File: pcol.sh
   1 #!/bin/sh
   2 
   3 # The MIT License (MIT)
   4 #
   5 # Copyright © 2020-2025 pacman64
   6 #
   7 # Permission is hereby granted, free of charge, to any person obtaining a copy
   8 # of this software and associated documentation files (the “Software”), to deal
   9 # in the Software without restriction, including without limitation the rights
  10 # to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
  11 # copies of the Software, and to permit persons to whom the Software is
  12 # furnished to do so, subject to the following conditions:
  13 #
  14 # The above copyright notice and this permission notice shall be included in
  15 # all copies or substantial portions of the Software.
  16 #
  17 # THE SOFTWARE IS PROVIDED “AS IS”, WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
  18 # IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
  19 # FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
  20 # AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
  21 # LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
  22 # OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
  23 # SOFTWARE.
  24 
  25 
  26 # pcol [column names...]
  27 #
  28 #
  29 # Pick COLumns lets you select/reorder a subset of a table's columns, matching
  30 # the column names given using the first line from the standard input. Input
  31 # lines can be either space-separated or tab-separated; output lines are always
  32 # TSV (Tab-Separated Values) ones, where trailing tabs are added if any values
  33 # are missing.
  34 #
  35 # When a column name isn't matched exactly, a case-insensitive match is tried:
  36 # if the latter also fails, number-matching is finally tried, before giving up
  37 # on that column name. Column numbers start at 1, and can be negative to count
  38 # backward from the last column.
  39 
  40 
  41 case "$1" in
  42     -h|--h|-help|--help)
  43         awk '/^# +pcol /, /^$/ { gsub(/^# ?/, ""); print }' "$0"
  44         exit 0
  45     ;;
  46 esac
  47 
  48 [ "$1" = "--" ] && shift
  49 
  50 command='awk'
  51 if [ -p /dev/stdout ] || [ -t /dev/stdout ]; then
  52     command='stdbuf -oL awk'
  53 fi
  54 
  55 ${command} -F "\t" '
  56     function findcol(name, lowname, i) {
  57         for (i = 1; i <= NF; i++) if (name == $i) return i
  58         for (i = 1; i <= NF; i++) if (lowname == tolower($i)) return i
  59 
  60         if (1 <= name && name <= NF) return name + 0
  61         if (name < 0 && -name <= NF) return NF + name + 1
  62 
  63         return 0
  64     }
  65 
  66     BEGIN {
  67         for (i = 1; i < ARGC; i++) {
  68             colnames[++n] = ARGV[i]
  69             lownames[n] = tolower(ARGV[i])
  70             delete ARGV[i]
  71         }
  72     }
  73 
  74     { gsub(/\r$/, "") }
  75 
  76     FNR == 1 { FS = ($0 ~ /\t/) ? "\t" : " "; $0 = $0 }
  77 
  78     NR == 1 {
  79         for (i = 1; i <= n; i++) {
  80             j = findcol(colnames[i], lownames[i])
  81             if (j > 0) pick[++numcols] = j
  82 
  83             if (j == 0) {
  84                 fmt = "\x1b[31mno column match for \"%s\"\x1b[0m\n"
  85                 printf(fmt, colnames[i]) > "/dev/stderr"
  86                 errors++
  87             }
  88         }
  89 
  90         if (errors > 0) exit 1
  91         if (numcols == 0) exit
  92     }
  93 
  94     {
  95         for (i = 1; i <= numcols; i++) {
  96             if (i > 1) printf "\t"
  97             printf "%s", $(pick[i])
  98         }
  99 
 100         printf "\n"
 101     }
 102 ' "$@"