+#
+# $Id: Encode.pm,v 1.75 2002/06/01 18:07:42 dankogai Exp $
+#
package Encode;
use strict;
-our $VERSION = do { my @r = (q$Revision: 1.57 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
+our $VERSION = do { my @r = (q$Revision: 1.75 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
our $DEBUG = 0;
use XSLoader ();
-XSLoader::load 'Encode';
+XSLoader::load(__PACKAGE__, $VERSION);
require Exporter;
-our @ISA = qw(Exporter);
+use base qw/Exporter/;
# Public, encouraged API is exported by default
encodings find_encoding
);
-our @FB_FLAGS = qw(DIE_ON_ERR WARN_ON_ERR RETURN_ON_ERR LEAVE_SRC PERLQQ);
-our @FB_CONSTS = qw(FB_DEFAULT FB_QUIET FB_WARN FB_PERLQQ FB_CROAK);
+our @FB_FLAGS = qw(DIE_ON_ERR WARN_ON_ERR RETURN_ON_ERR LEAVE_SRC
+ PERLQQ HTMLCREF XMLCREF);
+our @FB_CONSTS = qw(FB_DEFAULT FB_CROAK FB_QUIET FB_WARN
+ FB_PERLQQ FB_HTMLCREF FB_XMLCREF);
our @EXPORT_OK =
(
# Documentation moved after __END__ for speed - NI-S
-use Carp;
-
our $ON_EBCDIC = (ord("A") == 193);
use Encode::Alias;
sub encodings
{
my $class = shift;
- my @modules = (@_ and $_[0] eq ":all") ? values %ExtModule : @_;
- for my $mod (@modules){
- $mod =~ s,::,/,g or $mod = "Encode/$mod";
- $mod .= '.pm';
- $DEBUG and warn "about to require $mod;";
- eval { require $mod; };
+ 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} = $mod;
+ }
+ }
}
- my %modules = map {$_ => 1} @modules;
return
sort { lc $a cmp lc $b }
- grep {!/^(?:Internal|Unicode)$/o} keys %Encoding;
+ grep {!/^(?:Internal|Unicode|Guess)$/o} keys %enc;
}
sub perlio_ok{
$Encoding{$name} = $obj;
my $lc = lc($name);
define_alias($lc => $obj) unless $lc eq $name;
- while (@_)
- {
+ while (@_){
my $alias = shift;
- define_alias($alias,$obj);
+ define_alias($alias, $obj);
}
return $obj;
}
sub getEncoding
{
- my ($class,$name,$skip_external) = @_;
- my $enc;
- if (ref($name) && $name->can('new_sequence'))
- {
- return $name;
- }
+ my ($class, $name, $skip_external) = @_;
+
+ ref($name) && $name->can('new_sequence') and return $name;
+ exists $Encoding{$name} and return $Encoding{$name};
my $lc = lc $name;
- if (exists $Encoding{$name})
- {
- return $Encoding{$name};
- }
- if (exists $Encoding{$lc})
- {
- return $Encoding{$lc};
- }
+ exists $Encoding{$lc} and return $Encoding{$lc};
my $oc = $class->find_alias($name);
- return $oc if defined $oc;
-
- $oc = $class->find_alias($lc) if $lc ne $name;
- return $oc if defined $oc;
+ defined($oc) and return $oc;
+ $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; };
- return $Encoding{$name} if exists $Encoding{$name};
+ exists $Encoding{$name} and return $Encoding{$name};
}
}
return;
sub find_encoding
{
- my ($name,$skip_external) = @_;
+ my ($name, $skip_external) = @_;
return __PACKAGE__->getEncoding($name,$skip_external);
}
sub encode($$;$)
{
- my ($name,$string,$check) = @_;
+ my ($name, $string, $check) = @_;
$check ||=0;
my $enc = find_encoding($name);
- croak("Unknown encoding '$name'") unless defined $enc;
+ unless(defined $enc){
+ require Carp;
+ Carp::croak("Unknown encoding '$name'");
+ }
my $octets = $enc->encode($string,$check);
return undef if ($check && length($string));
return $octets;
my ($name,$octets,$check) = @_;
$check ||=0;
my $enc = find_encoding($name);
- croak("Unknown encoding '$name'") unless defined $enc;
+ unless(defined $enc){
+ require Carp;
+ Carp::croak("Unknown encoding '$name'");
+ }
my $string = $enc->decode($octets,$check);
$_[1] = $octets if $check;
return $string;
my ($string,$from,$to,$check) = @_;
$check ||=0;
my $f = find_encoding($from);
- croak("Unknown encoding '$from'") unless defined $f;
+ unless (defined $f){
+ require Carp;
+ Carp::croak("Unknown encoding '$from'");
+ }
my $t = find_encoding($to);
- croak("Unknown encoding '$to'") unless defined $t;
+ 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,$check);
#
# This is to restore %Encoding if really needed;
#
+
sub predefine_encodings{
+ use Encode::Encoding;
if ($ON_EBCDIC) {
# was in Encode::UTF_EBCDIC
package Encode::UTF_EBCDIC;
- *name = sub{ shift->{'Name'} };
- *new_sequence = sub{ return $_[0] };
+ push @Encode::UTF_EBCDIC::ISA, 'Encode::Encoding';
*decode = sub{
my ($obj,$str,$chk) = @_;
my $res = '';
$Encode::Encoding{Unicode} =
bless {Name => "UTF_EBCDIC"} => "Encode::UTF_EBCDIC";
} else {
- # was in Encode::UTF_EBCDIC
package Encode::Internal;
- *name = sub{ shift->{'Name'} };
- *new_sequence = sub{ return $_[0] };
+ push @Encode::Internal::ISA, 'Encode::Encoding';
*decode = sub{
my ($obj,$str,$chk) = @_;
utf8::upgrade($str);
{
# was in Encode::utf8
package Encode::utf8;
- *name = sub{ shift->{'Name'} };
- *new_sequence = sub{ return $_[0] };
+ push @Encode::utf8::ISA, 'Encode::Encoding';
*decode = sub{
my ($obj,$octets,$chk) = @_;
my $str = Encode::decode_utf8($octets);
$_[1] = '' if $chk;
return $octets;
};
- $Encode::Encoding{utf8} =
+ $Encode::Encoding{utf8} =
bless {Name => "utf8"} => "Encode::utf8";
}
}
=head2 TERMINOLOGY
-=over 4
+=over 2
=item *
=back
-The marker [INTERNAL] marks Internal Implementation Details, in
-general meant only for those who think they know what they are doing,
-and such details may change in future releases.
-
=head1 PERL ENCODING API
-=over 4
+=over 2
-=item $octets = encode(ENCODING, $string[, CHECK])
+=item $octets = encode(ENCODING, $string [, CHECK])
Encodes a string from Perl's internal form into I<ENCODING> and returns
a sequence of octets. ENCODING can be either a canonical name or
an alias. For encoding names and aliases, see L</"Defining Aliases">.
For CHECK, see L</"Handling Malformed Data">.
-For example, to convert (internally UTF-8 encoded) Unicode string to
+For example, to convert a string from Perl's internal format to
iso-8859-1 (also known as Latin1),
- $octets = encode("iso-8859-1", $unicode);
+ $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.
-=item $string = decode(ENCODING, $octets[, CHECK])
+encode($valid_encoding, undef) is harmless but warns you for
+C<Use of uninitialized value in subroutine entry>.
+encode($valid_encoding, '') is harmless and warnless.
+
+=item $string = decode(ENCODING, $octets [, CHECK])
Decodes a sequence of octets assumed to be in I<ENCODING> into Perl's
internal form and returns the resulting string. As in encode(),
and aliases, see L</"Defining Aliases">. For CHECK, see
L</"Handling Malformed Data">.
-For example, to convert ISO-8859-1 data to UTF-8:
+For example, to convert ISO-8859-1 data to a string in Perl's internal format:
+
+ $string = decode("iso-8859-1", $octets);
- $utf8 = decode("iso-8859-1", $latin1);
+B<CAVEAT>: When you run C<$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 $octets entirely consists of
+ASCII data (or EBCDIC on EBCDIC machines). See L</"The UTF-8 flag">
+below.
-=item [$length =] from_to($string, FROM_ENCODING, TO_ENCODING [,CHECK])
+decode($valid_encoding, undef) is harmless but warns you for
+C<Use of uninitialized value in subroutine entry>.
+decode($valid_encoding, '') is harmless and warnless.
-Converts B<in-place> data between two encodings.
-For example, to convert ISO-8859-1 data to UTF-8:
+=item [$length =] from_to($octets, FROM_ENC, TO_ENC [, CHECK])
- from_to($data, "iso-8859-1", "utf-8");
+Converts B<in-place> data between two encodings. The data in $octets
+must be encoded as octets and not as characters in Perl's internal
+format. For example, to convert ISO-8859-1 data to Microsoft's CP1250 encoding:
+
+ from_to($octets, "iso-8859-1", "cp1250");
and to convert it back:
- from_to($data, "utf-8", "iso-8859-1");
+ from_to($octets, "cp1250", "iso-8859-1");
Note that because the conversion happens in place, the data to be
converted cannot be a string constant; it must be a scalar variable.
-from_to() returns the length of the converted string on success, undef
+from_to() returns the length of the converted string in octets on success, undef
otherwise.
