Skip to content

Instantly share code, notes, and snippets.

@wolfkarl
Last active November 1, 2016 15:52
Show Gist options
  • Select an option

  • Save wolfkarl/80acad3a7290b34a5f94 to your computer and use it in GitHub Desktop.

Select an option

Save wolfkarl/80acad3a7290b34a5f94 to your computer and use it in GitHub Desktop.
Lazy Lover Python Word Count
#!/usr/bin/env python
# -*- coding: utf-8 -*-
import re
import glob
import os
# (C) 2015 Ich konzentriere mich völlig auf meine Bachelorarbeit GmbH
# v2: now mildly recursive (depth of 1)
# v3: sortiert die meisten Latexbefehle aus
def wordcount(value):
# Find all non-whitespace patterns.
words = re.findall("(\S+)", value)
latex_befehle = re.findall("(\\{\\})", value) + re.findall("(\\\\item)", value)
# Return length of resulting list.
return len(words) - len(latex_befehle)
def get_latex_files():
file_list = glob.glob('*.tex')
file_list += (glob.glob(os.path.join('*', '*.tex')))
return file_list
totalwords = 0
total_comment_lines = 0
file_output_format = "{:<25}"
wordcount_output_format = "{:>5}"
for filename in get_latex_files():
file = open(filename, 'r')
print file_output_format.format(filename),
words = 0
for line in file:
if line[0] != "%":
words += wordcount(line)
else:
total_comment_lines += 1
totalwords += words
print wordcount_output_format.format(words)
print "-" * 31
print file_output_format.format("TOTAL"),
print wordcount_output_format.format(totalwords)
print "(%i Zeilen Kommentar ignoriert)\n" % total_comment_lines
@mr-flannery

Copy link
Copy Markdown

This is like the most awesome script ever.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment