Mercurial > repos > galaxytrakr > data_manager_mapseq

comparison data_manager/data_manager_fetch_mapseq_db.py @ 0:f99c1cc0b190 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload commit bae430588c393222b68c5a7aa47f57bffee99475
author galaxytrakr
date Thu, 26 Mar 2026 20:22:36 +0000
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:f99c1cc0b190
1 #!/usr/bin/env python
2 # Python 3.6 compatible
3
4 import argparse
5 import json
6 import os
7 import shutil
8 import tarfile
9 import tempfile
10 from datetime import datetime
11
12 import wget
13
14 DB_paths = {
15 "mgnify_v5_lsu": "ftp://ftp.ebi.ac.uk/pub/databases/metagenomics/pipeline-5.0/ref-dbs/silva_lsu-20200130.tar.gz",
16 "mgnify_v5_ssu": "ftp://ftp.ebi.ac.uk/pub/databases/metagenomics/pipeline-5.0/ref-dbs/silva_ssu-20200130.tar.gz",
17 "mgnify_v5_its_unite": "ftp://ftp.ebi.ac.uk/pub/databases/metagenomics/pipeline-5.0/ref-dbs/UNITE-20200214.tar.gz",
18 "mgnify_v5_its_itsonedb": "ftp://ftp.ebi.ac.uk/pub/databases/metagenomics/pipeline-5.0/ref-dbs/ITSoneDB-20200214.tar.gz",
19 "mgnify_v6_lsu": "ftp://ftp.ebi.ac.uk/pub/databases/metagenomics/pipelines/tool-dbs/silva-lsu/silva-lsu_138.1.tar.gz",
20 "mgnify_v6_ssu": "ftp://ftp.ebi.ac.uk/pub/databases/metagenomics/pipelines/tool-dbs/silva-ssu/silva-ssu_138.1.tar.gz",
21 "mgnify_v6_its_unite": "ftp://ftp.ebi.ac.uk/pub/databases/metagenomics/pipelines/tool-dbs/unite/unite_9.0.tar.gz",
22 "mgnify_v6_its_itsonedb": "ftp://ftp.ebi.ac.uk/pub/databases/metagenomics/pipelines/tool-dbs/itsonedb/itsonedb_1.141.tar.gz",
23 "mgnify_v6_pr2": "ftp://ftp.ebi.ac.uk/pub/databases/metagenomics/pipelines/tool-dbs/pr2/pr2_5.0.0.tar.gz",
24 "test_lsu": "https://zenodo.org/record/8205348/files/test_lsu.tar.gz",
25 }
26
27 DB_names = {
28 "mgnify_v5_lsu": "MGnify LSU (v5.0.7) - silva_lsu-20200130",
29 "mgnify_v5_ssu": "MGnify SSU (v5.0.7) - silva_ssu-20200130",
30 "mgnify_v5_its_unite": "MGnify ITS UNITE (v5.0.7) - UNITE-20200214",
31 "mgnify_v5_its_itsonedb": "MGnify ITS ITSonedb (v5.0.7) - ITSoneDB-20200214",
32 "mgnify_v6_lsu": "MGnify LSU (v6.0) - silva_lsu-20240702",
33 "mgnify_v6_ssu": "MGnify SSU (v6.0) - silva_ssu-20240701",
34 "mgnify_v6_its_unite": "MGnify ITS UNITE (v6.0) - UNITE-20240702",
35 "mgnify_v6_its_itsonedb": "MGnify ITS ITSonedb (v6.0) - ITSoneDB-20240702",
36 "mgnify_v6_pr2": "MGnify PR2 (v6.0) - PR2-20240702",
37 "test_lsu": "Trimmed LSU Test DB",
38 }
39
40 def _empty_dir(path):
41 if not os.path.isdir(path):
42 os.makedirs(path)
43 return
44 for name in os.listdir(path):
45 p = os.path.join(path, name)
46 if os.path.isdir(p) and not os.path.islink(p):
47 shutil.rmtree(p)
48 else:
49 try:
50 os.remove(p)
51 except OSError:
52 pass
53
54 def _copy_all(src_dir, dest_dir):
55 for name in os.listdir(src_dir):
56 s = os.path.join(src_dir, name)
57 d = os.path.join(dest_dir, name)
58 if os.path.isdir(s) and not os.path.islink(s):
59 if os.path.exists(d):
60 shutil.rmtree(d)
61 shutil.copytree(s, d)
62 else:
63 shutil.copy2(s, dest_dir)
64
65 def _safe_members(members):
66 for m in members:
67 mpath = m.name
68 norm = mpath.replace("\\", "/")
69 if os.path.isabs(mpath) or ".." in norm.split("/"):
70 continue
71 yield m
72
73 def materialize_db_into(output_dir, url):
74 # Work entirely under /tmp to avoid job-dir races
75 tmp_root = tempfile.mkdtemp(prefix="mapseq_dm_", dir="/tmp")
76 temp_extract = tempfile.mkdtemp(prefix="extract_", dir=tmp_root)
77
78 tar_path = wget.download(url, out=tmp_root)
79 with tarfile.open(tar_path, "r:*") as tar:
80 tar.extractall(temp_extract, members=_safe_members(tar))
81
82 _empty_dir(output_dir)
83
84 entries = os.listdir(temp_extract)
85 if len(entries) == 1 and os.path.isdir(os.path.join(temp_extract, entries[0])):
86 inner = os.path.join(temp_extract, entries[0])
87 vf = os.path.join(inner, "VERSION.txt")
88 if os.path.exists(vf):
89 try:
90 os.remove(vf)
91 except OSError:
92 pass
93 _copy_all(inner, output_dir)
94 else:
95 vf = os.path.join(temp_extract, "VERSION.txt")
96 if os.path.exists(vf):
97 try:
98 os.remove(vf)
99 except OSError:
100 pass
101 _copy_all(temp_extract, output_dir)
102
103 try:
104 shutil.rmtree(tmp_root)
105 except Exception:
106 pass
107
108 def main():
109 parser = argparse.ArgumentParser(description="Fetch and register MAPseq DB")
110 parser.add_argument("--out", dest="output", required=True, help="Galaxy params/DM JSON path")
111 parser.add_argument("--version", dest="version", required=False, help="DB version label (e.g., 6.0)")
112 parser.add_argument("--database-type", dest="db_type", required=False, help="DB key (e.g., mgnify_v6_lsu)")
113 parser.add_argument("--test", action="store_true", help="Use small test DB")
114 args = parser.parse_args()
115
116 # Read Galaxy params to get extra_files_path
117 with open(args.output) as fh:
118 params = json.load(fh)
119
120 output_dir = params["output_data"][0]["extra_files_path"]
121 if not os.path.isdir(output_dir):
122 os.makedirs(output_dir)
123
124 # Resolve db_type/version: prefer CLI, else try params.select_version
125 db_type = args.db_type
126 version = args.version
127 sel = params.get("select_version") or {}
128 if not db_type:
129 db_type = sel.get("database_type")
130 if not version:
131 version = sel.get("version")
132
133 if not db_type:
134 raise RuntimeError("Missing --database-type and no params['select_version']['database_type'] provided.")
135 if db_type not in DB_paths:
136 raise KeyError("Unknown database type: {}. Valid keys: {}".format(db_type, ", ".join(sorted(DB_paths.keys()))))
137
138 url = DB_paths["test_lsu"] if args.test else DB_paths[db_type]
139 materialize_db_into(output_dir, url)
140
141 # Build DM JSON (value/name pattern you used earlier)
142 date_str = datetime.utcnow().strftime("%Y-%m-%d")
143 db_value = "{}_from_{}".format(db_type, date_str)
144 db_name = DB_names.get(db_type, db_type)
145 entry_name = "{} downloaded at {}".format(db_name, date_str)
146
147 data_manager_entry = {
148 "data_tables": {
149 "mapseq_db": [
150 {
151 "value": db_value,
152 "name": entry_name,
153 "path": output_dir,
154 "version": version,
155 }
156 ]
157 }
158 }
159
160 with open(args.output, "w") as fh:
161 json.dump(data_manager_entry, fh, indent=2, sort_keys=True)
162
163 try:
164 count = len(os.listdir(output_dir))
165 print("[INFO] Wrote {} items into {}".format(count, output_dir))
166 except Exception:
167 pass
168
169 print("[SUCCESS] Data Manager JSON written to {}".format(args.output))
170
171 if __name__ == "__main__":
172 main()