explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-02-04 13:40:34 +03:00
Code Issues Packages Projects Releases Wiki Activity

Move shared functions and constants to global language data

Browse Source
This commit is contained in:
Ines Montani 2016-12-17 12:32:48 +01:00
parent 6a60a61086
commit 08162dce67
12 changed files with 12 additions and 48 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
spacy/de/__init__.py
View File

@ -8,9 +8,9 @@ from ..attrs import LANG
from . import language_data from . import language_data
from ..language_data import update_exc from ..language_data import update_exc
from ..language_data import strings_to_exc
from ..language_data import EMOTICONS from ..language_data import EMOTICONS
from .language_data import ORTH_ONLY from .language_data import ORTH_ONLY
from .language_data import strings_to_exc
TOKENIZER_EXCEPTIONS = dict(language_data.TOKENIZER_EXCEPTIONS) TOKENIZER_EXCEPTIONS = dict(language_data.TOKENIZER_EXCEPTIONS)

8
spacy/de/language_data.py
View File

@ -2,18 +2,12 @@
from __future__ import unicode_literals from __future__ import unicode_literals
from ..symbols import * from ..symbols import *
from ..language_data import PRON_LEMMA
from ..language_data import TOKENIZER_PREFIXES from ..language_data import TOKENIZER_PREFIXES
from ..language_data import TOKENIZER_SUFFIXES from ..language_data import TOKENIZER_SUFFIXES
from ..language_data import TOKENIZER_INFIXES from ..language_data import TOKENIZER_INFIXES
def strings_to_exc(orths):
return {orth: [{ORTH: orth}] for orth in orths}
PRON_LEMMA = "-PRON-"
TAG_MAP = { TAG_MAP = {
"$(": {TAG: PUNCT, "PunctType": "brck"}, "$(": {TAG: PUNCT, "PunctType": "brck"},
"$,": {TAG: PUNCT, "PunctType": "comm"}, "$,": {TAG: PUNCT, "PunctType": "comm"},

2
spacy/en/__init__.py
View File

@ -12,9 +12,9 @@ from ..tokenizer import Tokenizer
from ..attrs import LANG from ..attrs import LANG
from ..language_data import update_exc from ..language_data import update_exc
from ..language_data import strings_to_exc
from ..language_data import EMOTICONS from ..language_data import EMOTICONS
from .language_data import ORTH_ONLY from .language_data import ORTH_ONLY
from .language_data import strings_to_exc
from .language_data import get_time_exc from .language_data import get_time_exc

8
spacy/en/language_data.py
View File

@ -2,15 +2,12 @@
from __future__ import unicode_literals from __future__ import unicode_literals
from ..symbols import * from ..symbols import *
from ..language_data import PRON_LEMMA
from ..language_data import TOKENIZER_PREFIXES from ..language_data import TOKENIZER_PREFIXES
from ..language_data import TOKENIZER_SUFFIXES from ..language_data import TOKENIZER_SUFFIXES
from ..language_data import TOKENIZER_INFIXES from ..language_data import TOKENIZER_INFIXES
def strings_to_exc(orths):
return {orth: [{ORTH: orth}] for orth in orths}
def get_time_exc(hours): def get_time_exc(hours):
exc = {} exc = {}
for hour in hours: for hour in hours:
@ -36,9 +33,6 @@ def get_time_exc(hours):
return exc return exc
PRON_LEMMA = "-PRON-"
TAG_MAP = { TAG_MAP = {
".": {POS: PUNCT, "PunctType": "peri"}, ".": {POS: PUNCT, "PunctType": "peri"},
",": {POS: PUNCT, "PunctType": "comm"}, ",": {POS: PUNCT, "PunctType": "comm"},

2
spacy/es/__init__.py
View File

@ -8,9 +8,9 @@ from . import language_data
from ..attrs import LANG from ..attrs import LANG
from ..language_data import update_exc from ..language_data import update_exc
from ..language_data import strings_to_exc
from ..language_data import EMOTICONS from ..language_data import EMOTICONS
from .language_data import ORTH_ONLY from .language_data import ORTH_ONLY
from .language_data import strings_to_exc
TOKENIZER_EXCEPTIONS = dict(language_data.TOKENIZER_EXCEPTIONS) TOKENIZER_EXCEPTIONS = dict(language_data.TOKENIZER_EXCEPTIONS)

