Created
September 5, 2011 06:48
-
-
Save venj/1194260 to your computer and use it in GitHub Desktop.
parse raw dict file to xml
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 __future__ import division | |
import sys,os | |
def decrypt(str): | |
i=0 | |
tmp='' | |
try: | |
while True: | |
tmp+=chr((255-ord(str[i]))) #XD | |
i+=1 | |
except IndexError:pass | |
return tmp | |
def parse_dict(file): | |
pointer = 0x404 | |
delDuplicate=False | |
f=open(file,'rb') | |
buffer='' | |
f.seek(pointer) | |
output_file = file.split(".")[0] + '.xml' | |
buffer = decrypt(f.read()) | |
rindex = buffer.rfind(r'</word>') + len(r'</word>') | |
open(output_file, "wb+").write(buffer[:rindex].replace(r'</word>', "</word>\n")) | |
if len(sys.argv) < 2: | |
print "Usage: %s dict_file_1 [...]" % sys.argv[0] | |
exit(1) | |
sys.argv.pop(0) | |
for f in sys.argv: | |
print "Processing: %s" % f | |
parse_dict(f) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment