Finds the largest duplicate text block in a file

find_dry_violations.py

#!/usr/bin/env python

import sys

orig_txt = open(sys.argv[-1], "r").readlines()
txt = [line.strip() for line in orig_txt]

match_len = 0
longest_match = [
	'occurence1 start', 'occurance1 end',
	'occurence2 start', 'occurance2 end',
]

for i in range(len(txt)):
	for j in range(i+1, len(txt)):
		if (txt[i] != txt[j]):
			continue
		matching_lines = 1
		try:
			while txt[i+matching_lines] == txt[j+matching_lines]:
				matching_lines += 1
		except IndexError: pass
		if matching_lines > match_len:
			match_len = matching_lines
			longest_match = [
				i, i + matching_lines,
				j, j + matching_lines,
			]

print "Longest match: %s lines" % match_len
print "Lines %s - %s and %s - %s match" % tuple(longest_match)

gistfile2.txt