package Regexp::CharProps::Thai;

use 5.008003;
use strict;
use warnings;

require Exporter;

our $VERSION = '1.01';

our @ISA = qw(Exporter);
our @EXPORT_OK = qw(
  InThai InThaiCons InThaiHCons InThaiMCons InThaiLCons InThaiVowel 
  InThaiPreVowel InThaiPostVowel InThaiCompVowel InThaiDigit InThaiTon
+e
  InThaiPunct
);

our %EXPORT_TAGS = ( 'all' => [ @EXPORT_OK ] );

=head1 NAME

Thai -  useful character properties for Unicode Thai

=head1 SYNOPSIS

 use Regexp::CharProps::Thai;

 $char = "...";  # some UTF8 string

 $char =~ /\p{InThaiCons}/;  # match a Thai consonant
 $char =~ /\p{InThaiTone}/;  # match a Thai tone mark


# see description for full set of terms

=head1 DESCRIPTION

This module supplements the Unicode character-class definitions with
special groups relevant to Thai linguistics.  The following classes 
are defined:

=over 4

=item InThai

Matches ALL characters in the Thai unicode code-point range.

=item InThaiCons

Matches Thai consonant letters, leaving out vowels, numerics, tone mar
+ks, etc.

=item InThaiVowel

Matches Thai vowels, including compounded and free-standing vowels.

NOTE: Exceptions here include several of the "consonants" which also s
+erve
as vowels: or-ang, yo-yak, double ro-reua, leut and reut, and wo-wen. 
+ 
These are included as vowels in this grouping to accept the widest pos
+sible 
definition, but cannot with certainty be determined by this to be in u
+se
as actual vowels in the instance of their identification here.

=item InThaiAlpha

Matches only the Thai alphabetic characters (consonants and vowels),
excluding all digits, tone marks, and punctuation marks.

=item InThaiTone

Matches only the Thai tone marks, leaving out all letters,
digits and punctuation marks.

=item InThaiPunct

Matches Thai punctuation characters, not including tone marks,
white space, digits or alphabetic characters, and not including
non-Thai punctuation marks (such as English [.,'"!?] etc.).

=item InThaiCompVowel

Matches only the Thai vowels which are compounded with a Thai consonan
+t,
and matching only the vowel portion of the compounded character.

=item InThaiPreVowel

Matches only the subset of vowels which appear _before_ the consonant 
with which they are associated (though in Thai they are sounded _after
+_ 
said consonant); this excludes all consonant-vowels and does not inclu
+de 
any of the compounded vowels.

=item InThaiPostVowel

Matches only the vowels which appear _after_ the consonant with which
they are associated; this excludes all consonant-vowels and does not 
include any of the compounded vowels.

=item InThaiHCons

Matches high-class Thai consonants.

=item InThaiMCons

Matches middle-class Thai consonants.

=item InThaiLCons

Matches low-class Thai consonants.

=item InThaiDigit

Matches Thai numerical digits only.

=back

=cut


sub InThai {
    return <<'END';
0E01 0E5B
END
}

sub InThaiCons {
    return <<'END';
0E01 0E2E
END
}

sub InThaiVowel {
    return join "\n", 
'0E30 0E45',
'0E47',#Thai semi-tone mark used above gor-gai in Thai "gor" (or)
'0E4D',
'0E22',#Thai consonant yo-yak can also be a vowel (like 'y' in English
+)
'0E2D',#Thai consonant or-ang can also be a vowel
'0E27',#Thai consonant wo-wen is only a vowel following mai han-akat
}


#+Thai::InThaiCons
#+Thai::InThaiVowel
sub InThaiAlpha {
    return <<'END';
0E01 0E2E
0E30 0E45
0E47
0E4D
0E22
0E2D
0E27
END
}

sub InThaiTone {
    return <<'END';
0E48 0E4B
END
}

sub InThaiPunct {
    return <<'END';
0E46
0E4C
0E4E
0E4F
0E5A
0E5B
END
}

sub InThaiCompVowel {
    return join "\n", 
'0E31',#Thai mai han-akat
'0E34',#Thai sara-i
'0E35',#Thai sara-ii
'0E36',#Thai sara-ue
'0E37',#Thai sara-uee
'0E38',#Thai sara-u
'0E39',#Thai sara-uu
'0E3A',#Thai phinthu
'0E47',#Thai semi-tone mark used above gor-gai in Thai "gor" (or)
}

sub InThaiPreVowel {
    return <<'END';
0E40 0E44
END
}

sub InThaiPostVowel {
    return <<'END';
0E45
0E30
0E32
0E33
END
}

sub InThaiHCons { 
    return <<'END';
0E02
0E03
0E09
0E10
0E16
0E1C
0E1D
0E28
0E29
0E2A
0E2B
END
}

sub InThaiMCons {
    return <<'END';
0E01
0E08
0E0E
0E0F
0E14
0E15
0E1A
0E1B
0E2D
END
}

#+Thai::InThaiCons
#-Thai::InThaiHcons
#-Thai::InThaiMCons
sub InThaiLCons {
    return <<'END';
0E04 0E07
0E0A 0E0D
0E11 0E13
0E17 0E19
0E1E 0E27
0E2C
0E2E
END
}

sub InThaiDigit {
    return <<'END';
0E50 0E59
END
}


=head1 AUTHOR

Erik Mundall 

=head1 COPYRIGHT

Copyright (C) 2015 Erik Mundall.  All Rights Reserved.

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

=cut

1;
[download]