Function get_close_matches

Lib/difflib.py:667–715

Use SequenceMatcher to return list of the best "good enough" matches. word is a sequence for which close matches are desired (typically a string). possibilities is a list of sequences against which to match word (typically a list of strings). Optional arg n (default 3) is the

(word, possibilities, n=3, cutoff=0.6)

def get_close_matches(word, possibilities, n=3, cutoff=0.6):
    """Use SequenceMatcher to return list of the best "good enough" matches.

    word is a sequence for which close matches are desired (typically a
    string).

    possibilities is a list of sequences against which to match word
    (typically a list of strings).

    Optional arg n (default 3) is the maximum number of close matches to
    return.  n must be > 0.

    Optional arg cutoff (default 0.6) is a float in [0, 1].  Possibilities
    that don't score at least that similar to word are ignored.

    The best (no more than n) matches among the possibilities are returned
    in a list, sorted by similarity score, most similar first.

    >>> get_close_matches("appel", ["ape", "apple", "peach", "puppy"])
    ['apple', 'ape']
    >>> import keyword as _keyword
    >>> get_close_matches("wheel", _keyword.kwlist)
    ['while']
    >>> get_close_matches("Apple", _keyword.kwlist)
    []
    >>> get_close_matches("accept", _keyword.kwlist)
    ['except']
    """

    if not n >  0:
        raise ValueError("n must be > 0: %r" % (n,))
    if not 0.0 <= cutoff <= 1.0:
        raise ValueError("cutoff must be in [0.0, 1.0]: %r" % (cutoff,))
    result = []
    s = SequenceMatcher()
    s.set_seq2(word)
    for x in possibilities:
        s.set_seq1(x)
        if s.real_quick_ratio() < cutoff or s.quick_ratio() < cutoff:
            continue

        ratio = s.ratio()
        if ratio >= cutoff:
            result.append((ratio, x))

    # Move the best scorers to head of list
    result = _nlargest(n, result)
    # Strip scores for the best n matches
    return [x for score, x in result]


def _keep_original_ws(s, tag_s):