explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-24 17:06:29 +03:00
Code Issues Packages Projects Releases Wiki Activity

Fix Issue #599, by considering empty documents to be parsed and tagged. Implementation is a bit dodgy.

Browse Source
This commit is contained in:
Matthew Honnibal 2016-11-02 23:47:46 +01:00
parent b6b01d4680
commit f292f7f0e6
1 changed files with 9 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
spacy/tokens/doc.pyx
View File

@ -151,6 +151,11 @@ cdef class Doc:
# must be created. # must be created.
self.push_back( self.push_back(
<const LexemeC*>self.vocab.get(self.mem, orth), has_space) <const LexemeC*>self.vocab.get(self.mem, orth), has_space)
# Tough to decide on policy for this. Is an empty doc tagged and parsed?
# There's no information we'd like to add to it, so I guess so?
if self.length == 0:
self.is_tagged = True
self.is_parsed = True
def __getitem__(self, object i): def __getitem__(self, object i):
''' '''
@ -430,6 +435,10 @@ cdef class Doc:
yield Span(self, start, self.length) yield Span(self, start, self.length)
cdef int push_back(self, LexemeOrToken lex_or_tok, bint has_space) except -1: cdef int push_back(self, LexemeOrToken lex_or_tok, bint has_space) except -1:
if self.length == 0:
# Flip these to false when we see the first token.
self.is_tagged = False
self.is_parsed = False
if self.length == self.max_length: if self.length == self.max_length:
self._realloc(self.length * 2) self._realloc(self.length * 2)
cdef TokenC* t = &self.c[self.length] cdef TokenC* t = &self.c[self.length]