From 8f983d5bccd4d48bc3f4543a563b1da0c2bd9a0c Mon Sep 17 00:00:00 2001
From: Damien Elmes <git@ichi2.net>
Date: Fri, 21 Nov 2008 23:41:14 +0900
Subject: [PATCH] always keep as unicode

---
 anki/db.py    | 10 ----------
 anki/utils.py | 24 ++++++++++++------------
 2 files changed, 12 insertions(+), 22 deletions(-)

diff --git a/anki/db.py b/anki/db.py
index 7ce0465f8..5ae209a19 100644
--- a/anki/db.py
+++ b/anki/db.py
@@ -40,16 +40,6 @@ except ImportError:
     from sqlalchemy import Unicode
     UnicodeText = Unicode
 
-# dump location of non-unicode string
-from sqlalchemy import util
-if getattr(util, 'warn', None):
-    import traceback
-    oldWarn = util.warn
-    def newWarn(*args, **kwargs):
-        traceback.print_stack()
-        oldWarn(*args, **kwargs)
-    util.warn = newWarn
-
 # shared metadata
 metadata = MetaData()
 
diff --git a/anki/utils.py b/anki/utils.py
index 6991ead46..8348913be 100644
--- a/anki/utils.py
+++ b/anki/utils.py
@@ -146,25 +146,25 @@ def stripHTML(s):
 def tidyHTML(html):
     "Remove cruft like body tags and return just the important part."
     # contents of body - no head or html tags
-    html = re.sub(".*<body.*?>(.*)</body></html>",
+    html = re.sub(u".*<body.*?>(.*)</body></html>",
                   "\\1", html.replace("\n", u""))
     # strip superfluous Qt formatting
-    html = re.sub("margin-top:\d+px; margin-bottom:\d+px; margin-left:\d+px; "
+    html = re.sub(u"margin-top:\d+px; margin-bottom:\d+px; margin-left:\d+px; "
                   "margin-right:\d+px; -qt-block-indent:0; "
-                  "text-indent:0px;", "", html)
-    html = re.sub("-qt-paragraph-type:empty;", "", html)
+                  "text-indent:0px;", u"", html)
+    html = re.sub(u"-qt-paragraph-type:empty;", u"", html)
     # collapse multiple spaces into one
-    html = re.sub("  +", " ", html)
+    html = re.sub(u"  +", u" ", html)
     # strip leading space in style statements, and remove if no contents
-    html = re.sub('style=" ', 'style="', html)
-    html = re.sub(' style=""', "", html)
+    html = re.sub(u'style=" ', u'style="', html)
+    html = re.sub(u' style=""', u"", html)
     # convert P tags into SPAN and/or BR
-    html = re.sub('<p( style=.+?)>(.*?)</p>', u'<span\\1>\\2</span><br>', html)
-    html = re.sub('<p>(.*?)</p>', u'\\1<br>', html)
-    html = re.sub('<br>$', u'', html)
+    html = re.sub(u'<p( style=.+?)>(.*?)</p>', u'<span\\1>\\2</span><br>', html)
+    html = re.sub(u'<p>(.*?)</p>', u'\\1<br>', html)
+    html = re.sub(u'<br>$', u'', html)
     # remove leading or trailing whitespace
-    html = re.sub('^ +', u'', html)
-    html = re.sub(' +$', u'', html)
+    html = re.sub(u'^ +', u'', html)
+    html = re.sub(u' +$', u'', html)
     return html
 
 def genID(static=[]):