mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-25 09:26:27 +03:00
Don't copy exception dicts if not necessary and tidy up
This commit is contained in:
parent
3c8db3e4da
commit
7e424a1804
|
@ -23,4 +23,4 @@ for exc_data in [
|
||||||
_exc[exc_data[ORTH]] = [dict(exc_data)]
|
_exc[exc_data[ORTH]] = [dict(exc_data)]
|
||||||
|
|
||||||
|
|
||||||
TOKENIZER_EXCEPTIONS = dict(_exc)
|
TOKENIZER_EXCEPTIONS = _exc
|
||||||
|
|
|
@ -30,4 +30,4 @@ for orth in [
|
||||||
_exc[orth] = [{ORTH: orth}]
|
_exc[orth] = [{ORTH: orth}]
|
||||||
|
|
||||||
|
|
||||||
TOKENIZER_EXCEPTIONS = dict(_exc)
|
TOKENIZER_EXCEPTIONS = _exc
|
||||||
|
|
|
@ -181,4 +181,4 @@ for orth in [
|
||||||
_exc[orth] = [{ORTH: orth}]
|
_exc[orth] = [{ORTH: orth}]
|
||||||
|
|
||||||
|
|
||||||
TOKENIZER_EXCEPTIONS = dict(_exc)
|
TOKENIZER_EXCEPTIONS = _exc
|
||||||
|
|
|
@ -456,4 +456,4 @@ for string in _exclude:
|
||||||
_exc.pop(string)
|
_exc.pop(string)
|
||||||
|
|
||||||
|
|
||||||
TOKENIZER_EXCEPTIONS = dict(_exc)
|
TOKENIZER_EXCEPTIONS = _exc
|
||||||
|
|
|
@ -54,4 +54,4 @@ for orth in [
|
||||||
_exc[orth] = [{ORTH: orth}]
|
_exc[orth] = [{ORTH: orth}]
|
||||||
|
|
||||||
|
|
||||||
TOKENIZER_EXCEPTIONS = dict(_exc)
|
TOKENIZER_EXCEPTIONS = _exc
|
||||||
|
|
|
@ -76,4 +76,4 @@ for exc_data in [
|
||||||
_exc[exc_data[ORTH]] = [dict(exc_data)]
|
_exc[exc_data[ORTH]] = [dict(exc_data)]
|
||||||
|
|
||||||
|
|
||||||
TOKENIZER_EXCEPTIONS = dict(_exc)
|
TOKENIZER_EXCEPTIONS = _exc
|
||||||
|
|
|
@ -147,5 +147,5 @@ _regular_exp += ["^{prefix}[{elision}][{alpha}][{alpha}{elision}{hyphen}\-]*$".f
|
||||||
_regular_exp.append(URL_PATTERN)
|
_regular_exp.append(URL_PATTERN)
|
||||||
|
|
||||||
|
|
||||||
TOKENIZER_EXCEPTIONS = dict(_exc)
|
TOKENIZER_EXCEPTIONS = _exc
|
||||||
TOKEN_MATCH = re.compile('|'.join('(?:{})'.format(m) for m in _regular_exp), re.IGNORECASE).match
|
TOKEN_MATCH = re.compile('|'.join('(?:{})'.format(m) for m in _regular_exp), re.IGNORECASE).match
|
||||||
|
|
|
@ -95,5 +95,5 @@ _nums = "(({ne})|({t})|({on})|({c}))({s})?".format(
|
||||||
c=CURRENCY, s=_suffixes)
|
c=CURRENCY, s=_suffixes)
|
||||||
|
|
||||||
|
|
||||||
TOKENIZER_EXCEPTIONS = dict(_exc)
|
TOKENIZER_EXCEPTIONS = _exc
|
||||||
TOKEN_MATCH = re.compile("^({u})|({n})$".format(u=URL_PATTERN, n=_nums)).match
|
TOKEN_MATCH = re.compile("^({u})|({n})$".format(u=URL_PATTERN, n=_nums)).match
|
||||||
|
|
|
@ -46,5 +46,4 @@ for orth in [
|
||||||
]:
|
]:
|
||||||
_exc[orth] = [{ORTH: orth}]
|
_exc[orth] = [{ORTH: orth}]
|
||||||
|
|
||||||
TOKENIZER_EXCEPTIONS = dict(_exc)
|
TOKENIZER_EXCEPTIONS = _exc
|
||||||
|
|
||||||
|
|
|
@ -35,4 +35,4 @@ for orth in [
|
||||||
_exc[orth] = [{ORTH: orth}]
|
_exc[orth] = [{ORTH: orth}]
|
||||||
|
|
||||||
|
|
||||||
TOKENIZER_EXCEPTIONS = dict(_exc)
|
TOKENIZER_EXCEPTIONS = _exc
|
||||||
|
|
|
@ -20,4 +20,4 @@ for orth in [
|
||||||
_exc[orth] = [{ORTH: orth}]
|
_exc[orth] = [{ORTH: orth}]
|
||||||
|
|
||||||
|
|
||||||
TOKENIZER_EXCEPTIONS = dict(_exc)
|
TOKENIZER_EXCEPTIONS = _exc
|
||||||
|
|
|
