Mercurial > repos > pjbriggs > ceas

comparison data_manager/data_manager_ceas_fetch_annotations.py @ 0:f411ce97a351 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded initial version 1.0.2-2
author pjbriggs
date Tue, 30 Jun 2015 07:08:05 -0400
parents
children df9033b88b53
comparison
equal deleted inserted replaced
-1:000000000000 0:f411ce97a351
1 #!/usr/bin/env python
2 #
3
4 import sys
5 import os
6 import subprocess
7 import tempfile
8 import optparse
9 import urllib2
10 import gzip
11 import shutil
12
13 from galaxy.util.json import from_json_string, to_json_string
14
15 # Download file from specified URL and put into local subdir
16
17 if __name__ == '__main__':
18 #Parse Command Line
19 parser = optparse.OptionParser()
20 options,args = parser.parse_args()
21 print "options: %s" % options
22 print "args : %s" % args
23 if len(args) != 2:
24 p.error("Need to supply JSON file name and description text")
25
26 # Read the JSON supplied from the data manager tool
27 # Results from this program will be returned via the
28 # same file
29 jsonfile = args[0]
30 params = from_json_string(open(jsonfile).read() )
31 print "%s" % params
32
33 # Extract the data from the input JSON
34 # See https://wiki.galaxyproject.org/Admin/Tools/DataManagers/HowTo/Define?highlight=%28\bAdmin%2FTools%2FDataManagers\b%29
35 # for example of JSON
36 #
37 # We want the values set in the data manager XML
38 dbkey = params['param_dict']['dbkey']
39 description = args[1].strip()
40 identifier = params['param_dict']['unique_id'].strip()
41 # Where to put the output file
42 # Nb we have to make this ourselves, it doesn't exist by default
43 target_dir = params['output_data'][0]['extra_files_path']
44 os.mkdir(target_dir)
45
46 method = params['param_dict']['reference_source']['reference_source_selector']
47
48 # Dictionary for returning to data manager
49 data_manager_dict = {}
50 data_manager_dict['data_tables'] = dict()
51
52 # Download from URL
53 if method == 'web':
54 url = params['param_dict']['reference_source']['annotation_url']
55 print "Downloading: %s" % url
56 annotation_file_name = os.path.basename(url)
57 annotation_file_path = os.path.join(target_dir,annotation_file_name)
58 print "Annotation file name: %s" % annotation_file_name
59 print "Annotation file path: %s" % annotation_file_path
60 open(annotation_file_path,'wb').write(urllib2.urlopen(url).read())
61 if annotation_file_name.endswith('.gz'):
62 # Uncompress
63 uncompressed_file = annotation_file_path[:-3]
64 open(uncompressed_file,'wb').write(gzip.open(annotation_file_path,'rb').read())
65 # Remove gzipped file
66 os.remove(annotation_file_path)
67 annotation_file_name = os.path.basename(uncompressed_file)
68 annotation_file_path = uncompressed_file
69 # Update the identifier and description
70 if not identifier:
71 identifier = "%s_ceas_web" % dbkey
72 if not description:
73 description = "%s (%s)" % (os.path.splitext(annotation_file_name)[0],dbkey)
74 # Update the output dictionary
75 data_manager_dict['data_tables']['ceas_annotations'] = {
76 'value': identifier,
77 'dbkey': dbkey,
78 'name': description,
79 'path': annotation_file_name,
80 }
81 elif method == 'server':
82 # Pull in a file from the server
83 filename = params['param_dict']['reference_source']['annotation_filename']
84 create_symlink = params['param_dict']['reference_source']['create_symlink']
85 print "Canonical gene list file name: %s" % filename
86 print "Create symlink: %s" % create_symlink
87 target_filename = os.path.join(target_dir,os.path.basename(filename))
88 if create_symlink == 'copy_file':
89 shutil.copyfile(filename,target_filename)
90 else:
91 os.symlink(filename,target_filename)
92 # Update the identifier and description
93 if not identifier:
94 identifier = "%s_%s" % (dbkey,
95 os.path.splitext(os.path.basename(filename))[0])
96 if not description:
97 description = "%s: %s" % (dbkey,
98 os.path.splitext(os.path.basename(filename))[0])
99 # Update the output dictionary
100 data_manager_dict['data_tables']['ceas_annotations'] = {
101 'value': identifier,
102 'dbkey': dbkey,
103 'name': description,
104 'path': os.path.basename(filename),
105 }
106 elif method == 'from_wig':
107 # Make a reference file from a wig file
108 wig_file = params['param_dict']['reference_source']['wig_file']
109 gene_annotation = params['param_dict']['reference_source']['gene_annotation']
110 target_filename = os.path.join(target_dir,"%s_%s.%s" % (dbkey,
111 os.path.basename(wig_file),
112 gene_annotation))
113 print "Wig file: %s" % wig_file
114 print "Gene annotation: %s" % gene_annotation
115 print "Output file: %s" % os.path.basename(target_filename)
116 # Make a working directory
117 working_dir = tempfile.mkdtemp()
118 # Collect stderr in a file for reporting later
119 stderr_filen = tempfile.NamedTemporaryFile().name
120 # Build the command to run
121 cmd = "build_genomeBG -d %s -g %s -w %s -o %s" % (dbkey,
122 gene_annotation,
123 wig_file,
124 target_filename)
125 print "Running %s" % cmd
126 proc = subprocess.Popen(args=cmd,shell=True,cwd=working_dir,
127 stderr=open(stderr_filen,'wb'))
128 proc.wait()
129 # Copy stderr to stdout
130 with open(stderr_filen,'r') as fp:
131 sys.stdout.write(fp.read())
132 # Update identifier and description
133 if not identifier:
134 identifier = "%s_%s_%s" % (dbkey,
135 gene_annotation,
136 os.path.basename(wig_file))
137 if not description:
138 description = "%s %s from %s" % (dbkey,
139 gene_annotation,
140 os.path.basename(wig_file))
141 # Update the output dictionary
142 data_manager_dict['data_tables']['ceas_annotations'] = {
143 'value': identifier,
144 'dbkey': dbkey,
145 'name': description,
146 'path': os.path.basename(target_filename),
147 }
148 else:
149 raise NotImplementedError("Method '%s' not implemented" % method)
150
151 #save info to json file
152 open(jsonfile,'wb').write(to_json_string(data_manager_dict))
153