#!/usr/bin/perl

use strict;
use warnings;

my $VERSION = 0.01;

=head1 NAME

test-unicodeprops.pl -- a simple script to get unicode properties of characters.

=head1 DESCRIPTION

This script lets you to test which characters
belongs to available Perl unicode properties.

=head1 COREQUISITES

v5.8.0

=pod OSNAMES

any

=pod SCRIPT CATEGORIES

Unicode

=cut


my @propnames = (
    'IsCc', #	Other, Control
    'IsCf', #	Other, Format
    'IsCn', #	Other, Not assigned
    'IsCo', #	Other, Private Use
    'IsCs', #	Other, Surrogate
    'IsLl', #	Letter, Lowercase
    'IsLm', #	Letter, Modifier
    'IsLo', #	Letter, Other
    'IsLt', #	Letter, Titlecase
    'IsLu', #	Letter, Uppercase
    'IsMc', #	Mark, Combining
    'IsMe', #	Mark, Enclosing
    'IsMn', #	Mark, Nonspacing
    'IsNd', #	Number, Decimal digit
    'IsNl', #	Number, Letter
    'IsNo', #	Number, Other
    'IsPc', #	Punctuation, Connector
    'IsPd', #	Punctuation, Dash
    'IsPe', #	Punctuation, Close
    'IsPf', #	Punctuation, Final quote
    'IsPi', #	Punctuation, Initial quote
    'IsPo', #	Punctuation, Other
    'IsPs', #	Punctuation, Open
    'IsSc', #	Symbol, Currency
    'IsSk', #	Symbol, Modifier
    'IsSm', #	Symbol, Math
    'IsSo', #	Symbol, Other
    'IsZl', #	Separator, Line
    'IsZp', #	Separator, Paragraph
    'IsZs', #	Separator, Space
);

push @propnames, qw(
    InArabic       InCyrillic     InHangulJamo   InMalayalam    InSyriac
    InArmenian     InDevanagari   InHebrew       InMongolian    InTamil
    InArrows       InDingbats     InHiragana     InMyanmar      InTelugu
    InBasicLatin   InEthiopic     InKanbun       InOgham        InThaana
    InBengali      InGeorgian     InKannada      InOriya        InThai
    InBopomofo     InGreek        InKatakana     InRunic        InTibetan
    InBoxDrawing   InGujarati     InKhmer        InSinhala      InYiRadicals
    InCherokee     InGurmukhi     InLao          InSpecials     InYiSyllables

    InAlphabeticPresentationForms         InHalfwidthandFullwidthForms
    InArabicPresentationForms-A           InHangulCompatibilityJamo
    InArabicPresentationForms-B           InHangulSyllables
    InBlockElements                       InHighPrivateUseSurrogates
    InBopomofoExtended                    InHighSurrogates
    InBraillePatterns                     InIdeographicDescriptionCharacters
    InCJKCompatibility                    InIPAExtensions
    InCJKCompatibilityForms               InKangxiRadicals
    InCJKCompatibilityIdeographs          InLatin-1Supplement
    InCJKRadicalsSupplement               InLatinExtended-A
    InCJKSymbolsandPunctuation            InLatinExtended-B
    InCJKUnifiedIdeographs                InLatinExtendedAdditional
    InCJKUnifiedIdeographsExtensionA      InLetterlikeSymbols
    InCombiningDiacriticalMarks           InLowSurrogates
    InCombiningHalfMarks                  InMathematicalOperators
    InMiscellaneousSymbols
    InControlPictures                     InMiscellaneousTechnical
    InCurrencySymbols                     InNumberForms
    InEnclosedAlphanumerics               InOpticalCharacterRecognition
    InEnclosedCJKLettersandMonths
    InGeneralPunctuation                  InSuperscriptsandSubscripts
    InGeometricShapes                     InSmallFormVariants
    InGreekExtended                       InSpacingModifierLetters
) if 0;

push @propnames, qw(
    ASCIIHexDigit
    BidiControl
    Dash
    Deprecated
    Diacritic
    Extender
    HexDigit
    Hyphen
    Ideographic
    IDSBinaryOperator
    IDSTrinaryOperator
    JoinControl
    LogicalOrderException
    NoncharacterCodePoint
    OtherAlphabetic
    OtherDefaultIgnorableCodePoint
    OtherGraphemeExtend
    OtherLowercase
    OtherMath
    OtherUppercase
    QuotationMark
    Radical
    SoftDotted
    TerminalPunctuation
    UnifiedIdeograph
    WhiteSpace
);

my @asciichars = map { chr } 0..127;

for my $prop_name (@propnames) {
    print "$prop_name: ";
    for my $chr (@asciichars) {
	if ($chr =~ m/^\p{$prop_name}$/) {
	    print make_chr_printable( $chr ).' ';
	}
    }
    print "\n";
}

sub make_chr_printable {
    my ($chr) = @_;

    my $code = ord( $chr );
    if ($code <= 32) {
	return "#$code;"
    }
    return $chr;
}