explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-11-04 01:48:04 +03:00
Code Issues Packages Projects Releases Wiki Activity

added prefix & suffix rules

Browse Source
This commit is contained in:
Jim Geovedi 2017-07-23 23:46:40 +07:00
parent ba922e30e8
commit 0e590c711f
1 changed files with 3 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
spacy/lang/id/__init__.py
View File

@ -2,6 +2,7 @@
from __future__ import unicode_literals from __future__ import unicode_literals
from .stop_words import STOP_WORDS from .stop_words import STOP_WORDS
from .punctuation import TOKENIZER_SUFFIXES, TOKENIZER_PREFIXES
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
from .norm_exceptions import NORM_EXCEPTIONS from .norm_exceptions import NORM_EXCEPTIONS
from .lex_attrs import LEX_ATTRS from .lex_attrs import LEX_ATTRS
@ -20,6 +21,8 @@ class IndonesianDefaults(Language.Defaults):
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS) tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
stop_words = set(STOP_WORDS) stop_words = set(STOP_WORDS)
prefixes = tuple(TOKENIZER_PREFIXES)
suffixes = tuple(TOKENIZER_SUFFIXES)
class Indonesian(Language): class Indonesian(Language):