File: grawk.sh
   1 #!/bin/sh
   2 
   3 # The MIT License (MIT)
   4 #
   5 # Copyright (c) 2026 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 # grawk [options...] [awk expression...] [files...]
  27 #
  28 #
  29 # GRoup via AWK groups lines using common results of the AWK expression given.
  30 # When not given any, whole lines are used, which effectively puts identical
  31 # lines next to each other.
  32 #
  33 # The handy case-insensitive shortcut options may cause this tool to fail,
  34 # if the main AWK tool installed doesn't support the special IGNORECASE
  35 # variable.
  36 #
  37 # The AWK options available only in single-dash versions are
  38 #
  39 #   -F fs               use `fs` for the field separator (the `FS` variable)
  40 #   -V                  show the AWK version installed
  41 #   -v var=val          set a variable to a given value
  42 #
  43 # The other options are, available both in single and double-dash versions
  44 #
  45 #   -h, -help             show this help message
  46 #   -ins, -insensitive    match regexes case-insensitively; fail if unsupported
  47 #   -tsv                  split fields using tabs, same as using -F "\t"
  48 
  49 
  50 case "$1" in
  51     -h|--h|-help|--help)
  52         awk '/^# +grawk /, /^$/ { gsub(/^# ?/, ""); print }' "$0"
  53         exit 0
  54     ;;
  55 esac
  56 
  57 tsv=0
  58 case_insensitive=0
  59 command='awk'
  60 
  61 while [ $# -gt 0 ]; do
  62     arg="$1"
  63 
  64     if [ "${arg}" = "--" ]; then
  65         shift
  66         break
  67     fi
  68 
  69     case "${arg}" in
  70         -F)
  71             shift
  72             if [ $# -eq 0 ]; then
  73                 printf "expected value after -F option\n" >&2
  74                 exit 1
  75             fi
  76             command="${command} -F $1"
  77             shift
  78             continue
  79         ;;
  80 
  81         -F*)
  82             command="${command} ${arg}"
  83             shift
  84             continue
  85         ;;
  86 
  87         -v)
  88             shift
  89             if [ $# -eq 0 ]; then
  90                 printf "expected variable assignment after -v option\n" >&2
  91                 exit 1
  92             fi
  93             command="${command} -v $1"
  94             shift
  95             continue
  96         ;;
  97 
  98         -ins|--ins|-insensitive|--insensitive)
  99             case_insensitive=1
 100             shift
 101             continue
 102         ;;
 103 
 104         -tsv|--tsv)
 105             tsv=1
 106             shift
 107             continue
 108         ;;
 109 
 110         -*)
 111             command="${command} ${arg}"
 112             shift
 113             continue
 114         ;;
 115     esac
 116 
 117     break
 118 done
 119 
 120 code="${1:-\$0}"
 121 [ $# -gt 0 ] && shift
 122 
 123 # show all non-existing files given
 124 failed=0
 125 for arg in "$@"; do
 126     if [ "${arg}" = "-" ]; then
 127         continue
 128     fi
 129     if [ ! -e "${arg}" ]; then
 130         printf "no file named \"%s\"\n" "${arg}" > /dev/stderr
 131         failed=1
 132     fi
 133 done
 134 
 135 if [ "${failed}" -gt 0 ]; then
 136     exit 2
 137 fi
 138 
 139 ci='
 140     BEGIN {
 141         if (IGNORECASE == "") {
 142             m = "your `awk` command lacks case-insensitive regex-matching"
 143             print(m) > "/dev/stderr"
 144             exit 125
 145         }
 146         IGNORECASE = 1
 147     }
 148 '
 149 if [ "${case_insensitive}" -eq 0 ]; then
 150     ci=''
 151 fi
 152 
 153 src="${ci}"'
 154     BEGIN { if (SUBSEP == "") SUBSEP = "\034" }
 155 
 156     FNR == 1 { FS = /\t/ ? "\t" : " "; $0 = $0 }
 157 
 158     {
 159         k = '"${code}"'
 160         if (tally[k]++ == 0) ordkeys[++numkeys] = k
 161         groups[k SUBSEP tally[k]] = $0
 162     }
 163 
 164     END {
 165         for (i = 1; i <= numkeys; i++) {
 166             k = ordkeys[i]
 167             n = tally[k]
 168             for (j = 1; j <= n; j++) print groups[k SUBSEP j]
 169         }
 170     }
 171 '
 172 
 173 if [ "${tsv}" -eq 1 ]; then
 174     ${command} -F "\t" "${src}" "$@"
 175 else
 176     ${command} "${src}" "$@"
 177 fi