explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-01-26 17:24:41 +03:00
Code Issues Packages Projects Releases Wiki Activity

* Add Python hooks for is_bracket/is_quote/is_left_punct/is_right_punct

Browse Source
This commit is contained in:
Matthew Honnibal 2016-02-04 13:04:16 +01:00
parent fe611132f0
commit 11810be33e
2 changed files with 31 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
spacy/lexeme.pyx
View File

@ -18,6 +18,7 @@ import numpy
from .attrs cimport IS_ALPHA, IS_ASCII, IS_DIGIT, IS_LOWER, IS_PUNCT, IS_SPACE
from .attrs cimport IS_TITLE, IS_UPPER, LIKE_URL, LIKE_NUM, LIKE_EMAIL, IS_STOP
from .attrs cimport IS_BRACKET, IS_QUOTE, IS_LEFT_PUNCT, IS_RIGHT_PUNCT
from .attrs cimport IS_OOV
@ -183,6 +184,23 @@ cdef class Lexeme:
def __get__(self): return Lexeme.c_check_flag(self.c, IS_SPACE)
def __set__(self, bint x): Lexeme.c_set_flag(self.c, IS_SPACE, x)
property is_bracket:
def __get__(self): return Lexeme.c_check_flag(self.c, IS_BRACKET)
def __set__(self, bint x): Lexeme.c_set_flag(self.c, IS_BRACKET, x)
property is_quote:
def __get__(self): return Lexeme.c_check_flag(self.c, IS_QUOTE)
def __set__(self, bint x): Lexeme.c_set_flag(self.c, IS_QUOTE, x)
property is_left_punct:
def __get__(self): return Lexeme.c_check_flag(self.c, IS_LEFT_PUNCT)
def __set__(self, bint x): Lexeme.c_set_flag(self.c, IS_LEFT_PUNCT, x)
property is_right_punct:
def __get__(self): return Lexeme.c_check_flag(self.c, IS_RIGHT_PUNCT)
def __set__(self, bint x): Lexeme.c_set_flag(self.c, IS_RIGHT_PUNCT, x)
property like_url:
def __get__(self): return Lexeme.c_check_flag(self.c, LIKE_URL)
def __set__(self, bint x): Lexeme.c_set_flag(self.c, LIKE_URL, x)

13
spacy/tokens/token.pyx
View File

@ -18,6 +18,7 @@ from ..attrs cimport POS, LEMMA, TAG, DEP
from ..parts_of_speech cimport CONJ, PUNCT
from ..attrs cimport IS_ALPHA, IS_ASCII, IS_DIGIT, IS_LOWER, IS_PUNCT, IS_SPACE
from ..attrs cimport IS_BRACKET, IS_QUOTE, IS_LEFT_PUNCT, IS_RIGHT_PUNCT
from ..attrs cimport IS_TITLE, IS_UPPER, LIKE_URL, LIKE_NUM, LIKE_EMAIL, IS_STOP
from ..attrs cimport IS_OOV
@ -362,6 +363,18 @@ cdef class Token:
property is_space:
def __get__(self): return Lexeme.c_check_flag(self.c.lex, IS_SPACE)
property is_bracket:
def __get__(self): return Lexeme.c_check_flag(self.c.lex, IS_BRACKET)
property is_quote:
def __get__(self): return Lexeme.c_check_flag(self.c.lex, IS_QUOTE)
property is_left_punct:
def __get__(self): return Lexeme.c_check_flag(self.c.lex, IS_LEFT_PUNCT)
property is_right_punct:
def __get__(self): return Lexeme.c_check_flag(self.c.lex, IS_RIGHT_PUNCT)
property like_url:
def __get__(self): return Lexeme.c_check_flag(self.c.lex, LIKE_URL)