Created
June 5, 2013 17:42
-
-
Save mdrcode/5715741 to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import sys | |
from itertools import islice | |
def window(seq, n=2): | |
"Returns a sliding window (of width n) over data from the iterable" | |
" s -> (s0,s1,...s[n-1]), (s1,s2,...,sn), ... " | |
it = iter(seq) | |
result = tuple(islice(it, n)) | |
if len(result) == n: | |
yield result | |
for elem in it: | |
result = result[1:] + (elem,) | |
yield result | |
f = open(sys.argv[1], 'r') | |
lines = f.readlines() | |
for (i, (prev2, prev1, line)) in enumerate(window(lines, 3)): | |
if len(line) > (100 * 1000): | |
print "PREV2: %s" % prev2.strip() | |
print "PREV1: %s" % prev1.strip() | |
print "LINE: #: %d length: %d start: %s end: %s" % \ | |
(i, len(line), line[22:100], line[-40:]) | |
print "" |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment