+#
+# $Id: Encode.pm,v 2.9 2004/12/03 19:16:40 dankogai Exp $
+#
package Encode;
use strict;
-our $VERSION = do { my @r = (q$Revision: 1.32 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
-our $DEBUG = 0;
+# our $VERSION = do { my @r = (q$Revision: 2.9 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
+our $VERSION = '2.0902_01';
+sub DEBUG () { 0 }
+use XSLoader ();
+XSLoader::load(__PACKAGE__, $VERSION);
-require DynaLoader;
require Exporter;
-
-our @ISA = qw(Exporter DynaLoader);
+use base qw/Exporter/;
# Public, encouraged API is exported by default
-our @EXPORT = qw (
- decode
- decode_utf8
- encode
- encode_utf8
- encodings
- find_encoding
+
+our @EXPORT = qw(
+ decode decode_utf8 encode encode_utf8
+ encodings find_encoding clone_encoding
);
+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 =
- qw(
- _utf8_off
- _utf8_on
- define_encoding
- from_to
- is_16bit
- is_8bit
- is_utf8
- resolve_alias
- utf8_downgrade
- utf8_upgrade
- );
-
-bootstrap Encode ();
+ (
+ 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,
+ );
+
+our %EXPORT_TAGS =
+ (
+ all => [ @EXPORT, @EXPORT_OK ],
+ fallbacks => [ @FB_CONSTS ],
+ fallback_all => [ @FB_CONSTS, @FB_FLAGS ],
+ );
# Documentation moved after __END__ for speed - NI-S
-use Carp;
-
our $ON_EBCDIC = (ord("A") == 193);
use Encode::Alias;
# Make a %Encoding package variable to allow a certain amount of cheating
our %Encoding;
-use Encode::Config;
+our %ExtModule;
+require Encode::Config;
+eval { require Encode::ConfigLocal };
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{
+ my $obj = ref($_[0]) ? $_[0] : find_encoding($_[0]);
+ $obj->can("perlio_ok") and return $obj->perlio_ok();
+ return 0; # safety net
}
sub define_encoding
$Encoding{$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('renew') 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
+sub find_encoding($;$)
{
- my ($name,$skip_external) = @_;
+ 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 $obj->name;
return;
}
-sub encode
+sub clone_encoding($){
+ my $obj = find_encoding(shift);
+ ref $obj or return;
+ eval { require Storable };
+ $@ and return;
+ return Storable::dclone($obj);
+}
+
+sub encode($$;$)
{
- my ($name,$string,$check) = @_;
+ my ($name, $string, $check) = @_;
+ return undef unless defined $string;
+ $string .= '' if ref $string; # stringify;
+ $check ||=0;
my $enc = find_encoding($name);
- croak("Unknown encoding '$name'") unless defined $enc;
+ unless(defined $enc){
+ require Carp;
+ Carp::croak("Unknown encoding '$name'");
+ }
my $octets = $enc->encode($string,$check);
- return undef if ($check && length($string));
+ $_[1] = $string if $check and !($check & LEAVE_SRC());
return $octets;
}
-sub decode
+sub decode($$;$)
{
my ($name,$octets,$check) = @_;
+ return undef unless defined $octets;
+ $octets .= '' if ref $octets;
+ $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;
+ $_[1] = $octets if $check and !($check & LEAVE_SRC());
return $string;
}
-sub from_to
+sub from_to($$$;$)
{
my ($string,$from,$to,$check) = @_;
+ return undef unless defined $string;
+ $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);
return defined($_[0] = $string) ? length($string) : undef ;
}
-sub encode_utf8
+sub encode_utf8($)
{
my ($str) = @_;
utf8::encode($str);
return $str;
}
-sub decode_utf8
+sub decode_utf8($;$)
{
- my ($str) = @_;
- return undef unless utf8::decode($str);
- return $str;
+ my ($str, $check) = @_;
+ if ($check){
+ return decode("utf8", $str, $check);
+ }else{
+ return undef unless utf8::decode($str);
+ return $str;
+ }
}
-predefine_encodings();
+predefine_encodings(1);
#
# This is to restore %Encoding if really needed;
#
+
sub predefine_encodings{
- if ($ON_EBCDIC) {
+ use Encode::Encoding;
+ no warnings 'redefine';
+ my $use_xs = shift;
+ 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 = '';
for (my $i = 0; $i < length($str); $i++) {
- $res .=
+ $res .=
chr(utf8::unicode_to_native(ord(substr($str,$i,1))));
}
$_[1] = '' if $chk;
my ($obj,$str,$chk) = @_;
my $res = '';
