package Encode;
use strict;
-
-our $VERSION = '0.02';
+our $VERSION = do { my @r = (q$Revision: 0.95 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
require DynaLoader;
require Exporter;
use Carp;
+use Encode::Alias;
+
# Make a %encoding package variable to allow a certain amount of cheating
our %encoding;
-my @alias; # ordered matching list
-my %alias; # cached known aliases
-
- # 0 1 2 3 4 5 6 7 8 9 10
-our @latin2iso_num = ( 0, 1, 2, 3, 4, 9, 10, 13, 14, 15, 16 );
-
-our %winlatin2cp = (
- 'Latin1' => 1252,
- 'Latin2' => 1250,
- 'Cyrillic' => 1251,
- 'Baltic' => 1257,
- 'Greek' => 1253,
- 'Turkish' => 1254,
- 'Hebrew' => 1255,
- 'Arabic' => 1256,
- 'Baltic' => 1257,
- 'Vietnamese' => 1258,
- );
+
+our %external_tables =
+ (
+ 'euc-cn' => 'Encode/CN.pm',
+ gb2312 => 'Encode/CN.pm',
+ gb12345 => 'Encode/CN.pm',
+ gbk => 'Encode/CN.pm',
+ cp936 => 'Encode/CN.pm',
+ 'iso-ir-165' => 'Encode/CN.pm',
+ 'euc-jp' => 'Encode/JP.pm',
+ 'iso-2022-jp' => 'Encode/JP.pm',
+ '7bit-jis' => 'Encode/JP.pm',
+ shiftjis => 'Encode/JP.pm',
+ macjapan => 'Encode/JP.pm',
+ cp932 => 'Encode/JP.pm',
+ 'euc-kr' => 'Encode/KR.pm',
+ ksc5601 => 'Encode/KR.pm',
+ cp949 => 'Encode/KR.pm',
+ big5 => 'Encode/TW.pm',
+ 'big5-hkscs' => 'Encode/TW.pm',
+ cp950 => 'Encode/TW.pm',
+ gb18030 => 'Encode/HanExtra.pm',
+ big5plus => 'Encode/HanExtra.pm',
+ 'euc-tw' => 'Encode/HanExtra.pm',
+ );
sub encodings
{
my ($class) = @_;
- return keys %encoding;
+ return
+ map { $_->[0] }
+ sort { $a->[1] cmp $b->[1] }
+ map { [$_, lc $_] }
+ grep { $_ ne 'Internal' }
+ keys %encoding;
}
-sub findAlias
+sub define_encoding
{
- my $class = shift;
- local $_ = shift;
- unless (exists $alias{$_})
- {
- for (my $i=0; $i < @alias; $i += 2)
+ my $obj = shift;
+ my $name = shift;
+ $encoding{$name} = $obj;
+ my $lc = lc($name);
+ define_alias($lc => $obj) unless $lc eq $name;
+ while (@_)
{
- my $alias = $alias[$i];
- my $val = $alias[$i+1];
- my $new;
- if (ref($alias) eq 'Regexp' && $_ =~ $alias)
- {
- $new = eval $val;
- }
- elsif (ref($alias) eq 'CODE')
- {
- $new = &{$alias}($val)
- }
- elsif (lc($_) eq lc($alias))
- {
- $new = $val;
- }
- if (defined($new))
- {
- next if $new eq $_; # avoid (direct) recursion on bugs
- my $enc = (ref($new)) ? $new : find_encoding($new);
- if ($enc)
- {
- $alias{$_} = $enc;
- last;
- }
- }
+ my $alias = shift;
+ define_alias($alias,$obj);
}
- }
- return $alias{$_};
+ return $obj;
}
-sub define_alias
+sub getEncoding
{
- while (@_)
- {
- my ($alias,$name) = splice(@_,0,2);
- push(@alias, $alias => $name);
- }
-}
+ my ($class,$name,$skip_external) = @_;
+ my $enc;
+ if (ref($name) && $name->can('new_sequence'))
+ {
+ return $name;
+ }
+ my $lc = lc $name;
+ if (exists $encoding{$name})
+ {
+ return $encoding{$name};
+ }
+ if (exists $encoding{$lc})
+ {
+ return $encoding{$lc};
+ }
-# Allow variants of iso-8859-1 etc.
