Moved html parsing from phd_pp.py to reindex_blog.py.

[phdru.name/phdru.name.git] / phd_pp.py

diff --git a/phd_pp.py b/phd_pp.py
index d731d38a270fe9d13d8c8e8337aefb6d5ed78e3a..f9c9a67dca9712272ba8141bf9e7e9d57ea43690 100644 (file)
--- a/phd_pp.py
+++ b/phd_pp.py
@@ -1,12 +1,14 @@
 import os, re, time, urllib
 from Cheetah.Template import Template
 
+
 url_re = r"(((https?|ftp|gopher|telnet)://|(mailto|file|news|about|ed2k|irc|sip|magnet):)[^' \t<>\"]+|(www|web|w3)[A-Za-z0-9_-]*\.[A-Za-z0-9._-]+\.[^' \t<>\"]+)[A-Za-z0-9/]"
 
 def _url2href(match):
    url = match.group(0)
    return '<a href="%s">%s</a>' % (url, url)
 
+
 full_dirs = len(os.getcwd().split('/')) + 1
 
 class phd_pp(Template):
@@ -34,13 +36,15 @@ class phd_pp(Template):
          return "%s, %s" % (start_year, this_year)
       return "%s-%s" % (start_year, this_year)
 
+
    def body(self):
       if hasattr(self, "body_html"):
-         return self.body_html()
+         body = self.body_html()
       if hasattr(self, "body_text"):
-         return self.text2html()
+         body = self.text2html()
       if hasattr(self, "body_rst"):
-         return self.rst2html()
+         body = self.rst2html()
+      return body
 
    def text2html(self):
       body = re.sub(url_re, _url2href, self.body_text())
@@ -63,8 +67,7 @@ class phd_pp(Template):
 
    def rst2html(self):
       from docutils.core import publish_parts
-      from locale import getpreferredencoding
-      encoding = getpreferredencoding()
+      from m_lib.defenc import default_encoding as encoding
 
       parts = publish_parts(self.body_rst(), writer_name="html")
 
@@ -80,6 +83,7 @@ class phd_pp(Template):
       parts = [part for part in (title, subtitle, body) if part]
       return "\n\n".join(parts)
 
+
    def img_thumbnail_800_1024(self, img_name):
       return """\
 <img src="%(img_name)s-thumbnail.jpg" alt="%(img_name)s-thumbnail.jpg" /><br />