2 # $Id: Encode.pm,v 2.19 2007/04/06 12:53:41 dankogai Exp dankogai $
7 our $VERSION = sprintf "%d.%02d", q$Revision: 2.19 $ =~ /(\d+)/g;
10 XSLoader::load( __PACKAGE__, $VERSION );
13 use base qw/Exporter/;
15 # Public, encouraged API is exported by default
18 decode decode_utf8 encode encode_utf8 str2bytes bytes2str
19 encodings find_encoding clone_encoding
22 DIE_ON_ERR WARN_ON_ERR RETURN_ON_ERR LEAVE_SRC
23 PERLQQ HTMLCREF XMLCREF STOP_AT_PARTIAL
26 FB_DEFAULT FB_CROAK FB_QUIET FB_WARN
27 FB_PERLQQ FB_HTMLCREF FB_XMLCREF
31 _utf8_off _utf8_on define_encoding from_to is_16bit is_8bit
32 is_utf8 perlio_ok resolve_alias utf8_downgrade utf8_upgrade
34 @FB_FLAGS, @FB_CONSTS,
38 all => [ @EXPORT, @EXPORT_OK ],
39 fallbacks => [@FB_CONSTS],
40 fallback_all => [ @FB_CONSTS, @FB_FLAGS ],
43 # Documentation moved after __END__ for speed - NI-S
45 our $ON_EBCDIC = ( ord("A") == 193 );
49 # Make a %Encoding package variable to allow a certain amount of cheating
52 require Encode::Config;
53 eval { require Encode::ConfigLocal };
58 if ( @_ and $_[0] eq ":all" ) {
59 %enc = ( %Encoding, %ExtModule );
63 for my $mod ( map { m/::/o ? $_ : "Encode::$_" } @_ ) {
65 for my $enc ( keys %ExtModule ) {
66 $ExtModule{$enc} eq $mod and $enc{$enc} = $mod;
70 return sort { lc $a cmp lc $b }
71 grep { !/^(?:Internal|Unicode|Guess)$/o } keys %enc;
75 my $obj = ref( $_[0] ) ? $_[0] : find_encoding( $_[0] );
76 $obj->can("perlio_ok") and return $obj->perlio_ok();
77 return 0; # safety net
83 $Encoding{$name} = $obj;
85 define_alias( $lc => $obj ) unless $lc eq $name;
88 define_alias( $alias, $obj );
94 my ( $class, $name, $skip_external ) = @_;
96 ref($name) && $name->can('renew') and return $name;
97 exists $Encoding{$name} and return $Encoding{$name};
99 exists $Encoding{$lc} and return $Encoding{$lc};
101 my $oc = $class->find_alias($name);
102 defined($oc) and return $oc;
103 $lc ne $name and $oc = $class->find_alias($lc);
104 defined($oc) and return $oc;
106 unless ($skip_external) {
107 if ( my $mod = $ExtModule{$name} || $ExtModule{$lc} ) {
110 eval { require $mod; };
111 exists $Encoding{$name} and return $Encoding{$name};
117 sub find_encoding($;$) {
118 my ( $name, $skip_external ) = @_;
119 return __PACKAGE__->getEncoding( $name, $skip_external );
122 sub resolve_alias($) {
123 my $obj = find_encoding(shift);
124 defined $obj and return $obj->name;
128 sub clone_encoding($) {
129 my $obj = find_encoding(shift);
131 eval { require Storable };
133 return Storable::dclone($obj);
137 my ( $name, $string, $check ) = @_;
138 return undef unless defined $string;
139 $string .= '' if ref $string; # stringify;
141 my $enc = find_encoding($name);
142 unless ( defined $enc ) {
144 Carp::croak("Unknown encoding '$name'");
146 my $octets = $enc->encode( $string, $check );
147 $_[1] = $string if $check and !( $check & LEAVE_SRC() );
150 *str2bytes = \&encode;
153 my ( $name, $octets, $check ) = @_;
154 return undef unless defined $octets;
155 $octets .= '' if ref $octets;
157 my $enc = find_encoding($name);
158 unless ( defined $enc ) {
160 Carp::croak("Unknown encoding '$name'");
162 my $string = $enc->decode( $octets, $check );
163 $_[1] = $octets if $check and !( $check & LEAVE_SRC() );
166 *bytes2str = \&decode;
169 my ( $string, $from, $to, $check ) = @_;
170 return undef unless defined $string;
172 my $f = find_encoding($from);
173 unless ( defined $f ) {
175 Carp::croak("Unknown encoding '$from'");
177 my $t = find_encoding($to);
178 unless ( defined $t ) {
180 Carp::croak("Unknown encoding '$to'");
