mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-11 12:18:04 +03:00
43 lines
1.2 KiB
Cython
43 lines
1.2 KiB
Cython
from libcpp.vector cimport vector
|
|
from libc.stdint cimport uint32_t
|
|
from libc.stdint cimport uint64_t
|
|
|
|
from sparsehash.dense_hash_map cimport dense_hash_map
|
|
|
|
# Circular import problems here
|
|
ctypedef size_t Lexeme_addr
|
|
ctypedef uint32_t StringHash
|
|
ctypedef dense_hash_map[StringHash, size_t] Vocab
|
|
from spacy.lexeme cimport Lexeme
|
|
|
|
from spacy.tokens cimport Tokens
|
|
|
|
# Put these above import to avoid circular import problem
|
|
ctypedef char Bits8
|
|
ctypedef uint64_t Bits64
|
|
ctypedef int ClusterID
|
|
|
|
|
|
from spacy.lexeme cimport Lexeme
|
|
|
|
|
|
cdef class Language:
|
|
cdef object name
|
|
cdef dense_hash_map[StringHash, size_t] chunks
|
|
cdef dense_hash_map[StringHash, size_t] vocab
|
|
cdef dict bacov
|
|
|
|
cpdef Tokens tokenize(self, unicode text)
|
|
|
|
cdef Lexeme* lookup(self, unicode string) except NULL
|
|
cdef Lexeme** lookup_chunk(self, unicode chunk) except NULL
|
|
|
|
cdef Lexeme** new_chunk(self, unicode string, list substrings) except NULL
|
|
cdef Lexeme* new_lexeme(self, unicode lex) except NULL
|
|
|
|
cpdef unicode unhash(self, StringHash hashed)
|
|
|
|
cpdef list find_substrings(self, unicode chunk)
|
|
cdef int find_split(self, unicode word)
|
|
cdef int set_orth(self, unicode string, Lexeme* word)
|