spaCy/spacy/es/language_data.py

55 lines
1.3 KiB
Python
Raw Normal View History

# encoding: utf8
from __future__ import unicode_literals
2016-11-02 22:43:12 +03:00
2016-12-18 18:54:19 +03:00
from .. import language_data as base
from ..language_data import update_exc, strings_to_exc
from ..symbols import ORTH, LEMMA
2016-12-18 18:54:19 +03:00
from .stop_words import STOP_WORDS
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS, ORTH_ONLY
2016-12-08 21:47:03 +03:00
def get_time_exc(hours):
exc = {
"12m.": [
{ORTH: "12"},
{ORTH: "m.", LEMMA: "p.m."}
]
}
for hour in hours:
exc["%sa.m." % hour] = [
{ORTH: hour},
{ORTH: "a.m."}
]
exc["%sp.m." % hour] = [
{ORTH: hour},
{ORTH: "p.m."}
]
exc["%sam" % hour] = [
{ORTH: hour},
{ORTH: "am", LEMMA: "a.m."}
]
exc["%spm" % hour] = [
{ORTH: hour},
{ORTH: "pm", LEMMA: "p.m."}
]
return exc
2016-12-18 18:54:19 +03:00
STOP_WORDS = set(STOP_WORDS)
2016-12-08 21:47:03 +03:00
TOKENIZER_EXCEPTIONS = dict(TOKENIZER_EXCEPTIONS)
2016-12-18 18:54:19 +03:00
update_exc(TOKENIZER_EXCEPTIONS, strings_to_exc(ORTH_ONLY))
update_exc(TOKENIZER_EXCEPTIONS, get_time_exc(
['%d' % hour for hour in range(1, 12 + 1)]))
2016-12-18 18:54:19 +03:00
update_exc(TOKENIZER_EXCEPTIONS, strings_to_exc(base.EMOTICONS))
update_exc(TOKENIZER_EXCEPTIONS, strings_to_exc(base.ABBREVIATIONS))
2016-12-08 21:47:03 +03:00
2016-12-18 18:54:19 +03:00
__all__ = ["TOKENIZER_EXCEPTIONS", "STOP_WORDS"]