True)\nprint(flag2 is not False)\n\n\n\nFile: Day01-15/code/Day02/centigrade.py\n\n\"\"\"\n将华氏温度转换为摄氏温度\nF = 1.8C + 32\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-02-27\n\"\"\"\n\nf = float(input('请输入华氏温度: '))\nc = (f - 32) / 1.8\nprint('%.1f华氏度 = %.1f摄氏度' % (f, c))\n\n\n\nFile: Day01-15/code/Day02/variable4.py\n\n\"\"\"\n检查变量的类型\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-02-27\n\"\"\"\n\na = 100\nb = 1000000000000000000\nc = 12.345\nd = 1 + 5j\ne = 'A'\nf = 'hello, world'\ng = True\nprint(type(a))\nprint(type(b))\nprint(type(c))\nprint(type(d))\nprint(type(e))\nprint(type(f))\nprint(type(g))\n\n\n\nFile: Day01-15/code/Day02/variable5.py\n\n\"\"\"\n类型转换\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-02-27\n\"\"\"\n\na = 100\nb = str(a)\nc = 12.345\nd = str(c)\ne = '123'\nf = int(e)\ng = '123.456'\nh = float(g)\ni = False\nj = str(i)\nk = 'hello'\nm = bool(k)\nprint(a)\nprint(type(a))\nprint(b)\nprint(type(b))\nprint(c)\nprint(type(c))\nprint(d)\nprint(type(d))\nprint(e)\nprint(type(e))\nprint(f)\nprint(type(f))\nprint(g)\nprint(type(g))\nprint(h)\nprint(type(h))\nprint(i)\nprint(type(i))\nprint(j)\nprint(type(j))\nprint(k)\nprint(type(k))\nprint(m)\nprint(type(m))\n\n\n\nFile: Day01-15/code/Day02/strings.py\n\n\"\"\"\n字符串常用操作\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-02-27\n\"\"\"\n\nstr1 = 'hello, world!'\nprint('字符串的长度是:', len(str1))\nprint('单词首字母大写: ', str1.title())\nprint('字符串变大写: ', str1.upper())\n# str1 = str1.upper()\nprint('字符串是不是大写: ', str1.isupper())\nprint('字符串是不是以hello开头: ', str1.startswith('hello'))\nprint('字符串是不是以hello结尾: ', str1.endswith('hello'))\nprint('字符串是不是以感叹号开头: ', str1.startswith('!'))\nprint('字符串是不是一感叹号结尾: ', str1.endswith('!'))\nstr2 = '- \\u9a86\\u660a'\nstr3 = str1.title() + ' ' + str2.lower()\nprint(str3)\n\n\n\nFile: Day01-15/code/Day02/variable1.py\n\n\"\"\"\n使用变量保存数据并进行操作\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-02-27\n\"\"\"\n\na = 321\nb = 123\nprint(a + b)\nprint(a - b)\nprint(a * b)\nprint(a / b)\nprint(a // b)\nprint(a % b)\nprint(a ** b)\n\n\n\nFile: Day01-15/code/Day05/prime.py\n\n\"\"\"\n输出2~99之间的素数\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-02\n\"\"\"\n\nimport math\n\nfor num in range(2, 100):\n is_prime = True\n for factor in range(2, int(math.sqrt(num)) + 1):\n if num % factor == 0:\n is_prime = False\n break\n if is_prime:\n print(num, end=' ')\n\n\n\nFile: Day01-15/code/Day05/palindrome.py\n\n\"\"\"\n判断输入的正整数是不是回文数\n回文数是指将一个正整数从左往右排列和从右往左排列值一样的数\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-02\n\"\"\"\n\nnum = int(input('请输入一个正整数: '))\ntemp = num\nnum2 = 0\nwhile temp > 0:\n num2 *= 10\n num2 += temp % 10\n temp //= 10\nif num == num2:\n print('%d是回文数' % num)\nelse:\n print('%d不是回文数' % num)\n\n\n\nFile: Day01-15/code/Day05/guess.py\n\n\"\"\"\n猜数字游戏\n计算机出一个1~100之间的随机数由人来猜\n计算机根据人猜的数字分别给出提示大一点/小一点/猜对了\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-02\n\"\"\"\nimport random\n\nanswer = random.randint(1, 100)\ncounter = 0\nwhile True:\n counter += 1\n number = int(input('请输入: '))\n if number < answer:\n print('大一点')\n elif number > answer:\n print('小一点')\n else:\n print('恭喜你猜对了!')\n break\nprint('你总共猜了%d次' % counter)\nif counter > 7:\n print('你的智商余额明显不足')\n\n\n\nFile: Day01-15/code/Day05/lily.py\n\n\"\"\"\n找出100~999之间的所有水仙花数\n水仙花数是各位立方和等于这个数本身的数\n如: 153 = 1**3 + 5**3 + 3**3\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-02\n\"\"\"\n\nfor num in range(100, 1000):\n low = num % 10\n mid = num // 10 % 10\n high = num // 100\n if num == low ** 3 + mid ** 3 + high ** 3:\n print(num)\n\n\n\nFile: Day01-15/code/Day05/perfect.py\n\n\"\"\"\n找出1~9999之间的所有完美数\n完美数是除自身外其他所有因子的和正好等于这个数本身的数\n例如: 6 = 1 + 2 + 3, 28 = 1 + 2 + 4 + 7 + 14\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-02\n\"\"\"\nimport math\n\nfor num in range(2, 10000):\n result = 0\n for factor in range(1, int(math.sqrt(num)) + 1):\n if num % factor == 0:\n result += factor\n if factor > 1 and num // factor != factor:\n result += num // factor\n if result == num:\n print(num)\n\n\n\nFile: Day01-15/code/Day05/table.py\n\n\"\"\"\n输出乘法口诀表(九九表)\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-02\n\"\"\"\n\nfor i in range(1, 10):\n for j in range(1, i + 1):\n print('%d*%d=%d' % (i, j, i * j), end='\\t')\n print()\n\n\n\nFile: Day01-15/code/Day05/craps.py\n\n\"\"\"\nCraps赌博游戏\n玩家摇两颗色子 如果第一次摇出7点或11点 玩家胜\n如果摇出2点 3点 12点 庄家胜 其他情况游戏继续\n玩家再次要色子 如果摇出7点 庄家胜\n如果摇出第一次摇的点数 玩家胜\n否则游戏继续 玩家继续摇色子\n玩家进入游戏时有1000元的赌注 全部输光游戏结束\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-02\n\"\"\"\nfrom random import randint\n\nmoney = 1000\nwhile money > 0:\n print('你的总资产为:', money)\n needs_go_on = False\n while True:\n debt = int(input('请下注: '))\n if 0 < debt <= money:\n break\n first = randint(1, 6) + randint(1, 6)\n print('玩家摇出了%d点' % first)\n if first == 7 or first == 11:\n print('玩家胜!')\n money += debt\n elif first == 2 or first == 3 or first == 12:\n print('庄家胜!')\n money -= debt\n else:\n needs_go_on = True\n\n while needs_go_on:\n current = randint(1, 6) + randint(1, 6)\n print('玩家摇出了%d点' % current)\n if current == 7:\n print('庄家胜')\n money -= debt\n needs_go_on = False\n elif current == first:\n print('玩家胜')\n money += debt\n needs_go_on = False\n\nprint('你破产了, 游戏结束!')\n\n\n\nFile: Day01-15/code/Day05/chicken.py\n\n\"\"\"\n求解《百钱百鸡》问题\n1只公鸡5元 1只母鸡3元 3只小鸡1元 用100元买100只鸡\n问公鸡 母鸡 小鸡各有多少只\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-02\n\"\"\"\n\nfor x in range(0, 20):\n for y in range(0, 33):\n z = 100 - x - y\n if 5 * x + 3 * y + z / 3 == 100:\n print('公鸡: %d只, 母鸡: %d只, 小鸡: %d只' % (x, y, z))\n\n\n\nFile: Day01-15/code/Day05/fibonacci.py\n\n\"\"\"\n输出斐波那契数列的前20个数\n1 1 2 3 5 8 13 21 ...\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-02\n\"\"\"\n\na = 0\nb = 1\nfor _ in range(20):\n a, b = b, a + b\n print(a, end=' ')\n\n\n\nFile: Day01-15/code/Day11/csv1.py\n\n\"\"\"\n读取CSV文件\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-13\n\"\"\"\n\nimport csv\n\nfilename = 'example.csv'\n\ntry:\n with open(filename) as f:\n reader = csv.reader(f)\n data = list(reader)\nexcept FileNotFoundError:\n print('无法打开文件:', filename)\nelse:\n for item in data:\n print('%-30s%-20s%-10s' % (item[0], item[1], item[2]))\n\n\n\nFile: Day01-15/code/Day11/json2.py\n\n\"\"\"\n写入JSON文件\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-13\n\"\"\"\n\nimport json\n\nteacher_dict = {'name': '白元芳', 'age': 25, 'title': '讲师'}\njson_str = json.dumps(teacher_dict)\nprint(json_str)\nprint(type(json_str))\nfruits_list = ['apple', 'orange', 'strawberry', 'banana', 'pitaya']\njson_str = json.dumps(fruits_list)\nprint(json_str)\nprint(type(json_str))\n\n\n\nFile: Day01-15/code/Day11/file2.py\n\n\"\"\"\n读取圆周率文件判断其中是否包含自己的生日\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-13\n\"\"\"\n\nbirth = input('请输入你的生日: ')\nwith open('pi_million_digits.txt') as f:\n lines = f.readlines()\n pi_string = ''\n for line in lines:\n pi_string += line.strip()\n if birth in pi_string:\n print('Bingo!!!')\n\n\n\nFile: Day01-15/code/Day11/ex2.py\n\n\"\"\"\n异常机制 - 处理程序在运行时可能发生的状态\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-13\n\"\"\"\n\ninput_again = True\nwhile input_again:\n try:\n a = int(input('a = '))\n b = int(input('b = '))\n print('%d / %d = %f' % (a, b, a / b))\n input_again = False\n except (ValueError, ZeroDivisionError) as msg:\n print(msg)\n\n\n\nFile: Day01-15/code/Day11/ex3.py\n\n\"\"\"\n异常机制 - 处理程序在运行时可能发生的状态\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-13\n\"\"\"\n\nimport time\nimport sys\n\nfilename = input('请输入文件名: ')\ntry:\n with open(filename) as f:\n lines = f.readlines()\nexcept FileNotFoundError as msg:\n print('无法打开文件:', filename)\n print(msg)\nexcept UnicodeDecodeError as msg:\n print('非文本文件无法解码')\n sys.exit()\nelse:\n for line in lines:\n print(line.rstrip())\n time.sleep(0.5)\nfinally:\n # 此处最适合做善后工作\n print('不管发生什么我都会执行')\n\n\n\nFile: Day01-15/code/Day11/file3.py\n\n\"\"\"\n写文本文件\n将100以内的素数写入到文件中\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-13\n\"\"\"\n\nfrom math import sqrt\n\n\ndef is_prime(n):\n for factor in range(2, int(sqrt(n)) + 1):\n if n % factor == 0:\n return False\n return True\n\n\n# 试一试有什么不一样\n# with open('prime.txt', 'a') as f:\nwith open('prime.txt', 'w') as f:\n for num in range(2, 100):\n if is_prime(num):\n f.write(str(num) + '\\n')\nprint('写入完成!')\n\n\n\nFile: Day01-15/code/Day11/file4.py\n\n\"\"\"\n读写二进制文件\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-13\n\"\"\"\nimport base64\n\nwith open('mm.jpg', 'rb') as f:\n data = f.read()\n # print(type(data))\n # print(data)\n print('字节数:', len(data))\n # 将图片处理成BASE-64编码\n print(base64.b64encode(data))\n\nwith open('girl.jpg', 'wb') as f:\n f.write(data)\nprint('写入完成!')\n\n\n\nFile: Day01-15/code/Day11/ex4.py\n\n\"\"\"\n引发异常和异常栈\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-13\n\"\"\"\n\n\ndef f1():\n raise AssertionError('发生异常')\n\n\ndef f2():\n f1()\n\n\ndef f3():\n f2()\n\n\nf3()\n\n\n\nFile: Day01-15/code/Day11/file1.py\n\n\"\"\"\n从文本文件中读取数据\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-13\n\"\"\"\n\nimport time\n\n\ndef main():\n # 一次性读取整个文件内容\n with open('致橡树.txt', 'r', encoding='utf-8') as f:\n print(f.read())\n\n # 通过for-in循环逐行读取\n with open('致橡树.txt', mode='r') as f:\n for line in f:\n print(line, end='')\n time.sleep(0.5)\n print()\n\n # 读取文件按行读取到列表中\n with open('致橡树.txt') as f:\n lines = f.readlines()\n print(lines)\n \n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day01-15/code/Day11/ex1.py\n\n\"\"\"\n异常机制 - 处理程序在运行时可能发生的状态\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-13\n\"\"\"\n\ninput_again = True\nwhile input_again:\n try:\n a = int(input('a = '))\n b = int(input('b = '))\n print('%d / %d = %f' % (a, b, a / b))\n input_again = False\n except ValueError:\n print('请输入整数')\n except ZeroDivisionError:\n print('除数不能为0')\n# 处理异常让代码不因异常而崩溃是一方面\n# 更重要的是可以通过对异常的处理让代码从异常中恢复过来\n\n\n\nFile: Day01-15/code/Day11/json1.py\n\n\"\"\"\n读取JSON数据\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-13\n\"\"\"\n\nimport json\nimport csv2\n\njson_str = '{\"name\": \"骆昊\", \"age\": 38, \"title\": \"叫兽\"}'\nresult = json.loads(json_str)\nprint(result)\nprint(type(result))\nprint(result['name'])\nprint(result['age'])\n\n# 把转换得到的字典作为关键字参数传入Teacher的构造器\nteacher = csv2.Teacher(**result)\nprint(teacher)\nprint(teacher.name)\nprint(teacher.age)\nprint(teacher.title)\n\n# 请思考如何将下面JSON格式的天气数据转换成对象并获取我们需要的信息\n# 稍后我们会讲解如何通过网络API获取我们需要的JSON格式的数据\n\"\"\"\n {\n \"wendu\": \"29\",\n \"ganmao\": \"各项气象条件适宜，发生感冒机率较低。但请避免长期处于空调房间中，以防感冒。\",\n \"forecast\": [\n {\n \"fengxiang\": \"南风\",\n \"fengli\": \"3-4级\",\n \"high\": \"高温 32℃\",\n \"type\": \"多云\",\n \"low\": \"低温 17℃\",\n \"date\": \"16日星期二\"\n },\n {\n \"fengxiang\": \"南风\",\n \"fengli\": \"微风级\",\n \"high\": \"高温 34℃\",\n \"type\": \"晴\",\n \"low\": \"低温 19℃\",\n \"date\": \"17日星期三\"\n },\n {\n \"fengxiang\": \"南风\",\n \"fengli\": \"微风级\",\n \"high\": \"高温 35℃\",\n \"type\": \"晴\",\n \"low\": \"低温 22℃\",\n \"date\": \"18日星期四\"\n },\n {\n \"fengxiang\": \"南风\",\n \"fengli\": \"微风级\",\n \"high\": \"高温 35℃\",\n \"type\": \"多云\",\n \"low\": \"低温 22℃\",\n \"date\": \"19日星期五\"\n },\n {\n \"fengxiang\": \"南风\",\n \"fengli\": \"3-4级\",\n \"high\": \"高温 34℃\",\n \"type\": \"晴\",\n \"low\": \"低温 21℃\",\n \"date\": \"20日星期六\"\n }\n ],\n \"yesterday\": {\n \"fl\": \"微风\",\n \"fx\": \"南风\",\n \"high\": \"高温 28℃\",\n \"type\": \"晴\",\n \"low\": \"低温 15℃\",\n \"date\": \"15日星期一\"\n },\n \"aqi\": \"72\",\n \"city\": \"北京\"\n }\n\"\"\"\n\n\n\nFile: Day01-15/code/Day11/csv2.py\n\n\"\"\"\n写入CSV文件\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-13\n\"\"\"\n\nimport csv\n\n\nclass Teacher(object):\n\n def __init__(self, name, age, title):\n self.__name = name\n self.__age = age\n self.__title = title\n self.__index = -1\n\n @property\n def name(self):\n return self.__name\n\n @property\n def age(self):\n return self.__age\n\n @property\n def title(self):\n return self.__title\n\n\nfilename = 'teacher.csv'\nteachers = [Teacher('骆昊', 38, '叫兽'), Teacher('狄仁杰', 25, '砖家')]\n\ntry:\n with open(filename, 'w') as f:\n writer = csv.writer(f)\n for teacher in teachers:\n writer.writerow([teacher.name, teacher.age, teacher.title])\nexcept BaseException as e:\n print('无法写入文件:', filename)\nelse:\n print('保存数据完成!')\n\n\n\nFile: Day01-15/code/Day10/renju.py\n\nimport pygame\n\nEMPTY = 0\nBLACK = 1\nWHITE = 2\n\nblack_color = [0, 0, 0]\nwhite_color = [255, 255, 255]\n\n\nclass RenjuBoard(object):\n\n def __init__(self):\n self._board = [[]] * 15\n self.reset()\n\n def reset(self):\n for row in range(len(self._board)):\n self._board[row] = [EMPTY] * 15\n\n def move(self, row, col, is_black):\n if self._board[row][col] == EMPTY:\n self._board[row][col] = BLACK if is_black else WHITE\n return True\n return False\n\n def draw(self, screen):\n for index in range(1, 16):\n pygame.draw.line(screen, black_color,\n [40, 40 * index], [600, 40 * index], 1)\n pygame.draw.line(screen, black_color,\n [40 * index, 40], [40 * index, 600], 1)\n pygame.draw.rect(screen, black_color, [36, 36, 568, 568], 4)\n pygame.draw.circle(screen, black_color, [320, 320], 5, 0)\n pygame.draw.circle(screen, black_color, [160, 160], 5, 0)\n pygame.draw.circle(screen, black_color, [480, 480], 5, 0)\n pygame.draw.circle(screen, black_color, [480, 160], 5, 0)\n pygame.draw.circle(screen, black_color, [160, 480], 5, 0)\n for row in range(len(self._board)):\n for col in range(len(self._board[row])):\n if self._board[row][col] != EMPTY:\n ccolor = black_color \\\n if self._board[row][col] == BLACK else white_color\n pos = [40 * (col + 1), 40 * (row + 1)]\n pygame.draw.circle(screen, ccolor, pos, 20, 0)\n\n\ndef main():\n board = RenjuBoard()\n is_black = True\n pygame.init()\n pygame.display.set_caption('五子棋')\n screen = pygame.display.set_mode([640, 640])\n screen.fill([255, 255, 0])\n board.draw(screen)\n pygame.display.flip()\n running = True\n while running:\n for event in pygame.event.get():\n if event.type == pygame.QUIT:\n running = False\n elif event.type == pygame.KEYUP:\n pass\n elif event.type == pygame.MOUSEBUTTONDOWN\\\n and event.button == 1:\n x, y = event.pos\n row = round((y - 40) / 40)\n col = round((x - 40) / 40)\n if board.move(row, col, is_black):\n is_black = not is_black\n screen.fill([255, 255, 0])\n board.draw(screen)\n pygame.display.flip()\n pygame.quit()\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day01-15/code/Day10/gui2.py\n\n\"\"\"\n使用tkinter创建GUI\n- 使用画布绘图\n- 处理鼠标事件\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-14\n\"\"\"\n\nimport tkinter\n\n\ndef mouse_evt_handler(evt=None):\n row = round((evt.y - 20) / 40)\n col = round((evt.x - 20) / 40)\n pos_x = 40 * col\n pos_y = 40 * row\n canvas.create_oval(pos_x, pos_y, 40 + pos_x, 40 + pos_y, fill='black')\n\n\ntop = tkinter.Tk()\n# 设置窗口尺寸\ntop.geometry('620x620')\n# 设置窗口标题\ntop.title('五子棋')\n# 设置窗口大小不可改变\ntop.resizable(False, False)\n# 设置窗口置顶\ntop.wm_attributes('-topmost', 1)\ncanvas = tkinter.Canvas(top, width=600, height=600, bd=0, highlightthickness=0)\ncanvas.bind('<Button-1>', mouse_evt_handler)\ncanvas.create_rectangle(0, 0, 600, 600, fill='yellow', outline='white')\nfor index in range(15):\n canvas.create_line(20, 20 + 40 * index, 580, 20 + 40 * index, fill='black')\n canvas.create_line(20 + 40 * index, 20, 20 + 40 * index, 580, fill='black')\ncanvas.create_rectangle(15, 15, 585, 585, outline='black', width=4)\ncanvas.pack()\ntkinter.mainloop()\n\n# 请思考如何用面向对象的编程思想对上面的代码进行封装\n\n\n\nFile: Day01-15/code/Day10/snake.py\n\nfrom abc import ABCMeta, abstractmethod\nfrom enum import Enum, unique\nfrom random import randrange\nfrom threading import Thread\n\nimport pygame\n\n\nclass Color(object):\n \"\"\"颜色\"\"\"\n\n GRAY = (242, 242, 242)\n BLACK = (0, 0, 0)\n GREEN = (0, 255, 0)\n PINK = (255, 20, 147)\n\n\n@unique\nclass Direction(Enum):\n \"\"\"方向\"\"\"\n\n UP = 0\n RIGHT = 1\n DOWN = 2\n LEFT = 3\n\n\nclass GameObject(object, metaclass=ABCMeta):\n \"\"\"游戏中的对象\"\"\"\n\n def __init__(self, x=0, y=0, color=Color.BLACK):\n \"\"\"\n 初始化方法\n\n :param x: 横坐标\n :param y: 纵坐标\n :param color: 颜色\n \"\"\"\n self._x = x\n self._y = y\n self._color = color\n\n @property\n def x(self):\n return self._x\n\n @property\n def y(self):\n return self._y\n\n @abstractmethod\n def draw(self, screen):\n \"\"\"\n 绘制\n\n :param screen: 屏幕\n \"\"\"\n pass\n\n\nclass Wall(GameObject):\n \"\"\"围墙\"\"\"\n\n def __init__(self, x, y, width, height, color=Color.BLACK):\n \"\"\"\n 初始化方法\n\n :param x: 横坐标\n :param y: 纵坐标\n :param width: 宽度\n :param height: 高度\n :param color: 颜色\n \"\"\"\n super().__init__(x, y, color)\n self._width = width\n self._height = height\n\n @property\n def width(self):\n return self._width\n\n @property\n def height(self):\n return self._height\n\n def draw(self, screen):\n pygame.draw.rect(screen, self._color,\n (self._x, self._y, self._width, self._height), 4)\n\n\nclass Food(GameObject):\n \"\"\"食物\"\"\"\n\n def __init__(self, x, y, size, color=Color.PINK):\n \"\"\"\n 初始化方法\n\n :param x: 横坐标\n :param y: 纵坐标\n :param size: 大小\n :param color: 颜色\n \"\"\"\n super().__init__(x, y, color)\n self._size = size\n self._hidden = False\n\n def draw(self, screen):\n if not self._hidden:\n pygame.draw.circle(screen, self._color,\n (self._x + self._size // 2, self._y + self._size // 2),\n self._size // 2, 0)\n self._hidden = not self._hidden\n\n\nclass SnakeNode(GameObject):\n \"\"\"蛇身上的节点\"\"\"\n\n def __init__(self, x, y, size, color=Color.GREEN):\n \"\"\"\n 初始化方法\n\n :param x: 横坐标\n :param y: 纵坐标\n :param size: 大小\n :param color: 颜色\n \"\"\"\n super().__init__(x, y, color)\n self._size = size\n\n @property\n def size(self):\n return self._size\n\n def draw(self, screen):\n pygame.draw.rect(screen, self._color,\n (self._x, self._y, self._size, self._size), 0)\n pygame.draw.rect(screen, Color.BLACK,\n (self._x, self._y, self._size, self._size), 1)\n\n\nclass Snake(GameObject):\n \"\"\"蛇\"\"\"\n\n def __init__(self, x, y, size=20, length=5):\n \"\"\"\n 初始化方法\n\n :param x: 横坐标\n :param y: 纵坐标\n :param size: 大小\n :param length: 初始长度\n \"\"\"\n super().__init__()\n self._dir = Direction.LEFT\n self._nodes = []\n self._alive = True\n self._new_dir = None\n for index in range(length):\n node = SnakeNode(x + index * size, y, size)\n self._nodes.append(node)\n\n @property\n def dir(self):\n return self._dir\n\n @property\n def alive(self):\n return self._alive\n\n @property\n def head(self):\n return self._nodes[0]\n\n def change_dir(self, new_dir):\n \"\"\"\n 改变方向\n\n :param new_dir: 新方向\n \"\"\"\n if new_dir != self._dir and \\\n (self._dir.value + new_dir.value) % 2 != 0:\n self._new_dir = new_dir\n\n def move(self):\n \"\"\"移动\"\"\"\n if self._new_dir:\n self._dir, self._new_dir = self._new_dir, None\n snake_dir = self._dir\n x, y, size = self.head.x, self.head.y, self.head.size\n if snake_dir == Direction.UP:\n y -= size\n elif snake_dir == Direction.RIGHT:\n x += size\n elif snake_dir == Direction.DOWN:\n y += size\n else:\n x -= size\n new_head = SnakeNode(x, y, size)\n self._nodes.insert(0, new_head)\n self._nodes.pop()\n\n def collide(self, wall):\n \"\"\"\n 撞墙\n\n :param wall: 围墙\n \"\"\"\n head = self.head\n if head.x < wall.x or head.x + head.size > wall.x + wall.width \\\n or head.y < wall.y or head.y + head.size > wall.y + wall.height:\n self._alive = False\n\n def eat_food(self, food):\n \"\"\"\n 吃食物\n\n :param food: 食物\n\n :return: 吃到食物返回True否则返回False\n \"\"\"\n if self.head.x == food.x and self.head.y == food.y:\n tail = self._nodes[-1]\n self._nodes.append(tail)\n return True\n return False\n\n def eat_self(self):\n \"\"\"咬自己\"\"\"\n for index in range(4, len(self._nodes)):\n node = self._nodes[index]\n if node.x == self.head.x and node.y == self.head.y:\n self._alive = False\n\n def draw(self, screen):\n for node in self._nodes:\n node.draw(screen)\n\n\ndef main():\n\n def refresh():\n \"\"\"刷新游戏窗口\"\"\"\n screen.fill(Color.GRAY)\n wall.draw(screen)\n food.draw(screen)\n snake.draw(screen)\n pygame.display.flip()\n\n def handle_key_event(key_event):\n \"\"\"处理按键事件\"\"\"\n key = key_event.key\n if key == pygame.K_F2:\n reset_game()\n elif key in (pygame.K_a, pygame.K_w, pygame.K_d, pygame.K_s):\n if snake.alive:\n if key == pygame.K_w:\n new_dir = Direction.UP\n elif key == pygame.K_d:\n new_dir = Direction.RIGHT\n elif key == pygame.K_s:\n new_dir = Direction.DOWN\n else:\n new_dir = Direction.LEFT\n snake.change_dir(new_dir)\n\n def create_food():\n \"\"\"创建食物\"\"\"\n unit_size = snake.head.size\n max_row = wall.height // unit_size\n max_col = wall.width // unit_size\n row = randrange(0, max_row)\n col = randrange(0, max_col)\n return Food(wall.x + unit_size * col, wall.y + unit_size * row, unit_size)\n\n def reset_game():\n \"\"\"重置游戏\"\"\"\n nonlocal food, snake\n food = create_food()\n snake = Snake(250, 290)\n\n def background_task():\n nonlocal running, food\n while running:\n if snake.alive:\n refresh()\n clock.tick(10)\n if snake.alive:\n snake.move()\n snake.collide(wall)\n if snake.eat_food(food):\n food = create_food()\n snake.eat_self()\n\n \"\"\"\n class BackgroundTask(Thread):\n\n def run(self):\n nonlocal running, food\n while running:\n if snake.alive:\n refresh()\n clock.tick(10)\n if snake.alive:\n snake.move()\n snake.collide(wall)\n if snake.eat_food(food):\n food = create_food()\n snake.eat_self()\n \"\"\"\n\n wall = Wall(10, 10, 600, 600)\n snake = Snake(250, 290)\n food = create_food()\n pygame.init()\n screen = pygame.display.set_mode((620, 620))\n pygame.display.set_caption('贪吃蛇')\n # 创建控制游戏每秒帧数的时钟\n clock = pygame.time.Clock()\n running = True\n # 启动后台线程负责刷新窗口和让蛇移动\n # BackgroundTask().start()\n Thread(target=background_task).start()\n # 处理事件的消息循环\n while running:\n for event in pygame.event.get():\n if event.type == pygame.QUIT:\n running = False\n elif event.type == pygame.KEYDOWN:\n handle_key_event(event)\n pygame.quit()\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day01-15/code/Day10/gui3.py\n\n\"\"\"\n\n使用tkinter创建GUI\n- 在窗口上制作动画\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-14\n\n\"\"\"\n\nimport tkinter\nimport time\n\n\n# 播放动画效果的函数\ndef play_animation():\n canvas.move(oval, 2, 2)\n canvas.update()\n top.after(50, play_animation)\n\n\nx = 10\ny = 10\ntop = tkinter.Tk()\ntop.geometry('600x600')\ntop.title('动画效果')\ntop.resizable(False, False)\ntop.wm_attributes('-topmost', 1)\ncanvas = tkinter.Canvas(top, width=600, height=600, bd=0, highlightthickness=0)\ncanvas.create_rectangle(0, 0, 600, 600, fill='gray')\noval = canvas.create_oval(10, 10, 60, 60, fill='red')\ncanvas.pack()\ntop.update()\nplay_animation()\ntkinter.mainloop()\n\n# 请思考如何让小球碰到屏幕的边界就弹回\n# 请思考如何用面向对象的编程思想对上面的代码进行封装\n\n\n\nFile: Day01-15/code/Day10/ball.py\n\nfrom enum import Enum, unique\nfrom math import sqrt\nfrom random import randint\n\nimport pygame\n\n\n@unique\nclass Color(Enum):\n \"\"\"颜色\"\"\"\n\n RED = (255, 0, 0)\n GREEN = (0, 255, 0)\n BLUE = (0, 0, 255)\n BLACK = (0, 0, 0)\n WHITE = (255, 255, 255)\n GRAY = (242, 242, 242)\n\n @staticmethod\n def random_color():\n \"\"\"获得随机颜色\"\"\"\n r = randint(0, 255)\n g = randint(0, 255)\n b = randint(0, 255)\n return (r, g, b)\n\n\nclass Ball(object):\n \"\"\"球\"\"\"\n\n def __init__(self, x, y, radius, sx, sy, color=Color.RED):\n \"\"\"初始化方法\"\"\"\n self.x = x\n self.y = y\n self.radius = radius\n self.sx = sx\n self.sy = sy\n self.color = color\n self.alive = True\n\n def move(self, screen):\n \"\"\"移动\"\"\"\n self.x += self.sx\n self.y += self.sy\n if self.x - self.radius <= 0 or self.x + self.radius >= screen.get_width():\n self.sx = -self.sx\n if self.y - self.radius <= 0 or self.y + self.radius >= screen.get_height():\n self.sy = -self.sy\n\n def eat(self, other):\n \"\"\"吃其他球\"\"\"\n if self.alive and other.alive and self != other:\n dx, dy = self.x - other.x, self.y - other.y\n distance = sqrt(dx ** 2 + dy ** 2)\n if distance < self.radius + other.radius \\\n and self.radius > other.radius:\n other.alive = False\n \tself.radius = self.radius + int(other.radius * 0.146)\n\n def draw(self, screen):\n \"\"\"在窗口上绘制球\"\"\"\n pygame.draw.circle(screen, self.color,\n (self.x, self.y), self.radius, 0)\n\n\ndef main():\n # 定义用来装所有球的容器\n balls = []\n # 初始化导入的pygame中的模块\n pygame.init()\n # 初始化用于显示的窗口并设置窗口尺寸\n screen = pygame.display.set_mode((800, 600))\n print(screen.get_width())\n print(screen.get_height())\n # 设置当前窗口的标题\n pygame.display.set_caption('大球吃小球')\n # 定义变量来表示小球在屏幕上的位置\n x, y = 50, 50\n running = True\n # 开启一个事件循环处理发生的事件\n while running:\n # 从消息队列中获取事件并对事件进行处理\n for event in pygame.event.get():\n if event.type == pygame.QUIT:\n running = False\n if event.type == pygame.MOUSEBUTTONDOWN and event.button == 1:\n x, y = event.pos\n radius = randint(10, 100)\n sx, sy = randint(-10, 10), randint(-10, 10)\n color = Color.random_color()\n ball = Ball(x, y, radius, sx, sy, color)\n balls.append(ball)\n screen.fill((255, 255, 255))\n for ball in balls:\n if ball.alive:\n ball.draw(screen)\n else:\n balls.remove(ball)\n pygame.display.flip()\n # 每隔50毫秒就改变小球的位置再刷新窗口\n pygame.time.delay(50)\n for ball in balls:\n ball.move(screen)\n for other in balls:\n ball.eat(other)\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day01-15/code/Day10/gui1.py\n\n\"\"\"\n使用tkinter创建GUI\n- 顶层窗口\n- 控件\n- 布局\n- 事件回调\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-14\n\"\"\"\n\nimport tkinter\nimport tkinter.messagebox\n\n\ndef main():\n flag = True\n\n # 修改标签上的文字\n def change_label_text():\n nonlocal flag\n flag = not flag\n color, msg = ('red', 'Hello, world!')\\\n if flag else ('blue', 'Goodbye, world!')\n label.config(text=msg, fg=color)\n\n # 确认退出\n def confirm_to_quit():\n if tkinter.messagebox.askokcancel('温馨提示', '确定要退出吗?'):\n top.quit()\n\n # 创建顶层窗口\n top = tkinter.Tk()\n # 设置窗口大小\n top.geometry('240x160')\n # 设置窗口标题\n top.title('小游戏')\n # 创建标签对象\n label = tkinter.Label(top, text='Hello, world!', font='Arial -32', fg='red')\n label.pack(expand=1)\n # 创建一个装按钮的容器\n panel = tkinter.Frame(top)\n # 创建按钮对象\n button1 = tkinter.Button(panel, text='修改', command=change_label_text)\n button1.pack(side='left')\n button2 = tkinter.Button(panel, text='退出', command=confirm_to_quit)\n button2.pack(side='right')\n panel.pack(side='bottom')\n # 开启主事件循环\n tkinter.mainloop()\n\n\nif __name__ == '__main__':\n main()\n\n\n\nFile: Day01-15/code/Day10/turtle1.py\n\n\"\"\"\n\n用turtle模块绘图\n这是一个非常有趣的模块 它模拟一只乌龟在窗口上爬行的方式来进行绘图\n\nVersion: 0.1\nAuthor: 骆昊\nDate: 2018-03-14\n\n\"\"\"\n\nimport turtle\n\nturtle.pensize(3)\nturtle.penup()\nturtle.goto(-180, 150)\nturtle.pencolor('red')\nturtle.fillcolor('yellow')\nturtle.pendown()\nturtle.begin_fill()\nfor _ in range(36):\n turtle.forward(200)\n turtle.right(170)\nturtle.end_fill()\nturtle.mainloop()\n\n\n"},"repo_readme":{"kind":"string","value":"## Python - 100天从新手到大师\n\n> **作者**：骆昊\n>\n> **说明**：从项目上线到获得8w+星标以来，一直收到反馈说基础部分（前15天的内容）对新手来说是比较困难的，建议有配套视频进行讲解。最近把基础部分的内容重新制作了一个名为[“Python-Core-50-Courses”](<https://github.com/jackfrued/Python-Core-50-Courses>)的项目，用更为简单通俗的方式重写了这部分内容并附带了视频讲解，初学者可以看看这个新的仓库。国内用户如果访问GitHub比较慢的话，可以关注我的**知乎号[Python-Jack](https://www.zhihu.com/people/jackfrued)**，上面的[“从零开始学Python”](<https://zhuanlan.zhihu.com/c_1216656665569013760>)专栏比较适合初学者，其他的专栏如“数据思维和统计思维”、“基于Python的数据分析”等也在持续创作和更新中，欢迎大家关注、点赞和评论。\n>\n> 想获取学习视频的小伙伴，大家可以扫描下面的二维码进入微信小程序，看看有没有适合自己的内容。大家心心念念的机器学习的内容在小程序中都可以找到，由我和我的同事为大家录制的。\n>\n> <img src=\"res/study_card.png\" style=\"zoom:20%;\">\n>\n> 大家在学习过程中如果遇到一些棘手的问题或者需要相关的学习资源，可以加入下面的QQ交流群，三个群是一样的加入一个即可，请不要重复加群，也不要在群里发布广告和其他色情、低俗或敏感内容。**如果缺乏自律性，有付费学习的需求，可以添加我的微信（jackfrued）私聊，备注好自己的称呼和需求，我会给大家提供一些学习方案和职业规划方面的指导**。\n>\n> <img src=\"res/python_study_qq_group.png\" style=\"zoom:30%;\">\n>\n> 配套的视频在抖音和B站持续更新中，有兴趣的小伙伴可以关注我的抖音或B站账号，最近刚刚起号，还希望大家多多支持，非常感谢您！\n>\n> <img src=\"res/qrcode.JPG\" style=\"zoom:20%;\">\n>\n> 大家一直催更的《机器学习和深度学习》因个人和公司的原因，一直处于停滞状态，近期会开始更新相关内容，感谢大家一如既往的支持和理解。\n\n### Python应用领域和职业发展分析\n\n简单的说，Python是一个“优雅”、“明确”、“简单”的编程语言。\n\n - 学习曲线低，非专业人士也能上手\n - 开源系统，拥有强大的生态圈\n - 解释型语言，完美的平台可移植性\n - 动态类型语言，支持面向对象和函数式编程\n - 代码规范程度高，可读性强\n\nPython在以下领域都有用武之地。\n\n - 后端开发 - Python / Java / Go / PHP\n - DevOps - Python / Shell / Ruby\n - 数据采集 - Python / C++ / Java\n - 量化交易 - Python / C++ / R\n - 数据科学 - Python / R / Julia / Matlab\n - 机器学习 - Python / R / C++ / Julia\n - 自动化测试 - Python / Shell\n\n作为一名Python开发者，根据个人的喜好和职业规划，可以选择的就业领域也非常多。\n\n- Python后端开发工程师（服务器、云平台、数据接口）\n- Python运维工程师（自动化运维、SRE、DevOps）\n- Python数据分析师（数据分析、商业智能、数字化运营）\n- Python数据挖掘工程师（机器学习、深度学习、算法专家）\n- Python爬虫工程师\n- Python测试工程师（自动化测试、测试开发）\n\n> **说明**：目前，**数据分析和数据挖掘是非常热门的方向**，因为不管是互联网行业还是传统行业都已经积累了大量的数据，各行各业都需要数据分析师从已有的数据中发现更多的商业价值，从而为企业的决策提供数据的支撑，这就是所谓的数据驱动决策。\n\n给初学者的几个建议：\n\n- Make English as your working language. （让英语成为你的工作语言）\n- Practice makes perfect. （熟能生巧）\n- All experience comes from mistakes. （所有的经验都源于你犯过的错误）\n- Don't be one of the leeches. （不要当伸手党）\n- Either outstanding or out. （要么出众，要么出局）\n\n### Day01~15 - Python语言基础\n\n#### Day01 - [初识Python](./Day01-15/01.初识Python.md)\n\n- Python简介 - Python的历史 / Python的优缺点 / Python的应用领域\n- 搭建编程环境 - Windows环境 / Linux环境 / MacOS环境\n- 从终端运行Python程序 - Hello, world / `print`函数 / 运行程序\n- 使用IDLE - 交互式环境(REPL) / 编写多行代码 / 运行程序 / 退出IDLE\n- 注释 - 注释的作用 / 单行注释 / 多行注释\n\n#### Day02 - [语言元素](./Day01-15/02.语言元素.md)\n\n- 程序和进制 - 指令和程序 / 冯诺依曼机 / 二进制和十进制 / 八进制和十六进制\n- 变量和类型 - 变量的命名 / 变量的使用 / `input`函数 / 检查变量类型 / 类型转换\n- 数字和字符串 - 整数 / 浮点数 / 复数 / 字符串 / 字符串基本操作 / 字符编码\n- 运算符 - 数学运算符 / 赋值运算符 / 比较运算符 / 逻辑运算符 / 身份运算符 / 运算符的优先级\n- 应用案例 - 华氏温度转换成摄氏温度 / 输入圆的半径计算周长和面积 / 输入年份判断是否是闰年\n\n#### Day03 - [分支结构](./Day01-15/03.分支结构.md)\n\n- 分支结构的应用场景 - 条件 / 缩进 / 代码块 / 流程图\n- if语句 - 简单的`if` / `if`-`else`结构 / `if`-`elif`-`else`结构 / 嵌套的`if`\n- 应用案例 - 用户身份验证 / 英制单位与公制单位互换 / 掷骰子决定做什么 / 百分制成绩转等级制 / 分段函数求值 / 输入三条边的长度如果能构成三角形就计算周长和面积\n\n#### Day04 - [循环结构](./Day01-15/04.循环结构.md)\n\n- 循环结构的应用场景 - 条件 / 缩进 / 代码块 / 流程图\n- while循环 - 基本结构 / `break`语句 / `continue`语句\n- for循环 - 基本结构 / `range`类型 / 循环中的分支结构 / 嵌套的循环 / 提前结束程序 \n- 应用案例 - 1~100求和 / 判断素数 / 猜数字游戏 / 打印九九表 / 打印三角形图案 / 猴子吃桃 / 百钱百鸡\n\n#### Day05 - [构造程序逻辑](./Day01-15/05.构造程序逻辑.md)\n\n- 经典案例：水仙花数 / 百钱百鸡 / Craps赌博游戏\n- 练习题目：斐波那契数列 / 完美数 / 素数\n\n#### Day06 - [函数和模块的使用](./Day01-15/06.函数和模块的使用.md)\n\n- 函数的作用 - 代码的坏味道 / 用函数封装功能模块\n- 定义函数 - `def`关键字 / 函数名 / 参数列表 / `return`语句 / 调用自定义函数\n- 调用函数 - Python内置函数 / 导入模块和函数\n- 函数的参数 - 默认参数 / 可变参数 / 关键字参数 / 命名关键字参数\n- 函数的返回值 - 没有返回值 / 返回单个值 / 返回多个值\n- 作用域问题 - 局部作用域 / 嵌套作用域 / 全局作用域 / 内置作用域 / 和作用域相关的关键字\n- 用模块管理函数 - 模块的概念 / 用自定义模块管理函数 / 命名冲突的时候会怎样（同一个模块和不同的模块）\n\n#### Day07 - [字符串和常用数据结构](./Day01-15/07.字符串和常用数据结构.md)\n\n- 字符串的使用 - 计算长度 / 下标运算 / 切片 / 常用方法\n- 列表基本用法 - 定义列表 / 用下表访问元素 / 下标越界 / 添加元素 / 删除元素 / 修改元素 / 切片 / 循环遍历\n- 列表常用操作 - 连接 / 复制(复制元素和复制数组) / 长度 / 排序 / 倒转 / 查找\n- 生成列表 - 使用`range`创建数字列表 / 生成表达式 / 生成器\n- 元组的使用 - 定义元组 / 使用元组中的值 / 修改元组变量 / 元组和列表转换\n- 集合基本用法 - 集合和列表的区别 / 创建集合 / 添加元素 / 删除元素 / 清空\n- 集合常用操作 - 交集 / 并集 / 差集 / 对称差 / 子集 / 超集\n- 字典的基本用法 - 字典的特点 / 创建字典 / 添加元素 / 删除元素 / 取值 / 清空\n- 字典常用操作 - `keys`方法 / `values`方法 / `items`方法 / `setdefault`方法\n- 基础练习 - 跑马灯效果 / 列表找最大元素 / 统计考试成绩的平均分 / Fibonacci数列 / 杨辉三角\n- 综合案例 - 双色球选号 / 井字棋\n\n#### Day08 - [面向对象编程基础](./Day01-15/08.面向对象编程基础.md)\n\n- 类和对象 - 什么是类 / 什么是对象 / 面向对象其他相关概念\n- 定义类 - 基本结构 / 属性和方法 / 构造器 / 析构器 / `__str__`方法\n- 使用对象 - 创建对象 / 给对象发消息\n- 面向对象的四大支柱 - 抽象 / 封装 / 继承 / 多态\n- 基础练习 - 定义学生类 / 定义时钟类 / 定义图形类 / 定义汽车类\n\n#### Day09 - [面向对象进阶](./Day01-15/09.面向对象进阶.md)\n\n- 属性 - 类属性 / 实例属性 / 属性访问器 / 属性修改器 / 属性删除器 / 使用`__slots__`\n- 类中的方法 - 实例方法 / 类方法 / 静态方法\n- 运算符重载 - `__add__` / `__sub__` / `__or__` /`__getitem__` / `__setitem__` / `__len__` / `__repr__` / `__gt__` / `__lt__` / `__le__` / `__ge__` / `__eq__` / `__ne__` / `__contains__` \n- 类(的对象)之间的关系 - 关联 / 继承 / 依赖\n- 继承和多态 - 什么是继承 / 继承的语法 / 调用父类方法 / 方法重写 / 类型判定 / 多重继承 / 菱形继承(钻石继承)和C3算法\n- 综合案例 - 工资结算系统 / 图书自动折扣系统 / 自定义分数类\n\n#### Day10 - [图形用户界面和游戏开发](./Day01-15/10.图形用户界面和游戏开发.md)\n\n- 使用`tkinter`开发GUI程序\n- 使用`pygame`三方库开发游戏应用\n- “大球吃小球”游戏\n\n#### Day11 - [文件和异常](./Day01-15/11.