mirror of
https://github.com/explosion/spaCy.git
synced 2025-07-13 09:42:26 +03:00
5bebbf7550
In order to support Python 3.13, we had to migrate to Cython 3.0. This caused some tricky interaction with our Pydantic usage, because Cython 3 uses the from __future__ import annotations semantics, which causes type annotations to be saved as strings. The end result is that we can't have Language.factory decorated functions in Cython modules anymore, as the Language.factory decorator expects to inspect the signature of the functions and build a Pydantic model. If the function is implemented in Cython, an error is raised because the type is not resolved. To address this I've moved the factory functions into a new module, spacy.pipeline.factories. I've added __getattr__ importlib hooks to the previous locations, in case anyone was importing these functions directly. The change should have no backwards compatibility implications. Along the way I've also refactored the registration of functions for the config. Previously these ran as import-time side-effects, using the registry decorator. I've created instead a new module spacy.registrations. When the registry is accessed it calls a function ensure_populated(), which cases the registrations to occur. I've made a similar change to the Language.factory registrations in the new spacy.pipeline.factories module. I want to remove these import-time side-effects so that we can speed up the loading time of the library, which can be especially painful on the CLI. I also find that I'm often working to track down the implementations of functions referenced by strings in the config. Having the registrations all happen in one place will make this easier. With these changes I've fortunately avoided the need to migrate to Pydantic v2 properly --- we're still using the v1 compatibility shim. We might not be able to hold out forever though: Pydantic (reasonably) aren't actively supporting the v1 shims. I put a lot of work into v2 migration when investigating the 3.13 support, and it's definitely challenging. In any case, it's a relief that we don't have to do the v2 migration at the same time as the Cython 3.0/Python 3.13 support.
99 lines
2.6 KiB
Cython
99 lines
2.6 KiB
Cython
from numpy cimport ndarray
|
|
|
|
from .attrs cimport (
|
|
ID,
|
|
LANG,
|
|
LENGTH,
|
|
LOWER,
|
|
NORM,
|
|
ORTH,
|
|
PREFIX,
|
|
SHAPE,
|
|
SUFFIX,
|
|
attr_id_t,
|
|
)
|
|
from .strings cimport StringStore
|
|
from .structs cimport LexemeC
|
|
from .typedefs cimport attr_t, flags_t, hash_t, len_t, tag_t
|
|
from .vocab cimport Vocab
|
|
|
|
|
|
cdef LexemeC EMPTY_LEXEME
|
|
cdef attr_t OOV_RANK
|
|
|
|
cdef class Lexeme:
|
|
cdef LexemeC* c
|
|
cdef readonly Vocab vocab
|
|
cdef readonly attr_t orth
|
|
|
|
@staticmethod
|
|
cdef inline Lexeme from_ptr(LexemeC* lex, Vocab vocab):
|
|
cdef Lexeme self = Lexeme.__new__(Lexeme, vocab, lex.orth)
|
|
self.c = lex
|
|
self.vocab = vocab
|
|
self.orth = lex.orth
|
|
return self
|
|
|
|
@staticmethod
|
|
cdef inline void set_struct_attr(LexemeC* lex, attr_id_t name, attr_t value) noexcept nogil:
|
|
if name < (sizeof(flags_t) * 8):
|
|
Lexeme.c_set_flag(lex, name, value)
|
|
elif name == ID:
|
|
lex.id = value
|
|
elif name == LOWER:
|
|
lex.lower = value
|
|
elif name == NORM:
|
|
lex.norm = value
|
|
elif name == SHAPE:
|
|
lex.shape = value
|
|
elif name == PREFIX:
|
|
lex.prefix = value
|
|
elif name == SUFFIX:
|
|
lex.suffix = value
|
|
elif name == LANG:
|
|
lex.lang = value
|
|
|
|
@staticmethod
|
|
cdef inline attr_t get_struct_attr(const LexemeC* lex, attr_id_t feat_name) noexcept nogil:
|
|
if feat_name < (sizeof(flags_t) * 8):
|
|
if Lexeme.c_check_flag(lex, feat_name):
|
|
return 1
|
|
else:
|
|
return 0
|
|
elif feat_name == ID:
|
|
return lex.id
|
|
elif feat_name == ORTH:
|
|
return lex.orth
|
|
elif feat_name == LOWER:
|
|
return lex.lower
|
|
elif feat_name == NORM:
|
|
return lex.norm
|
|
elif feat_name == SHAPE:
|
|
return lex.shape
|
|
elif feat_name == PREFIX:
|
|
return lex.prefix
|
|
elif feat_name == SUFFIX:
|
|
return lex.suffix
|
|
elif feat_name == LENGTH:
|
|
return lex.length
|
|
elif feat_name == LANG:
|
|
return lex.lang
|
|
else:
|
|
return 0
|
|
|
|
@staticmethod
|
|
cdef inline bint c_check_flag(const LexemeC* lexeme, attr_id_t flag_id) noexcept nogil:
|
|
cdef flags_t one = 1
|
|
if lexeme.flags & (one << flag_id):
|
|
return True
|
|
else:
|
|
return False
|
|
|
|
@staticmethod
|
|
cdef inline bint c_set_flag(LexemeC* lex, attr_id_t flag_id, bint value) noexcept nogil:
|
|
cdef flags_t one = 1
|
|
if value:
|
|
lex.flags |= one << flag_id
|
|
else:
|
|
lex.flags &= ~(one << flag_id)
|