iskm/wordfreq
1
0
Fork 0
mirror of https://github.com/rspeer/wordfreq.git synced 2024-12-23 09:21:37 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Fixed CLD2_BAD_CHAR regex

Browse Source
This commit is contained in:
Joshua Chin 2015-06-18 10:18:00 -04:00
parent 87285b8b90
commit 2f4fe92c90
1 changed files with 3 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
wordfreq_builder/wordfreq_builder/tokenizers.py
View File

@ -4,13 +4,15 @@ import re
import pycld2
CLD2_BAD_CHAR_RANGE = "".join([
'[',
'\x00-\x08',
'\x0b',
'\x0e-\x1f',
'\x7f-\x9f',
'\ud800-\udfff',
'\ufdd0-\ufdef'] +
[chr(65534+65536*x+y) for x in range(17) for y in range(2)])
[chr(65534+65536*x+y) for x in range(17) for y in range(2)] +
[']'])
CLD2_BAD_CHARS_RE = re.compile(CLD2_BAD_CHAR_RANGE)
TWITTER_HANDLE_RE = re.compile('@{0}+'.format(NON_PUNCT_RANGE))