elasticsearch.py 文件源码

def filter_hits_by_distance(hits, source_text,
                            min_similarity=DEFAULT_MIN_SIMILARITY):
    """Returns ES `hits` filtered according to their Levenshtein distance
    to the `source_text`.

    Any hits with a similarity value (0..1) lower than `min_similarity` will be
    discarded. It's assumed that `hits` is already sorted from higher to lower
    score.
    """
    if min_similarity <= 0 or min_similarity >= 1:
        min_similarity = DEFAULT_MIN_SIMILARITY

    filtered_hits = []
    for hit in hits:
        hit_source_text = hit['_source']['source']
        distance = Levenshtein.distance(source_text, hit_source_text)
        similarity = (
            1 - distance / float(max(len(source_text), len(hit_source_text)))
        )

        logger.debug(
            'Similarity: %.2f (distance: %d)\nOriginal:\t%s\nComparing with:\t%s',
            similarity, distance, source_text, hit_source_text
        )

        if similarity < min_similarity:
            break

        filtered_hits.append(hit)

    return filtered_hits