-define_alias( qr/^iso[-_]?(\d+)[-_](\d+)$/i => '"iso-$1-$2"' );
-
-# At least HP-UX has these.
-define_alias( qr/^iso8859(\d+)$/i => '"iso-8859-$1"' );
-
-# More HP stuff.
-define_alias( qr/^(?:hp-)?(arabic|greek|hebrew|kana|roman|thai|turkish)8$/i => '"${1}8"' );
-
-# This is a font issue, not an encoding issue.
-# (The currency symbol of the Latin 1 upper half
-# has been redefined as the euro symbol.)
-define_alias( qr/^(.+)\@euro$/i => '"$1"' );
-
-# Allow latin-1 style names as well
-define_alias( qr/^(?:iso[-_]?)?latin[-_]?(\d+)$/i => '"iso-8859-$latin2iso_num[$1]"' );
-
-# Allow winlatin1 style names as well
-define_alias( qr/^win(latin[12]|cyrillic|baltic|greek|turkish|hebrew|arabic|baltic|vietnamese)$/i => '"cp$winlatin2cp{\u$1}"' );
-
-# Common names for non-latin prefered MIME names
-define_alias( 'ascii' => 'US-ascii',
- 'cyrillic' => 'iso-8859-5',
- 'arabic' => 'iso-8859-6',
- 'greek' => 'iso-8859-7',
- 'hebrew' => 'iso-8859-8',
- 'thai' => 'iso-8859-11',
- 'tis620' => 'iso-8859-11',
- );
-
-# At least AIX has IBM-NNN (surprisingly...) instead of cpNNN.
-define_alias( qr/^ibm[-_]?(\d\d\d\d?)$/i => '"cp$1"');
-
-# Standardize on the dashed versions.
-define_alias( qr/^utf8$/i => 'utf-8' );
-define_alias( qr/^koi8r$/i => 'koi8-r' );
-define_alias( qr/^koi8u$/i => 'koi8-u' );
-
-# TODO: HP-UX '8' encodings arabic8 greek8 hebrew8 kana8 thai8 turkish8
-# TODO: HP-UX '15' encodings japanese15 korean15 roi15
-# TODO: Cyrillic encoding ISO-IR-111 (useful?)
-# TODO: Chinese encodings GB18030 GBK Big5-HSKCS EUC-TW
-# TODO: Armenian encoding ARMSCII-8
-# TODO: Hebrew encoding ISO-8859-8-1
-# TODO: Thai encoding TCVN
-# TODO: Korean encoding Johab
-# TODO: Vietnamese encodings VISCII VPS
-# TODO: Japanese encoding JIS (not the same as SJIS)
-# TODO: Mac Asian+African encodings: Arabic Armenian Bengali Burmese
-# ChineseSimp ChineseTrad Devanagari Ethiopic ExtArabic
-# Farsi Georgian Gujarati Gurmukhi Hebrew Japanese
-# Kannada Khmer Korean Laotian Malayalam Mongolian
-# Oriya Sinhalese Symbol Tamil Telugu Tibetan Vietnamese
-# TODO: what is the Japanese 'UJIS' encoding seen in some Linuxes?
