explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-01-26 09:14:32 +03:00
Code Issues Packages Projects Releases Wiki Activity

* Link in tagger, to work on integrating POS tagging

Browse Source
This commit is contained in:
Matthew Honnibal 2014-12-07 15:29:41 +11:00
parent 0c7aeb9de7
commit 5caabec789
2 changed files with 4 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
spacy/lang.pxd
View File

@ -8,6 +8,7 @@ from cymem.cymem cimport Pool
from .typedefs cimport hash_t
from .tokens cimport Tokens, TokenC
from .lexeme cimport Lexeme
from .tagger cimport Tagger
from .utf8string cimport StringStore, UniStr
@ -29,6 +30,7 @@ cdef class Language:
cdef PreshMap _cache
cdef PreshMap _specials
cpdef readonly Lexicon lexicon
cpdef readonly Tagger pos_tagger
cdef object _prefix_re
cdef object _suffix_re

2
spacy/lang.pyx
View File

@ -39,10 +39,12 @@ cdef class Language:
self._infix_re = re.compile(infix)
self.lexicon = Lexicon(self.set_flags)
self._load_special_tokenization(rules)
self.pos_tagger = None
def load(self):
self.lexicon.load(path.join(util.DATA_DIR, self.name, 'lexemes'))
self.lexicon.strings.load(path.join(util.DATA_DIR, self.name, 'strings'))
self.pos_tagger = Tagger(path.join(util.DATA_DIR, self.name, 'pos'))
cpdef Tokens tokens_from_list(self, list strings):
cdef int length = sum([len(s) for s in strings])