explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-09-23 12:36:46 +03:00
Code Issues Packages Projects Releases Wiki Activity

correct check on sent_start & raise if no boundaries

Browse Source
This commit is contained in:
Thomas Opsomer 2018-02-15 16:58:30 +01:00
parent b902731313
commit deab391cbf
1 changed files with 14 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
spacy/tokens/span.pyx
View File

@ -291,6 +291,7 @@ cdef class Span:
# if doc is parsed we can use the deps to find the sentence # if doc is parsed we can use the deps to find the sentence
# otherwise we use the `sent_start` token attribute # otherwise we use the `sent_start` token attribute
cdef int n = 0 cdef int n = 0
cdef int i
if self.doc.is_parsed: if self.doc.is_parsed:
root = &self.doc.c[self.start] root = &self.doc.c[self.start]
while root.head != 0: while root.head != 0:
@ -300,19 +301,30 @@ cdef class Span:
raise RuntimeError raise RuntimeError
return self.doc[root.l_edge:root.r_edge + 1] return self.doc[root.l_edge:root.r_edge + 1]
else: else:
# Check if the document has sentence boundaries,
# i.e at least one tok has the sent_start == 1
for i in range(self.doc.length):
if self.doc.c[i].sent_start == 1:
break
else:
raise ValueError(
"Access to sentence requires either the dependency parse "
"or sentence boundaries to be set by setting " +
"doc[i].is_sent_start = True")
# find start of the sentence # find start of the sentence
start = self.start start = self.start
while not self.doc.c[start].sent_start and start > 0: while self.doc.c[start].sent_start != 1 and start > 0:
start += -1 start += -1
# find end of the sentence # find end of the sentence
end = self.end end = self.end
while not self.doc.c[end].sent_start: while self.doc.c[end].sent_start != 1:
end += 1 end += 1
if n >= self.doc.length: if n >= self.doc.length:
break break
# #
return self.doc[start:end] 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.
""" """