def get_completions2()

in reference/src/main/python/similar.py [0:0]

• 83 lines of code
• 16 McCabe index (conditional complexity)

def get_completions2(query_record, candidate_records):
    l = len(candidate_records)
    ret = []

    n_clusters = 0
    n_uniques = 0
    print("2-way")
    for i in range(l):
        jmax = None
        maxscore = 0
        for j in range(i + 1, l):
            pscore = find_similarity_score_features(
                candidate_records[i][2], candidate_records[j][2]
            )
            if pscore > config.THRESHOLD1:
                query_score_un = find_similarity_score_features_un(
                    candidate_records[i][2], candidate_records[j][2]
                )
                tmp_score = find_similarity_score_features_un(
                    candidate_records[i][0], candidate_records[j][0]
                )
                if (
                    tmp_score > config.THRESHOLD2 * query_score_un
                    and tmp_score > maxscore
                ):
                    jmax = j
                    maxscore = tmp_score
        if jmax is not None:
            pruned_record = prune_last_jd(
                [query_record, candidate_records[jmax][0]], candidate_records[i][0]
            )
            ret.append((pruned_record, i, jmax))
            print(ast_to_code(pruned_record["ast"]))
            n_clusters += 1
        # else:
        #     ret.append((candidate_records[i][0]['ast'], i, i))
        #     n_uniques += 1

    ret2 = []
    print("3-way")
    for (record, i, j) in ret:
        if i != j:
            kmax = None
            maxscore = 0
            for k in range(l):
                if k != i and k != j:
                    pscore = find_similarity_score_features_set(
                        [
                            candidate_records[i][2],
                            candidate_records[j][2],
                            candidate_records[k][2],
                        ]
                    )
                    if pscore > config.THRESHOLD1:
                        query_score_un = find_similarity_score_features_set_un(
                            [
                                candidate_records[i][2],
                                candidate_records[j][2],
                                candidate_records[k][2],
                            ]
                        )
                        tmp_score = find_similarity_score_features_set_un(
                            [
                                candidate_records[i][0],
                                candidate_records[j][0],
                                candidate_records[k][0],
                            ]
                        )
                        if (
                            tmp_score > config.THRESHOLD2 * query_score_un
                            and tmp_score > maxscore
                        ):
                            kmax = k
                            maxscore = tmp_score
            if kmax is not None:
                pruned_record = prune_last_jd(
                    [query_record, candidate_records[kmax][0]], record
                )
                n_clusters += 1
                print(ast_to_code(pruned_record["ast"]))
                ret2.append((pruned_record, i, j, kmax))
    logging.info(
        f"(# similars, #clusters, #singles, #completions) = ({len(candidate_records)}, {n_clusters}, {n_uniques}, {len(ret)})"
    )
    print(
        f"(# similars, #clusters, #singles, #completions) = ({len(candidate_records)}, {n_clusters}, {n_uniques}, {len(ret)})"
    )
    return ret2 + ret