203ed6d1fda8de579c2bf311e5890dca05c14985,cnvlib/target.py,,shorten_labels,#Any#,185

Before Change

    curr_gene_coords = []

    for row in interval_rows:
        next_coords = row[:-1]
        next_names = set(row[-1].rstrip().split(","))
        assert len(next_names)
        overlap = curr_names.intersection(next_names)
        if overlap:
            // Continuing the same gene; update shared accessions
            curr_names = filter_names(overlap)
            curr_gene_coords.append(next_coords)
        else:
            // End of the old gene -- emit coords + shared name(s)
            for coords in curr_gene_coords:
                out_row = emit(coords, curr_names)
                yield out_row
                longest_name_len = max(longest_name_len, len(out_row[-1]))

            // Start of a new gene
            curr_gene_coords = [next_coords]
            curr_names = next_names
    // Final emission
    for coords in curr_gene_coords:
        out_row = emit(coords, curr_names)
        yield out_row
        longest_name_len = max(longest_name_len, len(out_row[-1]))

    logging.info("Longest name length: %d", longest_name_len)


def filter_names(names, exclude=("mRNA",)):

After Change

        else:
            // End of the old gene -- emit shared name(s)
            for _i in range(curr_gene_count):
                out_name = shortest_name(curr_names)
                yield out_name
                longest_name_len = max(longest_name_len, len(out_name))

            // Start of a new gene
            curr_gene_count = 1
            curr_names = next_names
    // Final emission
    for _i in range(curr_gene_count):
        out_name = shortest_name(curr_names)
        yield out_name
        longest_name_len = max(longest_name_len, len(out_name))

    logging.info("Longest name length: %d", longest_name_len)

Instances