Some changes and new stuff

Code/python/bannedWords

@@ -0,0 +1,199 @@
+aboard
+about
+above
+across
+after
+against
+along
+amid
+among
+anti
+around
+as
+at
+before
+behind
+below
+beneath
+beside
+besides
+between
+beyond
+but
+by
+concerning
+considering
+despite
+down
+during
+except
+excepting
+excluding
+following
+for
+from
+in
+inside
+into
+like
+minus
+near
+of
+off
+on
+onto
+opposite
+outside
+over
+past
+per
+plus
+regarding
+round
+save
+since
+than
+through
+to
+toward
+towards
+under
+underneath
+unlike
+until
+up
+upon
+versus
+via
+with
+within
+without
+all
+another
+any
+anybody
+anyone
+anything
+both
+each
+either
+everybody
+everyone
+everything
+few
+he
+her
+hers
+herself
+him
+himself
+his
+it
+its
+itself
+many
+me mine
+more
+most
+much
+my
+myself
+neither
+no one
+nobody
+none
+one
+other
+others
+our
+ours
+ourselves
+several
+she
+some
+somebody
+someone
+something
+that
+their
+theirs
+them
+themselves
+these
+they
+this
+those
+us
+we
+what
+whatever
+which
+whichever
+who
+whoever
+whom
+whomever
+whose
+you
+your
+yours
+yourself
+yourselves
+an
+am
+as
+to
+up
+us
+in
+be
+can
+how
+get
+got
+has
+did
+every
+also
+too
+try
+is
+was
+do
+if
+oh
+so
+ill
+are
+been
+or
+dont
+just
+had
+set
+put
+have
+im
+ive
+not
+then
+goes
+youre
+use
+id
+the
+a
+and
+i
+me
+when
+where
+how
+would
+whats
+because
+thats
+there
+doing
+even
+does

Code/python/chatchecker.py

@@ -0,0 +1,29 @@
+#!/usr/bin/python
+import fileinput
+import json
+import time
+import calendar
+import shutil
+
+logfile = "/home/jumblesale/Code/irc/log"
+outfile = "/home/krowbar/logs/userData.json"
+userData = {} #hash keyed by "user" that contains an array of timestamps
+#we only care about recent chats, let's say for the past two weeks
+timeCutoff = calendar.timegm(time.gmtime()) - (2 * 7 * 24 * 60 * 60)
+
+with open(logfile, "r") as log:
+    for line in log:
+        try:
+            time, user, message = line.split("\t", 3)
+            time = int(time)
+        except ValueError:
+            continue #There are some bad lines in the log file that we'll ignore if we can't parse
+        if time > timeCutoff:
+            #if the user already exists in the list
+            if user in userData:
+                userData[user].append(time) #append the new time
+            else: #if they are new
+                userData[user] = [time] #create a new list
+with open(outfile + ".tmp", "w") as tmpFile:
+    tmpFile.write(json.dumps(userData))
+shutil.move(outfile + ".tmp", outfile)

Code/python/chatcloud.py

@@ -0,0 +1,38 @@
+#!/usr/bin/python
+import fileinput
+import json
+import time
+import calendar
+import re
+import shutil
+
+logfile = "/home/jumblesale/Code/irc/log"
+outfile = "/home/krowbar/logs/chatcloud.json"
+bannedWordsFile = "/home/krowbar/Code/python/bannedWords"
+wordData = {} # keyed by "word" that contains a count
+#we only care about recent chats, let's say for the past two weeks
+timeCutoff = calendar.timegm(time.gmtime()) - (2 * 7 * 24 * 60 * 60)
+minOccurance = 10
+bannedWords = open(bannedWordsFile).read().splitlines()
+
+with open(logfile, "r") as log:
+    for line in log:
+        try:
+            time, user, message = line.split("\t", 3)
+            time = int(time)
+        except ValueError:
+            continue #There are some bad lines in the log file that we'll ignore if we can't parse
+        if time > timeCutoff:
+            for word in re.sub('[\'\";:,.?!*&^\-()\[\]]', '', message).lower().split():
+                if word in bannedWords:
+                    continue
+                #if the word already exists in the list
+                if word in wordData:
+                    wordData[word] += 1
+                else: #if they are new
+                    wordData[word] = 1
+                    #print "Added word: " + word
+wordData = {i:wordData[i] for i in wordData if wordData[i] >= minOccurance }
+with open(outfile + ".tmp", "w") as tmpFile:
+    tmpFile.write(json.dumps(wordData))
+shutil.move(outfile + ".tmp", outfile)