Shell script to compare tex files in python with difflib, output HTML file to highlight the difference.

compare_tex_file.py

#!/usr/bin/env python

import sys
import re
import difflib as dl

if __name__ == '__main__':
    if len(sys.argv) < 3 or len(sys.argv) > 5:
        print ("usage: %s file1 file2 [output.html]" % sys.argv[0])
        sys.exit(0)
    filename1, filename2 = sys.argv[1], sys.argv[2]
    if len(sys.argv) == 4: outname = sys.argv[3]
    else: outname = "diff-output.html"
        
    with open(filename1) as file1, open(filename2) as file2, open(outname, 'w') as outfile:
        raw1, raw2 = file1.readlines(), file2.readlines()
        text1, text2 = [], []
        
        for l in raw1: # suppress TeX comment and blanks
            if (re.match('^%', l) == None and
                re.match('\s*\n', l) == None): text1.append(l)
        for l in raw2: 
            if (re.match('^%', l) == None and
                re.match('\s*\n', l) == None): text2.append(l)
            
        for diff in dl.HtmlDiff().make_file(text1, text2,
                                            filename1, filename2, context=False,
                                            numlines=0):
            outfile.write(diff)