Last active
December 15, 2015 07:19
-
-
Save rrader/5223087 to your computer and use it in GitHub Desktop.
Блочный алгоритм удаления комментариев из файла
This file contains 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
from StringIO import StringIO | |
import re | |
import itertools | |
s = 'text1 text2 /* asdasd */ text3 /* /*asdasd */ text4' | |
BLOCK = 6 # even number! | |
OPEN = 1 | |
CLOSE = 2 | |
another = {OPEN: CLOSE, CLOSE: OPEN} | |
def blocked(f, position=False): | |
while True: | |
block = f.read(BLOCK) | |
if not block: | |
break | |
if position: | |
yield (block, f.pos - BLOCK) | |
else: | |
yield block | |
def finder(block): | |
block, pos = block | |
comments = [(m.start() + pos, OPEN) for m in re.finditer('/\*', block)] + \ | |
[(m.end() + pos, CLOSE) for m in re.finditer('\*/', block)] | |
return comments | |
def reducer(datafile): | |
def do_reduce(data, item, waiting=[OPEN]): | |
if waiting[0] == item[1]: | |
waiting[0] = another[waiting[0]] | |
new_data = datafile.read(item[0] - datafile.pos) | |
if item[1] == OPEN: | |
data.append(new_data) | |
return data | |
else: | |
return data | |
else: | |
return data | |
return do_reduce | |
datafile = StringIO(s) | |
comments = itertools.chain([[]], *map(finder, blocked(datafile, position=True))) | |
datafile.seek(0) | |
result = ''.join(reduce(reducer(datafile), comments)) + datafile.read() | |
print result |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment