Mercurial > repos > iuc > data_manager_omamer

comparison data_manager/omamer.py @ 0:d28438704310 draft default tip

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 b890cd87ef5cfaa81eda29cc935de224ecb05bb6
author iuc
date Wed, 14 Aug 2024 15:42:38 +0000
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:d28438704310
1 #!/usr/bin/env python
2
3 import argparse
4 import json
5 import os
6 import sys
7
8 import requests
9
10 # URL for downloading OMAmer datasets
11 OMAMER_DATASETS_URL = "https://omabrowser.org/All/{dataset}"
12
13 # List of OMAmer data sets with versions
14 OMAMER_DATASETS = {
15 "Primates_v2.0.0": "Primates-v2.0.0.h5",
16 "Viridiplantae_v2.0.0": "Viridiplantae-v2.0.0.h5",
17 "Metazoa_v2.0.0": "Metazoa-v2.0.0.h5",
18 "LUCA_v0.2.5": "LUCA-v0.2.5.h5",
19 "LUCA_v2.0.0": "LUCA-v2.0.0.h5",
20 "Saccharomyceta": "Saccharomyceta.h5",
21 "Homininae": "Homininae.h5",
22 }
23
24 DEFAULT_OUTPUT_DIR = "database_omamer"
25
26
27 def download_file(url, dest):
28 try:
29 with requests.get(url, stream=True) as r:
30 r.raise_for_status()
31 with open(dest, 'wb') as f:
32 for chunk in r.iter_content(chunk_size=8192):
33 f.write(chunk)
34 print(f"Downloaded: {url} to {dest}")
35 except requests.exceptions.RequestException as e:
36 print(f"Error downloading {url}: {e}")
37 sys.exit(1)
38
39
40 def main(args):
41
42 with open(args.json) as fh:
43 params = json.load(fh)
44 target_directory = params["output_data"][0]["extra_files_path"]
45
46 # Create output directory if none exists
47 if not os.path.exists(target_directory):
48 os.makedirs(target_directory)
49
50 # Check if the selected dataset exists
51 if args.name not in OMAMER_DATASETS:
52 print(f"Error: Selected dataset '{args.name}' not found.")
53 sys.exit(1)
54
55 # Download the selected OMAmer dataset
56 dataset = OMAMER_DATASETS[args.name]
57 url = OMAMER_DATASETS_URL.format(dataset=dataset)
58 base_name = os.path.splitext(dataset)[0]
59 destination_path = os.path.join(target_directory, dataset)
60 download_file(url, destination_path)
61
62 data_manager_entry = {
63 "value": dataset,
64 "name": base_name,
65 "version": args.version,
66 "path": dataset,
67 }
68
69 # Creates a JSON dictionary representing the Data Manager configuration
70 data_manager_json = {"data_tables": {"omamer": [data_manager_entry]}}
71
72 # Writes this JSON dictionary to the specified output file
73 with open(args.json, "w") as fh:
74 json.dump(data_manager_json, fh, indent=2, sort_keys=True)
75
76
77 if __name__ == "__main__":
78 # Set up argparse to specify expected command line arguments
79 parser = argparse.ArgumentParser(description='Download data for OMAmer')
80 parser.add_argument('--name', default='Primates', choices=OMAMER_DATASETS.keys(), help='Select dataset to download')
81 parser.add_argument('--json', help='Path to JSON file')
82 parser.add_argument("--version", help="Omamer version")
83
84 args = parser.parse_args()
85
86 main(args)