for (my $i = 0; $i < length($str); $i++) {
- $res .=
+ $res .=
chr(utf8::native_to_unicode(ord(substr($str,$i,1))));
}
$_[1] = '' if $chk;
return $res;
};
- $Encode::Encoding{Internal} =
+ $Encode::Encoding{Unicode} =
bless {Name => "UTF_EBCDIC"} => "Encode::UTF_EBCDIC";
- } else {
- # was in Encode::UTF_EBCDIC
+ } else {
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);
return $str;
};
*encode = \&decode;
- $Encode::Encoding{Unicode} =
+ $Encode::Encoding{Unicode} =
bless {Name => "Internal"} => "Encode::Internal";
}
{
# was in Encode::utf8
package Encode::utf8;
- *name = sub{ shift->{'Name'} };
- *new_sequence = sub{ return $_[0] };
- *decode = sub{
- my ($obj,$octets,$chk) = @_;
- my $str = Encode::decode_utf8($octets);
- if (defined $str) {
+ 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 $str;
+ 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));
+ $$rpos = $npos + length($trm);
+ return 1;
}
- return undef;
- };
- *encode = sub {
- my ($obj,$string,$chk) = @_;
- my $octets = Encode::encode_utf8($string);
- $_[1] = '' if $chk;
- return $octets;
+ $$rdst .= substr($$rsrc, $pos);
+ $$rpos = length($$rsrc);
+ return '';
};
- $Encode::Encoding{utf8} =
+ $Encode::Encoding{utf8} =
bless {Name => "utf8"} => "Encode::utf8";
- }
- # do externals if necessary
- require File::Basename;
- require File::Spec;
- for my $ext (qw()){
- my $pm =
- File::Spec->catfile(File::Basename::dirname($INC{'Encode.pm'}),
- "Encode", "$ext.pm");
- do $pm;
+ $Encode::Encoding{"utf-8-strict"} =
+ bless {Name => "utf-8-strict", strict_utf8 => 1 } => "Encode::utf8";
}
}
-require Encode::Encoding;
-require Encode::XS;
-
1;
__END__
use Encode;
-
=head2 Table of Contents
-Encode consists of a collection of modules which details are too big
+Encode consists of a collection of modules whose details are too big
to fit in one document. This POD itself explains the top-level APIs
-and general topics at a glance. For other topics and more details,
-see the PODs below;
+and general topics at a glance. For other topics and more details,
+see the PODs below:
Name Description
--------------------------------------------------------
- Encode::Alias Alias defintions to encodings
+ Encode::Alias Alias definitions to encodings
Encode::Encoding Encode Implementation Base Class
Encode::Supported List of Supported Encodings
Encode::CN Simplified Chinese Encodings
the legacy encoding is some variant of EBCDIC rather than a super-set
of ASCII - see L<perlebcdic>).
-Traditionally computer data has been moved around in 8-bit chunks
+Traditionally, computer data has been moved around in 8-bit chunks
often called "bytes". These chunks are also known as "octets" in
networking standards. Perl is widely used to manipulate data of many
types - not only strings of characters representing human or computer
-languages but also "binary" data being the machines representation of
+languages but also "binary" data being the machine's representation of
numbers, pixels in an image - or just about anything.
-When Perl is processing "binary data" the programmer wants Perl to
+When Perl is processing "binary data", the programmer wants Perl to
process "sequences of bytes". This is not a problem for Perl - as a
-byte has 256 possible values it easily fits in Perl's much larger
+byte has 256 possible values, it easily fits in Perl's much larger
"logical character".
=head2 TERMINOLOGY
-=over 4
+=over 2
=item *
=item *
I<octet>: 8 bits of data, with ordinal values 0..255
-(Term for bytes passed to or from a non-Perl context, e.g. disk file.)
+(Term for bytes passed to or from a non-Perl context, e.g. a disk file.)
=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 string from Perl's internal form into I<ENCODING> and returns
+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
-alias. For encoding names and aliases, see L</"Defining Aliases">.
-For CHECK see L</"Handling Malformed Data">.
+an alias. For encoding names and aliases, see L</"Defining Aliases">.
+For CHECK, see L</"Handling Malformed Data">.
