#
# this is a parser function specially designed for the 'bzip2.log'
#
import re

def log_parse(log_file):
    # set up rule for regex
    reObj = re.compile('^(PASS|FAIL+?): (.+)', re.MULTILINE)

    # init a dictionary, it stores the return result
    case_list = dict()

    # open file
    test_log = open(log_file, 'r')

    # start to read the new line
    line = test_log.readline()

    while line:
        if ("Testing decompression and recompression..." in line):
            # dectect trigger line for part 2, change regex rule
            reObj = re.compile('^(PASS|FAIL+?): /usr/lib/bzip2/ptest/bzip2-tests/(.+)', re.MULTILINE)

        elif ("Testing detection of bad input data..." in line):
            # dectect trigger line for part 3, change regex rule
            reObj = re.compile('^(PASS|FAIL+?): .+/usr/lib/bzip2/ptest/bzip2-tests/(.+)', re.MULTILINE)

        # checking regex status in line
        matchs = reObj.search(line)

        # if the line fits the regex rule
        if matchs:
            # spliting elements into a tuple
            # it looks like ('PASS', '<File_Name Test_Name>')
            groups = matchs.groups()

            # adjust name
            tmp_name = groups[1]
            tmp_name = tmp_name.strip()
            case_name = tmp_name.replace('.bad', '.bad Check Integrity')

            # then just add a new key naming after case_name, along with its values
            case_list[case_name] = [case_name, groups[0], ""]

        # jump out if-else, read next line
        line = test_log.readline()

    test_log.close()

    return case_list