Mercurial > repos > matt-shirley > json_data_source
changeset 5:33fa019735a4
Save extra files path as extra_files, not extra_data. Changed type of dataset for new primary datasets. db_key becomes dbkey. Added example json files.
| author | Matt Shirley <mdshw5@gmail.com> |
|---|---|
| date | Thu, 10 Jul 2014 11:41:54 -0400 |
| parents | 96103d66b7af |
| children | 46b589e9747a |
| files | example.json example.line_sep.json json_data_source.py |
| diffstat | 3 files changed, 32 insertions(+), 4 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/example.json Thu Jul 10 11:41:54 2014 -0400 @@ -0,0 +1,20 @@ +[ {"url":"http://rafalab.jhsph.edu/CGI/model-based-cpg-islands-hg19.txt", + "name":"Rafa CpG islands (human)", + "extension":"bed", + "metadata":{"dbkey":"hg19"}, + "extra_data":[{"url":"http://hgdownload.cse.ucsc.edu/goldenpath/hg19/database/refGene.txt.gz", + "path":"path/to/refGene.txt.gz"}] + }, + {"url":"http://rafalab.jhsph.edu/CGI/model-based-cpg-islands-ce2.txt", + "name":"Rafa CpG islands (ce)", + "extension":"bed", + "metadata":{"dbkey":"ce2"} + }, + {"url":"http://rafalab.jhsph.edu/CGI/model-based-cpg-islands-mm9.txt", + "name":"Rafa CpG islands (mouse)", + "extension":"bed", + "metadata":{"dbkey":"mm9"}, + "extra_data":[{"url":"http://hgdownload.cse.ucsc.edu/goldenpath/mm9/database/refGene.txt.gz", + "path":"path/to/refGene.txt.gz"}] + } +]
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/example.line_sep.json Thu Jul 10 11:41:54 2014 -0400 @@ -0,0 +1,3 @@ +{"name": "Rafa CpG islands (human)", "filename": "/mnt/galaxy/files/000/dataset_125.dat", "ext": "bed", "dataset_id": 125, "extra_files": "/mnt/galaxy/files/000/dataset_125.dat_files", "type": "dataset", "metadata": {"dbkey": "hg19"}} +{"name": "Rafa CpG islands (ce)", "base_dataset_id": 125, "filename": "primary_125_http---rafalab.jhsph.edu-CGI-model-based-cpg-islands-ce2.txt_visible_bed", "ext": "bed", "type": "dataset", "metadata": {"dbkey": "ce2"}} +{"name": "Rafa CpG islands (mouse)", "base_dataset_id": 125, "filename": "primary_125_http---rafalab.jhsph.edu-CGI-model-based-cpg-islands-mm9.txt_visible_bed", "ext": "bed", "extra_files": "primary_125_http---rafalab.jhsph.edu-CGI-model-based-cpg-islands-mm9.txt_visible_bed_files", "type": "dataset", "metadata": {"dbkey": "mm9"}}
--- a/json_data_source.py Wed Jul 02 09:33:03 2014 -0400 +++ b/json_data_source.py Thu Jul 10 11:41:54 2014 -0400 @@ -73,7 +73,7 @@ name = metadata.get( 'name' ), metadata = metadata.get( 'metadata' ) ) if metadata.get( 'extra_data', None ): - meta_dict[ 'extra_data' ] = '_'.join( [ filename, 'files' ] ) + meta_dict[ 'extra_files' ] = '_'.join( [ filename, 'files' ] ) if primary: meta_dict[ 'base_dataset_id' ] = dataset_id else: @@ -96,14 +96,19 @@ filename = ''.join( c in VALID_CHARS and c or '-' for c in filename ) name = construct_multi_filename( hda_id, filename, extension ) target_output_filename = os.path.normpath( '/'.join( [ output_base_path, name ] ) ) + metadata_parameter_file.write( metadata_to_json( dataset_id, query_item, + target_output_filename, + ds_type='new_primary_dataset' + primary=primary) ) else: target_output_filename = output_filename + metadata_parameter_file.write( metadata_to_json( dataset_id, query_item, + target_output_filename, + ds_type='dataset' + primary=primary) ) download_from_query( query_item, target_output_filename ) if extra_data: download_extra_data( extra_data, '_'.join( [ target_output_filename, 'files' ] ) ) - metadata_parameter_file.write( metadata_to_json( dataset_id, query_item, - target_output_filename, - primary=primary) ) return True