182 my $uni = $f->decode($string);
183 $_[0] = $string = $t->encode( $uni, $check );
184 return undef if ( $check && length($uni) );
185 return defined( $_[0] ) ? length($string) : undef;
194 sub decode_utf8($;$) {
195 my ( $str, $check ) = @_;
196 return $str if is_utf8($str);
198 return decode( "utf8", $str, $check );
201 return decode( "utf8", $str );
206 predefine_encodings(1);
209 # This is to restore %Encoding if really needed;
212 sub predefine_encodings {
213 require Encode::Encoding;
214 no warnings 'redefine';
218 # was in Encode::UTF_EBCDIC
219 package Encode::UTF_EBCDIC;
220 push @Encode::UTF_EBCDIC::ISA, 'Encode::Encoding';
222 my ( $obj, $str, $chk ) = @_;
224 for ( my $i = 0 ; $i < length($str) ; $i++ ) {
227 utf8::unicode_to_native( ord( substr( $str, $i, 1 ) ) )
234 my ( $obj, $str, $chk ) = @_;
236 for ( my $i = 0 ; $i < length($str) ; $i++ ) {
239 utf8::native_to_unicode( ord( substr( $str, $i, 1 ) ) )
245 $Encode::Encoding{Unicode} =
246 bless { Name => "UTF_EBCDIC" } => "Encode::UTF_EBCDIC";
250 package Encode::Internal;
251 push @Encode::Internal::ISA, 'Encode::Encoding';
253 my ( $obj, $str, $chk ) = @_;
259 $Encode::Encoding{Unicode} =
260 bless { Name => "Internal" } => "Encode::Internal";
265 # was in Encode::utf8
266 package Encode::utf8;
267 push @Encode::utf8::ISA, 'Encode::Encoding';
271 Encode::DEBUG and warn __PACKAGE__, " XS on";
272 *decode = \&decode_xs;
273 *encode = \&encode_xs;
276 Encode::DEBUG and warn __PACKAGE__, " XS off";
278 my ( $obj, $octets, $chk ) = @_;
279 my $str = Encode::decode_utf8($octets);
280 if ( defined $str ) {
287 my ( $obj, $string, $chk ) = @_;
288 my $octets = Encode::encode_utf8($string);
293 *cat_decode = sub { # ($obj, $dst, $src, $pos, $trm, $chk)
294 # currently ignores $chk
295 my ( $obj, undef, undef, $pos, $trm ) = @_;
296 my ( $rdst, $rsrc, $rpos ) = \@_[ 1, 2, 3 ];
298 if ( ( my $npos = index( $$rsrc, $trm, $pos ) ) >= 0 ) {
300 substr( $$rsrc, $pos, $npos - $pos + length($trm) );
301 $$rpos = $npos + length($trm);
304 $$rdst .= substr( $$rsrc, $pos );
305 $$rpos = length($$rsrc);
308 $Encode::Encoding{utf8} =
309 bless { Name => "utf8" } => "Encode::utf8";
310 $Encode::Encoding{"utf-8-strict"} =
311 bless { Name => "utf-8-strict", strict_utf8 => 1 } =>
322 Encode - character encodings
328 =head2 Table of Contents
330 Encode consists of a collection of modules whose details are too big
331 to fit in one document. This POD itself explains the top-level APIs
332 and general topics at a glance. For other topics and more details,
336 --------------------------------------------------------
337 Encode::Alias Alias definitions to encodings
338 Encode::Encoding Encode Implementation Base Class
339 Encode::Supported List of Supported Encodings
340 Encode::CN Simplified Chinese Encodings
341 Encode::JP Japanese Encodings
342 Encode::KR Korean Encodings
343 Encode::TW Traditional Chinese Encodings
344 --------------------------------------------------------
348 The C<Encode> module provides the interfaces between Perl's strings
349 and the rest of the system. Perl strings are sequences of
352 The repertoire of characters that Perl can represent is at least that
353 defined by the Unicode Consortium. On most platforms the ordinal
354 values of the characters (as returned by C<ord(ch)>) is the "Unicode
355 codepoint" for the character (the exceptions are those platforms where
356 the legacy encoding is some variant of EBCDIC rather than a super-set
357 of ASCII - see L<perlebcdic>).