+
+For example, to convert a string from Perl's internal format to
+iso-8859-1 (also known as Latin1),
+
+ $octets = encode("iso-8859-1", $string);
-For example to convert (internally UTF-8 encoded) Unicode string to
-iso-8859-1 (also known as Latin1),
+B<CAVEAT>: When you run C<$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.
- $octets = encode("iso-8859-1", $unicode);
+If the $string is C<undef> then C<undef> is returned.
-=item $string = decode(ENCODING, $octets[, CHECK])
+=item $string = decode(ENCODING, $octets [, CHECK])
-Decode sequence of octets assumed to be in I<ENCODING> into Perl's
-internal form and returns the resulting string. as in encode(),
-ENCODING can be either a canonical name or alias. For encoding names
-and aliases, see L</"Defining Aliases">. For CHECK see
+Decodes a sequence of octets assumed to be in I<ENCODING> into Perl's
+internal form and returns the resulting string. As in encode(),
+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 ISO-8859-1 data to UTF-8:
+For example, to convert ISO-8859-1 data to a string in Perl's internal format:
- $utf8 = decode("iso-8859-1", $latin1);
+ $string = decode("iso-8859-1", $octets);
-=item [$length =] from_to($string, FROM_ENCODING, TO_ENCODING [,CHECK])
+B<CAVEAT>: When you run C<$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.
-Convert B<in-place> the data between two encodings. How did the data
-in $string originally get to be in FROM_ENCODING? Either using
-encode() or through PerlIO: See L</"Encoding and IO">.
-For encoding names and aliases, see L</"Defining Aliases">.
-For CHECK see L</"Handling Malformed Data">.
+If the $string is C<undef> then C<undef> is returned.
-For example to convert ISO-8859-1 data to UTF-8:
+=item [$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.
+converted cannot be a string constant; it must be a scalar variable.
-from_to() return the length of the converted string on success, undef
-otherwise.
+from_to() returns the length of the converted string in octets on
+success, I<undef> on error.
-=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 standard 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 returned as a sequence of bytes. All possible
+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
@all_encodings = Encode->encodings(":all");
-Or you can give the name of specific module.
+Or you can give the name of a specific module.
@with_jp = Encode->encodings("Encode::JP");
@ebcdic = Encode->encodings("EBCDIC");
-To find which encodings are supported by this package in details,
+To find out in detail which encodings are supported by this package,
see L<Encode::Supported>.
=head2 Defining Aliases
-To add new alias to a given encoding, Use;
+To add a new alias to a given encoding, use:
use Encode;
use Encode::Alias;
Encode::resolve_alias("iso-8859-12") # false; nonexistent
Encode::resolve_alias($name) eq $name # true if $name is canonical
-This resolve_alias() does not need C<use Encode::Alias> and is
-exported via C<use encode qw(resolve_alias)>.
+resolve_alias() does not need C<use Encode::Alias>; it can be
+exported via C<use Encode qw(resolve_alias)>.
-See L<Encode::Alias> on details.
+See L<Encode::Alias> for details.
-=head1 Encoding and IO
+=head1 Encoding via PerlIO
-It is very common to want to do encoding transformations when
-reading or writing files, network connections, pipes etc.
-If Perl is configured to use the new 'perlio' IO system then
-C<Encode> provides a "layer" (See L<perliol>) which can transform
-data as it is read or written.
+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.
-Here is how the blind poet would modernise the encoding:
+ # via PerlIO
+ open my $in, "<:encoding(shiftjis)", $infile or die;
+ open my $out, ">:encoding(euc-jp)", $outfile or die;
+ while(<$in>){ print $out $_; }
- use Encode;
- open(my $iliad,'<:encoding(iso-8859-7)','iliad.greek');
- open(my $utf8,'>:utf8','iliad.utf8');
- my @epic = <$iliad>;
- print $utf8 @epic;
- close($utf8);
- close($illiad);
+ # via from_to
+ open my $in, "<", $infile or die;
+ open my $out, ">", $outfile or die;
+ while(<$in>){
+ from_to($_, "shiftjis", "euc-jp", 1);
+ print $out $_;
+ }
+
+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.
-In addition the new IO system can also be configured to read/write
-UTF-8 encoded characters (as noted above this is efficient):
+ Encode::perlio_ok("hz"); # False
+ find_encoding("euc-cn")->perlio_ok; # True where PerlIO is available
- open(my $fh,'>:utf8','anything');
- print $fh "Any \x{0021} string \N{SMILEY FACE}\n";
+ use Encode qw(perlio_ok); # exported upon request
+ perlio_ok("euc-jp")
-Either of the above forms of "layer" specifications can be made the default
-for a lexical scope with the C<use open ...> pragma. See L<open>.
