2014-12-19 23:29:16 +03:00
|
|
|
from libcpp.vector cimport vector
|
|
|
|
|
|
|
|
|
|
from preshed.maps cimport PreshMap
|
|
|
|
|
from cymem.cymem cimport Pool
|
|
|
|
|
|
|
|
|
|
from .typedefs cimport hash_t
|
2015-08-26 20:20:11 +03:00
|
|
|
from .structs cimport LexemeC, TokenC
|
2014-12-19 23:29:16 +03:00
|
|
|
from .strings cimport StringStore
|
2015-07-13 21:20:58 +03:00
|
|
|
from .tokens.doc cimport Doc
|
2015-08-28 03:02:33 +03:00
|
|
|
from .vocab cimport Vocab, LexemesOrTokens, _Cached
|
2014-12-19 23:29:16 +03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
cdef class Tokenizer:
|
|
|
|
|
cdef Pool mem
|
|
|
|
|
cdef PreshMap _cache
|
|
|
|
|
cdef PreshMap _specials
|
|
|
|
|
cpdef readonly Vocab vocab
|
|
|
|
|
|
2019-09-08 21:52:46 +03:00
|
|
|
cdef object _token_match
|
2020-05-22 13:41:03 +03:00
|
|
|
cdef object _url_match
|
2019-09-08 21:52:46 +03:00
|
|
|
cdef object _prefix_search
|
|
|
|
|
cdef object _suffix_search
|
|
|
|
|
cdef object _infix_finditer
|
2015-10-24 08:18:47 +03:00
|
|
|
cdef object _rules
|
2014-12-19 23:29:16 +03:00
|
|
|
|
2015-07-08 19:53:00 +03:00
|
|
|
cpdef Doc tokens_from_list(self, list strings)
|
2014-12-19 23:29:16 +03:00
|
|
|
|
2015-07-13 22:46:02 +03:00
|
|
|
cdef int _try_cache(self, hash_t key, Doc tokens) except -1
|
2015-07-22 05:49:39 +03:00
|
|
|
cdef int _tokenize(self, Doc tokens, unicode span, hash_t key) except -1
|
2016-02-22 02:17:47 +03:00
|
|
|
cdef unicode _split_affixes(self, Pool mem, unicode string, vector[LexemeC*] *prefixes,
|
2017-10-24 17:07:44 +03:00
|
|
|
vector[LexemeC*] *suffixes, int* has_special)
|
2015-07-22 05:49:39 +03:00
|
|
|
cdef int _attach_tokens(self, Doc tokens, unicode string,
|
2015-01-12 02:26:22 +03:00
|
|
|
vector[LexemeC*] *prefixes, vector[LexemeC*] *suffixes) except -1
|
2015-07-22 05:49:39 +03:00
|
|
|
|
2017-10-24 17:07:44 +03:00
|
|
|
cdef int _save_cached(self, const TokenC* tokens, hash_t key, int has_special,
|
|
|
|
|
int n) except -1
|
