explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-07-22 22:20:08 +03:00
Code Issues Packages Projects Releases Wiki Activity

Find span sentence when only sentence boundaries (no parser)

Browse Source
This commit is contained in:
Thomas Opsomer 2018-02-14 22:18:54 +01:00
parent c2b0910db4
commit b902731313
1 changed files with 25 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

33
spacy/tokens/span.pyx
View File

@ -285,16 +285,33 @@ cdef class Span:
def __get__(self): def __get__(self):
if 'sent' in self.doc.user_span_hooks: if 'sent' in self.doc.user_span_hooks:
return self.doc.user_span_hooks['sent'](self) return self.doc.user_span_hooks['sent'](self)
# This should raise if we're not parsed. # This should raise if we're not parsed
# or doesen't have any sbd component :)
self.doc.sents self.doc.sents
# if doc is parsed we can use the deps to find the sentence
# otherwise we use the `sent_start` token attribute
cdef int n = 0 cdef int n = 0
root = &self.doc.c[self.start] if self.doc.is_parsed:
while root.head != 0: root = &self.doc.c[self.start]
root += root.head while root.head != 0:
n += 1 root += root.head
if n >= self.doc.length: n += 1
raise RuntimeError if n >= self.doc.length:
return self.doc[root.l_edge:root.r_edge + 1] raise RuntimeError
return self.doc[root.l_edge:root.r_edge + 1]
else:
# find start of the sentence
start = self.start
while not self.doc.c[start].sent_start and start > 0:
start += -1
# find end of the sentence
end = self.end
while not self.doc.c[end].sent_start:
end += 1
if n >= self.doc.length:
break
#
return self.doc[start:end]
property has_vector: property has_vector:
"""RETURNS (bool): Whether a word vector is associated with the object. """RETURNS (bool): Whether a word vector is associated with the object.