mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-15 14:17:58 +03:00
c5de9b463a
* Fix incorrect pickling of Japanese and Korean pipelines, which led to the entire pipeline being reset if pickled * Enable pickling of Vietnamese tokenizer * Update tokenizer APIs for Chinese, Japanese, Korean, Thai, and Vietnamese so that only the `Vocab` is required for initialization
113 lines
3.4 KiB
Python
113 lines
3.4 KiB
Python
from typing import Any, Dict
|
|
|
|
from .stop_words import STOP_WORDS
|
|
from .tag_map import TAG_MAP
|
|
from .lex_attrs import LEX_ATTRS
|
|
from ...language import Language
|
|
from ...tokens import Doc
|
|
from ...scorer import Scorer
|
|
from ...symbols import POS
|
|
from ...training import validate_examples
|
|
from ...util import DummyTokenizer, registry, load_config_from_str
|
|
from ...vocab import Vocab
|
|
|
|
|
|
DEFAULT_CONFIG = """
|
|
[nlp]
|
|
|
|
[nlp.tokenizer]
|
|
@tokenizers = "spacy.ko.KoreanTokenizer"
|
|
"""
|
|
|
|
|
|
@registry.tokenizers("spacy.ko.KoreanTokenizer")
|
|
def create_tokenizer():
|
|
def korean_tokenizer_factory(nlp):
|
|
return KoreanTokenizer(nlp.vocab)
|
|
|
|
return korean_tokenizer_factory
|
|
|
|
|
|
class KoreanTokenizer(DummyTokenizer):
|
|
def __init__(self, vocab: Vocab):
|
|
self.vocab = vocab
|
|
MeCab = try_mecab_import()
|
|
self.mecab_tokenizer = MeCab("-F%f[0],%f[7]")
|
|
|
|
def __reduce__(self):
|
|
return KoreanTokenizer, (self.vocab,)
|
|
|
|
def __del__(self):
|
|
self.mecab_tokenizer.__del__()
|
|
|
|
def __call__(self, text: str) -> Doc:
|
|
dtokens = list(self.detailed_tokens(text))
|
|
surfaces = [dt["surface"] for dt in dtokens]
|
|
doc = Doc(self.vocab, words=surfaces, spaces=list(check_spaces(text, surfaces)))
|
|
for token, dtoken in zip(doc, dtokens):
|
|
first_tag, sep, eomi_tags = dtoken["tag"].partition("+")
|
|
token.tag_ = first_tag # stem(어간) or pre-final(선어말 어미)
|
|
token.pos = TAG_MAP[token.tag_][POS]
|
|
token.lemma_ = dtoken["lemma"]
|
|
doc.user_data["full_tags"] = [dt["tag"] for dt in dtokens]
|
|
return doc
|
|
|
|
def detailed_tokens(self, text: str) -> Dict[str, Any]:
|
|
# 품사 태그(POS)[0], 의미 부류(semantic class)[1], 종성 유무(jongseong)[2], 읽기(reading)[3],
|
|
# 타입(type)[4], 첫번째 품사(start pos)[5], 마지막 품사(end pos)[6], 표현(expression)[7], *
|
|
for node in self.mecab_tokenizer.parse(text, as_nodes=True):
|
|
if node.is_eos():
|
|
break
|
|
surface = node.surface
|
|
feature = node.feature
|
|
tag, _, expr = feature.partition(",")
|
|
lemma, _, remainder = expr.partition("/")
|
|
if lemma == "*":
|
|
lemma = surface
|
|
yield {"surface": surface, "lemma": lemma, "tag": tag}
|
|
|
|
def score(self, examples):
|
|
validate_examples(examples, "KoreanTokenizer.score")
|
|
return Scorer.score_tokenization(examples)
|
|
|
|
|
|
class KoreanDefaults(Language.Defaults):
|
|
config = load_config_from_str(DEFAULT_CONFIG)
|
|
lex_attr_getters = LEX_ATTRS
|
|
stop_words = STOP_WORDS
|
|
writing_system = {"direction": "ltr", "has_case": False, "has_letters": False}
|
|
|
|
|
|
class Korean(Language):
|
|
lang = "ko"
|
|
Defaults = KoreanDefaults
|
|
|
|
|
|
def try_mecab_import() -> None:
|
|
try:
|
|
from natto import MeCab
|
|
|
|
return MeCab
|
|
except ImportError:
|
|
raise ImportError(
|
|
"Korean support requires [mecab-ko](https://bitbucket.org/eunjeon/mecab-ko/src/master/README.md), "
|
|
"[mecab-ko-dic](https://bitbucket.org/eunjeon/mecab-ko-dic), "
|
|
"and [natto-py](https://github.com/buruzaemon/natto-py)"
|
|
) from None
|
|
|
|
|
|
def check_spaces(text, tokens):
|
|
prev_end = -1
|
|
start = 0
|
|
for token in tokens:
|
|
idx = text.find(token, start)
|
|
if prev_end > 0:
|
|
yield prev_end != idx
|
|
prev_end = idx + len(token)
|
|
start = prev_end
|
|
if start > 0:
|
|
yield False
|
|
|
|
|
|
__all__ = ["Korean"]
|