X-Git-Url: https://git.phdru.name/?a=blobdiff_plain;f=bkmk_parser.py;h=86b62809679fb99ab5c9316b59713825d8170081;hb=68601d0cc97e734da6e29a0af39a834e4c3a34f1;hp=41df9ef30bd78b15f34bdb28f223b0f72f40c9db;hpb=5291c9e91503d288a4a50a30345d1d33ced56f32;p=bookmarks_db.git

diff --git a/bkmk_parser.py b/bkmk_parser.py
index 41df9ef..86b6280 100644
--- a/bkmk_parser.py
+++ b/bkmk_parser.py
@@ -1,11 +1,20 @@
-"""
-   Parser for Netscape Navigator's and Mozilla's bookmarks.html
+"""Parser for Netscape Navigator's and Mozilla's bookmarks.html
 
-   Written by BroytMann. Copyright (C) 1997-2007 PhiloSoft Design
+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) 1997-2011 PhiloSoft Design"
+__license__ = "GNU GPL"
+
+__all__ = ['BkmkParser']
+
 
 import sys, os
+from m_lib.defenc import default_encoding as DEFAULT_CHARSET
 from m_lib.net.www.html import HTMLParser
 from bkmk_objects import Folder, Bookmark, Ruler
 
@@ -29,8 +38,6 @@ else:
    dump_names = debug
 
 
-DEFAULT_CHARSET = None
-
 class BkmkParser(HTMLParser):
    def __init__(self):
       HTMLParser.__init__(self)
@@ -38,17 +45,15 @@ class BkmkParser(HTMLParser):
       self.urls = 0
       self.objects = 0
 
-      self.charset = ""
+      self.charset = None
       self.recode = None
 
-
    def handle_data(self, data):
       if data:
-         if DEFAULT_CHARSET:
-            data = unicode(data, self.charset, "replace").encode(DEFAULT_CHARSET, "replace")
+         if self.charset and DEFAULT_CHARSET:
+            data = unicode(data, self.charset, "replace").encode(DEFAULT_CHARSET, "xmlcharrefreplace")
          self.accumulator += data
 
-
    # Mozilla - get charset
    def do_meta(self, attrs):
       http_equiv = ""
@@ -67,17 +72,6 @@ class BkmkParser(HTMLParser):
             self.charset = content.split('=')[1]
          except IndexError:
             pass
-         else:
-            global DEFAULT_CHARSET
-            DEFAULT_CHARSET = sys.getdefaultencoding()
-            if DEFAULT_CHARSET == "ascii":
-               try:
-                  import locale
-               except ImportError:
-                  pass
-               else:
-                  DEFAULT_CHARSET = locale.getpreferredencoding()
-
 
    def start_title(self, attrs):
       if DEFAULT_CHARSET:
@@ -87,7 +81,6 @@ class BkmkParser(HTMLParser):
    def end_title(self):
       self.accumulator += "</TITLE>"
 
-
    # Start root folder
    def start_h1(self, attrs):
       root_folder = Folder()
@@ -106,7 +99,6 @@ class BkmkParser(HTMLParser):
       debug("Root folder name: `%s'" % accumulator)
       self.root_folder.name = accumulator
 
-
    # Start a folder
    def start_h3(self, attrs):
       last_modified = None
@@ -132,9 +124,9 @@ class BkmkParser(HTMLParser):
       debug("Folder name: `%s'" % accumulator)
       self.current_folder.name = accumulator
 
-
    # Start a bookmark
    def start_a(self, attrs):
+      add_date = None
       last_visit = None
       last_modified = None
       keyword = None
@@ -174,7 +166,6 @@ class BkmkParser(HTMLParser):
       bookmark = self.current_folder[-1]
       bookmark.name = accumulator
 
-
    def flush(self):
       accumulator = self.accumulator
 
@@ -186,13 +177,11 @@ class BkmkParser(HTMLParser):
             current_object.comment += accumulator.strip()
             debug("Comment: `%s'" % current_object.comment)
 
-
    def start_dl(self, attrs):
       self.flush()
 
    do_dt = start_dl
 
-
    # End of folder
    def end_dl(self):
       self.flush()
@@ -208,19 +197,16 @@ class BkmkParser(HTMLParser):
          debug("FOLDER STACK is EMPTY!!! (2)")
       self.current_object = None
 
-
    def close(self):
       HTMLParser.close(self)
       if self.folder_stack:
          raise ValueError, "wrong folder stack: %s" % self.folder_stack
 
-
    def do_dd(self, attrs):
       pass
 
    do_p = do_dd
 
-
    # Start ruler
    def do_hr(self, attrs):
       self.flush()
@@ -229,17 +215,14 @@ class BkmkParser(HTMLParser):
       self.current_object = None
       self.objects += 1
 
-
    # BR in comment
    def do_br(self, attrs):
       self.accumulator += "<BR>"
 
-
    # Allow < in the text
    def unknown_starttag(self, tag, attrs):
       self.accumulator += "<%s>" % tag
 
-
    # Do not allow unknow end tags
    def unknown_endtag(self, tag):
       raise NotImplementedError("Unknow end tag `%s'" % tag)