package Encode;
use strict;
-our $VERSION = do { my @r = (q$Revision: 0.99 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
+our $VERSION = do { my @r = (q$Revision: 1.26 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
our $DEBUG = 0;
require DynaLoader;
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;
-
-our %ExtModule =
- (
- viscii => 'Encode/Byte.pm',
- 'koi8-r' => 'Encode/Byte.pm',
- cp1047 => 'Encode/EBCDIC.pm',
- cp37 => 'Encode/EBCDIC.pm',
- 'posix-bc' => 'Encode/EBCDIC.pm',
- symbol => 'Encode/Symbol.pm',
- dingbats => 'Encode/Symbol.pm',
- );
+our %ExtModule;
+
+my @codepages = qw(
+ 37 424 437 500 737 775 850 852 855
+ 856 857 860 861 862 863 864 865 866
+ 869 874 875 932 936 949 950 1006 1026
+ 1047 1250 1251 1252 1253 1254 1255 1256 1257
+ 1258
+ );
+
+my @macintosh = qw(
+ CentralEurRoman Croatian Cyrillic Greek
+ Iceland Roman Rumanian Sami
+ Thai Turkish Ukrainian
+ );
for my $k (2..11,13..16){
$ExtModule{"iso-8859-$k"} = 'Encode/Byte.pm';
}
-for my $k (1250..1258){
+for my $k (@codepages){
$ExtModule{"cp$k"} = 'Encode/Byte.pm';
}
-unless ($ON_EBCDIC) { # CJK added to autoload unless EBCDIC env
-%ExtModule =(
- %ExtModule,
- 'euc-cn' => 'Encode/CN.pm',
- gb2312 => 'Encode/CN.pm',
- gb12345 => 'Encode/CN.pm',
- gbk => 'Encode/CN.pm',
- cp936 => 'Encode/CN.pm',
- 'iso-ir-165' => 'Encode/CN.pm',
- 'euc-jp' => 'Encode/JP.pm',
- 'iso-2022-jp' => 'Encode/JP.pm',
- 'iso-2022-jp-1' => 'Encode/JP.pm',
- '7bit-jis' => 'Encode/JP.pm',
- shiftjis => 'Encode/JP.pm',
- macjapan => 'Encode/JP.pm',
- cp932 => 'Encode/JP.pm',
- 'euc-kr' => 'Encode/KR.pm',
- ksc5601 => 'Encode/KR.pm',
- cp949 => 'Encode/KR.pm',
- big5 => 'Encode/TW.pm',
- 'big5-hkscs' => 'Encode/TW.pm',
- cp950 => 'Encode/TW.pm',
- gb18030 => 'Encode/HanExtra.pm',
- big5plus => 'Encode/HanExtra.pm',
- 'euc-tw' => 'Encode/HanExtra.pm',
- );
-}
-
-for my $k (qw(centeuro croatian cyrillic dingbats greek
- iceland roman rumanian sami
- thai turkish ukraine))
+for my $k (@macintosh)
{
$ExtModule{"mac$k"} = 'Encode/Byte.pm';
}
+%ExtModule =
+ (%ExtModule,
+ 'koi8-r' => 'Encode/Byte.pm',
+ 'posix-bc' => 'Encode/EBCDIC.pm',
+ cp037 => 'Encode/EBCDIC.pm',
+ cp1026 => 'Encode/EBCDIC.pm',
+ cp1047 => 'Encode/EBCDIC.pm',
+ cp500 => 'Encode/EBCDIC.pm',
+ cp875 => 'Encode/EBCDIC.pm',
+ dingbats => 'Encode/Symbol.pm',
+ macDingbats => 'Encode/Symbol.pm',
+ macSymbol => 'Encode/Symbol.pm',
+ symbol => 'Encode/Symbol.pm',
+ viscii => 'Encode/Byte.pm',
+);
+
+unless ($ON_EBCDIC) { # CJK added to autoload unless EBCDIC env
+%ExtModule =
+ (%ExtModule,
+
+ 'cp936' => 'Encode/CN.pm',
+ 'euc-cn' => 'Encode/CN.pm',
+ 'gb12345-raw' => 'Encode/CN.pm',
+ 'gb2312-raw' => 'Encode/CN.pm',
+ 'gbk' => 'Encode/CN.pm',
+ 'iso-ir-165' => 'Encode/CN.pm',
+
+ '7bit-jis' => 'Encode/JP.pm',
+ 'cp932' => 'Encode/JP.pm',
+ 'euc-jp' => 'Encode/JP.pm',
+ 'iso-2022-jp' => 'Encode/JP.pm',
+ 'iso-2022-jp-1' => 'Encode/JP.pm',
+ 'jis0201-raw' => 'Encode/JP.pm',
+ 'jis0208-raw' => 'Encode/JP.pm',
+ 'jis0212-raw' => 'Encode/JP.pm',
+ 'macJapanese' => 'Encode/JP.pm',
+ 'shiftjis' => 'Encode/JP.pm',
+
+ 'cp949' => 'Encode/KR.pm',
+ 'euc-kr' => 'Encode/KR.pm',
+ 'ksc5601' => 'Encode/KR.pm',
+ 'macKorean' => 'Encode/KR.pm',
+
+ 'big5' => 'Encode/TW.pm',
+ 'big5-hkscs' => 'Encode/TW.pm',
+ 'cp950' => 'Encode/TW.pm',
+
+ 'big5plus' => 'Encode/HanExtra.pm',
+ 'euc-tw' => 'Encode/HanExtra.pm',
+ 'gb18030' => 'Encode/HanExtra.pm',
+ );
+}
sub encodings
{
croak("Unknown encoding '$to'") unless defined $t;
my $uni = $f->decode($string,$check);
return undef if ($check && length($string));
- $string = $t->encode($uni,$check);
