# unicode examples

##################
# pragmas
##################
# allows UTF-8 in source code
use utf8; 

{
# perl can now use Unicode in utf8 encoding
# directly
$myname = "シメオン";
print "Utf8:\t$myname\n";

# by specifying HEX unicode
$myname = "\x{30B7}\x{30E1}\x{30AA}\x{30F3}"; # same thing
print "Unicode:hex\t$myname\n";

# or by character name using the charnames module
# and full unicode names, as in
use charnames qw(:full);
$myname ="\N{KATAKANA LETTER SI}\N{KATAKANA LETTER ME}\N{KATAKANA LETTER O}\N{KATAKANA LETTER N}";
print "Unicode:names\t$myname\n";

# or short unicode names in the form name:script
use charnames qw(:short);
$myname = "\N{katakana:si}\N{katakana:me}\N{katakana:o}\N{katakana:n}";
print "Or script:name\t$myname\n";
}

# text operators Do The Right Thing
print scalar(reverse $myname), "\n";
print "There are ", scalar split (//, $myname), " chars in $myname \n"; #

#... and so on
# same with text functions

# Many unicode properties and block ranges are supported.
# For all the supported properties, please see 
# lib/unicode/In 
# lib/unicode/Is and 
# lib/unicode/To directories 

#example: matching wide digits
$text = "１２３４５";
print "Saw numbers\n" if $text =~ /\p{IsDigit}/; 

# this does NOT work, though ;)
print +("１" + "２"), "\n"; 

# prints 0; while \d and \p{IsDigit} match digit characters,
# their representation is scalar representation, and not number.  

##################
# allow unicode names in text, and usage of unicode characters
# as identifiers - as in Java
##################

{ 
# charnames seems to break when packages change. Why? 
	$伝票=225;
	伝票印刷($伝票, "\n");
	sub 伝票印刷 {print @_;} 
	package テスト;
	sub テスト {	print "テスト\n";}
	package main;
	&テスト::テスト; # prints テスト
}