文件和异常.md)\n\n- 读文件 - 读取整个文件 / 逐行读取 / 文件路径\n- 写文件 - 覆盖写入 / 追加写入 / 文本文件 / 二进制文件\n- 异常处理 - 异常机制的重要性 / `try`-`except`代码块 / `else`代码块 / `finally`代码块 / 内置异常类型 / 异常栈 / `raise`语句\n- 数据持久化 - CSV文件概述 / `csv`模块的应用 / JSON数据格式 / `json`模块的应用\n\n#### Day12 - [字符串和正则表达式](./Day01-15/12.字符串和正则表达式.md)\n\n- 字符串高级操作 - 转义字符 / 原始字符串 / 多行字符串 / `in`和`not in`运算符 / `is_xxx`方法 / `join`和`split`方法 / `strip`相关方法 / `pyperclip`模块 / 不变字符串和可变字符串 / `StringIO`的使用\n- 正则表达式入门 - 正则表达式的作用 / 元字符 / 转义 / 量词 / 分组 / 零宽断言 /贪婪匹配与惰性匹配懒惰 / 使用`re`模块实现正则表达式操作（匹配、搜索、替换、捕获）\n- 使用正则表达式 - `re`模块 / `compile`函数 / `group`和`groups`方法 / `match`方法 / `search`方法 / `findall`和`finditer`方法 / `sub`和`subn`方法 / `split`方法\n- 应用案例 - 使用正则表达式验证输入的字符串\n\n#### Day13 - [进程和线程](./Day01-15/13.进程和线程.md)\n\n- 进程和线程的概念 - 什么是进程 / 什么是线程 / 多线程的应用场景\n- 使用进程 - `fork`函数 / `multiprocessing`模块 / 进程池 / 进程间通信\n- 使用线程 - `threading`模块 / `Thread`类 / `RLock`类 / `Condition`类 / 线程池\n\n#### Day14 - [网络编程入门和网络应用开发](./Day01-15/14.网络编程入门和网络应用开发.md)\n\n- 计算机网络基础 - 计算机网络发展史 / “TCP-IP”模型 / IP地址 / 端口 / 协议 / 其他相关概念\n- 网络应用模式 - “客户端-服务器”模式 / “浏览器-服务器”模式\n- 基于HTTP协议访问网络资源 - 网络API概述 / 访问URL / `requests`三方库 / 解析JSON格式数据\n- Python网络编程 - 套接字的概念 / `socket`模块 / `socket`函数 / 创建TCP服务器 / 创建TCP客户端 / 创建UDP服务器 / 创建UDP客户端\n- 电子邮件 - SMTP协议 / POP3协议 / IMAP协议 / `smtplib`模块 / `poplib`模块 / `imaplib`模块\n- 短信服务 - 调用短信服务网关\n\n#### Day15 - [图像和文档处理](./Day01-15/15.图像和办公文档处理.md)\n\n- 用Pillow处理图片 - 图片读写 / 图片合成 / 几何变换 / 色彩转换 / 滤镜效果\n- 读写Word文档 - 文本内容的处理 / 段落 / 页眉和页脚 / 样式的处理\n- 读写Excel文件 - `xlrd` / `xlwt` / `openpyxl`\n\n### Day16~Day20 - [Python语言进阶 ](./Day16-20/16-20.Python语言进阶.md)\n\n- 常用数据结构\n- 函数的高级用法 - “一等公民” / 高阶函数 / Lambda函数 / 作用域和闭包 / 装饰器\n- 面向对象高级知识 - “三大支柱” / 类与类之间的关系 / 垃圾回收 / 魔术属性和方法 / 混入 / 元类 / 面向对象设计原则 / GoF设计模式\n- 迭代器和生成器 - 相关魔术方法 / 创建生成器的两种方式 / \n- 并发和异步编程 - 多线程 / 多进程 / 异步IO / `async`和`awai`t\n\n### Day21~30 - [Web前端入门](./Day21-30/21-30.Web前端概述.md)\n\n- 用HTML标签承载页面内容\n- 用CSS渲染页面\n- 用JavaScript处理交互式行为\n- jQuery入门和提高\n- Vue.js入门\n- Element的使用\n- Bootstrap的使用\n\n### Day31~35 - [玩转Linux操作系统](./Day31-35/31-35.玩转Linux操作系统.md)\n\n- 操作系统发展史和Linux概述\n- Linux基础命令\n- Linux中的实用程序\n- Linux的文件系统\n- Vim编辑器的应用\n- 环境变量和Shell编程\n- 软件的安装和服务的配置\n- 网络访问和管理\n- 其他相关内容\n\n### Day36~45 - 数据库基础和进阶\n\n#### Day36 - [关系型数据库和MySQL概述](./Day36-45/36.关系型数据库和MySQL概述.md)\n\n- 关系型数据库概述\n- MySQL简介\n- 安装MySQL\n- MySQL基本命令\n\n#### Day37 - [SQL详解之DDL](./Day36-45/37.SQL详解之DDL.md)\n\n- 建库建表\n- 删除表和修改表\n\n#### Day38 - [SQL详解之DML](./Day36-45/38.SQL详解之DML.md)\n\n- insert操作\n- delete操作\n- update操作\n\n#### Day39 - [SQL详解之DQL](./Day36-45/39.SQL详解之DQL.md)\n\n- 投影和别名\n- 筛选数据\n- 空值处理\n- 去重\n- 排序\n- 聚合函数\n- 嵌套查询\n- 分组\n- 表连接\n - 笛卡尔积\n - 内连接\n - 自然连接\n - 外连接\n- 窗口函数\n - 定义窗口\n - 排名函数\n - 取数函数\n\n\n#### Day40 - [SQL详解之DCL](./Day36-45/40.SQL详解之DCL.md)\n\n- 创建用户\n- 授予权限\n- 召回权限\n\n#### Day41 - [MySQL新特性](./Day36-45/41.MySQL新特性.md)\n\n- JSON类型\n- 窗口函数\n- 公共表表达式\n\n#### Day42 - [视图、函数和过程](./Day36-45/42.视图、函数和过程.md)\n\n- 视图\n - 使用场景\n - 创建视图\n - 使用限制\n- 函数\n - 内置函数\n - 用户自定义函数（UDF）\n- 过程\n - 创建过程\n - 调用过程\n\n#### Day43 - [索引](./Day36-45/43.索引.md)\n\n- 执行计划\n- 索引的原理\n- 创建索引\n - 普通索引\n - 唯一索引\n - 前缀索引\n - 复合索引\n- 注意事项\n\n#### Day44 - [Python接入MySQL数据库](./Day36-45/44.Python接入MySQL数据库.md)\n\n- 安装三方库\n- 创建连接\n- 获取游标\n- 执行SQL语句\n- 通过游标抓取数据\n- 事务提交和回滚\n- 释放连接\n- 编写ETL脚本\n\n#### Day45 - [大数据平台和HiveSQL](./Day36-45/45.大数据平台和HiveSQL.md)\n\n- Hadoop生态圈\n- Hive概述\n- 准备工作\n- 数据类型\n- DDL操作\n- DML操作\n- 数据查询\n\n### Day46~60 - 实战Django\n\n#### Day46 - [Django快速上手](./Day46-60/46.Django快速上手.md)\n\n- Web应用工作机制\n- HTTP请求和响应\n- Django框架概述\n- 5分钟快速上手\n\n#### Day47 - [深入模型](./Day46-60/47.深入模型.md)\n\n- 关系型数据库配置\n- 使用ORM完成对模型的CRUD操作\n- 管理后台的使用\n- Django模型最佳实践\n- 模型定义参考\n\n#### Day48 - [静态资源和Ajax请求](./Day46-60/48.静态资源和Ajax请求.md)\n\n- 加载静态资源\n- Ajax概述\n- 用Ajax实现投票功能\n\n#### Day49 - [Cookie和Session](./Day46-60/49.Cookie和Session.md)\n\n- 实现用户跟踪\n- cookie和session的关系\n- Django框架对session的支持\n- 视图函数中的cookie读写操作\n\n#### Day50 - [报表和日志](./Day46-60/50.制作报表.md)\n\n- 通过`HttpResponse`修改响应头\n- 使用`StreamingHttpResponse`处理大文件\n- 使用`xlwt`生成Excel报表\n- 使用`reportlab`生成PDF报表\n- 使用ECharts生成前端图表\n\n#### Day51 - [日志和调试工具栏](./Day46-60/51.日志和调试工具栏.md)\n\n- 配置日志\n- 配置Django-Debug-Toolbar\n- 优化ORM代码\n\n#### Day52 - [中间件的应用](./Day46-60/52.中间件的应用.md)\n\n- 什么是中间件\n- Django框架内置的中间件\n- 自定义中间件及其应用场景\n\n#### Day53 - [前后端分离开发入门](./Day46-60/53.前后端分离开发入门.md)\n\n- 返回JSON格式的数据\n- 用Vue.js渲染页面\n\n#### Day54 - [RESTful架构和DRF入门](./Day46-60/54.RESTful架构和DRF入门.md)\n\n- REST概述\n- DRF库使用入门\n- 前后端分离开发\n- JWT的应用\n\n#### Day55 - [RESTful架构和DRF进阶](./Day46-60/55.RESTful架构和DRF进阶.md)\n\n- 使用CBV\n- 数据分页\n- 数据筛选\n\n#### Day56 - [使用缓存](./Day46-60/56.使用缓存.md)\n\n- 网站优化第一定律\n\n- 在Django项目中使用Redis提供缓存服务\n- 在视图函数中读写缓存\n- 使用装饰器实现页面缓存\n- 为数据接口提供缓存服务\n\n#### Day57 - [接入三方平台](./Day46-60/57.接入三方平台.md)\n\n- 文件上传表单控件和图片文件预览\n- 服务器端如何处理上传的文件\n\n#### Day58 - [异步任务和定时任务](./Day46-60/58.异步任务和定时任务.md)\n\n- 网站优化第二定律\n- 配置消息队列服务\n- 在项目中使用Celery实现任务异步化\n- 在项目中使用Celery实现定时任务\n\n#### Day59 - [单元测试](./Day46-60/59.单元测试.md)\n\n#### Day60 - [项目上线](./Day46-60/60.项目上线.md)\n\n- Python中的单元测试\n- Django框架对单元测试的支持\n- 使用版本控制系统\n- 配置和使用uWSGI\n- 动静分离和Nginx配置\n- 配置HTTPS\n- 配置域名解析\n\n### Day61~65 - [爬虫开发](./Day61-65)\n\n#### Day61 - [网络数据采集概述](./Day61-65/61.网络数据采集概述.md)\n\n- 网络爬虫的概念及其应用领域\n- 网络爬虫的合法性探讨\n- 开发网络爬虫的相关工具\n- 一个爬虫程序的构成\n\n#### Day62 - 数据抓取和解析\n\n- [使用`requests`三方库实现数据抓取](./Day61-65/62.用Python获取网络资源-1.md)\n- [页面解析的三种方式](./Day61-65/62.用Python解析HTML页面-2.md)\n - 正则表达式解析\n - XPath解析\n - CSS选择器解析\n\n\n#### Day63 - Python中的并发编程\n\n- [多线程](./Day61-65/63.Python中的并发编程-1.md)\n- [多进程](./Day61-65/63.Python中的并发编程-2.md)\n- [异步I/O](./Day61-65/63.Python中的并发编程-3.md)\n\n#### Day64 - [使用Selenium抓取网页动态内容](./Day61-65/64.使用Selenium抓取网页动态内容.md)\n\n- 安装Selenium\n- 加载页面\n- 查找元素和模拟用户行为\n- 隐式等待和显示等待\n- 执行JavaScript代码\n- Selenium反爬破解\n- 设置无头浏览器\n\n#### Day65 - [爬虫框架Scrapy简介](./Day61-65/65.爬虫框架Scrapy简介.md)\n\n- Scrapy核心组件\n- Scrapy工作流程\n- 安装Scrapy和创建项目\n- 编写蜘蛛程序\n- 编写中间件和管道程序\n- Scrapy配置文件\n\n### Day66~80 - 数据分析\n\n#### Day66 - [数据分析概述](./Day66-80/66.数据分析概述.md)\n\n- 数据分析师的职责\n- 数据分析师的技能栈\n- 数据分析相关库\n\n#### Day67 - [环境准备](./Day66-80/67.环境准备.md)\n\n- 安装和使用anaconda\n - conda相关命令\n- 安装和使用jupyter-lab\n - 安装和启动\n - 使用小技巧\n\n#### Day68 - [NumPy的应用-1](./Day66-80/68.NumPy的应用-1.md)\n\n- 创建数组对象\n- 数组对象的属性\n- 数组对象的索引运算\n - 普通索引\n - 花式索引\n - 布尔索引\n - 切片索引\n- 案例：使用数组处理图像\n\n#### Day69 - [NumPy的应用-2](./Day66-80/69.NumPy的应用-2.md)\n\n- 数组对象的相关方法\n - 获取描述性统计信息\n - 其他相关方法\n\n#### Day70 - [NumPy的应用-3](./Day66-80/70.NumPy的应用-3.md)\n\n- 数组的运算\n - 数组跟标量的运算\n - 数组跟数组的运算\n- 通用一元函数\n- 通用二元函数\n- 广播机制\n- Numpy常用函数\n\n#### Day71 - [NumPy的应用-4](./Day66-80/71.NumPy的应用-4.md)\n\n- 向量\n- 行列式\n- 矩阵\n- 多项式\n\n#### Day72 - [深入浅出pandas-1](./Day66-80/72.深入浅出pandas-1.md)\n\n- 创建`Series`对象\n- `Series`对象的运算\n- `Series`对象的属性和方法\n\n#### Day73 - [深入浅出pandas-2](./Day66-80/73.深入浅出pandas-2.md)\n\n- 创建`DataFrame`对象\n- `DataFrame`对象的属性和方法\n- 读写`DataFrame`中的数据\n\n#### Day74 - [深入浅出pandas-3](./Day66-80/74.深入浅出pandas-3.md)\n\n- 数据重塑\n - 数据拼接\n - 数据合并\n- 数据清洗\n - 缺失值\n - 重复值\n - 异常值\n - 预处理\n\n#### Day75 - [深入浅出pandas-4](./Day66-80/75.深入浅出pandas-4.md)\n\n- 数据透视\n - 获取描述性统计信息\n - 排序和头部值\n - 分组聚合\n - 透视表和交叉表\n- 数据呈现\n\n#### Day76 - [深入浅出pandas-5](./Day66-80/76.深入浅出pandas-5.md)\n\n- 计算同比环比\n- 窗口计算\n- 相关性判定\n\n#### Day77 - [深入浅出pandas-6](./Day66-80/77.深入浅出pandas-6.md)\n\n- 索引的使用\n - 范围索引\n - 分类索引\n - 多级索引\n - 间隔索引\n - 日期时间索引\n\n#### Day78 - [数据可视化-1](./Day66-80/78.数据可视化-1.md)\n\n- 安装和导入matplotlib\n- 创建画布\n- 创建坐标系\n- 绘制图表\n - 折线图\n - 散点图\n - 柱状图\n - 饼状图\n - 直方图\n - 箱线图\n- 显示和保存图表\n\n#### Day79 - [数据可视化-2](./Day66-80/79.数据可视化-2.md)\n\n- 高阶图表\n - 气泡图\n - 面积图\n - 雷达图\n - 玫瑰图\n - 3D图表\n\n#### Day80 - [数据可视化-3](./Day66-80/80.数据可视化-3.md)\n\n- Seaborn\n- Pyecharts\n\n### Day81~90 - [机器学习和深度学习](./Day81-90)\n\n#### Day81 - [机器学习基础](./Day81-90/81.机器学习基础.md)\n\n#### Day82 - [k最近邻分类](./Day81-90/82.k最近邻分类.md)\n\n#### Day83 - [决策树](./Day81-90/83.决策树.md)\n\n#### Day84 - [贝叶斯分类](./Day81-90/84.贝叶斯分类.md)\n\n#### Day85 - [支持向量机](./Day81-90/85.支持向量机.md)\n\n#### Day86 - [K-均值聚类](./Day81-90/86.K-均值聚类.md)\n\n#### Day87 - [回归分析](./Day81-90/87.回归分析.md)\n\n#### Day88 - [深度学习入门](./Day81-90/88.深度学习入门.md)\n\n#### Day89 - [PyTorch概述](./Day81-90/89.PyTorch概述.md)\n\n#### Day90 - [PyTorch实战](./Day81-90/90.PyTorch实战.md)\n\n### Day91~100 - [团队项目开发](./Day91-100)\n\n#### 第91天：[团队项目开发的问题和解决方案](./Day91-100/91.团队项目开发的问题和解决方案.md)\n\n1. 软件过程模型\n - 经典过程模型（瀑布模型）\n - 可行性分析（研究做还是不做），输出《可行性分析报告》。\n - 需求分析（研究做什么），输出《需求规格说明书》和产品界面原型图。\n - 概要设计和详细设计，输出概念模型图（ER图）、物理模型图、类图、时序图等。\n - 编码 / 测试。\n - 上线 / 维护。\n\n 瀑布模型最大的缺点是无法拥抱需求变化，整套流程结束后才能看到产品，团队士气低落。\n - 敏捷开发（Scrum）- 产品所有者、Scrum Master、研发人员 - Sprint\n - 产品的Backlog（用户故事、产品原型）。\n - 计划会议（评估和预算）。\n - 日常开发（站立会议、番茄工作法、结对编程、测试先行、代码重构……）。\n - 修复bug（问题描述、重现步骤、测试人员、被指派人）。\n - 发布版本。\n - 评审会议（Showcase，用户需要参与）。\n - 回顾会议（对当前迭代周期做一个总结）。\n\n > 补充：敏捷软件开发宣言\n >\n > - **个体和互动** 高于 流程和工具\n > - **工作的软件** 高于 详尽的文档\n > - **客户合作** 高于 合同谈判\n > - **响应变化** 高于 遵循计划\n\n \n\n > 角色：产品所有者（决定做什么，能对需求拍板的人）、团队负责人（解决各种问题，专注如何更好的工作，屏蔽外部对开发团队的影响）、开发团队（项目执行人员，具体指开发人员和测试人员）。\n\n > 准备工作：商业案例和资金、合同、憧憬、初始产品需求、初始发布计划、入股、组建团队。\n\n > 敏捷团队通常人数为8-10人。\n\n > 工作量估算：将开发任务量化，包括原型、Logo设计、UI设计、前端开发等，尽量把每个工作分解到最小任务量，最小任务量标准为工作时间不能超过两天，然后估算总体项目时间。把每个任务都贴在看板上面，看板上分三部分：to do（待完成）、in progress（进行中）和done（已完成）。\n\n2. 项目团队组建\n\n - 团队的构成和角色\n\n > 说明：感谢**付祥英**女士帮助我绘制了下面这张精美的公司组织架构图。\n\n \n\n - 编程规范和代码审查（`flake8`、`pylint`）\n\n \n\n - Python中的一些“惯例”（请参考[《Python惯例-如何编写Pythonic的代码》](Python惯例.md)）\n\n - 影响代码可读性的原因：\n\n - 代码注释太少或者没有注释\n - 代码破坏了语言的最佳实践\n - 反模式编程（意大利面代码、复制-黏贴编程、自负编程、……）\n\n3. 团队开发工具介绍\n - 版本控制：Git、Mercury\n - 缺陷管理：[Gitlab](https://about.gitlab.com/)、[Redmine](http://www.redmine.org.cn/)\n - 敏捷闭环工具：[禅道](https://www.zentao.net/)、[JIRA](https://www.atlassian.com/software/jira/features)\n - 持续集成：[Jenkins](https://jenkins.io/)、[Travis-CI](https://travis-ci.org/)\n\n 请参考[《团队项目开发的问题和解决方案》](Day91-100/91.团队项目开发的问题和解决方案.md)。\n\n##### 项目选题和理解业务\n\n1. 选题范围设定\n\n - CMS（用户端）：新闻聚合网站、问答/分享社区、影评/书评网站等。\n - MIS（用户端+管理端）：KMS、KPI考核系统、HRS、CRM系统、供应链系统、仓储管理系统等。\n\n - App后台（管理端+数据接口）：二手交易类、报刊杂志类、小众电商类、新闻资讯类、旅游类、社交类、阅读类等。\n - 其他类型：自身行业背景和工作经验、业务容易理解和把控。\n\n2. 需求理解、模块划分和任务分配\n\n - 需求理解：头脑风暴和竞品分析。\n - 模块划分：画思维导图（XMind），每个模块是一个枝节点，每个具体的功能是一个叶节点（用动词表述），需要确保每个叶节点无法再生出新节点，确定每个叶子节点的重要性、优先级和工作量。\n - 任务分配：由项目负责人根据上面的指标为每个团队成员分配任务。\n\n \n\n3. 制定项目进度表（每日更新）\n\n | 模块 | 功能 | 人员 | 状态 | 完成 | 工时 | 计划开始 | 实际开始 | 计划结束 | 实际结束 | 备注 |\n | ---- | -------- | ------ | -------- | ---- | ---- | -------- | -------- | -------- | -------- | ---------------- |\n | 评论 | 添加评论 | 王大锤 | 正在进行 | 50% | 4 | 2018/8/7 | | 2018/8/7 | | |\n | | 删除评论 | 王大锤 | 等待 | 0% | 2 | 2018/8/7 | | 2018/8/7 | | |\n | | 查看评论 | 白元芳 | 正在进行 | 20% | 4 | 2018/8/7 | | 2018/8/7 | | 需要进行代码审查 |\n | | 评论投票 | 白元芳 | 等待 | 0% | 4 | 2018/8/8 | | 2018/8/8 | | |\n\n4. OOAD和数据库设计\n\n - UML（统一建模语言）的类图\n\n \n\n - 通过模型创建表（正向工程），例如在Django项目中可以通过下面的命令创建二维表。\n\n ```Shell\n python manage.py makemigrations app\n python manage.py migrate\n ```\n\n - 使用PowerDesigner绘制物理模型图。\n\n \n\n - 通过数据表创建模型（反向工程），例如在Django项目中可以通过下面的命令生成模型。\n\n ```Shell\n python manage.py inspectdb > app/models.py\n ```\n\n#### 第92天：[Docker容器技术详解](./Day91-100/92.Docker容器技术详解.md)\n\n1. Docker简介\n2. 安装Docker\n3. 使用Docker创建容器（Nginx、MySQL、Redis、Gitlab、Jenkins）\n4. 构建Docker镜像（Dockerfile的编写和相关指令）\n5. 容器编排（Docker-compose）\n6. 集群管理（Kubernetes）\n\n#### 第93天：[MySQL性能优化](./Day91-100/93.MySQL性能优化.md)\n\n1. 基本原则\n2. InnoDB引擎\n3. 索引的使用和注意事项\n4. 数据分区\n5. SQL优化\n6. 配置优化\n7. 架构优化\n\n#### 第94天：[网络API接口设计](./Day91-100/94.网络API接口设计.md)\n\n- 设计原则\n - 关键问题\n - 其他问题\n- 文档撰写\n\n#### 第95天：[使用Django开发商业项目](./Day91-100/95.使用Django开发商业项\t目.md)\n\n##### 项目开发中的公共问题\n\n1. 数据库的配置（多数据库、主从复制、数据库路由）\n2. 缓存的配置（分区缓存、键设置、超时设置、主从复制、故障恢复（哨兵））\n3. 日志的配置\n4. 分析和调试（Django-Debug-ToolBar）\n5. 好用的Python模块（日期计算、图像处理、数据加密、三方API）\n\n##### REST API设计\n\n1. RESTful架构\n - [理解RESTful架构](http://www.ruanyifeng.com/blog/2011/09/restful.html)\n - [RESTful API设计指南](http://www.ruanyifeng.com/blog/2014/05/restful_api.html)\n - [RESTful API最佳实践](http://www.ruanyifeng.com/blog/2018/10/restful-api-best-practices.html)\n2. API接口文档的撰写\n - [RAP2](http://rap2.taobao.org/)\n - [YAPI](http://yapi.demo.qunar.com/)\n3. [django-REST-framework](https://www.django-rest-framework.org/)的应用\n\n##### 项目中的重点难点剖析\n\n1. 使用缓存缓解数据库压力 - Redis\n2. 使用消息队列做解耦合和削峰 - Celery + RabbitMQ\n\n#### 第96天：[软件测试和自动化测试](Day91-100/96.软件测试和自动化测试.md)\n\n##### 单元测试\n\n1. 测试的种类\n2. 编写单元测试（`unittest`、`pytest`、`nose2`、`tox`、`ddt`、……）\n3. 测试覆盖率（`coverage`）\n\n##### Django项目部署\n\n1. 部署前的准备工作\n - 关键设置（SECRET_KEY / DEBUG / ALLOWED_HOSTS / 缓存 / 数据库）\n - HTTPS / CSRF_COOKIE_SECUR / SESSION_COOKIE_SECURE \n - 日志相关配置\n2. Linux常用命令回顾\n3. Linux常用服务的安装和配置\n4. uWSGI/Gunicorn和Nginx的使用\n - Gunicorn和uWSGI的比较\n - 对于不需要大量定制化的简单应用程序，Gunicorn是一个不错的选择，uWSGI的学习曲线比Gunicorn要陡峭得多，Gunicorn的默认参数就已经能够适应大多数应用程序。\n - uWSGI支持异构部署。\n - 由于Nginx本身支持uWSGI，在线上一般都将Nginx和uWSGI捆绑在一起部署，而且uWSGI属于功能齐全且高度定制的WSGI中间件。\n - 在性能上，Gunicorn和uWSGI其实表现相当。\n5. 使用虚拟化技术（Docker）部署测试环境和生产环境\n\n##### 性能测试\n\n1. AB的使用\n2. SQLslap的使用\n3. sysbench的使用\n\n##### 自动化测试\n\n1. 使用Shell和Python进行自动化测试\n2. 使用Selenium实现自动化测试\n - Selenium IDE\n - Selenium WebDriver\n - Selenium Remote Control\n3. 测试工具Robot Framework介绍\n\n#### 第97天：[电商网站技术要点剖析](./Day91-100/97.电商网站技术要点剖析.md)\n\n1. 商业模式和需求要点\n2. 物理模型设计\n3. 第三方登录\n4. 缓存预热和查询缓存\n5. 购物车的实现\n6. 支付功能集成\n7. 秒杀和超卖问题\n8. 静态资源管理\n9. 全文检索方案\n\n#### 第98天：[项目部署上线和性能调优](./Day91-100/98.项目部署上线和性能调优.md)\n\n1. MySQL数据库调优\n2. Web服务器性能优化\n - Nginx负载均衡配置\n - Keepalived实现高可用\n3. 代码性能调优\n - 多线程\n - 异步化\n4. 静态资源访问优化\n - 云存储\n - CDN\n\n#### 第99天：[面试中的公共问题](./Day91-100/99.面试中的公共问题.md)\n\n- 计算机基础\n- Python基础\n- Web框架相关\n- 爬虫相关问题\n- 数据分析\n- 项目相关\n\n#### 第100天：[Python面试题实录](./Day91-100/100.Python面试题实录.md)\n\n"}}},{"rowIdx":157,"cells":{"repo_name":{"kind":"string","value":"ChatterBot"},"repo_commit":{"kind":"string","value":"4ff8af28567ed446ae796d37c246bb6a14032fe7"},"repo_content":{"kind":"string","value":"File: setup.py\n\n#!/usr/bin/env python\n\"\"\"\nChatterBot setup file.\n\"\"\"\nimport os\nimport sys\nimport platform\nimport configparser\nfrom setuptools import setup\n\n\nif sys.version_info[0] < 3:\n raise Exception(\n 'You are tying to install ChatterBot on Python version {}.\\n'\n 'Please install ChatterBot in Python 3 instead.'.format(\n platform.python_version()\n )\n )\n\nconfig = configparser.ConfigParser()\n\ncurrent_directory = os.path.dirname(os.path.abspath(__file__))\nconfig_file_path = os.path.join(current_directory, 'setup.cfg')\n\nconfig.read(config_file_path)\n\nVERSION = config['chatterbot']['version']\nAUTHOR = config['chatterbot']['author']\nAUTHOR_EMAIL = config['chatterbot']['email']\nURL = config['chatterbot']['url']\n\nwith open('README.md') as f:\n LONG_DESCRIPTION = f.read()\n\nREQUIREMENTS = []\nDEPENDENCIES = []\n\nwith open('requirements.txt') as requirements:\n for requirement in requirements.readlines():\n if requirement.startswith('git+git://'):\n DEPENDENCIES.append(requirement)\n else:\n REQUIREMENTS.append(requirement)\n\n\nsetup(\n name='ChatterBot',\n version=VERSION,\n url=URL,\n download_url='{}/tarball/{}'.format(URL, VERSION),\n project_urls={\n 'Documentation': 'https://chatterbot.readthedocs.io',\n },\n description='ChatterBot is a machine learning, conversational dialog engine.',\n long_description=LONG_DESCRIPTION,\n long_description_content_type='text/markdown',\n author=AUTHOR,\n author_email=AUTHOR_EMAIL,\n packages=[\n 'chatterbot',\n 'chatterbot.storage',\n 'chatterbot.logic',\n 'chatterbot.ext',\n 'chatterbot.ext.sqlalchemy_app',\n 'chatterbot.ext.django_chatterbot',\n 'chatterbot.ext.django_chatterbot.migrations',\n ],\n package_dir={'chatterbot': 'chatterbot'},\n include_package_data=True,\n install_requires=REQUIREMENTS,\n dependency_links=DEPENDENCIES,\n python_requires='>=3.4, <=3.8',\n license='BSD',\n zip_safe=True,\n platforms=['any'],\n keywords=['ChatterBot', 'chatbot', 'chat', 'bot'],\n classifiers=[\n 'Development Status :: 4 - Beta',\n 'Intended Audience :: Developers',\n 'License :: OSI Approved :: BSD License',\n 'Environment :: Console',\n 'Environment :: Web Environment',\n 'Operating System :: OS Independent',\n 'Topic :: Software Development :: Libraries :: Python Modules',\n 'Topic :: Communications :: Chat',\n 'Topic :: Internet',\n 'Programming Language :: Python',\n 'Programming Language :: Python :: 3',\n 'Programming Language :: Python :: 3.4',\n 'Programming Language :: Python :: 3.5',\n 'Programming Language :: Python :: 3.6',\n 'Programming Language :: Python :: 3.7',\n 'Programming Language :: Python :: 3.8',\n 'Programming Language :: Python :: 3 :: Only',\n ],\n test_suite='tests'\n)\n\n\n\nFile: runtests.py\n\n#!/usr/bin/env python\n\n\"\"\"\nThis is the test runner for the ChatterBot's Django tests.\n\"\"\"\n\nimport os\nimport sys\n\nimport django\nfrom django.conf import settings\nfrom django.test.utils import get_runner\n\nif __name__ == '__main__':\n os.environ['DJANGO_SETTINGS_MODULE'] = 'tests_django.test_settings'\n django.setup()\n TestRunner = get_runner(settings)\n test_runner = TestRunner(\n verbosity=2\n )\n failures = test_runner.run_tests(['tests_django'])\n sys.exit(bool(failures))\n\n\n\nFile: docs/conf.py\n\nimport os\nimport sys\nimport configparser\nfrom datetime import datetime\nimport sphinx_rtd_theme\n\n\nconfig = configparser.ConfigParser()\n\ncurrent_directory = os.path.dirname(os.path.abspath(__file__))\nparent_directory = os.path.abspath(os.path.join(current_directory, os.pardir))\nconfig_file_path = os.path.join(parent_directory, 'setup.cfg')\n\nconfig.read(config_file_path)\n\n# Insert the project root dir as the first element in the PYTHONPATH.\n# This lets us ensure that the source package is imported, and used to generate the documentation.\nsys.path.insert(0, parent_directory)\n\n\n# Sphinx extension modules\nextensions = [\n 'sphinx.ext.autodoc',\n 'sphinx.ext.autosectionlabel',\n 'sphinx.ext.coverage',\n 'sphinx.ext.doctest',\n 'sphinx.ext.intersphinx',\n 'sphinx.ext.mathjax',\n 'sphinx.ext.todo',\n 'sphinx.ext.viewcode'\n]\n\n# Add any paths that contain templates here, relative to this directory.\ntemplates_path = ['_templates']\n\n# The suffix(es) of source filenames.\n# You can specify multiple suffix as a list of string:\nsource_suffix = ['.rst', '.md']\n\n# The encoding of source files\n# source_encoding = 'utf-8-sig'\n\n# The master toctree document\nmaster_doc = 'index'\n\n# General information about the project\nproject = 'ChatterBot'\nauthor = config['chatterbot']['author']\ncopyright = '{}, {}'.format(\n datetime.now().year,\n author\n)\n\n# The full version, including alpha/beta/rc tags\nrelease = config['chatterbot']['version']\n\n# The short X.Y version\nversion = config['chatterbot']['version'].rsplit('.', 1)[0]\n\nlanguage = 'en'\n\n# List of patterns, relative to source directory, that match files and\n# directories to ignore when looking for source files.\n# This patterns also effect to html_static_path and html_extra_path\nexclude_patterns = []\n\n# If true, '()' will be appended to :func: etc. cross-reference text\n# add_function_parentheses = True\n\n# If true, the current module name will be prepended to all description\n# unit titles (such as .. function::)\n# add_module_names = True\n\n# If true, sectionauthor and moduleauthor directives will be shown in the\n# output. They are ignored by default.\n# show_authors = False\n\n# The name of the Pygments (syntax highlighting) style to use\npygments_style = 'sphinx'\n\n# -- Options for HTML output ----------------------------------------------\n\nhtml_theme = 'sphinx_rtd_theme'\n\nhtml_theme_path = [sphinx_rtd_theme.get_html_theme_path()]\n# Theme options are theme-specific and customize the look and feel of a theme\n# further. For a list of options available for each theme, see the\n# documentation.\nhtml_theme_options = {\n 'logo_only': True\n}\n\nhtml_show_sourcelink = False\n\n# A shorter title for the navigation bar. Default is the same as html_title.\n# html_short_title = None\n\n# The name of an image file (relative to this directory) to place at the top\n# of the sidebar.\nhtml_logo = '../graphics/banner.png'\n\n# The name of an image file (relative to this directory) to use as a favicon of\n# the docs. This file should be a Windows icon file (.ico) being 16x16 or 32x32\n# pixels large.\nhtml_favicon = '_static/favicon.ico'\n\n# Add any paths that contain custom static files (such as style sheets) here,\n# relative to this directory. They are copied after the builtin static files,\n# so a file named \"default.css\" will overwrite the builtin \"default.css\".\nhtml_static_path = ['_static']\n\n# Add any extra paths that contain custom files (such as robots.txt or\n# .htaccess) here, relative to this directory. These files are copied\n# directly to the root of the documentation.\n# html_extra_path = []\n\n# If not None, a 'Last updated on:' timestamp is inserted at every page\n# bottom, using the given strftime format.\n# The empty string is equivalent to '%b %d, %Y'.\n# html_last_updated_fmt = None\n\n# Custom sidebar templates, maps document names to template names.\n# html_sidebars = {}\n\n# Additional templates that should be rendered to pages, maps page names to\n# template names.\n# html_additional_pages = {}\n\n# If false, no module index is generated.\n# html_domain_indices = True\n\n# If false, no index is generated.\n# html_use_index = True\n\n# Split the index into individual pages for each letter.\nhtml_split_index = True\n\n# If true, \"Created using Sphinx\" is shown in the HTML footer. Default is True.\nhtml_show_sphinx = False\n\n# Language to be used for generating the HTML full-text search index.\n# Sphinx supports the following languages:\n# 'da', 'de', 'en', 'es', 'fi', 'fr', 'hu', 'it', 'ja'\n# 'nl', 'no', 'pt', 'ro', 'ru', 'sv', 'tr', 'zh'\nhtml_search_language = 'en'\n\n# Output file base name for HTML help builder\nhtmlhelp_basename = 'ChatterBotdoc'\n\n# Read the docs theme modifications\n\nhtml_context = {\n 'extra_css_files': [\n '_static/style.css'\n ]\n}\n\n# Grouping the document tree into LaTeX files. List of tuples\n# (source start file, target name, title,\n# author, documentclass [howto, manual, or own class])\nlatex_documents = [\n (master_doc, 'ChatterBot.tex', u'ChatterBot Documentation',\n u'Gunther Cox', 'manual'),\n]\n\n# -- Options for manual page output ---------------------------------------\n\n# One entry per manual page. List of tuples\n# (source start file, name, description, authors, manual section)\nman_pages = [\n (master_doc, 'chatterbot', u'ChatterBot Documentation',\n [author], 1)\n]\n\n# -- Options for Texinfo output -------------------------------------------\n\n# Grouping the document tree into Texinfo files. List of tuples\n# (source start file, target name, title, author,\n# dir menu entry, description, category)\ntexinfo_documents = [\n (master_doc, 'ChatterBot', u'ChatterBot Documentation',\n author, 'ChatterBot', 'One line description of project.',\n 'Miscellaneous'),\n]\n\n# -- Options for Epub output ----------------------------------------------\n\n# Bibliographic Dublin Core info\nepub_title = project\nepub_author = author\nepub_publisher = author\nepub_copyright = copyright\n\n# A list of files that should not be packed into the epub file\nepub_exclude_files = ['search.html']\n\n# Configuration for intersphinx\nintersphinx_mapping = {\n 'python': ('https://docs.python.org/3', None)\n}\n\n\n\nFile: chatterbot/response_selection.py\n\n\"\"\"\nResponse selection methods determines which response should be used in\nthe event that multiple responses are generated within a logic adapter.\n\"\"\"\nimport logging\n\n\ndef get_most_frequent_response(input_statement, response_list, storage=None):\n \"\"\"\n :param input_statement: A statement, that closely matches an input to the chat bot.\n :type input_statement: Statement\n\n :param response_list: A list of statement options to choose a response from.\n :type response_list: list\n\n :param storage: An instance of a storage adapter to allow the response selection\n method to access other statements if needed.\n :type storage: StorageAdapter\n\n :return: The response statement with the greatest number of occurrences.\n :rtype: Statement\n \"\"\"\n matching_response = None\n occurrence_count = -1\n\n logger = logging.getLogger(__name__)\n logger.info('Selecting response with greatest number of occurrences.')\n\n for statement in response_list:\n count = len(list(storage.filter(\n text=statement.text,\n in_response_to=input_statement.text)\n ))\n\n # Keep the more common statement\n if count >= occurrence_count:\n matching_response = statement\n occurrence_count = count\n\n # Choose the most commonly occuring matching response\n return matching_response\n\n\ndef get_first_response(input_statement, response_list, storage=None):\n \"\"\"\n :param input_statement: A statement, that closely matches an input to the chat bot.\n :type input_statement: Statement\n\n :param response_list: A list of statement options to choose a response from.\n :type response_list: list\n\n :param storage: An instance of a storage adapter to allow the response selection\n method to access other statements if needed.\n :type storage: StorageAdapter\n\n :return: Return the first statement in the response list.\n :rtype: Statement\n \"\"\"\n logger = logging.getLogger(__name__)\n logger.info('Selecting first response from list of {} options.'.format(\n len(response_list)\n ))\n return response_list[0]\n\n\ndef get_random_response(input_statement, response_list, storage=None):\n \"\"\"\n :param input_statement: A statement, that closely matches an input to the chat bot.\n :type input_statement: Statement\n\n :param response_list: A list of statement options to choose a response from.\n :type response_list: list\n\n :param storage: An instance of a storage adapter to allow the response selection\n method to access other statements if needed.\n :type storage: StorageAdapter\n\n :return: Choose a random response from the selection.\n :rtype: Statement\n \"\"\"\n from random import choice\n logger = logging.getLogger(__name__)\n logger.info('Selecting a response from list of {} options.'.format(\n len(response_list)\n ))\n return choice(response_list)\n\n\n\nFile: chatterbot/parsing.py\n\nimport re\nfrom datetime import timedelta, datetime\nimport calendar\n\n# Variations of dates that the parser can capture\nyear_variations = ['year', 'years', 'yrs']\nday_variations = ['days', 'day']\nminute_variations = ['minute', 'minutes', 'mins']\nhour_variations = ['hrs', 'hours', 'hour']\nweek_variations = ['weeks', 'week', 'wks']\nmonth_variations = ['month', 'months']\n\n# Variables used for RegEx Matching\nday_names = 'monday|tuesday|wednesday|thursday|friday|saturday|sunday'\nmonth_names_long = (\n 'january|february|march|april|may|june|july|august|september|october|november|december'\n)\nmonth_names = month_names_long + '|jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec'\nday_nearest_names = 'today|yesterday|tomorrow|tonight|tonite'\nnumbers = (\n r'(^a(?=\\s)|one|two|three|four|five|six|seven|eight|nine|ten|'\n r'eleven|twelve|thirteen|fourteen|fifteen|sixteen|seventeen|'\n r'eighteen|nineteen|twenty|thirty|forty|fifty|sixty|seventy|'\n r'eighty|ninety|hundred|thousand)'\n)\nre_dmy = '(' + '|'.join(day_variations + minute_variations + year_variations + week_variations + month_variations) + ')'\nre_duration = r'(before|after|earlier|later|ago|from\\snow)'\nre_year = r'(19|20)\\d{2}|^(19|20)\\d{2}'\nre_timeframe = r'this|coming|next|following|previous|last|end\\sof\\sthe'\nre_ordinal = r'st|nd|rd|th|first|second|third|fourth|fourth|' + re_timeframe\nre_time = r'(?P<hour>\\d{1,2})(?=\\s?(\\:\\d|(a|p)m))(\\:(?P<minute>\\d{1,2}))?(\\s?(?P<convention>(am|pm)))?'\nre_separator = r'of|at|on'\n\nNUMBERS = {\n 'zero': 0,\n 'one': 1,\n 'two': 2,\n 'three': 3,\n 'four': 4,\n 'five': 5,\n 'six': 6,\n 'seven': 7,\n 'eight': 8,\n 'nine': 9,\n 'ten': 10,\n 'eleven': 11,\n 'twelve': 12,\n 'thirteen': 13,\n 'fourteen': 14,\n 'fifteen': 15,\n 'sixteen': 16,\n 'seventeen': 17,\n 'eighteen': 18,\n 'nineteen': 19,\n 'twenty': 20,\n 'thirty': 30,\n 'forty': 40,\n 'fifty': 50,\n 'sixty': 60,\n 'seventy': 70,\n 'eighty': 80,\n 'ninety': 90,\n 'hundred': 100,\n 'thousand': 1000,\n 'million': 1000000,\n 'billion': 1000000000,\n 'trillion': 1000000000000,\n}\n\n\n# Mapping of Month name and Value\nHASHMONTHS = {\n 'january': 1,\n 'jan': 1,\n 'february': 2,\n 'feb': 2,\n 'march': 3,\n 'mar': 3,\n 'april': 4,\n 'apr': 4,\n 'may': 5,\n 'june': 6,\n 'jun': 6,\n 'july': 7,\n 'jul': 7,\n 'august': 8,\n 'aug': 8,\n 'september': 9,\n 'sep': 9,\n 'october': 10,\n 'oct': 10,\n 'november': 11,\n 'nov': 11,\n 'december': 12,\n 'dec': 12\n}\n\n# Days to number mapping\nHASHWEEKDAYS = {\n 'monday': 0,\n 'mon': 0,\n 'tuesday': 1,\n 'tue': 1,\n 'wednesday': 2,\n 'wed': 2,\n 'thursday': 3,\n 'thu': 3,\n 'friday': 4,\n 'fri': 4,\n 'saturday': 5,\n 'sat': 5,\n 'sunday': 6,\n 'sun': 6\n}\n\n# Ordinal to number\nHASHORDINALS = {\n 'zeroth': 0,\n 'first': 1,\n 'second': 2,\n 'third': 3,\n 'fourth': 4,\n 'forth': 4,\n 'fifth': 5,\n 'sixth': 6,\n 'seventh': 7,\n 'eighth': 8,\n 'ninth': 9,\n 'tenth': 10,\n 'eleventh': 11,\n 'twelfth': 12,\n 'thirteenth': 13,\n 'fourteenth': 14,\n 'fifteenth': 15,\n 'sixteenth': 16,\n 'seventeenth': 17,\n 'eighteenth': 18,\n 'nineteenth': 19,\n 'twentieth': 20,\n 'last': -1\n}\n\n# A list tuple of regular expressions / parser fn to match\n# Start with the widest match and narrow it down because the order of the match in this list matters\nregex = [\n (\n re.compile(\n r'''\n (\n ((?P<dow>%s)[,\\s]\\s*)? #Matches Monday, 12 Jan 2012, 12 Jan 2012 etc\n (?P<day>\\d{1,2}) # Matches a digit\n (%s)?\n [-\\s] # One or more space\n (?P<month>%s) # Matches any month name\n [-\\s] # Space\n (?P<year>%s) # Year\n ((\\s|,\\s|\\s(%s))?\\s*(%s))?\n )\n ''' % (day_names, re_ordinal, month_names, re_year, re_separator, re_time),\n (re.VERBOSE | re.IGNORECASE)\n ),\n lambda m, base_date: datetime(\n int(m.group('year') if m.group('year') else base_date.year),\n HASHMONTHS[m.group('month').strip().lower()],\n int(m.group('day') if m.group('day') else 1),\n ) + timedelta(**convert_time_to_hour_minute(\n m.group('hour'),\n m.group('minute'),\n m.group('convention')\n ))\n ),\n (\n re.compile(\n r'''\n (\n ((?P<dow>%s)[,\\s][-\\s]*)? #Matches Monday, Jan 12 2012, Jan 12 2012 etc\n (?P<month>%s) # Matches any month name\n [-\\s] # Space\n ((?P<day>\\d{1,2})) # Matches a digit\n (%s)?\n ([-\\s](?P<year>%s))? # Year\n ((\\s|,\\s|\\s(%s))?\\s*(%s))?\n )\n ''' % (day_names, month_names, re_ordinal, re_year, re_separator, re_time),\n (re.VERBOSE | re.IGNORECASE)\n ),\n lambda m, base_date: datetime(\n int(m.group('year') if m.group('year') else base_date.year),\n HASHMONTHS[m.group('month').strip().lower()],\n int(m.group('day') if m.group('day') else 1)\n ) + timedelta(**convert_time_to_hour_minute(\n m.group('hour'),\n m.group('minute'),\n m.group('convention')\n ))\n ),\n (\n re.compile(\n r'''\n (\n (?P<month>%s) # Matches any month name\n [-\\s] # One or more space\n (?P<day>\\d{1,2}) # Matches a digit\n (%s)?\n [-\\s]\\s*?\n (?P<year>%s) # Year\n ((\\s|,\\s|\\s(%s))?\\s*(%s))?\n )\n ''' % (month_names, re_ordinal, re_year, re_separator, re_time),\n (re.VERBOSE | re.IGNORECASE)\n ),\n lambda m, base_date: datetime(\n int(m.group('year') if m.group('year') else base_date.year),\n HASHMONTHS[m.group('month').strip().lower()],\n int(m.group('day') if m.group('day') else 1),\n ) + timedelta(**convert_time_to_hour_minute(\n m.group('hour'),\n m.group('minute'),\n m.group('convention')\n ))\n ),\n (\n re.compile(\n r'''\n (\n ((?P<number>\\d+|(%s[-\\s]?)+)\\s)? # Matches any number or string 25 or twenty five\n (?P<unit>%s)s?\\s # Matches days, months, years, weeks, minutes\n (?P<duration>%s) # before, after, earlier, later, ago, from now\n (\\s*(?P<base_time>(%s)))?\n ((\\s|,\\s|\\s(%s))?\\s*(%s))?\n )\n ''' % (numbers, re_dmy, re_duration, day_nearest_names, re_separator, re_time),\n (re.VERBOSE | re.IGNORECASE)\n ),\n lambda m, base_date: date_from_duration(\n base_date,\n m.group('number'),\n m.group('unit').lower(),\n m.group('duration').lower(),\n m.group('base_time')\n ) + timedelta(**convert_time_to_hour_minute(\n m.group('hour'),\n m.group('minute'),\n m.group('convention')\n ))\n ),\n (\n re.compile(\n r'''\n (\n (?P<ordinal>%s) # First quarter of 2014\n \\s+\n quarter\\sof\n \\s+\n (?P<year>%s)\n )\n ''' % (re_ordinal, re_year),\n (re.VERBOSE | re.IGNORECASE)\n ),\n lambda m, base_date: date_from_quarter(\n base_date,\n HASHORDINALS[m.group('ordinal').lower()],\n int(m.group('year') if m.group('year') else base_date.year)\n )\n ),\n (\n re.compile(\n r'''\n (\n (?P<ordinal_value>\\d+)\n (?P<ordinal>%s) # 1st January 2012\n ((\\s|,\\s|\\s(%s))?\\s*)?\n (?P<month>%s)\n ([,\\s]\\s*(?P<year>%s))?\n )\n ''' % (re_ordinal, re_separator, month_names, re_year),\n (re.VERBOSE | re.IGNORECASE)\n ),\n lambda m, base_date: datetime(\n int(m.group('year') if m.group('year') else base_date.year),\n int(HASHMONTHS[m.group('month').lower()] if m.group('month') else 1),\n int(m.group('ordinal_value') if m.group('ordinal_value') else 1),\n )\n ),\n (\n re.compile(\n r'''\n (\n (?P<month>%s)\n \\s+\n (?P<ordinal_value>\\d+)\n (?P<ordinal>%s) # January 1st 2012\n ([,\\s]\\s*(?P<year>%s))?\n )\n ''' % (month_names, re_ordinal, re_year),\n (re.VERBOSE | re.IGNORECASE)\n ),\n lambda m, base_date: datetime(\n int(m.group('year') if m.group('year') else base_date.year),\n int(HASHMONTHS[m.group('month').lower()] if m.group('month') else 1),\n int(m.group('ordinal_value') if m.group('ordinal_value') else 1),\n )\n ),\n (\n re.compile(\n r'''\n (?P<time>%s) # this, next, following, previous, last\n \\s+\n ((?P<number>\\d+|(%s[-\\s]?)+)\\s)?\n (?P<dmy>%s) # year, day, week, month, night, minute, min\n ((\\s|,\\s|\\s(%s))?\\s*(%s))?\n ''' % (re_timeframe, numbers, re_dmy, re_separator, re_time),\n (re.VERBOSE | re.IGNORECASE),\n ),\n lambda m, base_date: date_from_relative_week_year(\n base_date,\n m.group('time').lower(),\n m.group('dmy').lower(),\n m.group('number')\n ) + timedelta(**convert_time_to_hour_minute(\n m.group('hour'),\n m.group('minute'),\n m.group('convention')\n ))\n ),\n (\n re.compile(\n r'''\n (?P<time>%s) # this, next, following, previous, last\n \\s+\n (?P<dow>%s) # mon - fri\n ((\\s|,\\s|\\s(%s))?\\s*(%s))?\n ''' % (re_timeframe, day_names, re_separator, re_time),\n (re.VERBOSE | re.IGNORECASE),\n ),\n lambda m, base_date: date_from_relative_day(\n base_date,\n m.group('time').lower(),\n m.group('dow')\n ) + timedelta(**convert_time_to_hour_minute(\n m.group('hour'),\n m.group('minute'),\n m.group('convention')\n ))\n ),\n (\n re.compile(\n r'''\n (\n (?P<day>\\d{1,2}) # Day, Month\n (%s)\n [-\\s] # One or more space\n (?P<month>%s)\n )\n ''' % (re_ordinal, month_names),\n (re.VERBOSE | re.IGNORECASE)\n ),\n lambda m, base_date: datetime(\n base_date.year,\n HASHMONTHS[m.group('month').strip().lower()],\n int(m.group('day') if m.group('day') else 1)\n )\n ),\n (\n re.compile(\n r'''\n (\n (?P<month>%s) # Month, day\n [-\\s] # One or more space\n ((?P<day>\\d{1,2})\\b) # Matches a digit January 12\n (%s)?\n )\n ''' % (month_names, re_ordinal),\n (re.VERBOSE | re.IGNORECASE)\n ),\n lambda m, base_date: datetime(\n base_date.year,\n HASHMONTHS[m.group('month').strip().lower()],\n int(m.group('day') if m.group('day') else 1)\n )\n ),\n (\n re.compile(\n r'''\n (\n (?P<month>%s) # Month, year\n [-\\s] # One or more space\n ((?P<year>\\d{1,4})\\b) # Matches a digit January 12\n )\n ''' % (month_names),\n (re.VERBOSE | re.IGNORECASE)\n ),\n lambda m, base_date: datetime(\n int(m.group('year')),\n HASHMONTHS[m.group('month').strip().lower()],\n 1\n )\n ),\n (\n re.compile(\n r'''\n (\n (?P<month>\\d{1,2}) # MM/DD or MM/DD/YYYY\n /\n ((?P<day>\\d{1,2}))\n (/(?P<year>%s))?\n )\n ''' % (re_year),\n (re.VERBOSE | re.IGNORECASE)\n ),\n lambda m, base_date: datetime(\n int(m.group('year') if m.group('year') else base_date.year),\n int(m.group('month').strip()),\n int(m.group('day'))\n )\n ),\n (\n re.compile(\n r'''\n (?P<adverb>%s) # today, yesterday, tomorrow, tonight\n ((\\s|,\\s|\\s(%s))?\\s*(%s))?\n ''' % (day_nearest_names, re_separator, re_time),\n (re.VERBOSE | re.IGNORECASE)\n ),\n lambda m, base_date: date_from_adverb(\n base_date,\n m.group('adverb')\n ) + timedelta(**convert_time_to_hour_minute(\n m.group('hour'),\n m.group('minute'),\n m.group('convention')\n ))\n ),\n (\n re.compile(\n r'''\n (?P<named_day>%s) # Mon - Sun\n ''' % (day_names),\n (re.VERBOSE | re.IGNORECASE)\n ),\n lambda m, base_date: this_week_day(\n base_date,\n HASHWEEKDAYS[m.group('named_day').lower()]\n )\n ),\n (\n re.compile(\n r'''\n (?P<year>%s) # Year\n ''' % (re_year),\n (re.VERBOSE | re.IGNORECASE)\n ),\n lambda m, base_date: datetime(int(m.group('year')), 1, 1)\n ),\n (\n re.compile(\n r'''\n (?P<month>%s) # Month\n ''' % (month_names_long),\n (re.VERBOSE | re.IGNORECASE)\n ),\n lambda m, base_date: datetime(\n base_date.year,\n HASHMONTHS[m.group('month').lower()],\n 1\n )\n ),\n (\n re.compile(\n r'''\n (%s) # Matches time 12:00 am or 12:00 pm\n ''' % (re_time),\n (re.VERBOSE | re.IGNORECASE),\n ),\n lambda m, base_date: datetime(\n base_date.year,\n base_date.month,\n base_date.day\n ) + timedelta(**convert_time_to_hour_minute(\n m.group('hour'),\n m.group('minute'),\n m.group('convention')\n ))\n ),\n (\n re.compile(\n r'''\n (\n (?P<hour>\\d+) # Matches 12 hours, 2 hrs\n \\s+\n (%s)\n )\n ''' % ('|'.join(hour_variations)),\n (re.VERBOSE | re.IGNORECASE),\n ),\n lambda m, base_date: datetime(\n base_date.year,\n base_date.month,\n base_date.day,\n int(m.group('hour'))\n )\n )\n]\n\n\ndef convert_string_to_number(value):\n \"\"\"\n Convert strings to numbers\n \"\"\"\n if value is None:\n return 1\n if isinstance(value, int):\n return value\n if value.isdigit():\n return int(value)\n num_list = map(lambda s: NUMBERS[s], re.findall(numbers + '+', value.lower()))\n return sum(num_list)\n\n\ndef convert_time_to_hour_minute(hour, minute, convention):\n \"\"\"\n Convert time to hour, minute\n \"\"\"\n if hour is None:\n hour = 0\n if minute is None:\n minute = 0\n if convention is None:\n convention = 'am'\n\n hour = int(hour)\n minute = int(minute)\n\n if convention.lower() == 'pm':\n hour += 12\n\n return {'hours': hour, 'minutes': minute}\n\n\ndef date_from_quarter(base_date, ordinal, year):\n \"\"\"\n Extract date from quarter of a year\n \"\"\"\n interval = 3\n month_start = interval * (ordinal - 1)\n if month_start < 0:\n month_start = 9\n month_end = month_start + interval\n if month_start == 0:\n month_start = 1\n return [\n datetime(year, month_start, 1),\n datetime(year, month_end, calendar.monthrange(year, month_end)[1])\n ]\n\n\ndef date_from_relative_day(base_date, time, dow):\n \"\"\"\n Converts relative day to time\n Ex: this tuesday, last tuesday\n \"\"\"\n # Reset date to start of the day\n base_date = datetime(base_date.year, base_date.month, base_date.day)\n time = time.lower()\n dow = dow.lower()\n if time == 'this' or time == 'coming':\n # Else day of week\n num = HASHWEEKDAYS[dow]\n return this_week_day(base_date, num)\n elif time == 'last' or time == 'previous':\n # Else day of week\n num = HASHWEEKDAYS[dow]\n return previous_week_day(base_date, num)\n elif time == 'next' or time == 'following':\n # Else day of week\n num = HASHWEEKDAYS[dow]\n return next_week_day(base_date, num)\n\n\ndef date_from_relative_week_year(base_date, time, dow, ordinal=1):\n \"\"\"\n Converts relative day to time\n Eg. this tuesday, last tuesday\n \"\"\"\n # If there is an ordinal (next 3 weeks) => return a start and end range\n # Reset date to start of the day\n relative_date = datetime(base_date.year, base_date.month, base_date.day)\n ord = convert_string_to_number(ordinal)\n if dow in year_variations:\n if time == 'this' or time == 'coming':\n return datetime(relative_date.year, 1, 1)\n elif time == 'last' or time == 'previous':\n return datetime(relative_date.year - 1, relative_date.month, 1)\n elif time == 'next' or time == 'following':\n return relative_date + timedelta(ord * 365)\n elif time == 'end of the':\n return datetime(relative_date.year, 12, 31)\n elif dow in month_variations:\n if time == 'this':\n return datetime(relative_date.year, relative_date.month, relative_date.day)\n elif time == 'last' or time == 'previous':\n return datetime(relative_date.year, relative_date.month - 1, relative_date.day)\n elif time == 'next' or time == 'following':\n if relative_date.month + ord >= 12:\n month = relative_date.month - 1 + ord\n year = relative_date.year + month // 12\n month = month % 12 + 1\n day = min(relative_date.day, calendar.monthrange(year, month)[1])\n return datetime(year, month, day)\n else:\n return datetime(relative_date.year, relative_date.month + ord, relative_date.day)\n elif time == 'end of the':\n return datetime(\n relative_date.year,\n relative_date.month,\n calendar.monthrange(relative_date.year, relative_date.month)[1]\n )\n elif dow in week_variations:\n if time == 'this':\n return relative_date - timedelta(days=relative_date.weekday())\n elif time == 'last' or time == 'previous':\n return relative_date - timedelta(weeks=1)\n elif time == 'next' or time == 'following':\n return relative_date + timedelta(weeks=ord)\n elif time == 'end of the':\n day_of_week = base_date.weekday()\n return day_of_week + timedelta(days=6 - relative_date.weekday())\n elif dow in day_variations:\n if time == 'this':\n return relative_date\n elif time == 'last' or time == 'previous':\n return relative_date - timedelta(days=1)\n elif time == 'next' or time == 'following':\n return relative_date + timedelta(days=ord)\n elif time == 'end of the':\n return datetime(relative_date.year, relative_date.month, relative_date.day, 23, 59, 59)\n\n\ndef date_from_adverb(base_date, name):\n \"\"\"\n Convert Day adverbs to dates\n Tomorrow => Date\n Today => Date\n \"\"\"\n # Reset date to start of the day\n adverb_date = datetime(base_date.year, base_date.month, base_date.day)\n if name == 'today' or name == 'tonite' or name == 'tonight':\n return adverb_date.today().replace(hour=0, minute=0, second=0, microsecond=0)\n elif name == 'yesterday':\n return adverb_date - timedelta(days=1)\n elif name == 'tomorrow' or name == 'tom':\n return adverb_date + timedelta(days=1)\n\n\ndef date_from_duration(base_date, number_as_string, unit, duration, base_time=None):\n \"\"\"\n Find dates from duration\n Eg: 20 days from now\n Currently does not support strings like \"20 days from last monday\".\n \"\"\"\n # Check if query is `2 days before yesterday` or `day before yesterday`\n if base_time is not None:\n base_date = date_from_adverb(base_date, base_time)\n num = convert_string_to_number(number_as_string)\n if unit in day_variations:\n args = {'days': num}\n elif unit in minute_variations:\n args = {'minutes': num}\n elif unit in week_variations:\n args = {'weeks': num}\n elif unit in month_variations:\n args = {'days': 365 * num / 12}\n elif unit in year_variations:\n args = {'years': num}\n if duration == 'ago' or duration == 'before' or duration == 'earlier':\n if 'years' in args:\n return datetime(base_date.year - args['years'], base_date.month, base_date.day)\n return base_date - timedelta(**args)\n elif duration == 'after' or duration == 'later' or duration == 'from now':\n if 'years' in args:\n return datetime(base_date.year + args['years'], base_date.month, base_date.day)\n return base_date + timedelta(**args)\n\n\ndef this_week_day(base_date, weekday):\n \"\"\"\n Finds coming weekday\n \"\"\"\n day_of_week = base_date.weekday()\n # If today is Tuesday and the query is `this monday`\n # We should output the next_week monday\n if day_of_week > weekday:\n return next_week_day(base_date, weekday)\n start_of_this_week = base_date - timedelta(days=day_of_week + 1)\n day = start_of_this_week + timedelta(days=1)\n while day.weekday() != weekday:\n day = day + timedelta(days=1)\n return day\n\n\ndef previous_week_day(base_date, weekday):\n \"\"\"\n Finds previous weekday\n \"\"\"\n day = base_date - timedelta(days=1)\n while day.weekday() != weekday:\n day = day - timedelta(days=1)\n return day\n\n\ndef next_week_day(base_date, weekday):\n \"\"\"\n Finds next weekday\n \"\"\"\n day_of_week = base_date.weekday()\n end_of_this_week = base_date + timedelta(days=6 - day_of_week)\n day = end_of_this_week + timedelta(days=1)\n while day.weekday() != weekday:\n day = day + timedelta(days=1)\n return day\n\n\ndef datetime_parsing(text, base_date=datetime.now()):\n \"\"\"\n Extract datetime objects from a string of text.\n \"\"\"\n matches = []\n found_array = []\n\n # Find the position in the string\n for expression, function in regex:\n for match in expression.finditer(text):\n matches.append((match.group(), function(match, base_date), match.span()))\n\n # Wrap the matched text with TAG element to prevent nested selections\n for match, value, spans in matches:\n subn = re.subn(\n '(?!<TAG[^>]*?>)' + match + '(?![^<]*?</TAG>)', '<TAG>' + match + '</TAG>', text\n )\n text = subn[0]\n is_substituted = subn[1]\n if is_substituted != 0:\n found_array.append((match, value, spans))\n\n # To preserve order of the match, sort based on the start position\n return sorted(found_array, key=lambda match: match and match[2][0])\n\n\n\nFile: chatterbot/comparisons.py\n\n\"\"\"\nThis module contains various text-comparison algorithms\ndesigned to compare one statement to another.\n\"\"\"\nfrom chatterbot.exceptions import OptionalDependencyImportError\nfrom difflib import SequenceMatcher\n\n\nclass Comparator:\n\n def __init__(self, language):\n\n self.language = language\n\n def __call__(self, statement_a, statement_b):\n return self.compare(statement_a, statement_b)\n\n def compare(self, statement_a, statement_b):\n return 0\n\n\nclass LevenshteinDistance(Comparator):\n \"\"\"\n Compare two statements based on the Levenshtein distance\n of each statement's text.\n\n For example, there is a 65% similarity between the statements\n \"where is the post office?\" and \"looking for the post office\"\n based on the Levenshtein distance algorithm.\n \"\"\"\n\n def compare(self, statement_a, statement_b):\n \"\"\"\n Compare the two input statements.\n\n :return: The percent of similarity between the text of the statements.\n :rtype: float\n \"\"\"\n\n # Return 0 if either statement has a falsy text value\n if not statement_a.text or not statement_b.text:\n return 0\n\n # Get the lowercase version of both strings\n statement_a_text = str(statement_a.text.lower())\n statement_b_text = str(statement_b.text.lower())\n\n similarity = SequenceMatcher(\n None,\n statement_a_text,\n statement_b_text\n )\n\n # Calculate a decimal percent of the similarity\n percent = round(similarity.ratio(), 2)\n\n return percent\n\n\nclass SpacySimilarity(Comparator):\n \"\"\"\n Calculate the similarity of two statements using Spacy models.\n \"\"\"\n\n def __init__(self, language):\n super().__init__(language)\n try:\n import spacy\n except ImportError:\n message = (\n 'Unable to import \"spacy\".\\n'\n 'Please install \"spacy\" before using the SpacySimilarity comparator:\\n'\n 'pip3 install \"spacy>=2.1,<2.2\"'\n )\n raise OptionalDependencyImportError(message)\n\n self.nlp = spacy.load(self.language.ISO_639_1)\n\n def compare(self, statement_a, statement_b):\n \"\"\"\n Compare the two input statements.\n\n :return: The percent of similarity between the closest synset distance.\n :rtype: float\n \"\"\"\n document_a = self.nlp(statement_a.text)\n document_b = self.nlp(statement_b.text)\n\n return document_a.similarity(document_b)\n\n\nclass JaccardSimilarity(Comparator):\n \"\"\"\n Calculates the similarity of two statements based on the Jaccard index.\n\n The Jaccard index is composed of a numerator and denominator.\n In the numerator, we count the number of items that are shared between the sets.\n In the denominator, we count the total number of items across both sets.\n Let's say we define sentences to be equivalent if 50% or more of their tokens are equivalent.\n Here are two sample sentences:\n\n The young cat is hungry.\n The cat is very hungry.\n\n When we parse these sentences to remove stopwords, we end up with the following two sets:\n\n {young, cat, hungry}\n {cat, very, hungry}\n\n In our example above, our intersection is {cat, hungry}, which has count of two.\n The union of the sets is {young, cat, very, hungry}, which has a count of four.\n Therefore, our `Jaccard similarity index`_ is two divided by four, or 50%.\n Given our similarity threshold above, we would consider this to be a match.\n\n .. _`Jaccard similarity index`: https://en.wikipedia.org/wiki/Jaccard_index\n \"\"\"\n\n def __init__(self, language):\n super().__init__(language)\n try:\n import spacy\n except ImportError:\n message = (\n 'Unable to import \"spacy\".\\n'\n 'Please install \"spacy\" before using the JaccardSimilarity comparator:\\n'\n 'pip3 install \"spacy>=2.1,<2.2\"'\n )\n raise OptionalDependencyImportError(message)\n\n self.nlp = spacy.load(self.language.ISO_639_1)\n\n def compare(self, statement_a, statement_b):\n \"\"\"\n Return the calculated similarity of two\n statements based on the Jaccard index.\n \"\"\"\n # Make both strings lowercase\n document_a = self.nlp(statement_a.text.lower())\n document_b = self.nlp(statement_b.text.lower())\n\n statement_a_lemmas = set([\n token.lemma_ for token in document_a if not token.is_stop\n ])\n statement_b_lemmas = set([\n token.lemma_ for token in document_b if not token.is_stop\n ])\n\n # Calculate Jaccard similarity\n numerator = len(statement_a_lemmas.intersection(statement_b_lemmas))\n denominator = float(len(statement_a_lemmas.union(statement_b_lemmas)))\n ratio = numerator / denominator\n\n return ratio\n\n\n\nFile: chatterbot/conversation.py\n\nfrom pytz import UTC\nfrom datetime import datetime\nfrom dateutil import parser as date_parser\n\n\nclass StatementMixin(object):\n \"\"\"\n This class has shared methods used to\n normalize different statement models.\n \"\"\"\n\n statement_field_names = [\n 'id',\n 'text',\n 'search_text',\n 'conversation',\n 'persona',\n 'tags',\n 'in_response_to',\n 'search_in_response_to',\n 'created_at',\n ]\n\n extra_statement_field_names = []\n\n def get_statement_field_names(self):\n \"\"\"\n Return the list of field names for the statement.\n \"\"\"\n return self.statement_field_names + self.extra_statement_field_names\n\n def get_tags(self):\n \"\"\"\n Return the list of tags for this statement.\n \"\"\"\n return self.tags\n\n def add_tags(self, *tags):\n \"\"\"\n Add a list of strings to the statement as tags.\n \"\"\"\n self.tags.extend(tags)\n\n def serialize(self):\n \"\"\"\n :returns: A dictionary representation of the statement object.\n :rtype: dict\n \"\"\"\n data = {}\n\n for field_name in self.get_statement_field_names():\n format_method = getattr(self, 'get_{}'.format(\n field_name\n ), None)\n\n if format_method:\n data[field_name] = format_method()\n else:\n data[field_name] = getattr(self, field_name)\n\n return data\n\n\nclass Statement(StatementMixin):\n \"\"\"\n A statement represents a single spoken entity, sentence or\n phrase that someone can say.\n \"\"\"\n\n __slots__ = (\n 'id',\n 'text',\n 'search_text',\n 'conversation',\n 'persona',\n 'tags',\n 'in_response_to',\n 'search_in_response_to',\n 'created_at',\n 'confidence',\n 'storage',\n )\n\n def __init__(self, text, in_response_to=None, **kwargs):\n\n self.id = kwargs.get('id')\n self.text = str(text)\n self.search_text = kwargs.get('search_text', '')\n self.conversation = kwargs.get('conversation', '')\n self.persona = kwargs.get('persona', '')\n self.tags = kwargs.pop('tags', [])\n self.in_response_to = in_response_to\n self.search_in_response_to = kwargs.get('search_in_response_to', '')\n self.created_at = kwargs.get('created_at', datetime.now())\n\n if not isinstance(self.created_at, datetime):\n self.created_at = date_parser.parse(self.created_at)\n\n # Set timezone to UTC if no timezone was provided\n if not self.created_at.tzinfo:\n self.created_at = self.created_at.replace(tzinfo=UTC)\n\n # This is the confidence with which the chat bot believes\n # this is an accurate response. This value is set when the\n # statement is returned by the chat bot.\n self.confidence = 0\n\n self.storage = None\n\n def __str__(self):\n return self.text\n\n def __repr__(self):\n return '<Statement text:%s>' % (self.text)\n\n def save(self):\n \"\"\"\n Save the statement in the database.\n \"\"\"\n self.storage.update(self)\n\n\n\nFile: chatterbot/constants.py\n\n\"\"\"\nChatterBot constants\n\"\"\"\n\n'''\nThe maximum length of characters that the text of a statement can contain.\nThe number 255 is used because that is the maximum length of a char field\nin most databases. This value should be enforced on a per-model basis by\nthe data model for each storage adapter.\n'''\nSTATEMENT_TEXT_MAX_LENGTH = 255\n\n'''\nThe maximum length of characters that the text label of a conversation can contain.\nThe number 32 was chosen because that is the length of the string representation\nof a UUID4 with no hyphens.\n'''\nCONVERSATION_LABEL_MAX_LENGTH = 32\n\n'''\nThe maximum length of text that can be stored in the persona field of the statement model.\n'''\nPERSONA_MAX_LENGTH = 50\n\n# The maximum length of characters that the name of a tag can contain\nTAG_NAME_MAX_LENGTH = 50\n\nDEFAULT_DJANGO_APP_NAME = 'django_chatterbot'\n\n\n\nFile: chatterbot/__init__.py\n\n\"\"\"\nChatterBot is a machine learning, conversational dialog engine.\n\"\"\"\nfrom .chatterbot import ChatBot\n\n\n__all__ = (\n 'ChatBot',\n)\n\n\n\nFile: chatterbot/chatterbot.py\n\nimport logging\nfrom chatterbot.storage import StorageAdapter\nfrom chatterbot.logic import LogicAdapter\nfrom chatterbot.search import TextSearch, IndexedTextSearch\nfrom chatterbot import utils\n\n\nclass ChatBot(object):\n \"\"\"\n A conversational dialog chat bot.\n \"\"\"\n\n def __init__(self, name, **kwargs):\n self.name = name\n\n storage_adapter = kwargs.get('storage_adapter', 'chatterbot.storage.SQLStorageAdapter')\n\n logic_adapters = kwargs.get('logic_adapters', [\n 'chatterbot.logic.BestMatch'\n ])\n\n # Check that each adapter is a valid subclass of it's respective parent\n utils.validate_adapter_class(storage_adapter, StorageAdapter)\n\n # Logic adapters used by the chat bot\n self.logic_adapters = []\n\n self.storage = utils.initialize_class(storage_adapter, **kwargs)\n\n primary_search_algorithm = IndexedTextSearch(self, **kwargs)\n text_search_algorithm = TextSearch(self, **kwargs)\n\n self.search_algorithms = {\n primary_search_algorithm.name: primary_search_algorithm,\n text_search_algorithm.name: text_search_algorithm\n }\n\n for adapter in logic_adapters:\n utils.validate_adapter_class(adapter, LogicAdapter)\n logic_adapter = utils.initialize_class(adapter, self, **kwargs)\n self.logic_adapters.append(logic_adapter)\n\n preprocessors = kwargs.get(\n 'preprocessors', [\n 'chatterbot.preprocessors.clean_whitespace'\n ]\n )\n\n self.preprocessors = []\n\n for preprocessor in preprocessors:\n self.preprocessors.append(utils.import_module(preprocessor))\n\n self.logger = kwargs.get('logger', logging.getLogger(__name__))\n\n # Allow the bot to save input it receives so that it can learn\n self.read_only = kwargs.get('read_only', False)\n\n def get_response(self, statement=None, **kwargs):\n \"\"\"\n Return the bot's response based on the input.\n\n :param statement: An statement object or string.\n :returns: A response to the input.\n :rtype: Statement\n\n :param additional_response_selection_parameters: Parameters to pass to the\n chat bot's logic adapters to control response selection.\n :type additional_response_selection_parameters: dict\n\n :param persist_values_to_response: Values that should be saved to the response\n that the chat bot generates.\n :type persist_values_to_response: dict\n \"\"\"\n Statement = self.storage.get_object('statement')\n\n additional_response_selection_parameters = kwargs.pop('additional_response_selection_parameters', {})\n\n persist_values_to_response = kwargs.pop('persist_values_to_response', {})\n\n if isinstance(statement, str):\n kwargs['text'] = statement\n\n if isinstance(statement, dict):\n kwargs.update(statement)\n\n if statement is None and 'text' not in kwargs:\n raise self.ChatBotException(\n 'Either a statement object or a \"text\" keyword '\n 'argument is required. Neither was provided.'\n )\n\n if hasattr(statement, 'serialize'):\n kwargs.update(**statement.serialize())\n\n tags = kwargs.pop('tags', [])\n\n text = kwargs.pop('text')\n\n input_statement = Statement(text=text, **kwargs)\n\n input_statement.add_tags(*tags)\n\n # Preprocess the input statement\n for preprocessor in self.preprocessors:\n input_statement = preprocessor(input_statement)\n\n # Make sure the input statement has its search text saved\n\n if not input_statement.search_text:\n input_statement.search_text = self.storage.tagger.get_text_index_string(input_statement.text)\n\n if not input_statement.search_in_response_to and input_statement.in_response_to:\n input_statement.search_in_response_to = self.storage.tagger.get_text_index_string(input_statement.in_response_to)\n\n response = self.generate_response(input_statement, additional_response_selection_parameters)\n\n # Update any response data that needs to be changed\n if persist_values_to_response:\n for response_key in persist_values_to_response:\n response_value = persist_values_to_response[response_key]\n if response_key == 'tags':\n input_statement.add_tags(*response_value)\n response.add_tags(*response_value)\n else:\n setattr(input_statement, response_key, response_value)\n setattr(response, response_key, response_value)\n\n if not self.read_only:\n self.learn_response(input_statement)\n\n # Save the response generated for the input\n self.storage.create(**response.serialize())\n\n return response\n\n def generate_response(self, input_statement, additional_response_selection_parameters=None):\n \"\"\"\n Return a response based on a given input statement.\n\n :param input_statement: The input statement to be processed.\n \"\"\"\n Statement = self.storage.get_object('statement')\n\n results = []\n result = None\n max_confidence = -1\n\n for adapter in self.logic_adapters:\n if adapter.can_process(input_statement):\n\n output = adapter.process(input_statement, additional_response_selection_parameters)\n results.append(output)\n\n self.logger.info(\n '{} selected \"{}\" as a response with a confidence of {}'.format(\n adapter.class_name, output.text, output.confidence\n )\n )\n\n if output.confidence > max_confidence:\n result = output\n max_confidence = output.confidence\n else:\n self.logger.info(\n 'Not processing the statement using {}'.format(adapter.class_name)\n )\n\n class ResultOption:\n def __init__(self, statement, count=1):\n self.statement = statement\n self.count = count\n\n # If multiple adapters agree on the same statement,\n # then that statement is more likely to be the correct response\n if len(results) >= 3:\n result_options = {}\n for result_option in results:\n result_string = result_option.text + ':' + (result_option.in_response_to or '')\n\n if result_string in result_options:\n result_options[result_string].count += 1\n if result_options[result_string].statement.confidence < result_option.confidence:\n result_options[result_string].statement = result_option\n else:\n result_options[result_string] = ResultOption(\n result_option\n )\n\n most_common = list(result_options.values())[0]\n\n for result_option in result_options.values():\n if result_option.count > most_common.count:\n most_common = result_option\n\n if most_common.count > 1:\n result = most_common.statement\n\n response = Statement(\n text=result.text,\n in_response_to=input_statement.text,\n conversation=input_statement.conversation,\n persona='bot:' + self.name\n )\n\n response.confidence = result.confidence\n\n return response\n\n def learn_response(self, statement, previous_statement=None):\n \"\"\"\n Learn that the statement provided is a valid response.\n \"\"\"\n if not previous_statement:\n previous_statement = statement.in_response_to\n\n if not previous_statement:\n previous_statement = self.get_latest_response(statement.conversation)\n if previous_statement:\n previous_statement = previous_statement.text\n\n previous_statement_text = previous_statement\n\n if not isinstance(previous_statement, (str, type(None), )):\n statement.in_response_to = previous_statement.text\n elif isinstance(previous_statement, str):\n statement.in_response_to = previous_statement\n\n self.logger.info('Adding \"{}\" as a response to \"{}\"'.format(\n statement.text,\n previous_statement_text\n ))\n\n # Save the input statement\n return self.storage.create(**statement.serialize())\n\n def get_latest_response(self, conversation):\n \"\"\"\n Returns the latest response in a conversation if it exists.\n Returns None if a matching conversation cannot be found.\n \"\"\"\n from chatterbot.conversation import Statement as StatementObject\n\n conversation_statements = list(self.storage.filter(\n conversation=conversation,\n order_by=['id']\n ))\n\n # Get the most recent statement in the conversation if one exists\n latest_statement = conversation_statements[-1] if conversation_statements else None\n\n if latest_statement:\n if latest_statement.in_response_to:\n\n response_statements = list(self.storage.filter(\n conversation=conversation,\n text=latest_statement.in_response_to,\n order_by=['id']\n ))\n\n if response_statements:\n return response_statements[-1]\n else:\n return StatementObject(\n text=latest_statement.in_response_to,\n conversation=conversation\n )\n else:\n # The case that the latest statement is not in response to another statement\n return latest_statement\n\n return None\n\n class ChatBotException(Exception):\n pass\n\n\n\nFile: chatterbot/utils.py\n\n\"\"\"\nChatterBot utility functions\n\"\"\"\n\n\ndef import_module(dotted_path):\n \"\"\"\n Imports the specified module based on the\n dot notated import path for the module.\n \"\"\"\n import importlib\n\n module_parts = dotted_path.split('.')\n module_path = '.'.join(module_parts[:-1])\n module = importlib.import_module(module_path)\n\n return getattr(module, module_parts[-1])\n\n\ndef initialize_class(data, *args, **kwargs):\n \"\"\"\n :param data: A string or dictionary containing a import_path attribute.\n \"\"\"\n if isinstance(data, dict):\n import_path = data.get('import_path')\n data.update(kwargs)\n Class = import_module(import_path)\n\n return Class(*args, **data)\n else:\n Class = import_module(data)\n\n return Class(*args, **kwargs)\n\n\ndef validate_adapter_class(validate_class, adapter_class):\n \"\"\"\n Raises an exception if validate_class is not a\n subclass of adapter_class.\n\n :param validate_class: The class to be validated.\n :type validate_class: class\n\n :param adapter_class: The class type to check against.\n :type adapter_class: class\n\n :raises: Adapter.InvalidAdapterTypeException\n \"\"\"\n from chatterbot.adapters import Adapter\n\n # If a dictionary was passed in, check if it has an import_path attribute\n if isinstance(validate_class, dict):\n\n if 'import_path' not in validate_class:\n raise Adapter.InvalidAdapterTypeException(\n 'The dictionary {} must contain a value for \"import_path\"'.format(\n str(validate_class)\n )\n )\n\n # Set the class to the import path for the next check\n validate_class = validate_class.get('import_path')\n\n if not issubclass(import_module(validate_class), adapter_class):\n raise Adapter.InvalidAdapterTypeException(\n '{} must be a subclass of {}'.format(\n validate_class,\n adapter_class.__name__\n )\n )\n\n\ndef get_response_time(chatbot, statement='Hello'):\n \"\"\"\n Returns the amount of time taken for a given\n chat bot to return a response.\n\n :param chatbot: A chat bot instance.