2 # $Id: Encode.pm,v 2.17 2006/05/09 17:10:42 dankogai Exp dankogai $
6 our $VERSION = sprintf "%d.%02d", q$Revision: 2.17 $ =~ /(\d+)/g;
9 XSLoader::load( __PACKAGE__, $VERSION );
12 use base qw/Exporter/;
14 # Public, encouraged API is exported by default
17 decode decode_utf8 encode encode_utf8 str2bytes bytes2str
18 encodings find_encoding clone_encoding
21 DIE_ON_ERR WARN_ON_ERR RETURN_ON_ERR LEAVE_SRC
22 PERLQQ HTMLCREF XMLCREF STOP_AT_PARTIAL
25 FB_DEFAULT FB_CROAK FB_QUIET FB_WARN
26 FB_PERLQQ FB_HTMLCREF FB_XMLCREF
30 _utf8_off _utf8_on define_encoding from_to is_16bit is_8bit
31 is_utf8 perlio_ok resolve_alias utf8_downgrade utf8_upgrade
33 @FB_FLAGS, @FB_CONSTS,
37 all => [ @EXPORT, @EXPORT_OK ],
38 fallbacks => [@FB_CONSTS],
39 fallback_all => [ @FB_CONSTS, @FB_FLAGS ],
42 # Documentation moved after __END__ for speed - NI-S
44 our $ON_EBCDIC = ( ord("A") == 193 );
48 # Make a %Encoding package variable to allow a certain amount of cheating
51 require Encode::Config;
52 eval { require Encode::ConfigLocal };
57 if ( @_ and $_[0] eq ":all" ) {
58 %enc = ( %Encoding, %ExtModule );
62 for my $mod ( map { m/::/o ? $_ : "Encode::$_" } @_ ) {
64 for my $enc ( keys %ExtModule ) {
65 $ExtModule{$enc} eq $mod and $enc{$enc} = $mod;
69 return sort { lc $a cmp lc $b }
70 grep { !/^(?:Internal|Unicode|Guess)$/o } keys %enc;
74 my $obj = ref( $_[0] ) ? $_[0] : find_encoding( $_[0] );
75 $obj->can("perlio_ok") and return $obj->perlio_ok();
76 return 0; # safety net
82 $Encoding{$name} = $obj;
84 define_alias( $lc => $obj ) unless $lc eq $name;
87 define_alias( $alias, $obj );
93 my ( $class, $name, $skip_external ) = @_;
95 ref($name) && $name->can('renew') and return $name;
96 exists $Encoding{$name} and return $Encoding{$name};
98 exists $Encoding{$lc} and return $Encoding{$lc};
100 my $oc = $class->find_alias($name);
101 defined($oc) and return $oc;
102 $lc ne $name and $oc = $class->find_alias($lc);
103 defined($oc) and return $oc;
105 unless ($skip_external) {
106 if ( my $mod = $ExtModule{$name} || $ExtModule{$lc} ) {
109 eval { require $mod; };
110 exists $Encoding{$name} and return $Encoding{$name};
116 sub find_encoding($;$) {
117 my ( $name, $skip_external ) = @_;
118 return __PACKAGE__->getEncoding( $name, $skip_external );
121 sub resolve_alias($) {
122 my $obj = find_encoding(shift);
123 defined $obj and return $obj->name;
127 sub clone_encoding($) {
128 my $obj = find_encoding(shift);
130 eval { require Storable };
132 return Storable::dclone($obj);
136 my ( $name, $string, $check ) = @_;
137 return undef unless defined $string;
138 $string .= '' if ref $string; # stringify;
140 my $enc = find_encoding($name);
141 unless ( defined $enc ) {
143 Carp::croak("Unknown encoding '$name'");
145 my $octets = $enc->encode( $string, $check );
146 $_[1] = $string if $check and !( $check & LEAVE_SRC() );
149 *str2bytes = \&encode;
152 my ( $name, $octets, $check ) = @_;
153 return undef unless defined $octets;
154 $octets .= '' if ref $octets;
156 my $enc = find_encoding($name);
157 unless ( defined $enc ) {
159 Carp::croak("Unknown encoding '$name'");
161 my $string = $enc->decode( $octets, $check );
162 $_[1] = $octets if $check and !( $check & LEAVE_SRC() );
165 *bytes2str = \&decode;
168 my ( $string, $from, $to, $check ) = @_;
169 return undef unless defined $string;
171 my $f = find_encoding($from);
172 unless ( defined $f ) {
174 Carp::croak("Unknown encoding '$from'");
176 my $t = find_encoding($to);
177 unless ( defined $t ) {
179 Carp::croak("Unknown encoding '$to'");
