#
-# $Id: Encode.pm,v 2.12 2005/09/08 14:17:17 dankogai Exp dankogai $
+# $Id: Encode.pm,v 2.22 2007/05/29 07:35:27 dankogai Exp dankogai $
#
package Encode;
use strict;
-our $VERSION = sprintf "%d.%02d", q$Revision: 2.12 $ =~ /(\d+)/g;
+use warnings;
+our $VERSION = sprintf "%d.%02d", q$Revision: 2.22 $ =~ /(\d+)/g;
sub DEBUG () { 0 }
use XSLoader ();
-XSLoader::load(__PACKAGE__, $VERSION);
+XSLoader::load( __PACKAGE__, $VERSION );
require Exporter;
use base qw/Exporter/;
# Public, encouraged API is exported by default
our @EXPORT = qw(
- decode decode_utf8 encode encode_utf8
+ decode decode_utf8 encode encode_utf8 str2bytes bytes2str
encodings find_encoding clone_encoding
);
-
-our @FB_FLAGS = qw(DIE_ON_ERR WARN_ON_ERR RETURN_ON_ERR LEAVE_SRC
- PERLQQ HTMLCREF XMLCREF STOP_AT_PARTIAL);
-our @FB_CONSTS = qw(FB_DEFAULT FB_CROAK FB_QUIET FB_WARN
- FB_PERLQQ FB_HTMLCREF FB_XMLCREF);
-
-our @EXPORT_OK =
- (
- qw(
- _utf8_off _utf8_on define_encoding from_to is_16bit is_8bit
- is_utf8 perlio_ok resolve_alias utf8_downgrade utf8_upgrade
+our @FB_FLAGS = qw(
+ DIE_ON_ERR WARN_ON_ERR RETURN_ON_ERR LEAVE_SRC
+ PERLQQ HTMLCREF XMLCREF STOP_AT_PARTIAL
+);
+our @FB_CONSTS = qw(
+ FB_DEFAULT FB_CROAK FB_QUIET FB_WARN
+ FB_PERLQQ FB_HTMLCREF FB_XMLCREF
+);
+our @EXPORT_OK = (
+ qw(
+ _utf8_off _utf8_on define_encoding from_to is_16bit is_8bit
+ is_utf8 perlio_ok resolve_alias utf8_downgrade utf8_upgrade
),
- @FB_FLAGS, @FB_CONSTS,
- );
+ @FB_FLAGS, @FB_CONSTS,
+);
-our %EXPORT_TAGS =
- (
- all => [ @EXPORT, @EXPORT_OK ],
- fallbacks => [ @FB_CONSTS ],
- fallback_all => [ @FB_CONSTS, @FB_FLAGS ],
- );
+our %EXPORT_TAGS = (
+ all => [ @EXPORT, @EXPORT_OK ],
+ fallbacks => [@FB_CONSTS],
+ fallback_all => [ @FB_CONSTS, @FB_FLAGS ],
+);
# Documentation moved after __END__ for speed - NI-S
-our $ON_EBCDIC = (ord("A") == 193);
+our $ON_EBCDIC = ( ord("A") == 193 );
use Encode::Alias;
require Encode::Config;
eval { require Encode::ConfigLocal };
-sub encodings
-{
+sub encodings {
my $class = shift;
my %enc;
- if (@_ and $_[0] eq ":all"){
- %enc = ( %Encoding, %ExtModule );
- }else{
- %enc = %Encoding;
- for my $mod (map {m/::/o ? $_ : "Encode::$_" } @_){
- DEBUG and warn $mod;
- for my $enc (keys %ExtModule){
- $ExtModule{$enc} eq $mod and $enc{$enc} = $mod;
- }
- }
+ if ( @_ and $_[0] eq ":all" ) {
+ %enc = ( %Encoding, %ExtModule );
}
- return
- sort { lc $a cmp lc $b }
- grep {!/^(?:Internal|Unicode|Guess)$/o} keys %enc;
+ else {
+ %enc = %Encoding;
+ for my $mod ( map { m/::/o ? $_ : "Encode::$_" } @_ ) {
+ DEBUG and warn $mod;
+ for my $enc ( keys %ExtModule ) {
+ $ExtModule{$enc} eq $mod and $enc{$enc} = $mod;
+ }
+ }
+ }
+ return sort { lc $a cmp lc $b }
+ grep { !/^(?:Internal|Unicode|Guess)$/o } keys %enc;
}
-sub perlio_ok{
- my $obj = ref($_[0]) ? $_[0] : find_encoding($_[0]);
+sub perlio_ok {
+ my $obj = ref( $_[0] ) ? $_[0] : find_encoding( $_[0] );
$obj->can("perlio_ok") and return $obj->perlio_ok();
- return 0; # safety net
+ return 0; # safety net
}
-sub define_encoding
-{
+sub define_encoding {
my $obj = shift;
my $name = shift;
$Encoding{$name} = $obj;
my $lc = lc($name);
- define_alias($lc => $obj) unless $lc eq $name;
- while (@_){
- my $alias = shift;
- define_alias($alias, $obj);
+ define_alias( $lc => $obj ) unless $lc eq $name;
+ while (@_) {
+ my $alias = shift;
+ define_alias( $alias, $obj );
}
return $obj;
}
-sub getEncoding
-{
- my ($class, $name, $skip_external) = @_;
+sub getEncoding {
+ my ( $class, $name, $skip_external ) = @_;
ref($name) && $name->can('renew') and return $name;
exists $Encoding{$name} and return $Encoding{$name};
$lc ne $name and $oc = $class->find_alias($lc);
defined($oc) and return $oc;
- unless ($skip_external)
- {
- if (my $mod = $ExtModule{$name} || $ExtModule{$lc}){
- $mod =~ s,::,/,g ; $mod .= '.pm';
- eval{ require $mod; };
- exists $Encoding{$name} and return $Encoding{$name};
- }
+ unless ($skip_external) {
+ if ( my $mod = $ExtModule{$name} || $ExtModule{$lc} ) {
+ $mod =~ s,::,/,g;
+ $mod .= '.pm';
+ eval { require $mod; };
+ exists $Encoding{$name} and return $Encoding{$name};
+ }
}
return;
}
-sub find_encoding($;$)
-{
- my ($name, $skip_external) = @_;
- return __PACKAGE__->getEncoding($name,$skip_external);
+sub find_encoding($;$) {
+ my ( $name, $skip_external ) = @_;
+ return __PACKAGE__->getEncoding( $name, $skip_external );
}
-sub resolve_alias($){
+sub resolve_alias($) {
my $obj = find_encoding(shift);
defined $obj and return $obj->name;
return;
}
-sub clone_encoding($){
+sub clone_encoding($) {
my $obj = find_encoding(shift);
ref $obj or return;
eval { require Storable };
return Storable::dclone($obj);
}
-sub encode($$;$)
-{
- my ($name, $string, $check) = @_;
+sub encode($$;$) {
+ my ( $name, $string, $check ) = @_;
return undef unless defined $string;
- $string .= '' if ref $string; # stringify;
- $check ||=0;
+ $string .= '' if ref $string; # stringify;
+ $check ||= 0;
my $enc = find_encoding($name);
- unless(defined $enc){
- require Carp;
- Carp::croak("Unknown encoding '$name'");
+ unless ( defined $enc ) {
+ require Carp;
+ Carp::croak("Unknown encoding '$name'");
}
- my $octets = $enc->encode($string,$check);
- $_[1] = $string if $check and !($check & LEAVE_SRC());
+ my $octets = $enc->encode( $string, $check );
+ $_[1] = $string if $check and !ref $check and !( $check & LEAVE_SRC() );
return $octets;
}
+*str2bytes = \&encode;
-sub decode($$;$)
-{
- my ($name,$octets,$check) = @_;
+sub decode($$;$) {
+ my ( $name, $octets, $check ) = @_;
return undef unless defined $octets;
$octets .= '' if ref $octets;
- $check ||=0;
+ $check ||= 0;
my $enc = find_encoding($name);
- unless(defined $enc){
- require Carp;
- Carp::croak("Unknown encoding '$name'");
+ unless ( defined $enc ) {
+ require Carp;
+ Carp::croak("Unknown encoding '$name'");
}
- my $string = $enc->decode($octets,$check);
- $_[1] = $octets if $check and !($check & LEAVE_SRC());
+ my $string = $enc->decode( $octets, $check );
+ $_[1] = $octets if $check and !ref $check and !( $check & LEAVE_SRC() );
return $string;
}
+*bytes2str = \&decode;
-sub from_to($$$;$)
-{
- my ($string,$from,$to,$check) = @_;
+sub from_to($$$;$) {
+ my ( $string, $from, $to, $check ) = @_;
return undef unless defined $string;
- $check ||=0;
+ $check ||= 0;
my $f = find_encoding($from);
- unless (defined $f){
- require Carp;
- Carp::croak("Unknown encoding '$from'");
+ unless ( defined $f ) {
+ require Carp;
+ Carp::croak("Unknown encoding '$from'");
}
my $t = find_encoding($to);
- unless (defined $t){
- require Carp;
- Carp::croak("Unknown encoding '$to'");
+ unless ( defined $t ) {
+ require Carp;
+ Carp::croak("Unknown encoding '$to'");
}
- my $uni = $f->decode($string,$check);
- return undef if ($check && length($string));
- $string = $t->encode($uni,$check);
- return undef if ($check && length($uni));
- return defined($_[0] = $string) ? length($string) : undef ;
+ my $uni = $f->decode($string);
+ $_[0] = $string = $t->encode( $uni, $check );
+ return undef if ( $check && length($uni) );
+ return defined( $_[0] ) ? length($string) : undef;
}
-sub encode_utf8($)
-{
+sub encode_utf8($) {
my ($str) = @_;
utf8::encode($str);
return $str;
}
-sub decode_utf8($;$)
-{
- my ($str, $check) = @_;
- if ($check){
- return decode("utf8", $str, $check);
- }else{
- return decode("utf8", $str);
- return $str;
+sub decode_utf8($;$) {
+ my ( $str, $check ) = @_;
+ return $str if is_utf8($str);
+ if ($check) {
+ return decode( "utf8", $str, $check );
+ }
+ else {
+ return decode( "utf8", $str );
+ return $str;
}
}
# This is to restore %Encoding if really needed;
#
-sub predefine_encodings{
- use Encode::Encoding;
+sub predefine_encodings {
+ require Encode::Encoding;
no warnings 'redefine';
my $use_xs = shift;
if ($ON_EBCDIC) {
- # was in Encode::UTF_EBCDIC
- package Encode::UTF_EBCDIC;
- push @Encode::UTF_EBCDIC::ISA, 'Encode::Encoding';
- *decode = sub{
- my ($obj,$str,$chk) = @_;
- my $res = '';
- for (my $i = 0; $i < length($str); $i++) {
- $res .=
- chr(utf8::unicode_to_native(ord(substr($str,$i,1))));
- }
- $_[1] = '' if $chk;
- return $res;
- };
- *encode = sub{
- my ($obj,$str,$chk) = @_;
- my $res = '';
- for (my $i = 0; $i < length($str); $i++) {
- $res .=
- chr(utf8::native_to_unicode(ord(substr($str,$i,1))));
- }
- $_[1] = '' if $chk;
- return $res;
- };
- $Encode::Encoding{Unicode} =
- bless {Name => "UTF_EBCDIC"} => "Encode::UTF_EBCDIC";
- } else {
- package Encode::Internal;
- push @Encode::Internal::ISA, 'Encode::Encoding';
- *decode = sub{
- my ($obj,$str,$chk) = @_;
- utf8::upgrade($str);
- $_[1] = '' if $chk;
- return $str;
- };
- *encode = \&decode;
- $Encode::Encoding{Unicode} =
- bless {Name => "Internal"} => "Encode::Internal";
+
+ # was in Encode::UTF_EBCDIC
+ package Encode::UTF_EBCDIC;
+ push @Encode::UTF_EBCDIC::ISA, 'Encode::Encoding';
+ *decode = sub {
+ my ( $obj, $str, $chk ) = @_;
+ my $res = '';
+ for ( my $i = 0 ; $i < length($str) ; $i++ ) {
+ $res .=
+ chr(
+ utf8::unicode_to_native( ord( substr( $str, $i, 1 ) ) )
+ );
+ }
+ $_[1] = '' if $chk;
+ return $res;
+ };
+ *encode = sub {
+ my ( $obj, $str, $chk ) = @_;
+ my $res = '';
+ for ( my $i = 0 ; $i < length($str) ; $i++ ) {
+ $res .=
+ chr(
+ utf8::native_to_unicode( ord( substr( $str, $i, 1 ) ) )
+ );
+ }
+ $_[1] = '' if $chk;
+ return $res;
+ };
+ $Encode::Encoding{Unicode} =
+ bless { Name => "UTF_EBCDIC" } => "Encode::UTF_EBCDIC";
+ }
+ else {
+
+ package Encode::Internal;
+ push @Encode::Internal::ISA, 'Encode::Encoding';
+ *decode = sub {
+ my ( $obj, $str, $chk ) = @_;
+ utf8::upgrade($str);
+ $_[1] = '' if $chk;
+ return $str;
+ };
+ *encode = \&decode;
+ $Encode::Encoding{Unicode} =
+ bless { Name => "Internal" } => "Encode::Internal";
}
{
- # was in Encode::utf8
- package Encode::utf8;
- push @Encode::utf8::ISA, 'Encode::Encoding';
- #
- if ($use_xs){
- Encode::DEBUG and warn __PACKAGE__, " XS on";
- *decode = \&decode_xs;
- *encode = \&encode_xs;
- }else{
- Encode::DEBUG and warn __PACKAGE__, " XS off";
- *decode = sub{
- my ($obj,$octets,$chk) = @_;
- my $str = Encode::decode_utf8($octets);
- if (defined $str) {
- $_[1] = '' if $chk;
- return $str;
- }
- return undef;
- };
- *encode = sub {
- my ($obj,$string,$chk) = @_;
- my $octets = Encode::encode_utf8($string);
- $_[1] = '' if $chk;
- return $octets;
- };
- }
- *cat_decode = sub{ # ($obj, $dst, $src, $pos, $trm, $chk)
- my ($obj, undef, undef, $pos, $trm) = @_; # currently ignores $chk
- my ($rdst, $rsrc, $rpos) = \@_[1,2,3];
- use bytes;
- if ((my $npos = index($$rsrc, $trm, $pos)) >= 0) {
- $$rdst .= substr($$rsrc, $pos, $npos - $pos + length($trm));
- $$rpos = $npos + length($trm);
- return 1;
- }
- $$rdst .= substr($$rsrc, $pos);
- $$rpos = length($$rsrc);
- return '';
- };
- $Encode::Encoding{utf8} =
- bless {Name => "utf8"} => "Encode::utf8";
- $Encode::Encoding{"utf-8-strict"} =
- bless {Name => "utf-8-strict", strict_utf8 => 1 } => "Encode::utf8";
+
+ # was in Encode::utf8
+ package Encode::utf8;
+ push @Encode::utf8::ISA, 'Encode::Encoding';
+
+ #
+ if ($use_xs) {
+ Encode::DEBUG and warn __PACKAGE__, " XS on";
+ *decode = \&decode_xs;
+ *encode = \&encode_xs;
+ }
+ else {
+ Encode::DEBUG and warn __PACKAGE__, " XS off";
+ *decode = sub {
+ my ( $obj, $octets, $chk ) = @_;
+ my $str = Encode::decode_utf8($octets);
+ if ( defined $str ) {
+ $_[1] = '' if $chk;
+ return $str;
+ }
+ return undef;
+ };
+ *encode = sub {
+ my ( $obj, $string, $chk ) = @_;
+ my $octets = Encode::encode_utf8($string);
+ $_[1] = '' if $chk;
+ return $octets;
+ };
+ }
+ *cat_decode = sub { # ($obj, $dst, $src, $pos, $trm, $chk)
+ # currently ignores $chk
+ my ( $obj, undef, undef, $pos, $trm ) = @_;
+ my ( $rdst, $rsrc, $rpos ) = \@_[ 1, 2, 3 ];
+ use bytes;
+ if ( ( my $npos = index( $$rsrc, $trm, $pos ) ) >= 0 ) {
+ $$rdst .=
+ substr( $$rsrc, $pos, $npos - $pos + length($trm) );
+ $$rpos = $npos + length($trm);
+ return 1;
+ }
+ $$rdst .= substr( $$rsrc, $pos );
+ $$rpos = length($$rsrc);
+ return '';
+ };
+ $Encode::Encoding{utf8} =
+ bless { Name => "utf8" } => "Encode::utf8";
+ $Encode::Encoding{"utf-8-strict"} =
+ bless { Name => "utf-8-strict", strict_utf8 => 1 } =>
+ "Encode::utf8";
}
}
$octets = encode("iso-8859-1", $string);
-B<CAVEAT>: When you run C<$octets = encode("utf8", $string)>, then $octets
-B<may not be equal to> $string. Though they both contain the same data, the utf8 flag
-for $octets is B<always> off. When you encode anything, utf8 flag of
-the result is always off, even when it contains completely valid utf8
-string. See L</"The UTF-8 flag"> below.
+B<CAVEAT>: When you run C<$octets = encode("utf8", $string)>, then
+$octets B<may not be equal to> $string. Though they both contain the
+same data, the UTF8 flag for $octets is B<always> off. When you
+encode anything, UTF8 flag of the result is always off, even when it
+contains completely valid utf8 string. See L</"The UTF8 flag"> below.
If the $string is C<undef> then C<undef> is returned.
B<CAVEAT>: When you run C<$string = decode("utf8", $octets)>, then $string
B<may not be equal to> $octets. Though they both contain the same data,
-the utf8 flag for $string is on unless $octets entirely consists of
-ASCII data (or EBCDIC on EBCDIC machines). See L</"The UTF-8 flag">
+the UTF8 flag for $string is on unless $octets entirely consists of
+ASCII data (or EBCDIC on EBCDIC machines). See L</"The UTF8 flag">
below.
If the $string is C<undef> then C<undef> is returned.
+=item [$obj =] find_encoding(ENCODING)
+
+Returns the I<encoding object> corresponding to ENCODING. Returns
+undef if no matching ENCODING is find.
+
+This object is what actually does the actual (en|de)coding.
+
+ $utf8 = decode($name, $bytes);
+
+is in fact
+
+ $utf8 = do{
+ $obj = find_encoding($name);
+ croak qq(encoding "$name" not found) unless ref $obj;
+ $obj->decode($bytes)
+ };
+
+with more error checking.
+
+Therefore you can save time by reusing this object as follows;
+
+ my $enc = find_encoding("iso-8859-1");
+ while(<>){
+ my $utf8 = $enc->decode($_);
+ # and do someting with $utf8;
+ }
+
+Besides C<< ->decode >> and C<< ->encode >>, other methods are
+available as well. For instance, C<< -> name >> returns the canonical
+name of the encoding object.
