File Coverage

blib/lib/Unicode/CharName.pm

Criterion	Covered	Total	%
statement	37	37	100.0
branch	16	18	88.8
condition	12	15	80.0
subroutine	5	5	100.0
pod	0	2	0.0
total	70	77	90.9

package Unicode::CharName;

=head1 NAME

Unicode::CharName - Look up Unicode character names

=head1 SYNOPSIS

 use Unicode::CharName qw(uname ublock);
 print uname(ord('%')), "\n";
 print ublock(0x0300), "\n";

=head1 DESCRIPTION

This module provide a two functions named uname() and ublock().  The
uname() function will return the Unicode character name for the given
code (a number between 0 and 0x10FFFF).  Unicode character names are
written in upper-case ASCII letters, and are strings like:

  LATIN CAPITAL LETTER A
  LATIN SMALL LETTER A WITH RING ABOVE
  CJK UNIFIED IDEOGRAPH 7C80
  HANGUL SYLLABLE PWILH

The ublock() will return the name of the Unicode
character block that the given character belongs to.

=head1 SEE ALSO

L

=head1 COPYRIGHT

Copyright 1997,2005 Gisle Aas.

This library is free software; you can redistribute it and/or
modify it under the same terms as Perl itself.

Name table extracted from the Unicode 4.1 Character
Database. Copyright (c) 1991-2005 Unicode, Inc. All Rights reserved.

=cut

require Exporter;
@ISA=qw(Exporter);
@EXPORT_OK = qw(uname ublock);
$VERSION = sprintf("%d.%02d", q$Revision: 1.7 $ =~ /(\d+)\.(\d+)/);

use strict;
use vars qw(%JAMO_SHORT_NAME %NAMES @BLOCKS);

sub uname {
    my $code = shift;
    if ($code >= 0x4E00) {
	if ($code <= 0x9FFF || ($code >= 0xF900 && $code <= 0xFAFF)) {
	    # CJK Ideographs
	    return sprintf "CJK UNIFIED IDEOGRAPH %04X", $code;
	} elsif ($code >= 0xD800 && $code <= 0xF8FF) {
	    # Surrogate and private
	    if ($code <= 0xDFFF) {
		return "";
	    } else {
		return "";
	    }
	} elsif ($code >= 0xAC00 && $code <= 0xD7A3) {
	    # Hangul Syllables
	    my $sindex = $code - 0xAC00;
	    my $l = 0x1100 + int($sindex / (21*28));
	    my $v = 0x1161 + int(($sindex % (21*28)) / 28);
	    my $t = 0x11A7 + $sindex % 28;
	    my @s = ($l, $v, $t);
	    pop(@s) if $t == 0x11A7;
	    @s = map {
		$_ = sprintf("%04X", $_);
		$JAMO_SHORT_NAME{$_} || " U+$_ ";
            } @s;
	    return join("", "HANGUL SYLLABLE ", @s)
	}
    }
    _init_names() unless defined %NAMES;
    $NAMES{sprintf("%04X",$code)}
}

sub ublock
{
    my $code = shift;
    # XXX: could use a binary search, but I am too lazy today...
    my $block;
    for $block (@BLOCKS) {
	return $block->[2] if $block->[0] <= $code && $block->[1] >= $code;
    }
    undef;
}

