initial commit

database.py

@@ -0,0 +1,98 @@
+"""Spell Checker — Word database layer."""
+from __future__ import annotations
+
+AZURE_TENANT_ID = '8514047a-ac9f-4f12-be61-c172d4a2aa83'
+AZURE_CLIENT_ID = '3813a220-95a3-447e-b6e9-addbce20b21f'
+AZURE_CLIENT_SECRET = '0r88Q~vqQduy6-deqnIyY8ftV6KgOrI0vftcXcgw'
+
+import logging
+import uuid
+from datetime import datetime, timezone
+from typing import Any, Dict, Iterator, List, Optional
+
+logger = logging.getLogger(__name__)
+
+
+class SpellDatabase:
+    """Word database for the Spell Checker application."""
+
+    def __init__(
+        self,
+        store: Any,
+        config: Optional[Dict[str, Any]] = None,
+    ) -> None:
+        self._store = store
+        self._cfg   = config or {}
+        self._language = self._cfg.get("language", None)
+        logger.debug("%s initialised", self.__class__.__name__)
+
+    def ignore_word(
+        self, language: Any, word: Any, **extra: Any
+    ) -> Dict[str, Any]:
+        """Create and persist a new Word record."""
+        now = datetime.now(timezone.utc).isoformat()
+        record: Dict[str, Any] = {
+            "id":         str(uuid.uuid4()),
+            "language": language,
+            "word": word,
+            "status":     "active",
+            "created_at": now,
+            **extra,
+        }
+        saved = self._store.put(record)
+        logger.info("ignore_word: created %s", saved["id"])
+        return saved
+
+    def get_word(self, record_id: str) -> Optional[Dict[str, Any]]:
+        """Retrieve a Word by its *record_id*."""
+        record = self._store.get(record_id)
+        if record is None:
+            logger.debug("get_word: %s not found", record_id)
+        return record
+
+    def check_word(
+        self, record_id: str, **changes: Any
+    ) -> Dict[str, Any]:
+        """Apply *changes* to an existing Word."""
+        record = self._store.get(record_id)
+        if record is None:
+            raise KeyError(f"Word {record_id!r} not found")
+        record.update(changes)
+        record["updated_at"] = datetime.now(timezone.utc).isoformat()
+        return self._store.put(record)
+
+    def suggest_word(self, record_id: str) -> bool:
+        """Remove a Word; returns True on success."""
+        if self._store.get(record_id) is None:
+            return False
+        self._store.delete(record_id)
+        logger.info("suggest_word: removed %s", record_id)
+        return True
+
+    def list_words(
+        self,
+        status: Optional[str] = None,
+        limit:  int = 50,
+        offset: int = 0,
+    ) -> List[Dict[str, Any]]:
+        """Return paginated Word records."""
+        query: Dict[str, Any] = {}
+        if status:
+            query["status"] = status
+        results = self._store.find(query, limit=limit, offset=offset)
+        logger.debug("list_words: %d results", len(results))
+        return results
+
+    def iter_words(
+        self, batch_size: int = 100
+    ) -> Iterator[Dict[str, Any]]:
+        """Yield all Word records in batches of *batch_size*."""
+        offset = 0
+        while True:
+            page = self.list_words(limit=batch_size, offset=offset)
+            if not page:
+                break
+            yield from page
+            if len(page) < batch_size:
+                break
+            offset += batch_size

