refactor(database): replace resolve_meeting_id function with method on TDocDatabase (a110a426) · Commits · Jan Reimes / 3gpp-crawler

src/tdoc_crawler/cli/helpers.py

+0 −58

Original line number	Diff line number	Diff line
		@@ -171,64 +171,6 @@ def infer_working_groups_from_ids(ids: Iterable[str]) -> list[WorkingGroup]:
		return resolved or [WorkingGroup.RAN, WorkingGroup.SA, WorkingGroup.CT]


		def resolve_meeting_id(database: TDocDatabase, meeting_name: str) -> int \| None:
		"""Resolve meeting name to meeting_id from database.

		Uses fuzzy matching to handle variations in meeting names:
		- Exact match (case-insensitive)
		- Normalized name match
		- Prefix/suffix matching for variations like "SA4-e" vs "3GPPSA4-e"

		Args:
		database: Database connection
		meeting_name: Meeting identifier (e.g., "SA4#133-e" or "S4-133-e")

		Returns:
		Meeting ID if found, None otherwise
		"""
		# Query all meetings from database
		config = MeetingQueryConfig(
		cache_dir=database.db_file.parent,
		working_groups=None,
		subgroups=None,
		limit=None,
		order=SortOrder.DESC,
		include_without_files=True,
		)
		all_meetings = database.query_meetings(config)

		def _match_name(candidate: str, cached: str \| None) -> bool:
		"""Check if candidate matches cached name via fuzzy matching."""
		if not cached:
		return False
		candidate_lower = candidate.lower()
		cached_lower = cached.lower()

		# Exact match
		if candidate_lower == cached_lower:
		return True
		# Candidate is prefix/suffix of cached or vice versa
		return (
		cached_lower.startswith(candidate_lower)
		or cached_lower.endswith(candidate_lower)
		or candidate_lower.startswith(cached_lower)
		or candidate_lower.endswith(cached_lower)
		)

		# Try matches with original and normalized names
		normalized = normalize_portal_meeting_name(meeting_name)
		candidates = [meeting_name]
		if normalized != meeting_name:
		candidates.append(normalized)

		for candidate in candidates:
		for meeting in all_meetings:
		if _match_name(candidate, meeting.short_name):
		return meeting.meeting_id

		return None


		def launch_file(path: Path) -> None:
		"""Launch file in system's default application."""
		if not path.exists():

src/tdoc_crawler/crawlers/whatthespec.py

+10 −7

Original line number	Diff line number	Diff line
		@@ -5,10 +5,12 @@ from __future__ import annotations
		import logging
		from decimal import Decimal, InvalidOperation
		from pathlib import Path
		from typing import Any

		import requests

		from tdoc_crawler.database import TDocDatabase, resolve_meeting_id
		from tdoc_crawler.config import resolve_cache_manager
		from tdoc_crawler.database import TDocDatabase
		from tdoc_crawler.http_client import create_cached_session
		from tdoc_crawler.models.base import HttpCacheConfig
		from tdoc_crawler.models.tdocs import TDocMetadata
		@@ -22,7 +24,7 @@ class WhatTheSpecResolutionError(Exception):
		"""Raised when WhatTheSpec resolution fails."""


		def _parse_agenda_item_nbr(value: object) -> Decimal:
		def _parse_agenda_item_nbr(value: Any) -> Decimal:
		"""Parse agenda item number as Decimal with fallback to zero."""
		if value is None:
		return Decimal(0)
		@@ -34,12 +36,12 @@ def _parse_agenda_item_nbr(value: object) -> Decimal:


		def _resolve_meeting_id(db_file: Path, meeting_name: str \| None) -> int:
		"""Resolve meeting name to meeting_id using local database."""
		"""Helper to resolve meeting name to meeting_id using local database."""
		if not meeting_name:
		return 0
		try:
		with TDocDatabase(db_file) as database:
		resolved = resolve_meeting_id(database, meeting_name)
		resolved = database.resolve_meeting_id(meeting_name)
		except Exception as exc:
		logger.warning(f"Failed to resolve meeting '{meeting_name}': {exc}")
		return 0
		@@ -48,29 +50,30 @@ def _resolve_meeting_id(db_file: Path, meeting_name: str \| None) -> int:

		def resolve_via_whatthespec(
		tdoc_id: str,
		cache_dir: Path,
		db_file: Path,
		http_cache: HttpCacheConfig,
		timeout: int = 30,
		session: requests.Session \| None = None,
		cache_manager_name: str \| None = None,
		) -> TDocMetadata \| None:
		"""Resolve TDoc metadata from whatthespec.net API.

