2004-01-27 21:06:28 +01:00
|
|
|
#!/usr/bin/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.
|
|
|
|
###
|
|
|
|
|
|
|
|
"""
|
|
|
|
Keeps statistics on who says what words in a channel.
|
|
|
|
"""
|
|
|
|
|
2004-02-16 05:14:57 +01:00
|
|
|
__revision__ = "$Id$"
|
2004-02-09 05:40:30 +01:00
|
|
|
|
2004-01-30 07:11:51 +01:00
|
|
|
import os
|
2004-02-08 04:23:30 +01:00
|
|
|
import csv
|
2004-01-30 07:11:51 +01:00
|
|
|
import string
|
|
|
|
|
2004-02-08 04:23:30 +01:00
|
|
|
import log
|
2004-01-27 21:06:28 +01:00
|
|
|
import conf
|
|
|
|
import utils
|
2004-02-08 04:23:30 +01:00
|
|
|
import world
|
2004-01-30 07:11:51 +01:00
|
|
|
import ircdb
|
2004-01-27 21:06:28 +01:00
|
|
|
import plugins
|
2004-01-30 07:11:51 +01:00
|
|
|
import ircutils
|
2004-01-27 21:06:28 +01:00
|
|
|
import privmsgs
|
2004-01-30 07:11:51 +01:00
|
|
|
import registry
|
2004-01-27 21:06:28 +01:00
|
|
|
import callbacks
|
|
|
|
|
|
|
|
conf.registerPlugin('WordStats')
|
2004-04-14 12:13:53 +02:00
|
|
|
conf.registerChannelValue(conf.supybot.plugins.WordStats, 'rankingDisplay',
|
2004-01-27 21:06:28 +01:00
|
|
|
registry.PositiveInteger(3, """Determines the maximum number of top users
|
|
|
|
to show for a given wordstat when someone requests the wordstats for a
|
|
|
|
particular word."""))
|
2004-04-14 12:13:53 +02:00
|
|
|
conf.registerChannelValue(conf.supybot.plugins.WordStats, 'ignoreQueries',
|
|
|
|
registry.Boolean(False, """Determines whether the bot will ignore words
|
|
|
|
said in a channel if they're in a wordstats query (command)."""))
|
2004-01-27 21:06:28 +01:00
|
|
|
|
2004-02-08 04:23:30 +01:00
|
|
|
nonAlphaNumeric = filter(lambda s: not s.isalnum(), string.ascii)
|
2004-01-30 07:11:51 +01:00
|
|
|
|
2004-04-09 18:29:16 +02:00
|
|
|
WordDict = utils.InsensitivePreservingDict
|
|
|
|
|
2004-02-08 04:23:30 +01:00
|
|
|
class WordStatsDB(plugins.ChannelUserDB):
|
|
|
|
def __init__(self, *args, **kwargs):
|
|
|
|
self.channelWords = ircutils.IrcDict()
|
|
|
|
plugins.ChannelUserDB.__init__(self, *args, **kwargs)
|
2004-01-27 21:06:28 +01:00
|
|
|
|
2004-02-08 04:23:30 +01:00
|
|
|
def serialize(self, v):
|
|
|
|
L = []
|
|
|
|
for (word, count) in v.iteritems():
|
|
|
|
L.append('%s:%s' % (word, count))
|
|
|
|
return L
|
2004-01-27 21:06:28 +01:00
|
|
|
|
2004-02-08 04:23:30 +01:00
|
|
|
def deserialize(self, channel, id, L):
|
2004-04-09 18:29:16 +02:00
|
|
|
d = WordDict()
|
2004-02-08 04:23:30 +01:00
|
|
|
for s in L:
|
|
|
|
(word, count) = s.split(':')
|
|
|
|
count = int(count)
|
|
|
|
d[word] = count
|
|
|
|
if channel not in self.channelWords:
|
2004-04-09 18:29:16 +02:00
|
|
|
self.channelWords[channel] = WordDict()
