log_parser.py

""" This program that could take a big log file  and make a "single narrative" where text is not repeated """

import sys
import re


def parse_content(src):
    """Get only content(message) from log file"""
    return re.split(r'\((.*)\) ', src).pop()


def parse_timestamp(src):
    """Get only timestamp messages from log file"""
    result = re.search(r'\((.*)\)', src)
    if result is not None:
        return result.group(1)


def remove_repetition_from(lines):
    """Remove repetition data"""
    messages_dict = {}
    messages_array = []

    for _line in lines:
        line = _line.rstrip()
        content = parse_content(line)
        timestamp = parse_timestamp(line)

        if content not in messages_dict:
            messages_dict[content] = timestamp
            messages_array.append(_line)

    return messages_array


if __name__ == "__main__":
    if len(sys.argv) < 2:
        print 'Please input file path'
        sys.exit(1)

    fileName = sys.argv[1]
    print "File path: " + fileName + "\n"

    with open(fileName) as f:
        file_content = f.read().split('\n')
    for message in remove_repetition_from(file_content):
        print message


from unittest import TestCase


class TestRemove_repetition_from(TestCase):
    def test_empty_data(self):
        self.assertEqual(remove_repetition_from(''), [])

    def test_remove_repetition(self):
        list_test = ['fred: I said something', 'bob: Oh I see', '(10:30:28) fred: I said something',
                     '(10:30:29) bob: Oh I see', 'fred: Ah, the text was repeated', 'bob: yes it was',
                     '(Wed 26 10:30:28) fred: I said something', '(Wed 26 10:30:29) bob: Oh I see',
                     '(Wed 26 10:31:20) fred: Ah, the text was repeated', '(Wed 26 10:31:24) bob: yes it was']
        actual = ['fred: I said something', 'bob: Oh I see', 'fred: Ah, the text was repeated', 'bob: yes it was']

        self.assertEqual(remove_repetition_from(list_test), actual)