def test_get_doc_char_span(vocab, tokens, i, j, destructive, covering,
expected, label):
doc = Doc(vocab, tokens)
span = get_doc_char_span(doc,
i,
j,
destructive=destructive,
covering=covering,
label=label or "")
assert span.text == expected
if label is not None:
assert span.label_ == label
def __call__(self, doc: Doc) -> Doc:
matches = self.get_char_spans(doc.text)
spans = []
for i, j, text in matches:
span = get_doc_char_span(doc,
i,
j,
destructive=self.destructive,
label=self.get_label(text))
if span:
spans.append(span)
[s.text for s in spans
] # TODO: resolve the evaluation bug and remove this line
ents = filter_spans(doc.ents + tuple(spans))
doc.ents = tuple(ents)
return doc
def __call__(self, doc: Doc) -> Doc:
text = self._to_text(doc)
_matches = list(self.get_char_spans(text))
matches = _modify_spans(_matches, text, doc.text)
spans = []
for i, j, text in matches:
if i is None or j is None:
continue
span = get_doc_char_span(
doc,
i,
j,
destructive=self.destructive,
covering=not self.destructive,
label=self.get_label(text),
)
if span and self._to_text(span) == text:
spans.append(span)
[s.text for s in spans
] # TODO: resolve the evaluation bug and remove this line
ents = filter_spans(doc.ents + tuple(spans))
doc.ents = tuple(ents)
return doc
def test_get_doc_char_span(vocab, tokens, i, j, expected):
doc = Doc(vocab, tokens)
span = get_doc_char_span(doc, i, j)
assert span.text == expected