comparison split_file_to_collection.py @ 2:d150ac3d853d draft

"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/split_file_to_collection commit 06ffe450bafa280eee8a4331c9cfc9e1ece7c522"

1:750c1684d47c

updating the parser, and adding a new type option in the Galaxy wrapper
"""
FILETYPES = {'fasta': '^>',
             'fastq': '^@',
             'tabular': '^.*',
             'mgf': '^BEGIN IONS'}


def main():
    ps = parser_cli()

    top = args["top"]
    if top < 0:
        raise ValueError("Number of header lines cannot be negative")

    ftype = args["ftype"]

    if args["ftype"] == "tabular" and args["by"] == "col":
        args["match"] = replace_mapped_chars(args["match"])
        args["sub"] = replace_mapped_chars(args["sub"])
        split_by_column(args, in_file, out_dir, top)

    parser.add_argument('--out_dir', '-o', default=os.getcwd(), help="The output directory", required=True)
    parser.add_argument('--file_names', '-a', help="If not splitting by column, the base name of the new files")
    parser.add_argument('--file_ext', '-e', help="If not splitting by column," +
                                                 " the extension of the new files (without a period)")
    parser.add_argument('--ftype', '-f', help="The type of the file to split", required = True,
        choices=["mgf", "fastq", "fasta", "tabular"])
    parser.add_argument('--by', '-b', help="Split by line or by column (tabular only)",
        default = "row", choices = ["col", "row"])
    parser.add_argument('--top', '-t', type=int, default=0, help="Number of header lines to carry over to new files. " +
                                                                 "(tabular only).")
    parser.add_argument('--rand', '-r', help="Divide records randomly into new files", action='store_true')

    return pattern


def split_by_record(args, in_file, out_dir, top, ftype):
    # get record separator for given filetype
    sep = re.compile(FILETYPES[ftype])

    numnew = args["numnew"]

    # random division
    rand = args["rand"]

2:d150ac3d853d

updating the parser, and adding a new type option in the Galaxy wrapper
"""
FILETYPES = {'fasta': '^>',
             'fastq': '^@',
             'tabular': '^.*',
             'txt': '^.*',
             'mgf': '^BEGIN IONS'}


def main():
    ps = parser_cli()

    top = args["top"]
    if top < 0:
        raise ValueError("Number of header lines cannot be negative")

    ftype = args["ftype"]

    assert ftype != "generic" or args["generic_re"] != None, "--generic_re needs to be given for generic input"

    if args["ftype"] == "tabular" and args["by"] == "col":
        args["match"] = replace_mapped_chars(args["match"])
        args["sub"] = replace_mapped_chars(args["sub"])
        split_by_column(args, in_file, out_dir, top)

    parser.add_argument('--out_dir', '-o', default=os.getcwd(), help="The output directory", required=True)
    parser.add_argument('--file_names', '-a', help="If not splitting by column, the base name of the new files")
    parser.add_argument('--file_ext', '-e', help="If not splitting by column," +
                                                 " the extension of the new files (without a period)")
    parser.add_argument('--ftype', '-f', help="The type of the file to split", required = True,
        choices=["mgf", "fastq", "fasta", "tabular", "txt", "generic"])
    parser.add_argument('--generic_re', '-g', help="Regular expression indicating the start of a new record (only for generic)", required = False)
    parser.add_argument('--by', '-b', help="Split by line or by column (tabular only)",
        default = "row", choices = ["col", "row"])
    parser.add_argument('--top', '-t', type=int, default=0, help="Number of header lines to carry over to new files. " +
                                                                 "(tabular only).")
    parser.add_argument('--rand', '-r', help="Divide records randomly into new files", action='store_true')

    return pattern


def split_by_record(args, in_file, out_dir, top, ftype):
    # get record separator for given filetype
    sep = re.compile(FILETYPES.get(ftype, args["generic_re"]))

    numnew = args["numnew"]

    # random division
    rand = args["rand"]