Mercurial > repos > sanbi-uwc > data_manager_novocraft_index_builder

changeset 14:d053e7b179b5 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/zipho/data_manager_novocraft_index_builder commit 2117346f2705cc3990219e5e99d7feb3f5828b9b
author sanbi-uwc
date Fri, 11 Mar 2016 06:22:15 -0500
parents 7014d5b1a9f4
children 8de1d311afb3
files data_manager/novocraft_index_builder.py data_manager/novocraft_index_builder.xml
diffstat 2 files changed, 12 insertions(+), 10 deletions(-) [+]
line wrap: on
line diff
--- a/data_manager/novocraft_index_builder.py	Tue Mar 08 05:47:18 2016 -0500
+++ b/data_manager/novocraft_index_builder.py	Fri Mar 11 06:22:15 2016 -0500
@@ -30,21 +30,21 @@
             sequence_name = dbkey
     return dbkey, sequence_id, sequence_name
 
-def _make_novocraft_index(data_manager_dict, fasta_filename, target_directory, dbkey, sequence_id, sequence_name, data_table_name=DEFAULT_DATA_TABLE_NAME):
+def _make_novocraft_index(data_manager_dict, fasta_filename, target_directory, dbkey, sequence_id, sequence_name, add_system_module, data_table_name=DEFAULT_DATA_TABLE_NAME):
     if os.path.exists(target_directory) and not os.path.isdir(target_directory):
         print("Output directory path already exists but is not a directory: {}".format(target_directory),
               file=sys.stderr)
     elif not os.path.exists(target_directory):
         os.mkdir(target_directory)
 
-    print(sequence_id)
     nix_file = sequence_id + ".nix"
     index_filename = os.path.join(target_directory, nix_file)
     cmdline_str = 'novoindex {} {}'.format(index_filename, fasta_filename)
     cmdline = shlex.split(cmdline_str)
 
     try:
-        print(cmdline)
+        if add_system_module == 'true':
+            check_call(['module add novoindex'])
         check_call(cmdline)
     except CalledProcessError:
         print("Error building RNA STAR index", file=sys.stderr)
@@ -58,18 +58,18 @@
     data_manager_dict['data_tables'][ data_table_name ].append( data_table_entry )
     return data_manager_dict
 
-def download_from_url( data_manager_dict, params, target_directory, dbkey, sequence_id, sequence_name, data_table_name=DEFAULT_DATA_TABLE_NAME ):
+def download_from_url( data_manager_dict, params, target_directory, dbkey, sequence_id, sequence_name, add_system_module, data_table_name=DEFAULT_DATA_TABLE_NAME ):
     # TODO: we should automatically do decompression here
     urls = filter(bool, map(lambda x: x.strip(), params['param_dict']['reference_source']['user_url'].split('\n')))
     fasta_reader = [urllib2.urlopen(url) for url in urls]
 
-    _make_novocraft_index(data_manager_dict, fasta_reader, target_directory, dbkey, sequence_id, sequence_name, data_table_name)
+    _make_novocraft_index(data_manager_dict, fasta_reader, target_directory, dbkey, sequence_id, sequence_name, data_table_name, add_system_module)
 
-def download_from_history( data_manager_dict, params, target_directory, dbkey, sequence_id, sequence_name, data_table_name=DEFAULT_DATA_TABLE_NAME ):
+def download_from_history( data_manager_dict, params, target_directory, dbkey, sequence_id, sequence_name, add_system_module, data_table_name=DEFAULT_DATA_TABLE_NAME ):
     # TODO: allow multiple FASTA input files
     input_filename = params['param_dict']['reference_source']['input_fasta']
 
-    _make_novocraft_index(data_manager_dict, input_filename, target_directory, dbkey, sequence_id, sequence_name, data_table_name)
+    _make_novocraft_index(data_manager_dict, input_filename, target_directory, dbkey, sequence_id, sequence_name, add_system_module, data_table_name )
 
 REFERENCE_SOURCE_TO_DOWNLOAD = dict(url=download_from_url, history=download_from_history)
 
@@ -78,13 +78,14 @@
     parser.add_argument('output_filename')
     parser.add_argument('--dbkey_description')
     parser.add_argument('--data_table_name', default='novocraft_index')
+    parser.add_argument('--add_system_module', default=False)
     args = parser.parse_args()
 
     filename = args.output_filename
 
     params = loads(open(filename).read())
     target_directory = params['output_data'][0]['extra_files_path']
-    #os.makedirs(target_directory)
+    os.makedirs(target_directory)
     data_manager_dict = {}
 
     dbkey, sequence_id, sequence_name = get_dbkey_id_name(params, dbkey_description=args.dbkey_description)
@@ -94,7 +95,7 @@
 
     # Fetch the FASTA
     REFERENCE_SOURCE_TO_DOWNLOAD[params['param_dict']['reference_source']['reference_source_selector']]\
-        (data_manager_dict, params, target_directory, dbkey, sequence_id, sequence_name, data_table_name=args.data_table_name or DEFAULT_DATA_TABLE_NAME)
+        (data_manager_dict, params, target_directory, dbkey, sequence_id, sequence_name, args.add_system_module, data_table_name=args.data_table_name or DEFAULT_DATA_TABLE_NAME )
 
     open(filename, 'wb').write(dumps( data_manager_dict ))
 
--- a/data_manager/novocraft_index_builder.xml	Tue Mar 08 05:47:18 2016 -0500
+++ b/data_manager/novocraft_index_builder.xml	Fri Mar 11 06:22:15 2016 -0500
@@ -6,7 +6,7 @@
         <exit_code range="1:" />
     </stdio>
     <command interpreter="python">
-        novocraft_index_builder.py "${out_file}" --dbkey_description ${ dbkey.get_display_text() } --data_table_name "novocraft_index"
+        novocraft_index_builder.py "${out_file}" --dbkey_description ${ dbkey.get_display_text() } --data_table_name "novocraft_index" --add_system_module ${add_system_module}
     </command>
     <inputs>
         <param name="dbkey" type="genomebuild" label="DBKEY to assign to data" />
@@ -25,6 +25,7 @@
             <param name="input_fasta" type="data" format="fasta" label="FASTA File" multiple="False" optional="False" />
           </when>
         </conditional>
+        <param name="add_system_module" type="boolean" label="Add a Novo-align system Module" checked="true" truevalue="true" value="false" help="Add novoindex system module"/>
     </inputs>
     <outputs>
         <data name="out_file" format="data_manager_json" />