spaCy/spacy/lang/ur/__init__.py
Ines Montani e0cf4796a5 Move lookup tables out of the core library (#4346)
* Add default to util.get_entry_point

* Tidy up entry points

* Read lookups from entry points

* Remove lookup tables and related tests

* Add lookups install option

* Remove lemmatizer tests

* Remove logic to process language data files

* Update setup.cfg
2019-10-01 00:01:27 +02:00

32 lines
798 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}
class Urdu(Language):
lang = "ur"
Defaults = UrduDefaults
__all__ = ["Urdu"]