File: tawk.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 # tawk [options...] [awk expression...] [files...]
  27 #
  28 #
  29 # Tally via AWK group-counts lines using common results from the `awk`
  30 # expression given. Results are tab-separated lines each with a tally and
  31 # its respective common transformed value, starting with a header line,
  32 # where the data lines are backward-sorted by tally, highest to lowest.
  33 #
  34 # When not given an expression, the default is to use whole lines/records.
  35 # A `.` (no quotes) for the expression also enables the default behavior.
  36 #
  37 # The handy case-insensitive shortcut options may cause this tool to fail,
  38 # if the main `awk` tool installed doesn't support the special `IGNORECASE`
  39 # variable.
  40 #
  41 # The AWK options available only in single-dash versions are
  42 #
  43 #   -F fs, -Ffs, -F=fs    make `fs` the field separator
  44 #
  45 # The other options are, available both in single and double-dash versions
  46 #
  47 #   -h, -help    show this help message
  48 #   -i, -ins     match regexes case-insensitively; may fail `awk`
  49 #   -tsv         split fields using tabs, same as using -F "\t"
  50 
  51 
  52 tsv=0
  53 ins=0
  54 cmd='awk'
  55 
  56 while [ $# -gt 0 ]; do
  57     case "$1" in
  58         -F)
  59             if [ $# -lt 2 ]; then
  60                 printf "%s: expected value after -F option\n" "$0" >&2
  61                 exit 1
  62             fi
  63             cmd="${cmd} -F $2"; shift 2; continue
  64         ;;
  65 
  66         -F*) cmd="${cmd} $1"; shift; continue ;;
  67 
  68         -h|--h|-help|--help)
  69             awk '/^# +tawk /, /^$/ { gsub(/^# ?/, ""); print }' "$0"
  70             exit 0
  71         ;;
  72 
  73         -i|--i|-ins|--ins|-insensitive|--insensitive)
  74             ins=1; shift; continue
  75         ;;
  76 
  77         -tsv|--tsv) tsv=1; shift; continue ;;
  78 
  79         -v)
  80             if [ $# -lt 2 ]; then
  81                 printf "%s: missing variable assignment after -v option\n" \
  82                     "$0" >&2
  83                 exit 1
  84             fi
  85             cmd="${cmd} -v $1"; shift 2; continue
  86         ;;
  87 
  88         -) break ;;
  89 
  90         --) shift; break ;;
  91 
  92         -*)
  93             printf "%s: unsupported option %s\n" "$0" "$1" >&2
  94             exit 1
  95         ;;
  96     esac
  97 
  98     break
  99 done
 100 
 101 code="${1:-\$0}"
 102 [ $# -gt 0 ] && shift
 103 if [ "${code}" = '.' ]; then
 104     code='$0'
 105 fi
 106 
 107 # show all non-existing files given
 108 failed=0
 109 for arg in "$@"; do
 110     [ "${arg}" = '-' ] && continue
 111     [ -e "${arg}" ] && continue
 112     printf "%s: no file named \"%s\"\n" "$0" "${arg}" >&2
 113     failed=1
 114 done
 115 
 116 [ "${failed}" -gt 0 ] && exit 2
 117 
 118 ci='
 119 BEGIN {
 120     if (IGNORECASE == "") {
 121         m = "your `awk` command lacks case-insensitive regex-matching"
 122         print(m) > "/dev/stderr"
 123         exit 125
 124     }
 125     IGNORECASE = 1
 126 }
 127 '
 128 if [ "${ins}" -eq 0 ]; then
 129     ci=''
 130 fi
 131 
 132 src="${ci}"'
 133 {
 134     V = ('"${code}"')
 135     if (!TALLY[V]++) KEYS[++N] = V
 136 }
 137 
 138 END {
 139     for (i = 1; i <= N; i++) {
 140         k = KEYS[i]
 141         printf "%d\t%s\n", TALLY[k], k
 142     }
 143 }
 144 '
 145 
 146 printf "tally\tvalue\n"
 147 if [ "${tsv}" -eq 1 ]; then
 148     ${cmd} -F "\t" "${src}" "$@"
 149 else
 150     ${cmd} "${src}" "$@"
 151 fi | sort -t "$(printf "\t")" -k1,1