#!/bin/python

import re

### Logfile ###
logfiles    = [ 'Artex_logfile.txt' ] # List of logfiles to read


### Counters ###
nTrans     = 0 # Transfered calls counter (`transb)
nSent      = 0 # Sent calls counter (`sendb)
nClaimed   = 0 # Claimed calls counter


### Lists ###
claimed    = {} # People we claimed
senders    = {} # People to send us calls


### Patterns ###
prefix        = '[*] '
match_sent    = re.compile( '^(.*) needs help of .+ [Cc]hannel with: (.*) \(Sent by (.*)\)' )
match_trans   = re.compile( '^(.*) requests help: "(.*)",' )
match_claimed = re.compile( '^You are now the .+ for (.*)\. ' )


### Script Begins ########################################

print "---++ Data Collection Process ++---\n"

for logfile in logfiles:
    print "[+] Opening `%s` for reading..." % logfile
    fd        = open( logfile, 'r' )
    prefixlen = len(prefix)

    fd.seek(0,2)
    filesize  = fd.tell()
    fd.seek(0)

    print "[+] Parsing the log file..."
    while True:
	buffer = fd.readline()
    
	# EOF Check #
	if buffer == '':
	    break
    
	# Is it a channel issue? #
	buffer = buffer[0] + '*' + buffer[2:] # Making sure the prefix byte is universal
	if buffer[:prefixlen] == prefix and buffer[prefixlen:prefixlen+2] != '> ':    
	    # CLAIM check #
	    data = re.findall( match_claimed, buffer[prefixlen:] )
	    if data != []:
		nClaimed += 1
		user      = data[0]
	        user      = user.replace( ' ','|' )

		if claimed.has_key(user) == False:
		    claimed[user] = 0
	
		claimed[user] += 1

		# Displaying position remminder #
		if (nClaimed % 100.) == 0:
		    print "    > %3d calls read so far [%05.1f%% of file] - %dth caller: %s" % (nClaimed, fd.tell() / 1. / filesize * 100, nClaimed, user)

	    else:
		# SENT check #
		data = re.findall( match_sent, buffer[4:] )

		if data != []:
		    nSent += 1
		    sender = data[0][2]
		    sender = sender.replace( ' ','|' )
		
		    if senders.has_key(sender) == False:
			senders[sender] = 0

		    senders[sender] += 1

		else:
		    # TRANS check #
		    data = re.findall( match_trans, buffer[4:] )

		    if data != []:
			nTrans += 1


    print "[+] Done reading file!"
    fd.close()


### Statistics ###########################################

print "\n---++ Help Channel Statistics ++---\n"

print "[#] Claimed calls (unique/total): %d/%d" % (len(claimed), nClaimed)

values = claimed.values()
values.sort()
values.reverse()
mirror = claimed

for v in values[:5]:
    keys = mirror.keys()
    for idx in range(len(keys)):
	if v == mirror[keys[idx]]:
	    print "    > [%3d] %s" % (mirror[keys[idx]], keys[idx])
	    del(mirror[keys[idx]])
	    break

print "[#] Detected total sent calls: %d"    % nSent

values = senders.values()
values.sort()
values.reverse()
mirror = senders

for v in values[:5]:
    keys = mirror.keys()
    for idx in range(len(keys)):
	if v == mirror[keys[idx]]:
	    print "    > [%3d] %s" % (mirror[keys[idx]], keys[idx])
	    del(mirror[keys[idx]])
	    break

print "[#] Detected total transfered calls: %d"    % nTrans


### End of Script ########################################