def main(workspace, accessions_files):
headers = [
"project_id", "accession_id", "species", "cell", "label", "readType",
"qualities", "file_location", "dataType", "rnaExtract", "localization",
"lab", "view", "type", "replicate", "file_not_found", "file_size",
"configuration_file"
]
template = '\t'.join(['%s'] * len(headers)) + '\n'
output_file = open(os.path.join(workspace, "files.csv"), "w")
output_file.write('\t'.join(headers) + '\n')
for input_file in accessions_files:
accession_file = open(input_file, 'r')
accessions = parse_accession_file(accession_file)
project_id = os.path.split(os.path.split(input_file)[0])[-1]
files = extract_files(accessions)
for accession_id, item in files:
file_info = utils.file_info(item['file_location'])
output_file.write(
template %
(project_id, accession_id, item.get(
'species', ''), item.get('cell', ''), item.get(
'label', ''), item.get('readType', ''),
item.get('qualities', ''), item.get('file_location', ''),
item.get('dataType', ''), item.get('rnaExtract', ''),
item.get('localization', ''), item.get(
'lab', ''), item.get('view', ''), item.get('type', ''),
item.get('replicate', ''), file_info['file_not_found'],
file_info['file_size'], input_file))
accession_file.close()
output_file.close()
def main(workspace, accessions_files):
headers = ["project_id",
"accession_id",
"species",
"cell",
"label",
"readType",
"qualities",
"file_location",
"dataType",
"rnaExtract",
"localization",
"lab",
"view",
"type",
"replicate",
"file_not_found",
"file_size",
"configuration_file"
]
template = '\t'.join(['%s'] * len(headers)) + '\n'
output_file = open(os.path.join(workspace, "files.csv"), "w")
output_file.write('\t'.join(headers) + '\n')
for input_file in accessions_files:
accession_file = open(input_file, 'r')
accessions = parse_accession_file(accession_file)
project_id = os.path.split(os.path.split(input_file)[0])[-1]
files = extract_files(accessions)
for accession_id, item in files:
file_info = utils.file_info(item['file_location'])
output_file.write(template % (project_id,
accession_id,
item.get('species', ''),
item.get('cell', ''),
item.get('label', ''),
item.get('readType', ''),
item.get('qualities', ''),
item.get('file_location', ''),
item.get('dataType', ''),
item.get('rnaExtract', ''),
item.get('localization', ''),
item.get('lab', ''),
item.get('view', ''),
item.get('type', ''),
item.get('replicate', ''),
file_info['file_not_found'],
file_info['file_size'],
input_file
))
accession_file.close()
output_file.close()
def main(workspace, annotations_file):
headers = ("species", "version", "url", "file_location", "file_not_found",
"file_size")
template = '\t'.join(['%s'] * len(headers)) + '\n'
output_file = open(os.path.join(workspace, "annotations.csv"), "w")
output_file.write(template % headers)
parser = ConfigParser.RawConfigParser()
parser.optionxform = lambda s: s
parser.readfp(annotations_file)
for section in parser.sections():
data = dict(parser.items(section))
data.update(utils.file_info(data['file_location']))
output_file.write(template % tuple([data[h] for h in headers]))
annotations_file.close()
output_file.close()
def main(workspace, genomes_file):
headers = ("species",
"version",
"url",
"file_location",
"file_not_found",
"file_size")
template = '\t'.join(['%s'] * len(headers)) + '\n'
output_file = open(os.path.join(workspace, "genomes.csv"), "w")
output_file.write(template % headers)
parser = ConfigParser.RawConfigParser()
parser.optionxform = lambda s: s
parser.readfp(genomes_file)
for section in parser.sections():
data = dict(parser.items(section))
data.update(utils.file_info(data['file_location']))
output_file.write(template % tuple([data[h] for h in headers]))
genomes_file.close()
output_file.close()
