From b5247b5a88ad9cd19eba8d94e84da91a664f0b11 Mon Sep 17 00:00:00 2001 From: ayushcodes10 Date: Mon, 14 Sep 2026 22:37:08 +0530 Subject: [PATCH] Import the canonical Unicode aware id normalizer into dedup.py Toward issue 3352: _id_prefixes reimplements id slugification with its own ASCII only regex instead of the canonical normalize_id every real extractor uses to mint an id, so it silently drops non Latin characters. This adds the import with no behavior change yet; the swap lands in the next commit. Co-Authored-By: Claude Sonnet 5 Claude-Session: https://claude.ai/code/session_017qfdzgbA5KedGEjD1AayNh (cherry picked from commit 237f02d135cf479a66fb290c202db8b66ccd1d66) --- graphify/dedup.py | 1 + 1 file changed, 1 insertion(+) diff --git a/graphify/dedup.py b/graphify/dedup.py index e609053f3..c1dca1d6c 100644 --- a/graphify/dedup.py +++ b/graphify/dedup.py @@ -12,6 +12,7 @@ from collections import defaultdict from pathlib import Path from graphify._minhash import MinHash, MinHashLSH +from graphify.ids import normalize_id from rapidfuzz.distance import DamerauLevenshtein, Jaro, JaroWinkler