Mercurial > repos > iuc > data_manager_omamer

comparison data_manager/omamer.py @ 0:e1502e4f8725 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/data_managers/data_manager_omamer commit 8ff9ada22d22cb94ddfff51bcdd3ab7d30104f1a
author iuc
date Wed, 21 Feb 2024 19:26:53 +0000
parents
children 57db282ca204
comparison
equal deleted inserted replaced
-1:000000000000 0:e1502e4f8725
1 #!/usr/bin/env python
2
3 import argparse
4 import json
5 import os
6 import sys
7 from pathlib import Path
8
9 import requests
10
11 # URL for downloading OMAmer datasets
12 OMAMER_DATASETS_URL = "https://omabrowser.org/All/{dataset}"
13
14 # List of OMAmer data sets with versions
15 OMAMER_DATASETS = {
16 "Primates": "Primates-v2.0.0.h5",
17 "Viridiplantae": "Viridiplantae-v2.0.0.h5",
18 "Metazoa": "Metazoa-v2.0.0.h5",
19 "LUCA": "LUCA-v0.2.5.h5",
20 }
21
22
23 DEFAULT_OUTPUT_DIR = "database_omamer"
24
25
26 def download_file(url, dest):
27 try:
28 with requests.get(url, stream=True) as r:
29 r.raise_for_status()
30 with open(dest, 'wb') as f:
31 for chunk in r.iter_content(chunk_size=8192):
32 f.write(chunk)
33 print(f"Downloaded: {url} to {dest}")
34 except requests.exceptions.RequestException as e:
35 print(f"Error downloading {url}: {e}")
36 sys.exit(1)
37
38
39 def main(args):
40 # Set output directory to default
41 output_dir = DEFAULT_OUTPUT_DIR
42
43 # Create output directory if none exists
44 if not os.path.exists(output_dir):
45 os.makedirs(output_dir)
46
47 # Check if the selected dataset exists
48 if args.name not in OMAMER_DATASETS:
49 print(f"Error: Selected dataset '{args.name}' not found.")
50 sys.exit(1)
51
52 # Download the selected OMAmer dataset
53 dataset = OMAMER_DATASETS[args.name]
54 url = OMAMER_DATASETS_URL.format(dataset=dataset)
55 base_name = os.path.splitext(dataset)[0]
56 destination_path = os.path.join(output_dir, base_name)
57 download_file(url, destination_path)
58
59 data_manager_entry = {
60 "value": os.path.splitext(os.path.basename(base_name))[0],
61 "name": os.path.splitext(os.path.basename(base_name))[0],
62 "version": "2.0.2",
63 "path": str(Path(output_dir)),
64 }
65
66 # Creates a JSON dictionary representing the Data Manager configuration
67 data_manager_json = {"data_tables": {"omamer_data": [data_manager_entry]}}
68
69 # Writes this JSON dictionary to the specified output file
70 with open(args.json, "w") as fh:
71 json.dump(data_manager_json, fh, indent=2, sort_keys=True)
72
73
74 if __name__ == "__main__":
75 # Set up argparse to specify expected command line arguments
76 parser = argparse.ArgumentParser(description='Download data for OMAmer')
77 parser.add_argument('--name', default='Primates', choices=OMAMER_DATASETS.keys(), help='Select dataset to download')
78 parser.add_argument('--json', help='Path to JSON file')
79
80 args = parser.parse_args()
81
82 main(args)