Commit 5a504eea authored by Jan Reimes's avatar Jan Reimes
Browse files

refactor: remove model re-exports and update domain package imports 

- Remove re-exports of domain models from tdoc_crawler.models package
- Consumers must import directly from domain packages (models.tdocs, models.meetings, specs.models)
- Clarify module responsibilities and reduce implicit dependencies
- Update import paths for SpecDatabase location change
parent 7daefd6f

src/tdoc_crawler/meetings/__init__.py

+1 −9
Original line number Diff line number Diff line
@@ -2,12 +2,4 @@ 


from __future__ import annotations



from tdoc_crawler.meetings.operations import MeetingCrawler, MeetingCrawlResult

from tdoc_crawler.meetings.utils import normalize_subgroup_alias, normalize_working_group_alias



__all__ = [

    "MeetingCrawlResult",

    "MeetingCrawler",

    "normalize_subgroup_alias",

    "normalize_working_group_alias",

]
 
__all__ = []

src/tdoc_crawler/models/__init__.py

+18 −37
Original line number Diff line number Diff line 
"""Core data models and configuration primitives used across the CLI."""

"""Core data models and configuration primitives used across the CLI.



NOTE: Domain models (TDocMetadata, MeetingMetadata, etc.) should be imported

directly from their source modules:

- tdoc_crawler.tdocs.models (TDocMetadata, TDocCrawlConfig, QueryConfig)

- tdoc_crawler.meetings.models (MeetingMetadata, MeetingCrawlConfig, MeetingQueryConfig)

"""



from __future__ import annotations



# Re-export all public symbols

from .base import (

    BaseConfigModel,  # noqa: F401

    BaseConfigModel,

    HttpCacheConfig,

    OutputFormat,

    PortalCredentials,

    SortOrder,

)

from .crawl_limits import CrawlLimits  # noqa: F401

from .crawl_log import CrawlLogEntry  # noqa: F401

from .meetings import (

    MeetingCrawlConfig,

    MeetingMetadata,  # noqa: F401

    MeetingQueryConfig,

)

from .specs import (

    Specification,  # noqa: F401

    SpecificationDownload,

    SpecificationSourceRecord,

    SpecificationVersion,

    SpecQueryFilters,

    SpecQueryResult,

)

from .crawl_limits import CrawlLimits

from .crawl_log import CrawlLogEntry



# Note: Specification models have been moved to tdoc_crawler.specs.models

# Import from there directly to avoid circular dependencies

from .subworking_groups import (

    CODE_INDEX,

    SUBTB_INDEX,  # noqa: F401

    SUBTB_INDEX,

    SUBWORKING_GROUP_RECORDS,

    SubWorkingGroupRecord,

)

from .tdocs import (

    CrawlConfig,

    QueryConfig,

    TDocCrawlConfig,  # noqa: F401

    TDocMetadata,

)

from .working_groups import (

    WORKING_GROUP_RECORDS,

    WorkingGroup,  # noqa: F401

    WorkingGroup,

    WorkingGroupRecord,

)



__all__ = [

    "CODE_INDEX",

    "SUBTB_INDEX",

    "SUBWORKING_GROUP_RECORDS",

    "WORKING_GROUP_RECORDS",

    "BaseConfigModel",

    "CrawlConfig",

    "CrawlLimits",

    "CrawlLogEntry",

    "HttpCacheConfig",

    "MeetingCrawlConfig",

    "MeetingMetadata",

    "MeetingQueryConfig",

    "OutputFormat",

    "PortalCredentials",

    "QueryConfig",

    "SortOrder",

    "SpecQueryFilters",

    "SpecQueryResult",
@@ -67,8 +47,9 @@ __all__ = [ 
    "SpecificationSourceRecord",

    "SpecificationVersion",

    "SubWorkingGroupRecord",

    "TDocCrawlConfig",

    "TDocMetadata",

    "SUBTB_INDEX",

    "SUBWORKING_GROUP_RECORDS",

    "WorkingGroup",

    "WorkingGroupRecord",

    "WORKING_GROUP_RECORDS",

]

src/tdoc_crawler/specs/downloads.py

+1 −2
Original line number Diff line number Diff line
@@ -10,7 +10,6 @@ from zipinspect import HTTPZipReader 
from tdoc_crawler.config import resolve_cache_manager

from tdoc_crawler.constants.urls import SPEC_URL_TEMPLATE

from tdoc_crawler.http_client import download_to_path

from tdoc_crawler.specs.database import SpecDatabase

from tdoc_crawler.specs.sources.base import SpecSource

from tdoc_crawler.utils.normalization import normalize_spec_number
@@ -20,7 +19,7 @@ _logger = logging.getLogger(__name__) 
class SpecDownloads:

    """Download and extraction utilities for specs."""



    def __init__(self, database: SpecDatabase, cache_manager_name: str | None = None) -> None:

    def __init__(self, database, cache_manager_name: str | None = None) -> None:

        self._database = database

        self._cache_manager = resolve_cache_manager(cache_manager_name)

src/tdoc_crawler/specs/operations/checkout.py

+1 −1
Original line number Diff line number Diff line
@@ -10,7 +10,7 @@ import shutil 
from pathlib import Path

from typing import cast



from tdoc_crawler.specs.database import SpecDatabase

from tdoc_crawler.database.specs import SpecDatabase

from tdoc_crawler.specs.downloads import SpecDownloads

from tdoc_crawler.specs.sources.base import FunctionSpecSource, SpecSource

from tdoc_crawler.specs.sources.threegpp import fetch_threegpp_metadata

src/tdoc_crawler/tdocs/__init__.py

+4 −12
Original line number Diff line number Diff line
@@ -2,16 +2,8 @@ 


from __future__ import annotations



from tdoc_crawler.tdocs.operations import (

    HybridCrawlResult,

    HybridTDocCrawler,

    TDocCrawler,

    TDocCrawlResult,

)

# Note: Operations are available via explicit submodule imports

# Importing them here would create circular dependencies

# Use: from tdoc_crawler.tdocs.operations import TDocCrawler



__all__ = [

    "HybridCrawlResult",

    "HybridTDocCrawler",

    "TDocCrawlResult",

    "TDocCrawler",

]
 
__all__ = []