def test_strip_pair_symbols(self):
text = '"(A right of set-off; B)"'
cleared = TextBeautifier.strip_pair_symbols(text)
self.assertEqual('A right of set-off; B', cleared)
text = '("A right" of set-off; "B")'
cleared = TextBeautifier.strip_pair_symbols(text)
self.assertEqual('"A right" of set-off; "B"', cleared)
def test_strip_pair_symbols_untouched(self):
text = '(A) right of set-off; (B)'
cleared = TextBeautifier.strip_pair_symbols(text)
self.assertEqual(text, cleared)
text = '(A ( right) of set-off; (B)'
cleared = TextBeautifier.strip_pair_symbols(text)
self.assertEqual(text, cleared)
text = '"(A ( right)" "of set-off; (B)"'
cleared = TextBeautifier.strip_pair_symbols(text)
self.assertEqual(text, cleared)
def test_strip_pair_symbols_coords(self):
text = ' "(A right of set-off; B)"'
cleared = TextBeautifier.strip_pair_symbols((text, 2, 23))
self.assertEqual(('A right of set-off; B', 5, 21), cleared)
text = '("A right" of set-off; "B")'
cleared = TextBeautifier.strip_pair_symbols((text, 100, 119))
self.assertEqual(('"A right" of set-off; "B"', 101, 118), cleared)
text = ' "A right" of set-off; "B" '
cleared = TextBeautifier.strip_pair_symbols((text, 100, 119))
self.assertEqual(('"A right" of set-off; "B"', 102, 118), cleared)
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
def get_definition_list_in_sentence(
sentence_coords: Tuple[int, int, str],
decode_unicode=True) -> List[DefinitionCaught]:
"""
Find possible definitions in natural language in a single sentence.
:param sentence_coords: sentence, sentence start, end
:param decode_unicode:
:return:
"""
definitions = [] # type: List[DefinitionCaught]
sentence = sentence_coords[2]
# unify quotes and braces
# replace excess braces with ' ' so the str length will remain the same
sentence = TextBeautifier.unify_quotes_braces(sentence,
empty_replacement=' ')
sent_start = sentence_coords[0]
result = set() # type: Set[Tuple[str, int, int]]
# it really transforms string, e.g. replaces “ with "
if decode_unicode:
sentence = unidecode.unidecode(sentence)
sentence_coords = sentence_coords[0], sentence_coords[1], sentence
# case 1
for item in TRIGGER_WORDS_PTN_RE.finditer(sentence):
result.update(
regex_matches_to_word_coords(EXTRACT_PTN_RE, item.group(),
item.start() + sent_start))
# case 3
mts = regex_matches_to_word_coords(NOUN_PTN_RE, sentence, sent_start)
mts = [i for i in mts if not NOUN_ANTI_PTN_RE.fullmatch(i[0])]
mts = [
m for m in mts
if m[0].lower().strip(' ,;.') not in EnLanguageTokens.pronouns
]
if len(mts) > 0:
result.update(mts)
# cases 2, 4, 5, 6
for _ in TRIGGER_QUOTED_DEFINITION_RE.finditer(sentence):
for quoted_definition_re in QUOTED_DEFINITION_RE:
result.update(
regex_matches_to_word_coords(quoted_definition_re, sentence,
sent_start))
break
# make definitions out of entries
for term, start, end in result:
term_cleared = TextBeautifier.strip_pair_symbols((term, start, end))
term_cleared = trim_defined_term(term_cleared[0], term_cleared[1],
term_cleared[2])
was_quoted = term_cleared[3]
if PICK_DEFINITION_FROM_QUOTES:
term, start, end = term_cleared[0], term_cleared[1], term_cleared[
2]
if not term_cleared[0]:
continue
term, start, end = TextBeautifier.unify_quotes_braces_coords(
term, start, end)
# check the term is not empty
if len(term.strip(PUNCTUATION_STRIP_STR)) == 0:
continue
# returns [('word', 'token', (word_start, word_end)), ...] ...
term_pos = list(SpanTokenizer.get_token_spans(term))
if does_term_are_service_words(term_pos):
continue
term_wo_intro = IntroductoryWordsDetector.remove_term_introduction(
term, term_pos)
if term_wo_intro != term:
term = TextBeautifier.strip_pair_symbols(term_wo_intro)
if not term:
continue
# check the term is not too long
max_words_per_definition = MAX_TERM_TOKENS
if was_quoted:
max_words_per_definition = MAX_QUOTED_TERM_TOKENS
words_in_term = sum(
1 for w in word_processor.split_text_on_words(term_cleared[0])
if not w.is_separator)
quotes_in_text = get_quotes_count_in_string(term_cleared[0])
possible_definitions = quotes_in_text // 2 if quotes_in_text > 1 else 1
possible_tokens_count = max_words_per_definition * possible_definitions
if words_in_term > possible_tokens_count:
continue
split_definitions_lst = split_definitions_inside_term(
term, sentence_coords, start, end)
for definition, s, e in split_definitions_lst:
definition, s, e = TextBeautifier.strip_pair_symbols(
(definition, s, e))
definitions.append(DefinitionCaught(definition, sentence, (
s,
e,
)))
return definitions