+
+ find_encoding("latin1")->name; # iso-8859-1
+
+See L<Encode::Encoding> for details.
+
=item [$length =] from_to($octets, FROM_ENC, TO_ENC [, CHECK])
Converts B<in-place> data between two encodings. The data in $octets
$data = decode("iso-8859-1", $data); #2
Both #1 and #2 make $data consist of a completely valid UTF-8 string
-but only #2 turns utf8 flag on. #1 is equivalent to
+but only #2 turns UTF8 flag on. #1 is equivalent to
$data = encode("utf8", decode("iso-8859-1", $data));
-See L</"The UTF-8 flag"> below.
+See L</"The UTF8 flag"> below.
+
+Also note that
+
+ from_to($octets, $from, $to, $check);
+
+is equivalent to
+
+ $octets = encode($to, decode($from, $octets), $check);
+
+Yes, it does not respect the $check during decoding. It is
+deliberately done that way. If you need minute control, C<decode>
+then C<encode> as follows;
+
+ $octets = encode($to, decode($from, $octets, $check_from), $check_to);
=item $octets = encode_utf8($string);
See L<Encode::Alias> for details.
+=head2 Finding IANA Character Set Registry names
+
+The canonical name of a given encoding does not necessarily agree with
+IANA IANA Character Set Registry, commonly seen as C<< Content-Type:
+text/plain; charset=I<whatever> >>. For most cases canonical names
+work but sometimes it does not (notably 'utf-8-strict').
+
+Therefore as of Encode version 2.21, a new method C<mime_name()> is added.
+
+ use Encode;
+ my $enc = find_encoding('UTF-8');
+ warn $enc->name; # utf-8-strict
+ warn $enc->mime_name; # UTF-8
+
+See also: L<Encode::Encoding>
+
=head1 Encoding via PerlIO
-If your perl supports I<PerlIO> (which is the default), you can use a PerlIO layer to decode
-and encode directly via a filehandle. The following two examples
-are totally identical in their functionality.
+If your perl supports I<PerlIO> (which is the default), you can use a
+PerlIO layer to decode and encode directly via a filehandle. The
+following two examples are totally identical in their functionality.
# via PerlIO
open my $in, "<:encoding(shiftjis)", $infile or die;
=back
-=head2 coderef for CHECK
+=over 2
+
+=item Encode::LEAVE_SRC
+
+If the C<Encode::LEAVE_SRC> bit is not set, but I<CHECK> is, then the second
+argument to C<encode()> or C<decode()> may be assigned to by the functions. If
+you're not interested in this, then bitwise-or the bitmask with it.
+
+=back
+
+=Head2 coderef for CHECK
As of Encode 2.12 CHECK can also be a code reference which takes the
ord value of unmapped caharacter as an argument and returns a string
See L<Encode::Encoding> for more details.
-=head1 The UTF-8 flag
+=head1 The UTF8 flag
-Before the introduction of utf8 support in perl, The C<eq> operator
+Before the introduction of Unicode support in perl, The C<eq> operator
just compared the strings represented by two scalars. Beginning with
-perl 5.8, C<eq> compares two strings with simultaneous consideration
-of I<the utf8 flag>. To explain why we made it so, I will quote page
-402 of C<Programming Perl, 3rd ed.>
+perl 5.8, C<eq> compares two strings with simultaneous consideration of
+I<the UTF8 flag>. To explain why we made it so, I will quote page 402 of
+C<Programming Perl, 3rd ed.>
=over 2
Back when C<Programming Perl, 3rd ed.> was written, not even Perl 5.6.0
was born and many features documented in the book remained
unimplemented for a long time. Perl 5.8 corrected this and the introduction
-of the UTF-8 flag is one of them. You can think of this perl notion as of a
-byte-oriented mode (utf8 flag off) and a character-oriented mode (utf8
+of the UTF8 flag is one of them. You can think of this perl notion as of a
+byte-oriented mode (UTF8 flag off) and a character-oriented mode (UTF8
flag on).
