andras/perfect-postcode
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages 2 Wiki Activity Actions

ok

Browse source
This commit is contained in:
Andras Schmelczer 2026-07-03 18:01:10 +01:00
parent c2070693fb
commit 909e241907
55 changed files with 594 additions and 223 deletions
Download patch file Download diff file Expand all files Collapse all files

2
pipeline/utils/normalize.py
View file

@ -12,7 +12,7 @@ import re
import polars as pl
# One character outside [a-z0-9 ]. Callers lowercase first; each offending
# character becomes a single space (runs are NOT merged here — callers apply
# character becomes a single space (runs are NOT merged here; callers apply
# word-level rules and then collapse_whitespace).
_NON_ALNUM_LOWER_RE = re.compile(r"[^a-z0-9 ]")