mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-27 10:26:35 +03:00
446a3ecf34
* `strings`: Remove unused `hash32_utf8` function
* `strings`: Make `hash_utf8` and `decode_Utf8Str` private
* `strings`: Reorganize private functions
* 'strings': Raise error when non-string/-int types are passed to functions that don't accept them
* `strings`: Add `items()` method, add type hints, remove unused methods, restrict inputs to specific types, reorganize methods
* `Morphology`: Use `StringStore.items()` to enumerate features when pickling
* `test_stringstore`: Update pre-Python 3 tests
* Update `StringStore` docs
* Fix `get_string_id` imports
* Replace redundant test with tests for type checking
* Rename `_retrieve_interned_str`, remove `.get` default arg
* Add `get_string_id` to `strings.pyi`
Remove `mypy` ignore directives from imports of the above
* `strings.pyi`: Replace functions that consume `Union`-typed params with overloads
* `strings.pyi`: Revert some function signatures
* Update `SYMBOLS_BY_INT` lookups and error codes post-merge
* Revert clobbered change introduced in a previous merge
* Remove unnecessary type hint
* Invert tuple order in `StringStore.items()`
* Add test for `StringStore.items()`
* Revert "`Morphology`: Use `StringStore.items()` to enumerate features when pickling"
This reverts commit 1af9510ceb.
* Rename `keys` and `key_map`
* Add `keys()` and `values()`
* Add comment about the inverted key-value semantics in the API
* Fix type hints
* Implement `keys()`, `values()`, `items()` without generators
* Fix type hints, remove unnecessary boxing
* Update docs
* Simplify `keys/values/items()` impl
* `mypy` fix
* Fix error message, doc fixes
27 lines
726 B
Cython
27 lines
726 B
Cython
from libc.stdint cimport int64_t, uint32_t
|
|
from libcpp.vector cimport vector
|
|
from libcpp.set cimport set
|
|
from cymem.cymem cimport Pool
|
|
from preshed.maps cimport PreshMap
|
|
from murmurhash.mrmr cimport hash64
|
|
|
|
from .typedefs cimport attr_t, hash_t
|
|
|
|
ctypedef union Utf8Str:
|
|
unsigned char[8] s
|
|
unsigned char* p
|
|
|
|
|
|
cdef class StringStore:
|
|
cdef Pool mem
|
|
cdef vector[hash_t] _keys
|
|
cdef PreshMap _map
|
|
|
|
cdef hash_t _intern_str(self, str string)
|
|
cdef Utf8Str* _allocate_str_repr(self, const unsigned char* chars, uint32_t length) except *
|
|
cdef str _decode_str_repr(self, const Utf8Str* string)
|
|
|
|
|
|
cpdef hash_t hash_string(object string) except -1
|
|
cpdef hash_t get_string_id(object string_or_hash) except -1
|