+Fortunately, all encodings that come with Encode core are PerlIO-savvy
+except for hz and ISO-2022-kr. For gory details, see
+L<Encode::Encoding> and L<Encode::PerlIO>.
-Once a handle is open is layers can be altered using C<binmode>.
+=head1 Handling Malformed Data
+
+The optional I<CHECK> argument is used as follows. When you omit it,
+Encode::FB_DEFAULT ( == 0 ) is assumed.
-Without any such configuration, or if Perl itself is built using
-system's own IO, then write operations assume that file handle accepts
-only I<bytes> and will C<die> if a character larger than 255 is
-written to the handle. When reading, each octet from the handle
-becomes a byte-in-a-character. Note that this default is the same
-behaviour as bytes-only languages (including Perl before v5.6) would
-have, and is sufficient to handle native 8-bit encodings
-e.g. iso-8859-1, EBCDIC etc. and any legacy mechanisms for handling
-other encodings and binary data.
+=over 2
-In other cases it is the programs responsibility to transform
-characters into bytes using the API above before doing writes, and to
-transform the bytes read from a handle into characters before doing
-"character operations" (e.g. C<lc>, C</\W+/>, ...).
+=item B<NOTE:> Not all encoding suppport this feature
-You can also use PerlIO to convert larger amounts of data you don't
-want to bring into memory. For example to convert between ISO-8859-1
-(Latin 1) and UTF-8 (or UTF-EBCDIC in EBCDIC machines):
+Some encodings ignore I<CHECK> argument. For example,
+L<Encode::Unicode> ignores I<CHECK> and it always croaks on error.
- open(F, "<:encoding(iso-8859-1)", "data.txt") or die $!;
- open(G, ">:utf8", "data.utf") or die $!;
- while (<F>) { print G }
+=back
- # Could also do "print G <F>" but that would pull
- # the whole file into memory just to write it out again.
+Now here is the list of I<CHECK> values available
-More examples:
+=over 2
- open(my $f, "<:encoding(cp1252)")
- open(my $g, ">:encoding(iso-8859-2)")
- open(my $h, ">:encoding(latin9)") # iso-8859-15
+=item I<CHECK> = Encode::FB_DEFAULT ( == 0)
-See L<PerlIO> for more information.
+If I<CHECK> is 0, (en|de)code will put a I<substitution character> in
+place of a malformed character. When you encode, E<lt>subcharE<gt>
+will be used. When you decode the code point C<0xFFFD> is used. If
+the data is supposed to be UTF-8, an optional lexical warning
+(category utf8) is given.
-See also L<encoding> for how to change the default encoding of the
-data in your script.
+=item I<CHECK> = Encode::FB_CROAK ( == 1)
-=head1 Handling Malformed Data
+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
+error with eval{} unless you really want to let it die.
+
+=item I<CHECK> = Encode::FB_QUIET
+
+If I<CHECK> is set to Encode::FB_QUIET, (en|de)code will immediately
+return the portion of the data that has been processed so far when an
+error occurs. The data argument will be overwritten with everything
+after that point (that is, the unprocessed part of data). This is
+handy when you have to call decode repeatedly in the case where your
+source data may contain partial multi-byte character sequences,
+(i.e. you are reading with a fixed-width buffer). Here is a sample
+code that does exactly this:
+
+ my $buffer = ''; my $string = '';
+ while(read $fh, $buffer, 256, length($buffer)){
+ $string .= decode($encoding, $buffer, Encode::FB_QUIET);
+ # $buffer now contains the unprocessed partial character
+ }
-If I<CHECK> is not set, (en|de)code will put I<substitution character> in
-place of the malformed character. for UCM-based encodings,
-E<lt>subcharE<gt> will be used. For Unicode, \xFFFD is used. If the
-data is supposed to be UTF-8, an optional lexical warning (category
-utf8) is given.
+=item I<CHECK> = Encode::FB_WARN
-If I<CHECK> is true but not a code reference, dies with an error message.
+This is the same as above, except that it warns on error. Handy when
+you are debugging the mode above.
-In future you will be able to use a code reference to a callback
+=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, 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<NNN>;> where I<NNN> is a decimal number and
+XML uses C<&#xI<HHHH>;> where I<HHHH> is the hexadecimal number.
