Some more little fixes, and added a Makefile.

9 files changed, 150 insertions, 50 deletions

diff --git a/Makefile b/Makefile
new file mode 100644
index 0000000..bec372a
--- /dev/null
+++ b/Makefile
@@ -0,0 +1,6 @@
+# Makefile
+# Copyright 2008, Sean B. Palmer, inamidst.com
+# Licensed under the Eiffel Forum License 2.
+
+archive: ;
+        hg archive -t tbz2 phenny.tar.bz2
diff --git a/bot.py b/bot.py
index 4c27b7d..ae97d93 100755
--- a/bot.py
+++ b/bot.py
@@ -79,17 +79,16 @@ class Phenny(irc.Bot):
       
       def bind(self, priority, regexp, func): 
          print priority, regexp.pattern.encode('utf-8'), func
-         self.commands[priority].setdefault(regexp, []).append(func)
-         # @@ register documentation
+         # register documentation
+         if not hasattr(func, 'name'): 
+            func.name = func.__name__
          if func.__doc__: 
-            if hasattr(func, 'name'): 
-               name = func.name
-            else: name = func.__name__
             if hasattr(func, 'example'): 
                example = func.example
                example = example.replace('$nickname', self.nick)
             else: example = None
-            self.doc[name] = (func.__doc__, example)
+            self.doc[func.name] = (func.__doc__, example)
+         self.commands[priority].setdefault(regexp, []).append(func)
 
       def sub(pattern, self=self): 
          # These replacements have significant order
@@ -127,8 +126,8 @@ class Phenny(irc.Bot):
                   prefix = self.config.prefix
                   commands, pattern = func.rule
                   for command in commands: 
-                     command = r'(%s) +' % command
-                     regexp = re.compile(prefix + command + pattern)
+                     command = r'(%s)(?: +(?:%s))?' % (command, pattern)
+                     regexp = re.compile(prefix + command)
                      bind(self, func.priority, regexp, func)
 
                # 3) e.g. ('$nick', ['p', 'q'], '(.*)')
@@ -196,8 +195,6 @@ class Phenny(irc.Bot):
    
                match = regexp.match(text)
                if match: 
-                  # print 'STATS:', origin.sender, func.__name__
-
                   phenny = self.wrapped(origin, text, match)
                   input = self.input(origin, text, bytes, match, event)
 
@@ -207,5 +204,10 @@ class Phenny(irc.Bot):
                      t.start()
                   else: self.call(func, origin, phenny, input)
 
+                  for source in [origin.sender, origin.nick]: 
+                     try: self.stats[(func.name, source)] += 1
+                     except KeyError: 
+                        self.stats[(func.name, source)] = 1
+
 if __name__ == '__main__': 
    print __doc__
diff --git a/modules/codepoints.py b/modules/codepoints.py
index 83425c5..d966670 100644
--- a/modules/codepoints.py
+++ b/modules/codepoints.py
@@ -21,7 +21,8 @@ def about(u, cp=None, name=None):
 
 def codepoint_simple(arg): 
    arg = arg.upper()
-   r_label = re.compile('\\b' + arg.replace(' ', '.*\\b'))
+
+   r_label = re.compile('\\b' + arg.replace(' ', '.*\\b') + '\\b')
 
    results = []
    for cp in xrange(0xFFFF): 
@@ -32,6 +33,16 @@ def codepoint_simple(arg):
       if r_label.search(name): 
          results.append((len(name), u, cp, name))
    if not results: 
+      r_label = re.compile('\\b' + arg.replace(' ', '.*\\b'))
+      for cp in xrange(0xFFFF): 
+         u = unichr(cp)
+         try: name = unicodedata.name(u)
+         except ValueError: continue
+
+         if r_label.search(name): 
+            results.append((len(name), u, cp, name))
+
+   if not results: 
       return None
 
    length, u, cp, name = sorted(results)[0]
diff --git a/modules/head.py b/modules/head.py
index 193286a..8f687fa 100755
--- a/modules/head.py
+++ b/modules/head.py
@@ -7,22 +7,24 @@ Licensed under the Eiffel Forum License 2.
 http://inamidst.com/phenny/
 """
 
-import re, urllib, urlparse
+import re, urllib, urlparse, time
 from htmlentitydefs import name2codepoint
 import web
 from tools import deprecated
 