-
-# Map white space and _ to '-'
-define_alias( qr/^(\S+)[\s_]+(.*)$/i => '"$1-$2"' );
+ my $oc = $class->findAlias($name);
+ return $oc if defined $oc;
-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);
- }
- return $obj;
-}
+ $oc = $class->findAlias($lc) if $lc ne $name;
+ return $oc if defined $oc;
-sub getEncoding
-{
- my ($class,$name) = @_;
- my $enc;
- if (ref($name) && $name->can('new_sequence'))
- {
- return $name;
- }
- if (exists $encoding{$name})
- {
- return $encoding{$name};
- }
- else
- {
- return $class->findAlias($name);
- }
+ if (!$skip_external and exists $external_tables{$lc})
+ {
+ require $external_tables{$lc};
+ return $encoding{$name} if exists $encoding{$name};
+ }
+
+ return;
}
sub find_encoding
{
- my ($name) = @_;
- return __PACKAGE__->getEncoding($name);
+ my ($name,$skip_external) = @_;
+ return __PACKAGE__->getEncoding($name,$skip_external);
}
sub encode
{
- my ($name,$string,$check) = @_;
- my $enc = find_encoding($name);
- croak("Unknown encoding '$name'") unless defined $enc;
- my $octets = $enc->encode($string,$check);
- return undef if ($check && length($string));
- return $octets;
+ my ($name,$string,$check) = @_;
+ my $enc = find_encoding($name);
+ croak("Unknown encoding '$name'") unless defined $enc;
+ my $octets = $enc->encode($string,$check);
+ return undef if ($check && length($string));
+ return $octets;
}
sub decode
{
- my ($name,$octets,$check) = @_;
- my $enc = find_encoding($name);
- croak("Unknown encoding '$name'") unless defined $enc;
- my $string = $enc->decode($octets,$check);
- return undef if ($check && length($octets));
- return $string;
+ my ($name,$octets,$check) = @_;
+ my $enc = find_encoding($name);
+ croak("Unknown encoding '$name'") unless defined $enc;
+ my $string = $enc->decode($octets,$check);
+ $_[1] = $octets if $check;
+ return $string;
}
sub from_to
{
- my ($string,$from,$to,$check) = @_;
- my $f = find_encoding($from);
- croak("Unknown encoding '$from'") unless defined $f;
- my $t = find_encoding($to);
- croak("Unknown encoding '$to'") unless defined $t;
- my $uni = $f->decode($string,$check);
- return undef if ($check && length($string));
- $string = $t->encode($uni,$check);
- return undef if ($check && length($uni));
- return length($_[0] = $string);
+ my ($string,$from,$to,$check) = @_;
+ my $f = find_encoding($from);
+ croak("Unknown encoding '$from'") unless defined $f;
+ my $t = find_encoding($to);
+ croak("Unknown encoding '$to'") unless defined $t;
+ my $uni = $f->decode($string,$check);
+ return undef if ($check && length($string));
+ $string = $t->encode($uni,$check);
+ return undef if ($check && length($uni));
+ return length($_[0] = $string);
}
sub encode_utf8
{
- my ($str) = @_;
- utf8::encode($str);
- return $str;
+ my ($str) = @_;
+ utf8::encode($str);
+ return $str;
}
sub decode_utf8
{
- my ($str) = @_;
- return undef unless utf8::decode($str);
- return $str;
-}
-
-package Encode::Encoding;
-# Base class for classes which implement encodings
-
-sub Define
-{
- my $obj = shift;
- my $canonical = shift;
- $obj = bless { Name => $canonical },$obj unless ref $obj;
- # warn "$canonical => $obj\n";
- Encode::define_encoding($obj, $canonical, @_);
+ my ($str) = @_;
+ return undef unless utf8::decode($str);
+ return $str;
}
-sub name { shift->{'Name'} }
-
-# Temporary legacy methods
-sub toUnicode { shift->decode(@_) }
-sub fromUnicode { shift->encode(@_) }
-
-sub new_sequence { return $_[0] }
-
-package Encode::XS;
-use base 'Encode::Encoding';
-
-package Encode::Internal;
-use base 'Encode::Encoding';
-
-# Dummy package that provides the encode interface but leaves data
-# as UTF-X encoded. It is here so that from_to() works.
