babel fixes, iambuttbot utf8 fix

plugins/babel.py

@@ -1,46 +1,76 @@
 import yaml
 import urllib
+import htmlentitydefs
+import re
 
 import hook
+########### from http://effbot.org/zone/re-sub.htm#unescape-html #############
+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)
+##############################################################################
 
-languages = 'en ja de he es ko ru en zh en'.split();
+languages = 'ja fr de ko ru zh'.split();
 language_pairs = zip(languages[:-1], languages[1:])
 
-def babel_gen(inp):
+def goog_trans(text, slang, tlang):
     req_url = 'http://ajax.googleapis.com/ajax/services/language/translate' \
             '?v=1.0&q=%s&langpair=%s'
+    url = req_url % (urllib.quote(text, safe=''), slang + '%7C' + tlang)
+    json = urllib.urlopen(url).read()
+    parsed = yaml.load(json)
+    if not 200 <= parsed['responseStatus'] < 300:
+        print parsed
+        raise IOError, 'error with the translation server: %d: %s' % (
+                parsed['responseStatus'], '')
+    return unescape(parsed['responseData']['translatedText'])
 
-    yield 'en', inp
+def babel_gen(inp):
-    for slang, tlang in language_pairs:
+    for language in languages:
         inp = inp.encode('utf8')
-        print slang, tlang, inp
+        trans = goog_trans(inp, 'en', language).encode('utf8')
-        json = urllib.urlopen(req_url % (urllib.quote(inp, safe=''), 
+        inp = goog_trans(trans, language, 'en')
-                              slang + '%7C' + tlang)).read()
+        print language, trans, inp
-        parsed = yaml.load(json)
+        yield language, trans, inp
-        if not 200 <= parsed['responseStatus'] < 300:
-            raise IOError, 'error with the translation server'
-        inp = parsed['responseData']['translatedText']
-        yield tlang, inp
 
 @hook.command
 def babel(inp):
     try:
-        return list(babel_gen(inp))[-1][1]
+        return list(babel_gen(inp))[-1][2]
-    except IOError:
+    except IOError, e:
-        return 'error with the translation server'
+        return e
 
 @hook.command
-def babelexp(inp):
+def babelext(inp):
     try:
         babels = list(babel_gen(inp))
-    except IOError:
+    except IOError, e:
-        return 'error with the translation server'
+        return e
 
     out = u''
-    for lang, text in babels:
+    for lang, trans, text in babels:
         out += '%s:"%s", ' % (lang, text.decode('utf8'))
 
+    out += 'en:"' + babels[-1][2].decode('utf8') + '"'
+
     if len(out) > 300:
         out = out[:150] + ' ... ' + out[-150:]
 
-    return out[:-2]
+    return out

plugins/iambuttbot.py

@@ -13,6 +13,6 @@ def iambuttbot(bot, input):
 
     password = open('iambuttbot_password').readlines()[0].strip()
     status = input.inp if len(input.inp) <= 140 else input.inp[:137] + "..."
-    data = urllib.urlencode({"status": status})
+    data = urllib.urlencode({"status": status.encode('utf8')})
     url = 'http://iambuttbot:%s@twitter.com/statuses/update.xml' % password
     response = urllib.urlopen(url, data)