\n :type chatbot: ChatBot\n\n :returns: The response time in seconds.\n :rtype: float\n \"\"\"\n import time\n\n start_time = time.time()\n\n chatbot.get_response(statement)\n\n return time.time() - start_time\n\n\ndef print_progress_bar(description, iteration_counter, total_items, progress_bar_length=20):\n \"\"\"\n Print progress bar\n :param description: Training description\n :type description: str\n\n :param iteration_counter: Incremental counter\n :type iteration_counter: int\n\n :param total_items: total number items\n :type total_items: int\n\n :param progress_bar_length: Progress bar length\n :type progress_bar_length: int\n\n :returns: void\n :rtype: void\n \"\"\"\n import sys\n\n percent = float(iteration_counter) / total_items\n hashes = '#' * int(round(percent * progress_bar_length))\n spaces = ' ' * (progress_bar_length - len(hashes))\n sys.stdout.write('\\r{0}: [{1}] {2}%'.format(description, hashes + spaces, int(round(percent * 100))))\n sys.stdout.flush()\n if total_items == iteration_counter:\n print('\\r')\n\n\n\nFile: chatterbot/preprocessors.py\n\n\"\"\"\nStatement pre-processors.\n\"\"\"\n\n\ndef clean_whitespace(statement):\n \"\"\"\n Remove any consecutive whitespace characters from the statement text.\n \"\"\"\n import re\n\n # Replace linebreaks and tabs with spaces\n statement.text = statement.text.replace('\\n', ' ').replace('\\r', ' ').replace('\\t', ' ')\n\n # Remove any leeding or trailing whitespace\n statement.text = statement.text.strip()\n\n # Remove consecutive spaces\n statement.text = re.sub(' +', ' ', statement.text)\n\n return statement\n\n\ndef unescape_html(statement):\n \"\"\"\n Convert escaped html characters into unescaped html characters.\n For example: \"<b>\" becomes \"<b>\".\n \"\"\"\n import html\n\n statement.text = html.unescape(statement.text)\n\n return statement\n\n\ndef convert_to_ascii(statement):\n \"\"\"\n Converts unicode characters to ASCII character equivalents.\n For example: \"på fédéral\" becomes \"pa federal\".\n \"\"\"\n import unicodedata\n\n text = unicodedata.normalize('NFKD', statement.text)\n text = text.encode('ascii', 'ignore').decode('utf-8')\n\n statement.text = str(text)\n return statement\n\n\n\nFile: chatterbot/trainers.py\n\nimport os\nimport sys\nimport csv\nimport time\nfrom dateutil import parser as date_parser\nfrom chatterbot.conversation import Statement\nfrom chatterbot.tagging import PosLemmaTagger\nfrom chatterbot import utils\n\n\nclass Trainer(object):\n \"\"\"\n Base class for all other trainer classes.\n\n :param boolean show_training_progress: Show progress indicators for the\n trainer. The environment variable ``CHATTERBOT_SHOW_TRAINING_PROGRESS``\n can also be set to control this. ``show_training_progress`` will override\n the environment variable if it is set.\n \"\"\"\n\n def __init__(self, chatbot, **kwargs):\n self.chatbot = chatbot\n\n environment_default = os.getenv('CHATTERBOT_SHOW_TRAINING_PROGRESS', True)\n self.show_training_progress = kwargs.get(\n 'show_training_progress',\n environment_default\n )\n\n def get_preprocessed_statement(self, input_statement):\n \"\"\"\n Preprocess the input statement.\n \"\"\"\n for preprocessor in self.chatbot.preprocessors:\n input_statement = preprocessor(input_statement)\n\n return input_statement\n\n def train(self, *args, **kwargs):\n \"\"\"\n This method must be overridden by a child class.\n \"\"\"\n raise self.TrainerInitializationException()\n\n class TrainerInitializationException(Exception):\n \"\"\"\n Exception raised when a base class has not overridden\n the required methods on the Trainer base class.\n \"\"\"\n\n def __init__(self, message=None):\n default = (\n 'A training class must be specified before calling train(). '\n 'See http://chatterbot.readthedocs.io/en/stable/training.html'\n )\n super().__init__(message or default)\n\n def _generate_export_data(self):\n result = []\n for statement in self.chatbot.storage.filter():\n if statement.in_response_to:\n result.append([statement.in_response_to, statement.text])\n\n return result\n\n def export_for_training(self, file_path='./export.json'):\n \"\"\"\n Create a file from the database that can be used to\n train other chat bots.\n \"\"\"\n import json\n export = {'conversations': self._generate_export_data()}\n with open(file_path, 'w+', encoding='utf8') as jsonfile:\n json.dump(export, jsonfile, ensure_ascii=False)\n\n\nclass ListTrainer(Trainer):\n \"\"\"\n Allows a chat bot to be trained using a list of strings\n where the list represents a conversation.\n \"\"\"\n\n def train(self, conversation):\n \"\"\"\n Train the chat bot based on the provided list of\n statements that represents a single conversation.\n \"\"\"\n previous_statement_text = None\n previous_statement_search_text = ''\n\n statements_to_create = []\n\n for conversation_count, text in enumerate(conversation):\n if self.show_training_progress:\n utils.print_progress_bar(\n 'List Trainer',\n conversation_count + 1, len(conversation)\n )\n\n statement_search_text = self.chatbot.storage.tagger.get_text_index_string(text)\n\n statement = self.get_preprocessed_statement(\n Statement(\n text=text,\n search_text=statement_search_text,\n in_response_to=previous_statement_text,\n search_in_response_to=previous_statement_search_text,\n conversation='training'\n )\n )\n\n previous_statement_text = statement.text\n previous_statement_search_text = statement_search_text\n\n statements_to_create.append(statement)\n\n self.chatbot.storage.create_many(statements_to_create)\n\n\nclass ChatterBotCorpusTrainer(Trainer):\n \"\"\"\n Allows the chat bot to be trained using data from the\n ChatterBot dialog corpus.\n \"\"\"\n\n def train(self, *corpus_paths):\n from chatterbot.corpus import load_corpus, list_corpus_files\n\n data_file_paths = []\n\n # Get the paths to each file the bot will be trained with\n for corpus_path in corpus_paths:\n data_file_paths.extend(list_corpus_files(corpus_path))\n\n for corpus, categories, file_path in load_corpus(*data_file_paths):\n\n statements_to_create = []\n\n # Train the chat bot with each statement and response pair\n for conversation_count, conversation in enumerate(corpus):\n\n if self.show_training_progress:\n utils.print_progress_bar(\n 'Training ' + str(os.path.basename(file_path)),\n conversation_count + 1,\n len(corpus)\n )\n\n previous_statement_text = None\n previous_statement_search_text = ''\n\n for text in conversation:\n\n statement_search_text = self.chatbot.storage.tagger.get_text_index_string(text)\n\n statement = Statement(\n text=text,\n search_text=statement_search_text,\n in_response_to=previous_statement_text,\n search_in_response_to=previous_statement_search_text,\n conversation='training'\n )\n\n statement.add_tags(*categories)\n\n statement = self.get_preprocessed_statement(statement)\n\n previous_statement_text = statement.text\n previous_statement_search_text = statement_search_text\n\n statements_to_create.append(statement)\n\n if statements_to_create:\n self.chatbot.storage.create_many(statements_to_create)\n\n\nclass UbuntuCorpusTrainer(Trainer):\n \"\"\"\n Allow chatbots to be trained with the data from the Ubuntu Dialog Corpus.\n \"\"\"\n\n def __init__(self, chatbot, **kwargs):\n super().__init__(chatbot, **kwargs)\n home_directory = os.path.expanduser('~')\n\n self.data_download_url = kwargs.get(\n 'ubuntu_corpus_data_download_url',\n 'http://cs.mcgill.ca/~jpineau/datasets/ubuntu-corpus-1.0/ubuntu_dialogs.tgz'\n )\n\n self.data_directory = kwargs.get(\n 'ubuntu_corpus_data_directory',\n os.path.join(home_directory, 'ubuntu_data')\n )\n\n self.extracted_data_directory = os.path.join(\n self.data_directory, 'ubuntu_dialogs'\n )\n\n # Create the data directory if it does not already exist\n if not os.path.exists(self.data_directory):\n os.makedirs(self.data_directory)\n\n def is_downloaded(self, file_path):\n \"\"\"\n Check if the data file is already downloaded.\n \"\"\"\n if os.path.exists(file_path):\n self.chatbot.logger.info('File is already downloaded')\n return True\n\n return False\n\n def is_extracted(self, file_path):\n \"\"\"\n Check if the data file is already extracted.\n \"\"\"\n\n if os.path.isdir(file_path):\n self.chatbot.logger.info('File is already extracted')\n return True\n return False\n\n def download(self, url, show_status=True):\n \"\"\"\n Download a file from the given url.\n Show a progress indicator for the download status.\n Based on: http://stackoverflow.com/a/15645088/1547223\n \"\"\"\n import requests\n\n file_name = url.split('/')[-1]\n file_path = os.path.join(self.data_directory, file_name)\n\n # Do not download the data if it already exists\n if self.is_downloaded(file_path):\n return file_path\n\n with open(file_path, 'wb') as open_file:\n print('Downloading %s' % url)\n response = requests.get(url, stream=True)\n total_length = response.headers.get('content-length')\n\n if total_length is None:\n # No content length header\n open_file.write(response.content)\n else:\n download = 0\n total_length = int(total_length)\n for data in response.iter_content(chunk_size=4096):\n download += len(data)\n open_file.write(data)\n if show_status:\n done = int(50 * download / total_length)\n sys.stdout.write('\\r[%s%s]' % ('=' * done, ' ' * (50 - done)))\n sys.stdout.flush()\n\n # Add a new line after the download bar\n sys.stdout.write('\\n')\n\n print('Download location: %s' % file_path)\n return file_path\n\n def extract(self, file_path):\n \"\"\"\n Extract a tar file at the specified file path.\n \"\"\"\n import tarfile\n\n print('Extracting {}'.format(file_path))\n\n if not os.path.exists(self.extracted_data_directory):\n os.makedirs(self.extracted_data_directory)\n\n def track_progress(members):\n sys.stdout.write('.')\n for member in members:\n # This will be the current file being extracted\n yield member\n\n with tarfile.open(file_path) as tar:\n tar.extractall(path=self.extracted_data_directory, members=track_progress(tar))\n\n self.chatbot.logger.info('File extracted to {}'.format(self.extracted_data_directory))\n\n return True\n\n def train(self):\n import glob\n\n tagger = PosLemmaTagger(language=self.chatbot.storage.tagger.language)\n\n # Download and extract the Ubuntu dialog corpus if needed\n corpus_download_path = self.download(self.data_download_url)\n\n # Extract if the directory does not already exist\n if not self.is_extracted(self.extracted_data_directory):\n self.extract(corpus_download_path)\n\n extracted_corpus_path = os.path.join(\n self.extracted_data_directory,\n '**', '**', '*.tsv'\n )\n\n def chunks(items, items_per_chunk):\n for start_index in range(0, len(items), items_per_chunk):\n end_index = start_index + items_per_chunk\n yield items[start_index:end_index]\n\n file_list = glob.glob(extracted_corpus_path)\n\n file_groups = tuple(chunks(file_list, 10000))\n\n start_time = time.time()\n\n for tsv_files in file_groups:\n\n statements_from_file = []\n\n for tsv_file in tsv_files:\n with open(tsv_file, 'r', encoding='utf-8') as tsv:\n reader = csv.reader(tsv, delimiter='\\t')\n\n previous_statement_text = None\n previous_statement_search_text = ''\n\n for row in reader:\n if len(row) > 0:\n statement = Statement(\n text=row[3],\n in_response_to=previous_statement_text,\n conversation='training',\n created_at=date_parser.parse(row[0]),\n persona=row[1]\n )\n\n for preprocessor in self.chatbot.preprocessors:\n statement = preprocessor(statement)\n\n statement.search_text = tagger.get_text_index_string(statement.text)\n statement.search_in_response_to = previous_statement_search_text\n\n previous_statement_text = statement.text\n previous_statement_search_text = statement.search_text\n\n statements_from_file.append(statement)\n\n self.chatbot.storage.create_many(statements_from_file)\n\n print('Training took', time.time() - start_time, 'seconds.')\n\n\n\nFile: chatterbot/search.py\n\nclass IndexedTextSearch:\n \"\"\"\n :param statement_comparison_function: A comparison class.\n Defaults to ``LevenshteinDistance``.\n\n :param search_page_size:\n The maximum number of records to load into memory at a time when searching.\n Defaults to 1000\n \"\"\"\n\n name = 'indexed_text_search'\n\n def __init__(self, chatbot, **kwargs):\n from chatterbot.comparisons import LevenshteinDistance\n\n self.chatbot = chatbot\n\n statement_comparison_function = kwargs.get(\n 'statement_comparison_function',\n LevenshteinDistance\n )\n\n self.compare_statements = statement_comparison_function(\n language=self.chatbot.storage.tagger.language\n )\n\n self.search_page_size = kwargs.get(\n 'search_page_size', 1000\n )\n\n def search(self, input_statement, **additional_parameters):\n \"\"\"\n Search for close matches to the input. Confidence scores for\n subsequent results will order of increasing value.\n\n :param input_statement: A statement.\n :type input_statement: chatterbot.conversation.Statement\n\n :param **additional_parameters: Additional parameters to be passed\n to the ``filter`` method of the storage adapter when searching.\n\n :rtype: Generator yielding one closest matching statement at a time.\n \"\"\"\n self.chatbot.logger.info('Beginning search for close text match')\n\n input_search_text = input_statement.search_text\n\n if not input_statement.search_text:\n self.chatbot.logger.warn(\n 'No value for search_text was available on the provided input'\n )\n\n input_search_text = self.chatbot.storage.tagger.get_text_index_string(\n input_statement.text\n )\n\n search_parameters = {\n 'search_text_contains': input_search_text,\n 'persona_not_startswith': 'bot:',\n 'page_size': self.search_page_size\n }\n\n if additional_parameters:\n search_parameters.update(additional_parameters)\n\n statement_list = self.chatbot.storage.filter(**search_parameters)\n\n best_confidence_so_far = 0\n\n self.chatbot.logger.info('Processing search results')\n\n # Find the closest matching known statement\n for statement in statement_list:\n confidence = self.compare_statements(input_statement, statement)\n\n if confidence > best_confidence_so_far:\n best_confidence_so_far = confidence\n statement.confidence = confidence\n\n self.chatbot.logger.info('Similar text found: {} {}'.format(\n statement.text, confidence\n ))\n\n yield statement\n\n\nclass TextSearch:\n \"\"\"\n :param statement_comparison_function: A comparison class.\n Defaults to ``LevenshteinDistance``.\n\n :param search_page_size:\n The maximum number of records to load into memory at a time when searching.\n Defaults to 1000\n \"\"\"\n\n name = 'text_search'\n\n def __init__(self, chatbot, **kwargs):\n from chatterbot.comparisons import LevenshteinDistance\n\n self.chatbot = chatbot\n\n statement_comparison_function = kwargs.get(\n 'statement_comparison_function',\n LevenshteinDistance\n )\n\n self.compare_statements = statement_comparison_function(\n language=self.chatbot.storage.tagger.language\n )\n\n self.search_page_size = kwargs.get(\n 'search_page_size', 1000\n )\n\n def search(self, input_statement, **additional_parameters):\n \"\"\"\n Search for close matches to the input. Confidence scores for\n subsequent results will order of increasing value.\n\n :param input_statement: A statement.\n :type input_statement: chatterbot.conversation.Statement\n\n :param **additional_parameters: Additional parameters to be passed\n to the ``filter`` method of the storage adapter when searching.\n\n :rtype: Generator yielding one closest matching statement at a time.\n \"\"\"\n self.chatbot.logger.info('Beginning search for close text match')\n\n search_parameters = {\n 'persona_not_startswith': 'bot:',\n 'page_size': self.search_page_size\n }\n\n if additional_parameters:\n search_parameters.update(additional_parameters)\n\n statement_list = self.chatbot.storage.filter(**search_parameters)\n\n best_confidence_so_far = 0\n\n self.chatbot.logger.info('Processing search results')\n\n # Find the closest matching known statement\n for statement in statement_list:\n confidence = self.compare_statements(input_statement, statement)\n\n if confidence > best_confidence_so_far:\n best_confidence_so_far = confidence\n statement.confidence = confidence\n\n self.chatbot.logger.info('Similar text found: {} {}'.format(\n statement.text, confidence\n ))\n\n yield statement\n\n\n\nFile: chatterbot/exceptions.py\n\nclass OptionalDependencyImportError(ImportError):\n \"\"\"\n An exception raised when a feature requires an optional dependency to be installed.\n \"\"\"\n pass\n\n\n\nFile: chatterbot/tagging.py\n\nimport string\nfrom chatterbot import languages\n\n\nclass LowercaseTagger(object):\n \"\"\"\n Returns the text in lowercase.\n \"\"\"\n\n def __init__(self, language=None):\n self.language = language or languages.ENG\n\n def get_text_index_string(self, text):\n return text.lower()\n\n\nclass PosLemmaTagger(object):\n\n def __init__(self, language=None):\n import spacy\n\n self.language = language or languages.ENG\n\n self.punctuation_table = str.maketrans(dict.fromkeys(string.punctuation))\n\n self.nlp = spacy.load(self.language.ISO_639_1.lower())\n\n def get_text_index_string(self, text):\n \"\"\"\n Return a string of text containing part-of-speech, lemma pairs.\n \"\"\"\n bigram_pairs = []\n\n if len(text) <= 2:\n text_without_punctuation = text.translate(self.punctuation_table)\n if len(text_without_punctuation) >= 1:\n text = text_without_punctuation\n\n document = self.nlp(text)\n\n if len(text) <= 2:\n bigram_pairs = [\n token.lemma_.lower() for token in document\n ]\n else:\n tokens = [\n token for token in document if token.is_alpha and not token.is_stop\n ]\n\n if len(tokens) < 2:\n tokens = [\n token for token in document if token.is_alpha\n ]\n\n for index in range(1, len(tokens)):\n bigram_pairs.append('{}:{}'.format(\n tokens[index - 1].pos_,\n tokens[index].lemma_.lower()\n ))\n\n if not bigram_pairs:\n bigram_pairs = [\n token.lemma_.lower() for token in document\n ]\n\n return ' '.join(bigram_pairs)\n\n\n\nFile: chatterbot/languages.py\n\nclass AAR:\n ISO_639_1 = ''\n ISO_639 = 'aar'\n ENGLISH_NAME = 'Afar'\n\n\nclass ABK:\n ISO_639_1 = ''\n ISO_639 = 'abk'\n ENGLISH_NAME = 'Abkhazian'\n\n\nclass ACE:\n ISO_639_1 = ''\n ISO_639 = 'ace'\n ENGLISH_NAME = 'Achinese'\n\n\nclass ACH:\n ISO_639_1 = ''\n ISO_639 = 'ach'\n ENGLISH_NAME = 'Acoli'\n\n\nclass ADA:\n ISO_639_1 = ''\n ISO_639 = 'ada'\n ENGLISH_NAME = 'Adangme'\n\n\nclass ADY:\n ISO_639_1 = ''\n ISO_639 = 'ady'\n ENGLISH_NAME = 'Adyghe'\n\n\nclass AFH:\n ISO_639_1 = ''\n ISO_639 = 'afh'\n ENGLISH_NAME = 'Afrihili'\n\n\nclass AFR:\n ISO_639_1 = ''\n ISO_639 = 'afr'\n ENGLISH_NAME = 'Afrikaans'\n\n\nclass AIN:\n ISO_639_1 = ''\n ISO_639 = 'ain'\n ENGLISH_NAME = 'Ainu'\n\n\nclass AKA:\n ISO_639_1 = ''\n ISO_639 = 'aka'\n ENGLISH_NAME = 'Akan'\n\n\nclass AKK:\n ISO_639_1 = ''\n ISO_639 = 'akk'\n ENGLISH_NAME = 'Akkadian'\n\n\nclass ALB:\n ISO_639_1 = ''\n ISO_639 = 'alb'\n ENGLISH_NAME = 'Albanian'\n\n\nclass ALE:\n ISO_639_1 = ''\n ISO_639 = 'ale'\n ENGLISH_NAME = 'Aleut'\n\n\nclass ALT:\n ISO_639_1 = ''\n ISO_639 = 'alt'\n ENGLISH_NAME = 'SouthernAltai'\n\n\nclass AMH:\n ISO_639_1 = ''\n ISO_639 = 'amh'\n ENGLISH_NAME = 'Amharic'\n\n\nclass ANP:\n ISO_639_1 = ''\n ISO_639 = 'anp'\n ENGLISH_NAME = 'Angika'\n\n\nclass ARA:\n ISO_639_1 = ''\n ISO_639 = 'ara'\n ENGLISH_NAME = 'Arabic'\n\n\nclass ARG:\n ISO_639_1 = ''\n ISO_639 = 'arg'\n ENGLISH_NAME = 'Aragonese'\n\n\nclass ARM:\n ISO_639_1 = ''\n ISO_639 = 'arm'\n ENGLISH_NAME = 'Armenian'\n\n\nclass ARN:\n ISO_639_1 = ''\n ISO_639 = 'arn'\n ENGLISH_NAME = 'Mapudungun'\n\n\nclass ARP:\n ISO_639_1 = ''\n ISO_639 = 'arp'\n ENGLISH_NAME = 'Arapaho'\n\n\nclass ARW:\n ISO_639_1 = ''\n ISO_639 = 'arw'\n ENGLISH_NAME = 'Arawak'\n\n\nclass ASM:\n ISO_639_1 = ''\n ISO_639 = 'asm'\n ENGLISH_NAME = 'Assamese'\n\n\nclass AST:\n ISO_639_1 = ''\n ISO_639 = 'ast'\n ENGLISH_NAME = 'Asturian'\n\n\nclass AVA:\n ISO_639_1 = ''\n ISO_639 = 'ava'\n ENGLISH_NAME = 'Avaric'\n\n\nclass AVE:\n ISO_639_1 = ''\n ISO_639 = 'ave'\n ENGLISH_NAME = 'Avestan'\n\n\nclass AWA:\n ISO_639_1 = ''\n ISO_639 = 'awa'\n ENGLISH_NAME = 'Awadhi'\n\n\nclass AYM:\n ISO_639_1 = ''\n ISO_639 = 'aym'\n ENGLISH_NAME = 'Aymara'\n\n\nclass AZE:\n ISO_639_1 = ''\n ISO_639 = 'aze'\n ENGLISH_NAME = 'Azerbaijani'\n\n\nclass BAK:\n ISO_639_1 = ''\n ISO_639 = 'bak'\n ENGLISH_NAME = 'Bashkir'\n\n\nclass BAL:\n ISO_639_1 = ''\n ISO_639 = 'bal'\n ENGLISH_NAME = 'Baluchi'\n\n\nclass BAM:\n ISO_639_1 = ''\n ISO_639 = 'bam'\n ENGLISH_NAME = 'Bambara'\n\n\nclass BAN:\n ISO_639_1 = ''\n ISO_639 = 'ban'\n ENGLISH_NAME = 'Balinese'\n\n\nclass BAQ:\n ISO_639_1 = ''\n ISO_639 = 'baq'\n ENGLISH_NAME = 'Basque'\n\n\nclass BAS:\n ISO_639_1 = ''\n ISO_639 = 'bas'\n ENGLISH_NAME = 'Basa'\n\n\nclass BEJ:\n ISO_639_1 = ''\n ISO_639 = 'bej'\n ENGLISH_NAME = 'Beja'\n\n\nclass BEL:\n ISO_639_1 = ''\n ISO_639 = 'bel'\n ENGLISH_NAME = 'Belarusian'\n\n\nclass BEM:\n ISO_639_1 = ''\n ISO_639 = 'bem'\n ENGLISH_NAME = 'Bemba'\n\n\nclass BEN:\n ISO_639_1 = 'bn'\n ISO_639 = 'ben'\n ENGLISH_NAME = 'Bengali'\n\n\nclass BHO:\n ISO_639_1 = ''\n ISO_639 = 'bho'\n ENGLISH_NAME = 'Bhojpuri'\n\n\nclass BIK:\n ISO_639_1 = ''\n ISO_639 = 'bik'\n ENGLISH_NAME = 'Bikol'\n\n\nclass BIN:\n ISO_639_1 = ''\n ISO_639 = 'bin'\n ENGLISH_NAME = 'Bini'\n\n\nclass BIS:\n ISO_639_1 = ''\n ISO_639 = 'bis'\n ENGLISH_NAME = 'Bislama'\n\n\nclass BLA:\n ISO_639_1 = ''\n ISO_639 = 'bla'\n ENGLISH_NAME = 'Siksika'\n\n\nclass BOS:\n ISO_639_1 = ''\n ISO_639 = 'bos'\n ENGLISH_NAME = 'Bosnian'\n\n\nclass BRA:\n ISO_639_1 = ''\n ISO_639 = 'bra'\n ENGLISH_NAME = 'Braj'\n\n\nclass BRE:\n ISO_639_1 = ''\n ISO_639 = 'bre'\n ENGLISH_NAME = 'Breton'\n\n\nclass BUA:\n ISO_639_1 = ''\n ISO_639 = 'bua'\n ENGLISH_NAME = 'Buriat'\n\n\nclass BUG:\n ISO_639_1 = ''\n ISO_639 = 'bug'\n ENGLISH_NAME = 'Buginese'\n\n\nclass BUL:\n ISO_639_1 = ''\n ISO_639 = 'bul'\n ENGLISH_NAME = 'Bulgarian'\n\n\nclass BUR:\n ISO_639_1 = ''\n ISO_639 = 'bur'\n ENGLISH_NAME = 'Burmese'\n\n\nclass BYN:\n ISO_639_1 = ''\n ISO_639 = 'byn'\n ENGLISH_NAME = 'Blin'\n\n\nclass CAD:\n ISO_639_1 = ''\n ISO_639 = 'cad'\n ENGLISH_NAME = 'Caddo'\n\n\nclass CAR:\n ISO_639_1 = ''\n ISO_639 = 'car'\n ENGLISH_NAME = 'GalibiCarib'\n\n\nclass CAT:\n ISO_639_1 = ''\n ISO_639 = 'cat'\n ENGLISH_NAME = 'Catalan'\n\n\nclass CEB:\n ISO_639_1 = ''\n ISO_639 = 'ceb'\n ENGLISH_NAME = 'Cebuano'\n\n\nclass CHA:\n ISO_639_1 = ''\n ISO_639 = 'cha'\n ENGLISH_NAME = 'Chamorro'\n\n\nclass CHB:\n ISO_639_1 = ''\n ISO_639 = 'chb'\n ENGLISH_NAME = 'Chibcha'\n\n\nclass CHE:\n ISO_639_1 = ''\n ISO_639 = 'che'\n ENGLISH_NAME = 'Chechen'\n\n\nclass CHG:\n ISO_639_1 = ''\n ISO_639 = 'chg'\n ENGLISH_NAME = 'Chagatai'\n\n\nclass CHI:\n ISO_639_1 = 'zh'\n ISO_639 = 'chi'\n ENGLISH_NAME = 'Chinese'\n\n\nclass CHK:\n ISO_639_1 = ''\n ISO_639 = 'chk'\n ENGLISH_NAME = 'Chuukese'\n\n\nclass CHM:\n ISO_639_1 = ''\n ISO_639 = 'chm'\n ENGLISH_NAME = 'Mari'\n\n\nclass CHN:\n ISO_639_1 = ''\n ISO_639 = 'chn'\n ENGLISH_NAME = 'Chinookjargon'\n\n\nclass CHO:\n ISO_639_1 = ''\n ISO_639 = 'cho'\n ENGLISH_NAME = 'Choctaw'\n\n\nclass CHP:\n ISO_639_1 = ''\n ISO_639 = 'chp'\n ENGLISH_NAME = 'Chipewyan'\n\n\nclass CHR:\n ISO_639_1 = ''\n ISO_639 = 'chr'\n ENGLISH_NAME = 'Cherokee'\n\n\nclass CHV:\n ISO_639_1 = ''\n ISO_639 = 'chv'\n ENGLISH_NAME = 'Chuvash'\n\n\nclass CHY:\n ISO_639_1 = ''\n ISO_639 = 'chy'\n ENGLISH_NAME = 'Cheyenne'\n\n\nclass CNR:\n ISO_639_1 = ''\n ISO_639 = 'cnr'\n ENGLISH_NAME = 'Montenegrin'\n\n\nclass COP:\n ISO_639_1 = ''\n ISO_639 = 'cop'\n ENGLISH_NAME = 'Coptic'\n\n\nclass COR:\n ISO_639_1 = ''\n ISO_639 = 'cor'\n ENGLISH_NAME = 'Cornish'\n\n\nclass COS:\n ISO_639_1 = ''\n ISO_639 = 'cos'\n ENGLISH_NAME = 'Corsican'\n\n\nclass CPE:\n ISO_639_1 = ''\n ISO_639 = 'cpe'\n ENGLISH_NAME = 'Creolesandpidgins'\n\n\nclass CPF:\n ISO_639_1 = ''\n ISO_639 = 'cpf'\n ENGLISH_NAME = 'Creolesandpidgins'\n\n\nclass CPP:\n ISO_639_1 = ''\n ISO_639 = 'cpp'\n ENGLISH_NAME = 'Creolesandpidgins'\n\n\nclass CRE:\n ISO_639_1 = ''\n ISO_639 = 'cre'\n ENGLISH_NAME = 'Cree'\n\n\nclass CRH:\n ISO_639_1 = ''\n ISO_639 = 'crh'\n ENGLISH_NAME = 'CrimeanTatar'\n\n\nclass CRP:\n ISO_639_1 = ''\n ISO_639 = 'crp'\n ENGLISH_NAME = 'Creolesandpidgins'\n\n\nclass CSB:\n ISO_639_1 = ''\n ISO_639 = 'csb'\n ENGLISH_NAME = 'Kashubian'\n\n\nclass CZE:\n ISO_639_1 = ''\n ISO_639 = 'cze'\n ENGLISH_NAME = 'Czech'\n\n\nclass DAK:\n ISO_639_1 = ''\n ISO_639 = 'dak'\n ENGLISH_NAME = 'Dakota'\n\n\nclass DAN:\n ISO_639_1 = ''\n ISO_639 = 'dan'\n ENGLISH_NAME = 'Danish'\n\n\nclass DAR:\n ISO_639_1 = ''\n ISO_639 = 'dar'\n ENGLISH_NAME = 'Dargwa'\n\n\nclass DEL:\n ISO_639_1 = ''\n ISO_639 = 'del'\n ENGLISH_NAME = 'Delaware'\n\n\nclass DEN:\n ISO_639_1 = ''\n ISO_639 = 'den'\n ENGLISH_NAME = 'Slave'\n\n\nclass DGR:\n ISO_639_1 = ''\n ISO_639 = 'dgr'\n ENGLISH_NAME = 'Dogrib'\n\n\nclass DIN:\n ISO_639_1 = ''\n ISO_639 = 'din'\n ENGLISH_NAME = 'Dinka'\n\n\nclass DIV:\n ISO_639_1 = ''\n ISO_639 = 'div'\n ENGLISH_NAME = 'Divehi'\n\n\nclass DOI:\n ISO_639_1 = ''\n ISO_639 = 'doi'\n ENGLISH_NAME = 'Dogri'\n\n\nclass DUA:\n ISO_639_1 = ''\n ISO_639 = 'dua'\n ENGLISH_NAME = 'Duala'\n\n\nclass DUT:\n ISO_639_1 = 'nl'\n ISO_639 = 'dut'\n ENGLISH_NAME = 'Dutch'\n\n\nclass DYU:\n ISO_639_1 = ''\n ISO_639 = 'dyu'\n ENGLISH_NAME = 'Dyula'\n\n\nclass DZO:\n ISO_639_1 = ''\n ISO_639 = 'dzo'\n ENGLISH_NAME = 'Dzongkha'\n\n\nclass EFI:\n ISO_639_1 = ''\n ISO_639 = 'efi'\n ENGLISH_NAME = 'Efik'\n\n\nclass EKA:\n ISO_639_1 = ''\n ISO_639 = 'eka'\n ENGLISH_NAME = 'Ekajuk'\n\n\nclass ELX:\n ISO_639_1 = ''\n ISO_639 = 'elx'\n ENGLISH_NAME = 'Elamite'\n\n\nclass ENG:\n ISO_639_1 = 'en'\n ISO_639 = 'eng'\n ENGLISH_NAME = 'English'\n\n\nclass EPO:\n ISO_639_1 = ''\n ISO_639 = 'epo'\n ENGLISH_NAME = 'Esperanto'\n\n\nclass EST:\n ISO_639_1 = ''\n ISO_639 = 'est'\n ENGLISH_NAME = 'Estonian'\n\n\nclass EWE:\n ISO_639_1 = ''\n ISO_639 = 'ewe'\n ENGLISH_NAME = 'Ewe'\n\n\nclass EWO:\n ISO_639_1 = ''\n ISO_639 = 'ewo'\n ENGLISH_NAME = 'Ewondo'\n\n\nclass FAN:\n ISO_639_1 = ''\n ISO_639 = 'fan'\n ENGLISH_NAME = 'Fang'\n\n\nclass FAO:\n ISO_639_1 = ''\n ISO_639 = 'fao'\n ENGLISH_NAME = 'Faroese'\n\n\nclass FAT:\n ISO_639_1 = ''\n ISO_639 = 'fat'\n ENGLISH_NAME = 'Fanti'\n\n\nclass FIJ:\n ISO_639_1 = ''\n ISO_639 = 'fij'\n ENGLISH_NAME = 'Fijian'\n\n\nclass FIL:\n ISO_639_1 = ''\n ISO_639 = 'fil'\n ENGLISH_NAME = 'Filipino'\n\n\nclass FIN:\n ISO_639_1 = ''\n ISO_639 = 'fin'\n ENGLISH_NAME = 'Finnish'\n\n\nclass FON:\n ISO_639_1 = ''\n ISO_639 = 'fon'\n ENGLISH_NAME = 'Fon'\n\n\nclass FRE:\n ISO_639_1 = ''\n ISO_639 = 'fre'\n ENGLISH_NAME = 'French'\n\n\nclass FRR:\n ISO_639_1 = ''\n ISO_639 = 'frr'\n ENGLISH_NAME = 'NorthernFrisian'\n\n\nclass FRS:\n ISO_639_1 = ''\n ISO_639 = 'frs'\n ENGLISH_NAME = 'EasternFrisian'\n\n\nclass FRY:\n ISO_639_1 = ''\n ISO_639 = 'fry'\n ENGLISH_NAME = 'WesternFrisian'\n\n\nclass FUL:\n ISO_639_1 = ''\n ISO_639 = 'ful'\n ENGLISH_NAME = 'Fulah'\n\n\nclass FUR:\n ISO_639_1 = ''\n ISO_639 = 'fur'\n ENGLISH_NAME = 'Friulian'\n\n\nclass GAA:\n ISO_639_1 = ''\n ISO_639 = 'gaa'\n ENGLISH_NAME = 'Ga'\n\n\nclass GAY:\n ISO_639_1 = ''\n ISO_639 = 'gay'\n ENGLISH_NAME = 'Gayo'\n\n\nclass GBA:\n ISO_639_1 = ''\n ISO_639 = 'gba'\n ENGLISH_NAME = 'Gbaya'\n\n\nclass GEO:\n ISO_639_1 = ''\n ISO_639 = 'geo'\n ENGLISH_NAME = 'Georgian'\n\n\nclass GER:\n ISO_639_1 = 'de'\n ISO_639 = 'ger'\n ENGLISH_NAME = 'German'\n\n\nclass GEZ:\n ISO_639_1 = ''\n ISO_639 = 'gez'\n ENGLISH_NAME = 'Geez'\n\n\nclass GIL:\n ISO_639_1 = ''\n ISO_639 = 'gil'\n ENGLISH_NAME = 'Gilbertese'\n\n\nclass GLA:\n ISO_639_1 = ''\n ISO_639 = 'gla'\n ENGLISH_NAME = 'Gaelic'\n\n\nclass GLE:\n ISO_639_1 = ''\n ISO_639 = 'gle'\n ENGLISH_NAME = 'Irish'\n\n\nclass GLG:\n ISO_639_1 = ''\n ISO_639 = 'glg'\n ENGLISH_NAME = 'Galician'\n\n\nclass GLV:\n ISO_639_1 = ''\n ISO_639 = 'glv'\n ENGLISH_NAME = 'Manx'\n\n\nclass GON:\n ISO_639_1 = ''\n ISO_639 = 'gon'\n ENGLISH_NAME = 'Gondi'\n\n\nclass GOR:\n ISO_639_1 = ''\n ISO_639 = 'gor'\n ENGLISH_NAME = 'Gorontalo'\n\n\nclass GOT:\n ISO_639_1 = ''\n ISO_639 = 'got'\n ENGLISH_NAME = 'Gothic'\n\n\nclass GRB:\n ISO_639_1 = ''\n ISO_639 = 'grb'\n ENGLISH_NAME = 'Grebo'\n\n\nclass GRE:\n ISO_639_1 = 'el'\n ISO_639 = 'gre'\n ENGLISH_NAME = 'Greek'\n\n\nclass GRN:\n ISO_639_1 = ''\n ISO_639 = 'grn'\n ENGLISH_NAME = 'Guarani'\n\n\nclass GSW:\n ISO_639_1 = ''\n ISO_639 = 'gsw'\n ENGLISH_NAME = 'SwissGerman'\n\n\nclass GUJ:\n ISO_639_1 = ''\n ISO_639 = 'guj'\n ENGLISH_NAME = 'Gujarati'\n\n\nclass GWI:\n ISO_639_1 = ''\n ISO_639 = 'gwi'\n ENGLISH_NAME = 'Gwichin'\n\n\nclass HAI:\n ISO_639_1 = ''\n ISO_639 = 'hai'\n ENGLISH_NAME = 'Haida'\n\n\nclass HAT:\n ISO_639_1 = ''\n ISO_639 = 'hat'\n ENGLISH_NAME = 'Haitian'\n\n\nclass HAU:\n ISO_639_1 = ''\n ISO_639 = 'hau'\n ENGLISH_NAME = 'Hausa'\n\n\nclass HAW:\n ISO_639_1 = ''\n ISO_639 = 'haw'\n ENGLISH_NAME = 'Hawaiian'\n\n\nclass HEB:\n ISO_639_1 = 'he'\n ISO_639 = 'heb'\n ENGLISH_NAME = 'Hebrew'\n\n\nclass HER:\n ISO_639_1 = ''\n ISO_639 = 'her'\n ENGLISH_NAME = 'Herero'\n\n\nclass HIL:\n ISO_639_1 = ''\n ISO_639 = 'hil'\n ENGLISH_NAME = 'Hiligaynon'\n\n\nclass HIN:\n ISO_639_1 = 'hi'\n ISO_639 = 'hin'\n ENGLISH_NAME = 'Hindi'\n\n\nclass HIT:\n ISO_639_1 = ''\n ISO_639 = 'hit'\n ENGLISH_NAME = 'Hittite'\n\n\nclass HMN:\n ISO_639_1 = ''\n ISO_639 = 'hmn'\n ENGLISH_NAME = 'Hmong'\n\n\nclass HMO:\n ISO_639_1 = ''\n ISO_639 = 'hmo'\n ENGLISH_NAME = 'HiriMotu'\n\n\nclass HRV:\n ISO_639_1 = ''\n ISO_639 = 'hrv'\n ENGLISH_NAME = 'Croatian'\n\n\nclass HSB:\n ISO_639_1 = ''\n ISO_639 = 'hsb'\n ENGLISH_NAME = 'UpperSorbian'\n\n\nclass HUN:\n ISO_639_1 = ''\n ISO_639 = 'hun'\n ENGLISH_NAME = 'Hungarian'\n\n\nclass HUP:\n ISO_639_1 = ''\n ISO_639 = 'hup'\n ENGLISH_NAME = 'Hupa'\n\n\nclass IBA:\n ISO_639_1 = ''\n ISO_639 = 'iba'\n ENGLISH_NAME = 'Iban'\n\n\nclass IBO:\n ISO_639_1 = ''\n ISO_639 = 'ibo'\n ENGLISH_NAME = 'Igbo'\n\n\nclass ICE:\n ISO_639_1 = ''\n ISO_639 = 'ice'\n ENGLISH_NAME = 'Icelandic'\n\n\nclass IDO:\n ISO_639_1 = ''\n ISO_639 = 'ido'\n ENGLISH_NAME = 'Ido'\n\n\nclass III:\n ISO_639_1 = ''\n ISO_639 = 'iii'\n ENGLISH_NAME = 'SichuanYi'\n\n\nclass IKU:\n ISO_639_1 = ''\n ISO_639 = 'iku'\n ENGLISH_NAME = 'Inuktitut'\n\n\nclass ILE:\n ISO_639_1 = ''\n ISO_639 = 'ile'\n ENGLISH_NAME = 'Interlingue'\n\n\nclass ILO:\n ISO_639_1 = ''\n ISO_639 = 'ilo'\n ENGLISH_NAME = 'Iloko'\n\n\nclass INA:\n ISO_639_1 = ''\n ISO_639 = 'ina'\n ENGLISH_NAME = 'Interlingua'\n\n\nclass IND:\n ISO_639_1 = 'id'\n ISO_639 = 'ind'\n ENGLISH_NAME = 'Indonesian'\n\n\nclass INH:\n ISO_639_1 = ''\n ISO_639 = 'inh'\n ENGLISH_NAME = 'Ingush'\n\n\nclass IPK:\n ISO_639_1 = ''\n ISO_639 = 'ipk'\n ENGLISH_NAME = 'Inupiaq'\n\n\nclass ITA:\n ISO_639_1 = ''\n ISO_639 = 'ita'\n ENGLISH_NAME = 'Italian'\n\n\nclass JAV:\n ISO_639_1 = ''\n ISO_639 = 'jav'\n ENGLISH_NAME = 'Javanese'\n\n\nclass JBO:\n ISO_639_1 = ''\n ISO_639 = 'jbo'\n ENGLISH_NAME = 'Lojban'\n\n\nclass JPN:\n ISO_639_1 = 'ja'\n ISO_639 = 'jpn'\n ENGLISH_NAME = 'Japanese'\n\n\nclass JPR:\n ISO_639_1 = ''\n ISO_639 = 'jpr'\n ENGLISH_NAME = 'JudeoPersian'\n\n\nclass JRB:\n ISO_639_1 = ''\n ISO_639 = 'jrb'\n ENGLISH_NAME = 'JudeoArabic'\n\n\nclass KAA:\n ISO_639_1 = ''\n ISO_639 = 'kaa'\n ENGLISH_NAME = 'KaraKalpak'\n\n\nclass KAB:\n ISO_639_1 = ''\n ISO_639 = 'kab'\n ENGLISH_NAME = 'Kabyle'\n\n\nclass KAC:\n ISO_639_1 = ''\n ISO_639 = 'kac'\n ENGLISH_NAME = 'Kachin'\n\n\nclass KAL:\n ISO_639_1 = ''\n ISO_639 = 'kal'\n ENGLISH_NAME = 'Kalaallisut'\n\n\nclass KAM:\n ISO_639_1 = ''\n ISO_639 = 'kam'\n ENGLISH_NAME = 'Kamba'\n\n\nclass KAN:\n ISO_639_1 = ''\n ISO_639 = 'kan'\n ENGLISH_NAME = 'Kannada'\n\n\nclass KAS:\n ISO_639_1 = ''\n ISO_639 = 'kas'\n ENGLISH_NAME = 'Kashmiri'\n\n\nclass KAU:\n ISO_639_1 = ''\n ISO_639 = 'kau'\n ENGLISH_NAME = 'Kanuri'\n\n\nclass KAW:\n ISO_639_1 = ''\n ISO_639 = 'kaw'\n ENGLISH_NAME = 'Kawi'\n\n\nclass KAZ:\n ISO_639_1 = ''\n ISO_639 = 'kaz'\n ENGLISH_NAME = 'Kazakh'\n\n\nclass