X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=blobdiff_plain;f=ext%2FEncode%2FEncode.pm;h=c5e303de47378332a5d7e636eee065462b538e76;hb=21d92c23f49d139d8bddefbab6f984eb17e12d43;hp=bae93893e717b697954683a9da6d4a057e1f850d;hpb=8a36125691db1d8f79e98507373cbc6ea47271d4;p=p5sagit%2Fp5-mst-13.2.git diff --git a/ext/Encode/Encode.pm b/ext/Encode/Encode.pm index bae9389..c5e303d 100644 --- a/ext/Encode/Encode.pm +++ b/ext/Encode/Encode.pm @@ -1,455 +1,294 @@ +# +# $Id: Encode.pm,v 1.91 2003/03/09 20:07:20 dankogai Exp $ +# package Encode; use strict; +our $VERSION = do { my @r = (q$Revision: 1.91 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r }; +our $DEBUG = 0; +use XSLoader (); +XSLoader::load(__PACKAGE__, $VERSION); -our $VERSION = '0.02'; - -require DynaLoader; require Exporter; - -our @ISA = qw(Exporter DynaLoader); +use base qw/Exporter/; # Public, encouraged API is exported by default -our @EXPORT = qw ( - encode - decode - encode_utf8 - decode_utf8 - find_encoding - encodings + +our @EXPORT = qw( + decode decode_utf8 encode encode_utf8 + encodings find_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( - define_encoding - define_alias - from_to - is_utf8 - is_8bit - is_16bit - utf8_upgrade - utf8_downgrade - _utf8_on - _utf8_off - ); - -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; - -# 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 $ON_EBCDIC = (ord("A") == 193); -sub encodings -{ - my ($class) = @_; - return keys %encoding; -} +use Encode::Alias; + +# Make a %Encoding package variable to allow a certain amount of cheating +our %Encoding; +our %ExtModule; +require Encode::Config; +eval { require Encode::ConfigLocal }; -sub findAlias +sub encodings { - my $class = shift; - local $_ = shift; - # print "# findAlias $_\n"; - unless (exists $alias{$_}) - { - for (my $i=0; $i < @alias; $i += 2) - { - 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 $class = shift; + my %enc; + if (@_ and $_[0] eq ":all"){ + %enc = ( %Encoding, %ExtModule ); + }else{ + %enc = %Encoding; + for my $mod (map {m/::/o ? $_ : "Encode::$_" } @_){ + $DEBUG and warn $mod; + for my $enc (keys %ExtModule){ + $ExtModule{$enc} eq $mod and $enc{$enc} = $mod; + } + } } - } - return $alias{$_}; + return + sort { lc $a cmp lc $b } + grep {!/^(?:Internal|Unicode|Guess)$/o} keys %enc; } -sub define_alias -{ - while (@_) - { - my ($alias,$name) = splice(@_,0,2); - push(@alias, $alias => $name); - } +sub perlio_ok{ + my $obj = ref($_[0]) ? $_[0] : find_encoding($_[0]); + $obj->can("perlio_ok") and return $obj->perlio_ok(); + return 0; # safety net } -# Allow variants of iso-8859-1 etc. -define_alias( qr/^iso[-_]?(\d+)[-_](\d+)$/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 => '"${1}8"' ); - -# The Official name of ASCII. -define_alias( qr/^ANSI[-_]?X3\.4[-_]?1968$/i => '"ascii"' ); - -# 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"' ); - 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; + 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 $obj; } sub getEncoding { - my ($class,$name) = @_; - 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}; - } - - my $oc = $class->findAlias($name); - return $oc if defined $oc; - return $class->findAlias($lc) if $lc ne $name; + my ($class, $name, $skip_external) = @_; - return; -} - -sub find_encoding -{ - my ($name) = @_; - return __PACKAGE__->getEncoding($name); -} + ref($name) && $name->can('new_sequence') and return $name; + exists $Encoding{$name} and return $Encoding{$name}; + my $lc = lc $name; + exists $Encoding{$lc} and return $Encoding{$lc}; -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 $oc = $class->find_alias($name); + defined($oc) and return $oc; + $lc ne $name and $oc = $class->find_alias($lc); + defined($oc) and return $oc; -sub decode -{ - my ($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 $string; + unless ($skip_external) + { + if (my $mod = $ExtModule{$name} || $ExtModule{$lc}){ + $mod =~ s,::,/,g ; $mod .