From: Bernie Innocenti <bernie@codewiz.org>
Date: Mon, 15 Dec 2008 03:31:48 +0000 (-0500)
Subject: UTF-8 fixup for Python 3.0
X-Git-Tag: v4.0~16
X-Git-Url: https://codewiz.org/gitweb?a=commitdiff_plain;h=refs%2Fremotes%2Fsunjammer%2Fpython3;p=geekigeeki.git

UTF-8 fixup for Python 3.0
---

diff --git a/geekigeeki.py b/geekigeeki.py
index ca16283..6e1ba6e 100755
--- a/geekigeeki.py
+++ b/geekigeeki.py
@@ -221,7 +221,7 @@ def handle_fullsearch(needle):
     print("<ul>")
     for (count, page_name) in hits:
         print('<li><p>' + Page(page_name).link_to())
-        print(' . . . . ' + repr(count))
+        print(' . . . . ' + str(count))
         print(['match', 'matches'][count != 1])
         print('</p></li>')
     print("</ul>")
@@ -544,7 +544,7 @@ class WikiFormatter:
         indent_re = re.compile(r"^\s*")
         tr_re = re.compile(r"^\s*\|\|")
         eol_re = re.compile(r"\r?\n")
-        for self.line in eol_re.split(str(self.raw.expandtabs())):
+        for self.line in eol_re.split(str(self.raw.expandtabs(), 'utf-8')):
             # Skip pragmas
             if self.in_header:
                 if self.line.startswith('#'):
@@ -584,7 +584,7 @@ class Page:
         return os.path.join(data_dir, self.page_name)
 
     def _tmp_filename(self):
-        return os.path.join(data_dir, ('#' + self.page_name.replace('/','_') + '.' + repr(os.getpid()) + '#'))
+        return os.path.join(data_dir, ('#' + self.page_name.replace('/','_') + '.' + str(os.getpid()) + '#'))
 
     def exists(self):
         try:
@@ -631,6 +631,7 @@ class Page:
 
     def pragmas(self):
         if not '_pragmas' in self.__dict__:
+            self._pragmas = {}
             try:
                 file = open(self._filename(), 'rt')
                 attr_re = re.compile(r"^#(\S*)(.*)$")