paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-07-28 18:24:38 -05:00
Code Issues Packages Projects Releases Wiki Activity

directly use rapidfuzz

Browse Source
This commit is contained in:
Max Bachmann
2022-10-31 20:42:44 +01:00
committed by Trenton H
parent 9214b41255
commit e97c04c03d
3 changed files with 3 additions and 129 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
src/documents/matching.py
View File

@@ -142,14 +142,14 @@ def matches(matching_model, document):
return bool(match)
elif matching_model.matching_algorithm == MatchingModel.MATCH_FUZZY:
from fuzzywuzzy import fuzz
from rapidfuzz import fuzz
match = re.sub(r"[^\w\s]", "", matching_model.match)
text = re.sub(r"[^\w\s]", "", document_content)
if matching_model.is_insensitive:
match = match.lower()
text = text.lower()
if fuzz.partial_ratio(match, text) >= 90:
if fuzz.partial_ratio(match, text, score_cutoff=90):
# TODO: make this better
log_reason(
matching_model,