explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-25 17:36:30 +03:00
Code Issues Packages Projects Releases Wiki Activity

Remove two attributes marked for removal in 3.1 (#9150)

Browse Source 
* Remove two attributes marked for removal in 3.1

* Add back unused ints with changed names

* Change data_dir to _unused_object

This is still kept in the type definition, but I removed it from the
serialization code.

* Put serialization code back for now

Not sure how this interacts with old serialized models yet.
This commit is contained in:
Paul O'Leary McCann 2021-09-16 06:07:21 +09:00 committed by GitHub
parent 0f01f46e02
commit cd75f96501
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
4 changed files with 10 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
spacy/tokenizer.pxd
View File

@ -23,8 +23,10 @@ cdef class Tokenizer:
cdef object _infix_finditer cdef object _infix_finditer
cdef object _rules cdef object _rules
cdef PhraseMatcher _special_matcher cdef PhraseMatcher _special_matcher
cdef int _property_init_count # TODO: unused, remove in v3.1 # TODO next two are unused and should be removed in v4
cdef int _property_init_max # TODO: unused, remove in v3.1 # https://github.com/explosion/spaCy/pull/9150
cdef int _unused_int1
cdef int _unused_int2
cdef Doc _tokenize_affixes(self, str string, bint with_special_cases) cdef Doc _tokenize_affixes(self, str string, bint with_special_cases)
cdef int _apply_special_cases(self, Doc doc) except -1 cdef int _apply_special_cases(self, Doc doc) except -1

2
spacy/vocab.pxd
View File

@ -32,7 +32,7 @@ cdef class Vocab:
cdef public object writing_system cdef public object writing_system
cdef public object get_noun_chunks cdef public object get_noun_chunks
cdef readonly int length cdef readonly int length
cdef public object data_dir cdef public object _unused_object # TODO remove in v4, see #9150
cdef public object lex_attr_getters cdef public object lex_attr_getters
cdef public object cfg cdef public object cfg

2
spacy/vocab.pyi
View File

@ -71,7 +71,7 @@ def unpickle_vocab(
sstore: StringStore, sstore: StringStore,
vectors: Any, vectors: Any,
morphology: Any, morphology: Any,
data_dir: Any, _unused_object: Any,
lex_attr_getters: Any, lex_attr_getters: Any,
lookups: Any, lookups: Any,
get_noun_chunks: Any, get_noun_chunks: Any,

8
spacy/vocab.pyx
View File

@ -552,21 +552,21 @@ def pickle_vocab(vocab):
sstore = vocab.strings sstore = vocab.strings
vectors = vocab.vectors vectors = vocab.vectors
morph = vocab.morphology morph = vocab.morphology
data_dir = vocab.data_dir _unused_object = vocab._unused_object
lex_attr_getters = srsly.pickle_dumps(vocab.lex_attr_getters) lex_attr_getters = srsly.pickle_dumps(vocab.lex_attr_getters)
lookups = vocab.lookups lookups = vocab.lookups
get_noun_chunks = vocab.get_noun_chunks get_noun_chunks = vocab.get_noun_chunks
return (unpickle_vocab, return (unpickle_vocab,
(sstore, vectors, morph, data_dir, lex_attr_getters, lookups, get_noun_chunks)) (sstore, vectors, morph, _unused_object, lex_attr_getters, lookups, get_noun_chunks))
def unpickle_vocab(sstore, vectors, morphology, data_dir, def unpickle_vocab(sstore, vectors, morphology, _unused_object,
lex_attr_getters, lookups, get_noun_chunks): lex_attr_getters, lookups, get_noun_chunks):
cdef Vocab vocab = Vocab() cdef Vocab vocab = Vocab()
vocab.vectors = vectors vocab.vectors = vectors
vocab.strings = sstore vocab.strings = sstore
vocab.morphology = morphology vocab.morphology = morphology
vocab.data_dir = data_dir vocab._unused_object = _unused_object
vocab.lex_attr_getters = srsly.pickle_loads(lex_attr_getters) vocab.lex_attr_getters = srsly.pickle_loads(lex_attr_getters)
vocab.lookups = lookups vocab.lookups = lookups
vocab.get_noun_chunks = get_noun_chunks vocab.get_noun_chunks = get_noun_chunks