Added utils.py, with a quality HTML stripper; removed stripHtml from other source files

plugins/Forums.py

@@ -40,15 +40,12 @@ from baseplugin import *
 import re
 import urllib2
 
+import utils
 import debug
 import ircmsgs
 import ircutils
 import callbacks
 
-htmlStripper = re.compile(r'<[^>]+>')
-def stripHtml(s):
-    return htmlStripper.sub('', s)
-
 class Forums(callbacks.PrivmsgRegexp):
     threaded = True
     _ggThread = re.compile(r'from thread &quot;<b>(.*?)</b>&quot;')

plugins/Http.py

@@ -48,17 +48,13 @@ import re
 import time
 import urllib
 import urllib2
-import htmlentitydefs
 import xml.dom.minidom
 
+import utils
 import debug
 import privmsgs
 import callbacks
 
-_htmlstripper = re.compile('<[^>]+>')
-def stripHtml(s):
-    return _htmlstripper.sub('', s)
-
 class FreshmeatException(Exception):
     pass
 
@@ -132,7 +128,7 @@ class Http(callbacks.Privmsg):
         text = html.split('<P>\n', 2)[1]
         text = text.replace('.\n', '.  ')
         text = text.replace('\n', ' ')
-        text = stripHtml(text)
+        text = utils.htmlToText(text)
         irc.reply(msg, text.strip())
 
     _gkrating = re.compile(r'<font color="#FFFF33">(\d+)</font>')
@@ -246,10 +242,8 @@ class Http(callbacks.Privmsg):
         if m is None:
             irc.error(msg, 'No quote found.')
             return
-        quote = m.group(1)
+        quote = utils.htmlToText(m.group(1))
         quote = ' // '.join(quote.splitlines())
-        for (entity, replacement) in htmlentitydefs.entitydefs.iteritems():
-            quote = quote.replace(entity, replacement)
         irc.reply(msg, quote)
         
     _acronymre = re.compile('<td[^>]*><b>[^<]+</b></td>[^<]+<td[^>]*>(\w+)')

plugins/Relay.py

@@ -59,6 +59,7 @@ class Relay(privmsgs.CapabilityCheckingPrivmsg):
         callbacks.Privmsg.__init__(self)
         self.ircs = {}
         self.started = False
+        self.channels = set()
         self.abbreviations = {}
         
     def startrelay(self, irc, msg, args):
@@ -97,6 +98,7 @@ class Relay(privmsgs.CapabilityCheckingPrivmsg):
     def relayjoin(self, irc, msg, args):
         "<channel>"
         channel = privmsgs.getArgs(args)
+        self.channels.add(channel)
         for otherIrc in self.ircs.itervalues():
             if channel not in otherIrc.state.channels:
                 otherIrc.queueMsg(ircmsgs.join(channel))
@@ -105,6 +107,7 @@ class Relay(privmsgs.CapabilityCheckingPrivmsg):
     def relaypart(self, irc, msg, args):
         "<channel>"
         channel = privmsgs.getArgs(args)
+        self.channels.remove(channel)
         for otherIrc in self.ircs.itervalues():
             if channel in otherIrc.state.channels:
                 otherIrc.queueMsg(ircmsgs.part(channel))
@@ -122,6 +125,8 @@ class Relay(privmsgs.CapabilityCheckingPrivmsg):
             irc = irc.getRealIrc()
         if self.started and ircutils.isChannel(msg.args[0]):
             channel = msg.args[0]
+            if channel not in self.channels:
+                return
             #debug.printf('self.abbreviations = %s' % self.abbreviations)
             #debug.printf('self.ircs = %s' % self.ircs)
             #debug.printf('irc = %s' % irc)
@@ -171,6 +176,8 @@ class Relay(privmsgs.CapabilityCheckingPrivmsg):
             rAction = re.compile(r'\* \w+/(?:%s) ' % '|'.join(abbreviations))
             if not (rPrivmsg.match(msg.args[1]) or rAction.match(msg.args[1])):
                 channel = msg.args[0]
+                if channel not in self.channels:
+                    return
                 abbreviation = self.abbreviations[irc]
                 s = self._formatPrivmsg(irc.nick, abbreviation, msg)
                 for otherIrc in self.ircs.itervalues():

src/utils.py

@@ -0,0 +1,66 @@
+#!/usr/bin/env python
+
+###
+# Copyright (c) 2002, Jeremiah Fincher
+# All rights reserved.
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions are met:
+#
+#   * Redistributions of source code must retain the above copyright notice,
+#     this list of conditions, and the following disclaimer.
+#   * Redistributions in binary form must reproduce the above copyright notice,
+#     this list of conditions, and the following disclaimer in the
+#     documentation and/or other materials provided with the distribution.
+#   * Neither the name of the author of this software nor the name of
+#     contributors to this software may be used to endorse or promote products
+#     derived from this software without specific prior written consent.
+#
+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+# ARE DISCLAIMED.  IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+# POSSIBILITY OF SUCH DAMAGE.
+###
+
+"""
+Simple utility functions.
+"""
+
+from fix import *
+
+import sgmllib
+import htmlentitydefs
+
+class HtmlToText(sgmllib.SGMLParser):
+    """Taken from some eff-bot code on c.l.p."""
+    entitydefs = htmlentitydefs.entitydefs
+    def __init__(self):
+        self.data = []
+        sgmllib.SGMLParser.__init__(self)
+
+    def unknown_starttag(self, tag, attrib):
+        self.data.append(" ")
+
+    def unknown_endtag(self, tag):
+        self.data.append(" ")
+
+    def handle_data(self, data):
+        self.data.append(data)
+
+    def getText(self):
+        text = ''.join(self.data).strip()
+        return ''.join(text.split()) # normalize whitespace
+
+def htmlToText(s):
+    x = HtmlToText()
+    x.feed(s)
+    return x.getText()
+
+# vim:set shiftwidth=4 tabstop=8 expandtab textwidth=78: