# HG changeset patch
# User iuc
# Date 1491343718 14400
# Node ID b31f1fcb203c44014217835edb1d26011da80ee3
# Parent 700f2df51eb0bb87efddf49cc2bc20a6d7aeb213
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/data_managers/data_manager_gatk_picard_index_builder commit 8652f36a3a3838dca989426961561e81432acf4f
diff -r 700f2df51eb0 -r b31f1fcb203c data_manager/data_manager_gatk_picard_index_builder.py
--- a/data_manager/data_manager_gatk_picard_index_builder.py Fri May 08 17:06:38 2015 -0400
+++ b/data_manager/data_manager_gatk_picard_index_builder.py Tue Apr 04 18:08:38 2017 -0400
@@ -11,15 +11,15 @@
import tempfile
CHUNK_SIZE = 2**20
-
DEFAULT_DATA_TABLE_NAME = "fasta_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
@@ -27,6 +27,7 @@
sequence_name = dbkey
return sequence_id, sequence_name
+
def build_picard_index( data_manager_dict, fasta_filename, target_directory, dbkey, sequence_id, sequence_name, jar, data_table_name=DEFAULT_DATA_TABLE_NAME ):
fasta_base_name = os.path.split( fasta_filename )[-1]
gatk_sorted_fasta_filename = os.path.join( target_directory, fasta_base_name )
@@ -41,8 +42,9 @@
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 _run_command( command, target_directory ):
- tmp_stderr = tempfile.NamedTemporaryFile( prefix = "tmp-data-manager-gatk_picard_index_builder-stderr" )
+ tmp_stderr = tempfile.NamedTemporaryFile( prefix="tmp-data-manager-gatk_picard_index_builder-stderr" )
proc = subprocess.Popen( args=command, shell=False, cwd=target_directory, stderr=tmp_stderr.fileno() )
return_code = proc.wait()
if return_code:
@@ -57,12 +59,14 @@
sys.exit( return_code )
tmp_stderr.close()
+
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 _move_and_index_fasta_for_sorting( fasta_filename ):
unsorted_filename = tempfile.NamedTemporaryFile().name
shutil.move( fasta_filename, unsorted_filename )
@@ -77,13 +81,14 @@
line = line.split( None, 1 )[0][1:]
fasta_offsets[ line ] = offset
unsorted_fh.close()
- current_order = map( lambda x: x[1], sorted( map( lambda x: ( x[1], x[0] ), fasta_offsets.items() ) ) )
+ current_order = [x[1] for x in sorted( ( x[1], x[0] ) for x in fasta_offsets.items() )]
return ( unsorted_filename, fasta_offsets, current_order )
+
def _write_sorted_fasta( sorted_names, fasta_offsets, sorted_fasta_filename, unsorted_fasta_filename ):
unsorted_fh = open( unsorted_fasta_filename )
sorted_fh = open( sorted_fasta_filename, 'wb+' )
-
+
for name in sorted_names:
offset = fasta_offsets[ name ]
unsorted_fh.seek( offset )
@@ -96,11 +101,12 @@
unsorted_fh.close()
sorted_fh.close()
+
def _int_to_roman( integer ):
if not isinstance( integer, int ):
- raise TypeError, "expected integer, got %s" % type( integer )
+ raise TypeError("expected integer, got %s" % type( integer ))
if not 0 < integer < 4000:
- raise ValueError, "Argument must be between 1 and 3999, got %s" % str( integer )
+ raise ValueError("Argument must be between 1 and 3999, got %s" % str( integer ))
ints = ( 1000, 900, 500, 400, 100, 90, 50, 40, 10, 9, 5, 4, 1 )
nums = ( 'M', 'CM', 'D', 'CD', 'C', 'XC', 'L', 'XL', 'X', 'IX', 'V', 'IV', 'I' )
result = ""
@@ -110,39 +116,40 @@
integer -= ints[ i ] * count
return result
+
def _sort_fasta_gatk( fasta_filename ):
( unsorted_filename, fasta_offsets, current_order ) = _move_and_index_fasta_for_sorting( fasta_filename )
- sorted_names = map( str, range( 1, 100 ) ) + map( _int_to_roman, range( 1, 100 ) ) + [ 'X', 'Y', 'M' ]
- #detect if we have chrN, or just N
+ sorted_names = list(map( str, range( 1, 100 ) )) + list(map( _int_to_roman, range( 1, 100 ) )) + [ 'X', 'Y', 'M' ]
+ # detect if we have chrN, or just N
has_chr = False
for chrom in sorted_names:
if "chr%s" % chrom in current_order:
has_chr = True
break
-
+
if has_chr:
- sorted_names = map( lambda x: "chr%s" % x, sorted_names)
+ sorted_names = ["chr%s" % x for x in sorted_names]
else:
sorted_names.insert( 0, "MT" )
- sorted_names.extend( map( lambda x: "%s_random" % x, sorted_names ) )
-
+ sorted_names.extend( "%s_random" % x for x in sorted_names )
+
existing_sorted_names = []
for name in sorted_names:
