Split parse_html/__init__.py into __main__.py

[bookmarks_db.git] / bkmk_objects.py

diff --git a/bkmk_objects.py b/bkmk_objects.py
index be139edb3e205379733c8e7d38f8db42f2ce4c77..23fb816ee180100100722ee2b7ac9818cf63390d 100644 (file)
--- a/bkmk_objects.py
+++ b/bkmk_objects.py
@@ -1,13 +1,11 @@
 """Objects to represent bookmarks.html structure
 
 This file is a part of Bookmarks database and Internet robot.
+
 """
 
-__version__ = "$Revision$"[11:-2]
-__revision__ = "$Id$"[5:-2]
-__date__ = "$Date$"[7:-2]
 __author__ = "Oleg Broytman <phd@phdru.name>"
-__copyright__ = "Copyright (C) 2000-2011 PhiloSoft Design"
+__copyright__ = "Copyright (C) 2000-2012 PhiloSoft Design"
 __license__ = "GNU GPL"
 
 __all__ = ['Folder', 'Bookmark', 'Ruler', 'Walker', 'Writer', 'Robot',
@@ -67,33 +65,22 @@ class Bookmark:
             user, password = urllib.splitpasswd(user)
          host, port = urllib.splitport(host)
          if port: port = int(port)
-      path, tag = urllib.splittag(path)
-      path, query = urllib.splitquery(path)
-      path = urllib.unquote(path)
-      if tag: tag = urllib.unquote_plus(tag)
-
-      if host: # host can be None for Mozilla's place: URLs
-          host = host.decode(parser_charset or 'utf-8').encode('idna')
 
-      href = protocol + "://"
+      if protocol == 'place':
+         href = protocol + ":"
+      else:
+         href = protocol + "://"
       if user:
          href += urllib.quote(user)
          if password:
             href += ':' + urllib.quote(password)
          href += '@'
       if host:
-         href += host
+         href += host.decode(parser_charset or 'utf-8').encode('idna')
          if port:
             href += ':%d' % port
       if path:
-         if protocol == "file":
-            href += urllib.quote(path)
-         else:
-            href += urllib.quote(path)
-      if query:
-         href += '?' + query
-      if tag:
-         href += '#' + urllib.quote_plus(tag)
+         href += path
 
       self.href = href
       self.add_date = add_date
@@ -228,6 +215,6 @@ def quote_title(title):
 def unquote_title(title):
    if BKMK_FORMAT == "MOZILLA":
       from HTMLParser import HTMLParser
-      title = HTMLParser().unescape(title.replace("&amp;", '&'))
-      title = title.replace("&#39;", "'")
+      title = HTMLParser().unescape(title.replace("&amp;", '&').decode('utf-8'))
+      title = title.encode('utf-8').replace("&#39;", "'")
    return title