changeset 5:2a4ada1dfc4b draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/data_managers/data_manager_bwa_mem_index_builder commit 8652f36a3a3838dca989426961561e81432acf4f

--- a/data_manager/bwa_mem_index_builder.py	Thu Jan 19 11:48:14 2017 -0500
+++ b/data_manager/bwa_mem_index_builder.py	Tue Apr 04 17:49:24 2017 -0400
@@ -1,26 +1,24 @@
 #!/usr/bin/env python
-#Dan Blankenberg
+# Dan Blankenberg
+from __future__ import print_function
 
-import sys
+import optparse
 import os
-import tempfile
-import optparse
 import subprocess
+import sys
+from json import dumps, loads
 
-from json import loads, dumps
+CHUNK_SIZE = 2**20
+TWO_GB = 2**30 * 2
+DEFAULT_DATA_TABLE_NAME = "bwa_mem_indexes"
 
 
-CHUNK_SIZE = 2**20
-TWO_GB = 2**30*2
-
-DEFAULT_DATA_TABLE_NAME = "bwa_mem_indexes"
-
 def get_id_name( params, dbkey, fasta_description=None):
-    #TODO: ensure sequence_id is unique and does not already appear in location file
+    # TODO: ensure sequence_id is unique and does not already appear in location file
     sequence_id = params['param_dict']['sequence_id']
     if not sequence_id:
         sequence_id = dbkey
-    
+
     sequence_name = params['param_dict']['sequence_name']
     if not sequence_name:
         sequence_name = fasta_description
@@ -28,63 +26,66 @@
             sequence_name = dbkey
     return sequence_id, sequence_name
 
+
 def build_bwa_index( data_manager_dict, fasta_filename, params, target_directory, dbkey, sequence_id, sequence_name, data_table_name=DEFAULT_DATA_TABLE_NAME ):
-    #TODO: allow multiple FASTA input files
-    #tmp_dir = tempfile.mkdtemp( prefix='tmp-data-manager-bwa-index-builder-' )
+    # TODO: allow multiple FASTA input files
     fasta_base_name = os.path.split( fasta_filename )[-1]
     sym_linked_fasta_filename = os.path.join( target_directory, fasta_base_name )
     os.symlink( fasta_filename, sym_linked_fasta_filename )
     if params['param_dict']['index_algorithm'] == 'automatic':
-        if os.stat( fasta_filename ).st_size < TWO_GB: #use 2 GB as cut off for memory vs. max of 2gb database size; this is somewhat arbitrary
+        if os.stat( fasta_filename ).st_size < TWO_GB:  # use 2 GB as cut off for memory vs. max of 2gb database size; this is somewhat arbitrary
             index_algorithm = 'is'
         else:
             index_algorithm = 'bwtsw'
     else:
         index_algorithm = params['param_dict']['index_algorithm']
-    
+
     args = [ 'bwa', 'index', '-a', index_algorithm ]
     args.append( sym_linked_fasta_filename )
     proc = subprocess.Popen( args=args, shell=False, cwd=target_directory )
     return_code = proc.wait()
     if return_code:
-        print >> sys.stderr, "Error building index."
+        print("Error building index.", file=sys.stderr)
         sys.exit( return_code )
     data_table_entry = dict( value=sequence_id, dbkey=dbkey, name=sequence_name, path=fasta_base_name )
     _add_data_table_entry( data_manager_dict, data_table_name, data_table_entry )
 
+
 def _add_data_table_entry( data_manager_dict, data_table_name, data_table_entry ):
     data_manager_dict['data_tables'] = data_manager_dict.get( 'data_tables', {} )
     data_manager_dict['data_tables'][ data_table_name ] = data_manager_dict['data_tables'].get( data_table_name, [] )
     data_manager_dict['data_tables'][ data_table_name ].append( data_table_entry )
     return data_manager_dict
 