# Append each chromosome only once.
if name in current_order and name not in existing_sorted_names:
existing_sorted_names.append( name )
for name in current_order:
- #TODO: confirm that non-canonical names do not need to be sorted specially
+ # TODO: confirm that non-canonical names do not need to be sorted specially
if name not in existing_sorted_names:
existing_sorted_names.append( name )
-
+
if existing_sorted_names == current_order:
shutil.move( unsorted_filename, fasta_filename )
else:
_write_sorted_fasta( existing_sorted_names, fasta_offsets, fasta_filename, unsorted_filename )
+
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' )
@@ -150,30 +157,32 @@
parser.add_option( '-n', '--data_table_name', dest='data_table_name', action='store', type="string", default=None, help='data_table_name' )
parser.add_option( '-j', '--jar', dest='jar', action='store', type="string", default=None, help='GATK .jar file' )
(options, args) = parser.parse_args()
-
+
filename = args[0]
-
+
params = json.loads( open( filename ).read() )
target_directory = params[ 'output_data' ][0]['extra_files_path']
os.mkdir( target_directory )
data_manager_dict = {}
-
+
if options.fasta_dbkey in [ None, '', '?' ]:
raise Exception( '"%s" is not a valid dbkey. You must specify a valid dbkey.' % ( options.fasta_dbkey ) )
-
+
sequence_id, sequence_name = get_id_name( params, dbkey=options.fasta_dbkey, fasta_description=options.fasta_description )
-
- #build the index
- build_picard_index( data_manager_dict,
- options.fasta_filename,
- target_directory,
- options.fasta_dbkey,
- sequence_id,
- sequence_name,
- options.jar,
+
+ # build the index
+ build_picard_index( data_manager_dict,
+ options.fasta_filename,
+ target_directory,
+ options.fasta_dbkey,
+ sequence_id,
+ sequence_name,
+ options.jar,
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( json.dumps( data_manager_dict ) )
-
-if __name__ == "__main__": main()
+
+
+if __name__ == "__main__":
+ main()
diff -r 700f2df51eb0 -r b31f1fcb203c data_manager/data_manager_gatk_picard_index_builder.xml
--- a/data_manager/data_manager_gatk_picard_index_builder.xml Fri May 08 17:06:38 2015 -0400
+++ b/data_manager/data_manager_gatk_picard_index_builder.xml Tue Apr 04 18:08:38 2017 -0400
@@ -4,30 +4,28 @@
samtools
picard
-
- data_manager_gatk_picard_index_builder.py "${out_file}"
+
+ python '$__tool_directory__/data_manager_gatk_picard_index_builder.py' '${out_file}'
--jar "\$JAVA_JAR_PATH/CreateSequenceDictionary.jar"
- --fasta_filename "${all_fasta_source.fields.path}"
- --fasta_dbkey "${all_fasta_source.fields.dbkey}"
- --fasta_description "${all_fasta_source.fields.name}"
- --data_table_name "gatk_picard_indexes"
+ --fasta_filename '${all_fasta_source.fields.path}'
+ --fasta_dbkey '${all_fasta_source.fields.dbkey}'
+ --fasta_description '${all_fasta_source.fields.name}'
+ --data_table_name gatk_picard_indexes
-
-
+
+
-
.. class:: infomark
**Notice:** If you leave name, description, or id blank, it will be generated automatically.
-