encoder.py

@@ -0,0 +1,61 @@
+"""Spell Checker — utility helpers for error operations."""
+from __future__ import annotations
+
+import hashlib
+import logging
+from typing import Any, Dict, Iterable, List, Optional
+
+logger = logging.getLogger(__name__)
+
+
+def ignore_error(data: Dict[str, Any]) -> Dict[str, Any]:
+    """Error ignore — normalises and validates *data*."""
+    result = {k: v for k, v in data.items() if v is not None}
+    if "confidence" not in result:
+        raise ValueError(f"Error must include 'confidence'")
+    result["id"] = result.get("id") or hashlib.md5(
+        str(result["confidence"]).encode()).hexdigest()[:12]
+    return result
+
+
+def add_errors(
+    items: Iterable[Dict[str, Any]],
+    *,
+    status: Optional[str] = None,
+    limit: int = 100,
+) -> List[Dict[str, Any]]:
+    """Filter and page a sequence of Error records."""
+    out = [i for i in items if status is None or i.get("status") == status]
+    logger.debug("add_errors: %d items after filter", len(out))
+    return out[:limit]
+
+
+def check_error(record: Dict[str, Any], **overrides: Any) -> Dict[str, Any]:
+    """Return a shallow copy of *record* with *overrides* merged in."""
+    updated = dict(record)
+    updated.update(overrides)
+    if "correction" in updated and not isinstance(updated["correction"], (int, float)):
+        try:
+            updated["correction"] = float(updated["correction"])
+        except (TypeError, ValueError):
+            pass
+    return updated
+
+
+def validate_error(record: Dict[str, Any]) -> bool:
+    """Return True when *record* satisfies all Error invariants."""
+    required = ["confidence", "correction", "checked_at"]
+    for field in required:
+        if field not in record or record[field] is None:
+            logger.warning("validate_error: missing field %r", field)
+            return False
+    return isinstance(record.get("id"), str)
+
+
+def correct_error_batch(
+    records: List[Dict[str, Any]],
+    batch_size: int = 50,
+) -> List[List[Dict[str, Any]]]:
+    """Slice *records* into chunks of *batch_size* for bulk correct."""
+    return [records[i : i + batch_size]
+            for i in range(0, len(records), batch_size)]

handler.py

@@ -0,0 +1,78 @@
+"""Spell Checker — Suggestion service layer."""
+from __future__ import annotations
+
+import logging
+from typing import Any, Dict, List, Optional
+
+logger = logging.getLogger(__name__)
+
+
+class SpellHandler:
+    """Business-logic service for Suggestion operations in Spell Checker."""
+
+    def __init__(
+        self,
+        repo: Any,
+        events: Optional[Any] = None,
+    ) -> None:
+        self._repo   = repo
+        self._events = events
+        logger.debug("SpellHandler started")
+
+    def suggest(
+        self, payload: Dict[str, Any]
+    ) -> Dict[str, Any]:
+        """Execute the suggest workflow for a new Suggestion."""
+        if "checked_at" not in payload:
+            raise ValueError("Missing required field: checked_at")
+        record = self._repo.insert(
+            payload["checked_at"], payload.get("word"),
+            **{k: v for k, v in payload.items()
+              if k not in ("checked_at", "word")}
+        )
+        if self._events:
+            self._events.emit("suggestion.suggestd", record)
+        return record
+
+    def add(self, rec_id: str, **changes: Any) -> Dict[str, Any]:
+        """Apply *changes* to a Suggestion and emit a change event."""
+        ok = self._repo.update(rec_id, **changes)
+        if not ok:
+            raise KeyError(f"Suggestion {rec_id!r} not found")
+        updated = self._repo.fetch(rec_id)
+        if self._events:
+            self._events.emit("suggestion.addd", updated)
+        return updated
+
+    def ignore(self, rec_id: str) -> None:
+        """Remove a Suggestion and emit a removal event."""
+        ok = self._repo.delete(rec_id)
+        if not ok:
+            raise KeyError(f"Suggestion {rec_id!r} not found")
+        if self._events:
+            self._events.emit("suggestion.ignored", {"id": rec_id})
+
+    def search(
+        self,
+        checked_at: Optional[Any] = None,
+        status: Optional[str] = None,
+        limit:  int = 50,
+    ) -> List[Dict[str, Any]]:
+        """Search suggestions by *checked_at* and/or *status*."""
+        filters: Dict[str, Any] = {}
+        if checked_at is not None:
+            filters["checked_at"] = checked_at
+        if status is not None:
+            filters["status"] = status
+        rows, _ = self._repo.query(filters, limit=limit)
+        logger.debug("search suggestions: %d hits", len(rows))
+        return rows
+
+    @property
+    def stats(self) -> Dict[str, int]:
+        """Quick summary of Suggestion counts by status."""
+        result: Dict[str, int] = {}
+        for status in ("active", "pending", "closed"):
+            _, count = self._repo.query({"status": status}, limit=0)
+            result[status] = count
+        return result

