# HG changeset patch # User gibus # Date 1372343956 -7200 # Node ID c6105d922ac6151e59d3e5692ab27011dc35f2a8 # Parent 0be906e586e6bdb4c28abea728c6d785bf2e1708 For some reason, BeautifulSoup wants now fromEncoding='UTF-8' in some unidentified cases. diff -r 0be906e586e6 -r c6105d922ac6 src/cm/utils/spannifier.py --- a/src/cm/utils/spannifier.py Wed Jun 26 23:43:08 2013 +0200 +++ b/src/cm/utils/spannifier.py Thu Jun 27 16:39:16 2013 +0200 @@ -13,7 +13,7 @@ return not textNode.findParent('style') def get_the_soup(input): - return BeautifulSoup(input, convertEntities=BeautifulSoup.ALL_ENTITIES) + return BeautifulSoup(input, convertEntities=BeautifulSoup.ALL_ENTITIES, fromEncoding='UTF-8') from cm.utils.cache import memoize, dj_memoize @dj_memoize