Commit c15e4b63 authored by Jan Reimes's avatar Jan Reimes
Browse files

refactor(cli,config): remove unused CLI args and utility functions 

Remove unused CLI options (OverallTimeoutOption, SpecOption, ProcessTDocIdOption,
CheckoutPathOption), unused ConfigService.crawl_limits, and fix TDocQueryConfig
parameter name from target_ids to tdoc_ids.
parent 4483b101

src/tdoc_crawler/cli/app.py

+1 −1
Original line number Diff line number Diff line
@@ -133,7 +133,7 @@ def checkout( 


    manager = CacheManager(cache_dir).register()

    normalized_ids = [tid.strip().upper() for tid in tdoc_ids]

    config = TDocQueryConfig(target_ids=normalized_ids)

    config = TDocQueryConfig(tdoc_ids=normalized_ids)



    with create_cached_session() as session:

        with TDocDatabase(manager.db_file) as database:

src/tdoc_crawler/cli/args.py

+4 −4
Original line number Diff line number Diff line
@@ -52,7 +52,7 @@ IncrementalOption = Annotated[ 
]

LimitTDocsOption = Annotated[int | None, typer.Option("--limit-tdocs", help="Limit number of TDocs", envvar="TDC_LIMIT_TDOCS")]

ClearTDocsOption = Annotated[bool, typer.Option("--clear-tdocs", help="Clear all TDocs before crawling")]

OverallTimeoutOption = Annotated[

_ = Annotated[

    int | None,

    typer.Option("--overall-timeout", help="Maximum total crawl duration in seconds (None = unlimited)", envvar="TDC_OVERALL_TIMEOUT"),

]
@@ -99,7 +99,7 @@ AgendaPatternExcludeOption = Annotated[ 
ClearSpecsOption = Annotated[bool, typer.Option("--clear-specs", help="Clear all specs before crawling")]

TitleOption = Annotated[str | None, typer.Option("--title", help="Filter by title contains")]

StatusOption = Annotated[str | None, typer.Option("--status", help="Filter by status")]

SpecOption = Annotated[list[str] | None, typer.Option("--spec", help="Spec number(s) (dotted or undotted)")]

_ = Annotated[list[str] | None, typer.Option("--spec", help="Spec number(s) (dotted or undotted)")]



SpecFileOption = Annotated[Path | None, typer.Option("--spec-file", help="File with spec numbers")]

ReleaseOption = Annotated[
@@ -169,7 +169,7 @@ QueryOption = Annotated[str | None, typer.Option("--query", help="Semantic searc 
WorkspaceNameOption = Annotated[str | None, typer.Option("--workspace", "-w", help="Workspace name")]

EmbeddingTopKOption = Annotated[int, typer.Option("--top-k", "-k", help="Number of embedding results to return")]



ProcessTDocIdOption = Annotated[str | None, typer.Option("--tdoc-id", "-t", help="TDoc ID to process")]

_ = Annotated[str | None, typer.Option("--tdoc-id", "-t", help="TDoc ID to process")]

EmbeddingBackendOption = Annotated[

    Literal["torch", "onnx", "openvino"],

    typer.Option(
@@ -179,7 +179,7 @@ EmbeddingBackendOption = Annotated[ 
        envvar="TDC_AI_EMBEDDING_BACKEND",

    ),

]

CheckoutPathOption = Annotated[str | None, typer.Option("--checkout-path", help="Path to checkout document")]

_ = Annotated[str | None, typer.Option("--checkout-path", help="Path to checkout document")]

CheckoutBaseOption = Annotated[str | None, typer.Option("--checkout-base", help="Base path for checkout")]

ProcessAllOption = Annotated[bool, typer.Option("--all", help="Process all documents in workspace")]

ProcessNewOnlyOption = Annotated[bool, typer.Option("--new-only", help="Process only new documents")]

src/tdoc_crawler/cli/utils.py

+1 −1
Original line number Diff line number Diff line
@@ -11,7 +11,7 @@ import typer 


from tdoc_crawler.logging import get_console, get_logger



console = get_console()

_ = get_console()

logger = get_logger(__name__)

src/tdoc_crawler/config/service.py

+0 −11
Original line number Diff line number Diff line
@@ -76,17 +76,6 @@ class ConfigService: 
            self._http_cache = HttpCacheConfig.resolve_http_cache_config(cache_file=self.cache_manager.http_cache_file)

        return self._http_cache



    @property

    def crawl_limits(self) -> CrawlLimits:

        """Return crawl limits with all limits unset (use CLI overrides as needed).



        Returns:

            CrawlLimits instance with no restrictions applied.

        """

        if self._crawl_limits is None:

            self._crawl_limits = CrawlLimits()

        return self._crawl_limits



    @classmethod

    def from_env(cls, cache_manager_name: str | None = None) -> ConfigService:

        """Create ConfigService loading settings from environment variables.

src/tdoc_crawler/workers/tdoc_worker.py

+1 −1
Original line number Diff line number Diff line
@@ -8,7 +8,7 @@ from tdoc_crawler.logging import get_logger 
from tdoc_crawler.models import HttpCacheConfig

from tdoc_crawler.tdocs.sources.doclist import fetch_meeting_document_list



logger = get_logger(__name__)

_ = get_logger(__name__)





def fetch_meeting_document_list_subinterpreter(