= '.pm'; + eval{ require $mod; }; + exists $Encoding{$name} and return $Encoding{$name}; + } + } + return; } -sub from_to +sub find_encoding { - 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] = $string); + my ($name, $skip_external) = @_; + return __PACKAGE__->getEncoding($name,$skip_external); } -sub encode_utf8 -{ - my ($str) = @_; - utf8::encode($str); - return $str; +sub resolve_alias { + my $obj = find_encoding(shift); + defined $obj and return $obj->name; + return; } -sub decode_utf8 +sub encode($$;$) { - my ($str) = @_; - return undef unless utf8::decode($str); - return $str; + my ($name, $string, $check) = @_; + return undef unless defined $string; + $check ||=0; + my $enc = find_encoding($name); + unless(defined $enc){ + require Carp; + Carp::croak("Unknown encoding '$name'"); + } + my $octets = $enc->encode($string,$check); + return undef if ($check && length($string)); + return $octets; } -package Encode::Encoding; -# Base class for classes which implement encodings - -sub Define +sub decode($$;$) { - my $obj = shift; - my $canonical = shift; - $obj = bless { Name => $canonical },$obj unless ref $obj; - # warn "$canonical => $obj\n"; - Encode::define_encoding($obj, $canonical, @_); + my ($name,$octets,$check) = @_; + return undef unless defined $octets; + $check ||=0; + my $enc = find_encoding($name); + unless(defined $enc){ + require Carp; + Carp::croak("Unknown encoding '$name'"); + } + my $string = $enc->decode($octets,$check); + $_[1] = $octets if $check; + return $string; } -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 +sub from_to($$$;$) { - my ($obj,$str,$chk) = @_; - utf8::upgrade($str); - $_[1] = '' if $chk; - return $str; + my ($string,$from,$to,$check) = @_; + return undef unless defined $string; + $check ||=0; + my $f = find_encoding($from); + unless (defined $f){ + require Carp; + Carp::croak("Unknown encoding '$from'"); + } + my $t = find_encoding($to); + unless (defined $t){ + require Carp; + Carp::croak("Unknown encoding '$to'"); + } + my $uni = $f->decode($string,$check); + return undef if ($check && length($string)); + $string = $t->encode($uni,$check); + return undef if ($check && length($uni)); + return defined($_[0] = $string) ? length($string) : undef ; } -*encode = \&decode; - -package Encoding::Unicode; -use base 'Encode::Encoding'; - -__PACKAGE__->Define('Unicode') unless ord('A') == 65; - -sub decode +sub encode_utf8($) { - 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; + my ($str) = @_; + utf8::encode($str); + return $str; } -sub encode +sub decode_utf8($) { - 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; + my ($str) = @_; + return undef unless utf8::decode($str); + return $str; } +predefine_encodings(1); -package Encode::utf8; -use base 'Encode::Encoding'; -# package to allow long-hand -# $octets = encode( utf8 => $string ); +# +# This is to restore %Encoding if really needed; # -__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 predefine_encodings{ + use Encode::Encoding; + no warnings 'redefine'; + my $use_xs = shift; + if ($ON_EBCDIC) { + # was in Encode::UTF_EBCDIC + package Encode::UTF_EBCDIC; + push @Encode::UTF_EBCDIC::ISA, 'Encode::Encoding'; + *decode = sub{ + my ($obj,$str,$chk) = @_; + my $res = ''; + for (my $i = 0; $i < length($str); $i++) { + $res .= + chr(utf8::unicode_to_native(ord(substr($str,$i,1)))); + } + $_[1] = '' if $chk; + return $res; + }; + *encode = sub{ + my ($obj,$str,$chk) = @_; + my $res = ''; + for (my $i = 0; $i < length($str); $i++) { + $res .= + chr(utf8::native_to_unicode(ord(substr($str,$i,1)))); + } + $_[1] = '' if $chk; + return $res; + }; + $Encode::Encoding{Unicode} = + bless {Name => "UTF_EBCDIC"} => "Encode::UTF_EBCDIC"; + } else { + package Encode::Internal; + push @Encode::Internal::ISA, 'Encode::Encoding'; + *decode = sub{ + my ($obj,$str,$chk) = @_; + utf8::upgrade($str); + $_[1] = '' if $chk; + return $str; + }; + *encode = \&decode; + $Encode::Encoding{Unicode} = + bless {Name => "Internal"} => "Encode::Internal"; + } -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; + # was in Encode::utf8 + package Encode::utf8; + push @Encode::utf8::ISA, 'Encode::Encoding'; + # + if ($use_xs){ + $DEBUG and warn __PACKAGE__, " XS on"; + *decode = \&decode_xs; + *encode = \&encode_xs; + }else{ + $DEBUG and warn __PACKAGE__, " XS off"; + *decode = sub{ + my ($obj,$octets,$chk) = @_; + my $str = Encode::decode_utf8($octets); + if (defined $str) { + $_[1] = '' if $chk; + return $str; + } + return undef; + }; + *encode = sub { + my ($obj,$string,$chk) = @_; + my $octets = Encode::encode_utf8($string); + $_[1] = '' if $chk; + return $octets; + }; + } + *cat_decode = sub{ # ($obj, $dst, $src, $pos, $trm, $chk) + my ($obj, undef, undef, $pos, $trm) = @_; # currently ignores $chk + my ($rdst, $rsrc, $rpos) = \@_[1,2,3]; + use bytes; + if ((my $npos = index($$rsrc, $trm, $pos)) >= 0) { + $$rdst .