8
spacy/es/language_data.py
View File

@ -2,18 +2,12 @@
from __future__ import unicode_literals from __future__ import unicode_literals
from ..symbols import * from ..symbols import *
from ..language_data import PRON_LEMMA
from ..language_data import TOKENIZER_PREFIXES from ..language_data import TOKENIZER_PREFIXES
from ..language_data import TOKENIZER_SUFFIXES from ..language_data import TOKENIZER_SUFFIXES
from ..language_data import TOKENIZER_INFIXES from ..language_data import TOKENIZER_INFIXES
def strings_to_exc(orths):
return {orth: [{ORTH: orth}] for orth in orths}
PRON_LEMMA = "-PRON-"
TAG_MAP = { TAG_MAP = {
} }

2
spacy/fr/__init__.py
View File

@ -8,9 +8,9 @@ from . import language_data
from ..attrs import LANG from ..attrs import LANG
from ..language_data import update_exc from ..language_data import update_exc
from ..language_data import strings_to_exc
from ..language_data import EMOTICONS from ..language_data import EMOTICONS
from .language_data import ORTH_ONLY from .language_data import ORTH_ONLY
from .language_data import strings_to_exc
TOKENIZER_EXCEPTIONS = dict(language_data.TOKENIZER_EXCEPTIONS) TOKENIZER_EXCEPTIONS = dict(language_data.TOKENIZER_EXCEPTIONS)

8
spacy/fr/language_data.py
View File

@ -2,18 +2,12 @@
from __future__ import unicode_literals from __future__ import unicode_literals
from ..symbols import * from ..symbols import *
from ..language_data import PRON_LEMMA
from ..language_data import TOKENIZER_PREFIXES from ..language_data import TOKENIZER_PREFIXES
from ..language_data import TOKENIZER_SUFFIXES from ..language_data import TOKENIZER_SUFFIXES
from ..language_data import TOKENIZER_INFIXES from ..language_data import TOKENIZER_INFIXES
def strings_to_exc(orths):
return {orth: [{ORTH: orth}] for orth in orths}
PRON_LEMMA = "-PRON-"
TAG_MAP = { TAG_MAP = {
} }

2
spacy/it/__init__.py
View File

@ -8,9 +8,9 @@ from . import language_data
from ..attrs import LANG from ..attrs import LANG
from ..language_data import update_exc from ..language_data import update_exc
from ..language_data import strings_to_exc
from ..language_data import EMOTICONS from ..language_data import EMOTICONS
from .language_data import ORTH_ONLY from .language_data import ORTH_ONLY
from .language_data import strings_to_exc
TOKENIZER_EXCEPTIONS = dict(language_data.TOKENIZER_EXCEPTIONS) TOKENIZER_EXCEPTIONS = dict(language_data.TOKENIZER_EXCEPTIONS)

8
spacy/it/language_data.py
View File

@ -2,18 +2,12 @@
from __future__ import unicode_literals from __future__ import unicode_literals
from ..symbols import * from ..symbols import *
from ..language_data import PRON_LEMMA
from ..language_data import TOKENIZER_PREFIXES from ..language_data import TOKENIZER_PREFIXES
from ..language_data import TOKENIZER_SUFFIXES from ..language_data import TOKENIZER_SUFFIXES
from ..language_data import TOKENIZER_INFIXES from ..language_data import TOKENIZER_INFIXES
def strings_to_exc(orths):
return {orth: [{ORTH: orth}] for orth in orths}
PRON_LEMMA = "-PRON-"
TAG_MAP = { TAG_MAP = {
} }

2
spacy/pt/__init__.py
View File

@ -8,9 +8,9 @@ from . import language_data
from ..attrs import LANG from ..attrs import LANG
from ..language_data import update_exc from ..language_data import update_exc
from ..language_data import strings_to_exc
from ..language_data import EMOTICONS from ..language_data import EMOTICONS
from .language_data import ORTH_ONLY from .language_data import ORTH_ONLY
from .language_data import strings_to_exc
TOKENIZER_EXCEPTIONS = dict(language_data.TOKENIZER_EXCEPTIONS) TOKENIZER_EXCEPTIONS = dict(language_data.TOKENIZER_EXCEPTIONS)

8
spacy/pt/language_data.py
View File

@ -2,18 +2,12 @@
from __future__ import unicode_literals from __future__ import unicode_literals
from ..symbols import * from ..symbols import *
from ..language_data import PRON_LEMMA
from ..language_data import TOKENIZER_PREFIXES from ..language_data import TOKENIZER_PREFIXES
from ..language_data import TOKENIZER_SUFFIXES from ..language_data import TOKENIZER_SUFFIXES
from ..language_data import TOKENIZER_INFIXES from ..language_data import TOKENIZER_INFIXES
def strings_to_exc(orths):
return {orth: [{ORTH: orth}] for orth in orths}
PRON_LEMMA = "-PRON-"
TAG_MAP = { TAG_MAP = {
} }