mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-26 18:06:29 +03:00
db55577c45
* Remove unicode declarations * Remove Python 3.5 and 2.7 from CI * Don't require pathlib * Replace compat helpers * Remove OrderedDict * Use f-strings * Set Cython compiler language level * Fix typo * Re-add OrderedDict for Table * Update setup.cfg * Revert CONTRIBUTING.md * Revert lookups.md * Revert top-level.md * Small adjustments and docs [ci skip]
48 lines
1.4 KiB
Python
48 lines
1.4 KiB
Python
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
||
from .norm_exceptions import NORM_EXCEPTIONS
|
||
from .tag_map import TAG_MAP
|
||
from .stop_words import STOP_WORDS
|
||
from .lex_attrs import LEX_ATTRS
|
||
from .morph_rules import MORPH_RULES
|
||
from .syntax_iterators import SYNTAX_ITERATORS
|
||
|
||
from ..tokenizer_exceptions import BASE_EXCEPTIONS
|
||
from ..norm_exceptions import BASE_NORMS
|
||
from ...language import Language
|
||
from ...attrs import LANG, NORM
|
||
from ...util import update_exc, add_lookups
|
||
|
||
|
||
def _return_en(_):
|
||
return "en"
|
||
|
||
|
||
class EnglishDefaults(Language.Defaults):
|
||
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
|
||
lex_attr_getters.update(LEX_ATTRS)
|
||
lex_attr_getters[LANG] = _return_en
|
||
lex_attr_getters[NORM] = add_lookups(
|
||
Language.Defaults.lex_attr_getters[NORM], BASE_NORMS, NORM_EXCEPTIONS
|
||
)
|
||
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
|
||
tag_map = TAG_MAP
|
||
stop_words = STOP_WORDS
|
||
morph_rules = MORPH_RULES
|
||
syntax_iterators = SYNTAX_ITERATORS
|
||
single_orth_variants = [
|
||
{"tags": ["NFP"], "variants": ["…", "..."]},
|
||
{"tags": [":"], "variants": ["-", "—", "–", "--", "---", "——"]},
|
||
]
|
||
paired_orth_variants = [
|
||
{"tags": ["``", "''"], "variants": [("'", "'"), ("‘", "’")]},
|
||
{"tags": ["``", "''"], "variants": [('"', '"'), ("“", "”")]},
|
||
]
|
||
|
||
|
||
class English(Language):
|
||
lang = "en"
|
||
Defaults = EnglishDefaults
|
||
|
||
|
||
__all__ = ["English"]
|