Function split_weak_matches

src/licensedcode/match.py:1740–1765

Return a filtered list of kept LicenseMatch matches and a list of weak matches given a `matches` list of LicenseMatch by considering shorter sequence matches with a low coverage or match to unknown licenses. These are set aside before "unknown license" matching.

(matches)

def split_weak_matches(matches):
    """
    Return a filtered list of kept LicenseMatch matches and a list of weak
    matches given a `matches` list of LicenseMatch by considering shorter
    sequence matches with a low coverage or match to unknown licenses. These are
    set aside before "unknown license" matching.
    """
    from licensedcode.match_seq import MATCH_SEQ

    kept = []
    kept_append = kept.append
    discarded = []
    discarded_append = discarded.append

    for match in matches:
        # always keep exact matches
        if (match.matcher == MATCH_SEQ
            and match.len() <= SMALL_RULE
            and match.coverage() <= 25
        ) or match.rule.has_unknown:

            discarded_append(match)
        else:
            kept_append(match)

    return kept, discarded


def filter_spurious_matches(