mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-27 18:36:36 +03:00
61ce126d4c
* initial LT lang support * Added more stopwords. Started setting up some basic test environment (not complete) * Initial morph rules for LT lang * Closes #1 Adds tokenizer exceptions for Lithuanian * Closes #5 Punctuation rules. Closes #6 Lexical Attributes * test: add native examples to basic tests * feat: add tag map for lt lang * fix: remove undefined tag attribute 'Definite' * feat: add lemmatizer for lt lang * refactor: add new instances to lt lang morph rules; use tags from tag map * refactor: add morph rules to lt lang defaults * refactor: only keep nouns, verbs, adverbs and adjectives in lt lang lemmatizer lookup * refactor: add capitalized words to lt lang lemmatizer * refactor: add more num words to lt lang lex attrs * refactor: update lt lang stop word set * refactor: add new instances to lt lang tokenizer exceptions * refactor: remove comments form lt lang init file * refactor: use function instead of lambda in lt lex lang getter * refactor: remove conversion to dict in lt init when dict is already provided * chore: rename lt 'test_basic' to 'test_text' * feat: add more lt text tests * feat: add lemmatizer tests * refactor: remove unused imports, add newline to end of file * chore: add contributor agreement * chore: change 'en' to 'lt' in lt example description * fix: add missing encoding info * style: add newline to end of file * refactor: use python2 compatible syntax * style: reformat code using black
43 lines
1.1 KiB
Python
43 lines
1.1 KiB
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 .tag_map import TAG_MAP
|
|
from .lemmatizer import LOOKUP
|
|
from .morph_rules import MORPH_RULES
|
|
|
|
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
|
|
|
|
|
|
def _return_lt(_):
|
|
return "lt"
|
|
|
|
|
|
class LithuanianDefaults(Language.Defaults):
|
|
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
|
|
lex_attr_getters[LANG] = _return_lt
|
|
lex_attr_getters[NORM] = add_lookups(
|
|
Language.Defaults.lex_attr_getters[NORM], BASE_NORMS
|
|
)
|
|
lex_attr_getters.update(LEX_ATTRS)
|
|
|
|
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
|
|
stop_words = STOP_WORDS
|
|
tag_map = TAG_MAP
|
|
morph_rules = MORPH_RULES
|
|
lemma_lookup = LOOKUP
|
|
|
|
|
|
class Lithuanian(Language):
|
|
lang = "lt"
|
|
Defaults = LithuanianDefaults
|
|
|
|
|
|
__all__ = ["Lithuanian"]
|