def test_strip_text_coords(self):
text = ' (A) right of set-off; (B) '
stripped = TextBeautifier.strip_string_coords(text, 100, 127)
self.assertEqual(('(A) right of set-off; (B)', 104, 126), stripped)
text = ' (A) right of set-off; (B) '
stripped = TextBeautifier.lstrip_string_coords(text, 100, 127)
self.assertEqual(('(A) right of set-off; (B) ', 104, 127), stripped)
text = ' (A) right of set-off; (B) '
stripped = TextBeautifier.rstrip_string_coords(text, 100, 127)
self.assertEqual((' (A) right of set-off; (B)', 100, 126), stripped)
def trim_defined_term(term: str, start: int, end: int) -> \
Tuple[str, int, int, bool]:
"""
Remove pair of quotes / brackets framing text
Replace N-grams of spaces with single spaces
Replace line breaks with spaces
:param term: a phrase that may contain excess framing symbols
:param start: original term's start position, may be changed
:param end: original term's end position, may be changed
:return: updated term, start, end and the flag indicating that the whole phrase was inside quotes
"""
was_quoted = False
# pick text from quotes
# pick text from quotes
quoted_parts = [m.group() for m in QUOTED_TEXT_RE.finditer(term)]
if len(quoted_parts) == 1:
term = quoted_parts[0].strip('''\"'“„''')
was_quoted = True
orig_term_len = len(term)
orig_term_quotes = count_sequence_matches(
term, lambda c: c in TextBeautifier.QUOTES)
term, start, end = TextBeautifier.strip_pair_symbols((term, start, end))
if len(term) < orig_term_len:
# probably we removed quotes
updated_term_quotes = count_sequence_matches(
term, lambda c: c in TextBeautifier.QUOTES)
was_quoted = was_quoted or orig_term_quotes - updated_term_quotes > 1
term = term.replace('\n', ' ')
term = SPACES_RE.sub(' ', term)
term, start, end = TextBeautifier.strip_string_coords(
term, start, end, STRIP_PUNCT_SYMBOLS)
# strip all dots or just left one (if ends with abbreviation)
ends_with_abbr = ABBREVIATION_ENDING_RE.search(term)
if not ends_with_abbr:
term, start, end = TextBeautifier.strip_string_coords(
term, start, end, '.')
else:
term, start, end = TextBeautifier.lstrip_string_coords(
term, start, end, '.')
return term, start, end, was_quoted