Commit 2f6e950c authored by Jan Reimes's avatar Jan Reimes
Browse files

fix(lint): resolve ruff issues in protocols and utils 

- http_client/protocols.py: Remove undefined HttpClientProvider from __all__ (F822)
- parsers/protocols.py: Remove undefined ParserProtocol from __all__ (F822)
- utils/normalization.py: Remove duplicate normalize_tdoc_ids() (exists in tdocs/utils.py)
- utils/normalization.py: Remove duplicate normalize_portal_meeting_name() (exists in meetings/models.py)
- cli/ai.py: Add noqa: PLC0415 for intentional lazy import of resolve_cache_manager
- cli/app.py: Add noqa: PLC0415 for intentional lazy import of ai_app (optional feature)
parent cf67e609

src/tdoc_crawler/http_client/protocols.py

+1 −1
Original line number Diff line number Diff line
@@ -28,4 +28,4 @@ class DefaultHttpClientProvider: 
            self._session = None





__all__ = ["DefaultHttpClientProvider", "HttpClientProvider"]
 
__all__ = ["DefaultHttpClientProvider"]

src/tdoc_crawler/parsers/protocols.py

+1 −1
Original line number Diff line number Diff line
@@ -40,4 +40,4 @@ class ClientProtocol(Protocol): 
        ...





__all__ = ["ClientProtocol", "ParserProtocol"]
 
__all__ = ["ClientProtocol"]

src/tdoc_crawler/utils/normalization.py

+3 −43
Original line number Diff line number Diff line 
"""Normalization helpers for spec identifiers."""



import re

from collections.abc import Generator, Iterable

from collections.abc import Generator



_DOTTED_BODY_PATTERN = re.compile(r"^(?P<series>\d{2})\s*\.\s*(?P<increment>\d{1,3})$")

_UNDOTTED_BODY_PATTERN = re.compile(r"^(?P<series>\d{2})(?P<increment>\d{1,3})$")
@@ -14,48 +14,6 @@ class NormalizationError(ValueError): 
    """Raised when spec identifier normalization or expansion fails."""





# TODO is already defined in src/tdoc_crawler/tdocs/utils.py - should exist only at a single location!

def normalize_tdoc_ids(ids: Iterable[str]) -> list[str]:

    """Uppercase and strip whitespace from TDoc identifiers."""

    return [str(value).strip().upper() for value in ids]





# TODO is already defined in src/tdoc_crawler/meetings/models.py - should exist only at a single location!

def normalize_portal_meeting_name(portal_meeting: str | None) -> str:

    """Normalize portal meeting name to database format.



    The portal uses format like "SA4#133-e" while the database uses "S4-133-e".

    This function converts portal format to database format.



    Args:

        portal_meeting: Meeting name from portal (e.g., "SA4#133-e")



    Returns:

        Normalized meeting name (e.g., "S4-133-e")

    """

    if not portal_meeting:

        return ""



    # Replace "SA4#" with "S4-", "RAN1#" with "R1-", etc.

    normalized = portal_meeting.replace("#", "-")



    # Handle full working group names (SA, RAN, CT)

    for full_name, short_prefix in [("SA", "S"), ("RAN", "R"), ("CT", "C")]:

        # Match patterns like "SA4-" and replace with "S4-"

        if normalized.startswith(f"{full_name}"):

            # Extract subgroup number if present

            for i, char in enumerate(normalized[len(full_name) :]):

                if not char.isdigit():

                    subgroup_num = normalized[len(full_name) : len(full_name) + i] if i > 0 else ""

                    rest = normalized[len(full_name) + i :]

                    if subgroup_num:

                        normalized = f"{short_prefix}{subgroup_num}{rest}"

                    break

            break



    return normalized





def _strip_prefixes(value: str) -> str:

    """Strip optional 3GPP and TS/TR prefixes from a spec string."""

    cleaned = value.strip().upper()
@@ -299,6 +257,8 @@ def resolve_release_to_full_version(release: str, available_versions: list[str]) 


    if release_type == "prefix":

        # Match by prefix (major or major.minor)

        if release_value is None or specificity is None:

            raise ValueError(f"Invalid release format: '{release}'.")

        prefix_parts = release_value.split(".")

        for version in sorted_versions:

            version_parts = version.split(".")