File: hima.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 # hima [options...] [regexes...]
  27 #
  28 #
  29 # HIlight MAtches ANSI-styles matching regular expressions along lines read
  30 # from the standard input. The regular-expression mode used is a superset of
  31 # the commonly-used "extended-mode".
  32 #
  33 # All ANSI-style sequences from stdin are removed, to avoid messing those up:
  34 # the only ANSI styles left in the output will be from the matches, if any.
  35 #
  36 # Also, multiple matches in a line never overlap: at each step along a line,
  37 # the earliest-starting match among the regexes always wins, as the order
  38 # regexes are given among the arguments never matters.
  39 #
  40 # The options are, available both in single and double-dash versions
  41 #
  42 #     -h, -help      show this help message
  43 #     -f, -filter    filter out (ignore) lines with no matches
  44 #     -i, -ins       match regexes case-insensitively
  45 
  46 
  47 filter=0
  48 buffered=0
  49 case_insensitive=0
  50 
  51 while [ $# -gt 0 ]; do
  52     if [ "$1" = '--' ]; then
  53         shift
  54         break
  55     fi
  56 
  57     case "$1" in
  58         -b|--b|-buffered|--buffered)
  59             buffered=1
  60             shift
  61             continue
  62         ;;
  63 
  64         -f|--f|-filter|--filter)
  65             filter=1
  66             shift
  67             continue
  68         ;;
  69 
  70         -fi|--fi|-if|--if)
  71             filter=1
  72             case_insensitive=1
  73             shift
  74             continue
  75         ;;
  76 
  77         -h|--h|-help|--help)
  78             awk '/^# +hima /, /^$/ { gsub(/^# ?/, ""); print }' "$0"
  79             exit 0
  80         ;;
  81 
  82         -i|--i|-ins|--ins|-insensitive|--insensitive)
  83             case_insensitive=1
  84             shift
  85             continue
  86         ;;
  87     esac
  88 
  89     break
  90 done
  91 
  92 [ "$1" = '--' ] && shift
  93 
  94 flush=0
  95 if [ "${buffered}" -eq 0 ] && { [ -p /dev/stdout ] || [ -t 1 ]; }; then
  96     flush=1
  97 fi
  98 
  99 ci='
 100     BEGIN {
 101         if (IGNORECASE == "") {
 102             m = "your `awk` command lacks case-insensitive regex-matching"
 103             print(m) > "/dev/stderr"
 104             exit 125
 105         }
 106         IGNORECASE = 1
 107     }
 108 '
 109 if [ "${case_insensitive}" -eq 0 ]; then
 110     ci=''
 111 fi
 112 
 113 expr="$(awk '
 114     BEGIN {
 115         for (i = 1; i < ARGC; i++) {
 116             if (i > 1) printf "|"
 117             printf "(%s)", ARGV[i]
 118         }
 119         exit
 120     }
 121 ' "$@")"
 122 
 123 awk -v flush="${flush}" -v expr="${expr}" -v filter="${filter}" "${ci}"'
 124     {
 125         # ignore cursor-movers and style-changers
 126         gsub(/\x1b\[[0-9;]*[A-Za-z]/, "")
 127 
 128         # ignore OSC sequences
 129         gsub(/\x1b\][^\x1b]+\x1b\\/, "")
 130 
 131         if (filter && $0 !~ expr) next
 132 
 133         gsub(expr, "\x1b[7m&\x1b[0m")
 134         print
 135         if (flush) fflush()
 136     }
 137 '