= substr($$rsrc, $pos, $npos - $pos + length($trm)); + $$rpos = $npos + length($trm); + return 1; + } + $$rdst .= substr($$rsrc, $pos); + $$rpos = length($$rsrc); + return ''; + }; + $Encode::Encoding{utf8} = + bless {Name => "utf8"} => "Encode::utf8"; } - $str .= pack('n',$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; - 1; __END__ @@ -462,10 +301,29 @@ Encode - character encodings use Encode; +=head2 Table of Contents + +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: + + Name Description + -------------------------------------------------------- + Encode::Alias Alias definitions 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 module provides the interfaces between Perl's strings -and the rest of the system. Perl strings are sequences of B. +and the rest of the system. Perl strings are sequences of +B. The repertoire of characters that Perl can represent is at least that defined by the Unicode Consortium. On most platforms the ordinal @@ -474,20 +332,21 @@ 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). -Traditionaly 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 numbers, pixels in an image - or just about anything. +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 machine's 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". +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 +=over 2 =item * @@ -502,620 +361,410 @@ I: a character in the range 0..255 =item * I: 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 ENCODINGS - -=head2 Characteristics of an Encoding +=head1 PERL ENCODING API -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. +=over 2 -=head2 Types of Encodings +=item $octets = encode(ENCODING, $string [, CHECK]) -Encodings can be divided into the following types: +Encodes a string from Perl's internal form into I and returns +a sequence of octets. ENCODING can be either a canonical name or +an alias. For encoding names and aliases, see L. +For CHECK, see L. -=over 4 +For example, to convert a string from Perl's internal format to +iso-8859-1 (also known as Latin1), -=item * Fixed length 8-bit (or less) encodings. + $octets = encode("iso-8859-1", $string); -Each character is a single octet so may have a repertoire of up to -256 characters. ASCII and iso-8859-* are typical examples. +B: When you run C<$octets = encode("utf8", $string)>, then $octets +B $string. Though they both contain the same data, the utf8 flag +for $octets is B off. When you encode anything, utf8 flag of +the result is always off, even when it contains completely valid utf8 +string. See L below. -=item * Fixed length 16-bit encodings +encode($valid_encoding, undef) is harmless but warns you for +C. +encode($valid_encoding, '') is harmless and warnless. -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 $string = decode(ENCODING, $octets [, CHECK]) -=item * Fixed length 32-bit encodings. +Decodes a sequence of octets assumed to be in I 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. For CHECK, see +L. -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. +For example, to convert ISO-8859-1 data to a string in Perl's internal format: -=item * Multi-byte encodings + $string = decode("iso-8859-1", $octets); -The number of octets needed to represent a character varies. -UTF-8 is a particularly complex but regular case of a multi-byte -encoding. Several East Asian countries use a multi-byte encoding -where 1-octet is used to cover western roman characters and Asian -characters get 2-octets. -(UTF-16 is strictly a multi-byte encoding taking either 2 or 4 octets -to represent a Unicode code point.) +B: When you run C<$string = decode("utf8", $octets)>, then $string +B $octets. Though they both contain the same data, +the utf8 flag for $string is on unless $octets entirely consists of +ASCII data (or EBCDIC on EBCDIC machines). See L +below. -=item * "Escape" encodings. +decode($valid_encoding, undef) is harmless but warns you for +C. +decode($valid_encoding, '') is harmless and warnless. -These encodings embed "escape sequences" into the octet sequence -which describe how the following octets are to be interpreted. -The iso-2022-* family is typical. Following the escape sequence -octets are encoded by an "embedded" encoding (which will be one -of the above types) until another escape