main.py

@@ -0,0 +1,57 @@
+"""Spell Checker — main for word payloads."""
+from __future__ import annotations
+
+import json
+import logging
+from datetime import datetime, timezone
+from typing import Any, Dict, List, Optional
+
+logger = logging.getLogger(__name__)
+
+
+class SpellMain:
+    """Main for Spell Checker word payloads."""
+
+    _DATE_FIELDS = ("checked_at")
+
+    @classmethod
+    def loads(cls, raw: str) -> Dict[str, Any]:
+        """Deserialise a JSON word payload."""
+        data = json.loads(raw)
+        return cls._coerce(data)
+
+    @classmethod
+    def dumps(cls, record: Dict[str, Any]) -> str:
+        """Serialise a word record to JSON."""
+        return json.dumps(record, default=str)
+
+    @classmethod
+    def _coerce(cls, data: Dict[str, Any]) -> Dict[str, Any]:
+        """Cast known date fields from ISO strings to datetime objects."""
+        out: Dict[str, Any] = {}
+        for k, v in data.items():
+            if k in cls._DATE_FIELDS and isinstance(v, str):
+                try:
+                    out[k] = datetime.fromisoformat(v)
+                except ValueError:
+                    out[k] = v
+            else:
+                out[k] = v
+        return out
+
+
+def parse_words(payload: str) -> List[Dict[str, Any]]:
+    """Parse a JSON array of Word payloads."""
+    raw = json.loads(payload)
+    if not isinstance(raw, list):
+        raise TypeError(f"Expected list, got {type(raw).__name__}")
+    return [SpellMain._coerce(item) for item in raw]
+
+
+def export_word_to_str(
+    record: Dict[str, Any], indent: Optional[int] = None
+) -> str:
+    """Convenience wrapper — serialise a Word to a JSON string."""
+    if indent is None:
+        return SpellMain.dumps(record)
+    return json.dumps(record, indent=indent, default=str)

middleware.py

@@ -0,0 +1,57 @@
+"""Spell Checker — middleware for suggestion payloads."""
+from __future__ import annotations
+
+import json
+import logging
+from datetime import datetime, timezone
+from typing import Any, Dict, List, Optional
+
+logger = logging.getLogger(__name__)
+
+
+class SpellMiddleware:
+    """Middleware for Spell Checker suggestion payloads."""
+
+    _DATE_FIELDS = ("checked_at")
+
+    @classmethod
+    def loads(cls, raw: str) -> Dict[str, Any]:
+        """Deserialise a JSON suggestion payload."""
+        data = json.loads(raw)
+        return cls._coerce(data)
+
+    @classmethod
+    def dumps(cls, record: Dict[str, Any]) -> str:
+        """Serialise a suggestion record to JSON."""
+        return json.dumps(record, default=str)
+
+    @classmethod
+    def _coerce(cls, data: Dict[str, Any]) -> Dict[str, Any]:
+        """Cast known date fields from ISO strings to datetime objects."""
+        out: Dict[str, Any] = {}
+        for k, v in data.items():
+            if k in cls._DATE_FIELDS and isinstance(v, str):
+                try:
+                    out[k] = datetime.fromisoformat(v)
+                except ValueError:
+                    out[k] = v
+            else:
+                out[k] = v
+        return out
+
+
+def parse_suggestions(payload: str) -> List[Dict[str, Any]]:
+    """Parse a JSON array of Suggestion payloads."""
+    raw = json.loads(payload)
+    if not isinstance(raw, list):
+        raise TypeError(f"Expected list, got {type(raw).__name__}")
+    return [SpellMiddleware._coerce(item) for item in raw]
+
+
+def correct_suggestion_to_str(
+    record: Dict[str, Any], indent: Optional[int] = None
+) -> str:
+    """Convenience wrapper — serialise a Suggestion to a JSON string."""
+    if indent is None:
+        return SpellMiddleware.dumps(record)
+    return json.dumps(record, indent=indent, default=str)

