Commit b95567f0 authored by Jan Reimes's avatar Jan Reimes
Browse files

✨ feat(utils): add normalize_release_label and infer_working_groups_from_ids 

- normalize_release_label(): converts release number to Rel-N label
- infer_working_groups_from_ids(): infers WG enum from TDoc ID prefixes
parent 2a70b2b8

src/tdoc_crawler/utils/normalization.py

+18 −0
Original line number Diff line number Diff line
@@ -429,6 +429,24 @@ def normalize_release_version(release: str) -> str: 
    return ".".join(parts)





def normalize_release_label(release: str | None) -> str | None:

    """Normalize a release number to a standard label.



    Args:

        release: Release number (e.g., "18") or special value ("latest")



    Returns:

        "Rel-{number}" for numeric values, "latest" for "latest", None for

        None or empty string.

    """

    if release is None or release == "":

        return None

    if release.lower() == "latest":

        return "latest"

    cleaned = release.strip()

    return f"Rel-{cleaned}"





def normalize_working_group_alias(alias: str) -> WorkingGroup:

    """Normalize working group aliases to canonical working group enums.

src/tdoc_crawler/utils/parse.py

+32 −0
Original line number Diff line number Diff line
@@ -138,3 +138,35 @@ def collect_spec_numbers(specs: list[str] | None, spec_file: Path | None) -> lis 
        return []



    return expand_spec_ranges_batch(collected)





def infer_working_groups_from_ids(tdoc_ids: list[str]) -> list[WorkingGroup]:

    """Infer working groups from TDoc ID prefixes.



    The first character of a TDoc ID determines the working group:

    - R → RAN

    - S → SA

    - C or T → CT



    Args:

        tdoc_ids: List of TDoc identifiers (e.g., ["R1-2301234", "S4-2301890"])



    Returns:

        Deduplicated list of inferred working groups.

    """

    working_groups: list[WorkingGroup] = []

    for tdoc_id in tdoc_ids:

        if not tdoc_id:

            continue

        first_char = tdoc_id[0].upper()

        if first_char == "R":

            wg = WorkingGroup.RAN

        elif first_char == "S":

            wg = WorkingGroup.SA

        else:

            wg = WorkingGroup.CT



        if wg not in working_groups:

            working_groups.append(wg)



    return working_groups