@ -72,4 +72,4 @@ for orth in [
|
||||||
_exc[orth] = [{ORTH: orth}]
|
_exc[orth] = [{ORTH: orth}]
|
||||||
|
|
||||||
|
|
||||||
TOKENIZER_EXCEPTIONS = dict(_exc)
|
TOKENIZER_EXCEPTIONS = _exc
|
||||||
|
|
|
@ -80,4 +80,4 @@ for orth in [
|
||||||
_exc[orth] = [{ORTH: orth}]
|
_exc[orth] = [{ORTH: orth}]
|
||||||
|
|
||||||
|
|
||||||
TOKENIZER_EXCEPTIONS = dict(_exc)
|
TOKENIZER_EXCEPTIONS = _exc
|
||||||
|
|
|
@ -2,8 +2,8 @@
|
||||||
# data from Korakot Chaovavanich (https://www.facebook.com/photo.php?fbid=390564854695031&set=p.390564854695031&type=3&permPage=1&ifg=1)
|
# data from Korakot Chaovavanich (https://www.facebook.com/photo.php?fbid=390564854695031&set=p.390564854695031&type=3&permPage=1&ifg=1)
|
||||||
from __future__ import unicode_literals
|
from __future__ import unicode_literals
|
||||||
|
|
||||||
from ...symbols import *
|
from ...symbols import POS, NOUN, PRON, ADJ, ADV, INTJ, PROPN, DET, NUM, AUX
|
||||||
|
from ...symbols import ADP, CCONJ, PART, PUNCT, SPACE, SCONJ
|
||||||
TAG_MAP = {
|
TAG_MAP = {
|
||||||
# NOUN
|
# NOUN
|
||||||
"NOUN": {POS: NOUN},
|
"NOUN": {POS: NOUN},
|
||||||
|
|
|
@ -1,43 +1,23 @@
|
||||||
# encoding: utf8
|
# encoding: utf8
|
||||||
from __future__ import unicode_literals
|
from __future__ import unicode_literals
|
||||||
|
|
||||||
from ...symbols import *
|
from ...symbols import ORTH, LEMMA
|
||||||
|
|
||||||
TOKENIZER_EXCEPTIONS = {
|
|
||||||
"ม.ค.": [
|
_exc = {
|
||||||
{ORTH: "ม.ค.", LEMMA: "มกราคม"}
|
"ม.ค.": [{ORTH: "ม.ค.", LEMMA: "มกราคม"}],
|
||||||
],
|
"ก.พ.": [{ORTH: "ก.พ.", LEMMA: "กุมภาพันธ์"}],
|
||||||
"ก.พ.": [
|
"มี.ค.": [{ORTH: "มี.ค.", LEMMA: "มีนาคม"}],
|
||||||
{ORTH: "ก.พ.", LEMMA: "กุมภาพันธ์"}
|
"เม.ย.": [{ORTH: "เม.ย.", LEMMA: "เมษายน"}],
|
||||||
],
|
"พ.ค.": [{ORTH: "พ.ค.", LEMMA: "พฤษภาคม"}],
|
||||||
"มี.ค.": [
|
"มิ.ย.": [{ORTH: "มิ.ย.", LEMMA: "มิถุนายน"}],
|
||||||
{ORTH: "มี.ค.", LEMMA: "มีนาคม"}
|
"ก.ค.": [{ORTH: "ก.ค.", LEMMA: "กรกฎาคม"}],
|
||||||
],
|
"ส.ค.": [{ORTH: "ส.ค.", LEMMA: "สิงหาคม"}],
|
||||||
"เม.ย.": [
|
"ก.ย.": [{ORTH: "ก.ย.", LEMMA: "กันยายน"}],
|
||||||
{ORTH: "เม.ย.", LEMMA: "เมษายน"}
|
"ต.ค.": [{ORTH: "ต.ค.", LEMMA: "ตุลาคม"}],
|
||||||
],
|
"พ.ย.": [{ORTH: "พ.ย.", LEMMA: "พฤศจิกายน"}],
|
||||||
"พ.ค.": [
|
"ธ.ค.": [{ORTH: "ธ.ค.", LEMMA: "ธันวาคม"}]
|
||||||
{ORTH: "พ.ค.", LEMMA: "พฤษภาคม"}
|
|
||||||
],
|
|
||||||
"มิ.ย.": [
|
|
||||||
{ORTH: "มิ.ย.", LEMMA: "มิถุนายน"}
|
|
||||||
],
|
|
||||||
"ก.ค.": [
|
|
||||||
{ORTH: "ก.ค.", LEMMA: "กรกฎาคม"}
|
|
||||||
],
|
|
||||||
"ส.ค.": [
|
|
||||||
{ORTH: "ส.ค.", LEMMA: "สิงหาคม"}
|
|
||||||
],
|
|
||||||
"ก.ย.": [
|
|
||||||
{ORTH: "ก.ย.", LEMMA: "กันยายน"}
|
|
||||||
],
|
|
||||||
"ต.ค.": [
|
|
||||||
{ORTH: "ต.ค.", LEMMA: "ตุลาคม"}
|
|
||||||
],
|
|
||||||
"พ.ย.": [
|
|
||||||
{ORTH: "พ.ย.", LEMMA: "พฤศจิกายน"}
|
|
||||||
],
|
|
||||||
"ธ.ค.": [
|
|
||||||
{ORTH: "ธ.ค.", LEMMA: "ธันวาคม"}
|
|
||||||
]
|
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
||||||
|
TOKENIZER_EXCEPTIONS = _exc
|
||||||
|
|
Loading…
Reference in New Issue
Block a user