|
2004-02-08 04:23:30 +01:00
|
|
|
self.channelWords[channel].setdefault(word, 0)
|
|
|
|
self.channelWords[channel][word] += count
|
|
|
|
return d
|
|
|
|
|
|
|
|
def getWordCount(self, channel, id, word):
|
|
|
|
return self[channel, id][word]
|
|
|
|
|
|
|
|
def getUserWordCounts(self, channel, id):
|
|
|
|
return self[channel, id].items()
|
|
|
|
|
|
|
|
def getWords(self, channel):
|
|
|
|
if channel not in self.channelWords:
|
|
|
|
self.channelWords[channel] = {}
|
|
|
|
L = self.channelWords[channel].keys()
|
|
|
|
L.sort()
|
|
|
|
return L
|
|
|
|
|
|
|
|
def getTotalWordCount(self, channel, word):
|
|
|
|
return self.channelWords[channel][word]
|
|
|
|
|
|
|
|
def getNumUsers(self, channel):
|
|
|
|
i = 0
|
|
|
|
for ((chan, _), _) in self.iteritems():
|
2004-04-09 18:29:16 +02:00
|
|
|
if ircutils.nickEqual(chan, channel):
|
2004-02-08 04:23:30 +01:00
|
|
|
i += 1
|
|
|
|
return i
|
|
|
|
|
|
|
|
def getTopUsers(self, channel, word, n):
|
|
|
|
L = [(id, d[word]) for ((chan, id), d) in self.iteritems()
|
2004-04-09 18:29:16 +02:00
|
|
|
if ircutils.nickEqual(channel, chan) and word in d]
|
2004-02-08 04:23:30 +01:00
|
|
|
utils.sortBy(lambda (_, i): i, L)
|
|
|
|
L = L[-n:]
|
|
|
|
L.reverse()
|
|
|
|
return L
|
|
|
|
|
|
|
|
def getRankAndNumber(self, channel, id, word):
|
|
|
|
L = self.getTopUsers(channel, word, 0)
|
|
|
|
n = 0
|
|
|
|
for (someId, count) in L:
|
|
|
|
n += 1
|
|
|
|
if id == someId:
|
|
|
|
return (n, count)
|
2004-02-20 06:00:31 +01:00
|
|
|
raise KeyError
|
2004-02-08 04:23:30 +01:00
|
|
|
|
|
|
|
def addWord(self, channel, word):
|
|
|
|
if channel not in self.channelWords:
|
|
|
|
self.channelWords[channel] = {}
|
|
|
|
self.channelWords[channel][word] = 0
|
|
|
|
for ((chan, id), d) in self.iteritems():
|
2004-04-09 18:29:16 +02:00
|
|
|
if ircutils.nickEqual(chan, channel):
|
2004-02-08 04:23:30 +01:00
|
|
|
if word not in d:
|
|
|
|
d[word] = 0
|
2004-03-14 07:43:03 +01:00
|
|
|
|
|
|
|
def delWord(self, channel, word):
|
|
|
|
if word in self.channelWords[channel]:
|
|
|
|
del self.channelWords[channel][word]
|
|
|
|
for ((chan, id), d) in self.iteritems():
|
2004-04-09 18:29:16 +02:00
|
|
|
if ircutils.nickEqual(chan, channel):
|
2004-03-14 07:43:03 +01:00
|
|
|
if word in d:
|
|
|
|
del d[word]
|
2004-02-08 04:23:30 +01:00
|
|
|
|
|
|
|
def addMsg(self, msg):
|
|
|
|
assert msg.command == 'PRIVMSG'
|
2004-04-14 12:13:53 +02:00
|
|
|
(channel, text) = msg.args
|
|
|
|
if not ircutils.isChannel(channel):
|
|
|
|
return
|
|
|
|
text = text.strip().lower()
|
|
|
|
if not text:
|
|
|
|
return
|
2004-01-27 21:06:28 +01:00
|
|
|
try:
|
|
|
|
