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
33 lines
852 B
Python
33 lines
852 B
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
from .stop_words import STOP_WORDS
|
|
from .lex_attrs import LEX_ATTRS
|
|
from .punctuation import TOKENIZER_SUFFIXES
|
|
from .tag_map import TAG_MAP
|
|
|
|
from ..tokenizer_exceptions import BASE_EXCEPTIONS
|
|
from ...language import Language
|
|
from ...attrs import LANG
|
|
|
|
|
|
class UrduDefaults(Language.Defaults):
|
|
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
|
|
lex_attr_getters.update(LEX_ATTRS)
|
|
lex_attr_getters[LANG] = lambda text: "ur"
|
|
|
|
tokenizer_exceptions = BASE_EXCEPTIONS
|
|
tag_map = TAG_MAP
|
|
stop_words = STOP_WORDS
|
|
suffixes = TOKENIZER_SUFFIXES
|
|
writing_system = {"direction": "rtl", "has_case": False, "has_letters": True}
|
|
resources = {"lemma_lookup": "lemma_lookup.json"}
|
|
|
|
|
|
class Urdu(Language):
|
|
lang = "ur"
|
|
Defaults = UrduDefaults
|
|
|
|
|
|
__all__ = ["Urdu"]
|