181 my $uni = $f->decode($string);
182 $_[0] = $string = $t->encode( $uni, $check );
183 return undef if ( $check && length($uni) );
184 return defined( $_[0] ) ? length($string) : undef;
193 sub decode_utf8($;$) {
194 my ( $str, $check ) = @_;
195 return $str if is_utf8($str);
197 return decode( "utf8", $str, $check );
200 return decode( "utf8", $str );
205 predefine_encodings(1);
208 # This is to restore %Encoding if really needed;
211 sub predefine_encodings {
212 use Encode::Encoding;
213 no warnings 'redefine';
217 # was in Encode::UTF_EBCDIC
218 package Encode::UTF_EBCDIC;
219 push @Encode::UTF_EBCDIC::ISA, 'Encode::Encoding';
221 my ( $obj, $str, $chk ) = @_;
223 for ( my $i = 0 ; $i < length($str) ; $i++ ) {
226 utf8::unicode_to_native( ord( substr( $str, $i, 1 ) ) )
233 my ( $obj, $str, $chk ) = @_;
235 for ( my $i = 0 ; $i < length($str) ; $i++ ) {
238 utf8::native_to_unicode( ord( substr( $str, $i, 1 ) ) )
244 $Encode::Encoding{Unicode} =
245 bless { Name => "UTF_EBCDIC" } => "Encode::UTF_EBCDIC";
249 package Encode::Internal;
250 push @Encode::Internal::ISA, 'Encode::Encoding';
252 my ( $obj, $str, $chk ) = @_;
258 $Encode::Encoding{Unicode} =
259 bless { Name => "Internal" } => "Encode::Internal";
264 # was in Encode::utf8
265 package Encode::utf8;
266 push @Encode::utf8::ISA, 'Encode::Encoding';
270 Encode::DEBUG and warn __PACKAGE__, " XS on";
271 *decode = \&decode_xs;
272 *encode = \&encode_xs;
275 Encode::DEBUG and warn __PACKAGE__, " XS off";
277 my ( $obj, $octets, $chk ) = @_;
278 my $str = Encode::decode_utf8($octets);
279 if ( defined $str ) {
286 my ( $obj, $string, $chk ) = @_;
287 my $octets = Encode::encode_utf8($string);
292 *cat_decode = sub { # ($obj, $dst, $src, $pos, $trm, $chk)
293 # currently ignores $chk
294 my ( $obj, undef, undef, $pos, $trm ) = @_;
295 my ( $rdst, $rsrc, $rpos ) = \@_[ 1, 2, 3 ];
297 if ( ( my $npos = index( $$rsrc, $trm, $pos ) ) >= 0 ) {
299 substr( $$rsrc, $pos, $npos - $pos + length($trm) );
300 $$rpos = $npos + length($trm);
303 $$rdst .= substr( $$rsrc, $pos );
304 $$rpos = length($$rsrc);
307 $Encode::Encoding{utf8} =
308 bless { Name => "utf8" } => "Encode::utf8";
309 $Encode::Encoding{"utf-8-strict"} =
310 bless { Name => "utf-8-strict", strict_utf8 => 1 } =>
321 Encode - character encodings
327 =head2 Table of Contents
329 Encode consists of a collection of modules whose details are too big
330 to fit in one document. This POD itself explains the top-level APIs
331 and general topics at a glance. For other topics and more details,
335 --------------------------------------------------------
336 Encode::Alias Alias definitions to encodings
337 Encode::Encoding Encode Implementation Base Class
338 Encode::Supported List of Supported Encodings
339 Encode::CN Simplified Chinese Encodings
340 Encode::JP Japanese Encodings
341 Encode::KR Korean Encodings
342 Encode::TW Traditional Chinese Encodings
343 --------------------------------------------------------
347 The C<Encode> module provides the interfaces between Perl's strings
348 and the rest of the system. Perl strings are sequences of
351 The repertoire of characters that Perl can represent is at least that
352 defined by the Unicode Consortium. On most platforms the ordinal
353 values of the characters (as returned by C<ord(ch)>) is the "Unicode
354 codepoint" for the character (the exceptions are those platforms where
355 the legacy encoding is some variant of EBCDIC rather than a super-set
356 of ASCII - see L<perlebcdic>).