id = ircdb.users.getUserId(msg.prefix)
|
|
|
|
except KeyError:
|
|
|
|
return
|
2004-02-08 04:23:30 +01:00
|
|
|
msgwords = [s.strip(nonAlphaNumeric) for s in text.split()]
|
|
|
|
if channel not in self.channelWords:
|
|
|
|
self.channelWords[channel] = {}
|
|
|
|
for word in self.channelWords[channel]:
|
2004-04-09 18:29:16 +02:00
|
|
|
word = word.lower()
|
2004-02-08 04:23:30 +01:00
|
|
|
for msgword in msgwords:
|
|
|
|
if msgword == word:
|
|
|
|
self.channelWords[channel][word] += 1
|
|
|
|
if (channel, id) not in self:
|
|
|
|
self[channel, id] = {}
|
|
|
|
if word not in self[channel, id]:
|
|
|
|
self[channel, id][word] = 0
|
|
|
|
self[channel, id][word] += 1
|
|
|
|
|
|
|
|
|
|
|
|
filename=os.path.join(conf.supybot.directories.data(), 'WordStats.db')
|
|
|
|
class WordStats(callbacks.Privmsg):
|
|
|
|
noIgnore = True
|
|
|
|
def __init__(self):
|
|
|
|
callbacks.Privmsg.__init__(self)
|
|
|
|
self.db = WordStatsDB(filename)
|
2004-04-14 12:13:53 +02:00
|
|
|
self.queried = False
|
2004-02-08 04:23:30 +01:00
|
|
|
world.flushers.append(self.db.flush)
|
|
|
|
|
|
|
|
def die(self):
|
|
|
|
if self.db.flush in world.flushers:
|
|
|
|
world.flushers.remove(self.db.flush)
|
|
|
|
self.db.close()
|
|
|
|
callbacks.Privmsg.die(self)
|
|
|
|
|
|
|
|
def doPrivmsg(self, irc, msg):
|
2004-04-14 12:13:53 +02:00
|
|
|
# This depends on the fact that it's called after the command.
|
|
|
|
try:
|
|
|
|
channel = msg.args[0]
|
|
|
|
if ircutils.isChannel(channel):
|
|
|
|
if not (self.queried and
|
|
|
|
self.registryValue('ignoreQueries', channel)):
|
|
|
|
self.db.addMsg(msg)
|
|
|
|
else:
|
|
|
|
self.log.debug('Queried and ignoring.')
|
|
|
|
finally:
|
|
|
|
self.queried = False
|
2004-01-27 21:06:28 +01:00
|
|
|
|
|
|
|
def add(self, irc, msg, args):
|
|
|
|
"""[<channel>] <word>
|
|
|
|
|
|
|
|
Keeps stats on <word> in <channel>. <channel> is only necessary if the
|
|
|
|
message isn't sent in the channel itself.
|
|
|
|
"""
|
|
|
|
channel = privmsgs.getChannel(msg, args)
|
|
|
|
word = privmsgs.getArgs(args)
|
|
|
|
word = word.strip()
|
2004-02-08 04:23:30 +01:00
|
|
|
if word.strip(nonAlphaNumeric) != word:
|
2004-01-27 21:06:28 +01:00
|
|
|
irc.error('<word> must not contain non-alphanumeric chars.')
|
|
|
|
return
|
2004-02-08 04:23:30 +01:00
|
|
|
self.db.addWord(channel, word)
|
2004-04-14 12:13:53 +02:00
|
|
|
self.queried = True
|
2004-01-27 21:06:28 +01:00
|
|
|
irc.replySuccess()
|
|
|
|
|
2004-03-14 07:43:03 +01:00
|
|
|
def remove(self, irc, msg, args):
|
|
|
|
"""[<channel>] <word>
|
|
|
|
|
|
|
|
Removes <word> from the list of words being tracked. If <channel> is
|
|
|
|
not specified, uses current channel.
