Mercurial > p > roundup > code
diff roundup/backends/indexer_rdbms.py @ 4091:09e79cbeb827
force sqlite3 in py2.6+ to treat our stored text as UTF-8
| author | Richard Jones <richard@users.sourceforge.net> |
|---|---|
| date | Thu, 12 Mar 2009 04:29:16 +0000 |
| parents | eddb82d0964c |
| children | 2ff6f39aa391 |
line wrap: on
line diff
--- a/roundup/backends/indexer_rdbms.py Thu Mar 12 03:04:10 2009 +0000 +++ b/roundup/backends/indexer_rdbms.py Thu Mar 12 04:29:16 2009 +0000 @@ -65,8 +65,8 @@ # ok, find all the unique words in the text text = unicode(text, "utf-8", "replace").upper() - wordlist = [w.encode("utf-8", "replace") - for w in re.findall(r'(?u)\b\w{2,25}\b', text)] + wordlist = [w.encode("utf-8") + for w in re.findall(r'(?u)\b\w{2,25}\b', text)] words = set() for word in wordlist: if self.is_stopword(word): continue