explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-26 01:46:28 +03:00
Code Issues Packages Projects Releases Wiki Activity

Fix language data imports

Browse Source
This commit is contained in:
ines 2017-05-08 23:58:31 +02:00
parent 3c0f85de8e
commit 6eb6306843
1 changed files with 8 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
spacy/language.py
View File

@ -16,10 +16,12 @@ from .syntax.arc_eager import ArcEager
from .syntax.ner import BiluoPushDown from .syntax.ner import BiluoPushDown
from .compat import json_dumps from .compat import json_dumps
from .attrs import IS_STOP from .attrs import IS_STOP
from .lang.punctuation import TOKENIZER_PREFIXES, TOKENIZER_SUFFIXES, TOKENIZER_INFIXES
from .lang.tokenizer_exceptions import TOKEN_MATCH
from .lang.tag_map import TAG_MAP
from . import attrs from . import attrs
from . import orth from . import orth
from . import util from . import util
from . import language_data
class BaseDefaults(object): class BaseDefaults(object):
@ -135,11 +137,11 @@ class BaseDefaults(object):
pipeline.append(nlp.entity) pipeline.append(nlp.entity)
return pipeline return pipeline
token_match = language_data.TOKEN_MATCH token_match = TOKEN_MATCH
prefixes = tuple(language_data.TOKENIZER_PREFIXES) prefixes = tuple(TOKENIZER_PREFIXES)
suffixes = tuple(language_data.TOKENIZER_SUFFIXES) suffixes = tuple(TOKENIZER_SUFFIXES)
infixes = tuple(language_data.TOKENIZER_INFIXES) infixes = tuple(TOKENIZER_INFIXES)
tag_map = dict(language_data.TAG_MAP) tag_map = dict(TAG_MAP)
tokenizer_exceptions = {} tokenizer_exceptions = {}
parser_features = get_templates('parser') parser_features = get_templates('parser')
entity_features = get_templates('ner') entity_features = get_templates('ner')