mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-21 19:39:13 +03:00
5ca7dd0f94
* Improve load_language_data helper * WIP: Add Lookups implementation * Start moving lemma data over to JSON * WIP: move data over for more languages * Convert more languages * Fix lemmatizer fixtures in tests * Finish conversion * Auto-format JSON files * Fix test for now * Make sure tables are stored on instance
34 lines
1.1 KiB
Python
34 lines
1.1 KiB
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
|
from .punctuation import TOKENIZER_PREFIXES, TOKENIZER_SUFFIXES, TOKENIZER_INFIXES
|
|
from .tag_map import TAG_MAP
|
|
from .stop_words import STOP_WORDS
|
|
|
|
from ..tokenizer_exceptions import BASE_EXCEPTIONS
|
|
from ...language import Language
|
|
from ...attrs import LANG
|
|
from ...util import update_exc
|
|
|
|
|
|
class BengaliDefaults(Language.Defaults):
|
|
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
|
|
lex_attr_getters[LANG] = lambda text: "bn"
|
|
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
|
|
tag_map = TAG_MAP
|
|
stop_words = STOP_WORDS
|
|
prefixes = TOKENIZER_PREFIXES
|
|
suffixes = TOKENIZER_SUFFIXES
|
|
infixes = TOKENIZER_INFIXES
|
|
# Lemma rules: উচ্চতর বাংলা ব্যাকরণ ও রচনা - অধ্যাপক নিরঞ্জন অধিকারী ও অধ্যাপক ড. সফিউদ্দিন আহমদ
|
|
resources = {"lemma_rules": "lemma_rules.json"}
|
|
|
|
|
|
class Bengali(Language):
|
|
lang = "bn"
|
|
Defaults = BengaliDefaults
|
|
|
|
|
|
__all__ = ["Bengali"]
|