explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-09-21 11:29:13 +03:00
Code Issues Packages Projects Releases Wiki Activity

Update base punctuation

Browse Source
This commit is contained in:
ines 2017-10-14 14:59:23 +02:00
parent 9d6c8eaa49
commit e85e1d571b
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
spacy/lang/char_classes.py
View File

@ -33,7 +33,7 @@ _currency = r'\$ £ € ¥ ฿ US\$ C\$ A\$'
# These expressions contain various unicode variations, including characters
# used in Chinese (see #1333, #1340, #1351) – unless there are cross-language
# conflicts, spaCy's base tokenizer should handle all of those by default
_punct = r'… …… , : ; \! \? ¿ ¡ \( \) \[ \] \{ \} < > _ # \* & 。 ？ ！ ， 、 ； ： ～ ·'
_punct = r'… …… , : ; \! \? ¿ ¡ \( \) \[ \] \{ \} < > _ # \* & 。 ？ ！ ， 、 ； ： ～ · ।'
_quotes = r'\' \'\' " ” “ `` ` ‘ ´ ‘‘ ’’ ‚ , „ » « 「 」 『 』 （ ） 〔 〕 【 】 《 》 〈 〉'
_hyphens = '- – — -- --- —— ~'