Mercurial > repos > eric-rasche > gsaf_downloader

comparison gsaf_download.py @ 4:a90d7b00d727 draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Removed testing code
author eric-rasche
date Fri, 05 Dec 2014 14:38:00 -0500
parents ba70ea57cef9
children
comparison
equal deleted inserted replaced
3:ba70ea57cef9 4:a90d7b00d727
38 # "reads":["Sample10_S8_L001_R1_001.fastq.gz","Sample10_S8_L001_R2_001.fastq.gz"], 38 # "reads":["Sample10_S8_L001_R1_001.fastq.gz","Sample10_S8_L001_R2_001.fastq.gz"],
39 # "SA":"***"} 39 # "SA":"***"}
40 data = json.loads(gsafjson) 40 data = json.loads(gsafjson)
41 log.info("Fetching %s" % data['filename']) 41 log.info("Fetching %s" % data['filename'])
42 file_path = os.path.join('output', data['filename']) 42 file_path = os.path.join('output', data['filename'])
43 #urllib.urlretrieve(data['url'], file_path) 43 urllib.urlretrieve(data['url'], file_path)
44 log.info("Hashing file") 44 log.info("Hashing file")
45 #file_md5 = hashlib.md5(open(file_path).read()).hexdigest() 45 file_md5 = hashlib.md5(open(file_path).read()).hexdigest()
46 #log.debug("Hashed to %s" % file_md5) 46 log.debug("Hashed to %s" % file_md5)
47 47
48 stderr = '' 48 stderr = ''
49 #if file_md5 != data['md5']: 49 if file_md5 != data['md5']:
50 #stderr = 'md5sum mismatch: %s != %s' % (file_md5, data['md5']) 50 stderr = 'md5sum mismatch: %s != %s' % (file_md5, data['md5'])
51 51
52 # Galaxy.json 52 # Galaxy.json
53 # {"name": "lambda.fa", "stdout": "uploaded fasta file", "line_count": 811, "ext": "fasta", "dataset_id": 16220, "type": "dataset"} 53 # {"name": "lambda.fa", "stdout": "uploaded fasta file", "line_count": 811, "ext": "fasta", "dataset_id": 16220, "type": "dataset"}
54 line_count = subprocess.check_output(['wc', '-l', file_path]).strip() 54 line_count = subprocess.check_output(['wc', '-l', file_path]).strip()
55 line_count = line_count[0:line_count.index(' ')] 55 line_count = line_count[0:line_count.index(' ')]
63 'ext': data['file_type'].strip('.gz'), 63 'ext': data['file_type'].strip('.gz'),
64 'dataset_id': DATASET_ID, 64 'dataset_id': DATASET_ID,
65 'type': 'dataset' 65 'type': 'dataset'
66 } 66 }
67 67
68 #try: 68 try:
69 #subprocess.check_call(['gunzip', file_path]) 69 subprocess.check_call(['gunzip', file_path])
70 #except: 70 except:
71 #log.error("Couldn't extract %s" % data['filename']) 71 log.error("Couldn't extract %s" % data['filename'])
72 72
73 gx_json.write(json.dumps(galaxy_json) + "\n") 73 gx_json.write(json.dumps(galaxy_json) + "\n")
74 74