Python script that performs line matching over stale files generates inconsistent output

Question

I created a python script to parse mail (exim) logfiles and execute pattern matching in order to get a top 100 list for most send domains on my smtp servers. However, everytime I execute the script I get a different count. These are stale logfiles, and I cannot find a functional flaw in my code.

Example output:
    1:
    70353 gmail.com
    68337 hotmail.com
    53657 yahoo.com
    2:
    70020 gmail.com
    67741 hotmail.com
    54397 yahoo.com
    3:
    70191 gmail.com
    67917 hotmail.com
    54438 yahoo.com

Code:

#!/usr/bin/env python

import os
import datetime
import re
from collections import defaultdict

class DomainCounter(object):
def __init__(self):
    self.base_path = '/opt/mail_log'
    self.tmp = []
    self.date = datetime.date.today() - datetime.timedelta(days=14)
    self.file_out = '/var/tmp/parsed_exim_files-'  + str(self.date.strftime('%Y%m%d')) + '.decompressed'

def parse_log_files(self):
    sub_dir = os.listdir(self.base_path)
    for directory in sub_dir:
        if re.search('smtp\d+', directory):
            fileInput = self.base_path + '/' + directory + '/maillog-' + str(self.date.strftime('%Y%m%d')) + '.bz2'
            if not os.path.isfile(self.file_out):
                 os.popen('touch ' + self.file_out)
            proccessFiles = os.popen('/bin/bunzip2 -cd ' + fileInput + ' > ' + self.file_out)
            accessFileHandle =  open(self.file_out, 'r')
            readFileHandle = accessFileHandle.readlines()
            print "Proccessing %s." % fileInput
            for line in readFileHandle:
                if '<=' in line and ' for ' in line and '<>' not in line:
                    distinctLine = line.split(' for ')
                    recipientAddresses = distinctLine[1].strip()
                    recipientAddressList = recipientAddresses.strip().split(' ')
                    if len(recipientAddressList) > 1:
                        for emailaddress in recipientAddressList:
                            # Since syslog messages are transmitted over UDP some messages are dropped and needs to be filtered out.
                            if '@' in emailaddress:
                                (login, domein) = emailaddress.split("@")
                                self.tmp.append(domein)
                                continue
    else:
        try:
                                (login, domein) = recipientAddressList[0].split("@")
                                self.tmp.append(domein)
        except Exception as e:
             print e, '<<No valid email address found, skipping line>>'

    accessFileHandle.close()
    os.unlink(self.file_out)
return self.tmp


if __name__ == '__main__':
domainCounter = DomainCounter()
result = domainCounter.parse_log_files()
domainCounts = defaultdict(int)
top = 100
for domain in result:
    domainCounts[domain] += 1

sortedDict = dict(sorted(domainCounts.items(), key=lambda x: x[1], reverse=True)[:int(top)])
for w in sorted(sortedDict, key=sortedDict.get, reverse=True):
    print '%-3s %s' % (sortedDict[w], w)

Answer 1

proccessFiles = os.popen('/bin/bunzip2 -cd ' + fileInput + ' > ' + self.file_out)

This line is non-blocking. Therefore it will start the command, but the few following lines are already reading the file. This is basically a concurrency issue. Try to wait for the command to complete before reading the file.

Also see: Python popen command. Wait until the command is finished since os.popen is deprecated since python-2.6 (depending on which version you are using).

Sidenote - The same happens to the line below. The file may, or may not, exist after executing the following line:

os.popen('touch ' + self.file_out)