File size: 7,293 Bytes
5e9fb2f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
#######################################################################################
#
# Adapted from:
#  https://github.com/pypa/hatch/blob/5352e44/backend/src/hatchling/licenses/parse.py
#
# MIT License
#
# Copyright (c) 2017-present Ofek Lev <oss@ofek.dev>
#
# Permission is hereby granted, free of charge, to any person obtaining a copy of this
# software and associated documentation files (the "Software"), to deal in the Software
# without restriction, including without limitation the rights to use, copy, modify,
# merge, publish, distribute, sublicense, and/or sell copies of the Software, and to
# permit persons to whom the Software is furnished to do so, subject to the following
# conditions:
#
# The above copyright notice and this permission notice shall be included in all copies
# or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED,
# INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A
# PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
# HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF
# CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE
# OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
#
#
# With additional allowance of arbitrary `LicenseRef-` identifiers, not just
# `LicenseRef-Public-Domain` and `LicenseRef-Proprietary`.
#
#######################################################################################
from __future__ import annotations

import re
from typing import NewType, cast

from ._spdx import EXCEPTIONS, LICENSES

__all__ = [
    "InvalidLicenseExpression",
    "NormalizedLicenseExpression",
    "canonicalize_license_expression",
]


# Simple __dir__ implementation since there are no public submodules
def __dir__() -> list[str]:
    return __all__


license_ref_allowed = re.compile("^[A-Za-z0-9.-]*$")

NormalizedLicenseExpression = NewType("NormalizedLicenseExpression", str)
"""
A :class:`typing.NewType` of :class:`str`, representing a normalized
License-Expression.
"""


class InvalidLicenseExpression(ValueError):
    """Raised when a license-expression string is invalid

    >>> from packaging.licenses import canonicalize_license_expression
    >>> canonicalize_license_expression("invalid")
    Traceback (most recent call last):
        ...
    packaging.licenses.InvalidLicenseExpression: Invalid license expression: 'invalid'
    """


def canonicalize_license_expression(
    raw_license_expression: str,
) -> NormalizedLicenseExpression:
    """
    This function takes a valid License-Expression, and returns the normalized
    form of it.

    The return type is typed as :class:`NormalizedLicenseExpression`. This
    allows type checkers to help require that a string has passed through this
    function before use.

    :param str raw_license_expression: The License-Expression to canonicalize.
    :raises InvalidLicenseExpression: If the License-Expression is invalid due to an
        invalid/unknown license identifier or invalid syntax.

    .. doctest::

        >>> from packaging.licenses import canonicalize_license_expression
        >>> canonicalize_license_expression("mit")
        'MIT'
        >>> canonicalize_license_expression("mit and (apache-2.0 or bsd-2-clause)")
        'MIT AND (Apache-2.0 OR BSD-2-Clause)'
        >>> canonicalize_license_expression("(mit")
        Traceback (most recent call last):
          ...
        InvalidLicenseExpression: Invalid license expression: '(mit'
        >>> canonicalize_license_expression("Use-it-after-midnight")
        Traceback (most recent call last):
          ...
        InvalidLicenseExpression: Unknown license: 'Use-it-after-midnight'
    """
    if not raw_license_expression:
        message = f"Invalid license expression: {raw_license_expression!r}"
        raise InvalidLicenseExpression(message)

    # Pad any parentheses so tokenization can be achieved by merely splitting on
    # whitespace.
    license_expression = raw_license_expression.replace("(", " ( ").replace(")", " ) ")
    licenseref_prefix = "LicenseRef-"
    license_refs = {
        ref.lower(): "LicenseRef-" + ref[len(licenseref_prefix) :]
        for ref in license_expression.split()
        if ref.lower().startswith(licenseref_prefix.lower())
    }

    # Normalize to lower case so we can look up licenses/exceptions
    # and so boolean operators are Python-compatible.
    license_expression = license_expression.lower()

    tokens = license_expression.split()

    # Rather than implementing a parenthesis/boolean logic parser, create an
    # expression that Python can parse. Everything that is not involved with the
    # grammar itself is replaced with the placeholder `False` and the resultant
    # expression should become a valid Python expression.
    python_tokens = []
    for token in tokens:
        if token not in {"or", "and", "with", "(", ")"}:
            python_tokens.append("False")
        elif token == "with":
            python_tokens.append("or")
        elif (
            token == "("
            and python_tokens
            and python_tokens[-1] not in {"or", "and", "("}
        ) or (token == ")" and python_tokens and python_tokens[-1] == "("):
            message = f"Invalid license expression: {raw_license_expression!r}"
            raise InvalidLicenseExpression(message)
        else:
            python_tokens.append(token)

    python_expression = " ".join(python_tokens)
    try:
        compile(python_expression, "", "eval")
    except SyntaxError:
        message = f"Invalid license expression: {raw_license_expression!r}"
        raise InvalidLicenseExpression(message) from None

    # Take a final pass to check for unknown licenses/exceptions.
    normalized_tokens = []
    for token in tokens:
        if token in {"or", "and", "with", "(", ")"}:
            normalized_tokens.append(token.upper())
            continue

        if normalized_tokens and normalized_tokens[-1] == "WITH":
            if token not in EXCEPTIONS:
                message = f"Unknown license exception: {token!r}"
                raise InvalidLicenseExpression(message)

            normalized_tokens.append(EXCEPTIONS[token]["id"])
        else:
            if token.endswith("+"):
                final_token = token[:-1]
                suffix = "+"
            else:
                final_token = token
                suffix = ""

            if final_token.startswith("licenseref-"):
                if not license_ref_allowed.match(final_token):
                    message = f"Invalid licenseref: {final_token!r}"
                    raise InvalidLicenseExpression(message)
                normalized_tokens.append(license_refs[final_token] + suffix)
            else:
                if final_token not in LICENSES:
                    message = f"Unknown license: {final_token!r}"
                    raise InvalidLicenseExpression(message)
                normalized_tokens.append(LICENSES[final_token]["id"] + suffix)

    normalized_expression = " ".join(normalized_tokens)

    return cast(
        "NormalizedLicenseExpression",
        normalized_expression.replace("( ", "(").replace(" )", ")"),
    )