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