|
0
|
1 import csv, sys, argparse, logging
|
|
|
2
|
|
|
3 LOG_FORMAT = '%(asctime)s|%(levelname)-8s|%(message)s'
|
|
|
4 LOG_DATEFMT = '%Y-%m-%d %H:%M:%S'
|
|
|
5 LOG_LEVELS = ['DEBUG', 'INFO', 'WARNING', 'ERROR', 'CRITICAL']
|
|
|
6
|
|
|
7
|
|
|
8 def make_parser():
|
|
|
9 parser = argparse.ArgumentParser(description='build aligned seq data sample import files')
|
|
|
10 parser.add_argument('--logfile', type=str, help='log file (default=stderr)')
|
|
|
11 parser.add_argument('--loglevel', type=str, choices=LOG_LEVELS,
|
|
|
12 help='logging level', default='INFO')
|
|
|
13 parser.add_argument('--study', type=str, required=True,
|
|
|
14 help='study')
|
|
|
15 parser.add_argument('--label', type=str, required=True,
|
|
|
16 help='label')
|
|
|
17 parser.add_argument('--source', type=str, required=True,
|
|
|
18 help='source')
|
|
|
19 parser.add_argument('--device', type=str, required=True,
|
|
|
20 help='device')
|
|
|
21 parser.add_argument('--path', type=str, required=True,
|
|
|
22 help='path')
|
|
|
23 parser.add_argument('--sample', type=str, required=True,
|
|
|
24 help='sample')
|
|
|
25 parser.add_argument('--genome_reference', type=str, required=True,
|
|
|
26 help='genome reference')
|
|
|
27 parser.add_argument('--dsample_ofile', type=str, default='./genome_variations_dsample.tsv',
|
|
|
28 help='output file containing data samples definitions')
|
|
|
29 parser.add_argument('--dobject_ofile', type=str, default='./genome_variations_dobject.tsv',
|
|
|
30 help='output file containing data samples definitions')
|
|
|
31
|
|
|
32 return parser
|
|
|
33
|
|
|
34 def main(argv):
|
|
|
35 parser = make_parser()
|
|
|
36 args = parser.parse_args(argv)
|
|
|
37
|
|
|
38 log_level = getattr(logging, args.loglevel)
|
|
|
39 kwargs = {'format': LOG_FORMAT,
|
|
|
40 'datefmt': LOG_DATEFMT,
|
|
|
41 'level': log_level}
|
|
|
42 if args.logfile:
|
|
|
43 kwargs['filename'] = args.logfile
|
|
|
44 logging.basicConfig(**kwargs)
|
|
|
45 logger = logging.getLogger('prepare_aligned_seq_dsample_inport')
|
|
|
46
|
|
|
47
|
|
|
48 with open(args.dsample_ofile, 'w') as ofile:
|
|
|
49 out_file_header = ['study', 'label', 'source', 'source_type', 'seq_dsample_type', 'status', 'device', 'sample', 'genome_reference']
|
|
|
50 writer = csv.DictWriter(ofile, out_file_header, delimiter='\t')
|
|
|
51 writer.writeheader()
|
|
|
52 writer.writerow({'study': args.study,
|
|
|
53 'label': args.label,
|
|
|
54 'source': args.source,
|
|
|
55 'device': args.device,
|
|
|
56 'source_type' : 'Tube',
|
|
|
57 'seq_dsample_type': 'AlignedSeqDataSample',
|
|
|
58 'status': 'USABLE',
|
|
|
59 'sample' : args.sample,
|
|
|
60 'genome_reference': args.genome_reference})
|
|
|
61 logger.info('Done writing file %s' % args.dsample_ofile)
|
|
|
62
|
|
|
63 with open(args.dobject_ofile, 'w') as ofile:
|
|
|
64 out_file_header = ['study', 'path', 'data_sample', 'mimetype', 'size', 'sha1']
|
|
|
65 writer = csv.DictWriter(ofile, out_file_header, delimiter='\t')
|
|
|
66 writer.writeheader()
|
|
|
67 writer.writerow({'study': args.study,
|
|
|
68 'path': args.path,
|
|
|
69 'data_sample': args.label,
|
|
|
70 'mimetype': 'x-vl/bam',
|
|
|
71 'size': '-1',
|
|
|
72 'sha1': 'N.A.'})
|
|
|
73 logger.info('Done writing file %s' % args.dobject_ofile)
|
|
|
74
|
|
|
75 if __name__ == '__main__':
|
|
|
76 main(sys.argv[1:])
|
