comparison tools/blast2go/massage_xml_for_blast2go.py @ 25:242cf17c3bf9 draft default tip

"planemo upload for repository https://github.com/peterjc/galaxy_blast/tree/master/tools/blast2go commit 0c82b9ef284c686cbffd30582d2586e4fb52881e"

24:05eef6b222af

As part of this reformatting, we check for BLASTP or BLASTX output
(otherwise raise an error), and print the query count.

This script is called from my Galaxy wrapper for Blast2GO for pipelines,
available from the Galaxy Tool Shed here:
http://toolshed.g2.bx.psu.edu/view/peterjc/blast2go 

This script is under version control here:
https://github.com/peterjc/galaxy_blast/tree/master/blast2go
"""
import sys
import os

def stop_err(msg, error_level=1):
    """Print error message to stdout and quit with given error level."""
    sys.stderr.write("%s\n" % msg)
    sys.exit(error_level)

def prepare_xml(original_xml, mangled_xml):
    """Reformat BLAST XML to suit Blast2GO.

    Blast2GO can't cope with 1000s of <Iteration> tags within a

    footer = "  </BlastOutput_iterations>\n</BlastOutput>\n"
    header = ""
    while True:
        line = in_handle.readline()
        if not line:
            #No hits?
            stop_err("Problem with XML file?")
        if line.strip() == "<Iteration>":
            break
        header += line

    if "<BlastOutput_program>blastx</BlastOutput_program>" in header:
        print("BLASTX output identified")
    elif "<BlastOutput_program>blastp</BlastOutput_program>" in header:
        print("BLASTP output identified")
    else:
        in_handle.close()
        stop_err("Expect BLASTP or BLASTX output")

    out_handle = open(mangled_xml, "w")
    out_handle.write(header)
    out_handle.write(line)
    count = 1
    while True:
        line = in_handle.readline()
        if not line:
            break
        elif line.strip() == "<Iteration>":
           #Insert footer/header
           out_handle.write(footer)
           out_handle.write(header)
           count += 1
        out_handle.write(line)

    out_handle.close()
    in_handle.close()
    print("Input has %i queries" % count)


if __name__ == "__main__":
    # Run the conversion...
    if len(sys.argv) != 3:
        stop_err("Require two arguments: XML input filename, XML output filename")

    xml_file, out_xml_file = sys.argv[1:]

    if not os.path.isfile(xml_file):
        stop_err("Input BLAST XML file not found: %s" % xml_file)

    prepare_xml(xml_file, out_xml_file)

25:242cf17c3bf9

As part of this reformatting, we check for BLASTP or BLASTX output
(otherwise raise an error), and print the query count.

This script is called from my Galaxy wrapper for Blast2GO for pipelines,
available from the Galaxy Tool Shed here:
http://toolshed.g2.bx.psu.edu/view/peterjc/blast2go

This script is under version control here:
https://github.com/peterjc/galaxy_blast/tree/master/blast2go
"""

import os
import sys


def prepare_xml(original_xml, mangled_xml):
    """Reformat BLAST XML to suit Blast2GO.

    Blast2GO can't cope with 1000s of <Iteration> tags within a

    footer = "  </BlastOutput_iterations>\n</BlastOutput>\n"
    header = ""
    while True:
        line = in_handle.readline()
        if not line:
            # No hits?
            sys.exit("Problem with XML file?")
        if line.strip() == "<Iteration>":
            break
        header += line

    if "<BlastOutput_program>blastx</BlastOutput_program>" in header:
        print("BLASTX output identified")
    elif "<BlastOutput_program>blastp</BlastOutput_program>" in header:
        print("BLASTP output identified")
    else:
        in_handle.close()
        sys.exit("Expect BLASTP or BLASTX output")

    out_handle = open(mangled_xml, "w")
    out_handle.write(header)
    out_handle.write(line)
    count = 1
    while True:
        line = in_handle.readline()
        if not line:
            break
        elif line.strip() == "<Iteration>":
            # Insert footer/header
            out_handle.write(footer)
            out_handle.write(header)
            count += 1
        out_handle.write(line)

    out_handle.close()
    in_handle.close()
    print("Input has %i queries" % count)


if __name__ == "__main__":
    # Run the conversion...
    if len(sys.argv) != 3:
        sys.exit("Require two arguments: XML input filename, XML output filename")

    xml_file, out_xml_file = sys.argv[1:]

    if not os.path.isfile(xml_file):
        sys.exit("Input BLAST XML file not found: %s" % xml_file)

    prepare_xml(xml_file, out_xml_file)