sequence switches to -a different "embedded" encoding. +=item [$length =] from_to($octets, FROM_ENC, TO_ENC [, CHECK]) -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. +Converts B data between two encodings. The data in $octets +must be encoded as octets and not as characters in Perl's internal +format. For example, to convert ISO-8859-1 data to Microsoft's CP1250 encoding: -=back + from_to($octets, "iso-8859-1", "cp1250"); -=head2 Specifying Encodings +and to convert it back: -Encodings can be specified to the API described below in two ways: + from_to($octets, "cp1250", "iso-8859-1"); -=over 4 +Note that because the conversion happens in place, the data to be +converted cannot be a string constant; it must be a scalar variable. -=item 1. By name +from_to() returns the length of the converted string in octets on success, undef +otherwise. -Encoding names are strings with characters taken from a restricted -repertoire. See L. +B: The following operations look the same but are not quite so; -=item 2. As an object + from_to($data, "iso-8859-1", "utf8"); #1 + $data = decode("iso-8859-1", $data); #2 -Encoding objects are returned by C. +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 -=back + $data = encode("utf8", decode("iso-8859-1", $data)); -=head2 Encoding Names +See L below. -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: +=item $octets = encode_utf8($string); -=over 4 +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 * The MIME name as defined in IETF RFC-XXXX. -=item * The name in the IANA registry. +=item $string = decode_utf8($octets [, CHECK]); -=item * The name used by the the organization that defined it. +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. =back -Because of all the alias issues, and because in the general case -encodings have state C uses the encoding object internally -once an operation is in progress. - -=head1 PERL ENCODING API +=head2 Listing available encodings -=head2 Generic Encoding Interface + use Encode; + @list = Encode->encodings(); -=over 4 +Returns a list of the canonical names of the available encodings that +are loaded. To get a list of all available encodings including the +ones that are not loaded yet, say -=item * + @all_encodings = Encode->encodings(":all"); - $bytes = encode(ENCODING, $string[, CHECK]) +Or you can give the name of a specific module. -Encodes string from Perl's internal form into I and returns -a sequence of octets. For CHECK see L. + @with_jp = Encode->encodings("Encode::JP"); -=item * +When "::" is not in the name, "Encode::" is assumed. - $string = decode(ENCODING, $bytes[, CHECK]) + @ebcdic = Encode->encodings("EBCDIC"); -Decode sequence of octets assumed to be in I into Perl's -internal form and returns the resulting string. For CHECK see -L. +To find out in detail which encodings are supported by this package, +see L. -=item * +=head2 Defining Aliases - from_to($string, FROM_ENCODING, TO_ENCODING[, CHECK]) +To add a new alias to a given encoding, use: -Convert B the data between two encodings. How did the data -in $string originally get to be in FROM_ENCODING? Either using -encode() or through PerlIO: See L. For CHECK -see L. + use Encode; + use Encode::Alias; + define_alias(newName => ENCODING); -For example to convert ISO 8859-1 data to UTF-8: +After that, newName can be used as an alias for ENCODING. +ENCODING may be either the name of an encoding or an +I - from_to($data, "iso-8859-1", "utf-8"); +But before you do so, make sure the alias is nonexistent with +C, which returns the canonical name thereof. +i.e. -and to convert it back: + Encode::resolve_alias("latin1") eq "iso-8859-1" # true + Encode::resolve_alias("iso-8859-12") # false; nonexistent + Encode::resolve_alias($name) eq $name # true if $name is canonical - from_to($data, "utf-8", "iso-8859-1"); +resolve_alias() does not need C; it can be +exported via C. -Note that because the conversion happens in place, the data to be -converted cannot be a string constant, it must be a scalar variable. +See L for details. -=back +=head1 Encoding via PerlIO -=head2 Handling Malformed Data +If your perl supports I (which is the default), you can use a PerlIO layer to decode +and encode directly via a filehandle. The following two examples +are totally identical in their functionality. -If CHECK is not set, C 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. + # via