explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-01-13 10:46:29 +03:00
Code Issues Packages Projects Releases Wiki Activity

* Fix pickle problems

Browse Source
This commit is contained in:
Matthew Honnibal 2015-12-28 16:54:03 +01:00
parent 8c7e149ec9
commit 187960606f
2 changed files with 15 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
spacy/en/__init__.py
View File

@ -33,9 +33,7 @@ your yours yourself yourselves
STOPWORDS = set(w for w in STOPWORDS.split() if w) STOPWORDS = set(w for w in STOPWORDS.split() if w)
class English(Language): class English(Language):
def __init__(self, **kwargs): lang = 'en'
kwargs['lang'] = 'en'
super(English, self).__init__(**kwargs)
@staticmethod @staticmethod
def is_stop(string): def is_stop(string):

20
spacy/language.py
View File

@ -24,6 +24,8 @@ from .util import get_package
class Language(object): class Language(object):
lang = None
@staticmethod @staticmethod
def lower(string): def lower(string):
return string.lower() return string.lower()
@ -156,7 +158,6 @@ class Language(object):
def __init__(self, def __init__(self,
data_dir=None, data_dir=None,
lang=None,
model=None, model=None,
vocab=None, vocab=None,
tokenizer=None, tokenizer=None,
@ -209,26 +210,33 @@ class Language(object):
warn("load_vectors is deprecated", DeprecationWarning) warn("load_vectors is deprecated", DeprecationWarning)
if vocab in (None, True): if vocab in (None, True):
self.vocab = self.default_vocab(package) self.vocab = self.default_vocab(package)
self.vocab = vocab
if tokenizer in (None, True): if tokenizer in (None, True):
self.tokenizer = Tokenizer.from_package(package, self.vocab) self.tokenizer = Tokenizer.from_package(package, self.vocab)
self.tokenizer = tokenizer
if tagger in (None, True): if tagger in (None, True):
self.tagger = Tagger.from_package(package, self.vocab) tagger = Tagger.from_package(package, self.vocab)
self.tagger = tagger
if entity in (None, True): if entity in (None, True):
self.entity = self.default_entity(package, self.vocab) entity = self.default_entity(package, self.vocab)
self.entity = entity
if parser in (None, True): if parser in (None, True):
self.parser = self.default_parser(package, self.vocab) parser = self.default_parser(package, self.vocab)
self.parser = parser
if matcher in (None, True): if matcher in (None, True):
self.matcher = Matcher.from_package(package, self.vocab) matcher = Matcher.from_package(package, self.vocab)
self.matcher = matcher
def __reduce__(self): def __reduce__(self):
args = ( args = (
None, # data_dir None, # data_dir
None, # model
self.vocab, self.vocab,
self.tokenizer, self.tokenizer,
self.tagger, self.tagger,
self.parser, self.parser,
self.entity, self.entity,
self.matcher, self.matcher
) )
return (self.__class__, args, None, None) return (self.__class__, args, None, None)