+
 def main():
-    #Parse Command Line
     parser = optparse.OptionParser()
     parser.add_option( '-f', '--fasta_filename', dest='fasta_filename', action='store', type="string", default=None, help='fasta_filename' )
     parser.add_option( '-d', '--fasta_dbkey', dest='fasta_dbkey', action='store', type="string", default=None, help='fasta_dbkey' )
     parser.add_option( '-t', '--fasta_description', dest='fasta_description', action='store', type="string", default=None, help='fasta_description' )
     parser.add_option( '-n', '--data_table_name', dest='data_table_name', action='store', type="string", default=None, help='data_table_name' )
     (options, args) = parser.parse_args()
-    
+
     filename = args[0]
-    
+
     params = loads( open( filename ).read() )
     target_directory = params[ 'output_data' ][0]['extra_files_path']
     os.mkdir( target_directory )
     data_manager_dict = {}
-    
+
     dbkey = options.fasta_dbkey
-    
+
     if dbkey in [ None, '', '?' ]:
         raise Exception( '"%s" is not a valid dbkey. You must specify a valid dbkey.' % ( dbkey ) )
-    
+
     sequence_id, sequence_name = get_id_name( params, dbkey=dbkey, fasta_description=options.fasta_description )
-    
-    #build the index
+
+    # build the index
     build_bwa_index( data_manager_dict, options.fasta_filename, params, target_directory, dbkey, sequence_id, sequence_name, data_table_name=options.data_table_name or DEFAULT_DATA_TABLE_NAME )
-    
-    #save info to json file
+
+    # save info to json file
     open( filename, 'wb' ).write( dumps( data_manager_dict ) )
-        
-if __name__ == "__main__": main()
+
+
+if __name__ == "__main__":
+    main()

--- a/data_manager/bwa_mem_index_builder.xml	Thu Jan 19 11:48:14 2017 -0500
+++ b/data_manager/bwa_mem_index_builder.xml	Tue Apr 04 17:49:24 2017 -0400
@@ -3,35 +3,34 @@
     <requirements>
         <requirement type="package" version="0.7.15">bwa</requirement>
     </requirements>
-    <command interpreter="python">bwa_mem_index_builder.py "${out_file}" --fasta_filename "${all_fasta_source.fields.path}" --fasta_dbkey "${all_fasta_source.fields.dbkey}" --fasta_description "${all_fasta_source.fields.name}" --data_table_name "bwa_mem_indexes"</command>
-    <stdio>
-        <exit_code range=":-1" />
-        <exit_code range="1:" />
-    </stdio>
+    <command detect_errors="exit_code"><![CDATA[
+        python '$__tool_directory__/bwa_mem_index_builder.py'
+        '${out_file}'
+        --fasta_filename '${all_fasta_source.fields.path}'
+        --fasta_dbkey '${all_fasta_source.fields.dbkey}'
+        --fasta_description '${all_fasta_source.fields.name}'
+        --data_table_name bwa_mem_indexes
+    ]]></command>
     <inputs>
         <param name="all_fasta_source" type="select" label="Source FASTA Sequence">
             <options from_data_table="all_fasta"/>
         </param>
-        <param type="text" name="sequence_name" value="" label="Name of sequence" />
-        <param type="text" name="sequence_id" value="" label="ID for sequence" />
-        
+        <param name="sequence_name" type="text" value="" label="Name of sequence" />
+        <param name="sequence_id" type="text" value="" label="ID for sequence" />
+
         <param name="index_algorithm" type="select" label="Algorithm for constructing BWT index">
-            <option value="automatic" selected="True" help="2GB cut-off">Guess automatically</option>
-            <option value="is" hel="Small genomes">IS linear-time algorithm</option>
-            <!-- <option value="div">div</option> -->
-            <option value="bwtsw" help="Large genomes">BWT-SW</option>
+            <option value="automatic" selected="true">Guess automatically (2GB cut-off)</option>
+            <option value="is">IS linear-time algorithm (for small genomes)</option>
+            <option value="bwtsw">BWT-SW (for large genomes)</option>
         </param>
-        
     </inputs>
     <outputs>
         <data name="out_file" format="data_manager_json"/>
     </outputs>
 
     <help>
-
 .. class:: infomark
 
-**Notice:** If you leave name, description, or id blank, it will be generated automatically. 
-
+**Notice:** If you leave name, description, or id blank, it will be generated automatically.
     </help>
 </tool>