README

$ python xlogd.py sample.log

parsed: {'appname': 'test.app', 'timestamp': '2012-09-06 15:19:32', 'hostname': 'codezone.local', 'pid': '68898', 'priority': '132', 'message': 'bla bla bla warn'}
parsed: {'appname': 'test.app', 'timestamp': '2012-09-06 15:19:32', 'hostname': 'codezone.local', 'pid': '68902', 'priority': '131', 'message': 'bla bla bla error'}
parsed: {'appname': 'Dock', 'timestamp': '2012-09-06 15:19:32', 'hostname': 'codezone.local', 'pid': '154', 'priority': '11', 'message': 'CGSReleaseWindowList: called with 5 invalid window(s)'}
parsed: {'appname': 'WindowServer', 'timestamp': '2012-09-06 15:19:32', 'hostname': 'codezone.local', 'pid': '79', 'priority': '11', 'message': 'CGXSetWindowListAlpha: Invalid window 0'}

sample.log

<132>Sep  6 14:35:48 codezone.local test.app[68898]: bla bla bla warn
<131>Sep  6 14:35:58 codezone.local test.app[68902]: bla bla bla error
<11>Sep  6 14:37:53 codezone.local Dock[154]: CGSReleaseWindowList: called with 5 invalid window(s)
<11>Sep  6 14:38:09 codezone.local WindowServer[79]: CGXSetWindowListAlpha: Invalid window 0

xlog.py

from pyparsing import Word, alphas, Suppress, Combine, nums, string, Optional, Regex
from time import strftime

class Parser(object):
  def __init__(self):
    ints = Word(nums)

    # priority
    priority = Suppress("<") + ints + Suppress(">")

    # timestamp
    month = Word(string.uppercase, string.lowercase, exact=3)
    day   = ints
    hour  = Combine(ints + ":" + ints + ":" + ints)
    
    timestamp = month + day + hour

    # hostname
    hostname = Word(alphas + nums + "_" + "-" + ".")

    # appname
    appname = Word(alphas + "/" + "-" + "_" + ".") + Optional(Suppress("[") + ints + Suppress("]")) + Suppress(":")

    # message
    message = Regex(".*")
  
    # pattern build
    self.__pattern = priority + timestamp + hostname + appname + message
    
  def parse(self, line):
    parsed = self.__pattern.parseString(line)

    payload              = {}
    payload["priority"]  = parsed[0]
    payload["timestamp"] = strftime("%Y-%m-%d %H:%M:%S")
    payload["hostname"]  = parsed[4]
    payload["appname"]   = parsed[5]
    payload["pid"]       = parsed[6]
    payload["message"]   = parsed[7]
    
    return payload

""" --------------------------------- """

def main():
  parser = Parser()
  
  with open('./sample.log') as syslogFile:
    for line in syslogFile:
      fields = parser.parse(line)
      print "parsed:", fields
  
if __name__ == "__main__":
  main()