explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-06-01 03:33:12 +03:00
Code Issues Packages Projects Releases Wiki Activity

Make Doc's slicing behavior conform to Python conventions

Browse Source
This commit is contained in:
Yubing (Tom) Dong 2015-10-06 01:59:11 -07:00
parent 2fc33e8024
commit ef2af20cd3
2 changed files with 43 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
spacy/tokens/spans.pyx
View File

@ -16,9 +16,13 @@ cdef class Span:
def __cinit__(self, Doc tokens, int start, int end, int label=0, vector=None, def __cinit__(self, Doc tokens, int start, int end, int label=0, vector=None,
vector_norm=None): vector_norm=None):
if start < 0: if start < 0:
start = tokens.length - start start = tokens.length + start
start = min(tokens.length, max(0, start))
if end < 0: if end < 0:
end = tokens.length - end end = tokens.length + end
end = min(tokens.length, max(start, end))
self.doc = tokens self.doc = tokens
self.start = start self.start = start
self.end = end self.end = end

40
tests/tokens/test_tokens_api.py
View File

@ -12,17 +12,51 @@ def test_getitem(EN):
with pytest.raises(IndexError): with pytest.raises(IndexError):
tokens[len(tokens)] tokens[len(tokens)]
def to_str(span):
return '/'.join(token.orth_ for token in span)
span = tokens[1:1] span = tokens[1:1]
assert not '/'.join(token.orth_ for token in span) assert not to_str(span)
span = tokens[1:4] span = tokens[1:4]
assert '/'.join(token.orth_ for token in span) == 'it/back/!' assert to_str(span) == 'it/back/!'
span = tokens[1:4:1] span = tokens[1:4:1]
assert '/'.join(token.orth_ for token in span) == 'it/back/!' assert to_str(span) == 'it/back/!'
with pytest.raises(ValueError): with pytest.raises(ValueError):
tokens[1:4:2] tokens[1:4:2]
with pytest.raises(ValueError): with pytest.raises(ValueError):
tokens[1:4:-1] tokens[1:4:-1]
span = tokens[-3:6]
assert to_str(span) == 'He/pleaded'
span = tokens[4:-1]
assert to_str(span) == 'He/pleaded'
span = tokens[-5:-3]
assert to_str(span) == 'back/!'
span = tokens[5:4]
assert span.start == span.end == 5 and not to_str(span)
span = tokens[4:-3]
assert span.start == span.end == 4 and not to_str(span)
span = tokens[:]
assert to_str(span) == 'Give/it/back/!/He/pleaded/.'
span = tokens[4:]
assert to_str(span) == 'He/pleaded/.'
span = tokens[:4]
assert to_str(span) == 'Give/it/back/!'
span = tokens[:-3]
assert to_str(span) == 'Give/it/back/!'
span = tokens[-3:]
assert to_str(span) == 'He/pleaded/.'
span = tokens[4:50]
assert to_str(span) == 'He/pleaded/.'
span = tokens[-50:4]
assert to_str(span) == 'Give/it/back/!'
span = tokens[-50:-40]
assert span.start == span.end == 0 and not to_str(span)
span = tokens[40:50]
assert span.start == span.end == 7 and not to_str(span)
@pytest.mark.models @pytest.mark.models
def test_serialize(EN): def test_serialize(EN):