File: dtsv.awk
   1 #!/usr/bin/awk -f
   2 
   3 # The MIT License (MIT)
   4 #
   5 # Copyright © 2024 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 BEGIN {
  36     FS = "\t"
  37     for (i = 1; i < ARGC; i++) {
  38         colnames[++n] = ARGV[i]
  39         delete ARGV[i]
  40     }
  41 }
  42 
  43 function findcol(name, lowname, i) {
  44     for (i = 1; i <= NF; i++) {
  45         if (name == $i) return i
  46     }
  47 
  48     for (i = 1; i <= NF; i++) {
  49         if (lowname == tolower($i)) return i
  50     }
  51 
  52     if (1 <= name && name <= NF) return name + 0
  53     if (name < 0 && -name <= NF) return NF + name + 1
  54 
  55     return 0
  56 }
  57 
  58 { gsub(/\r$/, "") }
  59 
  60 NR == 1 {
  61     numcols = NF
  62     for (i = 1; i <= numcols; i++) keep[i] = 1
  63     for (i = 1; i <= n; i++) lownames[i] = tolower(colnames[i])
  64 
  65     colsused = numcols
  66     for (i = 1; i <= numcols; i++) {
  67         j = findcol(colnames[i], lownames[i])
  68         if (j > 0) {
  69             keep[j] = 0
  70             colsused--
  71         }
  72     }
  73 
  74     if (colsused == 0) exit
  75 }
  76 
  77 {
  78     c = 0
  79     for (i = 1; i <= numcols; i++) {
  80         if (keep[i] == 1) {
  81             if (c > 0) printf "\t"
  82             printf "%s", $i
  83             c++
  84         }
  85     }
  86 
  87     printf "\n"
  88     fflush()
  89 }