KBD:\n ISO_639_1 = ''\n ISO_639 = 'kbd'\n ENGLISH_NAME = 'Kabardian'\n\n\nclass KHA:\n ISO_639_1 = ''\n ISO_639 = 'kha'\n ENGLISH_NAME = 'Khasi'\n\n\nclass KHM:\n ISO_639_1 = ''\n ISO_639 = 'khm'\n ENGLISH_NAME = 'CentralKhmer'\n\n\nclass KHO:\n ISO_639_1 = ''\n ISO_639 = 'kho'\n ENGLISH_NAME = 'Khotanese'\n\n\nclass KIK:\n ISO_639_1 = ''\n ISO_639 = 'kik'\n ENGLISH_NAME = 'Kikuyu'\n\n\nclass KIN:\n ISO_639_1 = ''\n ISO_639 = 'kin'\n ENGLISH_NAME = 'Kinyarwanda'\n\n\nclass KIR:\n ISO_639_1 = ''\n ISO_639 = 'kir'\n ENGLISH_NAME = 'Kirghiz'\n\n\nclass KMB:\n ISO_639_1 = ''\n ISO_639 = 'kmb'\n ENGLISH_NAME = 'Kimbundu'\n\n\nclass KOK:\n ISO_639_1 = ''\n ISO_639 = 'kok'\n ENGLISH_NAME = 'Konkani'\n\n\nclass KOM:\n ISO_639_1 = ''\n ISO_639 = 'kom'\n ENGLISH_NAME = 'Komi'\n\n\nclass KON:\n ISO_639_1 = ''\n ISO_639 = 'kon'\n ENGLISH_NAME = 'Kongo'\n\n\nclass KOR:\n ISO_639_1 = 'ko'\n ISO_639 = 'kor'\n ENGLISH_NAME = 'Korean'\n\n\nclass KOS:\n ISO_639_1 = ''\n ISO_639 = 'kos'\n ENGLISH_NAME = 'Kosraean'\n\n\nclass KPE:\n ISO_639_1 = ''\n ISO_639 = 'kpe'\n ENGLISH_NAME = 'Kpelle'\n\n\nclass KRC:\n ISO_639_1 = ''\n ISO_639 = 'krc'\n ENGLISH_NAME = 'KarachayBalkar'\n\n\nclass KRL:\n ISO_639_1 = ''\n ISO_639 = 'krl'\n ENGLISH_NAME = 'Karelian'\n\n\nclass KRU:\n ISO_639_1 = ''\n ISO_639 = 'kru'\n ENGLISH_NAME = 'Kurukh'\n\n\nclass KUA:\n ISO_639_1 = ''\n ISO_639 = 'kua'\n ENGLISH_NAME = 'Kuanyama'\n\n\nclass KUM:\n ISO_639_1 = ''\n ISO_639 = 'kum'\n ENGLISH_NAME = 'Kumyk'\n\n\nclass KUR:\n ISO_639_1 = ''\n ISO_639 = 'kur'\n ENGLISH_NAME = 'Kurdish'\n\n\nclass KUT:\n ISO_639_1 = ''\n ISO_639 = 'kut'\n ENGLISH_NAME = 'Kutenai'\n\n\nclass LAD:\n ISO_639_1 = ''\n ISO_639 = 'lad'\n ENGLISH_NAME = 'Ladino'\n\n\nclass LAH:\n ISO_639_1 = ''\n ISO_639 = 'lah'\n ENGLISH_NAME = 'Lahnda'\n\n\nclass LAM:\n ISO_639_1 = ''\n ISO_639 = 'lam'\n ENGLISH_NAME = 'Lamba'\n\n\nclass LAO:\n ISO_639_1 = ''\n ISO_639 = 'lao'\n ENGLISH_NAME = 'Lao'\n\n\nclass LAT:\n ISO_639_1 = ''\n ISO_639 = 'lat'\n ENGLISH_NAME = 'Latin'\n\n\nclass LAV:\n ISO_639_1 = ''\n ISO_639 = 'lav'\n ENGLISH_NAME = 'Latvian'\n\n\nclass LEZ:\n ISO_639_1 = ''\n ISO_639 = 'lez'\n ENGLISH_NAME = 'Lezghian'\n\n\nclass LIM:\n ISO_639_1 = ''\n ISO_639 = 'lim'\n ENGLISH_NAME = 'Limburgan'\n\n\nclass LIN:\n ISO_639_1 = ''\n ISO_639 = 'lin'\n ENGLISH_NAME = 'Lingala'\n\n\nclass LIT:\n ISO_639_1 = ''\n ISO_639 = 'lit'\n ENGLISH_NAME = 'Lithuanian'\n\n\nclass LOL:\n ISO_639_1 = ''\n ISO_639 = 'lol'\n ENGLISH_NAME = 'Mongo'\n\n\nclass LOZ:\n ISO_639_1 = ''\n ISO_639 = 'loz'\n ENGLISH_NAME = 'Lozi'\n\n\nclass LTZ:\n ISO_639_1 = ''\n ISO_639 = 'ltz'\n ENGLISH_NAME = 'Luxembourgish'\n\n\nclass LUA:\n ISO_639_1 = ''\n ISO_639 = 'lua'\n ENGLISH_NAME = 'LubaLulua'\n\n\nclass LUB:\n ISO_639_1 = ''\n ISO_639 = 'lub'\n ENGLISH_NAME = 'LubaKatanga'\n\n\nclass LUG:\n ISO_639_1 = ''\n ISO_639 = 'lug'\n ENGLISH_NAME = 'Ganda'\n\n\nclass LUI:\n ISO_639_1 = ''\n ISO_639 = 'lui'\n ENGLISH_NAME = 'Luiseno'\n\n\nclass LUN:\n ISO_639_1 = ''\n ISO_639 = 'lun'\n ENGLISH_NAME = 'Lunda'\n\n\nclass LUO:\n ISO_639_1 = ''\n ISO_639 = 'luo'\n ENGLISH_NAME = 'Luo'\n\n\nclass LUS:\n ISO_639_1 = ''\n ISO_639 = 'lus'\n ENGLISH_NAME = 'Lushai'\n\n\nclass MAC:\n ISO_639_1 = ''\n ISO_639 = 'mac'\n ENGLISH_NAME = 'Macedonian'\n\n\nclass MAD:\n ISO_639_1 = ''\n ISO_639 = 'mad'\n ENGLISH_NAME = 'Madurese'\n\n\nclass MAG:\n ISO_639_1 = ''\n ISO_639 = 'mag'\n ENGLISH_NAME = 'Magahi'\n\n\nclass MAH:\n ISO_639_1 = ''\n ISO_639 = 'mah'\n ENGLISH_NAME = 'Marshallese'\n\n\nclass MAI:\n ISO_639_1 = ''\n ISO_639 = 'mai'\n ENGLISH_NAME = 'Maithili'\n\n\nclass MAK:\n ISO_639_1 = ''\n ISO_639 = 'mak'\n ENGLISH_NAME = 'Makasar'\n\n\nclass MAL:\n ISO_639_1 = ''\n ISO_639 = 'mal'\n ENGLISH_NAME = 'Malayalam'\n\n\nclass MAN:\n ISO_639_1 = ''\n ISO_639 = 'man'\n ENGLISH_NAME = 'Mandingo'\n\n\nclass MAO:\n ISO_639_1 = ''\n ISO_639 = 'mao'\n ENGLISH_NAME = 'Maori'\n\n\nclass MAR:\n ISO_639_1 = 'mr'\n ISO_639 = 'mar'\n ENGLISH_NAME = 'Marathi'\n\n\nclass MAS:\n ISO_639_1 = ''\n ISO_639 = 'mas'\n ENGLISH_NAME = 'Masai'\n\n\nclass MAY:\n ISO_639_1 = ''\n ISO_639 = 'may'\n ENGLISH_NAME = 'Malay'\n\n\nclass MDF:\n ISO_639_1 = ''\n ISO_639 = 'mdf'\n ENGLISH_NAME = 'Moksha'\n\n\nclass MDR:\n ISO_639_1 = ''\n ISO_639 = 'mdr'\n ENGLISH_NAME = 'Mandar'\n\n\nclass MEN:\n ISO_639_1 = ''\n ISO_639 = 'men'\n ENGLISH_NAME = 'Mende'\n\n\nclass MIC:\n ISO_639_1 = ''\n ISO_639 = 'mic'\n ENGLISH_NAME = 'Mikmaq'\n\n\nclass MIN:\n ISO_639_1 = ''\n ISO_639 = 'min'\n ENGLISH_NAME = 'Minangkabau'\n\n\nclass MLG:\n ISO_639_1 = ''\n ISO_639 = 'mlg'\n ENGLISH_NAME = 'Malagasy'\n\n\nclass MLT:\n ISO_639_1 = ''\n ISO_639 = 'mlt'\n ENGLISH_NAME = 'Maltese'\n\n\nclass MNC:\n ISO_639_1 = ''\n ISO_639 = 'mnc'\n ENGLISH_NAME = 'Manchu'\n\n\nclass MNI:\n ISO_639_1 = ''\n ISO_639 = 'mni'\n ENGLISH_NAME = 'Manipuri'\n\n\nclass MOH:\n ISO_639_1 = ''\n ISO_639 = 'moh'\n ENGLISH_NAME = 'Mohawk'\n\n\nclass MON:\n ISO_639_1 = ''\n ISO_639 = 'mon'\n ENGLISH_NAME = 'Mongolian'\n\n\nclass MOS:\n ISO_639_1 = ''\n ISO_639 = 'mos'\n ENGLISH_NAME = 'Mossi'\n\n\nclass MUS:\n ISO_639_1 = ''\n ISO_639 = 'mus'\n ENGLISH_NAME = 'Creek'\n\n\nclass MWL:\n ISO_639_1 = ''\n ISO_639 = 'mwl'\n ENGLISH_NAME = 'Mirandese'\n\n\nclass MWR:\n ISO_639_1 = ''\n ISO_639 = 'mwr'\n ENGLISH_NAME = 'Marwari'\n\n\nclass MYV:\n ISO_639_1 = ''\n ISO_639 = 'myv'\n ENGLISH_NAME = 'Erzya'\n\n\nclass NAP:\n ISO_639_1 = ''\n ISO_639 = 'nap'\n ENGLISH_NAME = 'Neapolitan'\n\n\nclass NAU:\n ISO_639_1 = ''\n ISO_639 = 'nau'\n ENGLISH_NAME = 'Nauru'\n\n\nclass NAV:\n ISO_639_1 = ''\n ISO_639 = 'nav'\n ENGLISH_NAME = 'Navajo'\n\n\nclass NBL:\n ISO_639_1 = ''\n ISO_639 = 'nbl'\n ENGLISH_NAME = 'Ndebele'\n\n\nclass NDE:\n ISO_639_1 = ''\n ISO_639 = 'nde'\n ENGLISH_NAME = 'Ndebele'\n\n\nclass NDO:\n ISO_639_1 = ''\n ISO_639 = 'ndo'\n ENGLISH_NAME = 'Ndonga'\n\n\nclass NEP:\n ISO_639_1 = ''\n ISO_639 = 'nep'\n ENGLISH_NAME = 'Nepali'\n\n\nclass NEW:\n ISO_639_1 = ''\n ISO_639 = 'new'\n ENGLISH_NAME = 'NepalBhasa'\n\n\nclass NIA:\n ISO_639_1 = ''\n ISO_639 = 'nia'\n ENGLISH_NAME = 'Nias'\n\n\nclass NIU:\n ISO_639_1 = ''\n ISO_639 = 'niu'\n ENGLISH_NAME = 'Niuean'\n\n\nclass NNO:\n ISO_639_1 = ''\n ISO_639 = 'nno'\n ENGLISH_NAME = 'NorwegianNynorsk'\n\n\nclass NOB:\n ISO_639_1 = ''\n ISO_639 = 'nob'\n ENGLISH_NAME = 'Bokmål'\n\n\nclass NOG:\n ISO_639_1 = ''\n ISO_639 = 'nog'\n ENGLISH_NAME = 'Nogai'\n\n\nclass NOR:\n ISO_639_1 = ''\n ISO_639 = 'nor'\n ENGLISH_NAME = 'Norwegian'\n\n\nclass NQO:\n ISO_639_1 = ''\n ISO_639 = 'nqo'\n ENGLISH_NAME = 'NKo'\n\n\nclass NSO:\n ISO_639_1 = ''\n ISO_639 = 'nso'\n ENGLISH_NAME = 'Pedi'\n\n\nclass NYA:\n ISO_639_1 = ''\n ISO_639 = 'nya'\n ENGLISH_NAME = 'Chichewa'\n\n\nclass NYM:\n ISO_639_1 = ''\n ISO_639 = 'nym'\n ENGLISH_NAME = 'Nyamwezi'\n\n\nclass NYN:\n ISO_639_1 = ''\n ISO_639 = 'nyn'\n ENGLISH_NAME = 'Nyankole'\n\n\nclass NYO:\n ISO_639_1 = ''\n ISO_639 = 'nyo'\n ENGLISH_NAME = 'Nyoro'\n\n\nclass NZI:\n ISO_639_1 = ''\n ISO_639 = 'nzi'\n ENGLISH_NAME = 'Nzima'\n\n\nclass OJI:\n ISO_639_1 = ''\n ISO_639 = 'oji'\n ENGLISH_NAME = 'Ojibwa'\n\n\nclass ORI:\n ISO_639_1 = 'or'\n ISO_639 = 'ori'\n ENGLISH_NAME = 'Oriya'\n\n\nclass ORM:\n ISO_639_1 = ''\n ISO_639 = 'orm'\n ENGLISH_NAME = 'Oromo'\n\n\nclass OSA:\n ISO_639_1 = ''\n ISO_639 = 'osa'\n ENGLISH_NAME = 'Osage'\n\n\nclass OSS:\n ISO_639_1 = ''\n ISO_639 = 'oss'\n ENGLISH_NAME = 'Ossetian'\n\n\nclass PAG:\n ISO_639_1 = ''\n ISO_639 = 'pag'\n ENGLISH_NAME = 'Pangasinan'\n\n\nclass PAL:\n ISO_639_1 = ''\n ISO_639 = 'pal'\n ENGLISH_NAME = 'Pahlavi'\n\n\nclass PAM:\n ISO_639_1 = ''\n ISO_639 = 'pam'\n ENGLISH_NAME = 'Pampanga'\n\n\nclass PAN:\n ISO_639_1 = ''\n ISO_639 = 'pan'\n ENGLISH_NAME = 'Panjabi'\n\n\nclass PAP:\n ISO_639_1 = ''\n ISO_639 = 'pap'\n ENGLISH_NAME = 'Papiamento'\n\n\nclass PAU:\n ISO_639_1 = ''\n ISO_639 = 'pau'\n ENGLISH_NAME = 'Palauan'\n\n\nclass PER:\n ISO_639_1 = 'fa'\n ISO_639 = 'per'\n ENGLISH_NAME = 'Persian'\n\n\nclass PHN:\n ISO_639_1 = ''\n ISO_639 = 'phn'\n ENGLISH_NAME = 'Phoenician'\n\n\nclass PLI:\n ISO_639_1 = ''\n ISO_639 = 'pli'\n ENGLISH_NAME = 'Pali'\n\n\nclass POL:\n ISO_639_1 = ''\n ISO_639 = 'pol'\n ENGLISH_NAME = 'Polish'\n\n\nclass PON:\n ISO_639_1 = ''\n ISO_639 = 'pon'\n ENGLISH_NAME = 'Pohnpeian'\n\n\nclass POR:\n ISO_639_1 = 'pt'\n ISO_639 = 'por'\n ENGLISH_NAME = 'Portuguese'\n\n\nclass PUS:\n ISO_639_1 = ''\n ISO_639 = 'pus'\n ENGLISH_NAME = 'Pushto'\n\n\nclass QUE:\n ISO_639_1 = ''\n ISO_639 = 'que'\n ENGLISH_NAME = 'Quechua'\n\n\nclass RAJ:\n ISO_639_1 = ''\n ISO_639 = 'raj'\n ENGLISH_NAME = 'Rajasthani'\n\n\nclass RAP:\n ISO_639_1 = ''\n ISO_639 = 'rap'\n ENGLISH_NAME = 'Rapanui'\n\n\nclass RAR:\n ISO_639_1 = ''\n ISO_639 = 'rar'\n ENGLISH_NAME = 'Rarotongan'\n\n\nclass ROH:\n ISO_639_1 = ''\n ISO_639 = 'roh'\n ENGLISH_NAME = 'Romansh'\n\n\nclass ROM:\n ISO_639_1 = ''\n ISO_639 = 'rom'\n ENGLISH_NAME = 'Romany'\n\n\nclass RUM:\n ISO_639_1 = ''\n ISO_639 = 'rum'\n ENGLISH_NAME = 'Romanian'\n\n\nclass RUN:\n ISO_639_1 = ''\n ISO_639 = 'run'\n ENGLISH_NAME = 'Rundi'\n\n\nclass RUP:\n ISO_639_1 = ''\n ISO_639 = 'rup'\n ENGLISH_NAME = 'Aromanian'\n\n\nclass RUS:\n ISO_639_1 = 'ru'\n ISO_639 = 'rus'\n ENGLISH_NAME = 'Russian'\n\n\nclass SAD:\n ISO_639_1 = ''\n ISO_639 = 'sad'\n ENGLISH_NAME = 'Sandawe'\n\n\nclass SAG:\n ISO_639_1 = ''\n ISO_639 = 'sag'\n ENGLISH_NAME = 'Sango'\n\n\nclass SAH:\n ISO_639_1 = ''\n ISO_639 = 'sah'\n ENGLISH_NAME = 'Yakut'\n\n\nclass SAM:\n ISO_639_1 = ''\n ISO_639 = 'sam'\n ENGLISH_NAME = 'SamaritanAramaic'\n\n\nclass SAN:\n ISO_639_1 = ''\n ISO_639 = 'san'\n ENGLISH_NAME = 'Sanskrit'\n\n\nclass SAS:\n ISO_639_1 = ''\n ISO_639 = 'sas'\n ENGLISH_NAME = 'Sasak'\n\n\nclass SAT:\n ISO_639_1 = ''\n ISO_639 = 'sat'\n ENGLISH_NAME = 'Santali'\n\n\nclass SCN:\n ISO_639_1 = ''\n ISO_639 = 'scn'\n ENGLISH_NAME = 'Sicilian'\n\n\nclass SCO:\n ISO_639_1 = ''\n ISO_639 = 'sco'\n ENGLISH_NAME = 'Scots'\n\n\nclass SEL:\n ISO_639_1 = ''\n ISO_639 = 'sel'\n ENGLISH_NAME = 'Selkup'\n\n\nclass SHN:\n ISO_639_1 = ''\n ISO_639 = 'shn'\n ENGLISH_NAME = 'Shan'\n\n\nclass SID:\n ISO_639_1 = ''\n ISO_639 = 'sid'\n ENGLISH_NAME = 'Sidamo'\n\n\nclass SIN:\n ISO_639_1 = ''\n ISO_639 = 'sin'\n ENGLISH_NAME = 'Sinhala'\n\n\nclass SLO:\n ISO_639_1 = ''\n ISO_639 = 'slo'\n ENGLISH_NAME = 'Slovak'\n\n\nclass SLV:\n ISO_639_1 = ''\n ISO_639 = 'slv'\n ENGLISH_NAME = 'Slovenian'\n\n\nclass SMA:\n ISO_639_1 = ''\n ISO_639 = 'sma'\n ENGLISH_NAME = 'SouthernSami'\n\n\nclass SME:\n ISO_639_1 = ''\n ISO_639 = 'sme'\n ENGLISH_NAME = 'NorthernSami'\n\n\nclass SMJ:\n ISO_639_1 = ''\n ISO_639 = 'smj'\n ENGLISH_NAME = 'LuleSami'\n\n\nclass SMN:\n ISO_639_1 = ''\n ISO_639 = 'smn'\n ENGLISH_NAME = 'InariSami'\n\n\nclass SMO:\n ISO_639_1 = ''\n ISO_639 = 'smo'\n ENGLISH_NAME = 'Samoan'\n\n\nclass SMS:\n ISO_639_1 = ''\n ISO_639 = 'sms'\n ENGLISH_NAME = 'SkoltSami'\n\n\nclass SNA:\n ISO_639_1 = ''\n ISO_639 = 'sna'\n ENGLISH_NAME = 'Shona'\n\n\nclass SND:\n ISO_639_1 = ''\n ISO_639 = 'snd'\n ENGLISH_NAME = 'Sindhi'\n\n\nclass SNK:\n ISO_639_1 = ''\n ISO_639 = 'snk'\n ENGLISH_NAME = 'Soninke'\n\n\nclass SOG:\n ISO_639_1 = ''\n ISO_639 = 'sog'\n ENGLISH_NAME = 'Sogdian'\n\n\nclass SOM:\n ISO_639_1 = ''\n ISO_639 = 'som'\n ENGLISH_NAME = 'Somali'\n\n\nclass SOT:\n ISO_639_1 = ''\n ISO_639 = 'sot'\n ENGLISH_NAME = 'Sotho'\n\n\nclass SPA:\n ISO_639_1 = 'es'\n ISO_639 = 'spa'\n ENGLISH_NAME = 'Spanish'\n\n\nclass SRD:\n ISO_639_1 = ''\n ISO_639 = 'srd'\n ENGLISH_NAME = 'Sardinian'\n\n\nclass SRN:\n ISO_639_1 = ''\n ISO_639 = 'srn'\n ENGLISH_NAME = 'SrananTongo'\n\n\nclass SRP:\n ISO_639_1 = ''\n ISO_639 = 'srp'\n ENGLISH_NAME = 'Serbian'\n\n\nclass SRR:\n ISO_639_1 = ''\n ISO_639 = 'srr'\n ENGLISH_NAME = 'Serer'\n\n\nclass SSW:\n ISO_639_1 = ''\n ISO_639 = 'ssw'\n ENGLISH_NAME = 'Swati'\n\n\nclass SUK:\n ISO_639_1 = ''\n ISO_639 = 'suk'\n ENGLISH_NAME = 'Sukuma'\n\n\nclass SUN:\n ISO_639_1 = ''\n ISO_639 = 'sun'\n ENGLISH_NAME = 'Sundanese'\n\n\nclass SUS:\n ISO_639_1 = ''\n ISO_639 = 'sus'\n ENGLISH_NAME = 'Susu'\n\n\nclass SUX:\n ISO_639_1 = ''\n ISO_639 = 'sux'\n ENGLISH_NAME = 'Sumerian'\n\n\nclass SWA:\n ISO_639_1 = ''\n ISO_639 = 'swa'\n ENGLISH_NAME = 'Swahili'\n\n\nclass SWE:\n ISO_639_1 = 'sv'\n ISO_639 = 'swe'\n ENGLISH_NAME = 'Swedish'\n\n\nclass SYC:\n ISO_639_1 = ''\n ISO_639 = 'syc'\n ENGLISH_NAME = 'ClassicalSyriac'\n\n\nclass SYR:\n ISO_639_1 = ''\n ISO_639 = 'syr'\n ENGLISH_NAME = 'Syriac'\n\n\nclass TAH:\n ISO_639_1 = 'th'\n ISO_639 = 'tah'\n ENGLISH_NAME = 'Tahitian'\n\n\nclass TAM:\n ISO_639_1 = ''\n ISO_639 = 'tam'\n ENGLISH_NAME = 'Tamil'\n\n\nclass TAT:\n ISO_639_1 = ''\n ISO_639 = 'tat'\n ENGLISH_NAME = 'Tatar'\n\n\nclass TEL:\n ISO_639_1 = 'te'\n ISO_639 = 'tel'\n ENGLISH_NAME = 'Telugu'\n\n\nclass TEM:\n ISO_639_1 = ''\n ISO_639 = 'tem'\n ENGLISH_NAME = 'Timne'\n\n\nclass TER:\n ISO_639_1 = ''\n ISO_639 = 'ter'\n ENGLISH_NAME = 'Tereno'\n\n\nclass TET:\n ISO_639_1 = ''\n ISO_639 = 'tet'\n ENGLISH_NAME = 'Tetum'\n\n\nclass TGK:\n ISO_639_1 = ''\n ISO_639 = 'tgk'\n ENGLISH_NAME = 'Tajik'\n\n\nclass TGL:\n ISO_639_1 = ''\n ISO_639 = 'tgl'\n ENGLISH_NAME = 'Tagalog'\n\n\nclass THA:\n ISO_639_1 = ''\n ISO_639 = 'tha'\n ENGLISH_NAME = 'Thai'\n\n\nclass TIB:\n ISO_639_1 = ''\n ISO_639 = 'tib'\n ENGLISH_NAME = 'Tibetan'\n\n\nclass TIG:\n ISO_639_1 = ''\n ISO_639 = 'tig'\n ENGLISH_NAME = 'Tigre'\n\n\nclass TIR:\n ISO_639_1 = ''\n ISO_639 = 'tir'\n ENGLISH_NAME = 'Tigrinya'\n\n\nclass TIV:\n ISO_639_1 = ''\n ISO_639 = 'tiv'\n ENGLISH_NAME = 'Tiv'\n\n\nclass TKL:\n ISO_639_1 = ''\n ISO_639 = 'tkl'\n ENGLISH_NAME = 'Tokelau'\n\n\nclass TLH:\n ISO_639_1 = ''\n ISO_639 = 'tlh'\n ENGLISH_NAME = 'Klingon'\n\n\nclass TLI:\n ISO_639_1 = ''\n ISO_639 = 'tli'\n ENGLISH_NAME = 'Tlingit'\n\n\nclass TMH:\n ISO_639_1 = ''\n ISO_639 = 'tmh'\n ENGLISH_NAME = 'Tamashek'\n\n\nclass TOG:\n ISO_639_1 = ''\n ISO_639 = 'tog'\n ENGLISH_NAME = 'Tonga'\n\n\nclass TON:\n ISO_639_1 = ''\n ISO_639 = 'ton'\n ENGLISH_NAME = 'Tonga'\n\n\nclass TPI:\n ISO_639_1 = ''\n ISO_639 = 'tpi'\n ENGLISH_NAME = 'TokPisin'\n\n\nclass TSI:\n ISO_639_1 = ''\n ISO_639 = 'tsi'\n ENGLISH_NAME = 'Tsimshian'\n\n\nclass TSN:\n ISO_639_1 = ''\n ISO_639 = 'tsn'\n ENGLISH_NAME = 'Tswana'\n\n\nclass TSO:\n ISO_639_1 = ''\n ISO_639 = 'tso'\n ENGLISH_NAME = 'Tsonga'\n\n\nclass TUK:\n ISO_639_1 = ''\n ISO_639 = 'tuk'\n ENGLISH_NAME = 'Turkmen'\n\n\nclass TUM:\n ISO_639_1 = ''\n ISO_639 = 'tum'\n ENGLISH_NAME = 'Tumbuka'\n\n\nclass TUR:\n ISO_639_1 = ''\n ISO_639 = 'tur'\n ENGLISH_NAME = 'Turkish'\n\n\nclass TVL:\n ISO_639_1 = ''\n ISO_639 = 'tvl'\n ENGLISH_NAME = 'Tuvalu'\n\n\nclass TWI:\n ISO_639_1 = ''\n ISO_639 = 'twi'\n ENGLISH_NAME = 'Twi'\n\n\nclass TYV:\n ISO_639_1 = ''\n ISO_639 = 'tyv'\n ENGLISH_NAME = 'Tuvinian'\n\n\nclass UDM:\n ISO_639_1 = ''\n ISO_639 = 'udm'\n ENGLISH_NAME = 'Udmurt'\n\n\nclass UGA:\n ISO_639_1 = ''\n ISO_639 = 'uga'\n ENGLISH_NAME = 'Ugaritic'\n\n\nclass UIG:\n ISO_639_1 = ''\n ISO_639 = 'uig'\n ENGLISH_NAME = 'Uighur'\n\n\nclass UKR:\n ISO_639_1 = ''\n ISO_639 = 'ukr'\n ENGLISH_NAME = 'Ukrainian'\n\n\nclass UMB:\n ISO_639_1 = ''\n ISO_639 = 'umb'\n ENGLISH_NAME = 'Umbundu'\n\n\nclass UND:\n ISO_639_1 = ''\n ISO_639 = 'und'\n ENGLISH_NAME = 'Undetermined'\n\n\nclass URD:\n ISO_639_1 = ''\n ISO_639 = 'urd'\n ENGLISH_NAME = 'Urdu'\n\n\nclass UZB:\n ISO_639_1 = ''\n ISO_639 = 'uzb'\n ENGLISH_NAME = 'Uzbek'\n\n\nclass VAI:\n ISO_639_1 = ''\n ISO_639 = 'vai'\n ENGLISH_NAME = 'Vai'\n\n\nclass VEN:\n ISO_639_1 = ''\n ISO_639 = 'ven'\n ENGLISH_NAME = 'Venda'\n\n\nclass VIE:\n ISO_639_1 = ''\n ISO_639 = 'vie'\n ENGLISH_NAME = 'Vietnamese'\n\n\nclass VOL:\n ISO_639_1 = ''\n ISO_639 = 'vol'\n ENGLISH_NAME = 'Volapük'\n\n\nclass VOT:\n ISO_639_1 = ''\n ISO_639 = 'vot'\n ENGLISH_NAME = 'Votic'\n\n\nclass WAL:\n ISO_639_1 = ''\n ISO_639 = 'wal'\n ENGLISH_NAME = 'Wolaitta'\n\n\nclass WAR:\n ISO_639_1 = ''\n ISO_639 = 'war'\n ENGLISH_NAME = 'Waray'\n\n\nclass WAS:\n ISO_639_1 = ''\n ISO_639 = 'was'\n ENGLISH_NAME = 'Washo'\n\n\nclass WEL:\n ISO_639_1 = ''\n ISO_639 = 'wel'\n ENGLISH_NAME = 'Welsh'\n\n\nclass WLN:\n ISO_639_1 = ''\n ISO_639 = 'wln'\n ENGLISH_NAME = 'Walloon'\n\n\nclass WOL:\n ISO_639_1 = ''\n ISO_639 = 'wol'\n ENGLISH_NAME = 'Wolof'\n\n\nclass XAL:\n ISO_639_1 = ''\n ISO_639 = 'xal'\n ENGLISH_NAME = 'Kalmyk'\n\n\nclass XHO:\n ISO_639_1 = ''\n ISO_639 = 'xho'\n ENGLISH_NAME = 'Xhosa'\n\n\nclass YAO:\n ISO_639_1 = ''\n ISO_639 = 'yao'\n ENGLISH_NAME = 'Yao'\n\n\nclass YAP:\n ISO_639_1 = ''\n ISO_639 = 'yap'\n ENGLISH_NAME = 'Yapese'\n\n\nclass YID:\n ISO_639_1 = ''\n ISO_639 = 'yid'\n ENGLISH_NAME = 'Yiddish'\n\n\nclass YOR:\n ISO_639_1 = ''\n ISO_639 = 'yor'\n ENGLISH_NAME = 'Yoruba'\n\n\nclass ZAP:\n ISO_639_1 = ''\n ISO_639 = 'zap'\n ENGLISH_NAME = 'Zapotec'\n\n\nclass ZBL:\n ISO_639_1 = ''\n ISO_639 = 'zbl'\n ENGLISH_NAME = 'Blissymbols'\n\n\nclass ZEN:\n ISO_639_1 = ''\n ISO_639 = 'zen'\n ENGLISH_NAME = 'Zenaga'\n\n\nclass ZGH:\n ISO_639_1 = ''\n ISO_639 = 'zgh'\n ENGLISH_NAME = 'StandardMoroccanTamazight'\n\n\nclass ZHA:\n ISO_639_1 = ''\n ISO_639 = 'zha'\n ENGLISH_NAME = 'Zhuang'\n\n\nclass ZHS:\n ISO_639_1 = ''\n ISO_639 = 'zhs'\n ENGLISH_NAME = 'SimplifiedChinese'\n\n\nclass ZHT:\n ISO_639_1 = ''\n ISO_639 = 'zht'\n ENGLISH_NAME = 'TraditionalChinese'\n\n\nclass ZUL:\n ISO_639_1 = ''\n ISO_639 = 'zul'\n ENGLISH_NAME = 'Zulu'\n\n\nclass ZUN:\n ISO_639_1 = ''\n ISO_639 = 'zun'\n ENGLISH_NAME = 'Zuni'\n\n\nclass ZZA:\n ISO_639_1 = ''\n ISO_639 = 'zza'\n ENGLISH_NAME = 'Zaza'\n\n\ndef get_language_classes():\n import sys\n import inspect\n\n return inspect.getmembers(sys.modules[__name__], inspect.isclass)\n\n\n\nFile: chatterbot/__main__.py\n\nimport configparser\nimport sys\nimport os\n\n\ndef get_chatterbot_version():\n config = configparser.ConfigParser()\n\n current_directory = os.path.dirname(os.path.abspath(__file__))\n parent_directory = os.path.abspath(os.path.join(current_directory, os.pardir))\n config_file_path = os.path.join(parent_directory, 'setup.cfg')\n\n config.read(config_file_path)\n\n return config['chatterbot']['version']\n\n\nif __name__ == '__main__':\n if '--version' in sys.argv:\n print(get_chatterbot_version())\n\n\n\nFile: chatterbot/filters.py\n\ndef get_recent_repeated_responses(chatbot, conversation, sample=10, threshold=3, quantity=3):\n \"\"\"\n A filter that eliminates possibly repetitive responses to prevent\n a chat bot from repeating statements that it has recently said.\n \"\"\"\n from collections import Counter\n\n # Get the most recent statements from the conversation\n conversation_statements = list(chatbot.storage.filter(\n conversation=conversation,\n order_by=['id']\n ))[sample * -1:]\n\n text_of_recent_responses = [\n statement.text for statement in conversation_statements\n ]\n\n counter = Counter(text_of_recent_responses)\n\n # Find the n most common responses from the conversation\n most_common = counter.most_common(quantity)\n\n return [\n counted[0] for counted in most_common\n if counted[1] >= threshold\n ]\n\n\n\nFile: chatterbot/corpus.py\n\nimport os\nimport io\nimport glob\nfrom pathlib import Path\nfrom chatterbot.exceptions import OptionalDependencyImportError\n\ntry:\n from chatterbot_corpus.corpus import DATA_DIRECTORY\nexcept (ImportError, ModuleNotFoundError):\n # Default to the home directory of the current user\n DATA_DIRECTORY = os.path.join(\n Path.home(),\n 'chatterbot_corpus',\n 'data'\n )\n\n\nCORPUS_EXTENSION = 'yml'\n\n\ndef get_file_path(dotted_path, extension='json'):\n \"\"\"\n Reads a dotted file path and returns the file path.\n \"\"\"\n # If the operating system's file path seperator character is in the string\n if os.sep in dotted_path or '/' in dotted_path:\n # Assume the path is a valid file path\n return dotted_path\n\n parts = dotted_path.split('.')\n if parts[0] == 'chatterbot':\n parts.pop(0)\n parts[0] = DATA_DIRECTORY\n\n corpus_path = os.path.join(*parts)\n\n path_with_extension = '{}.{}'.format(corpus_path, extension)\n if os.path.exists(path_with_extension):\n corpus_path = path_with_extension\n\n return corpus_path\n\n\ndef read_corpus(file_name):\n \"\"\"\n Read and return the data from a corpus json file.\n \"\"\"\n try:\n import yaml\n except ImportError:\n message = (\n 'Unable to import \"yaml\".\\n'\n 'Please install \"pyyaml\" to enable chatterbot corpus functionality:\\n'\n 'pip3 install pyyaml'\n )\n raise OptionalDependencyImportError(message)\n\n with io.open(file_name, encoding='utf-8') as data_file:\n return yaml.safe_load(data_file)\n\n\ndef list_corpus_files(dotted_path):\n \"\"\"\n Return a list of file paths to each data file in the specified corpus.\n \"\"\"\n corpus_path = get_file_path(dotted_path, extension=CORPUS_EXTENSION)\n paths = []\n\n if os.path.isdir(corpus_path):\n paths = glob.glob(corpus_path + '/**/*.' + CORPUS_EXTENSION, recursive=True)\n else:\n paths.append(corpus_path)\n\n paths.sort()\n return paths\n\n\ndef load_corpus(*data_file_paths):\n \"\"\"\n Return the data contained within a specified corpus.\n \"\"\"\n for file_path in data_file_paths:\n corpus = []\n corpus_data = read_corpus(file_path)\n\n conversations = corpus_data.get('conversations', [])\n corpus.extend(conversations)\n\n categories = corpus_data.get('categories', [])\n\n yield corpus, categories, file_path\n\n\n\nFile: chatterbot/adapters.py\n\nclass Adapter(object):\n \"\"\"\n A superclass for all adapter classes.\n\n :param chatbot: A ChatBot instance.\n \"\"\"\n\n def __init__(self, chatbot, **kwargs):\n self.chatbot = chatbot\n\n class AdapterMethodNotImplementedError(NotImplementedError):\n \"\"\"\n An exception to be raised when an adapter method has not been implemented.\n Typically this indicates that the developer is expected to implement the\n method in a subclass.\n \"\"\"\n\n def __init__(self, message='This method must be overridden in a subclass method.'):\n \"\"\"\n Set the message for the exception.\n \"\"\"\n super().__init__(message)\n\n class InvalidAdapterTypeException(Exception):\n \"\"\"\n An exception to be raised when an adapter\n of an unexpected class type is received.\n \"\"\"\n pass\n\n\n\nFile: chatterbot/ext/__init__.py\n\n\n\n\nFile: chatterbot/ext/django_chatterbot/model_admin.py\n\nfrom django.contrib import admin\n\n\nclass StatementAdmin(admin.ModelAdmin):\n list_display = ('text', 'in_response_to', 'conversation', 'created_at', )\n list_filter = ('text', 'created_at', )\n search_fields = ('text', )\n\n\nclass TagAdmin(admin.ModelAdmin):\n list_display = ('name', )\n list_filter = ('name', )\n search_fields = ('name', )\n\n\n\nFile: chatterbot/ext/django_chatterbot/abstract_models.py\n\nfrom chatterbot.conversation import StatementMixin\nfrom chatterbot import constants\nfrom django.db import models\nfrom django.utils import timezone\nfrom django.conf import settings\n\n\nDJANGO_APP_NAME = constants.DEFAULT_DJANGO_APP_NAME\nSTATEMENT_MODEL = 'Statement'\nTAG_MODEL = 'Tag'\n\nif hasattr(settings, 'CHATTERBOT'):\n \"\"\"\n Allow related models to be overridden in the project settings.\n Default to the original settings if one is not defined.\n \"\"\"\n DJANGO_APP_NAME = settings.CHATTERBOT.get(\n 'django_app_name',\n DJANGO_APP_NAME\n )\n STATEMENT_MODEL = settings.CHATTERBOT.get(\n 'statement_model',\n STATEMENT_MODEL\n )\n\n\nclass AbstractBaseTag(models.Model):\n \"\"\"\n The abstract base tag allows other models to be created\n using the attributes that exist on the default models.\n \"\"\"\n\n name = models.SlugField(\n max_length=constants.TAG_NAME_MAX_LENGTH,\n unique=True\n )\n\n class Meta:\n abstract = True\n\n def __str__(self):\n return self.name\n\n\nclass AbstractBaseStatement(models.Model, StatementMixin):\n \"\"\"\n The abstract base statement allows other models to be created\n using the attributes that exist on the default models.\n \"\"\"\n\n text = models.CharField(\n max_length=constants.STATEMENT_TEXT_MAX_LENGTH\n )\n\n search_text = models.CharField(\n max_length=constants.STATEMENT_TEXT_MAX_LENGTH,\n blank=True\n )\n\n conversation = models.CharField(\n max_length=constants.CONVERSATION_LABEL_MAX_LENGTH\n )\n\n created_at = models.DateTimeField(\n default=timezone.now,\n help_text='The date and time that the statement was created at.'\n )\n\n in_response_to = models.CharField(\n max_length=constants.STATEMENT_TEXT_MAX_LENGTH,\n null=True\n )\n\n search_in_response_to = models.CharField(\n max_length=constants.STATEMENT_TEXT_MAX_LENGTH,\n blank=True\n )\n\n persona = models.CharField(\n max_length=constants.PERSONA_MAX_LENGTH\n )\n\n tags = models.ManyToManyField(\n TAG_MODEL,\n related_name='statements'\n )\n\n # This is the confidence with which the chat bot believes\n # this is an accurate response. This value is set when the\n # statement is returned by the chat bot.\n confidence = 0\n\n class Meta:\n abstract = True\n\n def __str__(self):\n if len(self.text.strip()) > 60:\n return '{}...'.format(self.text[:57])\n elif len(self.text.strip()) > 0:\n return self.text\n return '<empty>'\n\n def get_tags(self):\n \"\"\"\n Return the list of tags for this statement.\n (Overrides the method from StatementMixin)\n \"\"\"\n return list(self.tags.values_list('name', flat=True))\n\n def add_tags(self, *tags):\n \"\"\"\n Add a list of strings to the statement as tags.\n (Overrides the method from StatementMixin)\n \"\"\"\n for _tag in tags:\n self.tags.get_or_create(name=_tag)\n\n\n\nFile: chatterbot/ext/django_chatterbot/models.py\n\nfrom chatterbot.ext.django_chatterbot.abstract_models import AbstractBaseStatement, AbstractBaseTag\n\n\nclass Statement(AbstractBaseStatement):\n \"\"\"\n A statement represents a single spoken entity, sentence or\n phrase that someone can say.\n \"\"\"\n pass\n\n\nclass Tag(AbstractBaseTag):\n \"\"\"\n A label that categorizes a statement.\n \"\"\"\n pass\n\n\n\nFile: chatterbot/ext/django_chatterbot/__init__.py\n\ndefault_app_config = (\n 'chatterbot.ext.django_chatterbot.apps.DjangoChatterBotConfig'\n)\n\n\n\nFile: chatterbot/ext/django_chatterbot/apps.py\n\nfrom django.apps import AppConfig\n\n\nclass DjangoChatterBotConfig(AppConfig):\n\n name = 'chatterbot.ext.django_chatterbot'\n label = 'django_chatterbot'\n verbose_name = 'Django ChatterBot'\n\n\n\nFile: chatterbot/ext/django_chatterbot/admin.py\n\nfrom django.contrib import admin\nfrom chatterbot.ext.django_chatterbot.model_admin import StatementAdmin, TagAdmin\nfrom chatterbot.ext.django_chatterbot.models import Statement, Tag\n\n\nadmin.site.register(Statement, StatementAdmin)\nadmin.site.register(Tag, TagAdmin)\n\n\n\nFile: chatterbot/ext/django_chatterbot/settings.py\n\n\"\"\"\nDefault ChatterBot settings for Django.\n\"\"\"\nfrom django.conf import settings\nfrom chatterbot import constants\n\n\nCHATTERBOT_SETTINGS = getattr(settings, 'CHATTERBOT', {})\n\nCHATTERBOT_DEFAULTS = {\n 'name': 'ChatterBot',\n 'storage_adapter': 'chatterbot.storage.DjangoStorageAdapter',\n 'django_app_name': constants.DEFAULT_DJANGO_APP_NAME\n}\n\nCHATTERBOT = CHATTERBOT_DEFAULTS.copy()\nCHATTERBOT.update(CHATTERBOT_SETTINGS)\n\n\n\nFile: chatterbot/ext/django_chatterbot/migrations/0013_change_conversations.py\n\n# Generated by Django 1.11 on 2018-09-13 01:01\nfrom django.db import migrations, models\n\n\nclass Migration(migrations.Migration):\n\n dependencies = [\n ('django_chatterbot', '0012_statement_created_at'),\n ]\n\n operations = [\n migrations.RemoveField(\n model_name='conversation',\n name='responses',\n ),\n migrations.RemoveField(\n model_name='response',\n name='response',\n ),\n migrations.RemoveField(\n model_name='response',\n name='statement',\n ),\n migrations.AddField(\n model_name='statement',\n name='conversation',\n field=models.CharField(default='default', max_length=32),\n preserve_default=False,\n ),\n migrations.AddField(\n model_name='statement',\n name='in_response_to',\n field=models.CharField(max_length=400, null=True),\n ),\n migrations.AlterField(\n model_name='statement',\n name='text',\n field=models.CharField(max_length=400),\n ),\n migrations.DeleteModel(\n name='Conversation',\n ),\n migrations.DeleteModel(\n name='Response',\n ),\n ]\n\n\n\nFile: chatterbot/ext/django_chatterbot/migrations/0016_statement_stemmed_text.py\n\nfrom django.db import migrations, models\n\n\nclass Migration(migrations.Migration):\n\n dependencies = [\n ('django_chatterbot', '0015_statement_persona'),\n ]\n\n operations = [\n migrations.AddField(\n model_name='statement',\n name='search_text',\n field=models.CharField(blank=True, max_length=400),\n ),\n migrations.AddField(\n model_name='statement',\n name='search_in_response_to',\n field=models.CharField(blank=True, max_length=400),\n ),\n ]\n\n\n\nFile: chatterbot/ext/django_chatterbot/migrations/0018_text_max_length.py\n\nfrom django.db import migrations, models\n\n\nclass Migration(migrations.Migration):\n\n dependencies = [\n ('django_chatterbot', '0017_tags_unique'),\n ]\n\n operations = [\n migrations.AlterField(\n model_name='statement',\n name='in_response_to',\n field=models.CharField(max_length=255, null=True),\n ),\n migrations.AlterField(\n model_name='statement',\n name='search_in_response_to',\n field=models.CharField(blank=True, max_length=255),\n ),\n migrations.AlterField(\n model_name='statement',\n name='search_text',\n field=models.CharField(blank=True, max_length=255),\n ),\n migrations.AlterField(\n model_name='statement',\n name='text',\n field=models.CharField(max_length=255),\n ),\n ]\n\n\n\nFile: chatterbot/ext/django_chatterbot/migrations/0017_tags_unique.py\n\nfrom django.db import migrations, models\n\n\nclass Migration(migrations.Migration):\n\n dependencies = [\n ('django_chatterbot', '0016_statement_stemmed_text'),\n ]\n\n operations = [\n migrations.RemoveField(\n model_name='tag',\n name='statements',\n ),\n migrations.AddField(\n model_name='statement',\n name='tags',\n field=models.ManyToManyField(\n related_name='statements',\n to='django_chatterbot.Tag'\n ),\n ),\n migrations.AlterField(\n model_name='tag',\n name='name',\n field=models.SlugField(unique=True),\n ),\n ]\n\n\n\nFile: chatterbot/ext/django_chatterbot/migrations/0004_rename_in_response_to.py\n\n# Generated by Django 1.10.3 on 2016-12-04 23:52\nfrom django.db import migrations, models\nimport django.db.models.deletion\n\n\nclass Migration(migrations.Migration):\n\n dependencies = [\n ('django_chatterbot', '0003_change_occurrence_default'),\n ]\n\n operations = [\n migrations.AlterField(\n model_name='response',\n name='statement',\n field=models.ForeignKey(on_delete=django.db.models.deletion.CASCADE, related_name='in_response', to='django_chatterbot.Statement'),\n ),\n migrations.AlterField(\n model_name='response',\n name='response',\n field=models.ForeignKey(on_delete=django.db.models.deletion.CASCADE, related_name='responses', to='django_chatterbot.Statement'),\n ),\n ]\n\n\n\nFile: chatterbot/ext/django_chatterbot/migrations/0007_response_created_at.py\n\n# Generated by Django 1.11 on 2017-07-18 00:16\nfrom django.db import migrations, models\nimport django.utils.timezone\n\n\nclass Migration(migrations.Migration):\n\n dependencies = [\n ('django_chatterbot', '0006_create_conversation'),\n ]\n\n operations = [\n migrations.AddField(\n model_name='response',\n name='created_at',\n field=models.DateTimeField(\n default=django.utils.timezone.now,\n help_text='The date and time that this response was created at.'\n ),\n ),\n ]\n\n\n\nFile: chatterbot/ext/django_chatterbot/migrations/0008_update_conversations.py\n\n# Generated by Django 1.11 on 2017-07-18 11:25\nfrom django.db import migrations, models\n\n\nclass Migration(migrations.Migration):\n\n dependencies = [\n ('django_chatterbot', '0007_response_created_at'),\n ]\n\n operations = [\n migrations.RemoveField(\n model_name='conversation',\n name='statements',\n ),\n migrations.RemoveField(\n model_name='response',\n name='occurrence',\n ),\n migrations.RemoveField(\n model_name='statement',\n name='created_at',\n ),\n migrations.AddField(\n model_name='conversation',\n name='responses',\n field=models.ManyToManyField(help_text='The responses in this conversation.', related_name='conversations', to='django_chatterbot.Response'),\n ),\n ]\n\n\n\nFile: chatterbot/ext/django_chatterbot/migrations/0010_statement_text.py\n\n# Generated by Django 1.11.4 on 2017-08-16 00:56\nfrom django.db import migrations, models\n\n\nclass Migration(migrations.Migration):\n\n dependencies = [\n ('django_chatterbot', '0009_tags'),\n ]\n\n operations = [\n migrations.AlterField(\n model_name='statement',\n name='text',\n field=models.CharField(max_length=400, unique=True),\n ),\n ]\n\n\n\nFile: chatterbot/ext/django_chatterbot/migrations/0012_statement_created_at.py\n\nfrom django.db import migrations, models\nimport django.utils.timezone\n\n\nclass Migration(migrations.Migration):\n\n dependencies = [\n ('django_chatterbot', '0011_blank_extra_data'),\n ]\n\n operations = [\n migrations.AddField(\n model_name='statement',\n name='created_at',\n field=models.DateTimeField(\n default=django.utils.timezone.now,\n help_text='The date and time that the statement was created at.'\n ),\n ),\n ]\n\n\n\nFile: chatterbot/ext/django_chatterbot/migrations/__init__.py\n\n\n\n\nFile: chatterbot/ext/django_chatterbot/migrations/0005_statement_created_at.py\n\n# Generated by Django 1.10.1 on 2016-12-29 19:20\nfrom django.db import migrations, models\nimport django.utils.timezone\n\n\nclass Migration(migrations.Migration):\n\n dependencies = [\n ('django_chatterbot', '0004_rename_in_response_to'),\n ]\n\n operations = [\n migrations.AddField(\n model_name='statement',\n name='created_at',\n field=models.DateTimeField(\n default=django.utils.timezone.now,\n help_text='The date and time that this statement was created at.'\n ),\n ),\n ]\n\n\n\nFile: chatterbot/ext/django_chatterbot/migrations/0006_create_conversation.py\n\n# Generated by Django 1.9 on 2017-01-17 07:02\nfrom django.db import migrations, models\nimport django.db.models.deletion\nimport django.utils.timezone\n\n\nclass Migration(migrations.Migration):\n\n dependencies = [\n ('django_chatterbot', '0005_statement_created_at'),\n ]\n\n operations = [\n migrations.CreateModel(\n name='Conversation',\n fields=[\n ('id', models.AutoField(auto_created=True, primary_key=True, serialize=False, verbose_name='ID')),\n ],\n ),\n migrations.AlterField(\n model_name='statement',\n name='created_at',\n field=models.DateTimeField(default=django.utils.timezone.now, help_text='The date and time that this statement was created at.'),\n ),\n migrations.AddField(\n model_name='conversation',\n name='statements',\n field=models.ManyToManyField(help_text='The statements in this conversation.', related_name='conversation', to='django_chatterbot.Statement'),\n ),\n ]\n\n\n\nFile: chatterbot/ext/django_chatterbot/migrations/0002_statement_extra_data.py\n\n# Generated by Django 1.10.2 on 2016-10-30 12:13\nfrom django.db import migrations, models\n\n\nclass Migration(migrations.Migration):\n\n dependencies = [\n ('django_chatterbot', '0001_initial'),\n ]\n\n operations = [\n migrations.AddField(\n model_name='statement',\n name='extra_data',\n field=models.CharField(default='{}', max_length=500),\n preserve_default=False,\n ),\n ]\n\n\n\nFile: chatterbot/ext/django_chatterbot/migrations/0011_blank_extra_data.py\n\n# Generated by Django 1.11.4 on 2017-08-20 13:55\nfrom django.db import migrations, models\n\n\nclass Migration(migrations.Migration):\n\n dependencies = [\n ('django_chatterbot', '0010_statement_text'),\n ]\n\n operations = [\n migrations.AlterField(\n model_name='statement',\n name='extra_data',\n field=models.CharField(blank=True, max_length=500),\n ),\n ]\n\n\n\nFile: chatterbot/ext/django_chatterbot/migrations/0009_tags.py\n\n# Generated by Django 1.11a1 on 2017-07-07 00:12\nfrom django.db import migrations, models\n\n\nclass Migration(migrations.Migration):\n\n dependencies = [\n ('django_chatterbot', '0008_update_conversations'),\n ]\n\n operations = [\n migrations.CreateModel(\n name='Tag',\n fields=[\n ('id', models.AutoField(auto_created=True, primary_key=True, serialize=False, verbose_name='ID')),\n ('name', models.SlugField()),\n ],\n options={\n 'abstract': False,\n },\n ),\n migrations.AlterField(\n model_name='statement',\n name='text',\n field=models.CharField(max_length=255, unique=True),\n ),\n migrations.AddField(\n model_name='tag',\n name='statements',\n field=models.ManyToManyField(related_name='tags', to='django_chatterbot.Statement'),\n ),\n ]\n\n\n\nFile: chatterbot/ext/django_chatterbot/migrations/0014_remove_statement_extra_data.py\n\nfrom django.db import migrations\n\n\nclass Migration(migrations.Migration):\n\n dependencies = [\n ('django_chatterbot', '0013_change_conversations'),\n ]\n\n operations = [\n migrations.RemoveField(\n model_name='statement',\n name='extra_data',\n ),\n ]\n\n\n\nFile: chatterbot/ext/django_chatterbot/migrations/0003_change_occurrence_default.py\n\n# Generated by Django 1.9 on 2016-12-12 00:06\nfrom django.db import migrations, models\n\n\nclass Migration(migrations.Migration):\n\n dependencies = [\n ('django_chatterbot', '0002_statement_extra_data'),\n ]\n\n operations = [\n migrations.AlterField(\n model_name='response',\n name='occurrence',\n field=models.PositiveIntegerField(default=1),\n ),\n ]\n\n\n\nFile: chatterbot/ext/django_chatterbot/migrations/0001_initial.py\n\nfrom django.db import migrations, models\nimport django.db.models.deletion\n\n\nclass Migration(migrations.Migration):\n\n initial = True\n\n dependencies = []\n\n operations = [\n migrations.CreateModel(\n name='Response',\n fields=[\n ('id', models.AutoField(auto_created=True, primary_key=True, serialize=False, verbose_name='ID')),\n ('occurrence', models.PositiveIntegerField(default=0)),\n ],\n ),\n migrations.CreateModel(\n name='Statement',\n fields=[\n ('id', models.AutoField(auto_created=True, primary_key=True, serialize=False, verbose_name='ID')),\n ('text', models.CharField(max_length=255, unique=True)),\n ],\n ),\n migrations.AddField(\n model_name='response',\n name='response',\n field=models.ForeignKey(on_delete=django.db.models.deletion.CASCADE, related_name='+', to='django_chatterbot.Statement'),\n ),\n migrations.AddField(\n model_name='response',\n name='statement',\n field=models.ForeignKey(on_delete=django.db.models.deletion.CASCADE, related_name='in_response_to', to='django_chatterbot.Statement'),\n ),\n ]\n\n\n\nFile: chatterbot/ext/django_chatterbot/migrations/0015_statement_persona.py\n\nfrom django.db import migrations, models\n\n\nclass Migration(migrations.Migration):\n\n dependencies = [\n ('django_chatterbot', '0014_remove_statement_extra_data'),\n ]\n\n operations = [\n migrations.AddField(\n model_name='statement',\n name='persona',\n field=models.CharField(default='', max_length=50),\n preserve_default=False,\n ),\n ]\n\n\n\nFile: chatterbot/ext/sqlalchemy_app/models.py\n\nfrom sqlalchemy import Table, Column, Integer, String, DateTime, ForeignKey\nfrom sqlalchemy.orm import relationship\nfrom sqlalchemy.sql import func\nfrom sqlalchemy.ext.declarative import declared_attr, declarative_base\n\nfrom chatterbot.conversation import StatementMixin\nfrom chatterbot import constants\n\n\nclass ModelBase(object):\n \"\"\"\n An augmented base class for SqlAlchemy models.\n \"\"\"\n\n @declared_attr\n def __tablename__(cls):\n \"\"\"\n Return the lowercase class name as the name of the table.\n \"\"\"\n return cls.__name__.lower()\n\n id = Column(\n Integer,\n primary_key=True,\n autoincrement=True\n )\n\n\nBase = declarative_base(cls=ModelBase)\n\n\ntag_association_table = Table(\n 'tag_association',\n Base.metadata,\n Column('tag_id', Integer, ForeignKey('tag.id')),\n Column('statement_id', Integer, ForeignKey('statement.id'))\n)\n\n\nclass Tag(Base):\n \"\"\"\n A tag that describes a statement.\n \"\"\"\n\n name = Column(\n String(constants.TAG_NAME_MAX_LENGTH),\n unique=True\n )\n\n\nclass Statement(Base, StatementMixin):\n \"\"\"\n A Statement represents a sentence or phrase.\n \"\"\"\n\n confidence = 0\n\n text = Column(\n String(constants.STATEMENT_TEXT_MAX_LENGTH)\n )\n\n search_text = Column(\n String(constants.STATEMENT_TEXT_MAX_LENGTH),\n nullable=False,\n server_default=''\n )\n\n conversation = Column(\n String(constants.CONVERSATION_LABEL_MAX_LENGTH),\n nullable=False,\n server_default=''\n )\n\n created_at = Column(\n DateTime(timezone=True),\n server_default=func.now()\n )\n\n tags = relationship(\n 'Tag',\n secondary=lambda: tag_association_table,\n backref='statements'\n )\n\n in_response_to = Column(\n String(constants.STATEMENT_TEXT_MAX_LENGTH),\n nullable=True\n )\n\n search_in_response_to = Column(\n String(constants.STATEMENT_TEXT_MAX_LENGTH),\n nullable=False,\n server_default=''\n )\n\n persona = Column(\n String(constants.PERSONA_MAX_LENGTH),\n nullable=False,\n server_default=''\n )\n\n def get_tags(self):\n \"\"\"\n Return a list of tags for this statement.\n \"\"\"\n return [tag.name for tag in self.tags]\n\n def add_tags(self, *tags):\n \"\"\"\n Add a list of strings to the statement as tags.\n \"\"\"\n self.tags.extend([\n Tag(name=tag) for tag in tags\n ])\n\n\n\nFile: chatterbot/ext/sqlalchemy_app/__init__.py\n\n\n\n\nFile: chatterbot/logic/logic_adapter.py\n\nfrom chatterbot.adapters import Adapter\nfrom chatterbot.storage import StorageAdapter\nfrom chatterbot.search import IndexedTextSearch\nfrom chatterbot.conversation import Statement\n\n\nclass LogicAdapter(Adapter):\n \"\"\"\n This is an abstract class that represents the interface\n that all logic adapters should implement.\n\n :param search_algorithm_name: The name of the search algorithm that should\n be used to search for close matches to the provided input.\n Defaults to the value of ``Search.name``.\n\n :param maximum_similarity_threshold:\n The maximum amount of similarity between two statement that is required\n before the search process is halted. The search for a matching statement\n will continue until a statement with a greater than or equal similarity\n is found or the search set is exhausted.\n Defaults to 0.95\n\n :param response_selection_method:\n The a response selection method.\n Defaults to ``get_first_response``\n :type response_selection_method: collections.abc.Callable\n\n :param default_response:\n The default response returned by this logic adaper\n if there is no other possible response to return.\n :type default_response: str or list or tuple\n \"\"\"\n\n def __init__(self, chatbot, **kwargs):\n super().__init__(chatbot, **kwargs)\n from chatterbot.response_selection import get_first_response\n\n self.search_algorithm_name = kwargs.get(\n 'search_algorithm_name',\n IndexedTextSearch.name\n )\n\n self.search_algorithm = self.chatbot.search_algorithms[\n self.search_algorithm_name\n ]\n\n self.maximum_similarity_threshold = kwargs.get(\n 'maximum_similarity_threshold', 0.95\n )\n\n # By default, select the first available response\n self.select_response = kwargs.get(\n 'response_selection_method',\n get_first_response\n )\n\n default_responses = kwargs.get('default_response', [])\n\n # Convert a single string into a list\n if isinstance(default_responses, str):\n default_responses = [\n default_responses\n ]\n\n self.default_responses = [\n Statement(text=default) for default in default_responses\n ]\n\n def can_process(self, statement):\n \"\"\"\n A preliminary check that is called to determine if a\n logic adapter can process a given statement. By default,\n this method returns true but it can be overridden in\n child classes as needed.\n\n :rtype: bool\n \"\"\"\n return True\n\n def process(self, statement, additional_response_selection_parameters=None):\n \"\"\"\n Override this method and implement your logic for selecting a response to an input statement.\n\n A confidence value and the selected response statement should be returned.\n The confidence value represents a rating of how accurate the logic adapter\n expects the selected response to be. Confidence scores are used to select\n the best response from multiple logic adapters.\n\n The confidence value should be a number between 0 and 1 where 0 is the\n lowest confidence level and 1 is the highest.\n\n :param statement: An input statement to be processed by the logic adapter.\n :type statement: Statement\n\n :param additional_response_selection_parameters: Parameters to be used when\n filtering results to choose a response from.\n :type additional_response_selection_parameters: dict\n\n :rtype: Statement\n \"\"\"\n raise self.AdapterMethodNotImplementedError()\n\n def get_default_response(self, input_statement):\n \"\"\"\n This method is called when a logic adapter is unable to generate any\n other meaningful response.\n \"\"\"\n from random import choice\n\n if self.default_responses:\n response = choice(self.default_responses)\n else:\n try:\n response = self.chatbot.storage.get_random()\n except StorageAdapter.EmptyDatabaseException:\n response = input_statement\n\n self.chatbot.logger.info(\n 'No known response to the input was found. Selecting a random response.'\n )\n\n # Set confidence to zero because a random response is selected\n response.confidence = 0\n\n return response\n\n @property\n def class_name(self):\n \"\"\"\n Return the name of the current logic adapter class.\n This is typically used for logging and debugging.\n \"\"\"\n return str(self.__class__.__name__)\n\n\n\nFile: chatterbot/logic/__init__.py\n\nfrom chatterbot.logic.logic_adapter import LogicAdapter\nfrom chatterbot.logic.best_match import BestMatch\nfrom chatterbot.logic.mathematical_evaluation import MathematicalEvaluation\nfrom chatterbot.logic.specific_response import SpecificResponseAdapter\nfrom chatterbot.logic.time_adapter import TimeLogicAdapter\nfrom chatterbot.logic.unit_conversion import UnitConversion\n\n__all__ = (\n 'LogicAdapter',\n 'BestMatch',\n 'MathematicalEvaluation',\n 'SpecificResponseAdapter',\n 'TimeLogicAdapter',\n 'UnitConversion',\n)\n\n\n\nFile: chatterbot/logic/best_match.py\n\nfrom chatterbot.logic import LogicAdapter\nfrom chatterbot import filters\n\n\nclass BestMatch(LogicAdapter):\n \"\"\"\n A logic adapter that returns a response based on known responses to\n the closest matches to the input statement.\n\n :param excluded_words:\n The excluded_words parameter allows a list of words to be set that will\n prevent the logic adapter from returning statements that have text\n containing any of those words. This can be useful for preventing your\n chat bot from saying swears when it is being demonstrated in front of\n an audience.\n Defaults to None\n :type excluded_words: list\n \"\"\"\n\n def __init__(self, chatbot, **kwargs):\n super().__init__(chatbot, **kwargs)\n\n self.excluded_words = kwargs.get('excluded_words')\n\n def process(self, input_statement, additional_response_selection_parameters=None):\n search_results = self.search_algorithm.search(input_statement)\n\n # Use the input statement as the closest match if no other results are found\n closest_match = next(search_results, input_statement)\n\n # Search for the closest match to the input statement\n for result in search_results:\n closest_match = result\n\n # Stop searching if a match that is close enough is found\n if result.confidence >= self.maximum_similarity_threshold:\n break\n\n self.chatbot.logger.info('Using \"{}\" as a close match to \"{}\" with a confidence of {}'.format(\n closest_match.text, input_statement.text, closest_match.confidence\n ))\n\n recent_repeated_responses = filters.get_recent_repeated_responses(\n self.chatbot,\n input_statement.conversation\n )\n\n for index, recent_repeated_response in enumerate(recent_repeated_responses):\n self.chatbot.logger.info('{}. Excluding recent repeated response of \"{}\"'.format(\n index, recent_repeated_response\n ))\n\n response_selection_parameters = {\n 'search_in_response_to': closest_match.search_text,\n 'exclude_text': recent_repeated_responses,\n 'exclude_text_words': self.excluded_words\n }\n\n alternate_response_selection_parameters = {\n 'search_in_response_to': self.chatbot.storage.tagger.get_text_index_string(\n input_statement.text\n ),\n 'exclude_text': recent_repeated_responses,\n 'exclude_text_words': self.excluded_words\n }\n\n if additional_response_selection_parameters:\n response_selection_parameters.update(additional_response_selection_parameters)\n alternate_response_selection_parameters.update(additional_response_selection_parameters)\n\n # Get all statements that are in response to the closest match\n response_list = list(self.chatbot.storage.filter(**response_selection_parameters))\n\n alternate_response_list = []\n\n if not response_list:\n self.chatbot.logger.info('No responses found. Generating alternate response list.')\n alternate_response_list = list(self.chatbot.storage.filter(**alternate_response_selection_parameters))\n\n if response_list:\n self.chatbot.logger.info(\n 'Selecting response from {} optimal responses.'.format(\n len(response_list)\n )\n )\n\n response = self.select_response(\n input_statement,\n response_list,\n self.chatbot.storage\n )\n\n response.confidence = closest_match.confidence\n self.chatbot.logger.info('Response selected. Using \"{}\"'.format(response.text))\n elif alternate_response_list:\n '''\n The case where there was no responses returned for the selected match\n but a value exists for the statement the match is in response to.\n '''\n self.chatbot.logger.info(\n 'Selecting response from {} optimal alternate responses.'.format(\n len(alternate_response_list)\n )\n )\n response = self.select_response(\n input_statement,\n alternate_response_list,\n self.chatbot.storage\n )\n\n response.confidence = closest_match.confidence\n self.chatbot.logger.info('Alternate response selected. Using \"{}\"'.format(response.text))\n else:\n response = self.get_default_response(input_statement)\n\n return response\n\n\n\nFile: chatterbot/logic/mathematical_evaluation.py\n\nfrom chatterbot.logic import LogicAdapter\nfrom chatterbot.conversation import Statement\nfrom chatterbot import languages\n\n\nclass MathematicalEvaluation(LogicAdapter):\n \"\"\"\n The MathematicalEvaluation logic adapter parses input to determine\n whether the user is asking a question that requires math to be done.\n If so, the equation is extracted from the input and returned with\n the evaluated result.\n\n For example:\n User: 'What is three plus five?'\n Bot: 'Three plus five equals eight'\n\n :kwargs:\n * *language* (``object``) --\n The language is set to ``chatterbot.languages.ENG`` for English by default.\n \"\"\"\n\n def __init__(self, chatbot, **kwargs):\n super().__init__(chatbot, **kwargs)\n\n self.language = kwargs.get('language', languages.ENG)\n self.cache = {}\n\n def can_process(self, statement):\n \"\"\"\n Determines whether it is appropriate for this\n adapter to respond to the user input.\n \"\"\"\n response = self.process(statement)\n self.cache[statement.text] = response\n return response.confidence == 1\n\n def process(self, statement, additional_response_selection_parameters=None):\n \"\"\"\n Takes a statement string.\n Returns the equation from the statement with the mathematical terms solved.\n \"\"\"\n from mathparse import mathparse\n\n input_text = statement.text\n\n # Use the result cached by the process method if it exists\n if input_text in self.cache:\n cached_result = self.cache[input_text]\n self.cache = {}\n return cached_result\n\n # Getting the mathematical terms within the input statement\n expression = mathparse.extract_expression(input_text, language=self.language.ISO_639.upper())\n\n response = Statement(text=expression)\n\n try:\n response.text = '{} = {}'.format(\n response.text,\n mathparse.parse(expression, language=self.language.ISO_639.upper())\n )\n\n # The confidence is 1 if the expression could be evaluated\n response.confidence = 1\n except mathparse.PostfixTokenEvaluationException:\n response.confidence = 0\n\n return response\n\n\n\nFile: chatterbot/logic/unit_conversion.py\n\nfrom chatterbot.logic import LogicAdapter\nfrom chatterbot.conversation import Statement\nfrom chatterbot.exceptions import OptionalDependencyImportError\nfrom chatterbot import languages\nfrom chatterbot import parsing\nfrom mathparse import mathparse\nimport re\n\n\nclass UnitConversion(LogicAdapter):\n \"\"\"\n The UnitConversion logic adapter parse inputs to convert values\n between several metric units.\n\n For example:\n User: 'How many meters are in one kilometer?'\n Bot: '1000.0'\n\n :kwargs:\n * *language* (``object``) --\n The language is set to ``chatterbot.languages.ENG`` for English by default.\n \"\"\"\n\n def __init__(self, chatbot, **kwargs):\n super().__init__(chatbot, **kwargs)\n try:\n from pint import UnitRegistry\n except ImportError:\n message = (\n 'Unable to import \"pint\".\\n'\n 'Please install \"pint\" before using the UnitConversion logic adapter:\\n'\n 'pip3 install pint'\n )\n raise OptionalDependencyImportError(message)\n\n self.language = kwargs.get('language', languages.ENG)\n self.cache = {}\n self.patterns = [\n (\n re.compile(r'''\n (([Hh]ow\\s+many)\\s+\n (?P<target>\\S+)\\s+ # meter, celsius, hours\n ((are)*\\s*in)\\s+\n (?P<number>([+-]?\\d+(?:\\.\\d+)?)|(a|an)|(%s[-\\s]?)+)\\s+\n (?P<from>\\S+)\\s*) # meter, celsius, hours\n ''' % (parsing.numbers),\n (re.VERBOSE | re.IGNORECASE)\n ),\n lambda m: self.handle_matches(m)\n ),\n (\n re.compile(r'''\n ((?P<number>([+-]?\\d+(?:\\.\\d+)?)|(%s[-\\s]?)+)\\s+\n (?P<from>\\S+)\\s+ # meter, celsius, hours\n (to)\\s+\n (?P<target>\\S+)\\s*) # meter, celsius, hours\n ''' % (parsing.numbers),\n (re.VERBOSE | re.IGNORECASE)\n ),\n lambda m: self.handle_matches(m)\n ),\n (\n re.compile(r'''\n ((?P<number>([+-]?\\d+(?:\\.\\d+)?)|(a|an)|(%s[-\\s]?)+)\\s+\n (?P<from>\\S+)\\s+ # meter, celsius, hours\n (is|are)\\s+\n (how\\s+many)*\\s+\n (?P<target>\\S+)\\s*) # meter, celsius, hours\n ''' % (parsing.numbers),\n (re.VERBOSE | re.IGNORECASE)\n ),\n lambda m: self.handle_matches(m)\n )\n ]\n self.unit_registry = UnitRegistry()\n\n def get_unit(self, unit_variations):\n \"\"\"\n Get the first match unit metric object supported by pint library\n given a variation of unit metric names (Ex:['HOUR', 'hour']).\n\n :param unit_variations: A list of strings with names of units\n :type unit_variations: str\n \"\"\"\n for unit in unit_variations:\n try:\n return getattr(self.unit_registry, unit)\n except Exception:\n continue\n return None\n\n def get_valid_units(self, from_unit, target_unit):\n \"\"\"\n Returns the first match `pint.unit.Unit` object for from_unit and\n target_unit strings from a possible variation of metric unit names\n supported by pint library.\n\n :param from_unit: source metric unit\n :type from_unit: str\n\n :param from_unit: target metric unit\n :type from_unit: str\n \"\"\"\n from_unit_variations = [from_unit.lower(), from_unit.upper()]\n target_unit_variations = [target_unit.lower(), target_unit.upper()]\n from_unit = self.get_unit(from_unit_variations)\n target_unit = self.get_unit(target_unit_variations)\n return from_unit, target_unit\n\n def handle_matches(self, match):\n \"\"\"\n Returns a response statement from a matched input statement.\n\n :param match: It is a valid matched pattern from the input statement\n :type: `_sre.SRE_Match`\n \"\"\"\n response = Statement(text='')\n\n from_parsed = match.group(\"from\")\n target_parsed = match.group(\"target\")\n n_statement = match.group(\"number\")\n\n if n_statement == 'a' or n_statement == 'an':\n n_statement = '1.0'\n\n n = mathparse.parse(n_statement, self.language.ISO_639.upper())\n\n from_parsed, target_parsed = self.get_valid_units(from_parsed, target_parsed)\n\n if from_parsed is None or target_parsed is None:\n response.confidence = 0.0\n else:\n from_value = self.unit_registry.Quantity(float(n), from_parsed)\n target_value = from_value.to(target_parsed)\n response.confidence = 1.0\n response.text = str(target_value.magnitude)\n\n return response\n\n def can_process(self, statement):\n response = self.process(statement)\n self.cache[statement.text] = response\n return response.confidence == 1.0\n\n def process(self, statement, additional_response_selection_parameters=None):\n response = Statement(text='')\n input_text = statement.text\n try:\n # Use the result cached by the process method if it exists\n if input_text in self.cache:\n response = self.cache[input_text]\n self.cache = {}\n return response\n\n for pattern, func in self.patterns:\n p = pattern.match(input_text)\n if p is not None:\n response = func(p)\n if response.confidence == 1.0:\n break\n except Exception:\n response.confidence = 0.0\n finally:\n return response\n\n\n\nFile: chatterbot/logic/specific_response.py\n\nfrom chatterbot.logic import LogicAdapter\n\n\nclass SpecificResponseAdapter(LogicAdapter):\n \"\"\"\n Return a specific response to a specific input.\n\n :kwargs:\n * *input_text* (``str``) --\n The input text that triggers this logic adapter.\n * *output_text* (``str``) --\n The output text returned by this logic adapter.\n \"\"\"\n\n def __init__(self, chatbot, **kwargs):\n super().__init__(chatbot, **kwargs)\n from chatterbot.conversation import Statement\n\n self.input_text = kwargs.get('input_text')\n\n output_text = kwargs.get('output_text')\n self.response_statement = Statement(text=output_text)\n\n def can_process(self, statement):\n if statement.text == self.input_text:\n return True\n\n return False\n\n def process(self, statement, additional_response_selection_parameters=None):\n\n if statement.text == self.input_text:\n self.response_statement.confidence = 1\n else:\n self.response_statement.confidence = 0\n\n return self.response_statement\n\n\n\nFile: chatterbot/logic/time_adapter.py\n\nfrom datetime import datetime\nfrom chatterbot.logic import LogicAdapter\nfrom chatterbot.conversation import Statement\nfrom chatterbot.exceptions import OptionalDependencyImportError\n\n\nclass TimeLogicAdapter(LogicAdapter):\n \"\"\"\n The TimeLogicAdapter returns the current time.\n\n :kwargs:\n * *positive* (``list``) --\n The time-related questions used to identify time questions.\n Defaults to a list of English sentences.\n * *negative* (``list``) --\n The non-time-related questions used to identify time questions.\n Defaults to a list of English sentences.\n \"\"\"\n\n def __init__(self, chatbot, **kwargs):\n super().__init__(chatbot, **kwargs)\n try:\n from nltk import NaiveBayesClassifier\n except ImportError:\n message = (\n 'Unable to import \"nltk\".\\n'\n 'Please install \"nltk\" before using the TimeLogicAdapter:\\n'\n 'pip3 install nltk'\n )\n raise OptionalDependencyImportError(message)\n\n self.positive = kwargs.get('positive', [\n 'what time is it',\n 'hey what time is it',\n 'do you have the time',\n 'do you know the time',\n 'do you know what time it is',\n 'what is the time'\n ])\n\n self.negative = kwargs.get('negative', [\n 'it is time to go to sleep',\n 'what is your favorite color',\n 'i had a great time',\n 'thyme is my favorite herb',\n 'do you have time to look at my essay',\n 'how do you have the time to do all this'\n 'what is it'\n ])\n\n labeled_data = (\n [\n (name, 0) for name in self.negative\n ] + [\n (name, 1) for name in self.positive\n ]\n )\n\n train_set = [\n (self.time_question_features(text), n) for (text, n) in labeled_data\n ]\n\n self.classifier = NaiveBayesClassifier.train(train_set)\n\n def time_question_features(self, text):\n \"\"\"\n Provide an analysis of significant features in the string.\n \"\"\"\n features = {}\n\n # A list of all words from the known sentences\n all_words = \" \".join(self.positive + self.negative).split()\n\n # A list of the first word in each of the known sentence\n all_first_words = []\n for sentence in self.positive + self.negative:\n all_first_words.append(\n sentence.split(' ', 1)[0]\n )\n\n for word in text.split():\n features['first_word({})'.format(word)] = (word in all_first_words)\n\n for word in text.split():\n features['contains({})'.format(word)] = (word in all_words)\n\n for letter in 'abcdefghijklmnopqrstuvwxyz':\n features['count({})'.format(letter)] = text.lower().count(letter)\n features['has({})'.format(letter)] = (letter in text.lower())\n\n return features\n\n def process(self, statement, additional_response_selection_parameters=None):\n now = datetime.now()\n\n time_features = self.time_question_features(statement.text.lower())\n confidence = self.classifier.classify(time_features)\n response = Statement(text='The current time is ' + now.strftime('%I:%M %p'))\n\n response.confidence = confidence\n return response\n\n\n\nFile: chatterbot/storage/sql_storage.py\n\nfrom chatterbot.storage import StorageAdapter\n\n\nclass SQLStorageAdapter(StorageAdapter):\n \"\"\"\n The SQLStorageAdapter allows ChatterBot to store conversation\n data in any database supported by the SQL Alchemy ORM.\n\n All parameters are optional, by default a sqlite database is used.\n\n It will check if tables are present, if they are not, it will attempt\n to create the required tables.\n\n :keyword database_uri: eg: sqlite:///database_test.sqlite3',\n The database_uri can be specified to choose database driver.\n :type database_uri: str\n \"\"\"\n\n def __init__(self, **kwargs):\n super().__init__(**kwargs)\n\n from sqlalchemy import create_engine\n from sqlalchemy.orm import sessionmaker\n\n self.database_uri = kwargs.get('database_uri', False)\n\n # None results in a sqlite in-memory database as the default\n if self.database_uri is None:\n self.database_uri = 'sqlite://'\n\n # Create a file database if the database is not a connection string\n if not self.database_uri:\n self.database_uri = 'sqlite:///db.sqlite3'\n\n self.engine = create_engine(self.database_uri, convert_unicode=True)\n\n if self.database_uri.startswith('sqlite://'):\n from sqlalchemy.engine import Engine\n from sqlalchemy import event\n\n @event.listens_for(Engine, 'connect')\n def set_sqlite_pragma(dbapi_connection, connection_record):\n dbapi_connection.execute('PRAGMA journal_mode=WAL')\n dbapi_connection.execute('PRAGMA synchronous=NORMAL')\n\n if not self.engine.dialect.has_table(self.engine, 'Statement'):\n self.create_database()\n\n self.Session = sessionmaker(bind=self.engine, expire_on_commit=True)\n\n def get_statement_model(self):\n \"\"\"\n Return the statement model.\n \"\"\"\n from chatterbot.ext.sqlalchemy_app.models import Statement\n return Statement\n\n def get_tag_model(self):\n \"\"\"\n Return the conversation model.\n \"\"\"\n from chatterbot.ext.sqlalchemy_app.models import Tag\n return Tag\n\n def model_to_object(self, statement):\n from chatterbot.conversation import Statement as StatementObject\n\n return StatementObject(**statement.serialize())\n\n def count(self):\n \"\"\"\n Return the number of entries in the database.\n \"\"\"\n Statement = self.get_model('statement')\n\n session = self.Session()\n statement_count = session.query(Statement).count()\n session.close()\n return statement_count\n\n def remove(self, statement_text):\n \"\"\"\n Removes the statement that matches the input text.\n Removes any responses from statements where the response text matches\n the input text.\n \"\"\"\n Statement = self.get_model('statement')\n session = self.Session()\n\n query = session.query(Statement).filter_by(text=statement_text)\n record = query.first()\n\n session.delete(record)\n\n self._session_finish(session)\n\n def filter(self, **kwargs):\n \"\"\"\n Returns a list of objects from the database.\n The kwargs parameter can contain any number\n of attributes. Only objects which contain all\n listed attributes and in which all values match\n for all listed attributes will be returned.