@BLOCKS = (
#  start   end        block name
  [0x0000, 0x007F => 'Basic Latin'],
  [0x0080, 0x00FF => 'Latin-1 Supplement'],
  [0x0100, 0x017F => 'Latin Extended-A'],
  [0x0180, 0x024F => 'Latin Extended-B'],
  [0x0250, 0x02AF => 'IPA Extensions'],
  [0x02B0, 0x02FF => 'Spacing Modifier Letters'],
  [0x0300, 0x036F => 'Combining Diacritical Marks'],
  [0x0370, 0x03FF => 'Greek and Coptic'],
  [0x0400, 0x04FF => 'Cyrillic'],
  [0x0500, 0x052F => 'Cyrillic Supplement'],
  [0x0530, 0x058F => 'Armenian'],
  [0x0590, 0x05FF => 'Hebrew'],
  [0x0600, 0x06FF => 'Arabic'],
  [0x0700, 0x074F => 'Syriac'],
  [0x0750, 0x077F => 'Arabic Supplement'],
  [0x0780, 0x07BF => 'Thaana'],
  [0x0900, 0x097F => 'Devanagari'],
  [0x0980, 0x09FF => 'Bengali'],
  [0x0A00, 0x0A7F => 'Gurmukhi'],
  [0x0A80, 0x0AFF => 'Gujarati'],
  [0x0B00, 0x0B7F => 'Oriya'],
  [0x0B80, 0x0BFF => 'Tamil'],
  [0x0C00, 0x0C7F => 'Telugu'],
  [0x0C80, 0x0CFF => 'Kannada'],
  [0x0D00, 0x0D7F => 'Malayalam'],
  [0x0D80, 0x0DFF => 'Sinhala'],
  [0x0E00, 0x0E7F => 'Thai'],
  [0x0E80, 0x0EFF => 'Lao'],
  [0x0F00, 0x0FFF => 'Tibetan'],
  [0x1000, 0x109F => 'Myanmar'],
  [0x10A0, 0x10FF => 'Georgian'],
  [0x1100, 0x11FF => 'Hangul Jamo'],
  [0x1200, 0x137F => 'Ethiopic'],
  [0x1380, 0x139F => 'Ethiopic Supplement'],
  [0x13A0, 0x13FF => 'Cherokee'],
  [0x1400, 0x167F => 'Unified Canadian Aboriginal Syllabics'],
  [0x1680, 0x169F => 'Ogham'],
  [0x16A0, 0x16FF => 'Runic'],
  [0x1700, 0x171F => 'Tagalog'],
  [0x1720, 0x173F => 'Hanunoo'],
  [0x1740, 0x175F => 'Buhid'],
  [0x1760, 0x177F => 'Tagbanwa'],
  [0x1780, 0x17FF => 'Khmer'],
  [0x1800, 0x18AF => 'Mongolian'],
  [0x1900, 0x194F => 'Limbu'],
  [0x1950, 0x197F => 'Tai Le'],
  [0x1980, 0x19DF => 'New Tai Lue'],
  [0x19E0, 0x19FF => 'Khmer Symbols'],
  [0x1A00, 0x1A1F => 'Buginese'],
  [0x1D00, 0x1D7F => 'Phonetic Extensions'],
  [0x1D80, 0x1DBF => 'Phonetic Extensions Supplement'],
  [0x1DC0, 0x1DFF => 'Combining Diacritical Marks Supplement'],
  [0x1E00, 0x1EFF => 'Latin Extended Additional'],
  [0x1F00, 0x1FFF => 'Greek Extended'],
  [0x2000, 0x206F => 'General Punctuation'],
  [0x2070, 0x209F => 'Superscripts and Subscripts'],
  [0x20A0, 0x20CF => 'Currency Symbols'],
  [0x20D0, 0x20FF => 'Combining Diacritical Marks for Symbols'],
  [0x2100, 0x214F => 'Letterlike Symbols'],
  [0x2150, 0x218F => 'Number Forms'],
  [0x2190, 0x21FF => 'Arrows'],
  [0x2200, 0x22FF => 'Mathematical Operators'],
  [0x2300, 0x23FF => 'Miscellaneous Technical'],
  [0x2400, 0x243F => 'Control Pictures'],
  [0x2440, 0x245F => 'Optical Character Recognition'],
  [0x2460, 0x24FF => 'Enclosed Alphanumerics'],
  [0x2500, 0x257F => 'Box Drawing'],
  [0x2580, 0x259F => 'Block Elements'],
  [0x25A0, 0x25FF => 'Geometric Shapes'],
  [0x2600, 0x26FF => 'Miscellaneous Symbols'],
  [0x2700, 0x27BF => 'Dingbats'],
  [0x27C0, 0x27EF => 'Miscellaneous Mathematical Symbols-A'],
  [0x27F0, 0x27FF => 'Supplemental Arrows-A'],
  [0x2800, 0x28FF => 'Braille Patterns'],
  [0x2900, 0x297F => 'Supplemental Arrows-B'],
  [0x2980, 0x29FF => 'Miscellaneous Mathematical Symbols-B'],
  [0x2A00, 0x2AFF => 'Supplemental Mathematical Operators'],
