diff data_manager/fetch_reference_data.py @ 1:5349705442d0 draft

planemo upload

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/data_manager/fetch_reference_data.py	Wed May 03 16:27:19 2017 -0400
@@ -0,0 +1,75 @@
+#!/usr/bin/env python
+# ref: https://galaxyproject.org/admin/tools/data-managers/how-to/define/
+
+import sys
+import os
+import tempfile
+import shutil
+import argparse
+import urllib2
+import tarfile
+
+from galaxy.util.json import from_json_string, to_json_string
+
+CHUNK_SIZE = 2**20 #1mb
+
+def cleanup_before_exit(tmp_dir):
+    if tmp_dir and os.path.exists(tmp_dir):
+        shutil.rmtree(tmp_dir)
+
+def stop_err(msg):
+    sys.stderr.write(msg)
+    sys.exit(1)
+
+def get_reference_id_name(params):
+    genome_id = params['param_dict']['genome_id']
+    genome_name = params['param_dict']['genome_name']
+    return genome_id, genome_name
+
+def download_from_GlimmerHMM(data_manager_dict, params, target_directory, sequence_id, sequence_name ):
+    GlimmerHMM_DOWNLOAD_URL = 'ftp://ccb.jhu.edu/pub/software/glimmerhmm/GlimmerHMM-3.0.4.tar.gz'
+    GlimmerHMM_TRAINED_DIR = os.path.join('GlimmerHMM', 'trained_dir', sequence_id)
+    with tarfile.open('GlimmerHMM-3.0.4.tar', mode='r:*') as tar:
+        subdir = [
+          tarinfo for tarinfo in tar.getmembers()
+          if sequence_id in tarinfo.name
+        ]
+        tar.extractall(members=subdir)
+    glimmerhmm_trained_target_dir = os.path.join(target_directory, sequence_id)
+    shutil.copytree(GlimmerHMM_TRAINED_DIR, glimmerhmm_trained_target_dir)
+    data_table_entry = dict(value=sequence_id, name=sequence_name, path=glimmerhmm_trained_target_dir)
+    _add_data_table_entry(data_manager_dict, data_table_entry)
+
+    cleanup_before_exit(GlimmerHMM_TRAINED_DIR)
+
+def _add_data_table_entry( data_manager_dict, data_table_entry ):
+    data_manager_dict['data_tables'] = data_manager_dict.get( 'data_tables', {} )
+    data_manager_dict['data_tables']['reference_data'] = data_manager_dict['data_tables'].get('reference_data', [])
+    data_manager_dict['data_tables']['reference_data'].append( data_table_entry )
+    return data_manager_dict
+
+REFERENCE_SOURCE_TO_DOWNLOAD = dict(glimmerhmm=download_from_GlimmerHMM)
+
+def main():
+    #Parse Command Line
+    parser = argparse.ArgumentParser()
+    args = parser.parse_args()
+
+    filename = args[0]
+
+    params = from_json_string(open(filename).read())
+    target_directory = params['output_data'][0]['extra_files_path']
+    os.mkdir(target_directory)
+    data_manager_dict = {}
+
+    sequence_id, sequence_name = get_reference_id_name(params)
+
+    #Fetch the FASTA
+    REFERENCE_SOURCE_TO_DOWNLOAD[params['param_dict']['file_path']](data_manager_dict, params, target_directory, sequence_id, sequence_name)
+
+    #save info to json file
+    open(filename, 'wb').write(to_json_string(data_manager_dict))
+
+if __name__ == "__main__":
+    main()
+