Function get_phrase_spans

src/licensedcode/tokenize.py:182–212

Yield position Spans for each tagged required phrase found in ``text``.

(text)

def get_phrase_spans(text):
    """
    Yield position Spans for each tagged required phrase found in ``text``.
    """
    ipos = 0
    in_required_phrase = False
    current_phrase_positions = []
    for token in required_phrase_tokenizer(text):
        if token == REQUIRED_PHRASE_OPEN:
            if in_required_phrase:
                raise InvalidRuleRequiredPhrase('Invalid rule with nested required phrase {{ {{ braces', text)
            in_required_phrase = True

        elif token == REQUIRED_PHRASE_CLOSE:
            if in_required_phrase:
                if current_phrase_positions:
                    yield Span(current_phrase_positions)
                    current_phrase_positions = []
                else:
                    raise InvalidRuleRequiredPhrase('Invalid rule with empty required phrase {{}} braces', text)
                in_required_phrase = False
            else:
                raise InvalidRuleRequiredPhrase(f'Invalid rule with dangling required phrase missing closing braces', text)
            continue
        else:
            if in_required_phrase:
                current_phrase_positions.append(ipos)
            ipos += 1

    if current_phrase_positions or in_required_phrase:
        raise InvalidRuleRequiredPhrase(f'Invalid rule with dangling required phrase missing final closing braces', text)