359 Traditionally, computer data has been moved around in 8-bit chunks
360 often called "bytes". These chunks are also known as "octets" in
361 networking standards. Perl is widely used to manipulate data of many
362 types - not only strings of characters representing human or computer
363 languages but also "binary" data being the machine's representation of
364 numbers, pixels in an image - or just about anything.
366 When Perl is processing "binary data", the programmer wants Perl to
367 process "sequences of bytes". This is not a problem for Perl - as a
368 byte has 256 possible values, it easily fits in Perl's much larger
377 I<character>: a character in the range 0..(2**32-1) (or more).
378 (What Perl's strings are made of.)
382 I<byte>: a character in the range 0..255
383 (A special case of a Perl character.)
387 I<octet>: 8 bits of data, with ordinal values 0..255
388 (Term for bytes passed to or from a non-Perl context, e.g. a disk file.)
392 =head1 PERL ENCODING API
396 =item $octets = encode(ENCODING, $string [, CHECK])
398 Encodes a string from Perl's internal form into I<ENCODING> and returns
399 a sequence of octets. ENCODING can be either a canonical name or
400 an alias. For encoding names and aliases, see L</"Defining Aliases">.
401 For CHECK, see L</"Handling Malformed Data">.
403 For example, to convert a string from Perl's internal format to
404 iso-8859-1 (also known as Latin1),
406 $octets = encode("iso-8859-1", $string);
408 B<CAVEAT>: When you run C<$octets = encode("utf8", $string)>, then $octets
409 B<may not be equal to> $string. Though they both contain the same data, the UTF8 flag
410 for $octets is B<always> off. When you encode anything, UTF8 flag of
411 the result is always off, even when it contains completely valid utf8
412 string. See L</"The UTF8 flag"> below.
414 If the $string is C<undef> then C<undef> is returned.
416 =item $string = decode(ENCODING, $octets [, CHECK])
418 Decodes a sequence of octets assumed to be in I<ENCODING> into Perl's
419 internal form and returns the resulting string. As in encode(),
420 ENCODING can be either a canonical name or an alias. For encoding names
421 and aliases, see L</"Defining Aliases">. For CHECK, see
422 L</"Handling Malformed Data">.
424 For example, to convert ISO-8859-1 data to a string in Perl's internal format:
426 $string = decode("iso-8859-1", $octets);
428 B<CAVEAT>: When you run C<$string = decode("utf8", $octets)>, then $string
429 B<may not be equal to> $octets. Though they both contain the same data,
430 the UTF8 flag for $string is on unless $octets entirely consists of
431 ASCII data (or EBCDIC on EBCDIC machines). See L</"The UTF8 flag">
434 If the $string is C<undef> then C<undef> is returned.
436 =item [$length =] from_to($octets, FROM_ENC, TO_ENC [, CHECK])
438 Converts B<in-place> data between two encodings. The data in $octets
439 must be encoded as octets and not as characters in Perl's internal
440 format. For example, to convert ISO-8859-1 data to Microsoft's CP1250
443 from_to($octets, "iso-8859-1", "cp1250");
445 and to convert it back:
447 from_to($octets, "cp1250", "iso-8859-1");
449 Note that because the conversion happens in place, the data to be
450 converted cannot be a string constant; it must be a scalar variable.
452 from_to() returns the length of the converted string in octets on
453 success, I<undef> on error.
455 B<CAVEAT>: The following operations look the same but are not quite so;
457 from_to($data, "iso-8859-1", "utf8"); #1
458 $data = decode("iso-8859-1", $data); #2
460 Both #1 and #2 make $data consist of a completely valid UTF-8 string
461 but only #2 turns UTF8 flag on. #1 is equivalent to
463 $data = encode("utf8", decode("iso-8859-1", $data));
465 See L</"The UTF8 flag"> below.
467 =item $octets = encode_utf8($string);
469 Equivalent to C<$octets = encode("utf8", $string);> The characters
470 that comprise $string are encoded in Perl's internal format and the
471 result is returned as a sequence of octets. All possible
472 characters have a UTF-8 representation so this function cannot fail.
475 =item $string = decode_utf8($octets [, CHECK]);
477 equivalent to C<$string = decode("utf8", $octets [, CHECK])>.
478 The sequence of octets represented by
479 $octets is decoded from UTF-8 into a sequence of logical
480 characters. Not all sequences of octets form valid UTF-8 encodings, so
481 it is possible for this call to fail. For CHECK, see
482 L</"Handling Malformed Data">.
486 =head2 Listing available encodings
489 @list = Encode->encodings();
491 Returns a list of the canonical names of the available encodings that
492 are loaded. To get a list of all available encodings including the
493 ones that are not loaded yet, say
495 @all_encodings = Encode->encodings(":all");
497 Or you can give the name of a specific module.
499 @with_jp = Encode->encodings("Encode::JP");
501 When "::" is not in the name, "Encode::" is assumed.
503 @ebcdic = Encode->encodings("EBCDIC");
505 To find out in detail which encodings are supported by this package,
506 see L<Encode::Supported>.
508 =head2 Defining Aliases
510 To add a new alias to a given encoding, use:
514 define_alias(newName => ENCODING);
516 After that, newName can be used as an alias for ENCODING.
517 ENCODING may be either the name of an encoding or an
520 But before you do so, make sure the alias is nonexistent with
521 C<resolve_alias()>, which returns the canonical name thereof.
524 Encode::resolve_alias("latin1") eq "iso-8859-1" # true
525 Encode::resolve_alias("iso-8859-12") # false; nonexistent
526 Encode::resolve_alias($name) eq $name # true if $name is canonical
528 resolve_alias() does not need C<use Encode::Alias>; it can be
529 exported via C<use Encode qw(resolve_alias)>.
531 See L<Encode::Alias> for details.
533 =head1 Encoding via PerlIO
535 If your perl supports I<PerlIO> (which is the default), you can use a PerlIO layer to decode
536 and encode directly via a filehandle. The following two examples
537 are totally identical in their functionality.
540 open my $in, "<:encoding(shiftjis)", $infile or die;
541 open my $out, ">:encoding(euc-jp)", $outfile or die;
542 while(<$in>){ print $out $_; }
545 open my $in, "<", $infile or die;
546 open my $out, ">", $outfile or die;
548 from_to($_, "shiftjis", "euc-jp", 1);
552 Unfortunately, it may be that encodings are PerlIO-savvy. You can check
553 if your encoding is supported by PerlIO by calling the C<perlio_ok>
556 Encode::perlio_ok("hz"); # False
557 find_encoding("euc-cn")->perlio_ok; # True where PerlIO is available
559 use Encode qw(perlio_ok); # exported upon request
562 Fortunately, all encodings that come with Encode core are PerlIO-savvy
563 except for hz and ISO-2022-kr. For gory details, see
564 L<Encode::Encoding> and L<Encode::PerlIO>.
566 =head1 Handling Malformed Data
568 The optional I<CHECK> argument tells Encode what to do when it
569 encounters malformed data. Without CHECK, Encode::FB_DEFAULT ( == 0 )
572 As of version 2.12 Encode supports coderef values for CHECK. See below.
576 =item B<NOTE:> Not all encoding support this feature
578 Some encodings ignore I<CHECK> argument. For example,
579 L<Encode::Unicode> ignores I<CHECK> and it always croaks on error.
583 Now here is the list of I<CHECK> values available
587 =item I<CHECK> = Encode::FB_DEFAULT ( == 0)
589 If I<CHECK> is 0, (en|de)code will put a I<substitution character> in
590 place of a malformed character. When you encode, E<lt>subcharE<gt>
591 will be used. When you decode the code point C<0xFFFD> is used. If
592 the data is supposed to be UTF-8, an optional lexical warning
593 (category utf8) is given.
595 =item I<CHECK> = Encode::FB_CROAK ( == 1)
597 If I<CHECK> is 1, methods will die on error immediately with an error
598 message. Therefore, when I<CHECK> is set to 1, you should trap the
599 error with eval{} unless you really want to let it die.
601 =item I<CHECK> = Encode::FB_QUIET
603 If I<CHECK> is set to Encode::FB_QUIET, (en|de)code will immediately
604 return the portion of the data that has been processed so far when an
605 error occurs. The data argument will be overwritten with everything
606 after that point (that is, the unprocessed part of data). This is
607 handy when you have to call decode repeatedly in the case where your
608 source data may contain partial multi-byte character sequences,
609 (i.e. you are reading with a fixed-width buffer). Here is a sample
610 code that does exactly this:
612 my $buffer = ''; my $string = '';
613 while(read $fh, $buffer, 256, length($buffer)){
614 $string .= decode($encoding, $buffer, Encode::FB_QUIET);
615 # $buffer now contains the unprocessed partial character
618 =item I<CHECK> = Encode::FB_WARN
620 This is the same as above, except that it warns on error. Handy when
621 you are debugging the mode above.
623 =item perlqq mode (I<CHECK> = Encode::FB_PERLQQ)
625 =item HTML charref mode (I<CHECK> = Encode::FB_HTMLCREF)
627 =item XML charref mode (I<CHECK> = Encode::FB_XMLCREF)
629 For encodings that are implemented by Encode::XS, CHECK ==
630 Encode::FB_PERLQQ turns (en|de)code into C<perlqq> fallback mode.
632 When you decode, C<\xI<HH>> will be inserted for a malformed character,
633 where I<HH> is the hex representation of the octet that could not be
634 decoded to utf8. And when you encode, C<\x{I<HHHH>}> will be inserted,
635 where I<HHHH> is the Unicode ID of the character that cannot be found
636 in the character repertoire of the encoding.
638 HTML/XML character reference modes are about the same, in place of
639 C<\x{I<HHHH>}>, HTML uses C<&#I<NNN>;> where I<NNN> is a decimal number and
640 XML uses C<&#xI<HHHH>;> where I<HHHH> is the hexadecimal number.
642 In Encode 2.10 or later, C<LEAVE_SRC> is also implied.
646 These modes are actually set via a bitmask. Here is how the FB_XX
647 constants are laid out. You can import the FB_XX constants via
648 C<use Encode qw(:fallbacks)>; you can import the generic bitmask
649 constants via C<use Encode qw(:fallback_all)>.
651 FB_DEFAULT FB_CROAK FB_QUIET FB_WARN FB_PERLQQ
654 RETURN_ON_ERR 0x0004 X X
662 =item Encode::LEAVE_SRC
664 If the C<Encode::LEAVE_SRC> bit is not set, but I<CHECK> is, then the second
665 argument to C<encode()> or C<decode()> may be assigned to by the functions. If
666 you're not interested in this, then bitwise-or the bitmask with it.
668 =head2 coderef for CHECK
670 As of Encode 2.12 CHECK can also be a code reference which takes the
671 ord value of unmapped caharacter as an argument and returns a string
672 that represents the fallback character. For instance,
674 $ascii = encode("ascii", $utf8, sub{ sprintf "<U+%04X>", shift });
676 Acts like FB_PERLQQ but E<lt>U+I<XXXX>E<gt> is used instead of
679 =head1 Defining Encodings
681 To define a new encoding, use:
683 use Encode qw(define_encoding);
684 define_encoding($object, 'canonicalName' [, alias...]);
686 I<canonicalName> will be associated with I<$object>. The object
687 should provide the interface described in L<Encode::Encoding>.
688 If more than two arguments are provided then additional
689 arguments are taken as aliases for I<$object>.
691 See L<Encode::Encoding> for more details.
695 Before the introduction of Unicode support in perl, The C<eq> operator
696 just compared the strings represented by two scalars. Beginning with
697 perl 5.8, C<eq> compares two strings with simultaneous consideration of
698 I<the UTF8 flag>. To explain why we made it so, I will quote page 402 of
699 C<Programming Perl, 3rd ed.>
705 Old byte-oriented programs should not spontaneously break on the old
706 byte-oriented data they used to work on.
710 Old byte-oriented programs should magically start working on the new
711 character-oriented data when appropriate.
715 Programs should run just as fast in the new character-oriented mode
716 as in the old byte-oriented mode.
720 Perl should remain one language, rather than forking into a
721 byte-oriented Perl and a character-oriented Perl.
725 Back when C<Programming Perl, 3rd ed.> was written, not even Perl 5.6.0
726 was born and many features documented in the book remained
727 unimplemented for a long time. Perl 5.8 corrected this and the introduction
728 of the UTF8 flag is one of them. You can think of this perl notion as of a
729 byte-oriented mode (UTF8 flag off) and a character-oriented mode (UTF8
732 Here is how Encode takes care of the UTF8 flag.
738 When you encode, the resulting UTF8 flag is always off.
742 When you decode, the resulting UTF8 flag is on unless you can
743 unambiguously represent data. Here is the definition of
746 After C<$utf8 = decode('foo', $octet);>,
748 When $octet is... The UTF8 flag in $utf8 is
749 ---------------------------------------------
750 In ASCII only (or EBCDIC only) OFF
752 In any other Encoding ON
753 ---------------------------------------------
755 As you see, there is one exception, In ASCII. That way you can assume
756 Goal #1. And with Encode Goal #2 is assumed but you still have to be
757 careful in such cases mentioned in B<CAVEAT> paragraphs.
759 This UTF8 flag is not visible in perl scripts, exactly for the same
760 reason you cannot (or you I<don't have to>) see if a scalar contains a
761 string, integer, or floating point number. But you can still peek
762 and poke these if you will. See the section below.
766 =head2 Messing with Perl's Internals
768 The following API uses parts of Perl's internals in the current
769 implementation. As such, they are efficient but may change.
773 =item is_utf8(STRING [, CHECK])
775 [INTERNAL] Tests whether the UTF8 flag is turned on in the STRING.
776 If CHECK is true, also checks the data in STRING for being well-formed
777 UTF-8. Returns true if successful, false otherwise.
779 As of perl 5.8.1, L<utf8> also has utf8::is_utf8().
781 =item _utf8_on(STRING)
783 [INTERNAL] Turns on the UTF8 flag in STRING. The data in STRING is
784 B<not> checked for being well-formed UTF-8. Do not use unless you
785 B<know> that the STRING is well-formed UTF-8. Returns the previous
786 state of the UTF8 flag (so please don't treat the return value as
787 indicating success or failure), or C<undef> if STRING is not a string.
789 =item _utf8_off(STRING)
791 [INTERNAL] Turns off the UTF8 flag in STRING. Do not use frivolously.
792 Returns the previous state of the UTF8 flag (so please don't treat the
793 return value as indicating success or failure), or C<undef> if STRING is
798 =head1 UTF-8 vs. utf8 vs. UTF8
800 ....We now view strings not as sequences of bytes, but as sequences
801 of numbers in the range 0 .. 2**32-1 (or in the case of 64-bit
802 computers, 0 .. 2**64-1) -- Programming Perl, 3rd ed.
804 That has been the perl's notion of UTF-8 but official UTF-8 is more
805 strict; Its ranges is much narrower (0 .. 10FFFF), some sequences are
806 not allowed (i.e. Those used in the surrogate pair, 0xFFFE, et al).
808 Now that is overruled by Larry Wall himself.
810 From: Larry Wall <larry@wall.org>
811 Date: December 04, 2004 11:51:58 JST
812 To: perl-unicode@perl.org
813 Subject: Re: Make Encode.pm support the real UTF-8
814 Message-Id: <20041204025158.GA28754@wall.org>
816 On Fri, Dec 03, 2004 at 10:12:12PM +0000, Tim Bunce wrote:
817 : I've no problem with 'utf8' being perl's unrestricted uft8 encoding,
818 : but "UTF-8" is the name of the standard and should give the
819 : corresponding behaviour.
821 For what it's worth, that's how I've always kept them straight in my
824 Also for what it's worth, Perl 6 will mostly default to strict but
825 make it easy to switch back to lax.
829 Do you copy? As of Perl 5.8.7, B<UTF-8> means strict, official UTF-8
830 while B<utf8> means liberal, lax, version thereof. And Encode version
831 2.10 or later thus groks the difference between C<UTF-8> and C"utf8".
833 encode("utf8", "\x{FFFF_FFFF}", 1); # okay
834 encode("UTF-8", "\x{FFFF_FFFF}", 1); # croaks
836 C<UTF-8> in Encode is actually a canonical name for C<utf-8-strict>.
837 Yes, the hyphen between "UTF" and "8" is important. Without it Encode
840 find_encoding("UTF-8")->name # is 'utf-8-strict'
841 find_encoding("utf-8")->name # ditto. names are case insensitive
842 find_encoding("utf_8")->name # ditto. "_" are treated as "-"
843 find_encoding("UTF8")->name # is 'utf8'.
845 The UTF8 flag is internally called UTF8, without a hyphen. It indicates
846 whether a string is internally encoded as utf8, also without a hypen.
851 L<Encode::Supported>,
858 the Perl Unicode Mailing List E<lt>perl-unicode@perl.orgE<gt>
862 This project was originated by Nick Ing-Simmons and later maintained
863 by Dan Kogai E<lt>dankogai@dan.co.jpE<gt>. See AUTHORS for a full
864 list of people involved. For any questions, use
865 E<lt>perl-unicode@perl.orgE<gt> so we can all share.
867 While Dan Kogai retains the copyright as a maintainer, the credit
868 should go to all those involoved. See AUTHORS for those submitted
873 Copyright 2002-2006 Dan Kogai E<lt>dankogai@dan.co.jpE<gt>
875 This library is free software; you can redistribute it and/or modify
876 it under the same terms as Perl itself.