+ $string = $t->encode($uni,$check);
return undef if ($check && length($uni));
- return length($_[0] = $string);
+ return defined($_[0] = $string) ? length($string) : undef ;
}
sub encode_utf8
return $str;
}
+predefine_encodings();
+
+#
+# This is to restore %Encoding if really needed;
+#
+sub predefine_encodings{
+ if ($ON_EBCDIC) {
+ # was in Encode::UTF_EBCDIC
+ package Encode::UTF_EBCDIC;
+ *name = sub{ shift->{'Name'} };
+ *new_sequence = sub{ return $_[0] };
+ *decode = sub{
+ my ($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 {
+ # was in Encode::UTF_EBCDIC
+ package Encode::Internal;
+ *name = sub{ shift->{'Name'} };
+ *new_sequence = sub{ return $_[0] };
+ *decode = sub{
+ my ($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;
+ *name = sub{ shift->{'Name'} };
+ *new_sequence = sub{ return $_[0] };
+ *decode = sub{
+ my ($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;
+ };
+ $Encode::Encoding{utf8} =
+ bless {Name => "utf8"}, "Encode::utf8";
+ }
+ # do externals if necessary
+ require File::Basename;
+ require File::Spec;
+ for my $ext (qw(Unicode)){
+ my $pm =
+ File::Spec->catfile(File::Basename::dirname($INC{'Encode.pm'}),
+ "Encode", "$ext.pm");
+ do $pm;
+ }
+}
+
require Encode::Encoding;
require Encode::XS;
-require Encode::Internal;
-require Encode::Unicode;
-require Encode::utf8;
-require Encode::10646_1;
-require Encode::ucs2_le;
1;
use Encode;
+
+=head2 Table of Contents
+
+Encode consists of a collection of modules which 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;
+
+ Name Description
+ --------------------------------------------------------
+ Encode::Alias Alias defintions to encodings
+ Encode::Encoding Encode Implementation Base Class
+ Encode::Supported List of Supported Encodings
+ Encode::CN Simplified Chinese Encodings
+ Encode::JP Japanese Encodings
+ Encode::KR Korean Encodings
+ Encode::TW Traditional Chinese Encodings
+ --------------------------------------------------------
+
=head1 DESCRIPTION
The C<Encode> module provides the interfaces between Perl's strings
-and the rest of the system. Perl strings are sequences of B<characters>.
+and the rest of the system. Perl strings are sequences of
+B<characters>.
+
+The repertoire of characters that Perl can represent is at least that
+defined by the Unicode Consortium. On most platforms the ordinal
+values of the characters (as returned by C<ord(ch)>) is the "Unicode
+codepoint" for the character (the exceptions are those platforms where
+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
+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
+numbers, pixels in an image - or just about anything.
+
+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
+"logical character".
+
+=head2 TERMINOLOGY
-To find more about character encodings, please consult
-L<Encode::Details>. This document focuses on programming references.
+=over 4
-=head1 PERL ENCODING API
+=item *
+
+I<character>: a character in the range 0..(2**32-1) (or more).
+(What Perl's strings are made of.)
+
+=item *
+
+I<byte>: a character in the range 0..255
+(A special case of a Perl character.)
+
+=item *
-=head2 Generic Encoding Interface
+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.)
+
+=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
-=item $bytes = encode(ENCODING, $string[, CHECK])
+=item $octets = encode(ENCODING, $string[, CHECK])
Encodes string from Perl's internal form into I<ENCODING> and returns
-a sequence of octets. For CHECK see L</"Handling Malformed Data">.
+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">.
-For example to convert (internally UTF-8 encoded) Unicode data
-to octets:
+For example to convert (internally UTF-8 encoded) Unicode string to
+iso-8859-1 (also known as Latin1),
- $octets = encode("utf8", $unicode);
+ $octets = encode("iso-8859-1", $unicode);
-=item $string = decode(ENCODING, $bytes[, 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. For CHECK see
+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
L</"Handling Malformed Data">.
For example to convert ISO-8859-1 data to UTF-8:
- $utf8 = decode("latin1", $latin1);
+ $utf8 = decode("iso-8859-1", $latin1);
-=item from_to($string, FROM_ENCODING, TO_ENCODING[, CHECK])
+=item [$length =] from_to($string, FROM_ENCODING, TO_ENCODING [,CHECK])
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 CHECK
-see L</"Handling Malformed Data">.
+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">.
For example to convert ISO-8859-1 data to UTF-8:
Note that because the conversion happens in place, the data to be
converted cannot be a string constant, it must be a scalar variable.
-=back
-
-=head2 Handling Malformed Data
-
-If CHECK is not set, C<undef> is returned. If the data is supposed to
-be UTF-8, an optional lexical warning (category utf8) is given. If
-CHECK is true but not a code reference, dies.
-
-It would desirable to have a way to indicate that transform should use
-the encodings "replacement character" - no such mechanism is defined yet.
-
-It is also planned to allow I<CHECK> to be a code reference.
-
-This is not yet implemented as there are design issues with what its
-arguments should be and how it returns its results.
-
-=over 4
-
-=item Scheme 1
-
-Passed remaining fragment of string being processed.
-Modifies it in place to remove bytes/characters it can understand
-and returns a string used to represent them.
-e.g.
-
- sub fixup {
- my $ch = substr($_[0],0,1,'');
- return sprintf("\x{%02X}",ord($ch);
- }
-
-This scheme is close to how underlying C code for Encode works, but gives
-the fixup routine very little context.
-
-=item Scheme 2
-
-Passed original string, and an index into it of the problem area, and
-output string so far. Appends what it will to output string and
-returns new index into original string. For example:
-
- sub fixup {
- # my ($s,$i,$d) = @_;
- my $ch = substr($_[0],$_[1],1);
- $_[2] .= sprintf("\x{%02X}",ord($ch);
- return $_[1]+1;
- }
-
-This scheme gives maximal control to the fixup routine but is more
-complicated to code, and may need internals of Encode to be tweaked to
-keep original string intact.
-
-=item Other Schemes
-
-Hybrids of above.
-
-Multiple return values rather than in-place modifications.
-
-Index into the string could be C<pos($str)> allowing C<s/\G...//>.
+from_to() return the length of the converted string on success, undef
+otherwise.
=back
=over 4
-=item $bytes = encode_utf8($string);
+=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
characters have a UTF-8 representation so this function cannot fail.
-=item $string = decode_utf8($bytes [, CHECK]);
+=item $string = decode_utf8($octets [, CHECK]);
-The sequence of octets represented by $bytes is decoded from UTF-8
+The sequence of octets represented by $octets is decoded from UTF-8
into a sequence of logical characters. Not all sequences of octets
form valid UTF-8 encodings, so it is possible for this call to fail.
For CHECK see L</"Handling Malformed Data">.
=head2 Defining Aliases
+To add new alias to a given encoding, Use;
+
use Encode;
use Encode::Alias;
define_alias(newName => ENCODING);
-Allows newName to be used as am alias for ENCODING. ENCODING may be
-either the name of an encoding or and encoding object (as above).
+After that, newName can be used as an alias for ENCODING.
+ENCODING may be either the name of an encoding or an
+I<encoding object>
See L<Encode::Alias> on details.
-=head1 Defining Encodings
-
- use Encode qw(define_alias);
- define_encoding($object, 'canonicalName' [, alias...]);
-
-Causes I<canonicalName> to be associated with I<$object>. The object
-should provide the interface described in L<Encode::Encoding>
-below. If more than two arguments are provided then additional
-arguments are taken as aliases for I<$object> as for C<define_alias>.
-
=head1 Encoding and IO
It is very common to want to do encoding transformations when
See also L<encoding> for how to change the default encoding of the
data in your script.
+=head1 Handling Malformed Data
+
+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.
+
+If I<CHECK> is true but not a code reference, dies with an error message.
+
+In 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.
+
+=head1 Defining Encodings
+
+To define a new encoding, use:
+
+ use Encode qw(define_alias);
+ 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>.
+
+See L<Encode::Encoding> for more details.
+
=head1 Messing with Perl's Internals
The following API uses parts of Perl's internals in the current
=head1 SEE ALSO
-L<Encode::Details>,
L<Encode::Encoding>,
L<Encode::Supported>,
L<PerlIO>,