* improve handling of unicode data

diff --git a/rss2maildir.py b/rss2maildir.py
index 6a319f47ad2ba14a44df777dfd83b21c7cf0d9da..cacf1ee8eaabe04a6d5fc20d21c3e9e8d664c9c1 100755 (executable)
--- a/rss2maildir.py
+++ b/rss2maildir.py
@@ -199,8 +199,10 @@ class HTML2Text(HTMLParser):
             self.text = self.text \
                 + u'\n> ' \
                 + u'\n> '.join( \
             self.text = self.text \
                 + u'\n> ' \
                 + u'\n> '.join( \

-                    [a.strip() for a in textwrap.wrap(self.blockquote, 68)] \
-                    ).encode("utf-8") \
+                    [a.strip() \
+                        for a in textwrap.wrap( \
+                            self.blockquote, 68)] \
+                    ) \

                 + u'\n'
             self.inblockquote = False
             self.blockquote = u''
                 + u'\n'
             self.inblockquote = False
             self.blockquote = u''


@@ -248,11 +250,11 @@ class HTML2Text(HTMLParser):
             entity = "&" + name + ";"
 
         if self.inparagraph:
             entity = "&" + name + ";"
 
         if self.inparagraph:

-            self.currentparagraph = self.currentparagraph + entity
+            self.currentparagraph = self.currentparagraph + unicode(entity, "utf-8")

         elif self.inblockquote:
         elif self.inblockquote:

-            self.blockquote = self.blockquote + entity
+            self.blockquote = self.blockquote + unicode(entity, "utf-8")

         else:
         else:

-            self.text = self.text + entity
+            self.text = self.text + unicode(entity, "utf-8")

 
     def gettext(self):
         data = self.text
 
     def gettext(self):
         data = self.text