358 Traditionally, computer data has been moved around in 8-bit chunks
359 often called "bytes". These chunks are also known as "octets" in
360 networking standards. Perl is widely used to manipulate data of many
361 types - not only strings of characters representing human or computer
362 languages but also "binary" data being the machine's representation of
363 numbers, pixels in an image - or just about anything.
365 When Perl is processing "binary data", the programmer wants Perl to
366 process "sequences of bytes". This is not a problem for Perl - as a
367 byte has 256 possible values, it easily fits in Perl's much larger
376 I<character>: a character in the range 0..(2**32-1) (or more).
377 (What Perl's strings are made of.)
381 I<byte>: a character in the range 0..255
382 (A special case of a Perl character.)
386 I<octet>: 8 bits of data, with ordinal values 0..255
387 (Term for bytes passed to or from a non-Perl context, e.g. a disk file.)
391 =head1 PERL ENCODING API
395 =item $octets = encode(ENCODING, $string [, CHECK])
397 Encodes a string from Perl's internal form into I<ENCODING> and returns
398 a sequence of octets. ENCODING can be either a canonical name or
399 an alias. For encoding names and aliases, see L</"Defining Aliases">.
400 For CHECK, see L</"Handling Malformed Data">.
402 For example, to convert a string from Perl's internal format to
403 iso-8859-1 (also known as Latin1),
405 $octets = encode("iso-8859-1", $string);
407 B<CAVEAT>: When you run C<$octets = encode("utf8", $string)>, then $octets
408 B<may not be equal to> $string. Though they both contain the same data, the utf8 flag
409 for $octets is B<always> off. When you encode anything, utf8 flag of
410 the result is always off, even when it contains completely valid utf8
411 string. See L</"The UTF-8 flag"> below.
413 If the $string is C<undef> then C<undef> is returned.
415 =item $string = decode(ENCODING, $octets [, CHECK])
417 Decodes a sequence of octets assumed to be in I<ENCODING> into Perl's
418 internal form and returns the resulting string. As in encode(),
419 ENCODING can be either a canonical name or an alias. For encoding names
420 and aliases, see L</"Defining Aliases">. For CHECK, see
421 L</"Handling Malformed Data">.
423 For example, to convert ISO-8859-1 data to a string in Perl's internal format:
425 $string = decode("iso-8859-1", $octets);
427 B<CAVEAT>: When you run C<$string = decode("utf8", $octets)>, then $string
428 B<may not be equal to> $octets. Though they both contain the same data,
429 the utf8 flag for $string is on unless $octets entirely consists of
430 ASCII data (or EBCDIC on EBCDIC machines). See L</"The UTF-8 flag">
433 If the $string is C<undef> then C<undef> is returned.
435 =item [$length =] from_to($octets, FROM_ENC, TO_ENC [, CHECK])
437 Converts B<in-place> data between two encodings. The data in $octets
438 must be encoded as octets and not as characters in Perl's internal
439 format. For example, to convert ISO-8859-1 data to Microsoft's CP1250
442 from_to($octets, "iso-8859-1", "cp1250");
444 and to convert it back:
446 from_to($octets, "cp1250", "iso-8859-1");
448 Note that because the conversion happens in place, the data to be
449 converted cannot be a string constant; it must be a scalar variable.
451 from_to() returns the length of the converted string in octets on
452 success, I<undef> on error.
454 B<CAVEAT>: The following operations look the same but are not quite so;
456 from_to($data, "iso-8859-1", "utf8"); #1
457 $data = decode("iso-8859-1", $data); #2
459 Both #1 and #2 make $data consist of a completely valid UTF-8 string
460 but only #2 turns utf8 flag on. #1 is equivalent to
462 $data = encode("utf8", decode("iso-8859-1", $data));
464 See L</"The UTF-8 flag"> below.
466 =item $octets = encode_utf8($string);
468 Equivalent to C<$octets = encode("utf8", $string);> The characters
469 that comprise $string are encoded in Perl's internal format and the
470 result is returned as a sequence of octets. All possible
471 characters have a UTF-8 representation so this function cannot fail.
474 =item $string = decode_utf8($octets [, CHECK]);
476 equivalent to C<$string = decode("utf8", $octets [, CHECK])>.
