#! /usr/bin/perl -CS

use warnings;
use strict;
use utf8;
use Text::CSV_XS 'csv';
use Symbol;

sub usage {
  print <<\EoF;
Example usage:
  :; echo 'ContrіƄսte𝄞' | od-unicode
====    C      o      n      t      r      і      Ƅ      ս
       43     6f     6e     74     72    0456   0184   057d
====    t      e      𝄞      ␊
       74     65   01d11e   0a
EoF
}

my $junk = <<\EoF;
  0456 : Cyrillic Small Letter Byelorussian-Ukrainian I
  0184 : Latin Capital Letter Tone Six
  057D : Armenian Small Letter Seh
01D11E : MUSICAL SYMBOL G CLEF
EoF

sub read_data {
  my $replace;
  my $csv = Text::CSV_XS->new;
  my $aoa = $csv->getline_all('DATA');
  ####my $NR = 0+$aoa->@*;
  my %replace = ();
  rower: for my $row ($aoa->@*) {
    my $code = $row->[1];
    next rower if $code eq '';
    $replace->{$code} = $row->[6];
  }
  return $replace;
}

main: {
  while (@ARGV) {
    my $arg = shift @ARGV;
    if ($arg eq '-h') {
      usage();
      exit;
    }
    else {
      die "Unrecognized arg '$arg'\n";
    }
  }
  my $replace = read_data;
  my $horiz = 0;
  liner: for (;;) {
    my $line;
    my $nn = read(STDIN, $line, 8);
    last liner if ! $nn;
    my $l1;
    my $l2;
    for my $char (split ('', $line)) {
      my $ord = ord($char);
      my $xchar = $char;
      if (exists $replace->{$ord}) {
        $xchar = $replace->{$ord};
      }
      $l1 .= sprintf "%4s   ", $xchar;
      if ($ord <= 255) {
        $l2 .= sprintf "  %02x   ", $ord;
      } elsif ($ord <= 65535) {
        $l2 .= sprintf " %04x  ", $ord;
      } else {
        $l2 .= sprintf "%06x ", $ord;
      }
    }
    print "==== ", $l1, "\n";
    print "     ", $l2, "\n";
  }
}


__DATA__
0,0,0,NUL,,"U+ 2400",␀,"Symbol For Null"
1,1,1,SOH,,"U+ 2401",␁,"Symbol For Start Of Heading"
2,2,2,STX,,"U+ 2402",␂,"Symbol For Start Of Text"
3,3,3,ETX,,"U+ 2403",␃,"Symbol For End Of Text"
4,4,4,EOT,,"U+ 2404",␄,"Symbol For End Of Transmission"
5,5,5,ENQ,,"U+ 2405",␅,"Symbol For Enquiry"
6,6,6,ACK,,"U+ 2406",␆,"Symbol For Acknowledge"
7,7,7,BEL,,"U+ 2407",␇,"Symbol For Bell"
10,8,8,BS,,"U+ 2408",␈,"Symbol For Backspace"
11,9,9,HT,,"U+ 2409",␉,"Symbol For Horizontal Tabulation"
12,10,0A,LF,,"U+ 240A",␊,"Symbol For Line Feed"
13,11,0B,VT,,"U+ 240B",␋,"Symbol For Vertical Tabulation"
14,12,0C,FF,,"U+ 240C",␌,"Symbol For Form Feed"
15,13,0D,CR,,"U+ 240D",␍,"Symbol For Carriage Return"
16,14,0E,SO,,"U+ 240E",␎,"Symbol For Shift Out"
17,15,0F,SI,,"U+ 240F",␏,"Symbol For Shift In"
20,16,10,DLE,,"U+ 2410",␐,"Symbol For Data Link Escape"
21,17,11,DC1,,"U+ 2411",␑,"Symbol For Device Control One"
22,18,12,DC2,,"U+ 2412",␒,"Symbol For Device Control Two"
23,19,13,DC3,,"U+ 2413",␓,"Symbol For Device Control Three"
24,20,14,DC4,,"U+ 2414",␔,"Symbol For Device Control Four"
25,21,15,NAK,,"U+ 2415",␕,"Symbol For Negative Acknowledge"
26,22,16,SYN,,"U+ 2416",␖,"Symbol For Synchronous Idle"
27,23,17,ETB,,"U+ 2417",␗,"Symbol For End Of Transmission Block"
30,24,18,CAN,,"U+ 2418",␘,"Symbol For Cancel"
31,25,19,EM,,"U+ 2419",␙,"Symbol For End Of Medium"
32,26,1A,SUB,,"U+ 241A",␚,"Symbol For Substitute"
33,27,1B,ESC,,"U+ 241B",␛,"Symbol For Escape"
34,28,1C,FS,,"U+ 241C",␜,"Symbol For File Separator"
35,29,1D,GS,,"U+ 241D",␝,"Symbol For Group Separator"
36,30,1E,RS,,"U+ 241E",␞,"Symbol For Record Separator"
37,31,1F,US,,"U+ 241F",␟,"Symbol For Unit Separator"
,,,,,"U+ 2420",␠,"Symbol For Space"
,,,,,"U+ 2421",␡,"Symbol For Delete"
,,,,,"U+ 2422",␢,"Blank Symbol"
240,160,A0,,,"U+ 2423",␣,"Open Box"
,,,,,"U+ 2424",␤,"Symbol For Newline"
,,,,,"U+ 2425",␥,"Symbol For Delete Form Two"
,,,,,"U+ 2426",␦,"Symbol For Substitute Form Two"