File: match.sh
   1 #!/bin/sh
   2 
   3 # The MIT License (MIT)
   4 #
   5 # Copyright © 2025 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 # match [options...] [regular expressions...]
  27 #
  28 # Only keep lines which match any of the extended-mode regular expressions
  29 # given. When not given any regex, match non-empty lines by default.
  30 #
  31 # The options are, available both in single and double-dash versions
  32 #
  33 #   -h, -help     show this help message
  34 #   -i, -ins      match regexes case-insensitively
  35 #   -l, -links    add a regex to match HTTP/HTTPS links case-insensitively
  36 
  37 
  38 case "$1" in
  39     -h|--h|-help|--help)
  40         # show help message, using the info-comment from this very script
  41         awk '/^# +match /, /^$/ { gsub(/^# ?/, ""); print }' "$0"
  42         exit 0
  43     ;;
  44 esac
  45 
  46 links=0
  47 case_ins=0
  48 
  49 for arg in "$@"; do
  50     if [ "${arg}" = '--' ]; then
  51         shift
  52         break
  53     fi
  54 
  55     case "${arg}" in
  56         -i|--i|-ins|--ins)
  57             case_ins=1
  58             shift
  59             continue
  60         ;;
  61         -l|--l|-links|--links)
  62             links=1
  63             shift
  64             continue
  65         ;;
  66     esac
  67 
  68     break
  69 done
  70 
  71 command='awk'
  72 if [ -e /usr/bin/gawk ]; then
  73     command='/usr/bin/gawk'
  74 fi
  75 if [ -p /dev/stdout ] || [ -t 1 ]; then
  76     command="stdbuf -oL ${command}"
  77 fi
  78 
  79 re='[Hh][Tt][Tt][Pp][Ss]?://[A-Za-z0-9+_.:%-]+(/[A-Za-z0-9+_.%/,#?&=-]*)*'
  80 
  81 ${command} -v ci="${case_ins}" -v add_links="${links}" -v links="${re}" '
  82     BEGIN {
  83         if (ci && IGNORECASE == "") {
  84             msg = "this variant of AWK lacks case-insensitive regex-matching"
  85             print(msg) > "/dev/stderr"
  86             exit 125
  87         }
  88         if (ci) IGNORECASE = 1
  89 
  90         for (i = 1; i < ARGC; i++) {
  91             re[i] = ARGV[i]
  92             delete ARGV[i]
  93         }
  94 
  95         n = length(re)
  96         if (add_links) re[++n] = links
  97         if (n == 0) re[++n] = "[^\\r]"
  98     }
  99 
 100     {
 101         for (i = 1; i <= n; i++) {
 102             if ($0 ~ re[i]) {
 103                 print
 104                 got++
 105                 next
 106             }
 107         }
 108     }
 109 
 110     END { exit(got == 0) }
 111 ' "$@"