-=back
+B<CAVEAT>: The following operations look the same but are not quite so;
-=head2 UTF-8 / utf8
+ from_to($data, "iso-8859-1", "utf8"); #1
+ $data = decode("iso-8859-1", $data); #2
-The Unicode Consortium defines the UTF-8 transformation format as a
-way of encoding the entire Unicode repertoire as sequences of octets.
-This encoding is expected to become very widespread. Perl can use this
-form internally to represent strings, so conversions to and from this
-form are particularly efficient (as octets in memory do not have to
-change, just the meta-data that tells Perl how to treat them).
+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
-=over 4
+ $data = encode("utf8", decode("iso-8859-1", $data));
+
+See L</"The UTF-8 flag"> below.
=item $octets = encode_utf8($string);
-The characters that comprise $string are encoded in Perl's superset of
-UTF-8 and the resulting octets are returned as a sequence of bytes. All
-possible characters have a UTF-8 representation so this function cannot
-fail.
+Equivalent to C<$octets = encode("utf8", $string);> The characters
+that comprise $string are encoded in Perl's internal format and the
+result is returned as a sequence of octets. All possible
+characters have a UTF-8 representation so this function cannot fail.
+
=item $string = decode_utf8($octets [, CHECK]);
-The sequence of octets represented by $octets is decoded from UTF-8
-into a sequence of logical characters. Not all sequences of octets
-form valid UTF-8 encodings, so it is possible for this call to fail.
-For CHECK, see L</"Handling Malformed Data">.
+equivalent to C<$string = decode("utf8", $octets [, CHECK])>.
+The sequence of octets represented by
+$octets is decoded from UTF-8 into a sequence of logical
+characters. Not all sequences of octets form valid UTF-8 encodings, so
+it is possible for this call to fail. For CHECK, see
+L</"Handling Malformed Data">.
=back
=head1 Encoding via PerlIO
-If your perl supports I<PerlIO>, you can use a PerlIO layer to decode
+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;
open my $out, ">:encoding(euc-jp)", $outfile or die;
- while(<>){ print; }
+ while(<$in>){ print $out $_; }
# via from_to
open my $in, "<", $infile or die;
open my $out, ">", $outfile or die;
- while(<>){
+ while(<$in>){
from_to($_, "shiftjis", "euc-jp", 1);
+ print $out $_;
}
-Unfortunately, there may be encodings are PerlIO-savvy. You can check
+Unfortunately, it may be that encodings are PerlIO-savvy. You can check
if your encoding is supported by PerlIO by calling the C<perlio_ok>
method.
perlio_ok("euc-jp")
Fortunately, all encodings that come with Encode core are PerlIO-savvy
-except for hz and ISO-2022-kr. See L<Encode::Encoding> for details.
-
-For gory details, see L<Encode::PerlIO>.
+except for hz and ISO-2022-kr. For gory details, see L<Encode::Encoding> and L<Encode::PerlIO>.
=head1 Handling Malformed Data
-=over 4
+=over 2
The I<CHECK> argument is used as follows. When you omit it,
the behaviour is the same as if you had passed a value of 0 for
If I<CHECK> is 0, (en|de)code will put a I<substitution character>
in place of a malformed character. For UCM-based encodings,
-E<lt>subcharE<gt> will be used. For Unicode, "\x{FFFD}" is used.
+E<lt>subcharE<gt> will be used. For Unicode, the code point C<0xFFFD> is used.
If the data is supposed to be UTF-8, an optional lexical warning
(category utf8) is given.
-=item I<CHECK> = Encode::DIE_ON_ERROR (== 1)
+=item I<CHECK> = Encode::FB_CROAK ( == 1)
-If I<CHECK> is 1, methods will die immediately with an error
+If I<CHECK> is 1, methods will die on error immediately with an error
message. Therefore, when I<CHECK> is set to 1, you should trap the
fatal error with eval{} unless you really want to let it die on error.
sequences, for example because you are reading with a fixed-width
buffer. Here is some sample code that does exactly this:
- my $data = '';
+ my $data = ''; my $utf8 = '';
while(defined(read $fh, $buffer, 256)){
# buffer may end in a partial character so we append
$data .= $buffer;
=item perlqq mode (I<CHECK> = Encode::FB_PERLQQ)
+=item HTML charref mode (I<CHECK> = Encode::FB_HTMLCREF)
+
+=item XML charref mode (I<CHECK> = Encode::FB_XMLCREF)
+
For encodings that are implemented by Encode::XS, CHECK ==
Encode::FB_PERLQQ turns (en|de)code into C<perlqq> fallback mode.
-When you decode, '\xI<XX>' will be inserted for a malformed character,
-where I<XX> is the hex representation of the octet that could not be
-decoded to utf8. And when you encode, '\x{I<xxxx>}' will be inserted,
-where I<xxxx> is the Unicode ID of the character that cannot be found
+When you decode, C<\xI<HH>> will be inserted for a malformed character,
+where I<HH> is the hex representation of the octet that could not be
+decoded to utf8. And when you encode, C<\x{I<HHHH>}> will be inserted,
+where I<HHHH> is the Unicode ID of the character that cannot be found
in the character repertoire of the encoding.
+HTML/XML character reference modes are about the same, in place of
+C<\x{I<HHHH>}>, HTML uses C<&#I<NNNN>>; where I<NNNN> is a decimal digit and
+XML uses C<&#xI<HHHH>>; where I<HHHH> is the hexadecimal digit.
+
=item The bitmask
These modes are actually set via a bitmask. Here is how the FB_XX
FB_DEFAULT FB_CROAK FB_QUIET FB_WARN FB_PERLQQ
DIE_ON_ERR 0x0001 X
- WARN_ON_ER 0x0002 X
+ WARN_ON_ERR 0x0002 X
RETURN_ON_ERR 0x0004 X X
LEAVE_SRC 0x0008
PERLQQ 0x0100 X
+ HTMLCREF 0x0200
+ XMLCREF 0x0400
=head2 Unimplemented fallback schemes
In the future, you will be able to use a code reference to a callback
function for the value of I<CHECK> but its API is still undecided.
+The fallback scheme does not work on EBCDIC platforms.
+
=head1 Defining Encodings
To define a new encoding, use:
- use Encode qw(define_alias);
+ use Encode qw(define_encoding);
define_encoding($object, 'canonicalName' [, alias...]);
I<canonicalName> will be associated with I<$object>. The object
should provide the interface described in L<Encode::Encoding>.
If more than two arguments are provided then additional
-arguments are taken as aliases for I<$object>, as for C<define_alias>.
+arguments are taken as aliases for I<$object>.
See L<Encode::Encoding> for more details.
-=head1 Messing with Perl's Internals
+=head1 The UTF-8 flag
+
+Before the introduction of utf8 support in perl, The C<eq> operator
+just compared the strings represented by two scalars. Beginning with
+perl 5.8, C<eq> compares two strings with simultaneous consideration
+of I<the utf8 flag>. To explain why we made it so, I will quote page
+402 of C<Programming Perl, 3rd ed.>
+
+=over 2
+
+=item Goal #1:
+
+Old byte-oriented programs should not spontaneously break on the old
+byte-oriented data they used to work on.
+
+=item Goal #2:
+
+Old byte-oriented programs should magically start working on the new
+character-oriented data when appropriate.
+
+=item Goal #3:
+
+Programs should run just as fast in the new character-oriented mode
+as in the old byte-oriented mode.
+
+=item Goal #4:
+
+Perl should remain one language, rather than forking into a
+byte-oriented Perl and a character-oriented Perl.
+
+=back
+
+Back when C<Programming Perl, 3rd ed.> was written, not even Perl 5.6.0
+was born and many features documented in the book remained
+unimplemented for a long time. Perl 5.8 corrected this and the introduction
+of the UTF-8 flag is one of them. You can think of this perl notion as of a
+byte-oriented mode (utf8 flag off) and a character-oriented mode (utf8
+flag on).
+
+Here is how Encode takes care of the utf8 flag.
+
+=over 2
+
+=item *
+
+When you encode, the resulting utf8 flag is always off.
+
+=item
+
+When you decode, the resulting utf8 flag is on unless you can
+unambiguously represent data. Here is the definition of
+dis-ambiguity.
+
+After C<$utf8 = decode('foo', $octet);>,
+
+ When $octet is... The utf8 flag in $utf8 is
+ ---------------------------------------------
+ In ASCII only (or EBCDIC only) OFF
+ In ISO-8859-1 ON
+ In any other Encoding ON
+ ---------------------------------------------
+
+As you see, there is one exception, In ASCII. That way you can assue
+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
+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.
+
+=back
+
+=head2 Messing with Perl's Internals
The following API uses parts of Perl's internals in the current
implementation. As such, they are efficient but may change.
-=over 4
+=over 2
=item is_utf8(STRING [, CHECK])
=head1 MAINTAINER
This project was originated by Nick Ing-Simmons and later maintained
-by Dan Kogai E<lt>dankogai@dan.co.jpE<gt>. See AUTHORS for a full list
-of people involved. For any questions, use
-E<lt>perl-unicode@perl.orgE<gt> so others can share.
+by Dan Kogai E<lt>dankogai@dan.co.jpE<gt>. See AUTHORS for a full
+list of people involved. For any questions, use
+E<lt>perl-unicode@perl.orgE<gt> so we can all share.
=cut