-Here is how Encode takes care of the utf8 flag.
+Here is how Encode takes care of the UTF8 flag.
=over 2
=item *
-When you encode, the resulting utf8 flag is always off.
+When you encode, the resulting UTF8 flag is always off.
=item *
-When you decode, the resulting utf8 flag is on unless you can
+When you decode, the resulting UTF8 flag is on unless you can
unambiguously represent data. Here is the definition of
dis-ambiguity.
After C<$utf8 = decode('foo', $octet);>,
- When $octet is... The utf8 flag in $utf8 is
+ When $octet is... The UTF8 flag in $utf8 is
---------------------------------------------
In ASCII only (or EBCDIC only) OFF
In ISO-8859-1 ON
Goal #1. And with Encode Goal #2 is assumed but you still have to be
careful in such cases mentioned in B<CAVEAT> paragraphs.
-This utf8 flag is not visible in perl scripts, exactly for the same
+This UTF8 flag is not visible in perl scripts, exactly for the same
reason you cannot (or you I<don't have to>) see if a scalar contains a
string, integer, or floating point number. But you can still peek
and poke these if you will. See the section below.
=item is_utf8(STRING [, CHECK])
-[INTERNAL] Tests whether the UTF-8 flag is turned on in the STRING.
+[INTERNAL] Tests whether the UTF8 flag is turned on in the STRING.
If CHECK is true, also checks the data in STRING for being well-formed
UTF-8. Returns true if successful, false otherwise.
=item _utf8_on(STRING)
-[INTERNAL] Turns on the UTF-8 flag in STRING. The data in STRING is
+[INTERNAL] Turns on the UTF8 flag in STRING. The data in STRING is
B<not> checked for being well-formed UTF-8. Do not use unless you
B<know> that the STRING is well-formed UTF-8. Returns the previous
-state of the UTF-8 flag (so please don't treat the return value as
+state of the UTF8 flag (so please don't treat the return value as
indicating success or failure), or C<undef> if STRING is not a string.
=item _utf8_off(STRING)
-[INTERNAL] Turns off the UTF-8 flag in STRING. Do not use frivolously.
-Returns the previous state of the UTF-8 flag (so please don't treat the
+[INTERNAL] Turns off the UTF8 flag in STRING. Do not use frivolously.
+Returns the previous state of the UTF8 flag (so please don't treat the
return value as indicating success or failure), or C<undef> if STRING is
not a string.
=back
-=head1 UTF-8 vs. utf8
+=head1 UTF-8 vs. utf8 vs. UTF8
....We now view strings not as sequences of bytes, but as sequences
of numbers in the range 0 .. 2**32-1 (or in the case of 64-bit
find_encoding("UTF-8")->name # is 'utf-8-strict'
find_encoding("utf-8")->name # ditto. names are case insensitive
- find_encoding("utf8")->name # ditto. "_" are treated as "-"
+ find_encoding("utf_8")->name # ditto. "_" are treated as "-"
find_encoding("UTF8")->name # is 'utf8'.
+The UTF8 flag is internally called UTF8, without a hyphen. It indicates
+whether a string is internally encoded as utf8, also without a hypen.
=head1 SEE ALSO
list of people involved. For any questions, use
E<lt>perl-unicode@perl.orgE<gt> so we can all share.
+While Dan Kogai retains the copyright as a maintainer, the credit
+should go to all those involoved. See AUTHORS for those submitted
+codes.
+
+=head1 COPYRIGHT
+
+Copyright 2002-2006 Dan Kogai E<lt>dankogai@dan.co.jpE<gt>
+
+This library is free software; you can redistribute it and/or modify
+it under the same terms as Perl itself.
+
=cut
projects / p5sagit/p5-mst-13.2.git / blobdiff