-
-__PACKAGE__->Define('Internal');
-
-Encode::define_alias( 'Unicode' => 'Internal' ) if ord('A') == 65;
-
-sub decode
-{
- my ($obj,$str,$chk) = @_;
- utf8::upgrade($str);
- $_[1] = '' if $chk;
- return $str;
-}
-
-*encode = \&decode;
-
-package Encoding::Unicode;
-use base 'Encode::Encoding';
-
-__PACKAGE__->Define('Unicode') unless ord('A') == 65;
-
-sub decode
-{
- my ($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 $res;
-}
-
-sub encode
-{
- my ($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;
-}
-
-
-package Encode::utf8;
-use base 'Encode::Encoding';
-# package to allow long-hand
-# $octets = encode( utf8 => $string );
-#
-
-__PACKAGE__->Define(qw(UTF-8 utf8));
-
-sub decode
-{
- my ($obj,$octets,$chk) = @_;
- my $str = Encode::decode_utf8($octets);
- if (defined $str)
- {
- $_[1] = '' if $chk;
- return $str;
- }
- return undef;
-}
-
-sub encode
-{
- my ($obj,$string,$chk) = @_;
- my $octets = Encode::encode_utf8($string);
- $_[1] = '' if $chk;
- return $octets;
-}
-
-package Encode::iso10646_1;
-use base 'Encode::Encoding';
-# Encoding is 16-bit network order Unicode (no surogates)
-# Used for X font encodings
-
-__PACKAGE__->Define(qw(UCS-2 iso-10646-1));
-
-sub decode
-{
- my ($obj,$str,$chk) = @_;
- my $uni = '';
- while (length($str))
- {
- my $code = unpack('n',substr($str,0,2,'')) & 0xffff;
- $uni .= chr($code);
- }
- $_[1] = $str if $chk;
- utf8::upgrade($uni);
- return $uni;
-}
-
-sub encode
-{
- my ($obj,$uni,$chk) = @_;
- my $str = '';
- while (length($uni))
- {
- my $ch = substr($uni,0,1,'');
- my $x = ord($ch);
- unless ($x < 32768)
- {
- last if ($chk);
- $x = 0;
- }
- $str .= pack('n',$x);
- }
- $_[1] = $uni if $chk;
- return $str;
-}
-
-package Encode::ucs_2le;
-use base 'Encode::Encoding';
-
-__PACKAGE__->Define(qw(UCS-2le UCS-2LE ucs-2le));
-
-sub decode
-{
- my ($obj,$str,$chk) = @_;
- my $uni = '';
- while (length($str))
- {
- my $code = unpack('v',substr($str,0,2,'')) & 0xffff;
- $uni .= chr($code);
- }
- $_[1] = $str if $chk;
- utf8::upgrade($uni);
- return $uni;
-}
-
-sub encode
-{
- my ($obj,$uni,$chk) = @_;
- my $str = '';
- while (length($uni))
- {
- my $ch = substr($uni,0,1,'');
- my $x = ord($ch);
- unless ($x < 32768)
- {
- last if ($chk);
- $x = 0;
- }
- $str .= pack('v',$x);
- }
- $_[1] = $uni if $chk;
- return $str;
-}
-
-# switch back to Encode package in case we ever add AutoLoader
-package Encode;
+require Encode::Encoding;
+require Encode::XS;
+require Encode::Internal;
+require Encode::Unicode;
+require Encode::utf8;
+require Encode::iso10646_1;
+require Encode::ucs2_le;
1;
The C<Encode> module provides the interfaces between Perl's strings
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>).
-
-Traditionaly 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
-
-=over 4
-
-=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 *
-
-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 ENCODINGS
-
-=head2 Characteristics of an Encoding
-
-An encoding has a "repertoire" of characters that it can represent,
-and for each representable character there is at least one sequence of
-octets that represents it.
-
-=head2 Types of Encodings
-
-Encodings can be divided into the following types:
-
-=over 4
-
-=item * Fixed length 8-bit (or less) encodings.
-
-Each character is a single octet so may have a repertoire of up to
-256 characters. ASCII and iso-8859-* are typical examples.
-
-=item * Fixed length 16-bit encodings
-
-Each character is two octets so may have a repertoire of up to
-65 536 characters. Unicode's UCS-2 is an example. Also used for
-encodings for East Asian languages.
-
-=item * Fixed length 32-bit encodings.
-
-Not really very "encoded" encodings. The Unicode code points
-are just represented as 4-octet integers. None the less because
-different architectures use different representations of integers
-(so called "endian") there at least two disctinct encodings.
-
-=item * Multi-byte encodings
-
-The number of octets needed to represent a character varies.
-UTF-8 is a particularly complex but regular case of a multi-byte
-encoding. Several East Asian countries use a multi-byte encoding
-where 1-octet is used to cover western roman characters and Asian
-characters get 2-octets.
