class KoreanTokenizer(DummyTokenizer):
def __init__(self, cls, nlp=None):
self.vocab = nlp.vocab if nlp is not None else cls.create_vocab(nlp)
MeCab = try_mecab_import()
self.mecab_tokenizer = MeCab("-F%f[0],%f[7]")
def __del__(self):
self.mecab_tokenizer.__del__()
def __call__(self, text):
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.lemma_ = dtoken["lemma"]
doc.user_data["full_tags"] = [dt["tag"] for dt in dtokens]
return doc
def detailed_tokens(self, text):
# 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}
class KoreanTokenizer(DummyTokenizer):
def __init__(self, vocab: Vocab):
self.vocab = vocab
MeCab = try_mecab_import() # type: ignore[func-returns-value]
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) -> Iterator[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)
