mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-14 13:47:13 +03:00
a5cd203284
* Reduce stored lexemes data, move feats to lookups
* Move non-derivable lexemes features (`norm / cluster / prob`) to
`spacy-lookups-data` as lookups
* Get/set `norm` in both lookups and `LexemeC`, serialize in lookups
* Remove `cluster` and `prob` from `LexemesC`, get/set/serialize in
lookups only
* Remove serialization of lexemes data as `vocab/lexemes.bin`
* Remove `SerializedLexemeC`
* Remove `Lexeme.to_bytes/from_bytes`
* Modify normalization exception loading:
* Always create `Vocab.lookups` table `lexeme_norm` for
normalization exceptions
* Load base exceptions from `lang.norm_exceptions`, but load
language-specific exceptions from lookups
* Set `lex_attr_getter[NORM]` including new lookups table in
`BaseDefaults.create_vocab()` and when deserializing `Vocab`
* Remove all cached lexemes when deserializing vocab to override
existing normalizations with the new normalizations (as a replacement
for the previous step that replaced all lexemes data with the
deserialized data)
* Skip English normalization test
Skip English normalization test because the data is now in
`spacy-lookups-data`.
* Remove norm exceptions
Moved to spacy-lookups-data.
* Move norm exceptions test to spacy-lookups-data
* Load extra lookups from spacy-lookups-data lazily
Load extra lookups (currently for cluster and prob) lazily from the
entry point `lg_extra` as `Vocab.lookups_extra`.
* Skip creating lexeme cache on load
To improve model loading times, do not create the full lexeme cache when
loading. The lexemes will be created on demand when processing.
* Identify numeric values in Lexeme.set_attrs()
With the removal of a special case for `PROB`, also identify `float` to
avoid trying to convert it with the `StringStore`.
* Skip lexeme cache init in from_bytes
* Unskip and update lookups tests for python3.6+
* Update vocab pickle to include lookups_extra
* Update vocab serialization tests
Check strings rather than lexemes since lexemes aren't initialized
automatically, account for addition of "_SP".
* Re-skip lookups test because of python3.5
* Skip PROB/float values in Lexeme.set_attrs
* Convert is_oov from lexeme flag to lex in vectors
Instead of storing `is_oov` as a lexeme flag, `is_oov` reports whether
the lexeme has a vector.
Co-authored-by: Matthew Honnibal <honnibal+gh@gmail.com>
48 lines
1.3 KiB
Cython
48 lines
1.3 KiB
Cython
from libcpp.vector cimport vector
|
|
|
|
from preshed.maps cimport PreshMap
|
|
from cymem.cymem cimport Pool
|
|
from murmurhash.mrmr cimport hash64
|
|
|
|
from .structs cimport LexemeC, TokenC
|
|
from .typedefs cimport utf8_t, attr_t, hash_t
|
|
from .strings cimport StringStore
|
|
from .morphology cimport Morphology
|
|
|
|
|
|
cdef LexemeC EMPTY_LEXEME
|
|
|
|
|
|
cdef union LexemesOrTokens:
|
|
const LexemeC* const* lexemes
|
|
const TokenC* tokens
|
|
|
|
|
|
cdef struct _Cached:
|
|
LexemesOrTokens data
|
|
bint is_lex
|
|
int length
|
|
|
|
|
|
cdef class Vocab:
|
|
cdef Pool mem
|
|
cpdef readonly StringStore strings
|
|
cpdef public Morphology morphology
|
|
cpdef public object vectors
|
|
cpdef public object lookups
|
|
cpdef public object lookups_extra
|
|
cdef readonly int length
|
|
cdef public object data_dir
|
|
cdef public object lex_attr_getters
|
|
cdef public object cfg
|
|
|
|
cdef const LexemeC* get(self, Pool mem, unicode string) except NULL
|
|
cdef const LexemeC* get_by_orth(self, Pool mem, attr_t orth) except NULL
|
|
cdef const TokenC* make_fused_token(self, substrings) except NULL
|
|
|
|
cdef const LexemeC* _new_lexeme(self, Pool mem, unicode string) except NULL
|
|
cdef int _add_lex_to_vocab(self, hash_t key, const LexemeC* lex) except -1
|
|
cdef const LexemeC* _new_lexeme(self, Pool mem, unicode string) except NULL
|
|
|
|
cdef PreshMap _by_orth
|