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

Add words and spaces keyword arguments to Doc.

This commit is contained in:
Matthew Honnibal 2016-10-16 18:13:03 +02:00
parent 2508117553
commit 06322ba99d
1 changed files with 5 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
spacy/tokens/doc.pyx
View File

@ -75,7 +75,7 @@ cdef class Doc:
doc = Doc(nlp.vocab, orths_and_spaces=[(u'Some', True), (u'text', True)]) doc = Doc(nlp.vocab, orths_and_spaces=[(u'Some', True), (u'text', True)])
""" """
def __init__(self, Vocab vocab, orths_and_spaces=None): def __init__(self, Vocab vocab, words=None, spaces=None, orths_and_spaces=None):
''' '''
Create a Doc object. Create a Doc object.
@ -117,6 +117,10 @@ cdef class Doc:
self.noun_chunks_iterator = CHUNKERS.get(self.vocab.lang) self.noun_chunks_iterator = CHUNKERS.get(self.vocab.lang)
cdef unicode orth cdef unicode orth
cdef bint has_space cdef bint has_space
if orths_and_spaces is None and words is not None:
if spaces is None:
spaces = [True] * len(words)
orths_and_spaces = zip(words, spaces)
if orths_and_spaces is not None: if orths_and_spaces is not None:
for orth_space in orths_and_spaces: for orth_space in orths_and_spaces:
if isinstance(orth_space, unicode): if isinstance(orth_space, unicode):