File: dedup.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 # dedup [options...] [files...]
  27 #
  28 # Deduplicate lines, ensuring each unique input line appears only once on the
  29 # output. Unlike the standard cmd-line app `uniq`, which only works correctly
  30 # when given sorted lines, this tool works correctly without any scrambling.
  31 #
  32 # The options are, available both in single and double-dash versions
  33 #
  34 #   -h, -help    show this help message
  35 #   -i, -ins     compare lines case-insensitively
  36 
  37 
  38 buffered=0
  39 compare='$0'
  40 
  41 while [ $# -gt 0 ]; do
  42     case "$1" in
  43         -b|--b|-buffered|--buffered) buffered=1; shift; continue ;;
  44 
  45         -h|--h|-help|--help)
  46             awk '/^# +dedup /, /^$/ { gsub(/^# ?/, ""); print }' "$0"
  47             exit 0
  48         ;;
  49 
  50         -i|--i|-ins|--ins|-insensitive|--insensitive)
  51             compare='tolower($0)'
  52             shift
  53             continue
  54         ;;
  55 
  56         -) break ;;
  57 
  58         --) shift; break ;;
  59 
  60         -*)
  61             printf "unsupported option '%s'\n" "$1" >&2
  62             exit 1
  63         ;;
  64     esac
  65 
  66     break
  67 done
  68 
  69 # show all non-existing files given
  70 failed=0
  71 for arg in "$@"; do
  72     [ "${arg}" = "-" ] && continue
  73     [ -e "${arg}" ] && continue
  74     printf "no file named \"%s\"\n" "${arg}" >&2
  75     failed=1
  76 done
  77 
  78 [ "${failed}" -gt 0 ] && exit 2
  79 
  80 flush=0
  81 if [ "${buffered}" -eq 0 ] && { [ -p /dev/stdout ] || [ -t 1 ]; }; then
  82     flush=1
  83 fi
  84 
  85 awk -v flush="${flush}" '
  86     BEGIN { for (i = 1; i < ARGC; i++) if (files[ARGV[i]]++) delete ARGV[i] }
  87     !c['"${compare}"']++
  88     flush { fflush() }
  89 ' "$@"