src/knowledge_extraction/diff/glossary_diff.py

"""Classify each candidate against the ACTIVE glossary version: new, duplicate
or conflicting.

The prototype diffed against the file it then overwrote, so every entry came
back `new` and the interesting paths never ran. The baseline must therefore be
supplied explicitly — an approved, versioned set — rather than read from
wherever the last run happened to write.
"""

from __future__ import annotations

from ..models import DiffStatus
from ..settings import DUPLICATE_OVERLAP_THRESHOLD
from ..validate.conflict import overlap


def classify(entry: dict, existing_by_term: dict[str, dict]) -> DiffStatus:
    prior = existing_by_term.get((entry.get("term") or "").casefold())
    if prior is None:
        return "new"
    a = (entry.get("definition") or "").strip()
    b = (prior.get("definition") or "").strip()
    if a and a == b:
        return "duplicate"
    if not a or not b:
        # One side abstained: not a contradiction, just less information.
        return "new"
    return "duplicate" if overlap(a, b) >= DUPLICATE_OVERLAP_THRESHOLD else "conflicting"


def diff_glossary(entries: list[dict], active: list[dict]) -> list[dict]:
    existing_by_term = {(e.get("term") or "").casefold(): e for e in active}
    return [{**entry, "diff_status": classify(entry, existing_by_term)} for entry in entries]