-@deprecated
-def f_httphead(self, origin, match, args): 
-   """.head <URI> <FieldName>? - Perform an HTTP HEAD on URI."""
-   if origin.sender == '#talis': return
-   uri = match.group(2)
-   header = match.group(3)
+def head(phenny, input): 
+   """Provide HTTP HEAD information."""
+   uri = input.group(2)
+   uri = (uri or '').encode('utf-8')
+   if ' ' in uri: 
+      uri, header = uri.rsplit(' ', 1)
+   else: uri, header = uri, None
+
+   if not uri and hasattr(phenny, 'last_seen_uri'): 
+      uri = phenny.last_seen_uri
 
    try: info = web.head(uri)
-   except IOError: 
-      self.msg(origin.sender, "Can't connect to %s" % uri)
-      return
+   except IOError: return phenny.say("Can't connect to %s" % uri)
 
    if not isinstance(info, list): 
       info = dict(info)
@@ -33,17 +35,27 @@ def f_httphead(self, origin, match, args):
       info = newInfo
 
    if header is None: 
-      msg = 'Status: %s (for more, try ".head uri header")' % info['Status']
-      self.msg(origin.sender, msg)
+      data = []
+      if info.has_key('Status'): 
+         data.append(info['Status'])
+      if info.has_key('content-type'): 
+         data.append(info['content-type'].replace('; charset=', ', '))
+      if info.has_key('last-modified'): 
+         modified = info['last-modified']
+         modified = time.strptime(modified, '%a, %d %b %Y %H:%M:%S %Z')
+         data.append(time.strftime('%Y-%m-%d %H:%M:%S UTC', modified))
+      if info.has_key('content-length'): 
+         data.append(info['content-length'] + ' bytes')
+      phenny.reply(', '.join(data))
    else: 
       headerlower = header.lower()
       if info.has_key(headerlower): 
-         self.msg(origin.sender, header + ': ' + info.get(headerlower))
+         phenny.say(header + ': ' + info.get(headerlower))
       else: 
          msg = 'There was no %s header in the response.' % header
-         self.msg(origin.sender, msg)
-f_httphead.rule = (['head'], r'(\S+)(?: +(\S+))?')
-f_httphead.thread = True
+         phenny.say(msg)
+head.commands = ['head']
+head.example = '.head http://www.w3.org/'
 
 r_title = re.compile(r'(?ims)<title[^>]*>(.*?)</title\s*>')
 r_entity = re.compile(r'&[A-Za-z0-9#]+;')
@@ -52,6 +64,11 @@ r_entity = re.compile(r'&[A-Za-z0-9#]+;')
 def f_title(self, origin, match, args): 
    """.title <URI> - Return the title of URI."""
    uri = match.group(2)
+   uri = (uri or '').encode('utf-8')
+
+   if not uri and hasattr(self, 'last_seen_uri'): 
+      uri = self.last_seen_uri
+
    if not ':' in uri: 
       uri = 'http://' + uri
 
@@ -74,10 +91,10 @@ def f_title(self, origin, match, args):
             self.msg(origin.sender, origin.nick + ": Too many redirects")
             return
 
-      try: mtype = info['Content-Type']
+      try: mtype = info['content-type']
       except: 
-         self.msg(origin.sender, origin.nick + ": Document isn't HTML")
-         return
+         err = ": Couldn't get the Content-Type, sorry"
+         return self.msg(origin.sender, origin.nick + err)
       if not (('/html' in mtype) or ('/xhtml' in mtype)): 
          self.msg(origin.sender, origin.nick + ": Document isn't HTML")
          return
@@ -119,8 +136,13 @@ def f_title(self, origin, match, args):
          title = '[Title is the empty document, "".]'
       self.msg(origin.sender, origin.nick + ': ' + title)
    else: self.msg(origin.sender, origin.nick + ': No title found')
-f_title.rule = (['title'], r'(\S+)')
-f_title.thread = True
+f_title.commands = ['title']
+
+def noteuri(phenny, input): 
+   uri = input.group(1).encode('utf-8')
+   phenny.bot.last_seen_uri = uri
+noteuri.rule = r'.*(http://[^<> "]+)[,.]?'
+noteuri.priority = 'low'
 
 if __name__ == '__main__': 
    print __doc__
diff --git a/modules/info.py b/modules/info.py
index a70c823..df6ad69 100644
--- a/modules/info.py
+++ b/modules/info.py
@@ -40,5 +40,48 @@ def help(phenny, input):
 help.rule = ('$nick', r'(?i)help(?:[?!]+)?$')
 help.priority = 'low'
 
+def stats(phenny, input): 
+   commands = {}
+   users = {}
+   channels = {}
+
+   ignore = set(['f_note', 'startup', 'message', 'noteuri'])
+   for (name, user), count in phenny.stats.iteritems(): 
+      if name in ignore: continue
+
+      if not user.startswith('#'): 
+         try: users[user] += count
+         except KeyError: users[user] = count
+      else: 
+         try: commands[name] += count
+         except KeyError: commands[name] = count
+
+         try: channels[user] += count
+         except KeyError: channels[user] = count
+
+   comrank = sorted([(b, a) for (a, b) in commands.iteritems()], reverse=True)
+   userank = sorted([(b, a) for (a, b) in users.iteritems()], reverse=True)
+   charank = sorted([(b, a) for (a, b) in channels.iteritems()], reverse=True)
+
+   # most heavily used commands
+   creply = 'most used commands: '
+   for count, command in comrank[:10]: 
+      creply += '%s (%s), ' % (command, count)
+   phenny.say(creply.rstrip(', '))
+
+   # most heavy users
+   reply = 'power users: '
+   for count, user in userank[:10]: 
+      reply += '%s (%s), ' % (user, count)
+   phenny.say(reply.rstrip(', '))
+
+   # most heavy channels
+   chreply = 'power channels: '
+   for count, channel in charank[:3]: 
+      chreply += '%s (%s), ' % (channel, count)
+   phenny.say(chreply.rstrip(', '))
+stats.commands = ['stats']
+stats.priority = 'low'
+
 if __name__ == '__main__': 
    print __doc__.strip()
diff --git a/modules/reload.py b/modules/reload.py
index 7a4c76f..2febcd2 100755
--- a/modules/reload.py
+++ b/modules/reload.py
@@ -14,6 +14,10 @@ def f_reload(phenny, input):
    if not input.admin: return
 
    name = input.group(2)
+   if not name: 
+      phenny.setup()
+      return phenny.reply('done')
+
    try: module = getattr(__import__('modules.' + name), name)
    except ImportError: 
       module = getattr(__import__('opt.' + name), name)
@@ -30,7 +34,8 @@ def f_reload(phenny, input):
 
    phenny.reply('%r (version: %s)' % (module, modified))
 f_reload.name = 'reload'
-f_reload.rule = ('$nick', ['reload'], r'(\S+)')
+f_reload.rule = ('$nick', ['reload'], r'(\S+)?')
+f_reload.priority = 'low'
 
 if __name__ == '__main__': 
    print __doc__.strip()
diff --git a/modules/translate.py b/modules/translate.py
index 7e14b1d..d90de43 100644
--- a/modules/translate.py
+++ b/modules/translate.py
@@ -8,7 +8,7 @@ Licensed under the Eiffel Forum License 2.
 http://inamidst.com/phenny/
 """
 
-import re
+import re, time
 import web
 
 r_translation = re.compile(r'<div style=padding:10px;>([^<]+)</div>')
@@ -43,7 +43,7 @@ def guess_language(phrase):
          try: return languages[lang]
          except KeyError: 
             return lang
-   return 'unknown'
+   return 'Moon Language'
 
 def translate(phrase, lang, target='en'): 
    babelfish = 'http://world.altavista.com/tr'
@@ -68,35 +68,40 @@ def translate(phrase, lang, target='en'):
 
 def tr(phenny, input): 
    """Translates a phrase, with an optional language hint."""
-   lang, phrase = input.groups()
+   input, output, phrase = input.groups()
    phrase = phrase.encode('utf-8')
    if (len(phrase) > 350) and (not phenny.admin(input.nick)): 
       return phenny.reply('Phrase must be under 350 characters.')
 
-   language = guess_language(phrase)
-   if language is None: 
+   input = input or guess_language(phrase)
+   if not input: 
       return phenny.reply('Unable to guess the language, sorry.')
-   else: language = lang.encode('utf-8')
+   input = input.encode('utf-8')
+   output = (output or 'en').encode('utf-8')
 
-   if language != 'en': 
-      translation = translate(phrase, language)
+   if not ((input == 'en') and (output == 'en')): 
+      translation = translate(phrase, input, output)
       if translation is not None: 
          translation = translation.decode('utf-8').encode('utf-8')
-         return phenny.reply('"%s" (%s)' % (translation, language))
+         if output == 'en': 
+            return phenny.reply('"%s" (%s)' % (translation, input))
+         else: return phenny.reply('"%s" (%s -> %s)' % \
+                                   (translation, input, output))
 
       error = "I think it's %s, which I can't translate."
-      return phenny.reply(error % language.title())
+      return phenny.reply(error % input.title())
 
    # Otherwise, it's English, so mangle it for fun
-   for other in ['de', 'ja']: 
+   for other in ['de', 'ja', 'de', 'ja', 'de', 'ja', 'de', 'ja', 'de', 'ja']: 
       phrase = translate(phrase, 'en', other)
       phrase = translate(phrase, other, 'en')
+      time.sleep(0.1)
 
    if phrase is not None: 
       return phenny.reply(u'"%s" (en-unmangled)' % phrase)
    return phenny.reply("I think it's English already.")
    # @@ or 'Why but that be English, sire.'
-tr.rule = ('$nick', ur'(?:([a-z]{2}) +)?["“](.+?)["”]\? *$')
+tr.rule = ('$nick', ur'(?:([a-z]{2}) +)?(?:([a-z]{2}) +)?["“](.+?)["”]\? *$')
 tr.example = '$nickname: "mon chien"? or $nickname: fr "mon chien"?'
 tr.priority = 'low'
 
diff --git a/modules/wikipedia.py b/modules/wikipedia.py
index 0a0a415..696bce4 100644
--- a/modules/wikipedia.py
+++ b/modules/wikipedia.py
@@ -55,6 +55,7 @@ def search(term):
    else: return term
 
 def wikipedia(term, last=False): 
+   global wikiuri
    bytes = web.get(wikiuri % urllib.quote(term))
    bytes = r_tr.sub('', bytes)
 
@@ -83,7 +84,8 @@ def wikipedia(term, last=False):
                           and not 'disambiguation)"' in para) 
                           and not '(images and media)' in para
                           and not 'This article contains a' in para 
-                          and not 'id="coordinates"' in para]
+                          and not 'id="coordinates"' in para
+                          and not 'class="thumb' in para]
 
    for i, para in enumerate(paragraphs): 
       para = para.replace('<sup>', '|')
@@ -119,7 +121,9 @@ def wikipedia(term, last=False):
       return None
 
    sentence = '"' + sentence.replace('"', "'") + '"'
-   return sentence + ' - ' + (wikiuri % term)
+   sentence = sentence.decode('utf-8').encode('utf-8')
+   wikiuri = wikiuri.encode('utf-8')
+   return sentence + ' - ' + (wikiuri % term.encode('utf-8'))
 
 def wik(phenny, input): 
    origterm = input.groups()[1]
diff --git a/opt/freenode.py b/opt/freenode.py
index b87a5e2..f3d285c 100644
--- a/opt/freenode.py
+++ b/opt/freenode.py
@@ -20,13 +20,15 @@ def replaced(phenny, input):
       'v': '.v has been replaced by .val', 
       'validate': '.validate has been replaced by .validate', 
       'thesaurus': ".thesaurus hasn't been ported to my new codebase yet", 
-      'rate': ".rate hasn't been ported to my new codebase yet, sorry!", 
-      'rates': ".rates hasn't been ported to my new codebase yet, sorry!"
+      'rates': "moon wanter. moOOoon wanter!", 
+      'web': 'the .web command has been removed; ask sbp for details', 
+      'mangle': ".mangle hasn't been ported to my new codebase yet", 
+      'origin': ".origin hasn't been ported to my new codebase yet"
    }[command]
    phenny.reply(response)
 replaced.commands = [
    'cp', 'pc', 'unicode', 'compare', 'map', 'acronym', 'img', 
-   'v', 'validate', 'thesaurus', 'rate', 'rates'
+   'v', 'validate', 'thesaurus', 'rates', 'web', 'mangle', 'origin'
 ]
 replaced.priority = 'low'