|
|
|
|
"""
|
|
|
|
channel = privmsgs.getChannel(msg, args)
|
|
|
|
word = privmsgs.getArgs(args)
|
|
|
|
words = self.db.getWords(channel)
|
|
|
|
if words:
|
|
|
|
if word in words:
|
|
|
|
self.db.delWord(channel, word)
|
|
|
|
irc.replySuccess()
|
|
|
|
else:
|
|
|
|
irc.error('%r doesn\'t look like a word I am keeping stats '
|
|
|
|
'on.' % word)
|
|
|
|
return
|
|
|
|
else:
|
|
|
|
irc.error('I am not currently keeping any word stats.')
|
|
|
|
return
|
|
|
|
|
2004-01-30 07:11:51 +01:00
|
|
|
def wordstats(self, irc, msg, args):
|
2004-01-27 21:06:28 +01:00
|
|
|
"""[<channel>] [<user>] [<word>]
|
|
|
|
|
|
|
|
With no arguments, returns the list of words that are being monitored
|
|
|
|
for stats. With <user> alone, returns all the stats for that user.
|
|
|
|
With <word> alone, returns the top users for that word. With <user>
|
|
|
|
and <word>, returns that user's stat for that word. <channel> is only
|
|
|
|
needed if not said in the channel. (Note: if only one of <user> or
|
|
|
|
<word> is given, <word> is assumed first and only if no stats are
|
|
|
|
available for that word, do we assume it's <user>.)
|
|
|
|
"""
|
|
|
|
channel = privmsgs.getChannel(msg, args)
|
|
|
|
(arg1, arg2) = privmsgs.getArgs(args, required=0, optional=2)
|
|
|
|
if not arg1 and not arg2:
|
2004-02-08 04:23:30 +01:00
|
|
|
words = self.db.getWords(channel)
|
|
|
|
if words:
|
|
|
|
commaAndify = utils.commaAndify
|
|
|
|
s = 'I am currently keeping stats for %s.' % commaAndify(words)
|
|
|
|
irc.reply(s)
|
|
|
|
else:
|
2004-01-27 21:06:28 +01:00
|
|
|
irc.reply('I am not currently keeping any word stats.')
|
|
|
|
return
|
|
|
|
elif arg1 and arg2:
|
|
|
|
user, word = (arg1, arg2)
|
|
|
|
try:
|
|
|
|
id = ircdb.users.getUserId(user)
|
|
|
|
except KeyError: # Maybe it was a nick. Check the hostmask.
|
|
|
|
try:
|
|
|
|
hostmask = irc.state.nickToHostmask(user)
|
|
|
|
id = ircdb.users.getUserId(hostmask)
|
|
|
|
except KeyError:
|
|
|
|
irc.errorNoUser()
|
|
|
|
return
|
2004-02-08 04:23:30 +01:00
|
|
|
try:
|
|
|
|
count = self.db.getWordCount(channel, id, word)
|
|
|
|
except KeyError:
|
|
|
|
irc.error('I\'m not keeping stats on %r.' % word)
|
2004-01-27 21:06:28 +01:00
|
|
|
return
|
2004-02-08 04:23:30 +01:00
|
|
|
if count:
|
|
|
|
s = '%s has said %r %s.' % \
|
|
|
|
(user, word, utils.nItems('time', count))
|
2004-04-14 12:13:53 +02:00
|
|
|
self.queried = True
|
2004-02-08 04:23:30 +01:00
|
|
|
irc.reply(s)
|
|
|
|
else:
|
|
|
|
irc.error('%s has never said %r.' % (user, word))
|
2004-04-09 18:29:16 +02:00
|
|
|
elif arg1 in WordDict.fromkeys(self.db.getWords(channel)):
|
2004-02-08 04:23:30 +01:00
|
|
|
word = arg1
|
|
|
|
total = self.db.getTotalWordCount(channel, word)
|
2004-04-14 12:13:53 +02:00
|
|
|
if total == 0:
|
|
|
|
irc.reply('I\'m keeping stats on %s, but I haven\'t seen it '
|
|
|
|
'in this channel.' % word)
|
|
|
|
self.queried = True
|
|
|
|
return
|
2004-02-08 04:23:30 +01:00
|
|
|
n = self.registryValue('rankingDisplay', channel)
|
|
|
|
try:
|
|
|
|
id = ircdb.users.getUserId(msg.prefix)
|
|
|
|
(rank, number) = self.db.getRankAndNumber(channel, id, word)
|
|
|
|
except (KeyError, ValueError):
|
|
|
|
id = None
|
|
|
|
rank = None
|
|
|
|
number = None
|
|
|
|
ers = '%rer' % word
|
|
|
|
L = []
|
|
|
|
for (userid, count) in self.db.getTopUsers(channel, word, n):
|
|
|
|
if userid == id:
|
|
|
|
rank = None
|
2004-02-11 07:06:19 +01:00
|
|
|
try:
|
|
|
|
username = ircdb.users.getUser(userid).name
|
2004-04-09 18:29:16 +02:00
|
|
|
L.append('%s: %s' % (username, count))
|
2004-02-11 07:06:19 +01:00
|
|
|
except KeyError:
|
2004-04-09 18:29:16 +02:00
|
|
|
self.log.warning('Odd, I have a user in my WordStats '
|
|
|
|
'database that doesn\'t exist in my '
|
|
|
|
'user database: #%s.', userid)
|
2004-02-08 04:23:30 +01:00
|
|
|
ret = 'Top %s (out of a total of %s seen):' % \
|
|
|
|
(utils.nItems(ers, len(L)), utils.nItems(repr(word), total))
|
|
|
|
users = self.db.getNumUsers(channel)
|
|
|
|
if rank is not None:
|
|
|
|
s = ' You are ranked %s out of %s with %s.' % \
|
|
|
|
(rank, utils.nItems(ers, users),
|
|
|
|
utils.nItems(repr(word), number))
|
|
|
|
else:
|
|
|
|
s = ''
|
|
|
|
ret = '%s %s.%s' % (ret, utils.commaAndify(L), s)
|
2004-04-14 12:13:53 +02:00
|
|
|
self.queried = True
|
2004-02-08 04:23:30 +01:00
|
|
|
irc.reply(ret)
|
2004-01-27 21:06:28 +01:00
|
|
|
else:
|
2004-02-08 04:23:30 +01:00
|
|
|
user = arg1
|
|
|
|
try:
|
|
|
|
id = ircdb.users.getUserId(user)
|
|
|
|
except KeyError:
|
|
|
|
irc.error('%r doesn\'t look like a word I\'m keeping stats '
|
|
|
|
'on or a user in my database.' % user)
|
2004-01-27 21:06:28 +01:00
|
|
|
return
|
2004-02-08 04:23:30 +01:00
|
|
|
try:
|
|
|
|
L = ['%r: %s' % (word, count)
|
|
|
|
for (word,count) in self.db.getUserWordCounts(channel,id)]
|
2004-03-14 07:43:03 +01:00
|
|
|
if L:
|
|
|
|
L.sort()
|
|
|
|
irc.reply(utils.commaAndify(L))
|
|
|
|
else:
|
|
|
|
irc.error('%r doesn\'t look like a word I\'m keeping stats'
|
|
|
|
' on or a user in my database.' % user)
|
|
|
|
return
|
2004-02-08 04:23:30 +01:00
|
|
|
except KeyError:
|
2004-03-14 07:43:03 +01:00
|
|
|
irc.error('I have no word stats for that person.')
|
2004-01-27 21:06:28 +01:00
|
|
|
Class = WordStats
|
|
|
|
|
|
|
|
# vim:set shiftwidth=4 tabstop=8 expandtab textwidth=78:
|