comparison data_manager/fetch_reference_data.py @ 5:2f926e7d623d draft

planemo upload

4:464d75111b16

def get_reference_id_name(params):
    genome_id = params['param_dict']['genome_id']
    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:
        subdir = [
          tarinfo for tarinfo in tar.getmembers()
          if sequence_id in tarinfo.name
        ]
        tar.extractall(members=subdir)
    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(GlimmerHMM_TRAINED_DIR)

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()
    parser.add_argument('-o', '--out', help='Output file')

    target_directory = params['output_data'][0]['extra_files_path']
    os.mkdir(target_directory)
    data_manager_dict = {}

    sequence_id, sequence_name = get_reference_id_name(params)

    #Fetch the FASTA
    REFERENCE_SOURCE_TO_DOWNLOAD[params['param_dict']['trained_dir']](data_manager_dict, params, target_directory, sequence_id, sequence_name)

    #save info to json file
    open(filename, 'wb').write(to_json_string(data_manager_dict))

if __name__ == "__main__":
    main()

5:2f926e7d623d

def get_reference_id_name(params):
    genome_id = params['param_dict']['genome_id']
    genome_name = params['param_dict']['genome_name']
    return genome_id, genome_name

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')

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

def main():
    #Parse Command Line
    parser = argparse.ArgumentParser()
    parser.add_argument('-o', '--out', help='Output file')

    target_directory = params['output_data'][0]['extra_files_path']
    os.mkdir(target_directory)
    data_manager_dict = {}

    sequence_id, sequence_name = get_reference_id_name(params)
    trained_dir = get_url(params)
    #Fetch the FASTA
    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))

if __name__ == "__main__":
    main()