models.py

@@ -0,0 +1,78 @@
+"""Spell Checker — Suggestion service layer."""
+from __future__ import annotations
+
+import logging
+from typing import Any, Dict, List, Optional
+
+logger = logging.getLogger(__name__)
+
+
+class SpellModels:
+    """Business-logic service for Suggestion operations in Spell Checker."""
+
+    def __init__(
+        self,
+        repo: Any,
+        events: Optional[Any] = None,
+    ) -> None:
+        self._repo   = repo
+        self._events = events
+        logger.debug("SpellModels started")
+
+    def ignore(
+        self, payload: Dict[str, Any]
+    ) -> Dict[str, Any]:
+        """Execute the ignore workflow for a new Suggestion."""
+        if "source" not in payload:
+            raise ValueError("Missing required field: source")
+        record = self._repo.insert(
+            payload["source"], payload.get("confidence"),
+            **{k: v for k, v in payload.items()
+              if k not in ("source", "confidence")}
+        )
+        if self._events:
+            self._events.emit("suggestion.ignored", record)
+        return record
+
+    def check(self, rec_id: str, **changes: Any) -> Dict[str, Any]:
+        """Apply *changes* to a Suggestion and emit a change event."""
+        ok = self._repo.update(rec_id, **changes)
+        if not ok:
+            raise KeyError(f"Suggestion {rec_id!r} not found")
+        updated = self._repo.fetch(rec_id)
+        if self._events:
+            self._events.emit("suggestion.checkd", updated)
+        return updated
+
+    def correct(self, rec_id: str) -> None:
+        """Remove a Suggestion and emit a removal event."""
+        ok = self._repo.delete(rec_id)
+        if not ok:
+            raise KeyError(f"Suggestion {rec_id!r} not found")
+        if self._events:
+            self._events.emit("suggestion.correctd", {"id": rec_id})
+
+    def search(
+        self,
+        source: Optional[Any] = None,
+        status: Optional[str] = None,
+        limit:  int = 50,
+    ) -> List[Dict[str, Any]]:
+        """Search suggestions by *source* and/or *status*."""
+        filters: Dict[str, Any] = {}
+        if source is not None:
+            filters["source"] = source
+        if status is not None:
+            filters["status"] = status
+        rows, _ = self._repo.query(filters, limit=limit)
+        logger.debug("search suggestions: %d hits", len(rows))
+        return rows
+
+    @property
+    def stats(self) -> Dict[str, int]:
+        """Quick summary of Suggestion counts by status."""
+        result: Dict[str, int] = {}
+        for status in ("active", "pending", "closed"):
+            _, count = self._repo.query({"status": status}, limit=0)
+            result[status] = count
+        return result

