upstream-extended/community/tools/text_processing/column_arrange_by_header/column_arrange.py
1#!/usr/bin/env python
2
3import argparse
4
5parser = argparse.ArgumentParser()
6parser.add_argument("-i", "--input", help="Tabular Input File Name")
7parser.add_argument("-o", "--output", help="Tabular Output File")
8parser.add_argument("-c", "--columns", nargs="+", help="Column Headers to Sort By")
9parser.add_argument(
10 "-d", "--discard", action="store_true", help="Discard remaining columns"
11)
12
13args = parser.parse_args()
14
15with open(args.input) as data:
16 hdr = next(data)
17 columns = hdr.rstrip("\n").split("\t")
18 idx = [columns.index(name) for name in args.columns]
19 if not args.discard:
20 idx += [i for i in range(len(columns)) if i not in idx]
21 rearranged_cols = [columns[i] for i in idx]
22 with open(args.output, "w") as out:
23 out.write("\t".join(rearranged_cols) + "\n")
24 for line in data:
25 columns = line.rstrip("\n").split("\t")
26 rearranged_cols = [columns[i] for i in idx]
27 out.write("\t".join(rearranged_cols) + "\n")