explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-24 17:06:29 +03:00
Code Issues Packages Projects Releases Wiki Activity

Move Defaults subclass to module scope (necessary for pickling)

Browse Source
This commit is contained in:
ines 2017-05-20 19:02:27 +02:00
parent 27de0834b2
commit 924e8506de
16 changed files with 187 additions and 158 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
spacy/lang/bn/__init__.py
View File

@ -13,21 +13,23 @@ from ...attrs import LANG
from ...util import update_exc
class BengaliDefaults(Language.Defaults):
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
lex_attr_getters[LANG] = lambda text: 'bn'
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
tag_map = TAG_MAP
stop_words = STOP_WORDS
lemma_rules = LEMMA_RULES
prefixes = tuple(TOKENIZER_PREFIXES)
suffixes = tuple(TOKENIZER_SUFFIXES)
infixes = tuple(TOKENIZER_INFIXES)
class Bengali(Language):
lang = 'bn'
class Defaults(Language.Defaults):
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
lex_attr_getters[LANG] = lambda text: 'bn'
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
tag_map = TAG_MAP
stop_words = STOP_WORDS
lemma_rules = LEMMA_RULES
prefixes = tuple(TOKENIZER_PREFIXES)
suffixes = tuple(TOKENIZER_SUFFIXES)
infixes = tuple(TOKENIZER_INFIXES)
Defaults = BengaliDefaults
__all__ = ['Bengali']

16
spacy/lang/da/__init__.py
View File

@ -10,15 +10,17 @@ from ...attrs import LANG
from ...util import update_exc
class DanishDefaults(Language.Defaults):
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
lex_attr_getters[LANG] = lambda text: 'da'
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
stop_words = set(STOP_WORDS)
class Danish(Language):
lang = 'da'
class Defaults(Language.Defaults):
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
lex_attr_getters[LANG] = lambda text: 'da'
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
stop_words = set(STOP_WORDS)
Defaults = DanishDefaults
__all__ = ['Danish']

28
spacy/lang/de/__init__.py
View File

@ -14,21 +14,23 @@ from ...attrs import LANG
from ...util import update_exc
class GermanDefaults(Language.Defaults):
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
lex_attr_getters[LANG] = lambda text: 'de'
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
tag_map = dict(TAG_MAP)
stop_words = set(STOP_WORDS)
syntax_iterators = dict(SYNTAX_ITERATORS)
@classmethod
def create_lemmatizer(cls, nlp=None):
return Lemmatizer(LOOKUP)
class German(Language):
lang = 'de'
class Defaults(Language.Defaults):
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
lex_attr_getters[LANG] = lambda text: 'de'
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
tag_map = dict(TAG_MAP)
stop_words = set(STOP_WORDS)
syntax_iterators = dict(SYNTAX_ITERATORS)
@classmethod
def create_lemmatizer(cls, nlp=None):
return Lemmatizer(LOOKUP)
Defaults = GermanDefaults
__all__ = ['German']

30
spacy/lang/en/__init__.py
View File

@ -15,22 +15,24 @@ from ...attrs import LANG
from ...util import update_exc
class EnglishDefaults(Language.Defaults):
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
lex_attr_getters[LANG] = lambda text: 'en'
lex_attr_getters.update(LEX_ATTRS)
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
tag_map = dict(TAG_MAP)
stop_words = set(STOP_WORDS)
morph_rules = dict(MORPH_RULES)
lemma_rules = dict(LEMMA_RULES)
lemma_index = dict(LEMMA_INDEX)
lemma_exc = dict(LEMMA_EXC)
sytax_iterators = dict(SYNTAX_ITERATORS)
class English(Language):
lang = 'en'
class Defaults(Language.Defaults):
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
lex_attr_getters[LANG] = lambda text: 'en'
lex_attr_getters.update(LEX_ATTRS)
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
tag_map = dict(TAG_MAP)
stop_words = set(STOP_WORDS)
morph_rules = dict(MORPH_RULES)
lemma_rules = dict(LEMMA_RULES)
lemma_index = dict(LEMMA_INDEX)
lemma_exc = dict(LEMMA_EXC)
sytax_iterators = dict(SYNTAX_ITERATORS)
Defaults = EnglishDefaults
__all__ = ['English']

2
spacy/lang/es/__init__.py
View File

@ -28,7 +28,7 @@ class SpanishDefaults(Language.Defaults):
class Spanish(Language):
lang = 'es'
Defaults = SpanishDefaults
__all__ = ['Spanish']

16
spacy/lang/fi/__init__.py
View File

@ -10,15 +10,17 @@ from ...attrs import LANG
from ...util import update_exc
class FinnishDefaults(Language.Defaults):
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
lex_attr_getters[LANG] = lambda text: 'fi'
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
stop_words = set(STOP_WORDS)
class Finnish(Language):
lang = 'fi'
class Defaults(Language.Defaults):
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
lex_attr_getters[LANG] = lambda text: 'fi'
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
stop_words = set(STOP_WORDS)
Defaults = FinnishDefaults
__all__ = ['Finnish']

30
spacy/lang/fr/__init__.py
View File

@ -13,22 +13,24 @@ from ...attrs import LANG
from ...util import update_exc
class FrenchDefaults(Language.Defaults):
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
lex_attr_getters[LANG] = lambda text: 'fr'
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
stop_words = set(STOP_WORDS)
infixes = tuple(TOKENIZER_INFIXES)
suffixes = tuple(TOKENIZER_SUFFIXES)
token_match = TOKEN_MATCH
@classmethod
def create_lemmatizer(cls, nlp=None):
return Lemmatizer(LOOKUP)
class French(Language):
lang = 'fr'
class Defaults(Language.Defaults):
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
lex_attr_getters[LANG] = lambda text: 'fr'
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
stop_words = set(STOP_WORDS)
infixes = tuple(TOKENIZER_INFIXES)
suffixes = tuple(TOKENIZER_SUFFIXES)
token_match = TOKEN_MATCH
@classmethod
def create_lemmatizer(cls, nlp=None):
return Lemmatizer(LOOKUP)
Defaults = FrenchDefaults
__all__ = ['French']

16
spacy/lang/he/__init__.py
View File

@ -9,15 +9,17 @@ from ...attrs import LANG
from ...util import update_exc
class HebrewDefaults(Language.Defaults):
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
lex_attr_getters[LANG] = lambda text: 'he'
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS)
stop_words = set(STOP_WORDS)
class Hebrew(Language):
lang = 'he'
class Defaults(Language.Defaults):
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
lex_attr_getters[LANG] = lambda text: 'he'
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS)
stop_words = set(STOP_WORDS)
Defaults = HebrewDefaults
__all__ = ['Hebrew']

32
spacy/lang/hu/__init__.py
View File

@ -13,23 +13,25 @@ from ...attrs import LANG
from ...util import update_exc
class HungarianDefaults(Language.Defaults):
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
lex_attr_getters[LANG] = lambda text: 'hu'
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
stop_words = set(STOP_WORDS)
prefixes = tuple(TOKENIZER_PREFIXES)
suffixes = tuple(TOKENIZER_SUFFIXES)
infixes = tuple(TOKENIZER_INFIXES)
token_match = TOKEN_MATCH
@classmethod
def create_lemmatizer(cls, nlp=None):
return Lemmatizer(LOOKUP)
class Hungarian(Language):
lang = 'hu'
class Defaults(Language.Defaults):
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
lex_attr_getters[LANG] = lambda text: 'hu'
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
stop_words = set(STOP_WORDS)
prefixes = tuple(TOKENIZER_PREFIXES)
suffixes = tuple(TOKENIZER_SUFFIXES)
infixes = tuple(TOKENIZER_INFIXES)
token_match = TOKEN_MATCH
@classmethod
def create_lemmatizer(cls, nlp=None):
return Lemmatizer(LOOKUP)
Defaults = HungarianDefaults
__all__ = ['Hungarian']

24
spacy/lang/it/__init__.py
View File

@ -11,19 +11,21 @@ from ...attrs import LANG
from ...util import update_exc
class ItalianDefaults(Language.Defaults):
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
lex_attr_getters[LANG] = lambda text: 'it'
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS)
stop_words = set(STOP_WORDS)
@classmethod
def create_lemmatizer(cls, nlp=None):
return Lemmatizer(LOOKUP)
class Italian(Language):
lang = 'it'
class Defaults(Language.Defaults):
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
lex_attr_getters[LANG] = lambda text: 'it'
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS)
stop_words = set(STOP_WORDS)
@classmethod
def create_lemmatizer(cls, nlp=None):
return Lemmatizer(LOOKUP)
Defaults = ItalianDefaults
__all__ = ['Italian']