-(UTF-16 is strictly a multi-byte encoding taking either 2 or 4 octets
-to represent a Unicode code point.)
-
-=item * "Escape" encodings.
-
-These encodings embed "escape sequences" into the octet sequence
-which describe how the following octets are to be interpreted.
-The iso-2022-* family is typical. Following the escape sequence
-octets are encoded by an "embedded" encoding (which will be one
-of the above types) until another escape sequence switches to
-a different "embedded" encoding.
-
-These schemes are very flexible and can handle mixed languages but are
-very complex to process (and have state). No escape encodings are
-implemented for Perl yet.
-
-=back
-
-=head2 Specifying Encodings
-
-Encodings can be specified to the API described below in two ways:
-
-=over 4
-
-=item 1. By name
-
-Encoding names are strings with characters taken from a restricted
-repertoire. See L</"Encoding Names">.
-
-=item 2. As an object
-
-Encoding objects are returned by C<find_encoding($name)>.
-
-=back
-
-=head2 Encoding Names
-
-Encoding names are case insensitive. White space in names is ignored.
-In addition an encoding may have aliases. Each encoding has one
-"canonical" name. The "canonical" name is chosen from the names of
-the encoding by picking the first in the following sequence:
-
-=over 4
-
-=item * The MIME name as defined in IETF RFC-XXXX.
-
-=item * The name in the IANA registry.
-
-=item * The name used by the the organization that defined it.
-
-=back
-
-Because of all the alias issues, and because in the general case
-encodings have state C<Encode> uses the encoding object internally
-once an operation is in progress.
+To find more about character encodings, please consult
+L<Encode::Details> . This document focuses on programming references.
=head1 PERL ENCODING API
Encodes string from Perl's internal form into I<ENCODING> and returns
a sequence of octets. For CHECK see L</"Handling Malformed Data">.
+For example to convert (internally UTF-8 encoded) Unicode data
+to octets:
+
+ $octets = encode("utf8", $unicode);
+
=item *
$string = decode(ENCODING, $bytes[, CHECK])
internal form and returns the resulting string. For CHECK see
L</"Handling Malformed Data">.
+For example to convert ISO-8859-1 data to UTF-8:
+
+ $utf8 = decode("latin1", $latin1);
+
=item *
from_to($string, FROM_ENCODING, TO_ENCODING[, CHECK])
encode() or through PerlIO: See L</"Encoding and IO">. 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 UTF-8:
from_to($data, "iso-8859-1", "utf-8");
=back
-=head2 Other Encodings of Unicode
-
-UTF-16 is similar to UCS-2, 16 bit or 2-byte chunks. UCS-2 can only
-represent 0..0xFFFF, while UTF-16 has a "surrogate pair" scheme which
-allows it to cover the whole Unicode range.
-
-Encode implements big-endian UCS-2 aliased to "iso-10646-1" as that
-happens to be the name used by that representation when used with X11
-fonts.
-
-UTF-32 or UCS-4 is 32-bit or 4-byte chunks. Perl's logical characters
-can be considered as being in this form without encoding. An encoding
-to transfer strings in this form (e.g. to write them to a file) would
-need to
-
- pack('L*', unpack('U*', $string)); # native
- or
- pack('V*', unpack('U*', $string)); # little-endian
- or
- pack('N*', unpack('U*', $string)); # big-endian
-
-depending on the endianness required.
-
-No UTF-32 encodings are implemented yet.
-
-Both UCS-2 and UCS-4 style encodings can have "byte order marks" by
-representing the code point 0xFFFE as the very first thing in a file.
-
=head2 Listing available encodings
use Encode qw(encodings);
@list = encodings();
-Returns a list of the canonical names of the available encodings.
+Returns a list of the canonical names of the available encodings.
+
+To find which encodings are suppoted by this package in details,
+see L<Encode::Supported>.
=head2 Defining Aliases
Allows newName to be used as am alias for ENCODING. ENCODING may be
either the name of an encoding or and encoding object (as above).
-Currently I<newName> can be specified in the following ways:
-
-=over 4
-
-=item As a simple string.
