Warning

This document is for an old release of Galaxy. You can alternatively view this page in the latest release if it exists or view the top of the latest release's documentation.

Source code for galaxy.datatypes.converters.fastq_to_fqtoc

#!/usr/bin/env python
from __future__ import print_function

import sys

from galaxy.util.checkers import is_gzip


[docs]def main(): """ The format of the file is JSON:: { "sections" : [ { "start" : "x", "end" : "y", "sequences" : "z" }, ... ]} This works only for UNCOMPRESSED fastq files. The Python GzipFile does not provide seekable offsets via tell(), so clients just have to split the slow way """ input_fname = sys.argv[1] if is_gzip(input_fname): print('Conversion is only possible for uncompressed files') sys.exit(1) out_file = open(sys.argv[2], 'w') current_line = 0 sequences = 1000000 lines_per_chunk = 4 * sequences chunk_begin = 0 in_file = open(input_fname) out_file.write('{"sections" : [') for line in in_file: current_line += 1 if 0 == current_line % lines_per_chunk: chunk_end = in_file.tell() out_file.write('{"start":"%s","end":"%s","sequences":"%s"},' % (chunk_begin, chunk_end, sequences)) chunk_begin = chunk_end chunk_end = in_file.tell() out_file.write('{"start":"%s","end":"%s","sequences":"%s"}' % (chunk_begin, chunk_end, (current_line % lines_per_chunk) / 4)) out_file.write(']}\n')
if __name__ == "__main__": main()