16
spacy/lang/nb/__init__.py
View File

@ -11,15 +11,17 @@ from ...attrs import LANG
from ...util import update_exc
class NorwegianDefaults(Language.Defaults):
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
lex_attr_getters[LANG] = lambda text: 'nb'
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
stop_words = set(STOP_WORDS)
class Norwegian(Language):
lang = 'nb'
class Defaults(Language.Defaults):
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
lex_attr_getters[LANG] = lambda text: 'nb'
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
stop_words = set(STOP_WORDS)
Defaults = NorwegianDefaults
__all__ = ['Norwegian']

15
spacy/lang/nl/__init__.py
View File

@ -9,16 +9,17 @@ from ...attrs import LANG
from ...util import update_exc
class DutchDefaults(Language.Defaults):
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
lex_attr_getters[LANG] = lambda text: 'nl'
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS)
stop_words = set(STOP_WORDS)
class Dutch(Language):
lang = 'nl'
class Defaults(Language.Defaults):
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
lex_attr_getters[LANG] = lambda text: 'nl'
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS)
stop_words = set(STOP_WORDS)
Defaults = DutchDefaults
__all__ = ['Dutch']

16
spacy/lang/pl/__init__.py
View File

@ -9,15 +9,17 @@ from ...attrs import LANG
from ...util import update_exc
class PolishDefaults(Language.Defaults):
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
lex_attr_getters[LANG] = lambda text: 'pl'
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS)
stop_words = set(STOP_WORDS)
class Polish(Language):
lang = 'pl'
class Defaults(Language.Defaults):
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
lex_attr_getters[LANG] = lambda text: 'pl'
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS)
stop_words = set(STOP_WORDS)
Defaults = PolishDefaults
__all__ = ['Polish']

26
spacy/lang/pt/__init__.py
View File

@ -13,20 +13,22 @@ from ...attrs import LANG
from ...util import update_exc
class PortugueseDefaults(Language.Defaults):
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
lex_attr_getters[LANG] = lambda text: 'pt'
lex_attr_getters.update(LEX_ATTRS)
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
stop_words = set(STOP_WORDS)
@classmethod
def create_lemmatizer(cls, nlp=None):
return Lemmatizer(LOOKUP)
class Portuguese(Language):
lang = 'pt'
class Defaults(Language.Defaults):
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
lex_attr_getters[LANG] = lambda text: 'pt'
lex_attr_getters.update(LEX_ATTRS)
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
stop_words = set(STOP_WORDS)
@classmethod
def create_lemmatizer(cls, nlp=None):
return Lemmatizer(LOOKUP)
Defaults = PortugueseDefaults
__all__ = ['Portuguese']

24
spacy/lang/sv/__init__.py
View File

@ -13,19 +13,21 @@ from ...attrs import LANG
from ...util import update_exc
class SwedishDefaults(Language.Defaults):
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
lex_attr_getters[LANG] = lambda text: 'sv'
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
stop_words = set(STOP_WORDS)
@classmethod
def create_lemmatizer(cls, nlp=None):
return Lemmatizer(LOOKUP)
class Swedish(Language):
lang = 'sv'
class Defaults(Language.Defaults):
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
lex_attr_getters[LANG] = lambda text: 'sv'
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
stop_words = set(STOP_WORDS)
@classmethod
def create_lemmatizer(cls, nlp=None):
return Lemmatizer(LOOKUP)
Defaults = SwedishDefaults
__all__ = ['Swedish']

26
website/docs/usage/adding-languages.jade
View File

@ -56,20 +56,22 @@ p
from ...attrs import LANG
from ...util import update_exc
# create Defaults class in the module scope (necessary for pickling!)
class XxxxxDefaults(Language.Defaults):
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
lex_attr_getters[LANG] = lambda text: 'xx' # language ISO code
# optional: replace flags with custom functions, e.g. like_num()
lex_attr_getters.update(LEX_ATTRS)
# merge base exceptions and custom tokenizer exceptions
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
stop_words = set(STOP_WORDS)
# create actual Language class
class Xxxxx(Language):
lang = 'xx' # language ISO code
# override defaults
class Defaults(Language.Defaults):
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
lex_attr_getters[LANG] = lambda text: 'xx' # language ISO code
# optional: replace flags with custom functions, e.g. like_num()
lex_attr_getters.update(LEX_ATTRS)
# merge base exceptions and custom tokenizer exceptions
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
stop_words = set(STOP_WORDS)
Defaults = XxxxxDefaults # override defaults
# set default export – this allows the language class to be lazy-loaded
__all__ = ['Xxxxx']