Function get_ignorables

src/licensedcode/models.py:2909–2956

Return a mapping of ignorable clues lists found in a ``text`` for copyrights, holders, authors, urls, emails. Do not include items with empty values. Display progress messages if ``verbose`` is True.

(text, verbose=False)

def get_ignorables(text, verbose=False):
    """
    Return a mapping of ignorable clues lists found in a ``text`` for
    copyrights, holders, authors, urls, emails. Do not include items with empty values.

    Display progress messages if ``verbose`` is True.
    """
    from cluecode.copyrights import detect_copyrights_from_lines
    from cluecode.copyrights import Detection

    from cluecode.finder import find_urls
    from cluecode.finder import find_emails

    text_lines = text.splitlines()

    # Redundant clues found in a license or rule text can be ignored.
    # Therefdore we collect and set ignorable copyrights, holders and authors
    detections = detect_copyrights_from_lines(numbered_lines=enumerate(text.splitlines(), 1))
    copyrights, holders, authors = Detection.split_values(detections)

    if verbose:
        for detection in (copyrights + holders + authors):
            print(f'  Found ignorable: {detection}')

    copyrights = set(copyrights)
    holders = set(holders)
    authors = set(authors)

    # collect and set ignorable emails and urls
    urls = set(u for (u, _ln) in find_urls(location=text_lines) if u)
    if verbose:
        print(f'  Found urls: {urls}')

    emails = set(e for (e, _ln) in find_emails(text_lines) if e)
    if verbose:
        print(f'  Found emails: {emails}')

    ignorables = build_ignorables_mapping(
        copyrights=copyrights,
        holders=holders,
        authors=authors,
        urls=urls,
        emails=emails,
    )

    if verbose:
        print(f'  Found ignorables: {ignorables}')
    return ignorables


def get_normalized_ignorables(licensish):