Print certain stats for subject line length in mailbox files.

mbox_subject_stats.py

#!/usr/bin/env python
# _*_ coding: UTF-8 _*_

"""Print certain stats for subject line length in mailbox files.

The idea is to find out the percentage of lines up to the length
of twice the mailing list tag inside square brackets.
"""

import re


def stats(path, tag):
    "Print mbox subject line stats."
    
    archive = open(path).read()
    pat = re.compile("^Betreff: (.*)$", re.M)
    subjects = re.findall(pat, archive)
    subjects = [s for s in subjects if tag in s]
    
    length_counts = [0] * (max([len(s) for s in subjects]) + 1)
    for k, s in enumerate(subjects):
        length_counts[len(s)] += 1
        # print k, len(s), s
    
    print "Length, #strings, sum(#strings), %"
    total_sum = sum([j for j in length_counts])
    for i in range(len(length_counts)):
        acc_sum = sum([j for j in length_counts[:i+1]])
        args = (i, length_counts[i], acc_sum, 100*float(acc_sum)/total_sum)
        print "%2d %2d %2d %6.2f" % args
    

if __name__ == "__main__":
    # tag = "[Berlin-SZ] "
    tag = "[Berlin-Steglitz-Zehlendorf] "
    path = "2011-September.txt"
    stats(path, tag)