477 The sequence of octets represented by
478 $octets is decoded from UTF-8 into a sequence of logical
479 characters. Not all sequences of octets form valid UTF-8 encodings, so
480 it is possible for this call to fail. For CHECK, see
481 L</"Handling Malformed Data">.
485 =head2 Listing available encodings
488 @list = Encode->encodings();
490 Returns a list of the canonical names of the available encodings that
491 are loaded. To get a list of all available encodings including the
492 ones that are not loaded yet, say
494 @all_encodings = Encode->encodings(":all");
496 Or you can give the name of a specific module.
498 @with_jp = Encode->encodings("Encode::JP");
500 When "::" is not in the name, "Encode::" is assumed.
502 @ebcdic = Encode->encodings("EBCDIC");
504 To find out in detail which encodings are supported by this package,
505 see L<Encode::Supported>.
507 =head2 Defining Aliases
509 To add a new alias to a given encoding, use:
513 define_alias(newName => ENCODING);
515 After that, newName can be used as an alias for ENCODING.
516 ENCODING may be either the name of an encoding or an
519 But before you do so, make sure the alias is nonexistent with
520 C<resolve_alias()>, which returns the canonical name thereof.
523 Encode::resolve_alias("latin1") eq "iso-8859-1" # true
524 Encode::resolve_alias("iso-8859-12") # false; nonexistent
525 Encode::resolve_alias($name) eq $name # true if $name is canonical
527 resolve_alias() does not need C<use Encode::Alias>; it can be
528 exported via C<use Encode qw(resolve_alias)>.
530 See L<Encode::Alias> for details.
532 =head1 Encoding via PerlIO
534 If your perl supports I<PerlIO> (which is the default), you can use a PerlIO layer to decode
535 and encode directly via a filehandle. The following two examples
536 are totally identical in their functionality.
539 open my $in, "<:encoding(shiftjis)", $infile or die;
540 open my $out, ">:encoding(euc-jp)", $outfile or die;
541 while(<$in>){ print $out $_; }
544 open my $in, "<", $infile or die;
545 open my $out, ">", $outfile or die;
547 from_to($_, "shiftjis", "euc-jp", 1);
551 Unfortunately, it may be that encodings are PerlIO-savvy. You can check
552 if your encoding is supported by PerlIO by calling the C<perlio_ok>
555 Encode::perlio_ok("hz"); # False
556 find_encoding("euc-cn")->perlio_ok; # True where PerlIO is available
558 use Encode qw(perlio_ok); # exported upon request
561 Fortunately, all encodings that come with Encode core are PerlIO-savvy
562 except for hz and ISO-2022-kr. For gory details, see
563 L<Encode::Encoding> and L<Encode::PerlIO>.
565 =head1 Handling Malformed Data
567 The optional I<CHECK> argument tells Encode what to do when it
568 encounters malformed data. Without CHECK, Encode::FB_DEFAULT ( == 0 )
571 As of version 2.12 Encode supports coderef values for CHECK. See below.
575 =item B<NOTE:> Not all encoding support this feature
577 Some encodings ignore I<CHECK> argument. For example,
578 L<Encode::Unicode> ignores I<CHECK> and it always croaks on error.
582 Now here is the list of I<CHECK> values available
586 =item I<CHECK> = Encode::FB_DEFAULT ( == 0)
588 If I<CHECK> is 0, (en|de)code will put a I<substitution character> in
589 place of a malformed character. When you encode, E<lt>subcharE<gt>
590 will be used. When you decode the code point C<0xFFFD> is used. If
591 the data is supposed to be UTF-8, an optional lexical warning
592 (category utf8) is given.
594 =item I<CHECK> = Encode::FB_CROAK ( == 1)
596 If I<CHECK> is 1, methods will die on error immediately with an error
597 message. Therefore, when I<CHECK> is set to 1, you should trap the
598 error with eval{} unless you really want to let it die.
600 =item I<CHECK> = Encode::FB_QUIET
602 If I<CHECK> is set to Encode::FB_QUIET, (en|de)code will immediately
603 return the portion of the data that has been processed so far when an
604 error occurs. The data argument will be overwritten with everything
605 after that point (that is, the unprocessed part of data). This is
606 handy when you have to call decode repeatedly in the case where your
607 source data may contain partial multi-byte character sequences,
608 (i.e. you are reading with a fixed-width buffer). Here is a sample
609 code that does exactly this:
611 my $buffer = ''; my $string = '';
612 while(read $fh, $buffer, 256, length($buffer)){
613 $string .= decode($encoding, $buffer, Encode::FB_QUIET);
614 # $buffer now contains the unprocessed partial character
617 =item I<CHECK> = Encode::FB_WARN
619 This is the same as above, except that it warns on error. Handy when
620 you are debugging the mode above.