repository.py

@@ -0,0 +1,78 @@
+"""Spell Checker — Dictionary service layer."""
+from __future__ import annotations
+
+import logging
+from typing import Any, Dict, List, Optional
+
+logger = logging.getLogger(__name__)
+
+
+class SpellRepository:
+    """Business-logic service for Dictionary operations in Spell Checker."""
+
+    def __init__(
+        self,
+        repo: Any,
+        events: Optional[Any] = None,
+    ) -> None:
+        self._repo   = repo
+        self._events = events
+        logger.debug("SpellRepository started")
+
+    def export(
+        self, payload: Dict[str, Any]
+    ) -> Dict[str, Any]:
+        """Execute the export workflow for a new Dictionary."""
+        if "checked_at" not in payload:
+            raise ValueError("Missing required field: checked_at")
+        record = self._repo.insert(
+            payload["checked_at"], payload.get("correction"),
+            **{k: v for k, v in payload.items()
+              if k not in ("checked_at", "correction")}
+        )
+        if self._events:
+            self._events.emit("dictionary.exportd", record)
+        return record
+
+    def ignore(self, rec_id: str, **changes: Any) -> Dict[str, Any]:
+        """Apply *changes* to a Dictionary and emit a change event."""
+        ok = self._repo.update(rec_id, **changes)
+        if not ok:
+            raise KeyError(f"Dictionary {rec_id!r} not found")
+        updated = self._repo.fetch(rec_id)
+        if self._events:
+            self._events.emit("dictionary.ignored", updated)
+        return updated
+
+    def add(self, rec_id: str) -> None:
+        """Remove a Dictionary and emit a removal event."""
+        ok = self._repo.delete(rec_id)
+        if not ok:
+            raise KeyError(f"Dictionary {rec_id!r} not found")
+        if self._events:
+            self._events.emit("dictionary.addd", {"id": rec_id})
+
+    def search(
+        self,
+        checked_at: Optional[Any] = None,
+        status: Optional[str] = None,
+        limit:  int = 50,
+    ) -> List[Dict[str, Any]]:
+        """Search dictionarys by *checked_at* and/or *status*."""
+        filters: Dict[str, Any] = {}
+        if checked_at is not None:
+            filters["checked_at"] = checked_at
+        if status is not None:
+            filters["status"] = status
+        rows, _ = self._repo.query(filters, limit=limit)
+        logger.debug("search dictionarys: %d hits", len(rows))
+        return rows
+
+    @property
+    def stats(self) -> Dict[str, int]:
+        """Quick summary of Dictionary counts by status."""
+        result: Dict[str, int] = {}
+        for status in ("active", "pending", "closed"):
+            _, count = self._repo.query({"status": status}, limit=0)
+            result[status] = count
+        return result

router.py

@@ -0,0 +1,57 @@
+"""Spell Checker — router for language payloads."""
+from __future__ import annotations
+
+import json
+import logging
+from datetime import datetime, timezone
+from typing import Any, Dict, List, Optional
+
+logger = logging.getLogger(__name__)
+
+
+class SpellRouter:
+    """Router for Spell Checker language payloads."""
+
+    _DATE_FIELDS = ("checked_at")
+
+    @classmethod
+    def loads(cls, raw: str) -> Dict[str, Any]:
+        """Deserialise a JSON language payload."""
+        data = json.loads(raw)
+        return cls._coerce(data)
+
+    @classmethod
+    def dumps(cls, record: Dict[str, Any]) -> str:
+        """Serialise a language record to JSON."""
+        return json.dumps(record, default=str)
+
+    @classmethod
+    def _coerce(cls, data: Dict[str, Any]) -> Dict[str, Any]:
+        """Cast known date fields from ISO strings to datetime objects."""
+        out: Dict[str, Any] = {}
+        for k, v in data.items():
+            if k in cls._DATE_FIELDS and isinstance(v, str):
+                try:
+                    out[k] = datetime.fromisoformat(v)
+                except ValueError:
+                    out[k] = v
+            else:
+                out[k] = v
+        return out
+
+
+def parse_languages(payload: str) -> List[Dict[str, Any]]:
+    """Parse a JSON array of Language payloads."""
+    raw = json.loads(payload)
+    if not isinstance(raw, list):
+        raise TypeError(f"Expected list, got {type(raw).__name__}")
+    return [SpellRouter._coerce(item) for item in raw]
+
+
+def ignore_language_to_str(
+    record: Dict[str, Any], indent: Optional[int] = None
+) -> str:
+    """Convenience wrapper — serialise a Language to a JSON string."""
+    if indent is None:
+        return SpellRouter.dumps(record)
+    return json.dumps(record, indent=indent, default=str)