+
+In Encode 2.10 or later, C<LEAVE_SRC> is also implied.
+
+=item The bitmask
+
+These modes are actually set via a bitmask. Here is how the FB_XX
+constants are laid out. You can import the FB_XX constants via
+C<use Encode qw(:fallbacks)>; you can import the generic bitmask
+constants via C<use Encode qw(:fallback_all)>.
+
+ FB_DEFAULT FB_CROAK FB_QUIET FB_WARN FB_PERLQQ
+ DIE_ON_ERR 0x0001 X
+ WARN_ON_ERR 0x0002 X
+ RETURN_ON_ERR 0x0004 X X
+ LEAVE_SRC 0x0008 X
+ PERLQQ 0x0100 X
+ HTMLCREF 0x0200
+ XMLCREF 0x0400
+
+=back
+
+=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<$object>. The object
-should provide the interface described in L<Encode::Encoding>
+should provide the interface described in L<Encode::Encoding>.
If more than two arguments are provided then additional
-arguments are taken as aliases for I<$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.
+implementation. As such, they are efficient but may change.
-=over 4
+=over 2
=item is_utf8(STRING [, CHECK])
-[INTERNAL] Test whether the UTF-8 flag is turned on in the STRING.
+[INTERNAL] Tests whether the UTF-8 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.
+As of perl 5.8.1, L<utf8> also has utf8::is_utf8().
+
=item _utf8_on(STRING)
-[INTERNAL] Turn on the UTF-8 flag in STRING. The data in STRING is
+[INTERNAL] Turns on the UTF-8 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 test the return value as
-I<not> success or failure), or C<undef> if STRING is not a string.
+state of the UTF-8 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] Turn off the UTF-8 flag in STRING. Do not use frivolously.
-Returns the previous state of the UTF-8 flag (so please don't test the
-return value as I<not> success or failure), or C<undef> if STRING is
+[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
+return value as indicating success or failure), or C<undef> if STRING is
not a string.
=back
+=head1 UTF-8 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
+ computers, 0 .. 2**64-1) -- Programming Perl, 3rd ed.
+
+That has been the perl's notion of UTF-8 but official UTF-8 is more
+strict; Its ranges is much narrower (0 .. 10FFFF), some sequences are
+not allowed (i.e. Those used in the surrogate pair, 0xFFFE, et al).
+
+Now that is overruled by Larry Wall himself.
+
+ From: Larry Wall <larry@wall.org>
+ Date: December 04, 2004 11:51:58 JST
+ To: perl-unicode@perl.org
+ Subject: Re: Make Encode.pm support the real UTF-8
+ Message-Id: <20041204025158.GA28754@wall.org>
+
+ On Fri, Dec 03, 2004 at 10:12:12PM +0000, Tim Bunce wrote:
+ : I've no problem with 'utf8' being perl's unrestricted uft8 encoding,
+ : but "UTF-8" is the name of the standard and should give the
+ : corresponding behaviour.
+
+ For what it's worth, that's how I've always kept them straight in my
+ head.
+
+ Also for what it's worth, Perl 6 will mostly default to strict but
+ make it easy to switch back to lax.
+
+ Larry
+
+Do you copy? As of Perl 5.8.7, B<UTF-8> means strict, official UTF-8
+while B<utf8> means liberal, lax, version thereof. And Encode version
+2.10 or later thus groks the difference between C<UTF-8> and C"utf8".
+
+ encode("utf8", "\x{FFFF_FFFF}", 1); # okay
+ encode("UTF-8", "\x{FFFF_FFFF}", 1); # croaks
+
+C<UTF-8> in Encode is actually a canonical name for C<utf-8-strict>.
+Yes, the hyphen between "UTF" and "8" is important. Without it Encode
+goes "liberal"
+
+ 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("UTF8")->name # is 'utf8'.
+
+
=head1 SEE ALSO
L<Encode::Encoding>,
L<Encode::Supported>,
-L<PerlIO>,
+L<Encode::PerlIO>,
L<encoding>,
-L<perlebcdic>,
-L<perlfunc/open>,
-L<perlunicode>,
-L<utf8>,
+L<perlebcdic>,
+L<perlfunc/open>,
+L<perlunicode>,
+L<utf8>,
the Perl Unicode Mailing List E<lt>perl-unicode@perl.orgE<gt>
+=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 we can all share.
+
=cut
https://perl5.git.perl.org / perl5.git / blobdiff