Rooba
/
spaCy
mirror of https://github.com/explosion/spaCy.git
1
1
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Defer some attributes to Doc, via getters_for_tokens attribute.

This commit is contained in:
Matthew Honnibal 2016-10-17 02:44:49 +02:00
parent 8829984efb
commit 5d10e2005c
1 changed files with 14 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
spacy/tokens/token.pyx
View File

@ -94,6 +94,8 @@ cdef class Token:
return self.doc[self.i+i] return self.doc[self.i+i]
def similarity(self, other): def similarity(self, other):
if 'similarity' in self.doc.getters_for_tokens:
return self.doc.getters_for_tokens['similarity'](self, other)
if self.vector_norm == 0 or other.vector_norm == 0: if self.vector_norm == 0 or other.vector_norm == 0:
return 0.0 return 0.0
return numpy.dot(self.vector, other.vector) / (self.vector_norm * other.vector_norm) return numpy.dot(self.vector, other.vector) / (self.vector_norm * other.vector_norm)
@ -182,6 +184,8 @@ cdef class Token:
property has_vector: property has_vector:
def __get__(self): def __get__(self):
if 'has_vector' in self.doc.getters_for_tokens:
return self.doc.getters_for_tokens['has_vector'](self)
cdef int i cdef int i
for i in range(self.vocab.vectors_length): for i in range(self.vocab.vectors_length):
if self.c.lex.vector[i] != 0: if self.c.lex.vector[i] != 0:
@ -191,6 +195,8 @@ cdef class Token:
property vector: property vector:
def __get__(self): def __get__(self):
if 'vector' in self.doc.getters_for_tokens:
return self.doc.getters_for_tokens['vector'](self)
cdef int length = self.vocab.vectors_length cdef int length = self.vocab.vectors_length
if length == 0: if length == 0:
raise ValueError( raise ValueError(
@ -387,11 +393,14 @@ cdef class Token:
def __get__(self): def __get__(self):
"""Get a list of conjoined words.""" """Get a list of conjoined words."""
cdef Token word cdef Token word
if self.dep_ != 'conj': if 'conjuncts' in self.doc.getters_for_tokens:
for word in self.rights: yield from self.doc.getters_for_tokens['conjuncts'](self)
if word.dep_ == 'conj': else:
yield word if self.dep_ != 'conj':
yield from word.conjuncts for word in self.rights:
if word.dep_ == 'conj':
yield word
yield from word.conjuncts
property ent_type: property ent_type:
def __get__(self): def __get__(self):