Mercurial > repos > iuc > ncbi_eutils_efetch

comparison esummary.py @ 3:c09fcbe4b16a draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/ncbi_entrez_eutils commit dae34e5e182b4cceb808d7353080f14aa9a78ca9"
author iuc
date Wed, 23 Sep 2020 09:48:53 +0000
parents 0fc65a60436f
children
comparison
equal deleted inserted replaced
2:0977ec0f3ba8 3:c09fcbe4b16a
1 #!/usr/bin/env python 1 #!/usr/bin/env python
2 from __future__ import print_function
3 2
4 import argparse 3 import argparse
4 import json
5 import logging
6 import os
5 7
6 import eutils 8 import eutils
9
10
11 logging.basicConfig(level=logging.INFO)
7 12
8 13
9 if __name__ == '__main__': 14 if __name__ == '__main__':
10 parser = argparse.ArgumentParser(description='ESummary', epilog='') 15 parser = argparse.ArgumentParser(description='ESummary', epilog='')
11 parser.add_argument('db', help='Database to use') 16 parser.add_argument('db', help='Database to use')
17 parser.add_argument('--user_email', help="User email")
18 parser.add_argument('--admin_email', help="Admin email")
19
20 parser.add_argument('--version', action='version', version=eutils.Client.getVersion(), help='Version (reports Biopython version)')
21
22 # ID source
23 parser.add_argument('--id_xml', help='list of ids in an xml file as returned by esearch or elink')
24 parser.add_argument('--id_json', help='list of ids in a json file as returned by esearch or elink')
12 parser.add_argument('--id_list', help='list of ids') 25 parser.add_argument('--id_list', help='list of ids')
13 parser.add_argument('--id', help='Comma separated individual IDs') 26 parser.add_argument('--id', help='Comma separated individual IDs')
14 parser.add_argument('--history_file', help='Filter existing history') 27 parser.add_argument('--history_file', help='Fetch results from previous query')
15 parser.add_argument('--user_email', help="User email") 28 parser.add_argument('--history_xml', help='Fetch results from previous query')
16 parser.add_argument('--admin_email', help="Admin email") 29
30 # Output
31 parser.add_argument('--retmode', help='Retmode')
32 parser.add_argument('--retstart', type=int, default=0, help='Retstart - Starting rec number (0)')
33 parser.add_argument('--retmax', type=int, default=20, help='Retmax - max number of recs returned (20, max 100000')
34
17 args = parser.parse_args() 35 args = parser.parse_args()
18 36
19 c = eutils.Client(history_file=args.history_file, user_email=args.user_email, admin_email=args.admin_email) 37 c = eutils.Client(history_file=args.history_file, user_email=args.user_email, admin_email=args.admin_email)
20
21 merged_ids = c.parse_ids(args.id_list, args.id, args.history_file)
22 38
23 payload = { 39 payload = {
24 'db': args.db, 40 'db': args.db,
25 } 41 }
26 42
27 if args.history_file is not None: 43 for attr in ('retmode', 'retmax', 'retstart'):
28 payload.update(c.get_history()) 44 if getattr(args, attr, None) is not None:
45 payload[attr] = getattr(args, attr)
46
47 results = []
48 qkeys = []
49 if args.history_file is not None or args.history_xml is not None:
50 payload['retmode'] = args.retmode
51 if args.history_file is not None:
52 input_histories = c.get_histories()
53 else:
54 input_histories = c.extract_histories_from_xml_file(args.history_xml)
55
56 for hist in input_histories:
57 qkeys += [hist['query_key']]
58 tmp_payload = payload
59 tmp_payload.update(hist)
60 results += [c.summary(**tmp_payload)]
29 else: 61 else:
62 # There is no uilist retmode
63 if args.retmode == "uilist":
64 payload['retmode'] = 'xml'
65 else:
66 payload['retmode'] = args.retmode
67 merged_ids = c.parse_ids(args.id_list, args.id, args.history_file, args.id_xml, args.id_json)
30 payload['id'] = ','.join(merged_ids) 68 payload['id'] = ','.join(merged_ids)
69 qkeys += [1]
70 results += [c.summary(**payload)]
31 71
32 print(c.summary(**payload)) 72 # There could be multiple sets of results if a history was supplied
73 if args.history_file is not None or args.history_xml is not None:
74 # Multiple result sets can be returned
75 # Create a directory for the output files
76 current_directory = os.getcwd()
77 final_directory = os.path.join(current_directory, r'downloads')
78 if not os.path.exists(final_directory):
79 os.makedirs(final_directory)
80
81 logging.info("Writing files:")
82 count = 0
83 if args.retmode == 'json':
84 for result in results:
85 qkey = qkeys[count]
86 count += 1
87 file_path = os.path.join('downloads', '%s-querykey%s.json' % (args.db, qkey))
88 logging.info('%s-link%s.json' % (args.db, count))
89 with open(file_path, 'w') as handle:
90 json_data = c.jsonstring2jsondata(result)
91 handle.write(json.dumps(json_data, indent=4))
92 else:
93 for result in results:
94 qkey = qkeys[count]
95 count += 1
96 file_path = os.path.join('downloads', '%s-querykey%s.xml' % (args.db, qkey))
97 logging.info('%s-link%s.xml' % (args.db, count))
98 with open(file_path, 'w') as handle:
99 handle.write(result)
100 else:
101 # When rettype is uilist, convert to text format (which elink does not do)
102 if args.retmode == 'json':
103 json_data = c.jsonstring2jsondata(results[0])
104 print(json.dumps(json_data, indent=4))
105 else:
106 print(results[0])