Created
June 20, 2023 12:50
-
-
Save bhanpuramufaddal/895ebfad88060def0f3178fff176b0df to your computer and use it in GitHub Desktop.
Tokenization and Lemmatization using Mecab and Fugashi
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| from typing import Iterable | |
| from typing import Callable | |
| from typing import Text | |
| from MeCab import Tagger | |
| def _get_tagger() -> Tagger: | |
| opts = getenv('MECAB_OPTS', '-d /usr/local/Cellar/mecab-ipadic/2.7.0-20070801/lib/mecab/dic/ipadic') | |
| tagger = Tagger(opts) | |
| # for some reason the first request to the tagger doesn't produce output | |
| # so pre-warming it here once to avoid serving daft results later | |
| parsed = tagger.parseToNode('サザエさんは走った') | |
| while parsed: | |
| parsed = parsed.next | |
| return tagger | |
| def _tokenize(sentence: Text) -> Iterable[Text]: | |
| parsed = _get_tagger().parseToNode(sentence) | |
| while parsed: | |
| token = parsed.surface.strip() | |
| if token: | |
| yield token | |
| parsed = parsed.next |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment