indymedia
/
epicyon
mirror of https://gitlab.com/bashrc2/epicyon
7
4
Fork 1
Code Issues 14 Releases Wiki Activity

Don't guess very small tags

main
Bob Mottram 2020-12-22 10:13:15 +00:00
parent 69a24ad454
commit 679c06b20e
1 changed files with 13 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
inbox.py
View File

@ -81,14 +81,20 @@ def guessHashtagCategory(tagName: str, hashtagCategories: {}) -> str:
for categoryStr, hashtagList in hashtagCategories.items():
for hashtag in hashtagList:
if hashtag in tagName or tagName in hashtag:
if not categoryMatched:
tagMatchedLen = len(hashtag)
if len(hashtag) < 3:
# avoid matching very small strings which often
# lead to spurious categories
continue
if hashtag not in tagName:
if tagName not in hashtag:
continue
if not categoryMatched:
tagMatchedLen = len(hashtag)
categoryMatched = categoryStr
else:
# match the longest tag
if len(hashtag) > tagMatchedLen:
categoryMatched = categoryStr
else:
# match the longest tag
if len(hashtag) > tagMatchedLen:
categoryMatched = categoryStr
if not categoryMatched:
return
return categoryMatched