mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-27 10:26:35 +03:00
a5cd203284
* Reduce stored lexemes data, move feats to lookups
* Move non-derivable lexemes features (`norm / cluster / prob`) to
`spacy-lookups-data` as lookups
* Get/set `norm` in both lookups and `LexemeC`, serialize in lookups
* Remove `cluster` and `prob` from `LexemesC`, get/set/serialize in
lookups only
* Remove serialization of lexemes data as `vocab/lexemes.bin`
* Remove `SerializedLexemeC`
* Remove `Lexeme.to_bytes/from_bytes`
* Modify normalization exception loading:
* Always create `Vocab.lookups` table `lexeme_norm` for
normalization exceptions
* Load base exceptions from `lang.norm_exceptions`, but load
language-specific exceptions from lookups
* Set `lex_attr_getter[NORM]` including new lookups table in
`BaseDefaults.create_vocab()` and when deserializing `Vocab`
* Remove all cached lexemes when deserializing vocab to override
existing normalizations with the new normalizations (as a replacement
for the previous step that replaced all lexemes data with the
deserialized data)
* Skip English normalization test
Skip English normalization test because the data is now in
`spacy-lookups-data`.
* Remove norm exceptions
Moved to spacy-lookups-data.
* Move norm exceptions test to spacy-lookups-data
* Load extra lookups from spacy-lookups-data lazily
Load extra lookups (currently for cluster and prob) lazily from the
entry point `lg_extra` as `Vocab.lookups_extra`.
* Skip creating lexeme cache on load
To improve model loading times, do not create the full lexeme cache when
loading. The lexemes will be created on demand when processing.
* Identify numeric values in Lexeme.set_attrs()
With the removal of a special case for `PROB`, also identify `float` to
avoid trying to convert it with the `StringStore`.
* Skip lexeme cache init in from_bytes
* Unskip and update lookups tests for python3.6+
* Update vocab pickle to include lookups_extra
* Update vocab serialization tests
Check strings rather than lexemes since lexemes aren't initialized
automatically, account for addition of "_SP".
* Re-skip lookups test because of python3.5
* Skip PROB/float values in Lexeme.set_attrs
* Convert is_oov from lexeme flag to lex in vectors
Instead of storing `is_oov` as a lexeme flag, `is_oov` reports whether
the lexeme has a vector.
Co-authored-by: Matthew Honnibal <honnibal+gh@gmail.com>
56 lines
1.5 KiB
Python
56 lines
1.5 KiB
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
|
from .tag_map import TAG_MAP
|
|
from .stop_words import STOP_WORDS
|
|
from .lex_attrs import LEX_ATTRS
|
|
|
|
from ...attrs import LANG
|
|
from ...language import Language
|
|
from ...tokens import Doc
|
|
from ...util import DummyTokenizer
|
|
|
|
|
|
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"
|
|
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"]
|