622 =item perlqq mode (I<CHECK> = Encode::FB_PERLQQ)
624 =item HTML charref mode (I<CHECK> = Encode::FB_HTMLCREF)
626 =item XML charref mode (I<CHECK> = Encode::FB_XMLCREF)
628 For encodings that are implemented by Encode::XS, CHECK ==
629 Encode::FB_PERLQQ turns (en|de)code into C<perlqq> fallback mode.
631 When you decode, C<\xI<HH>> will be inserted for a malformed character,
632 where I<HH> is the hex representation of the octet that could not be
633 decoded to utf8. And when you encode, C<\x{I<HHHH>}> will be inserted,
634 where I<HHHH> is the Unicode ID of the character that cannot be found
635 in the character repertoire of the encoding.
637 HTML/XML character reference modes are about the same, in place of
638 C<\x{I<HHHH>}>, HTML uses C<&#I<NNN>;> where I<NNN> is a decimal number and
639 XML uses C<&#xI<HHHH>;> where I<HHHH> is the hexadecimal number.
641 In Encode 2.10 or later, C<LEAVE_SRC> is also implied.
645 These modes are actually set via a bitmask. Here is how the FB_XX
646 constants are laid out. You can import the FB_XX constants via
647 C<use Encode qw(:fallbacks)>; you can import the generic bitmask
648 constants via C<use Encode qw(:fallback_all)>.
650 FB_DEFAULT FB_CROAK FB_QUIET FB_WARN FB_PERLQQ
653 RETURN_ON_ERR 0x0004 X X
661 =head2 coderef for CHECK
663 As of Encode 2.12 CHECK can also be a code reference which takes the
664 ord value of unmapped caharacter as an argument and returns a string
665 that represents the fallback character. For instance,
667 $ascii = encode("ascii", $utf8, sub{ sprintf "<U+%04X>", shift });
669 Acts like FB_PERLQQ but E<lt>U+I<XXXX>E<gt> is used instead of
672 =head1 Defining Encodings
674 To define a new encoding, use:
676 use Encode qw(define_encoding);
677 define_encoding($object, 'canonicalName' [, alias...]);
679 I<canonicalName> will be associated with I<$object>. The object
680 should provide the interface described in L<Encode::Encoding>.
681 If more than two arguments are provided then additional
682 arguments are taken as aliases for I<$object>.
684 See L<Encode::Encoding> for more details.
686 =head1 The UTF-8 flag
688 Before the introduction of utf8 support in perl, The C<eq> operator
689 just compared the strings represented by two scalars. Beginning with
690 perl 5.8, C<eq> compares two strings with simultaneous consideration
691 of I<the utf8 flag>. To explain why we made it so, I will quote page
692 402 of C<Programming Perl, 3rd ed.>
698 Old byte-oriented programs should not spontaneously break on the old
699 byte-oriented data they used to work on.
703 Old byte-oriented programs should magically start working on the new
704 character-oriented data when appropriate.
708 Programs should run just as fast in the new character-oriented mode
709 as in the old byte-oriented mode.
713 Perl should remain one language, rather than forking into a
714 byte-oriented Perl and a character-oriented Perl.
718 Back when C<Programming Perl, 3rd ed.> was written, not even Perl 5.6.0
719 was born and many features documented in the book remained
720 unimplemented for a long time. Perl 5.8 corrected this and the introduction
721 of the UTF-8 flag is one of them. You can think of this perl notion as of a
722 byte-oriented mode (utf8 flag off) and a character-oriented mode (utf8
725 Here is how Encode takes care of the utf8 flag.
731 When you encode, the resulting utf8 flag is always off.
735 When you decode, the resulting utf8 flag is on unless you can
736 unambiguously represent data. Here is the definition of
739 After C<$utf8 = decode('foo', $octet);>,
741 When $octet is... The utf8 flag in $utf8 is
742 ---------------------------------------------
743 In ASCII only (or EBCDIC only) OFF
745 In any other Encoding ON
746 ---------------------------------------------
748 As you see, there is one exception, In ASCII. That way you can assume
749 Goal #1. And with Encode Goal #2 is assumed but you still have to be
750 careful in such cases mentioned in B<CAVEAT> paragraphs.
752 This utf8 flag is not visible in perl scripts, exactly for the same
753 reason you cannot (or you I<don't have to>) see if a scalar contains a
754 string, integer, or floating point number. But you can still peek
755 and poke these if you will. See the section below.
759 =head2 Messing with Perl's Internals
761 The following API uses parts of Perl's internals in the current
762 implementation. As such, they are efficient but may change.
766 =item is_utf8(STRING [, CHECK])
768 [INTERNAL] Tests whether the UTF-8 flag is turned on in the STRING.
769 If CHECK is true, also checks the data in STRING for being well-formed
770 UTF-8. Returns true if successful, false otherwise.
772 As of perl 5.8.1, L<utf8> also has utf8::is_utf8().
774 =item _utf8_on(STRING)
776 [INTERNAL] Turns on the UTF-8 flag in STRING. The data in STRING is
777 B<not> checked for being well-formed UTF-8. Do not use unless you
778 B<know> that the STRING is well-formed UTF-8. Returns the previous
779 state of the UTF-8 flag (so please don't treat the return value as
780 indicating success or failure), or C<undef> if STRING is not a string.
782 =item _utf8_off(STRING)
784 [INTERNAL] Turns off the UTF-8 flag in STRING. Do not use frivolously.
785 Returns the previous state of the UTF-8 flag (so please don't treat the
786 return value as indicating success or failure), or C<undef> if STRING is
791 =head1 UTF-8 vs. utf8
793 ....We now view strings not as sequences of bytes, but as sequences
794 of numbers in the range 0 .. 2**32-1 (or in the case of 64-bit
795 computers, 0 .. 2**64-1) -- Programming Perl, 3rd ed.
797 That has been the perl's notion of UTF-8 but official UTF-8 is more
798 strict; Its ranges is much narrower (0 .. 10FFFF), some sequences are
799 not allowed (i.e. Those used in the surrogate pair, 0xFFFE, et al).
801 Now that is overruled by Larry Wall himself.
803 From: Larry Wall <larry@wall.org>
804 Date: December 04, 2004 11:51:58 JST
805 To: perl-unicode@perl.org
806 Subject: Re: Make Encode.pm support the real UTF-8
807 Message-Id: <20041204025158.GA28754@wall.org>
809 On Fri, Dec 03, 2004 at 10:12:12PM +0000, Tim Bunce wrote:
810 : I've no problem with 'utf8' being perl's unrestricted uft8 encoding,
811 : but "UTF-8" is the name of the standard and should give the
812 : corresponding behaviour.
814 For what it's worth, that's how I've always kept them straight in my
817 Also for what it's worth, Perl 6 will mostly default to strict but
818 make it easy to switch back to lax.
822 Do you copy? As of Perl 5.8.7, B<UTF-8> means strict, official UTF-8
823 while B<utf8> means liberal, lax, version thereof. And Encode version
824 2.10 or later thus groks the difference between C<UTF-8> and C"utf8".
826 encode("utf8", "\x{FFFF_FFFF}", 1); # okay
827 encode("UTF-8", "\x{FFFF_FFFF}", 1); # croaks
829 C<UTF-8> in Encode is actually a canonical name for C<utf-8-strict>.
830 Yes, the hyphen between "UTF" and "8" is important. Without it Encode
833 find_encoding("UTF-8")->name # is 'utf-8-strict'
834 find_encoding("utf-8")->name # ditto. names are case insensitive
835 find_encoding("utf_8")->name # ditto. "_" are treated as "-"
836 find_encoding("UTF8")->name # is 'utf8'.
842 L<Encode::Supported>,
849 the Perl Unicode Mailing List E<lt>perl-unicode@perl.orgE<gt>
853 This project was originated by Nick Ing-Simmons and later maintained
854 by Dan Kogai E<lt>dankogai@dan.co.jpE<gt>. See AUTHORS for a full
855 list of people involved. For any questions, use
856 E<lt>perl-unicode@perl.orgE<gt> so we can all share.
858 While Dan Kogai retains the copyright as a maintainer, the credit
859 should go to all those involoved. See AUTHORS for those submitted
864 Copyright 2002-2006 Dan Kogai E<lt>dankogai@dan.co.jpE<gt>
866 This library is free software; you can redistribute it and/or modify
867 it under the same terms as Perl itself.