mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-21 19:39:13 +03:00
db55577c45
* Remove unicode declarations * Remove Python 3.5 and 2.7 from CI * Don't require pathlib * Replace compat helpers * Remove OrderedDict * Use f-strings * Set Cython compiler language level * Fix typo * Re-add OrderedDict for Table * Update setup.cfg * Revert CONTRIBUTING.md * Revert lookups.md * Revert top-level.md * Small adjustments and docs [ci skip]
58 lines
1.7 KiB
Python
58 lines
1.7 KiB
Python
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
|
from .tag_map import TAG_MAP
|
|
from .stop_words import STOP_WORDS
|
|
from .norm_exceptions import NORM_EXCEPTIONS
|
|
from .lex_attrs import LEX_ATTRS
|
|
|
|
from ..norm_exceptions import BASE_NORMS
|
|
from ...attrs import LANG, NORM
|
|
from ...language import Language
|
|
from ...tokens import Doc
|
|
from ...util import DummyTokenizer, add_lookups
|
|
|
|
|
|
class ThaiTokenizer(DummyTokenizer):
|
|
def __init__(self, cls, nlp=None):
|
|
try:
|
|
from pythainlp.tokenize import word_tokenize
|
|
except ImportError:
|
|
raise ImportError(
|
|
"The Thai tokenizer requires the PyThaiNLP library: "
|
|
"https://github.com/PyThaiNLP/pythainlp"
|
|
)
|
|
|
|
self.word_tokenize = word_tokenize
|
|
self.vocab = nlp.vocab if nlp is not None else cls.create_vocab(nlp)
|
|
|
|
def __call__(self, text):
|
|
words = list(self.word_tokenize(text))
|
|
spaces = [False] * len(words)
|
|
return Doc(self.vocab, words=words, spaces=spaces)
|
|
|
|
|
|
class ThaiDefaults(Language.Defaults):
|
|
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
|
|
lex_attr_getters.update(LEX_ATTRS)
|
|
lex_attr_getters[LANG] = lambda _text: "th"
|
|
lex_attr_getters[NORM] = add_lookups(
|
|
Language.Defaults.lex_attr_getters[NORM], BASE_NORMS, NORM_EXCEPTIONS
|
|
)
|
|
tokenizer_exceptions = dict(TOKENIZER_EXCEPTIONS)
|
|
tag_map = TAG_MAP
|
|
stop_words = STOP_WORDS
|
|
|
|
@classmethod
|
|
def create_tokenizer(cls, nlp=None):
|
|
return ThaiTokenizer(cls, nlp)
|
|
|
|
|
|
class Thai(Language):
|
|
lang = "th"
|
|
Defaults = ThaiDefaults
|
|
|
|
def make_doc(self, text):
|
|
return self.tokenizer(text)
|
|
|
|
|
|
__all__ = ["Thai"]
|