HTML Entities in UTF-8 messages (still needs testing).

3 files changed, 45 insertions, 7 deletions

diff --git a/sunshine/channel/text.py b/sunshine/channel/text.py
index 9d01f74..d37b6d0 100644
--- a/sunshine/channel/text.py
+++ b/sunshine/channel/text.py
@@ -24,7 +24,7 @@ import time
 
 import telepathy
 
-from sunshine.util.decorator import async
+from sunshine.util.decorator import async, escape
 from sunshine.handle import SunshineHandleFactory
 
 __all__ = ['SunshineTextChannel']
@@ -47,7 +47,9 @@ class SunshineTextChannel(telepathy.server.ChannelTypeText):
         if message_type == telepathy.CHANNEL_TEXT_MESSAGE_TYPE_NORMAL:
             logger.info("Sending message to %s, id %s, body: '%s'" % (str(self.handle.name), str(self.handle.id), unicode(text)))
             msg = text.decode('UTF-8').encode('windows-1250', 'replace')
-            self.conn.gadu_client.sendTo(int(self.handle.name), str(text), str(msg))
+            #gg_text = escape(text.decode('UTF-8')).encode('UTF-8').replace('<', '&lt;').replace('>', '&gt;')
+            gg_text = text.decode('UTF-8', 'xmlcharrefreplace').replace('<', '&lt;').replace('>', '&gt;')
+            self.conn.gadu_client.sendTo(int(self.handle.name), str(gg_text), str(msg))
         else:
             raise telepathy.NotImplemented("Unhandled message type")
         self.Sent(int(time.time()), message_type, text)
diff --git a/sunshine/connection.py b/sunshine/connection.py
index 87bda75..c480f71 100644
--- a/sunshine/connection.py
+++ b/sunshine/connection.py
@@ -42,7 +42,7 @@ from sunshine.handle import SunshineHandleFactory
 from sunshine.capabilities import SunshineCapabilities
 from sunshine.contacts import SunshineContacts
 from sunshine.channel_manager import SunshineChannelManager
-from sunshine.util.decorator import async, stripHTML
+from sunshine.util.decorator import async, stripHTML, unescape
 
 __all__ = ['SunshineConfig', 'GaduClientFactory', 'SunshineConnection']
 
@@ -658,9 +658,9 @@ class SunshineConnection(telepathy.server.Connection,
 
             if msg.content.html_message:
                 #we need to strip all html tags
-                text = stripHTML(msg.content.html_message).replace('&lt;', '<').replace('&gt;', '>')
+                text = unescape(stripHTML(msg.content.html_message))
             else:
-                text = (msg.content.plain_message).decode('windows-1250')
+                text = unescape((msg.content.plain_message).decode('windows-1250'))
 
 
             message = "%s" % unicode(str(text).replace('\x00', '').replace('\r', ''))
diff --git a/sunshine/util/decorator.py b/sunshine/util/decorator.py
index fe53b33..7b86fbe 100644
--- a/sunshine/util/decorator.py
+++ b/sunshine/util/decorator.py
@@ -25,17 +25,53 @@ import time
 
 import gobject
 
+import htmlentitydefs
 import re
 
-__all__ = ['stripHTML', 'decorator', 'rw_property', 'deprecated', 'unstable', 'async',
+__all__ = ['unescape', 'escape', 'stripHTML', 'decorator', 'rw_property', 'deprecated', 'unstable', 'async',
         'throttled']
 
+##
+# Removes HTML or XML character references and entities from a text string.
+#
+# @param text The HTML (or XML) source text.
+# @return The plain text, as a Unicode string, if necessary.
+def unescape(text):
+    def fixup(m):
+        text = m.group(0)
+        if text[:2] == "&#":
+            # character reference
+            try:
+                if text[:3] == "&#x":
+                    return unichr(int(text[3:-1], 16))
+                else:
+                    return unichr(int(text[2:-1]))
+            except ValueError:
+                pass
+        else:
+            # named entity
+            try:
+                text = unichr(htmlentitydefs.name2codepoint[text[1:-1]])
+            except KeyError:
+                pass
+        return text # leave as is
+    return re.sub("&#?\w+;", fixup, text)
+
+def escape(u):
+    htmlentities = list()
+
+    for c in u:
+        try:
+            htmlentities.append('&%s;' % htmlentitydefs.codepoint2name[ord(c)])
+        except KeyError:
+            htmlentities.append(c)
+    return ''.join(htmlentities)
+
 def stripHTML(string):
     "Replacing HTML-like tags from text."
     p = re.compile(r'<.*?>')
     return p.sub('', string)
 
-
 def decorator(function):
     """decorator to be used on decorators, it preserves the docstring and
     function attributes of functions to which it is applied."""