File: dtsv.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 # dtsv [column names...]
  27 #
  28 # Drop Tab Separated-Values, ignoring all columns given, and keeping all the
  29 # others. The column names given are matched using the first line from stdin.
  30 # Matching works by first trying exact matching, then by case-insensitive
  31 # matching, when there's no exact match, finally giving up when there's no
  32 # match either way.
  33 
  34 
  35 case "$1" in
  36     -h|--h|-help|--help)
  37         awk '/^# +dtsv /, /^$/ { gsub(/^# ?/, ""); print }' "$0"
  38         exit 0
  39     ;;
  40 esac
  41 
  42 [ "$1" = "--" ] && shift
  43 
  44 command="awk"
  45 if [ -p 1 ] || [ -t 1 ]; then
  46     command="stdbuf -oL awk"
  47 fi
  48 
  49 ${command} -F "\t" '
  50     BEGIN {
  51         for (i = 1; i < ARGC; i++) {
  52             colnames[++n] = ARGV[i]
  53             lownames[n] = tolower(ARGV[i])
  54             delete ARGV[i]
  55         }
  56     }
  57 
  58     function findcol(name, lowname, i) {
  59         for (i = 1; i <= NF; i++) if (name == $i) return i
  60         for (i = 1; i <= NF; i++) if (lowname == tolower($i)) return i
  61 
  62         if (1 <= name && name <= NF) return name + 0
  63         if (name < 0 && -name <= NF) return NF + name + 1
  64 
  65         return 0
  66     }
  67 
  68     { gsub(/\r$/, "") }
  69 
  70     NR == 1 {
  71         numcols = NF
  72         for (i = 1; i <= numcols; i++) keep[i] = 1
  73 
  74         colsused = numcols
  75         for (i = 1; i <= n; i++) {
  76             j = findcol(colnames[i], lownames[i])
  77             if (j > 0) {
  78                 keep[j] = 0
  79                 colsused--
  80             }
  81 
  82             if (j == 0) {
  83                 fmt = "\x1b[31mno column match for \"%s\"\x1b[0m\n"
  84                 printf(fmt, colnames[i]) > "/dev/stderr"
  85                 errors++
  86             }
  87         }
  88 
  89         if (errors > 0) exit 1
  90         if (colsused == 0) exit
  91     }
  92 
  93     {
  94         c = 0
  95         for (i = 1; i <= numcols; i++) {
  96             if (keep[i] == 1) {
  97                 if (c > 0) printf "\t"
  98                 printf "%s", $i
  99                 c++
 100             }
 101         }
 102 
 103         printf "\n"
 104     }
 105 ' "$@"