Rooba
/
spaCy
mirror of https://github.com/explosion/spaCy.git
1
1
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Reorganise Spanish language data

This commit is contained in:
ines 2017-05-08 15:48:04 +02:00
parent c7c21b980f
commit 8e483ec950
4 changed files with 71 additions and 97 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
spacy/es/__init__.py
View File

@ -1,14 +1,17 @@
# coding: utf8
from __future__ import unicode_literals, print_function
from __future__ import unicode_literals
from os import path
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
from .tag_map import TAG_MAP
from .stop_words import STOP_WORDS
from .lemmatizer import LOOKUP
from ..language_data import BASE_EXCEPTIONS
from ..language import Language
from ..attrs import LANG
from .language_data import *
from ..lemmatizerlookup import Lemmatizer
from .lemmatization import LOOK_UP
from ..attrs import LANG
from ..util import update_exc
class Spanish(Language):
lang = 'es'
@ -17,10 +20,13 @@ class Spanish(Language):
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
lex_attr_getters[LANG] = lambda text: 'es'
tokenizer_exceptions = TOKENIZER_EXCEPTIONS
tag_map = TAG_MAP
stop_words = STOP_WORDS
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
tag_map = dict(TAG_MAP)
stop_words = set(STOP_WORDS)
@classmethod
def create_lemmatizer(cls, nlp=None):
return Lemmatizer(LOOKUP)
EXPORT = Spanish
__all__ = ['Spanish']

5
spacy/es/lemmatization.py → spacy/es/lemmatizer.py
View File

@ -1,7 +1,8 @@
# coding: utf8
from __future__ import unicode_literals
LOOK_UP = {
LOOKUP = {
"aba": "abar",
"ababa": "abar",
"ababais": "abar",
@ -491549,4 +491550,4 @@ LOOK_UP = {
"útiles": "útil",
"úveas": "úvea",
"úvulas": "úvula"
}
}

2
spacy/es/tag_map.py
View File

@ -1,8 +1,6 @@
# coding: utf8
from __future__ import unicode_literals
from ..symbols import *
TAG_MAP = {
"ADJ___": {"morph": "_", "pos": "ADJ"},

133
spacy/es/tokenizer_exceptions.py
View File

@ -1,113 +1,82 @@
# coding: utf8
from __future__ import unicode_literals
from ..symbols import *
from ..language_data import PRON_LEMMA, DET_LEMMA
from ..symbols import ORTH, LEMMA, TAG, NORM, ADP, DET
from ..deprecated import PRON_LEMMA, DET_LEMMA
TOKENIZER_EXCEPTIONS = {
_exc = {
"al": [
{ORTH: "a", LEMMA: "a", TAG: ADP},
{ORTH: "el", LEMMA: "el", TAG: DET}
],
{ORTH: "l", LEMMA: "el", TAG: DET}],
"consigo": [
{ORTH: "con", LEMMA: "con"},
{ORTH: "sigo", LEMMA: PRON_LEMMA, NORM: "sí"}
],
{ORTH: "sigo", LEMMA: PRON_LEMMA, NORM: "sí"}],
"conmigo": [
{ORTH: "con", LEMMA: "con"},
{ORTH: "migo", LEMMA: PRON_LEMMA, NORM: "mí"}
],
{ORTH: "migo", LEMMA: PRON_LEMMA, NORM: "mí"}],
"contigo": [
{ORTH: "con", LEMMA: "con"},
{ORTH: "tigo", LEMMA: PRON_LEMMA, NORM: "ti"}
],
{ORTH: "tigo", LEMMA: PRON_LEMMA, NORM: "ti"}],
"del": [
{ORTH: "de", LEMMA: "de", TAG: ADP},
{ORTH: "l", LEMMA: "el", TAG: DET}
],
{ORTH: "l", LEMMA: "el", TAG: DET}],
"pel": [
{ORTH: "pe", LEMMA: "per", TAG: ADP},
{ORTH: "l", LEMMA: "el", TAG: DET}
],
{ORTH: "l", LEMMA: "el", TAG: DET}],
"pal": [
{ORTH: "pa", LEMMA: "para"},
{ORTH: "l", LEMMA: DET_LEMMA, NORM: "el"}
],
{ORTH: "l", LEMMA: DET_LEMMA, NORM: "el"}],
"pala": [
{ORTH: "pa", LEMMA: "para"},
{ORTH: "la", LEMMA: DET_LEMMA}
],
"aprox.": [
{ORTH: "aprox.", LEMMA: "aproximadamente"}
],
"dna.": [
{ORTH: "dna.", LEMMA: "docena"}
],
"esq.": [
{ORTH: "esq.", LEMMA: "esquina"}
],
"pág.": [
{ORTH: "pág.", LEMMA: "página"}
],
"p.ej.": [
{ORTH: "p.ej.", LEMMA: "por ejemplo"}
],
"Ud.": [
{ORTH: "Ud.", LEMMA: PRON_LEMMA, NORM: "usted"}
],
"Vd.": [
{ORTH: "Vd.", LEMMA: PRON_LEMMA, NORM: "usted"}
],
"Uds.": [
{ORTH: "Uds.", LEMMA: PRON_LEMMA, NORM: "ustedes"}
],
"Vds.": [
{ORTH: "Vds.", LEMMA: PRON_LEMMA, NORM: "ustedes"}
]
{ORTH: "la", LEMMA: DET_LEMMA}]
}
ORTH_ONLY = [
"a.C.",
"a.J.C.",
"apdo.",
"Av.",
"Avda.",
"Cía.",
"etc.",
"Gob.",
"Gral.",
"Ing.",
"J.C.",
"Lic.",
"m.n.",
"no.",
"núm.",
"P.D.",
"Prof.",
"Profa.",
"q.e.p.d."
"S.A.",
"S.L.",
"s.s.s.",
"Sr.",
"Sra.",
"Srta."
]
for exc_data in [
{ORTH: "aprox.", LEMMA: "aproximadamente"},
{ORTH: "dna.", LEMMA: "docena"},
{ORTH: "esq.", LEMMA: "esquina"},
{ORTH: "pág.", LEMMA: "página"},
{ORTH: "p.ej.", LEMMA: "por ejemplo"},
{ORTH: "Ud.", LEMMA: PRON_LEMMA, NORM: "usted"},
{ORTH: "Vd.", LEMMA: PRON_LEMMA, NORM: "usted"},
{ORTH: "Uds.", LEMMA: PRON_LEMMA, NORM: "ustedes"},
{ORTH: "Vds.", LEMMA: PRON_LEMMA, NORM: "ustedes"}]:
_exc[exc_data[ORTH]] = [dict(exc_data)]
# Times
_exc["12m."] = [
{ORTH: "12"},
{ORTH: "m.", LEMMA: "p.m."}]
for h in range(1, 12 + 1):
hour = str(h)
for period in ["a.m.", "am"]:
_exc[hour+period] = [
{ORTH: hour},
{ORTH: period, LEMMA: "a.m."}]
for period in ["p.m.", "pm"]:
_exc[hour+period] = [
{ORTH: hour},
{ORTH: period, LEMMA: "p.m."}]
for orth in [
"a.C.", "a.J.C.", "apdo.", "Av.", "Avda.", "Cía.", "etc.", "Gob.", "Gral.",
"Ing.", "J.C.", "Lic.", "m.n.", "no.", "núm.", "P.D.", "Prof.", "Profa.",
"q.e.p.d.", "S.A.", "S.L.", "s.s.s.", "Sr.", "Sra.", "Srta."]:
_exc[orth] = [{ORTH: orth}]
TOKENIZER_EXCEPTIONS = dict(_exc)