#!/bin/sh -
#
# graphics_utf [options] {character_set}
# graphics_utf [options] {start_utf_hex}[-{end_utf_hex}]
#
# Print UTF characters tables to standard output...
#
# Options:   -n   no formating around charcaters
#            -N   no formating, and no linefeeds either
#
# Character-Sets Known by this script include:
#       ascii, latin, meta, ascii+meta, latin_ext, tolkan, punct, indices,
#       numbers, fractions, roman, arrows, arrows-a, arrows-b, arrows-d,
#       math, mathsup, technical, misc, graphics, dingbats, braile,
#       and asian (big)
#
# For example
#    graphics_utf numbers
#    graphics_utf 0000-0200
#
# Use ImageMagick to magick display in a specific font...
#
#   graphics_utf dingbats |
#     magick -font Mincho -pointsize 24 label:@- x:
#
# Or just magick display using Pango (some chars get re-mapped to emoji)...
#
#   graphics_utf dingbats |
#     pango-view --font=Courier <(cat -) &
#
####
#
# WARNING: Input arguments are NOT tested for correctness.
# This script represents a security risk if used ONLINE.
# I accept no responsiblity for misuse. Use at own risk.
#
# Anthony Thyssen    30 August 2005
#
PROGNAME=`type $0 | awk '{print $3}'`  # search for executable on path
PROGDIR=`dirname $PROGNAME`            # extract directory of program
PROGNAME=`basename $PROGNAME`          # base name of program
Usage() {                              # output the script comments as docs
  echo >&2 "$PROGNAME:" "$@"
  sed >&2 -n '/^###/q; /^#/!q; s/^#//; s/^ //; 3s/^/Usage: /; 2,$ p' \
          "$PROGDIR/$PROGNAME"
  exit 10;
}

FORMAT=normal

while [  $# -gt 0 ]; do
  case "$1" in
  --help|--doc*)      Usage ;;
  -n|--noheaders)     FORMAT=nohead ;;
  -N|--nolinefeeds)   FORMAT= ;;

  --) shift; break ;;    # end of user options
  -*) Usage "Unknown option \"$1\"" ;;
  *)  break ;;           # end of user options

  esac
  shift   # next option
done

case `echo "$1" | tr 'A-Z' 'a-z'` in
ascii)        start=`printf '%d' 0x0020` end=`printf '%d' 0x0080` ;;
ascii+meta)   start=`printf '%d' 0x0020` end=`printf '%d' 0x0100` ;;
latin)        start=`printf '%d' 0x0000` end=`printf '%d' 0x0250` ;;
meta)         start=`printf '%d' 0x00A0` end=`printf '%d' 0x0100` ;;
latin_ext)    start=`printf '%d' 0x1E00` end=`printf '%d' 0x1F00` ;;
runic|tolkan) start=`printf '%d' 0x16A0` end=`printf '%d' 0x1700` ;;
punctuation|\
  punct)      start=`printf '%d' 0x2000` end=`printf '%d' 0x2070` ;;
indices)      start=`printf '%d' 0x2070` end=`printf '%d' 0x20A0` ;;
numbers)      start=`printf '%d' 0x2150` end=`printf '%d' 0x2180` ;;
fractions)    start=`printf '%d' 0x2150` end=`printf '%d' 0x2160` ;;
roman)        start=`printf '%d' 0x2160` end=`printf '%d' 0x2190` ;;
arrows)       start=`printf '%d' 0x2190` end=`printf '%d' 0x2200` ;;
arrows-dingbats|\
  arrows-d)   start=`printf '%d' 0x2790` end=`printf '%d' 0x27C0` ;;
arrows-a)     start=`printf '%d' 0x27F0` end=`printf '%d' 0x2800` ;;
arrows-b)     start=`printf '%d' 0x2900` end=`printf '%d' 0x2980` ;;
math)         start=`printf '%d' 0x2200` end=`printf '%d' 0x2300` ;;
technical)    start=`printf '%d' 0x2300` end=`printf '%d' 0x2400` ;;
graphics)     start=`printf '%d' 0x2500` end=`printf '%d' 0x2600` ;;
miscellaneous|\
  misc)       start=`printf '%d' 0x2600` end=`printf '%d' 0x2700` ;;
dingbats)     start=`printf '%d' 0x2700` end=`printf '%d' 0x2800` ;;
braile)       start=`printf '%d' 0x2800` end=`printf '%d' 0x2900` ;;
mathsup)      start=`printf '%d' 0x2A00` end=`printf '%d' 0x2B00` ;;
asian)        start=`printf '%d' 0x4E00` end=`printf '%d' 0xA000` ;;

[0-9a-fA-F]*-[0-9a-fA-F]*)      # AAAA-BBBB
  start=`expr "$1" : '\(....\)-' `
  start=`printf '%d' 0x$start`
  end=`expr "$1" : '....-\(....\)$' `
  end=`printf '%d' 0x$end`
  ;;

[0-9a-fA-F][0-9a-fA-F][0-9a-fA-F][0-9a-fA-F])   #  AAAA [BBBB]
  start=`printf '%d' 0x${1:-2000}`
  if [ "X$2" = 'X' ]; then
    case "$FORMAT" in
    normal) end=`expr $start + 16 \* 16` ;;
    nohead) end=`expr $start + 16` ;;
    *)      end=`expr $start + 1` ;;
    esac
  else
    end=`printf '%d' 0x$2`
  fi
  ;;

'') # no argument -- standard charcaters
  start=`printf '%d' 0x0020` end=`printf '%d' 0x0080`
  ;;
*)
  Usage
  echo >&2 "Usage: $0 character_set"
  echo >&2 "       $0 start_utf_hex  [end_utf_hex]"
  echo >&2 "Continuing with the 'latin' character_set..."
  echo >&2 ""
  start=`printf '%d' 0x0020` end=`printf '%d' 0x0080`
  ;;
esac

# ------------------------------------------------------------------------

i=$start

[ "$FORMAT" = 'normal' ] &&
   printf '             UTF-8 Characters  %04X to %04X\n'  $start  $end

while [ $i -lt $end ]; do

  if [ "$FORMAT" = 'normal' ]; then
    [  `expr $i % 256` -eq 0 -o $i -eq $start ] &&
      printf "      _0__1__2__3__4__5__6__7__8__9__a__b__c__d__e__f_\n"
    printf "%04X " $i
    #[ $i -lt 32 -o $i -eq 128 -o $i -eq 144 ] &&
  fi
  if [ $i -lt 32 ]; then
    if [ "$FORMAT" = 'normal' ]; then
      printf "       Skipping  Control  Character  Range\n"
    fi
  else
    for j in  0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15; do
      c=`expr $i + $j`
      if [ "$FORMAT" = 'normal' ]; then
        printf "  "
      elif [ $c -ge $end ]; then
        break
      fi
      if [ $i -ge 160 ]; then    # full unicode character
        c=`printf "%04X" $c`
        #env LC_CTYPE=en_AU.utf8 printf "\u$c"
        env LC_CTYPE=en_AU.utf8 \
           perl -e "binmode(STDOUT, ':utf8'); print chr(0x$c)"
      elif [ $i -ge 128 ]; then  # meta-control character
        printf "\xc2\x`printf "%02X" $c`"
      else                       # normal character
        printf "\x`printf "%02X" $c`"
      fi
    done
    [ "$FORMAT" ] && printf "\n"
  fi
  i=`expr $i + 16`

done

# ------------------------------------------------------------------------