File: match.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 # 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 # Input lines always come from the standard input.
  32 #
  33 # The options are, available both in single and double-dash versions
  34 #
  35 #   -h, -help     show this help message
  36 #   -i, -ins      match regexes case-insensitively
  37 #   -l, -links    add a regex to match HTTP/HTTPS links case-insensitively
  38 
  39 
  40 case "$1" in
  41     -h|--h|-help|--help)
  42         awk '/^# +match /, /^$/ { gsub(/^# ?/, ""); print }' "$0"
  43         exit 0
  44     ;;
  45 esac
  46 
  47 links=0
  48 avoid=0
  49 buffered=0
  50 case_ins=0
  51 
  52 while [ $# -gt 0 ]; do
  53     case "$1" in
  54         -b|--b|-buffered|--buffered)
  55             buffered=1
  56             shift
  57             continue
  58         ;;
  59 
  60         -i|--i|-ins|--ins|-insensitive|--insensitive)
  61             case_ins=1
  62             shift
  63             continue
  64         ;;
  65 
  66         -iv|-vi)
  67             case_ins=1
  68             avoid=1
  69             shift
  70             continue
  71         ;;
  72 
  73         -l|--l|-links|--links)
  74             links=1
  75             shift
  76             continue
  77         ;;
  78 
  79         -v|--v|-inv|--inv|-neg|--neg)
  80             avoid=1
  81             shift
  82             continue
  83         ;;
  84     esac
  85 
  86     break
  87 done
  88 
  89 [ "$1" = '--' ] && shift
  90 
  91 flush=0
  92 if [ "${buffered}" -eq 0 ] && { [ -p /dev/stdout ] || [ -t 1 ]; }; then
  93     flush=1
  94 fi
  95 
  96 re='[Hh][Tt][Tt][Pp][Ss]?://[A-Za-z0-9+_.:%-]+(/[A-Za-z0-9+_.%/,#?&=-]*)*'
  97 
  98 awk -v flush="${flush}" -v ci="${case_ins}" -v add_links="${links}" \
  99     -v links="${re}" -v avoid="${avoid}" '
 100     BEGIN {
 101         if (ci && IGNORECASE == "") {
 102             msg = "this variant of AWK lacks case-insensitive regex-matching"
 103             print(msg) > "/dev/stderr"
 104             exit 125
 105         }
 106         if (ci) IGNORECASE = 1
 107 
 108         for (i = 1; i < ARGC; i++) {
 109             re[i] = ARGV[i]
 110             delete ARGV[i]
 111         }
 112 
 113         n = ARGC - 1
 114         if (add_links) re[++n] = links
 115         if (n == 0) re[++n] = "[^\\r]"
 116     }
 117 
 118     {
 119         plain = $0
 120         gsub(/\x1b\[([0-9]{4,}[A-Za-z])/, "", plain)
 121 
 122         for (i = 1; i <= n; i++) {
 123             if (plain ~ re[i]) {
 124                 if (avoid) next
 125                 print
 126                 if (flush) fflush()
 127                 got++
 128                 next
 129             }
 130         }
 131 
 132         if (avoid) { print; if (flush) fflush() }
 133     }
 134 
 135     END { exit(got == 0) }
 136 ' "$@"