  [0x2B00, 0x2BFF => 'Miscellaneous Symbols and Arrows'],
  [0x2C00, 0x2C5F => 'Glagolitic'],
  [0x2C80, 0x2CFF => 'Coptic'],
  [0x2D00, 0x2D2F => 'Georgian Supplement'],
  [0x2D30, 0x2D7F => 'Tifinagh'],
  [0x2D80, 0x2DDF => 'Ethiopic Extended'],
  [0x2E00, 0x2E7F => 'Supplemental Punctuation'],
  [0x2E80, 0x2EFF => 'CJK Radicals Supplement'],
  [0x2F00, 0x2FDF => 'Kangxi Radicals'],
  [0x2FF0, 0x2FFF => 'Ideographic Description Characters'],
  [0x3000, 0x303F => 'CJK Symbols and Punctuation'],
  [0x3040, 0x309F => 'Hiragana'],
  [0x30A0, 0x30FF => 'Katakana'],
  [0x3100, 0x312F => 'Bopomofo'],
  [0x3130, 0x318F => 'Hangul Compatibility Jamo'],
  [0x3190, 0x319F => 'Kanbun'],
  [0x31A0, 0x31BF => 'Bopomofo Extended'],
  [0x31C0, 0x31EF => 'CJK Strokes'],
  [0x31F0, 0x31FF => 'Katakana Phonetic Extensions'],
  [0x3200, 0x32FF => 'Enclosed CJK Letters and Months'],
  [0x3300, 0x33FF => 'CJK Compatibility'],
  [0x3400, 0x4DBF => 'CJK Unified Ideographs Extension A'],
  [0x4DC0, 0x4DFF => 'Yijing Hexagram Symbols'],
  [0x4E00, 0x9FFF => 'CJK Unified Ideographs'],
  [0xA000, 0xA48F => 'Yi Syllables'],
  [0xA490, 0xA4CF => 'Yi Radicals'],
  [0xA700, 0xA71F => 'Modifier Tone Letters'],
  [0xA800, 0xA82F => 'Syloti Nagri'],
  [0xAC00, 0xD7AF => 'Hangul Syllables'],
  [0xD800, 0xDB7F => 'High Surrogates'],
  [0xDB80, 0xDBFF => 'High Private Use Surrogates'],
  [0xDC00, 0xDFFF => 'Low Surrogates'],
  [0xE000, 0xF8FF => 'Private Use Area'],
  [0xF900, 0xFAFF => 'CJK Compatibility Ideographs'],
  [0xFB00, 0xFB4F => 'Alphabetic Presentation Forms'],
  [0xFB50, 0xFDFF => 'Arabic Presentation Forms-A'],
  [0xFE00, 0xFE0F => 'Variation Selectors'],
  [0xFE10, 0xFE1F => 'Vertical Forms'],
  [0xFE20, 0xFE2F => 'Combining Half Marks'],
  [0xFE30, 0xFE4F => 'CJK Compatibility Forms'],
  [0xFE50, 0xFE6F => 'Small Form Variants'],
  [0xFE70, 0xFEFF => 'Arabic Presentation Forms-B'],
  [0xFF00, 0xFFEF => 'Halfwidth and Fullwidth Forms'],
  [0xFFF0, 0xFFFF => 'Specials'],
  [0x10000, 0x1007F => 'Linear B Syllabary'],
  [0x10080, 0x100FF => 'Linear B Ideograms'],
  [0x10100, 0x1013F => 'Aegean Numbers'],
  [0x10140, 0x1018F => 'Ancient Greek Numbers'],
  [0x10300, 0x1032F => 'Old Italic'],
  [0x10330, 0x1034F => 'Gothic'],
  [0x10380, 0x1039F => 'Ugaritic'],
  [0x103A0, 0x103DF => 'Old Persian'],
  [0x10400, 0x1044F => 'Deseret'],
  [0x10450, 0x1047F => 'Shavian'],
  [0x10480, 0x104AF => 'Osmanya'],
  [0x10800, 0x1083F => 'Cypriot Syllabary'],
  [0x10A00, 0x10A5F => 'Kharoshthi'],
  [0x1D000, 0x1D0FF => 'Byzantine Musical Symbols'],
  [0x1D100, 0x1D1FF => 'Musical Symbols'],
  [0x1D200, 0x1D24F => 'Ancient Greek Musical Notation'],
  [0x1D300, 0x1D35F => 'Tai Xuan Jing Symbols'],
  [0x1D400, 0x1D7FF => 'Mathematical Alphanumeric Symbols'],
  [0x20000, 0x2A6DF => 'CJK Unified Ideographs Extension B'],
  [0x2F800, 0x2FA1F => 'CJK Compatibility Ideographs Supplement'],
  [0xE0000, 0xE007F => 'Tags'],
  [0xE0100, 0xE01EF => 'Variation Selectors Supplement'],
  [0xF0000, 0xFFFFF => 'Supplementary Private Use Area-A'],
  [0x100000, 0x10FFFF => 'Supplementary Private Use Area-B'],
);

