def legal_generator(doc):
legal_spans = []
for span in utils.get_spans(doc, ["proper2_detector", "nnp_detector"]):
if not utils.is_likely_proper(doc[span.end - 1]):
continue
last_token = doc[span.end - 1].text.title().rstrip("s")
if last_token in LEGAL:
legal_spans.append((span.start, span.end, "LAW"))
# Handling legal references such as Article 5
for i in range(len(doc) - 1):
if doc[i].text.rstrip("s") in {
"Article", "Paragraph", "Section", "Chapter", "§"
}:
if doc[i + 1].text[0].isdigit() or doc[i +
1].text in ROMAN_NUMERALS:
start, end = i, i + 2
if (i < len(doc) - 3 and doc[i + 2].text in {"-", "to", "and"}
and (doc[i + 3].text[0].isdigit()
or doc[i + 3].text in ROMAN_NUMERALS)):
end = i + 4
legal_spans.append((start, end, "LAW"))
# Merge contiguous spans of legal references ("Article 5, Paragraph 3")
legal_spans = utils.merge_contiguous_spans(legal_spans, doc)
for start, end, label in legal_spans:
yield start, end, label
def date_generator(doc):
"""Searches for occurrences of date patterns in text"""
spans = []
i = 0
while i < len(doc):
tok = doc[i]
if tok.lemma_ in DAYS | DAYS_ABBRV:
spans.append((i, i + 1, "DATE"))
elif tok.is_digit and re.match(
"\\d+$", tok.text) and 1920 < int(tok.text) < 2040:
spans.append((i, i + 1, "DATE"))
elif tok.lemma_ in MONTHS | MONTHS_ABBRV:
if tok.tag_ == "MD": # Skipping "May" used as auxiliary
pass
elif i > 0 and re.match(
"\\d+$", doc[i - 1].text) and int(doc[i - 1].text) < 32:
spans.append((i - 1, i + 1, "DATE"))
elif i > 1 and re.match(
"\\d+(?:st|nd|rd|th)$",
doc[i - 2].text) and doc[i - 1].lower_ == "of":
spans.append((i - 2, i + 1, "DATE"))
elif i < len(doc) - 1 and re.match(
"\\d+$", doc[i + 1].text) and int(doc[i + 1].text) < 32:
spans.append((i, i + 2, "DATE"))
i += 1
else:
spans.append((i, i + 1, "DATE"))
i += 1
for start, end, content in utils.merge_contiguous_spans(spans, doc):
yield start, end, content