\n \"\"\"\n from sqlalchemy import or_\n\n Statement = self.get_model('statement')\n Tag = self.get_model('tag')\n\n session = self.Session()\n\n page_size = kwargs.pop('page_size', 1000)\n order_by = kwargs.pop('order_by', None)\n tags = kwargs.pop('tags', [])\n exclude_text = kwargs.pop('exclude_text', None)\n exclude_text_words = kwargs.pop('exclude_text_words', [])\n persona_not_startswith = kwargs.pop('persona_not_startswith', None)\n search_text_contains = kwargs.pop('search_text_contains', None)\n\n # Convert a single sting into a list if only one tag is provided\n if type(tags) == str:\n tags = [tags]\n\n if len(kwargs) == 0:\n statements = session.query(Statement).filter()\n else:\n statements = session.query(Statement).filter_by(**kwargs)\n\n if tags:\n statements = statements.join(Statement.tags).filter(\n Tag.name.in_(tags)\n )\n\n if exclude_text:\n statements = statements.filter(\n ~Statement.text.in_(exclude_text)\n )\n\n if exclude_text_words:\n or_word_query = [\n Statement.text.ilike('%' + word + '%') for word in exclude_text_words\n ]\n statements = statements.filter(\n ~or_(*or_word_query)\n )\n\n if persona_not_startswith:\n statements = statements.filter(\n ~Statement.persona.startswith('bot:')\n )\n\n if search_text_contains:\n or_query = [\n Statement.search_text.contains(word) for word in search_text_contains.split(' ')\n ]\n statements = statements.filter(\n or_(*or_query)\n )\n\n if order_by:\n\n if 'created_at' in order_by:\n index = order_by.index('created_at')\n order_by[index] = Statement.created_at.asc()\n\n statements = statements.order_by(*order_by)\n\n total_statements = statements.count()\n\n for start_index in range(0, total_statements, page_size):\n for statement in statements.slice(start_index, start_index + page_size):\n yield self.model_to_object(statement)\n\n session.close()\n\n def create(self, **kwargs):\n \"\"\"\n Creates a new statement matching the keyword arguments specified.\n Returns the created statement.\n \"\"\"\n Statement = self.get_model('statement')\n Tag = self.get_model('tag')\n\n session = self.Session()\n\n tags = set(kwargs.pop('tags', []))\n\n if 'search_text' not in kwargs:\n kwargs['search_text'] = self.tagger.get_text_index_string(kwargs['text'])\n\n if 'search_in_response_to' not in kwargs:\n in_response_to = kwargs.get('in_response_to')\n if in_response_to:\n kwargs['search_in_response_to'] = self.tagger.get_text_index_string(in_response_to)\n\n statement = Statement(**kwargs)\n\n for tag_name in tags:\n tag = session.query(Tag).filter_by(name=tag_name).first()\n\n if not tag:\n # Create the tag\n tag = Tag(name=tag_name)\n\n statement.tags.append(tag)\n\n session.add(statement)\n\n session.flush()\n\n session.refresh(statement)\n\n statement_object = self.model_to_object(statement)\n\n self._session_finish(session)\n\n return statement_object\n\n def create_many(self, statements):\n \"\"\"\n Creates multiple statement entries.\n \"\"\"\n Statement = self.get_model('statement')\n Tag = self.get_model('tag')\n\n session = self.Session()\n\n create_statements = []\n create_tags = {}\n\n for statement in statements:\n\n statement_data = statement.serialize()\n tag_data = statement_data.pop('tags', [])\n\n statement_model_object = Statement(**statement_data)\n\n if not statement.search_text:\n statement_model_object.search_text = self.tagger.get_text_index_string(statement.text)\n\n if not statement.search_in_response_to and statement.in_response_to:\n statement_model_object.search_in_response_to = self.tagger.get_text_index_string(statement.in_response_to)\n\n new_tags = set(tag_data) - set(create_tags.keys())\n\n if new_tags:\n existing_tags = session.query(Tag).filter(\n Tag.name.in_(new_tags)\n )\n\n for existing_tag in existing_tags:\n create_tags[existing_tag.name] = existing_tag\n\n for tag_name in tag_data:\n if tag_name in create_tags:\n tag = create_tags[tag_name]\n else:\n # Create the tag if it does not exist\n tag = Tag(name=tag_name)\n\n create_tags[tag_name] = tag\n\n statement_model_object.tags.append(tag)\n create_statements.append(statement_model_object)\n\n session.add_all(create_statements)\n session.commit()\n\n def update(self, statement):\n \"\"\"\n Modifies an entry in the database.\n Creates an entry if one does not exist.\n \"\"\"\n Statement = self.get_model('statement')\n Tag = self.get_model('tag')\n\n if statement is not None:\n session = self.Session()\n record = None\n\n if hasattr(statement, 'id') and statement.id is not None:\n record = session.query(Statement).get(statement.id)\n else:\n record = session.query(Statement).filter(\n Statement.text == statement.text,\n Statement.conversation == statement.conversation,\n ).first()\n\n # Create a new statement entry if one does not already exist\n if not record:\n record = Statement(\n text=statement.text,\n conversation=statement.conversation,\n persona=statement.persona\n )\n\n # Update the response value\n record.in_response_to = statement.in_response_to\n\n record.created_at = statement.created_at\n\n record.search_text = self.tagger.get_text_index_string(statement.text)\n\n if statement.in_response_to:\n record.search_in_response_to = self.tagger.get_text_index_string(statement.in_response_to)\n\n for tag_name in statement.get_tags():\n tag = session.query(Tag).filter_by(name=tag_name).first()\n\n if not tag:\n # Create the record\n tag = Tag(name=tag_name)\n\n record.tags.append(tag)\n\n session.add(record)\n\n self._session_finish(session)\n\n def get_random(self):\n \"\"\"\n Returns a random statement from the database.\n \"\"\"\n import random\n\n Statement = self.get_model('statement')\n\n session = self.Session()\n count = self.count()\n if count < 1:\n raise self.EmptyDatabaseException()\n\n random_index = random.randrange(0, count)\n random_statement = session.query(Statement)[random_index]\n\n statement = self.model_to_object(random_statement)\n\n session.close()\n return statement\n\n def drop(self):\n \"\"\"\n Drop the database.\n \"\"\"\n Statement = self.get_model('statement')\n Tag = self.get_model('tag')\n\n session = self.Session()\n\n session.query(Statement).delete()\n session.query(Tag).delete()\n\n session.commit()\n session.close()\n\n def create_database(self):\n \"\"\"\n Populate the database with the tables.\n \"\"\"\n from chatterbot.ext.sqlalchemy_app.models import Base\n Base.metadata.create_all(self.engine)\n\n def _session_finish(self, session, statement_text=None):\n from sqlalchemy.exc import InvalidRequestError\n try:\n session.commit()\n except InvalidRequestError:\n # Log the statement text and the exception\n self.logger.exception(statement_text)\n finally:\n session.close()\n\n\n\nFile: chatterbot/storage/mongodb.py\n\nimport re\nfrom chatterbot.storage import StorageAdapter\n\n\nclass MongoDatabaseAdapter(StorageAdapter):\n \"\"\"\n The MongoDatabaseAdapter is an interface that allows\n ChatterBot to store statements in a MongoDB database.\n\n :keyword database_uri: The URI of a remote instance of MongoDB.\n This can be any valid\n `MongoDB connection string <https://docs.mongodb.com/manual/reference/connection-string/>`_\n :type database_uri: str\n\n .. code-block:: python\n\n database_uri='mongodb://example.com:8100/'\n \"\"\"\n\n def __init__(self, **kwargs):\n super().__init__(**kwargs)\n from pymongo import MongoClient\n from pymongo.errors import OperationFailure\n\n self.database_uri = kwargs.get(\n 'database_uri', 'mongodb://localhost:27017/chatterbot-database'\n )\n\n # Use the default host and port\n self.client = MongoClient(self.database_uri)\n\n # Increase the sort buffer to 42M if possible\n try:\n self.client.admin.command({'setParameter': 1, 'internalQueryExecMaxBlockingSortBytes': 44040192})\n except OperationFailure:\n pass\n\n # Specify the name of the database\n self.database = self.client.get_database()\n\n # The mongo collection of statement documents\n self.statements = self.database['statements']\n\n def get_statement_model(self):\n \"\"\"\n Return the class for the statement model.\n \"\"\"\n from chatterbot.conversation import Statement\n\n # Create a storage-aware statement\n statement = Statement\n statement.storage = self\n\n return statement\n\n def count(self):\n return self.statements.count()\n\n def mongo_to_object(self, statement_data):\n \"\"\"\n Return Statement object when given data\n returned from Mongo DB.\n \"\"\"\n Statement = self.get_model('statement')\n\n statement_data['id'] = statement_data['_id']\n\n return Statement(**statement_data)\n\n def filter(self, **kwargs):\n \"\"\"\n Returns a list of statements in the database\n that match the parameters specified.\n \"\"\"\n import pymongo\n\n page_size = kwargs.pop('page_size', 1000)\n order_by = kwargs.pop('order_by', None)\n tags = kwargs.pop('tags', [])\n exclude_text = kwargs.pop('exclude_text', None)\n exclude_text_words = kwargs.pop('exclude_text_words', [])\n persona_not_startswith = kwargs.pop('persona_not_startswith', None)\n search_text_contains = kwargs.pop('search_text_contains', None)\n\n if tags:\n kwargs['tags'] = {\n '$in': tags\n }\n\n if exclude_text:\n if 'text' not in kwargs:\n kwargs['text'] = {}\n elif 'text' in kwargs and isinstance(kwargs['text'], str):\n text = kwargs.pop('text')\n kwargs['text'] = {\n '$eq': text\n }\n kwargs['text']['$nin'] = exclude_text\n\n if exclude_text_words:\n if 'text' not in kwargs:\n kwargs['text'] = {}\n elif 'text' in kwargs and isinstance(kwargs['text'], str):\n text = kwargs.pop('text')\n kwargs['text'] = {\n '$eq': text\n }\n exclude_word_regex = '|'.join([\n '.*{}.*'.format(word) for word in exclude_text_words\n ])\n kwargs['text']['$not'] = re.compile(exclude_word_regex)\n\n if persona_not_startswith:\n if 'persona' not in kwargs:\n kwargs['persona'] = {}\n elif 'persona' in kwargs and isinstance(kwargs['persona'], str):\n persona = kwargs.pop('persona')\n kwargs['persona'] = {\n '$eq': persona\n }\n kwargs['persona']['$not'] = re.compile('^bot:*')\n\n if search_text_contains:\n or_regex = '|'.join([\n '{}'.format(re.escape(word)) for word in search_text_contains.split(' ')\n ])\n kwargs['search_text'] = re.compile(or_regex)\n\n mongo_ordering = []\n\n if order_by:\n\n # Sort so that newer datetimes appear first\n if 'created_at' in order_by:\n order_by.remove('created_at')\n mongo_ordering.append(('created_at', pymongo.DESCENDING, ))\n\n for order in order_by:\n mongo_ordering.append((order, pymongo.ASCENDING))\n\n total_statements = self.statements.find(kwargs).count()\n\n for start_index in range(0, total_statements, page_size):\n if mongo_ordering:\n for match in self.statements.find(kwargs).sort(mongo_ordering).skip(start_index).limit(page_size):\n yield self.mongo_to_object(match)\n else:\n for match in self.statements.find(kwargs).skip(start_index).limit(page_size):\n yield self.mongo_to_object(match)\n\n def create(self, **kwargs):\n \"\"\"\n Creates a new statement matching the keyword arguments specified.\n Returns the created statement.\n \"\"\"\n Statement = self.get_model('statement')\n\n if 'tags' in kwargs:\n kwargs['tags'] = list(set(kwargs['tags']))\n\n if 'search_text' not in kwargs:\n kwargs['search_text'] = self.tagger.get_text_index_string(kwargs['text'])\n\n if 'search_in_response_to' not in kwargs:\n if kwargs.get('in_response_to'):\n kwargs['search_in_response_to'] = self.tagger.get_text_index_string(kwargs['in_response_to'])\n\n inserted = self.statements.insert_one(kwargs)\n\n kwargs['id'] = inserted.inserted_id\n\n return Statement(**kwargs)\n\n def create_many(self, statements):\n \"\"\"\n Creates multiple statement entries.\n \"\"\"\n create_statements = []\n\n for statement in statements:\n statement_data = statement.serialize()\n tag_data = list(set(statement_data.pop('tags', [])))\n statement_data['tags'] = tag_data\n\n if not statement.search_text:\n statement_data['search_text'] = self.tagger.get_text_index_string(statement.text)\n\n if not statement.search_in_response_to and statement.in_response_to:\n statement_data['search_in_response_to'] = self.tagger.get_text_index_string(statement.in_response_to)\n\n create_statements.append(statement_data)\n\n self.statements.insert_many(create_statements)\n\n def update(self, statement):\n data = statement.serialize()\n data.pop('id', None)\n data.pop('tags', None)\n\n data['search_text'] = self.tagger.get_text_index_string(data['text'])\n\n if data.get('in_response_to'):\n data['search_in_response_to'] = self.tagger.get_text_index_string(data['in_response_to'])\n\n update_data = {\n '$set': data\n }\n\n if statement.tags:\n update_data['$addToSet'] = {\n 'tags': {\n '$each': statement.tags\n }\n }\n\n search_parameters = {}\n\n if statement.id is not None:\n search_parameters['_id'] = statement.id\n else:\n search_parameters['text'] = statement.text\n search_parameters['conversation'] = statement.conversation\n\n update_operation = self.statements.update_one(\n search_parameters,\n update_data,\n upsert=True\n )\n\n if update_operation.acknowledged:\n statement.id = update_operation.upserted_id\n\n return statement\n\n def get_random(self):\n \"\"\"\n Returns a random statement from the database\n \"\"\"\n from random import randint\n\n count = self.count()\n\n if count < 1:\n raise self.EmptyDatabaseException()\n\n random_integer = randint(0, count - 1)\n\n statements = self.statements.find().limit(1).skip(random_integer)\n\n return self.mongo_to_object(list(statements)[0])\n\n def remove(self, statement_text):\n \"\"\"\n Removes the statement that matches the input text.\n \"\"\"\n self.statements.delete_one({'text': statement_text})\n\n def drop(self):\n \"\"\"\n Remove the database.\n \"\"\"\n self.client.drop_database(self.database.name)\n\n\n\nFile: chatterbot/storage/__init__.py\n\nfrom chatterbot.storage.storage_adapter import StorageAdapter\nfrom chatterbot.storage.django_storage import DjangoStorageAdapter\nfrom chatterbot.storage.mongodb import MongoDatabaseAdapter\nfrom chatterbot.storage.sql_storage import SQLStorageAdapter\n\n\n__all__ = (\n 'StorageAdapter',\n 'DjangoStorageAdapter',\n 'MongoDatabaseAdapter',\n 'SQLStorageAdapter',\n)\n\n\n\nFile: chatterbot/storage/storage_adapter.py\n\nimport logging\nfrom chatterbot import languages\nfrom chatterbot.tagging import PosLemmaTagger\n\n\nclass StorageAdapter(object):\n \"\"\"\n This is an abstract class that represents the interface\n that all storage adapters should implement.\n \"\"\"\n\n def __init__(self, *args, **kwargs):\n \"\"\"\n Initialize common attributes shared by all storage adapters.\n\n :param str tagger_language: The language that the tagger uses to remove stopwords.\n \"\"\"\n self.logger = kwargs.get('logger', logging.getLogger(__name__))\n\n Tagger = kwargs.get('tagger', PosLemmaTagger)\n\n self.tagger = Tagger(language=kwargs.get(\n 'tagger_language', languages.ENG\n ))\n\n def get_model(self, model_name):\n \"\"\"\n Return the model class for a given model name.\n\n model_name is case insensitive.\n \"\"\"\n get_model_method = getattr(self, 'get_%s_model' % (\n model_name.lower(),\n ))\n\n return get_model_method()\n\n def get_object(self, object_name):\n \"\"\"\n Return the class for a given object name.\n\n object_name is case insensitive.\n \"\"\"\n get_model_method = getattr(self, 'get_%s_object' % (\n object_name.lower(),\n ))\n\n return get_model_method()\n\n def get_statement_object(self):\n from chatterbot.conversation import Statement\n\n StatementModel = self.get_model('statement')\n\n Statement.statement_field_names.extend(\n StatementModel.extra_statement_field_names\n )\n\n return Statement\n\n def count(self):\n \"\"\"\n Return the number of entries in the database.\n \"\"\"\n raise self.AdapterMethodNotImplementedError(\n 'The `count` method is not implemented by this adapter.'\n )\n\n def remove(self, statement_text):\n \"\"\"\n Removes the statement that matches the input text.\n Removes any responses from statements where the response text matches\n the input text.\n \"\"\"\n raise self.AdapterMethodNotImplementedError(\n 'The `remove` method is not implemented by this adapter.'\n )\n\n def filter(self, **kwargs):\n \"\"\"\n Returns a list of objects from the database.\n The kwargs parameter can contain any number\n of attributes. Only objects which contain\n all listed attributes and in which all values\n match for all listed attributes will be returned.\n\n :param page_size: The maximum number of records to load into\n memory at once when returning results.\n Defaults to 1000\n\n :param order_by: The field name that should be used to determine\n the order that results are returned in.\n Defaults to None\n\n :param tags: A list of tags. When specified, the results will only\n include statements that have a tag in the provided list.\n Defaults to [] (empty list)\n\n :param exclude_text: If the ``text`` of a statement is an exact match\n for the value of this parameter the statement will not be\n included in the result set.\n Defaults to None\n\n :param exclude_text_words: If the ``text`` of a statement contains a\n word from this list then the statement will not be included in\n the result set.\n Defaults to [] (empty list)\n\n :param persona_not_startswith: If the ``persona`` field of a\n statement starts with the value specified by this parameter,\n then the statement will not be returned in the result set.\n Defaults to None\n\n :param search_text_contains: If the ``search_text`` field of a\n statement contains a word that is in the string provided to\n this parameter, then the statement will be included in the\n result set.\n Defaults to None\n \"\"\"\n raise self.AdapterMethodNotImplementedError(\n 'The `filter` method is not implemented by this adapter.'\n )\n\n def create(self, **kwargs):\n \"\"\"\n Creates a new statement matching the keyword arguments specified.\n Returns the created statement.\n \"\"\"\n raise self.AdapterMethodNotImplementedError(\n 'The `create` method is not implemented by this adapter.'\n )\n\n def create_many(self, statements):\n \"\"\"\n Creates multiple statement entries.\n \"\"\"\n raise self.AdapterMethodNotImplementedError(\n 'The `create_many` method is not implemented by this adapter.'\n )\n\n def update(self, statement):\n \"\"\"\n Modifies an entry in the database.\n Creates an entry if one does not exist.\n \"\"\"\n raise self.AdapterMethodNotImplementedError(\n 'The `update` method is not implemented by this adapter.'\n )\n\n def get_random(self):\n \"\"\"\n Returns a random statement from the database.\n \"\"\"\n raise self.AdapterMethodNotImplementedError(\n 'The `get_random` method is not implemented by this adapter.'\n )\n\n def drop(self):\n \"\"\"\n Drop the database attached to a given adapter.\n \"\"\"\n raise self.AdapterMethodNotImplementedError(\n 'The `drop` method is not implemented by this adapter.'\n )\n\n class EmptyDatabaseException(Exception):\n\n def __init__(self, message=None):\n default = 'The database currently contains no entries. At least one entry is expected. You may need to train your chat bot to populate your database.'\n super().__init__(message or default)\n\n class AdapterMethodNotImplementedError(NotImplementedError):\n \"\"\"\n An exception to be raised when a storage adapter method has not been implemented.\n Typically this indicates that the method should be implement in a subclass.\n \"\"\"\n pass\n\n\n\nFile: chatterbot/storage/django_storage.py\n\nfrom chatterbot.storage import StorageAdapter\nfrom chatterbot import constants\n\n\nclass DjangoStorageAdapter(StorageAdapter):\n \"\"\"\n Storage adapter that allows ChatterBot to interact with\n Django storage backends.\n \"\"\"\n\n def __init__(self, **kwargs):\n super().__init__(**kwargs)\n\n self.django_app_name = kwargs.get(\n 'django_app_name',\n constants.DEFAULT_DJANGO_APP_NAME\n )\n\n def get_statement_model(self):\n from django.apps import apps\n return apps.get_model(self.django_app_name, 'Statement')\n\n def get_tag_model(self):\n from django.apps import apps\n return apps.get_model(self.django_app_name, 'Tag')\n\n def count(self):\n Statement = self.get_model('statement')\n return Statement.objects.count()\n\n def filter(self, **kwargs):\n \"\"\"\n Returns a list of statements in the database\n that match the parameters specified.\n \"\"\"\n from django.db.models import Q\n\n Statement = self.get_model('statement')\n\n kwargs.pop('page_size', 1000)\n order_by = kwargs.pop('order_by', None)\n tags = kwargs.pop('tags', [])\n exclude_text = kwargs.pop('exclude_text', None)\n exclude_text_words = kwargs.pop('exclude_text_words', [])\n persona_not_startswith = kwargs.pop('persona_not_startswith', None)\n search_text_contains = kwargs.pop('search_text_contains', None)\n\n # Convert a single sting into a list if only one tag is provided\n if type(tags) == str:\n tags = [tags]\n\n if tags:\n kwargs['tags__name__in'] = tags\n\n statements = Statement.objects.filter(**kwargs)\n\n if exclude_text:\n statements = statements.exclude(\n text__in=exclude_text\n )\n\n if exclude_text_words:\n or_query = [\n ~Q(text__icontains=word) for word in exclude_text_words\n ]\n\n statements = statements.filter(\n *or_query\n )\n\n if persona_not_startswith:\n statements = statements.exclude(\n persona__startswith='bot:'\n )\n\n if search_text_contains:\n or_query = Q()\n\n for word in search_text_contains.split(' '):\n or_query |= Q(search_text__contains=word)\n\n statements = statements.filter(\n or_query\n )\n\n if order_by:\n statements = statements.order_by(*order_by)\n\n for statement in statements.iterator():\n yield statement\n\n def create(self, **kwargs):\n \"\"\"\n Creates a new statement matching the keyword arguments specified.\n Returns the created statement.\n \"\"\"\n Statement = self.get_model('statement')\n Tag = self.get_model('tag')\n\n tags = kwargs.pop('tags', [])\n\n if 'search_text' not in kwargs:\n kwargs['search_text'] = self.tagger.get_text_index_string(kwargs['text'])\n\n if 'search_in_response_to' not in kwargs:\n if kwargs.get('in_response_to'):\n kwargs['search_in_response_to'] = self.tagger.get_text_index_string(kwargs['in_response_to'])\n\n statement = Statement(**kwargs)\n\n statement.save()\n\n tags_to_add = []\n\n for _tag in tags:\n tag, _ = Tag.objects.get_or_create(name=_tag)\n tags_to_add.append(tag)\n\n statement.tags.add(*tags_to_add)\n\n return statement\n\n def create_many(self, statements):\n \"\"\"\n Creates multiple statement entries.\n \"\"\"\n Statement = self.get_model('statement')\n Tag = self.get_model('tag')\n\n tag_cache = {}\n\n for statement in statements:\n\n statement_data = statement.serialize()\n tag_data = statement_data.pop('tags', [])\n\n statement_model_object = Statement(**statement_data)\n\n if not statement.search_text:\n statement_model_object.search_text = self.tagger.get_text_index_string(statement.text)\n\n if not statement.search_in_response_to and statement.in_response_to:\n statement_model_object.search_in_response_to = self.tagger.get_text_index_string(statement.in_response_to)\n\n statement_model_object.save()\n\n tags_to_add = []\n\n for tag_name in tag_data:\n if tag_name in tag_cache:\n tag = tag_cache[tag_name]\n else:\n tag, _ = Tag.objects.get_or_create(name=tag_name)\n tag_cache[tag_name] = tag\n tags_to_add.append(tag)\n\n statement_model_object.tags.add(*tags_to_add)\n\n def update(self, statement):\n \"\"\"\n Update the provided statement.\n \"\"\"\n Statement = self.get_model('statement')\n Tag = self.get_model('tag')\n\n if hasattr(statement, 'id'):\n statement.save()\n else:\n statement = Statement.objects.create(\n text=statement.text,\n search_text=self.tagger.get_text_index_string(statement.text),\n conversation=statement.conversation,\n in_response_to=statement.in_response_to,\n search_in_response_to=self.tagger.get_text_index_string(statement.in_response_to),\n created_at=statement.created_at\n )\n\n for _tag in statement.tags.all():\n tag, _ = Tag.objects.get_or_create(name=_tag)\n\n statement.tags.add(tag)\n\n return statement\n\n def get_random(self):\n \"\"\"\n Returns a random statement from the database\n \"\"\"\n Statement = self.get_model('statement')\n\n statement = Statement.objects.order_by('?').first()\n\n if statement is None:\n raise self.EmptyDatabaseException()\n\n return statement\n\n def remove(self, statement_text):\n \"\"\"\n Removes the statement that matches the input text.\n Removes any responses from statements if the response text matches the\n input text.\n \"\"\"\n Statement = self.get_model('statement')\n\n statements = Statement.objects.filter(text=statement_text)\n\n statements.delete()\n\n def drop(self):\n \"\"\"\n Remove all data from the database.\n \"\"\"\n Statement = self.get_model('statement')\n Tag = self.get_model('tag')\n\n Statement.objects.all().delete()\n Tag.objects.all().delete()\n\n\n"},"repo_readme":{"kind":"string","value":"\n\n# ChatterBot\n\nChatterBot is a machine-learning based conversational dialog engine build in\nPython which makes it possible to generate responses based on collections of\nknown conversations. The language independent design of ChatterBot allows it\nto be trained to speak any language.\n\n[](https://pypi.python.org/pypi/chatterbot/)\n[](https://www.python.org/downloads/release/python-360/)\n[](https://docs.djangoproject.com/en/2.1/releases/2.0/)\n[](https://requires.io/github/gunthercox/ChatterBot/requirements/?branch=master)\n[](https://travis-ci.org/gunthercox/ChatterBot)\n[](http://chatterbot.readthedocs.io/en/stable/?badge=stable)\n[](https://coveralls.io/r/gunthercox/ChatterBot)\n[](https://codeclimate.com/github/gunthercox/ChatterBot)\n[](https://gitter.im/chatterbot/Lobby?utm_source=badge&utm_medium=badge&utm_content=badge)\n\nAn example of typical input would be something like this:\n\n> **user:** Good morning! How are you doing? \n> **bot:** I am doing very well, thank you for asking. \n> **user:** You're welcome. \n> **bot:** Do you like hats? \n\n## How it works\n\nAn untrained instance of ChatterBot starts off with no knowledge of how to communicate. Each time a user enters a statement, the library saves the text that they entered and the text that the statement was in response to. As ChatterBot receives more input the number of responses that it can reply and the accuracy of each response in relation to the input statement increase. The program selects the closest matching response by searching for the closest matching known statement that matches the input, it then returns the most likely response to that statement based on how frequently each response is issued by the people the bot communicates with.\n\n## Installation\n\nThis package can be installed from [PyPi](https://pypi.python.org/pypi/ChatterBot) by running:\n\n```\npip install chatterbot\n```\n\n## Basic Usage\n\n```\nfrom chatterbot import ChatBot\nfrom chatterbot.trainers import ChatterBotCorpusTrainer\n\nchatbot = ChatBot('Ron Obvious')\n\n# Create a new trainer for the chatbot\ntrainer = ChatterBotCorpusTrainer(chatbot)\n\n# Train the chatbot based on the english corpus\ntrainer.train(\"chatterbot.corpus.english\")\n\n# Get a response to an input statement\nchatbot.get_response(\"Hello, how are you today?\")\n```\n\n# Training data\n\nChatterBot comes with a data utility module that can be used to train chat bots.\nAt the moment there is training data for over a dozen languages in this module.\nContributions of additional training data or training data\nin other languages would be greatly appreciated. Take a look at the data files\nin the [chatterbot-corpus](https://github.com/gunthercox/chatterbot-corpus)\npackage if you are interested in contributing.\n\n```\nfrom chatterbot.trainers import ChatterBotCorpusTrainer\n\n# Create a new trainer for the chatbot\ntrainer = ChatterBotCorpusTrainer(chatbot)\n\n# Train based on the english corpus\ntrainer.train(\"chatterbot.corpus.english\")\n\n# Train based on english greetings corpus\ntrainer.train(\"chatterbot.corpus.english.greetings\")\n\n# Train based on the english conversations corpus\ntrainer.train(\"chatterbot.corpus.english.conversations\")\n```\n\n**Corpus contributions are welcome! Please make a pull request.**\n\n# [Documentation](https://chatterbot.readthedocs.io/)\n\nView the [documentation](https://chatterbot.readthedocs.io/)\nfor ChatterBot on Read the Docs.\n\nTo build the documentation yourself using [Sphinx](http://www.sphinx-doc.org/), run:\n\n```\nsphinx-build -b html docs/ build/\n```\n\n# Examples\n\nFor examples, see the [examples](https://github.com/gunthercox/ChatterBot/tree/master/examples)\ndirectory in this project's git repository.\n\nThere is also an example [Django project using ChatterBot](https://github.com/gunthercox/ChatterBot/tree/master/examples), as well as an example [Flask project using ChatterBot](https://github.com/chamkank/flask-chatterbot).\n\n# History\n\nSee release notes for changes https://github.com/gunthercox/ChatterBot/releases\n\n# Development pattern for contributors\n\n1. [Create a fork](https://help.github.com/articles/fork-a-repo/) of\n the [main ChatterBot repository](https://github.com/gunthercox/ChatterBot) on GitHub.\n2. Make your changes in a branch named something different from `master`, e.g. create\n a new branch `my-pull-request`.\n3. [Create a pull request](https://help.github.com/articles/creating-a-pull-request/).\n4. Please follow the [Python style guide for PEP-8](https://www.python.org/dev/peps/pep-0008/).\n5. Use the projects [built-in automated testing](https://chatterbot.readthedocs.io/en/latest/testing.html).\n to help make sure that your contribution is free from errors.\n\n# License\n\nChatterBot is licensed under the [BSD 3-clause license](https://opensource.org/licenses/BSD-3-Clause).\n"}}}],"truncated":false,"partial":false},"paginationData":{"pageIndex":1,"numItemsPerPage":100,"numTotalItems":158,"offset":100,"length":100}},"jwt":"eyJhbGciOiJFZERTQSJ9.eyJyZWFkIjp0cnVlLCJwZXJtaXNzaW9ucyI6eyJyZXBvLmNvbnRlbnQucmVhZCI6dHJ1ZX0sImlhdCI6MTc3NjcyMzY4Nywic3ViIjoiL2RhdGFzZXRzL3BhdGNoZWQtY29kZXMvZ2VuZXJhdGUtcmVhZG1lLWV2YWwiLCJleHAiOjE3NzY3MjcyODcsImlzcyI6Imh0dHBzOi8vaHVnZ2luZ2ZhY2UuY28ifQ.dQ2H4jSV7E2ZrBkKppVvfNVMOW01TJsIHLH2S4n4E_B0M3wLbyxohmcxg44-qEjQgGCCTi5wMlVIUSWk-4iVDA","displayUrls":true,"splitSizeSummaries":[{"config":"default","split":"train","numRows":158,"numBytesParquet":9326742},{"config":"default","split":"test","numRows":40,"numBytesParquet":2980790}]},"discussionsStats":{"closed":3,"open":1,"total":4},"fullWidth":true,"hasGatedAccess":true,"hasFullAccess":true,"isEmbedded":false,"savedQueries":{"community":[],"user":[]}}">
repo_name stringlengths 3 38 | repo_commit stringlengths 40 40 | repo_content stringlengths 0 949k | repo_readme stringlengths 34 275k |
|---|---|---|---|
wtfpython | d2673bba08d0ec2d52bb34576e1d55772e4ba0c1 | File: mixed_tabs_and_spaces.py
def square(x):
sum_so_far = 0
for _ in range(x):
sum_so_far += x
return sum_so_far # noqa: E999 # pylint: disable=mixed-indentation Python 3 will raise a TabError here
print(square(10))
File: wtfpython-pypi/setup.py
from setuptools import setup, find_packages
if _... | <p align="center"><img src="/images/logo.png#gh-light-mode-only" alt=""><img src="/images/logo-dark.png#gh-dark-mode-only" alt=""></p>
<h1 align="center">What the f*ck Python! 😱</h1>
<p align="center">Exploring and understanding Python through surprising snippets.</p>
Translations: [Chinese 中文](https://github.com/le... |
mailinabox | ca123515aad102327701b18a7d65d180f800b815 | File: tools/mail.py
#!/bin/bash
# This script has moved.
management/cli.py "$@"
File: tools/readable_bash.py
#!/usr/bin/python3
#
# Generate documentation for how this machine works by
# parsing our bash scripts!
import cgi, re
import markdown
from modgrammar import *
def generate_documentation():
print("""<!DO... | Mail-in-a-Box
=============
By [@JoshData](https://github.com/JoshData) and [contributors](https://github.com/mail-in-a-box/mailinabox/graphs/contributors).
Mail-in-a-Box helps individuals take back control of their email by defining a one-click, easy-to-deploy SMTP+everything else server: a mail server in a box.
**... |
HelloGitHub | 739e7f170bd65fa27ad52804cef107c4fb020184 | File: script/make_content/make_content.py
#!/usr/bin/env python
# -*- coding:utf-8 -*-
#
# Author : XueWeiHan
# E-mail : 595666367@qq.com
# Date : 16/10/21 下午1:41
# Desc : HelloGitHub项目——生成月刊脚本
"""
该脚本主要用于：生成月刊
《HelloGitHub》月刊每期内容都遵循统一格式，如果需要对通用部分的内容进行修改，需要手动修改每一
期的内容，这是不优雅的。
所以，我打算写个脚本，用于生成月... | <p align="center">
<img src="https://raw.githubusercontent.com/521xueweihan/img_logo/master/logo/readme.gif"/>
<br>中文 | <a href="README_en.md">English</a> | <a href="README_ja.md">日本語</a>
<br>分享 GitHub 上有趣、入门级的开源项目。<br>兴趣是最好的老师，这里能够帮你找到编程的兴趣！
</p>
<p align="center">
<a href="https://raw.githubusercontent.com/5... |
facefusion | 57016d7c778c70f58fc54c49013d57179874a505 | File: run.py
#!/usr/bin/env python3
from facefusion import core
if __name__ == '__main__':
core.cli()
File: install.py
#!/usr/bin/env python3
import os
import subprocess
os.environ['PIP_BREAK_SYSTEM_PACKAGES'] = '1'
subprocess.call([ 'pip', 'install', 'inquirer', '-q' ])
from facefusion import installer
if ... | FaceFusion
==========
> Next generation face swapper and enhancer.
[](https://github.com/facefusion/facefusion/actions?query=workflow:ci)
Pr... |
wtfpython | d2673bba08d0ec2d52bb34576e1d55772e4ba0c1 | File: mixed_tabs_and_spaces.py
def square(x):
sum_so_far = 0
for _ in range(x):
sum_so_far += x
return sum_so_far # noqa: E999 # pylint: disable=mixed-indentation Python 3 will raise a TabError here
print(square(10))
File: wtfpython-pypi/setup.py
from setuptools import setup, find_packages
if _... | <p align="center"><img src="/images/logo.png#gh-light-mode-only" alt=""><img src="/images/logo-dark.png#gh-dark-mode-only" alt=""></p>
<h1 align="center">What the f*ck Python! 😱</h1>
<p align="center">Exploring and understanding Python through surprising snippets.</p>
Translations: [Chinese 中文](https://github.com/le... |
stylegan | 1e0d5c781384ef12b50ef20a62fee5d78b38e88f | File: dataset_tool.py
# Copyright (c) 2019, NVIDIA CORPORATION. All rights reserved.
#
# This work is licensed under the Creative Commons Attribution-NonCommercial
# 4.0 International License. To view a copy of this license, visit
# http://creativecommons.org/licenses/by-nc/4.0/ or send a letter to
# Creative Commons,... | ## StyleGAN — Official TensorFlow Implementation
.
We have s... |
interview_internal_reference | 9fe6c758e98c03c40c8908c39e78ab98a7ab53d6 |
## 2023年最新总结，阿里，腾讯，百度，美团，头条等技术面试题目，以及答案，专家出题人分析汇总。持续更新中。
* [阿里篇](#1)
* [华为篇](#2)
* [百度篇](#3)
* [腾讯篇](#4)
* [美团篇](#5)
* [头条篇](#6)
* [滴滴篇](#7)
* [京东篇](#8)
* [MySQL篇](#9)
* [Redis篇](#10)
* [MongoDB篇](#11)
* [Zookeeper篇](#12)
* [Nginx篇](#13)
* [算法篇](#14)
* [内存篇](#15)
* [cpu篇](#16)
* [磁盘篇](#17)
* [网络通信篇](#18)
* [安全篇](#19)... | |
learn-python | 52c3a655cc2efd5ac01004f6f529c3262812a84e | File: src/data_types/test_numbers.py
"""Numbers.
@see: https://docs.python.org/3/tutorial/introduction.html
@see: https://www.w3schools.com/python/python_numbers.asp
There are three numeric types in Python:
- int (e.g. 2, 4, 20)
- bool (e.g. False and True, acting like 0 and 1)
- float (e.g. 5.0, 1.6)
- complex ... | # Playground and Cheatsheet for Learning Python
> 🇺🇦 UKRAINE [IS BEING ATTACKED](https://war.ukraine.ua/) BY RUSSIAN ARMY. CIVILIANS ARE GETTING KILLED. RESIDENTIAL AREAS ARE GETTING BOMBED.
> - Help Ukraine via:
> - [Serhiy Prytula Charity Foundation](https://prytulafoundation.org/en/)
> - [Come Back Alive Char... |
awesome-python | 2252650cfdff3782d5a85458507fe9ec6edde7a4 | File: sort.py
#!/usr/bin/env python
# coding: utf-8
"""
The approach taken is explained below. I decided to do it simply.
Initially I was considering parsing the data into some sort of
structure and then generating an appropriate README. I am still
considering doing it - but for now this should work. ... | # Awesome Python [](https://github.com/sindresorhus/awesome)
An opinionated list of awesome Python frameworks, libraries, software and resources.
Inspired by [awesome-php](https://github.com/ziadoz/awesome-... |
Chinese-LLaMA-Alpaca | f213c2c53e92f2bfb41859ffdb2cf47a261c24fb | File: scripts/merge_llama_with_chinese_lora.py
"""
Usage:
python merge_llama_with_chinese_lora.py \
--base_model path/to/llama/model \
--lora_model path/to/first/lora/model [path/to/second/lora/model] \
--output_type [pth|huggingface] \
--output_dir path/to/output/dir
"""
import argparse
import json
i... | # [Chinese-LLaMA-Alpaca-3](https://github.com/ymcui/Chinese-LLaMA-Alpaca-3)项目启动！
[**🇨🇳中文**](./README.md) | [**🌐English**](./README_EN.md) | [**📖文档/Docs**](https://github.com/ymcui/Chinese-LLaMA-Alpaca/wiki) | [**❓提问/Issues**](https://github.com/ymcui/Chinese-LLaMA-Alpaca/issues) | [**💬讨论/Discussions**](https://gi... |
ML-From-Scratch | a2806c6732eee8d27762edd6d864e0c179d8e9e8 | File: setup.py
from setuptools import setup, find_packages
from codecs import open
from os import path
__version__ = '0.0.4'
here = path.abspath(path.dirname(__file__))
# get the dependencies and installs
with open(path.join(here, 'requirements.txt'), encoding='utf-8') as f:
all_reqs = f.read().split('\n')
ins... | # Machine Learning From Scratch
## About
Python implementations of some of the fundamental Machine Learning models and algorithms from scratch.
The purpose of this project is not to produce as optimized and computationally efficient algorithms as possible
but rather to present the inner workings of them in a transpar... |
Python-100-Days | bf24146944745bb25c66c82307fd218abd179c6a | File: Day31-35/code/josephu.py
def main():
persons = [True] * 30
counter = 0
index = 0
number = 0
while counter < 15:
if persons[index]:
number += 1
if number == 9:
persons[index] = False
number = 0
counter += 1
... | ## Python - 100天从新手到大师
> **作者**：骆昊
>
> **说明**：从项目上线到获得8w+星标以来，一直收到反馈说基础部分（前15天的内容）对新手来说是比较困难的，建议有配套视频进行讲解。最近把基础部分的内容重新制作了一个名为[“Python-Core-50-Courses”](<https://github.com/jackfrued/Python-Core-50-Courses>)的项目，用更为简单通俗的方式重写了这部分内容并附带了视频讲解，初学者可以看看这个新的仓库。国内用户如果访问GitHub比较慢的话，可以关注我的**知乎号[Python-Jack](https://www.zhihu.com/p... |
ddia | a735a7937df7533122defd88884ce34f67ef0505 | File: bin/translate.py
"""Convert zh-cn to zh-tw
Refer to https://github.com/BYVoid/OpenCC
"""
import click
import opencc
from pathlib import Path
from pprint import pprint
@click.group()
def cli():
pass
def convert(infile: str, outfile: str, cfg: str):
"""read >> convert >> write file
Args:
i... | # 设计数据密集型应用 - 中文翻译版
[](https://ddia.pigsty.io)
[](https://ddia2.pigsty.io)
[
from autojump_argparse import ArgumentParser # noqa
def is_empty_dir(path):
"""
Checks if any files are present within a directo... | NAME
----
autojump - a faster way to navigate your filesystem
DESCRIPTION
-----------
autojump is a faster way to navigate your filesystem. It works by
maintaining a database of the directories you use the most from the
command line.
*Directories must be visited first before they can be jumped to.*
USAGE
-----
`j... |
Deep-Learning-Papers-Reading-Roadmap | a994642f82f071926fcb472bcf6cd63e4abba7ab | File: download.py
from __future__ import print_function
import os
import re
from six.moves.urllib.error import HTTPError
import shutil
import argparse
import mistune
import bs4 as BeautifulSoup
import socket
import time
import requests
# encoding=utf8
import sys
try:
reload(sys)
except NameError:
pass
try... | # Deep Learning Papers Reading Roadmap
>If you are a newcomer to the Deep Learning area, the first question you may have is "Which paper should I start reading from?"
>Here is a reading roadmap of Deep Learning papers!
The roadmap is constructed in accordance with the following four guidelines:
- From outline to de... |
Real-ESRGAN | a4abfb2979a7bbff3f69f58f58ae324608821e27 | File: inference_realesrgan.py
import argparse
import cv2
import glob
import os
from basicsr.archs.rrdbnet_arch import RRDBNet
from basicsr.utils.download_util import load_file_from_url
from realesrgan import RealESRGANer
from realesrgan.archs.srvgg_arch import SRVGGNetCompact
def main():
"""Inference demo for R... | <p align="center">
<img src="assets/realesrgan_logo.png" height=120>
</p>
## <div align="center"><b><a href="README.md">English</a> | <a href="README_CN.md">简体中文</a></b></div>
<div align="center">
👀[**Demos**](#-demos-videos) **|** 🚩[**Updates**](#-updates) **|** ⚡[**Usage**](#-quick-inference) **|** 🏰[**Model ... |
requests | f12ccbef6d6b95564da8d22e280d28c39d53f0e9 | File: setup.py
#!/usr/bin/env python
import os
import sys
from codecs import open
from setuptools import setup
CURRENT_PYTHON = sys.version_info[:2]
REQUIRED_PYTHON = (3, 8)
if CURRENT_PYTHON < REQUIRED_PYTHON:
sys.stderr.write(
"""
==========================
Unsupported Python version
=================... | # Requests
**Requests** is a simple, yet elegant, HTTP library.
```python
>>> import requests
>>> r = requests.get('https://httpbin.org/basic-auth/user/pass', auth=('user', 'pass'))
>>> r.status_code
200
>>> r.headers['content-type']
'application/json; charset=utf8'
>>> r.encoding
'utf-8'
>>> r.text
'{"authenticated"... |
prophet | 36421b70f077cc657f143161de5a97f5a214e18b | File: python/setup.py
# Copyright (c) Facebook, Inc. and its affiliates.
# This source code is licensed under the MIT license found in the
# LICENSE file in the root directory of this source tree.
import os
import platform
from pathlib import Path
from shutil import copy, copytree, rmtree
from typing import List
imp... |
# Prophet: Automatic Forecasting Procedure
[](https://pypi.python.org/pypi/prophet)
[](https://pepy.tech/project/prophet)
[... |
dalle-mini | f0be4de610285a002052024a1e096126f9452cc4 | File: setup.py
from setuptools import setup
if __name__ == "__main__":
setup()
File: tools/train/train.py
#!/usr/bin/env python
# coding=utf-8
# Copyright 2021-2022 The HuggingFace & DALL·E Mini team. All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use th... | # DALL·E Mini
<a href="https://www.craiyon.com/"><img src="https://www.craiyon.com/thumbnail.png" width="300"></a>
## How to use it?
You can use the model on [🖍️ craiyon](https://www.craiyon.com/)
## How does it work?
Refer to our reports:
* [DALL·E mini - Generate Images from Any Text Prompt](https://wandb.ai/d... |
diagrams | 4c2d8a3795d2a15a168224b2a5919c2950df679b | File: config.py
# fmt: off
#########################
# Application #
#########################
APP_NAME = "diagrams"
DIR_DOC_ROOT = "docs/nodes"
DIR_APP_ROOT = "diagrams"
DIR_RESOURCE = "resources"
DIR_TEMPLATE = "templates"
PROVIDERS = (
"base",
"onprem",
"aws",
"azure",
"digitalocea... | 
# Diagrams
[](/LICENSE)
[](https://badge.fury.io/py/diagrams)
![Run tests](h... |
data-science-ipython-notebooks | 5b3c00d462c6e9200315afe46d0093948621eb95 | File: __init__.py
File: deep-learning/theano-tutorial/rnn_tutorial/lstm_text.py
import cPickle as pkl
import time
import numpy
import theano
from theano import config
import theano.tensor as T
from theano.tensor.nnet import categorical_crossentropy
from fuel.datasets import TextFile
from fuel.streams import Data... | <br/>
<p align="center">
<img src="https://raw.githubusercontent.com/donnemartin/data-science-ipython-notebooks/master/images/README_1200x800.gif">
</p>
<p align="center">
<img src="https://raw.githubusercontent.com/donnemartin/data-science-ipython-notebooks/master/images/coversmall_alt.png">
<br/>
</p>
# data-... |
avatarify-python | 862182cfbca5bd8a7473bed9c5f69f92e8d5cc7b | File: afy/arguments.py
from argparse import ArgumentParser
parser = ArgumentParser()
parser.add_argument("--config", help="path to config")
parser.add_argument("--checkpoint", default='vox-cpk.pth.tar', help="path to checkpoint to restore")
parser.add_argument("--relative", dest="relative", action="store_true", help... | 
# Avatarify Python
Photorealistic avatars for video-conferencing.
Avatarify Python requires manually downloading and installing some dependencies, and is therefore best suited for users who have some experience with command line applications. [Avatarify Desktop](https://github.com/alievk/avatarify... |
awesome-quant | 2ab6db153bec32873c94aecb58ade6e1fb71b2c4 | File: topic.py
import os
from github import Github
# using an access token
g = Github(os.environ['GITHUB_ACCESS_TOKEN'])
# ts = g.search_topics('trading')
# for t in ts:
# print(t)
# t = ts[0]
# print(t)
# print(t.name)
# print(t.updated_at)
# print(t.score)
topic = 'quant'
repos = g.search_repositories(quer... | # Awesome Quant
A curated list of insanely awesome libraries, packages and resources for Quants (Quantitative Finance).
[](https://awesome.re)
## Languages
- [Python](#python)
- [R](#r)
- [Matlab](#matlab)
- [Julia](#julia)
- [Java](#java)
- [JavaScript](#javascript)
- [Haskell](#ha... |
Shadowrocket-ADBlock-Rules | 1b691dc27ac483cfc0574c7559c6f9db9293c6f7 | File: factory/build_confs.py
# -*- coding: utf-8 -*-
import re
import time
# confs names in template/ and ../
# except sr_head and sr_foot
confs_names = [
'sr_top500_banlist_ad',
'sr_top500_banlist',
'sr_top500_whitelist_ad',
'sr_top500_whitelist',
'sr_adb',
'sr_direct_banad',
'sr_proxy_... | ## 最完善的 iOS 翻墙规则
### 停止更新公告
维护该项目已花费了我过多的时间，而生活中值得花费时间的东西太多，所以从即日起停止更新该项目。
------------------------------------------------------
这里是一系列好用的翻墙规则，针对 [Shadowrocket](https://liguangming.com/Shadowrocket) 开发，支持广告过滤。规则定义了哪些网站可以直连，哪些必须走代理，规则是一个纯文本文件，无法提供翻墙功能。使用 Python 按照一定的规则和模板定期自动生成，并且使用开源的力量，集众人之力逐渐完善。
**正在使用手机浏览本页面的用... |
crewAI | 322780a5f36840bf566aac97d872dc64261f4474 | File: src/crewai/task.py
import datetime
import json
import os
import threading
import uuid
from concurrent.futures import Future
from copy import copy
from hashlib import md5
from typing import Any, Dict, List, Optional, Set, Tuple, Type, Union
from opentelemetry.trace import Span
from pydantic import (
UUID4,
... | <div align="center">
# **crewAI**
🤖 **crewAI**: Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
<h... |
spotify-downloader | 866daddc9fdc7f764b89e8278426fcbb2af6b03e | File: scripts/build.py
import os
import sys
from pathlib import Path
import PyInstaller.__main__ # type: ignore
import pykakasi
import yt_dlp
import ytmusicapi
from spotdl._version import __version__
LOCALES_PATH = str((Path(ytmusicapi.__file__).parent / "locales"))
PYKAKASI_PATH = str((Path(pykakasi.__file__).par... |
<!--- mdformat-toc start --slug=github --->
<!---
!!! IF EDITING THE README, ENSURE TO COPY THE WHOLE FILE TO index.md in `/docs/` AND REMOVE THE REFERENCES TO ReadTheDocs THERE.
--->
<div align="center">
# spotDL v4
**spotDL** finds songs from Spotify playlists on YouTube and downloads them - along with album art... |
Hitomi-Downloader | c6dc4c421d0e3986936ad740073c3ee52e226c1f | File: src/extractor/danbooru_downloader.py
#coding: utf-8
import downloader
import ree as re
from utils import Downloader, get_max_range, clean_title, get_print, try_n, urljoin, check_alive, LazyUrl, get_ext, limits
from translator import tr_
from urllib.parse import urlparse, parse_qs, quote
import clf2
class Down... | <p align="center">
<img src="imgs/card_crop.png" width="50%"/>
<br>
</p>
[](https://github.com/KurtBestor/Hitomi-Downloader/releases/latest)
[: cog push r8.im/xinntao/gfpgan
import os
os.system('python setup.py develop')
os.syst... | <p align="center">
<img src="assets/gfpgan_logo.png" height=130>
</p>
## <div align="center"><b><a href="README.md">English</a> | <a href="README_CN.md">简体中文</a></b></div>
<div align="center">
<!-- <a href="https://twitter.com/_Xintao_" style="text-decoration:none;">
<img src="https://user-images.githubusercont... |
gaussian-splatting | 8a70a8cd6f0d9c0a14f564844ead2d1147d5a7ac | File: metrics.py
#
# Copyright (C) 2023, Inria
# GRAPHDECO research group, https://team.inria.fr/graphdeco
# All rights reserved.
#
# This software is free for non-commercial, research and evaluation use
# under the terms of the LICENSE.md file.
#
# For inquiries contact george.drettakis@inria.fr
#
from pathlib imp... | # 3D Gaussian Splatting for Real-Time Radiance Field Rendering
Bernhard Kerbl*, Georgios Kopanas*, Thomas Leimkühler, George Drettakis (* indicates equal contribution)<br>
| [Webpage](https://repo-sam.inria.fr/fungraph/3d-gaussian-splatting/) | [Full Paper](https://repo-sam.inria.fr/fungraph/3d-gaussian-splatting/3d_ga... |
ChatGLM3 | 045be71ff8df03b8819a6560866c9a86ec9be363 | File: basic_demo/cli_demo.py
import os
import platform
from transformers import AutoTokenizer, AutoModel
MODEL_PATH = os.environ.get('MODEL_PATH', 'THUDM/chatglm3-6b')
TOKENIZER_PATH = os.environ.get("TOKENIZER_PATH", MODEL_PATH)
tokenizer = AutoTokenizer.from_pretrained(TOKENIZER_PATH, trust_remote_code=True)
model... | # ChatGLM3
<p align="center">
📄<a href="https://arxiv.org/pdf/2406.12793" target="_blank"> Report </a> • 🤗 <a href="https://huggingface.co/THUDM/chatglm3-6b" target="_blank">HF Repo</a> • 🤖 <a href="https://modelscope.cn/models/ZhipuAI/chatglm3-6b" target="_blank">ModelScope</a> • 🟣 <a href="https://www.wisemodel.... |
diagrams | 4c2d8a3795d2a15a168224b2a5919c2950df679b | File: config.py
# fmt: off
#########################
# Application #
#########################
APP_NAME = "diagrams"
DIR_DOC_ROOT = "docs/nodes"
DIR_APP_ROOT = "diagrams"
DIR_RESOURCE = "resources"
DIR_TEMPLATE = "templates"
PROVIDERS = (
"base",
"onprem",
"aws",
"azure",
"digitalocea... | 
# Diagrams
[](/LICENSE)
[](https://badge.fury.io/py/diagrams)
![Run tests](h... |
Mask_RCNN | 3deaec5d902d16e1daf56b62d5971d428dc920bc | File: setup.py
"""
The build/compilations setup
>> pip install -r requirements.txt
>> python setup.py install
"""
import pip
import logging
import pkg_resources
try:
from setuptools import setup
except ImportError:
from distutils.core import setup
def _parse_requirements(file_path):
pip_ver = pkg_resour... | # Mask R-CNN for Object Detection and Segmentation
This is an implementation of [Mask R-CNN](https://arxiv.org/abs/1703.06870) on Python 3, Keras, and TensorFlow. The model generates bounding boxes and segmentation masks for each instance of an object in the image. It's based on Feature Pyramid Network (FPN) and a Res... |
ungoogled-chromium | 1b11ca4600fc48faaa77260d53e20e259c0ee180 | File: utils/filescfg.py
#!/usr/bin/env python3
# -*- coding: UTF-8 -*-
# Copyright (c) 2019 The ungoogled-chromium Authors. All rights reserved.
# Use of this source code is governed by a BSD-style license that can be
# found in the LICENSE file.
"""
Operations with FILES.cfg (for portable packages)
"""
import argpa... | # ungoogled-chromium
*A lightweight approach to removing Google web service dependency*
**Help is welcome!** See the [docs/contributing.md](docs/contributing.md) document for more information.
## Objectives
In descending order of significance (i.e. most important objective first):
1. **ungoogled-chromium is Google... |
wifiphisher | bc4a077e090d59b065cf2c65b0ec1890b9eb4698 | File: setup.py
#!/usr/bin/env python3
r"""
_ __ _ _ _ _
(_)/ _(_) | | (_) | |
((.)) __ ___| |_ _ _ __ | |__ _ ___| |__ ___ _ __
| \ \ /\ / / | _| | '_ \| '_ \| / __| '_ \ / _ \ '__|
/_\ \ V V /| | | | | |_) | | | | \__ \ | ... | [](https://travis-ci.org/wifiphisher/wifiphisher)
[](http://wifiphisher.readthedocs.io/en/latest/?badge=latest)
![Python Version](https://img.shields... |
flask | 2fec0b206c6e83ea813ab26597e15c96fab08be7 | File: docs/conf.py
import packaging.version
from pallets_sphinx_themes import get_version
from pallets_sphinx_themes import ProjectLink
# Project --------------------------------------------------------------
project = "Flask"
copyright = "2010 Pallets"
author = "Pallets"
release, version = get_version("Flask")
# G... | # Flask
Flask is a lightweight [WSGI][] web application framework. It is designed
to make getting started quick and easy, with the ability to scale up to
complex applications. It began as a simple wrapper around [Werkzeug][]
and [Jinja][], and has become one of the most popular Python web
application frameworks.
Flas... |
vit-pytorch | fcb9501cdd9e056dd040915deb3e0a6378821843 | File: setup.py
from setuptools import setup, find_packages
with open('README.md') as f:
long_description = f.read()
setup(
name = 'vit-pytorch',
packages = find_packages(exclude=['examples']),
version = '1.7.12',
license='MIT',
description = 'Vision Transformer (ViT) - Pytorch',
long_description=long... | <img src="./images/vit.gif" width="500px"></img>
## Table of Contents
- [Vision Transformer - Pytorch](#vision-transformer---pytorch)
- [Install](#install)
- [Usage](#usage)
- [Parameters](#parameters)
- [Simple ViT](#simple-vit)
- [NaViT](#navit)
- [Distillation](#distillation)
- [Deep ViT](#deep-vit)
- [CaiT](#cait... |
awesome-oss-alternatives | 09d7f8b76ef063c5987caf6361110904f449ece6 | File: sort.py
def sort_readme():
with open("README.md", "r", encoding="utf-8") as f:
all = f.readlines()
table_start = "|Category|Company|Description|GitHub Stars|Alternative to|\n"
table_end = "<!-- END STARTUP LIST -->\n"
idx = all.index(table_start)
idx_end = all.index(table_end)
... | # Awesome open-source alternatives to SaaS
[](https://github.com/sindresorhus/awesome)
Awesome list of open-source startup alternatives to established SaaS products. Maintained by folks at [![Runa Capital](h... |
python-patterns | 328b2d469e92d6a0dfe17d37d3b180412723db45 | File: setup.py
from setuptools import find_packages, setup
setup(
name="patterns",
packages=find_packages(),
description="A collection of design patterns and idioms in Python.",
classifiers=[
"Programming Language :: Python :: 2",
"Programming Language :: Python :: 2.7",
"Progr... | python-patterns
===============
A collection of design patterns and idioms in Python.
Remember that each pattern has its own trade-offs. And you need to pay attention more to why you're choosing a certain pattern than to how to implement it.
Current Patterns
----------------
__Creational Patterns__:
| Pattern | De... |
awesome-free-chatgpt | da28eb22153b4a34eae188335a27f14d411f7d6c | File: convert.py
# convert the urls in README.md to json format, and save it to urls.json, colapse the same urls, remove the last `/` in the url
import json
import re
# Read the content of README.md
with open("README.md", "r", encoding="utf-8") as file:
content = file.read()
# Stop reading when reaching a l... | # Awesome Free ChatGPT
 [](README_en.md)  
import os
import sys
from app import app, CONFIG
if '--debug' in sys.argv:
# Not all debug mode features are available under `gevent`
# https://g... |
Unified access to the best community driven cheat sheets repositories of the world.
Let's imagine for a moment that there is such a thing as an ideal cheat sheet.
What should it look like?
What features should it have?
* **Concise** — It should only con... |
shadowsocks | 938bba32a4008bdde9c064dda6a0597987ddef54 | Removed according to regulations.
| |
12306 | a495af88346a0d794493c6030f6a6207debb5824 | File: run.py
# -*- coding=utf-8 -*-
import argparse
import sys
def parser_arguments(argv):
"""
不应该在这里定义，先放在这里
:param argv:
:return:
"""
parser = argparse.ArgumentParser()
parser.add_argument("operate", type=str, help="r: 运行抢票程序, c: 过滤cdn, t: 测试邮箱和server酱，server酱需要打开开关")
return parser... | ### 12306 购票小助手
#### python版本
- [ ] 2.7.10 - 2.7.15
- [x] 3.6 - 3.7.4
- [ ] 2.7.9
#### 已有功能
- [x] 自动打码
- [x] 自动登录
- [x] 准点预售和捡漏
- [x] 智能候补
- [x] 邮件通知
- [x] server酱通知
#### 依赖库
- 验证码目前可以本地识别，需要下载模型，放于项目根目录，全部代码来源于此项目 [传送门](https://github.com/zhaipro/easy12306)，表示感谢
```
1. 模型下载链接:https://pa... |
Llama-Chinese | ecff929b627122ef10da3f7ed2085caf793ba7e5 | File: scripts/api/accelerate_client.py
# coding=utf-8
import json
import time
import urllib.request
import sys
def test_api_server(input_text):
header = {'Content-Type': 'application/json'}
data = {
"system_prompt": "",
"history": inputs,
"n" : 1,
"best_of": 1,
... | <p align="left">
<a href="README_EN.md">English</a> ｜ 中文
</p>
<h1 align="center">
Llama中文社区
</h1>
<p align="center" width="100%">
<img src="assets/llama.jpg" alt="Llama" style="width: 20%; display: block; margin: auto;"></a>
</p>
<p align="center">
<font face="黑体" color=orange size="6"> Llama3体验和微调已开放，最好的中文L... |
cookiecutter | b4451231809fb9e4fc2a1e95d433cb030e4b9e06 | File: setup.py
"""cookiecutter distutils configuration."""
from pathlib import Path
from setuptools import setup
def _get_version() -> str:
"""Read cookiecutter/VERSION.txt and return its contents."""
path = Path("cookiecutter").resolve()
version_file = path / "VERSION.txt"
return version_file.read... | <h1 align="center">
<img alt="cookiecutter Logo" width="200px" src="https://raw.githubusercontent.com/cookiecutter/cookiecutter/3ac078356adf5a1a72042dfe72ebfa4a9cd5ef38/logo/cookiecutter_medium.png">
</h1>
<div align="center">
[](https://pypi.org/project/cook... |
marker | 6534333c6a53e023152d85d76d28563977c6ccfc | File: marker_app.py
import os
os.environ["PYTORCH_ENABLE_MPS_FALLBACK"] = "1"
os.environ["IN_STREAMLIT"] = "true"
import base64
import io
import re
import tempfile
from typing import List, Any, Dict
import pypdfium2
import streamlit as st
from marker.convert import convert_single_pdf
from marker.models import load_... | # Marker
Marker converts PDF to markdown quickly and accurately.
- Supports a wide range of documents (optimized for books and scientific papers)
- Supports all languages
- Removes headers/footers/other artifacts
- Formats tables and code blocks
- Extracts and saves images along with the markdown
- Converts most equa... |
12306 | a495af88346a0d794493c6030f6a6207debb5824 | File: run.py
# -*- coding=utf-8 -*-
import argparse
import sys
def parser_arguments(argv):
"""
不应该在这里定义，先放在这里
:param argv:
:return:
"""
parser = argparse.ArgumentParser()
parser.add_argument("operate", type=str, help="r: 运行抢票程序, c: 过滤cdn, t: 测试邮箱和server酱，server酱需要打开开关")
return parser... | ### 12306 购票小助手
#### python版本
- [ ] 2.7.10 - 2.7.15
- [x] 3.6 - 3.7.4
- [ ] 2.7.9
#### 已有功能
- [x] 自动打码
- [x] 自动登录
- [x] 准点预售和捡漏
- [x] 智能候补
- [x] 邮件通知
- [x] server酱通知
#### 依赖库
- 验证码目前可以本地识别，需要下载模型，放于项目根目录，全部代码来源于此项目 [传送门](https://github.com/zhaipro/easy12306)，表示感谢
```
1. 模型下载链接:https://pa... |
codellama | e81b597e44dbecc2a0dedb9949fdf84adfc22395 | File: example_infilling.py
# Copyright (c) Meta Platforms, Inc. and affiliates.
# This software may be used and distributed according to the terms of the Llama 2 Community License Agreement.
import fire
from llama import Llama
def main(
ckpt_dir: str,
tokenizer_path: str,
temperature: float = 0.0,
... | # Introducing Code Llama
Code Llama is a family of large language models for code based on [Llama 2](https://github.com/facebookresearch/llama) providing state-of-the-art performance among open models, infilling capabilities, support for large input contexts, and zero-shot instruction following ability for programming... |
GitHub520 | 586c0d2e2bebb5962c4419edada24a3a416c9e3d | File: fetch_ips.py
#!/usr/bin/env python
# -*- coding:utf-8 -*-
#
# Author : XueWeiHan
# E-mail : 595666367@qq.com
# Date : 2020-05-19 15:27
# Desc : 获取最新的 GitHub 相关域名对应 IP
import os
import re
import json
from typing import Any, Optional
from datetime import datetime, timezone, timedelta
f... | # GitHub520
<p align="center">
<a href="https://hellogithub.com/repository/d05ff820bf36470581c02cda5cbd17ea" target="_blank"><img src="https://api.hellogithub.com/v1/widgets/recommend.svg?rid=d05ff820bf36470581c02cda5cbd17ea&claim_uid=8MKvZoxaWt" alt="Featured｜HelloGitHub" style="width: 250px; height: 54px;" width="25... |
shadowsocks | 938bba32a4008bdde9c064dda6a0597987ddef54 | Removed according to regulations.
| |
Real-Time-Voice-Cloning | 911679d0c27fb57cde8ef2b5967e9ed2dd543e10 | File: encoder_preprocess.py
from encoder.preprocess import preprocess_librispeech, preprocess_voxceleb1, preprocess_voxceleb2
from utils.argutils import print_args
from pathlib import Path
import argparse
if __name__ == "__main__":
class MyFormatter(argparse.ArgumentDefaultsHelpFormatter, argparse.RawDescription... | # Real-Time Voice Cloning
This repository is an implementation of [Transfer Learning from Speaker Verification to
Multispeaker Text-To-Speech Synthesis](https://arxiv.org/pdf/1806.04558.pdf) (SV2TTS) with a vocoder that works in real-time. This was my [master's thesis](https://matheo.uliege.be/handle/2268.2/6801).
SV2... |
OSX-KVM | 182e2dd0715175801521f6342ac7cc715044cb12 | File: fetch-macOS-v2.py
#!/usr/bin/env python3
# pylint: disable=C0301,C0116,C0103,R0903
"""
Gather recovery information for Macs.
Copyright (c) 2019, vit9696
macrecovery is a tool that helps to automate recovery interaction. It can be
used to download diagnostics and recovery as well as analyse MLB.
Requires pyth... | ### Note
This `README.md` documents the process of creating a `Virtual Hackintosh`
system.
Note: All blobs and resources included in this repository are re-derivable (all
instructions are included!).
:green_heart: Looking for **commercial** support with this stuff? I am [available
over email](mailto:dhiru.kholia@gma... |
cli | f4cf43ecdd6c5c52b5c4ba91086d5c6ccfebcd6d | File: setup.py
from setuptools import setup
setup()
File: docs/installation/generate.py
import re
import sys
from pathlib import Path
from typing import Dict
import yaml
from jinja2 import Template
Database = Dict[str, dict]
# Files
HERE = Path(__file__).parent
DB_FILE = HERE / 'methods.yml'
DOC_FILE = HERE.pa... | <h2 align="center">
<a href="https://httpie.io" target="blank_">
<img height="100" alt="HTTPie" src="https://raw.githubusercontent.com/httpie/cli/master/docs/httpie-logo.svg" />
</a>
<br>
HTTPie CLI: human-friendly HTTP client for the API era
</h2>
<div align="center">
[
https://pytorch.org/examples/
`pytorch/examples` is a repository showcasing examples of using [PyTorch](https://github.com/pytorch/pytorch). The goal is to have curated, short, few/no dependencies _high quality... | |
localGPT | a1dea3becb8b1ae28a87369b1636c4c4a4501c27 | File: localGPT_UI.py
import torch
import subprocess
import streamlit as st
from run_localGPT import load_model
from langchain.vectorstores import Chroma
from constants import CHROMA_SETTINGS, EMBEDDING_MODEL_NAME, PERSIST_DIRECTORY, MODEL_ID, MODEL_BASENAME
from langchain.embeddings import HuggingFaceInstructEmbedding... | # LocalGPT: Secure, Local Conversations with Your Documents 🌐
[](https://github.com/PromtEngineer/localGPT/stargazers)
[](https://github.com/... |
Python-100-Days | bf24146944745bb25c66c82307fd218abd179c6a | File: Day31-35/code/josephu.py
def main():
persons = [True] * 30
counter = 0
index = 0
number = 0
while counter < 15:
if persons[index]:
number += 1
if number == 9:
persons[index] = False
number = 0
counter += 1
... | ## Python - 100天从新手到大师
> **作者**：骆昊
>
> **说明**：从项目上线到获得8w+星标以来，一直收到反馈说基础部分（前15天的内容）对新手来说是比较困难的，建议有配套视频进行讲解。最近把基础部分的内容重新制作了一个名为[“Python-Core-50-Courses”](<https://github.com/jackfrued/Python-Core-50-Courses>)的项目，用更为简单通俗的方式重写了这部分内容并附带了视频讲解，初学者可以看看这个新的仓库。国内用户如果访问GitHub比较慢的话，可以关注我的**知乎号[Python-Jack](https://www.zhihu.com/p... |
ChatterBot | 4ff8af28567ed446ae796d37c246bb6a14032fe7 | File: setup.py
#!/usr/bin/env python
"""
ChatterBot setup file.
"""
import os
import sys
import platform
import configparser
from setuptools import setup
if sys.version_info[0] < 3:
raise Exception(
'You are tying to install ChatterBot on Python version {}.\n'
'Please install ChatterBot in Python... | 
# ChatterBot
ChatterBot is a machine-learning based conversational dialog engine build in
Python which makes it possible to generate responses based on collections of
known conversations. The language independent design of ChatterBot allows it... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.