+See L<Encode::Alias> on details.
-=item As a qr// compiled regular expression, e.g.:
-
- define_alias( qr/^iso8859-(\d+)$/i => '"iso-8859-$1"' );
-
-In this case if I<ENCODING> is not a reference it is C<eval>-ed to
-allow C<$1> etc. to be subsituted. The example is one way to names as
-used in X11 font names to alias the MIME names for the iso-8859-*
-family.
-
-=item As a code reference, e.g.:
-
- define_alias( sub { return /^iso8859-(\d+)$/i ? "iso-8859-$1" : undef } , '');
-
-In this case C<$_> will be set to the name that is being looked up and
-I<ENCODING> is passed to the sub as its first argument. The example
-is another way to names as used in X11 font names to alias the MIME
-names for the iso-8859-* family.
-
-=back
-
-=head2 Defining Encodings
+=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</"IMPLEMENTATION CLASSES">
+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>.
"character operations" (e.g. C<lc>, C</\W+/>, ...).
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
+want to bring into memory. For example to convert between ISO-8859-1
(Latin 1) and UTF-8 (or UTF-EBCDIC in EBCDIC machines):
open(F, "<:encoding(iso-8859-1)", "data.txt") or die $!;
See L<PerlIO> for more information.
-=head1 Encoding How to ...
-
-To do:
-
-=over 4
-
-=item * IO with mixed content (faking iso-2020-*)
-
-=item * MIME's Content-Length:
-
-=item * UTF-8 strings in binary data.
-
-=item * Perl/Encode wrappers on non-Unicode XS modules.
-
-=back
+See also L<encoding> for how to change the default encoding of the
+data in your script.
=head1 Messing with Perl's Internals
If CHECK is true, also checks the data in STRING for being well-formed
UTF-8. Returns true if successful, false otherwise.
-=item * valid_utf8(STRING)
-
-[INTERNAL] Test whether STRING is in a consistent state. Will return
-true if string is held as bytes, or is well-formed UTF-8 and has the
-UTF-8 flag on. Main reason for this routine is to allow Perl's
-testsuite to check that operations have left strings in a consistent
-state.
-
=item *
_utf8_on(STRING)
=back
-=head1 IMPLEMENTATION CLASSES
-
-As mentioned above encodings are (in the current implementation at least)
-defined by objects. The mapping of encoding name to object is via the
-C<%encodings> hash.
-
-The values of the hash can currently be either strings or objects.
-The string form may go away in the future. The string form occurs
-when C<encodings()> has scanned C<@INC> for loadable encodings but has
-not actually loaded the encoding in question. This is because the
-current "loading" process is all Perl and a bit slow.
-
-Once an encoding is loaded then value of the hash is object which
-implements the encoding. The object should provide the following
-interface:
-
-=over 4
-
-=item -E<gt>name
-
-Should return the string representing the canonical name of the encoding.
-
-=item -E<gt>new_sequence
-
-This is a placeholder for encodings with state. It should return an
-object which implements this interface, all current implementations
-return the original object.
-
-=item -E<gt>encode($string,$check)
-
-Should return the octet sequence representing I<$string>. If I<$check>
-is true it should modify I<$string> in place to remove the converted
-part (i.e. the whole string unless there is an error). If an error
-occurs it should return the octet sequence for the fragment of string
-that has been converted, and modify $string in-place to remove the
-converted part leaving it starting with the problem fragment.
-
-If check is is false then C<encode> should make a "best effort" to
-convert the string - for example by using a replacement character.
-
-=item -E<gt>decode($octets,$check)
-
-Should return the string that I<$octets> represents. If I<$check> is
-true it should modify I<$octets> in place to remove the converted part
-(i.e. the whole sequence unless there is an error). If an error
-occurs it should return the fragment of string that has been
-converted, and modify $octets in-place to remove the converted part
-leaving it starting with the problem fragment.
-
-If check is is false then C<decode> should make a "best effort" to
-convert the string - for example by using Unicode's "\x{FFFD}" as a
-replacement character.
