paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-10-30 03:56:23 -05:00
Code Issues Packages Projects Releases Wiki Activity

Support search terms that contain multiple words in ANY/ALL matching modes, by surrounding the terms with double quotes.

Browse Source
This commit is contained in:
ishirav
2017-12-23 06:05:48 +02:00
parent d3a8a072c4
commit e89cb0d6e0
1 changed files with 15 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
src/documents/models.py
View File

@@ -89,7 +89,7 @@ class MatchingModel(models.Model):
search_kwargs = {"flags": re.IGNORECASE}
if self.matching_algorithm == self.MATCH_ALL:
for word in self.match.split(" "):
for word in self._split_match():
search_result = re.search(
r"\b{}\b".format(word), text, **search_kwargs)
if not search_result:
@@ -97,7 +97,7 @@ class MatchingModel(models.Model):
return True
if self.matching_algorithm == self.MATCH_ANY:
for word in self.match.split(" "):
for word in self._split_match():
if re.search(r"\b{}\b".format(word), text, **search_kwargs):
return True
return False
@@ -121,6 +121,19 @@ class MatchingModel(models.Model):
raise NotImplementedError("Unsupported matching algorithm")
def _split_match(self):
'''
Splits the match to invidual keywords, getting rid of unecessary spaces
and grouping quoted words together.
Example:
' some random words "with quotes " and spaces'
==>
['some', 'random', 'words', 'with quotes', 'and', 'spaces']
'''
findterms = re.compile(r'"([^"]+)"|(\S+)').findall
normspace = re.compile(r'\s{2,}').sub
return [normspace(' ', (t[0] or t[1]).strip()) for t in findterms(self.match)]
def save(self, *args, **kwargs):
self.match = self.match.lower()