mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-26 01:46:28 +03:00
1448ad100c
* Improved stop words list * Removed some wrong stop words form list * Improved stop words list * Removed some wrong stop words form list * Improved Polish Tokenizer (#38) * Add tests for polish tokenizer * Add polish tokenizer exceptions * Don't split any words containing hyphens * Fix test case with wrong model answer * Remove commented out line of code until better solution is found * Add source srx' license * Rename exception_list.py to match spaCy conventionality * Add a brief explanation of where the exception list comes from * Add newline after reach exception * Rename COPYING.txt to LICENSE * Delete old files * Add header to the license * Agreements signed * Stanisław Giziński agreement * Krzysztof Kowalczyk - signed agreement * Mateusz Olko agreement * Add DoomCoder's contributor agreement * Improve like number checking in polish lang * like num tests added * all from SI system added * Final licence and removed splitting exceptions * Added polish stop words to LEX_ATTRA * Add encoding info to pl tokenizer exceptions
32 lines
951 B
Python
32 lines
951 B
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
|
from .stop_words import STOP_WORDS
|
|
from .lex_attrs import LEX_ATTRS
|
|
from .punctuation import TOKENIZER_INFIXES
|
|
|
|
from ..tokenizer_exceptions import BASE_EXCEPTIONS
|
|
from ..norm_exceptions import BASE_NORMS
|
|
from ...language import Language
|
|
from ...attrs import LANG, NORM
|
|
from ...util import update_exc, add_lookups
|
|
|
|
|
|
class PolishDefaults(Language.Defaults):
|
|
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
|
|
lex_attr_getters.update(LEX_ATTRS)
|
|
lex_attr_getters[LANG] = lambda text: 'pl'
|
|
lex_attr_getters[NORM] = add_lookups(Language.Defaults.lex_attr_getters[NORM], BASE_NORMS)
|
|
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
|
|
infixes = tuple(TOKENIZER_INFIXES)
|
|
stop_words = STOP_WORDS
|
|
|
|
|
|
class Polish(Language):
|
|
lang = 'pl'
|
|
Defaults = PolishDefaults
|
|
|
|
|
|
__all__ = ['Polish']
|