-
-=back
-
-It should be noted that the check behaviour is different from the
-outer public API. The logic is that the "unchecked" case is useful
-when encoding is part of a stream which may be reporting errors
-(e.g. STDERR). In such cases it is desirable to get everything
-through somehow without causing additional errors which obscure the
-original one. Also the encoding is best placed to know what the
-correct replacement character is, so if that is the desired behaviour
-then letting low level code do it is the most efficient.
-
-In contrast if check is true, the scheme above allows the encoding to
-do as much as it can and tell layer above how much that was. What is
-lacking at present is a mechanism to report what went wrong. The most
-likely interface will be an additional method call to the object, or
-perhaps (to avoid forcing per-stream objects on otherwise stateless
-encodings) and additional parameter.
-
-It is also highly desirable that encoding classes inherit from
-C<Encode::Encoding> as a base class. This allows that class to define
-additional behaviour for all encoding objects. For example built in
-Unicode, UCS-2 and UTF-8 classes use :
-
- package Encode::MyEncoding;
- use base qw(Encode::Encoding);
-
- __PACKAGE__->Define(qw(myCanonical myAlias));
-
-To create an object with bless {Name => ...},$class, and call
-define_encoding. They inherit their C<name> method from
-C<Encode::Encoding>.
-
-=head2 Compiled Encodings
-
-F<Encode.xs> provides a class C<Encode::XS> which provides the
-interface described above. It calls a generic octet-sequence to
-octet-sequence "engine" that is driven by tables (defined in
-F<encengine.c>). The same engine is used for both encode and
-decode. C<Encode:XS>'s C<encode> forces Perl's characters to their
-UTF-8 form and then treats them as just another multibyte
-encoding. C<Encode:XS>'s C<decode> transforms the sequence and then
-turns the UTF-8-ness flag as that is the form that the tables are
-defined to produce. For details of the engine see the comments in
-F<encengine.c>.
-
-The tables are produced by the Perl script F<compile> (the name needs
-to change so we can eventually install it somewhere). F<compile> can
-currently read two formats:
-
-=over 4
-
-=item *.enc
-
-This is a coined format used by Tcl. It is documented in
-Encode/EncodeFormat.pod.
-
-=item *.ucm
-
-This is the semi-standard format used by IBM's ICU package.
-
-=back
-
-F<compile> can write the following forms:
-
-=over 4
-
-=item *.ucm
-
-See above - the F<Encode/*.ucm> files provided with the distribution have
-been created from the original Tcl .enc files using this approach.
-
-=item *.c
-
-Produces tables as C data structures - this is used to build in encodings
-into F<Encode.so>/F<Encode.dll>.
-
-=item *.xs
-
-In theory this allows encodings to be stand-alone loadable Perl
-extensions. The process has not yet been tested. The plan is to use
-this approach for large East Asian encodings.
-
-=back
-
-The set of encodings built-in to F<Encode.so>/F<Encode.dll> is
-determined by F<Makefile.PL>. The current set is as follows:
-
-=over 4
-
-=item ascii and iso-8859-*
-
-That is all the common 8-bit "western" encodings.
-
-=item IBM-1047 and two other variants of EBCDIC.
-
-These are the same variants that are supported by EBCDIC Perl as
-"native" encodings. They are included to prove "reversibility" of
-some constructs in EBCDIC Perl.
-
-=item symbol and dingbats as used by Tk on X11.
-
-(The reason Encode got started was to support Perl/Tk.)
-
-=back
-
-That set is rather ad hoc and has been driven by the needs of the
-tests rather than the needs of typical applications. It is likely
-to be rationalized.
-
=head1 SEE ALSO
-L<perlunicode>, L<perlebcdic>, L<perlfunc/open>, L<PerlIO>
+L<Encode::Details>,
+L<Encode::Encoding>,
+L<Encode::Supported>,
+L<PerlIO>,
+L<encoding>,
+L<perlebcdic>,
+L<perlfunc/open>,
+L<perlunicode>,
+L<utf8>,
+the Perl Unicode Mailing List E<lt>perl-unicode@perl.orgE<gt>
=cut
-
projects / p5sagit/p5-mst-13.2.git / blobdiff