explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-01-12 02:06:31 +03:00
Code Issues Packages Projects Releases Wiki Activity

Add input error handling in Doc

Browse Source
This commit is contained in:
Matthew Honnibal 2016-10-16 18:16:42 +02:00
parent 4e9727b474
commit 311a985fe0
1 changed files with 6 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
spacy/tokens/doc.pyx
View File

@ -120,6 +120,12 @@ cdef class Doc:
if orths_and_spaces is None and words is not None: if orths_and_spaces is None and words is not None:
if spaces is None: if spaces is None:
spaces = [True] * len(words) spaces = [True] * len(words)
elif len(spaces) != len(words):
raise ValueError(
"Arguments 'words' and 'spaces' should be sequences of the "
"same length, or 'spaces' should be left default at None. "
"spaces should be a sequence of booleans, with True meaning "
"that the word owns a ' ' character following it.")
orths_and_spaces = zip(words, spaces) 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: