def get_box(span: SpanMention) -> Tuple[int, int, int, int, int]:
box = (
min(span.get_attrib_tokens("page")),
min(span.get_attrib_tokens("top")),
min(span.get_attrib_tokens("left")),
max(span.get_attrib_tokens("bottom")),
max(span.get_attrib_tokens("right")),
)
return box
def get_box(span: SpanMention) -> Bbox:
"""Get the bounding box."""
warnings.warn(
"get_box(span) is deprecated. Use span.get_bbox() instead.",
DeprecationWarning,
)
return Bbox(
min(span.get_attrib_tokens("page")),
min(span.get_attrib_tokens("top")),
max(span.get_attrib_tokens("bottom")),
min(span.get_attrib_tokens("left")),
max(span.get_attrib_tokens("right")),
)
def _get_word_feats(span: SpanMention) -> Iterator[str]:
attrib = "words"
if span.stable_id not in unary_word_feats:
unary_word_feats[span.stable_id] = set()
for ngram in tokens_to_ngrams(span.get_attrib_tokens(attrib),
n_min=1,
n_max=2):
feature = f"CONTAINS_{attrib.upper()}_[{ngram}]"
unary_word_feats[span.stable_id].add(feature)
for ngram in get_left_ngrams(
span,
window=settings["featurization"]["textual"]["word_feature"]
["window"],
n_max=2,
attrib=attrib,
):
feature = f"LEFT_{attrib.upper()}_[{ngram}]"
unary_word_feats[span.stable_id].add(feature)
for ngram in get_right_ngrams(
span,
window=settings["featurization"]["textual"]["word_feature"]
["window"],
n_max=2,
attrib=attrib,
):
feature = f"RIGHT_{attrib.upper()}_[{ngram}]"
unary_word_feats[span.stable_id].add(feature)
unary_word_feats[span.stable_id].add((
f"SPAN_TYPE_["
f"{'IMPLICIT' if isinstance(span, ImplicitSpanMention) else 'EXPLICIT'}"
f"]"))
if span.get_span()[0].isupper():
unary_word_feats[span.stable_id].add("STARTS_WITH_CAPITAL")
unary_word_feats[span.stable_id].add(f"LENGTH_{span.get_num_words()}")
for f in unary_word_feats[span.stable_id]:
yield f