__init__.py 文件源码

def split(args):
    assert len(args.read1s) == len(args.read2s)

    chunks = []

    # Determine the number of buckets required to achieve
    # the given chunk size.
    chunks_per_gem_group = {}
    with open(args.reads_summary) as f:
        reads_summary = json.load(f)
        for gg in args.gem_groups:
            readpairs = reads_summary['%d_total_reads_per_gem_group' % gg]
            chunks_per_gem_group[str(gg)] = max(2,
                                                int(math.ceil(float(readpairs) / \
                                                              args.readpairs_per_chunk)))

    for fastq1, fastq2 in itertools.izip(args.read1s, args.read2s):
        chunks.append({
            'read1s_chunk': fastq1,
            'read2s_chunk': fastq2,
            'chunks_per_gem_group': chunks_per_gem_group,
        })
    return {'chunks': chunks}