File: links.sh
   1 #!/bin/sh
   2 
   3 # The MIT License (MIT)
   4 #
   5 # Copyright © 2024 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 # links [options...] [files...]
  27 #
  28 # This script finds all web (hyper)links in the input(s) given, specifically
  29 # HTTP/HTTPS links, showing each match on its own output line. It can match
  30 # multiple links on each input line.
  31 #
  32 # The help option is `-h`, `--h`, `-help`, or `--help`.
  33 
  34 
  35 # handle leading options
  36 case "$1" in
  37     -h|--h|-help|--help)
  38         awk '/^# +links/, /^$/ { gsub(/^# ?/, ""); print }' "$0"
  39         exit 0
  40     ;;
  41 esac
  42 
  43 awk '{
  44     # ignore notifications (code 9) and hyperlinks (code 8)
  45     gsub(/\x1b\](8|9);[^\x07]*\x07/, "")
  46     # ignore cursor-movers and style-changers
  47     gsub(/\x1b\[([0-9]*[A-HJKST]|[0-9;]*m)/, "")
  48 
  49     s = $0
  50     while (match(s, /https?:\/\/[A-Za-z0-9+_.:%-]+(\/[A-Za-z0-9+_.%\/,#?&=-]*)*/)) {
  51         print substr(s, RSTART, RLENGTH)
  52         s = substr(s, RSTART + RLENGTH)
  53     }
  54 }' "$@"