explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-10-31 07:57:35 +03:00
Code Issues Packages Projects Releases Wiki Activity

* Rename external hashing lib, from trustyc to preshed

Browse Source
This commit is contained in:
Matthew Honnibal 2014-09-26 18:40:03 +02:00
parent 11a346fd5e
commit 096ef2b199
3 changed files with 10 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
requirements.txt
View File

@ -1,6 +1,8 @@
cython
fabric
cymem
preshed
murmurhash
pytest
sphinx
sphinxcontrib-napoleon

8
spacy/lang.pxd
View File

@ -3,7 +3,7 @@ from libc.stdint cimport uint64_t
from spacy.word cimport Lexeme
from spacy.tokens cimport Tokens
from spacy.lexeme cimport LexemeC
from trustyc.maps cimport PointerMap
from preshed.maps cimport PreshMap
from cymem.cymem cimport Pool
@ -30,7 +30,7 @@ cdef class Lexicon:
cpdef Lexeme lookup(self, unicode string)
cdef LexemeC* get(self, String* s) except NULL
cdef PointerMap _dict
cdef PreshMap _dict
cdef list _string_features
cdef list _flag_features
@ -39,8 +39,8 @@ cdef class Lexicon:
cdef class Language:
cdef Pool _mem
cdef unicode name
cdef PointerMap cache
cdef PointerMap specials
cdef PreshMap cache
cdef PreshMap specials
cpdef readonly Lexicon lexicon
cdef object prefix_re

8
spacy/lang.pyx
View File

@ -26,7 +26,7 @@ from cython.operator cimport preincrement as preinc
from cython.operator cimport dereference as deref
from trustyc.maps cimport PointerMap
from preshed.maps cimport PreshMap
from spacy import orth
from spacy import util
@ -130,8 +130,8 @@ cdef class Language:
def __cinit__(self, name, user_string_features, user_flag_features):
self.name = name
self._mem = Pool()
self.cache = PointerMap(2 ** 25)
self.specials = PointerMap(2 ** 16)
self.cache = PreshMap(2 ** 25)
self.specials = PreshMap(2 ** 16)
lang_data = util.read_lang_data(name)
rules, prefix, suffix, words, probs, clusters, case_stats, tag_stats = lang_data
self.prefix_re = re.compile(prefix)
@ -352,7 +352,7 @@ cdef class Lexicon:
self._mem = Pool()
self._flag_features = flag_features
self._string_features = string_features
self._dict = PointerMap(2 ** 20)
self._dict = PreshMap(2 ** 20)
self.size = 0
cdef String string
for uni_string in words: