iskm/wordfreq
1
0
Fork 0
mirror of https://github.com/rspeer/wordfreq.git synced 2024-12-23 17:31:41 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

cleaned up BAD_CHAR_RANGE

Browse Source
This commit is contained in:
Joshua Chin 2015-07-17 15:00:59 -04:00
parent c2d1cdcb31
commit 3b368b66dd
1 changed files with 11 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
wordfreq_builder/wordfreq_builder/tokenizers.py
View File

@ -3,16 +3,17 @@ from wordfreq import tokenize, TOKEN_RE, NON_PUNCT_RANGE
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)] +
[']'])
CLD2_BAD_CHAR_RANGE = "[%s]" % "".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)]
)
CLD2_BAD_CHARS_RE = re.compile(CLD2_BAD_CHAR_RANGE)
TWITTER_HANDLE_RE = re.compile('@{0}+'.format(NON_PUNCT_RANGE))