strip more garbage out of twitter urls (esp the ?s=[:digits:]) tracking code - thanks...

[irc.git] / commands.py

diff --git a/commands.py b/commands.py
index 2864bb9de6ae05b1a9c867738e79fafedbc352f8..698bfdbe64c7161b83afba284a580203bfe2ff20 100755 (executable)
--- a/commands.py
+++ b/commands.py
@@ -1,8 +1,13 @@
 # Part of Acrobat.
-import string, cPickle, random, urllib, sys, time, re, os, twitter, subprocess, datetime, urlparse
+import string, cPickle, random, urllib, sys, time, re, os, twitter, subprocess, datetime, urlparse, hashlib
 from collections import defaultdict
 from irclib import irc_lower, nm_to_n
 
+try:
+    from blame_filter import bfd
+except ImportError:
+    bfd = None
+
 # query karma
 def karmaq(bot, cmd, nick, conn, public, karma):
     try:
@@ -279,8 +284,12 @@ def __getcommitinfo(commit):
        return(err)
 
     ts,mes=out.split('|')
+    mes=mes.strip()
+    md5mes=hashlib.md5(mes).hexdigest()
+    if bfd and md5mes in bfd:
+        mes=bfd[md5mes]
     when=datetime.date.fromtimestamp(float(ts))
-    return mes.strip(), when
+    return mes, when
 
 ###Return an array of commit messages and timestamps for lines in db that match what
 def __getcommits(db,keys,what):
@@ -517,9 +526,9 @@ def getTweet(urlstring,twitapi,inclusion=False,recurlvl=0):
   unobfuscate_urls=True
   expand_included_tweets=True
   stringsout=[]
-  
-  parts = string.split(urlstring,'/')
-  tweetID = parts[-1]
+
+  path = urlparse.urlparse(urlstring).path
+  tweetID = path.split('/')[-1]
   try:
     status = twitapi.GetStatus(tweetID)
     if status == {}: