paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-04-19 10:19:27 -05:00
Code Issues Packages Projects Releases Wiki Activity

fixes #668 (see https://github.com/the-paperless-project/paperless/pull/571)

Browse Source
This commit is contained in:
jonaswinkler 2021-03-17 22:44:18 +01:00
parent 391db73ea8
commit b39c3f7866
1 changed files with 5 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
src/documents/matching.py
View File

@ -90,7 +90,7 @@ def matches(matching_model, document):
elif matching_model.matching_algorithm == MatchingModel.MATCH_LITERAL: elif matching_model.matching_algorithm == MatchingModel.MATCH_LITERAL:
result = bool(re.search( result = bool(re.search(
rf"\b{matching_model.match}\b", rf"\b{re.escape(matching_model.match)}\b",
document_content, document_content,
**search_kwargs **search_kwargs
)) ))
@ -161,6 +161,9 @@ def _split_match(matching_model):
findterms = re.compile(r'"([^"]+)"|(\S+)').findall findterms = re.compile(r'"([^"]+)"|(\S+)').findall
normspace = re.compile(r"\s+").sub normspace = re.compile(r"\s+").sub
return [ return [
normspace(" ", (t[0] or t[1]).strip()).replace(" ", r"\s+") # normspace(" ", (t[0] or t[1]).strip()).replace(" ", r"\s+")
re.escape(
normspace(" ", (t[0] or t[1]).strip())
).replace(r"\ ", r"\s+")
for t in findterms(matching_model.match) for t in findterms(matching_model.match)
] ]