%JAMO_SHORT_NAME = (
    '1100' => 'G',
    '1101' => 'GG',
    '1102' => 'N',
    '1103' => 'D',
    '1104' => 'DD',
    '1105' => 'L',
    '1106' => 'M',
    '1107' => 'B',
    '1108' => 'BB',
    '1109' => 'S',
    '110A' => 'SS',
    '110B' => '',
    '110C' => 'J',
    '110D' => 'JJ',
    '110E' => 'C',
    '110F' => 'K',
    '1110' => 'T',
    '1111' => 'P',
    '1112' => 'H',
    '1161' => 'A',
    '1162' => 'AE',
    '1163' => 'YA',
    '1164' => 'YAE',
    '1165' => 'EO',
    '1166' => 'E',
    '1167' => 'YEO',
    '1168' => 'YE',
    '1169' => 'O',
    '116A' => 'WA',
    '116B' => 'WAE',
    '116C' => 'OE',
    '116D' => 'YO',
    '116E' => 'U',
    '116F' => 'WEO',
    '1170' => 'WE',
    '1171' => 'WI',
    '1172' => 'YU',
    '1173' => 'EU',
    '1174' => 'YI',
    '1175' => 'I',
    '11A8' => 'G',
    '11A9' => 'GG',
    '11AA' => 'GS',
    '11AB' => 'N',
    '11AC' => 'NJ',
    '11AD' => 'NH',
    '11AE' => 'D',
    '11AF' => 'L',
    '11B0' => 'LG',
    '11B1' => 'LM',
    '11B2' => 'LB',
    '11B3' => 'LS',
    '11B4' => 'LT',
    '11B5' => 'LP',
    '11B6' => 'LH',
    '11B7' => 'M',
    '11B8' => 'B',
    '11B9' => 'BS',
    '11BA' => 'S',
    '11BB' => 'SS',
    '11BC' => 'NG',
    '11BD' => 'J',
    '11BE' => 'C',
    '11BF' => 'K',
    '11C0' => 'T',
    '11C1' => 'P',
    '11C2' => 'H',
);

sub _init_names
{
    keys %NAMES = 16351;  # preextent
    local($_);
    while () {
	chop;
	my($code, $name) = split(' ', $_, 2);
	$NAMES{$code} = $name;
    }
    close(DATA);
}

1;


__DATA__