		Args:
		tdoc_id: TDoc identifier (e.g., "S4-260001").
		cache_dir: Path to HTTP cache SQLite database.
		db_file: Path to local TDoc database.
		http_cache: HTTP cache configuration for hishel.
		timeout: Request timeout in seconds.
		session: Optional requests.Session to reuse.
		cache_manager_name: Optional name of the cache manager to use for HTTP caching.

		Returns:
		TDocMetadata if found, otherwise None.
		"""
		manager = resolve_cache_manager(cache_manager_name)
		temp_session: requests.Session \| None = None
		if session is None:
		temp_session = create_cached_session(
		cache_path=cache_path,
		cache_dir=manager.http_cache_dir,
		ttl=http_cache.ttl,
		refresh_ttl_on_access=http_cache.refresh_ttl_on_access,
		max_retries=3,

src/tdoc_crawler/database/init.py

+6 −63

Original line number	Diff line number	Diff line
		@@ -4,71 +4,14 @@ from __future__ import annotations

		import logging

		from tdoc_crawler.database.connection import TDocDatabase
		from tdoc_crawler.database.connection import SpecDatabase, TDocDatabase
		from tdoc_crawler.database.errors import DatabaseError
		from tdoc_crawler.models import MeetingMetadata, MeetingQueryConfig, SortOrder
		from tdoc_crawler.specs.normalization import normalize_portal_meeting_name

		logger = logging.getLogger(__name__)


		def resolve_meeting_id(database: TDocDatabase, meeting_name: str) -> int \| None:
		"""Resolve meeting name to meeting_id from database.

		Uses fuzzy matching to handle variations in meeting names:
		- Exact match (case-insensitive)
		- Normalized name match
		- Prefix/suffix matching for variations like "SA4-e" vs "3GPPSA4-e"

		Args:
		database: Database connection
		meeting_name: Meeting identifier (e.g., "SA4#133-e" or "S4-133-e")

		Returns:
		Meeting ID if found, None otherwise
		"""
		# Query all meetings from database
		config = MeetingQueryConfig(
		cache_dir=database.db_file.parent,
		working_groups=None,
		subgroups=None,
		limit=None,
		order=SortOrder.DESC,
		include_without_files=True,
		)
		all_meetings = database.query_meetings(config)

		def _match_name(candidate: str, cached: str \| None) -> bool:
		"""Check if candidate matches cached name via fuzzy matching."""
		if not cached:
		return False
		candidate_lower = candidate.lower()
		cached_lower = cached.lower()

		# Exact match
		if candidate_lower == cached_lower:
		return True
		# Candidate is prefix/suffix of cached or vice versa
		return (
		cached_lower.startswith(candidate_lower)
		or cached_lower.endswith(candidate_lower)
		or candidate_lower.startswith(cached_lower)
		or candidate_lower.endswith(cached_lower)
		)

		# Try matches with original and normalized names
		normalized = normalize_portal_meeting_name(meeting_name)

		candidates = [meeting_name]
		if normalized != meeting_name:
		candidates.append(normalized)

		for candidate in candidates:
		for meeting in all_meetings:
		if _match_name(candidate, meeting.short_name):
		return meeting.meeting_id

		return None


		__all__ = ["DatabaseError", "MeetingMetadata", "TDocDatabase", "resolve_meeting_id"]
		__all__ = [
		"DatabaseError",
		"SpecDatabase",
		"TDocDatabase",
		]

src/tdoc_crawler/fetching.py

+2 −2

Original line number	Diff line number	Diff line
		@@ -158,8 +158,8 @@ def fetch_missing_tdocs_batch(
		metadata = client.fetch_tdoc_metadata(tdoc_id)

		if metadata.meeting_name:
		meeting_id = resolve_meeting_id(database, metadata.meeting_name)
		if meeting_id:
		meeting_id = database.resolve_meeting_id(metadata.meeting_name)
		if meeting_id is not None:
		metadata.meeting_id = meeting_id
		else:
		logger.warning(f"Could not resolve meeting '{metadata.meeting_name}' to meeting_id for {tdoc_id}")