changeset 5:2f926e7d623d draft

planemo upload

--- a/data_manager/fetch_reference_data.py	Wed May 03 16:54:57 2017 -0400
+++ b/data_manager/fetch_reference_data.py	Wed May 03 17:43:57 2017 -0400
@@ -26,30 +26,41 @@
     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:
+def get_url(params):
+    trained_url = params['param_dict']['trained_url']
+    return trained_url
+
+def download_from_GlimmerHMM(data_manager_dict, target_directory, sequence_id, sequence_name, trained_dir):
+    if not trained_dir:
+        trained_dir = 'ftp://ccb.jhu.edu/pub/software/glimmerhmm/GlimmerHMM-3.0.4.tar.gz'
+    #Download trained data, ref: https://dzone.com/articles/how-download-file-python
+    f = urllib2.urlopen(trained_dir)
+    data = f.read()
+    downloadpath = 'tmp'
+    os.mkdir(downloadpath)
+    filepath = os.path.join(downloadpath, 'GlimmerHMM-3.0.4.tar')
+    with open(filepath, 'wb') as code:
+        code.write(data)
+    with tarfile.open(filepath, mode='r:*') as tar:
         subdir = [
           tarinfo for tarinfo in tar.getmembers()
           if sequence_id in tarinfo.name
         ]
         tar.extractall(members=subdir)
+    GlimmerHMM_TRAINED_DIR = os.path.join(downloadpath, 'GlimmerHMM', 'trained_dir', sequence_id)
     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('tmp')
 
-    cleanup_before_exit(GlimmerHMM_TRAINED_DIR)
-
-def _add_data_table_entry( data_manager_dict, data_table_entry ):
+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()
@@ -64,10 +75,9 @@
     data_manager_dict = {}
 
     sequence_id, sequence_name = get_reference_id_name(params)
-
+    trained_dir = get_url(params)
     #Fetch the FASTA
-    REFERENCE_SOURCE_TO_DOWNLOAD[params['param_dict']['trained_dir']](data_manager_dict, params, target_directory, sequence_id, sequence_name)
-
+    download_from_GlimmerHMM(data_manager_dict, target_directory, sequence_id, sequence_name, trained_dir)
     #save info to json file
     open(filename, 'wb').write(to_json_string(data_manager_dict))
 

--- a/data_manager/fetch_reference_data.xml	Wed May 03 16:54:57 2017 -0400
+++ b/data_manager/fetch_reference_data.xml	Wed May 03 17:43:57 2017 -0400
@@ -4,7 +4,7 @@
     <inputs>
         <param name="genome_id" type="text" label="Id of the reference genome" />
         <param name="genome_name" type="text" label="Name of the reference genome" />
-        <param name="trained_dir" type="text" value="" label="Directory of the genome file" />
+        <param name="trained_url" type="text" value="" label="Directory of the genome file" />
     </inputs>
     <outputs>
         <data name="out_file" format="data_manager_json" />