File: shame512.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 # shame512 [options...] [files/folders...]
  27 #
  28 # Group files by common/same SHA-512 hashes: having the same hash means a high
  29 # chance of having the same contents, even though that's not a guarantee.
  30 #
  31 # Files and folder names can be given together for convenience: folder names
  32 # are searched recursively to find all files, including in any subfolders.
  33 #
  34 # The options are, available both in single and double-dash versions
  35 #
  36 #   -h, -help    show this help message
  37 
  38 
  39 case "$1" in
  40     -h|--h|-help|--help)
  41         awk '/^# +shame512 /, /^$/ { gsub(/^# ?/, ""); print }' "$0"
  42         exit 0
  43     ;;
  44 
  45     -) ;;
  46 
  47     --) shift ;;
  48 
  49     -*)
  50         printf "unsupported option '%s'\n" "$1" >&2
  51         exit 1
  52     ;;
  53 esac
  54 
  55 if [ $# -eq 0 ]; then
  56     awk '/^# +shame512 /, /^$/ { gsub(/^# ?/, ""); print }' "$0" >&2
  57     exit 1
  58 fi
  59 
  60 for arg in "${@:-.}"; do
  61     if [ -f "${arg}" ]; then
  62         printf "%s\n" "${arg}"
  63         continue
  64     fi
  65 
  66     if [ -d "${arg}" ]; then
  67         if echo "${arg}" | grep -q '/$'; then
  68             find "${arg}" -type f
  69         else
  70             find "${arg}/" -type f
  71         fi
  72     fi
  73 done | awk -v ORS='\000' '!names[$0]++' | xargs -0 sha512sum | awk '
  74     BEGIN { if (SUBSEP == "") SUBSEP = "\034" }
  75 
  76     {
  77         hash = $1
  78         name = $0
  79         gsub(/^[^ ]+ *| *\r?$/, "", name)
  80 
  81         if (!(hash in names)) hashes[++nhashes] = hash
  82         names[hash SUBSEP (++nitems[hash])] = name
  83     }
  84 
  85     END {
  86         for (i = 1; i <= nhashes; i++) {
  87             k = hashes[i]
  88             n = nitems[k]
  89 
  90             if (i > 1) print ""
  91             print k
  92             for (j = 1; j <= n; j++) print names[k SUBSEP j]
  93         }
  94     }
  95 '