Rooba
/
spaCy
mirror of https://github.com/explosion/spaCy.git
1
1
Fork 0
Code Issues Packages Projects Releases Wiki Activity

reworked

This commit is contained in:
Jim Geovedi 2017-08-20 13:43:21 +07:00
parent fbc62a09c7
commit f77443ab68
2 changed files with 2 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

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

@ -3,7 +3,7 @@ from __future__ import unicode_literals
from .stop_words import STOP_WORDS
from .punctuation import TOKENIZER_SUFFIXES, TOKENIZER_PREFIXES, TOKENIZER_INFIXES
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS, TOKEN_MATCH
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
from .norm_exceptions import NORM_EXCEPTIONS
from .lemmatizer import LOOKUP
from .lex_attrs import LEX_ATTRS
@ -24,7 +24,6 @@ class IndonesianDefaults(Language.Defaults):
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
stop_words = set(STOP_WORDS)
token_match = TOKEN_MATCH
prefixes = tuple(TOKENIZER_PREFIXES)
suffixes = tuple(TOKENIZER_SUFFIXES)
infixes = tuple(TOKENIZER_INFIXES)

22
spacy/lang/id/tokenizer_exceptions.py
View File

@ -46,25 +46,5 @@ for orth in [
]:
_exc[orth] = [{ORTH: orth}]
_hyphen_prefix = """abdur abdus abou aboul abror abshar abu abubakar abul
aero agri agro ahmadi ahmed air abd abdel abdul ad adz afro al ala ali all
amir an antar anti ar as ash asy at ath az bekas ber best bi co di double
dual duo e eco eks el era ex full hi high i in inter intra ke kontra korona
kuartal lintas m macro makro me mem meng micro mid mikro mini multi neo nge
no non on pan pasca pe pem poli poly post pra pre pro re se self serba seri
sub super t trans u ultra un x""".split()
_hyphen_infix = """ber-an berke-an de-isasi di-kan di-kannya di-nya ke-an
ke-annya me-kan me-kannya men-kan men-kannya meng-kannya pe-an pen-an
per-an per-i se-an se-nya ter-i ter-kan ter-kannya""".split()
_hyphen_suffix = """el"""
_regular_exp = ['^{p}-[A-Za-z0-9]+$'.format(p=prefix) for prefix in _hyphen_prefix]
_regular_exp += ['^{0}-[A-Za-z0-9]+-{1}$'.format(*infix.split('-')) for infix in _hyphen_infix]
_regular_exp += ['^[A-Za-z0-9]+-{s}$'.format(s=suffix) for suffix in _hyphen_suffix]
_regular_exp.append(URL_PATTERN)
TOKENIZER_EXCEPTIONS = dict(_exc)
TOKEN_MATCH = re.compile('|'.join('(?:{})'.format(m) for m in _regular_exp), re.IGNORECASE).match