PerlIO + open my $in, "<:encoding(shiftjis)", $infile or die; + open my $out, ">:encoding(euc-jp)", $outfile or die; + while(<$in>){ print $out $_; } -It would desirable to have a way to indicate that transform should use -the encodings "replacement character" - no such mechanism is defined yet. + # 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 $_; + } -It is also planned to allow I to be a code reference. +Unfortunately, it may be that encodings are PerlIO-savvy. You can check +if your encoding is supported by PerlIO by calling the C +method. -This is not yet implemented as there are design issues with what its -arguments should be and how it returns its results. + Encode::perlio_ok("hz"); # False + find_encoding("euc-cn")->perlio_ok; # True where PerlIO is available -=over 4 + use Encode qw(perlio_ok); # exported upon request + perlio_ok("euc-jp") -=item Scheme 1 +Fortunately, all encodings that come with Encode core are PerlIO-savvy +except for hz and ISO-2022-kr. For gory details, see L and L. -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. +=head1 Handling Malformed Data - sub fixup { - my $ch = substr($_[0],0,1,''); - return sprintf("\x{%02X}",ord($ch); - } +The I argument is used as follows. When you omit it, +the behaviour is the same as if you had passed a value of 0 for +I. -This scheme is close to how underlying C code for Encode works, but gives -the fixup routine very little context. +=over 2 -=item Scheme 2 +=item I = Encode::FB_DEFAULT ( == 0) -Passed original string, and an index into it of the problem area, and -output string so far. Appends what it will to output string and -returns new index into original string. For example: +If I is 0, (en|de)code will put a I +in place of a malformed character. For UCM-based encodings, +EsubcharE will be used. For Unicode, the code point C<0xFFFD> is used. +If the data is supposed to be UTF-8, an optional lexical warning +(category utf8) is given. - sub fixup { - # my ($s,$i,$d) = @_; - my $ch = substr($_[0],$_[1],1); - $_[2] .= sprintf("\x{%02X}",ord($ch); - return $_[1]+1; - } +=item I = Encode::FB_CROAK ( == 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. +If I is 1, methods will die on error immediately with an error +message. Therefore, when I is set to 1, you should trap the +fatal error with eval{} unless you really want to let it die on error. -=item Other Schemes +=item I = Encode::FB_QUIET -Hybrids of above. +If I 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, for example because you are reading with a fixed-width +buffer. Here is some sample code that does exactly this: -Multiple return values rather than in-place modifications. + my $data = ''; my $utf8 = ''; + while(defined(read $fh, $buffer, 256)){ + # buffer may end in a partial character so we append + $data .= $buffer; + $utf8 .= decode($encoding, $data, Encode::FB_QUIET); + # $data now contains the unprocessed partial character + } -Index into the string could be pos($str) allowing s/\G...//. +=item I = Encode::FB_WARN -=back +This is the same as above, except that it warns on error. Handy when +you are debugging the mode above. -=head2 UTF-8 / utf8 +=item perlqq mode (I = Encode::FB_PERLQQ) -The Unicode consortium defines the UTF-8 standard as a way of encoding -the entire Unicode repertiore as sequences of octets. This encoding is -expected to become very widespread. Perl can use this form internaly -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). +=item HTML charref mode (I = Encode::FB_HTMLCREF) -=over 4 +=item XML charref mode (I = Encode::FB_XMLCREF) -=item * +For encodings that are implemented by Encode::XS, CHECK == +Encode::FB_PERLQQ turns (en|de)code into C fallback mode. - $bytes = encode_utf8($string); +When you decode, C<\xI> will be inserted for a malformed character, +where I is the hex representation of the octet that could not be +decoded to utf8. And when you encode, C<\x{I}> will be inserted, +where I is the Unicode ID of the character that cannot be found +in the character repertoire of the encoding. -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. +HTML/XML character reference modes are about the same, in place of +C<\x{I}>, HTML uses C<&#I>; where I is a decimal digit and +XML uses C<&#xI>; where I is the hexadecimal digit. -=item * +=item The bitmask - $string = decode_utf8($bytes [,CHECK]); +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; you can import the generic bitmask +constants via C. -The sequence of octets represented by $bytes 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. + 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 + PERLQQ 0x0100 X + HTMLCREF 0x0200 + XMLCREF 0x0400 =back -=head2 Other Encodings of Unicode +=head2 Unimplemented fallback schemes -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 I scheme which -allows it to cover the whole Unicode range. +In the future, you will be able to use a code reference to a callback +function for the value of I but its API is still undecided. -Surrogates are code points set aside to encode the 0x01000..0x10FFFF -range of Unicode code points in pairs of 16-bit units. The I are the range 0xD800..0xDBFF, and the I -are the range 0xDC00..0xDFFFF. The surrogate encoding is +The fallback scheme does not work on EBCDIC platforms. - $hi = ($uni - 0x10000) / 0x400 + 0xD800; - $lo = ($uni - 0x10000) % 0x400 + 0xDC00; +=head1 Defining Encodings -and the decoding is +To define a new encoding, use: - $uni = 0x10000 + ($hi - 0xD8000) * 0x400 + ($lo - 0xDC00); + use Encode qw(define_encoding); + define_encoding($object, 'canonicalName' [, alias...]); -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. +I will be associated with I<$object>. The object +should provide the interface described in L. +If more than two arguments are provided then additional +arguments are taken as aliases for I<$object>. -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 +See L for more details. - pack('L*', unpack('U*', $string)); # native - or - pack('V*', unpack('U*', $string)); # little-endian - or - pack('N*', unpack('U*', $string)); # big-endian +=head1 The UTF-8 flag -depending on the endianness required. +Before the introduction of utf8 support in perl, The C operator +just compared the strings represented by two scalars. Beginning with +perl 5.8, C compares two strings with simultaneous consideration +of I. To explain why we made it so, I will quote page +402 of C -No UTF-32 encodings are implemented yet. +=over 2 -Both UCS-2 and UCS-4 style encodings can have "byte order marks" by -representing the code point 0xFFFE as the very first thing in a file. +=item Goal #1: -=head2 Listing available encodings - - use Encode qw(encodings); - @list = encodings(); +Old byte-oriented programs should not spontaneously break on the old +byte-oriented data they used to work on. -Returns a list of the canonical names of the available encodings. +=item Goal #2: -=head2 Defining Aliases +Old byte-oriented programs should magically start working on the new +character-oriented data when appropriate. - use Encode qw(define_alias); - define_alias( newName => ENCODING); +=item Goal #3: -Allows newName to be used as am alias for ENCODING. ENCODING may be -either the name of an encoding or and encoding object (as above). +Programs should run just as fast in the new character-oriented mode +as in the old byte-oriented mode. -Currently I can be specified in the following ways: +=item Goal #4: -=over 4 - -=item As a simple string. - -=item As a qr// compiled regular expression, e.g.: - - define_alias( qr/^iso8859-(\d+)$/i => '"iso-8859-$1"' ); - -In this case if I is not a reference it is C-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 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. +Perl should remain one language, rather than forking into a +byte-oriented Perl and a character-oriented Perl. =back -=head2 Defining Encodings - - use Encode qw(define_alias); - define_encoding( $object, 'canonicalName' [,alias...]); - -Causes I to be associated with I<$object>. The object -should provide the interface described in L -below. If more than two arguments are provided then additional -arguments are taken as aliases for I<$object> as for C. - -=head1 Encoding and IO - -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 provides a "layer" (See L) which can transform -data as it is read or written. - -Here is how the blind poet would modernise the encoding: +Back when C 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). - 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); - -In addition the new IO system can also be configured to read/write -UTF-8 encoded characters (as noted above this is efficient): - - open(my $fh,'>:utf8','anything'); - print $fh "Any \x{0021} string \N{SMILEY FACE}\n"; - -Either of the above forms of "layer" specifications can be made the default -for a lexical scope with the C pragma. See L. - -Once a handle is open is layers can be altered using C. - -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 and will C 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. - -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, C, ...). +Here is how Encode takes care of the utf8 flag. -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): +=over 2 - open(F, "<:encoding(iso-8859-1)", "data.txt") or die $!; - open(G, ">:utf8", "data.utf") or die $!; - while () { print G } - - # Could also do "print G " but that would pull - # the whole file into memory just to write it out again. - -More examples: - - open(my $f, "<:encoding(cp1252)") - open(my $g, ">:encoding(iso-8859-2)") - open(my $h, ">:encoding(latin9)") # iso-8859-15 - -See L for more information. - -See also L for how to change the default encoding of the -data in your script. +=item * -=head1 Encoding How to ... +When you encode, the resulting utf8 flag is always off. -To do: +=item * -=over 4 +When you decode, the resulting utf8 flag is on unless you can +unambiguously represent data. Here is the definition of +dis-ambiguity. -=item * IO with mixed content (faking iso-2020-*) +After C<$utf8 = decode('foo', $octet);>, -=item * MIME's Content-Length: + 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 + --------------------------------------------- -=item * UTF-8 strings in binary data. +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 paragraphs. -=item * Perl/Encode wrappers on non-Unicode XS modules. +This utf8 flag is not visible in perl scripts, exactly for the same +reason you cannot (or you I) 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 -=head1 Messing with Perl's Internals +=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]) +=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. -=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) +=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 checked for being well-formed UTF-8. Do not use unless you B 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 success or failure), or C if STRING is not a string. - -=item * +state of the UTF-8 flag (so please don't treat the return value as +indicating success or failure), or C if STRING is not a string. - _utf8_off(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 success or failure), or C 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 if STRING is not a 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 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 -Ename - -Should return the string representing the canonical name of the encoding. - -=item -Enew_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 -Eencode($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 $string in-place to remove the -converted part leaving it starting with the problem fragment. - -If check is is false then C should make a "best effort" to -convert the string - for example by using a replacement character. - -=item -Edecode($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 $octets in-place to remove the converted part -leaving it starting with the problem fragment. - -If check is is false then C should make a "best effort" to -convert the string - for example by using Unicode's "\x{FFFD}" as a -replacement character. - -=back - -It should be noted that the check behaviour is different from the -outer public API. The logic is that the "unchecked" case is useful -when encoding is part of a stream which may be reporting errors -(e.g. STDERR). In such cases it is desirable to get everything -through somehow without causing additional errors which obscure the -original one. Also the encoding is best placed to know what the -correct replacement character is, so if that is the desired behaviour -then letting low level code do it is the most efficient. - -In contrast if check is true, the scheme above allows the encoding to -do as much as it can and tell layer above how much that was. What is -lacking at present is a mechanism to report what went wrong. The most -likely interface will be an additional method call to the object, or -perhaps (to avoid forcing per-stream objects on otherwise stateless -encodings) and additional parameter. - -It is also highly desirable that encoding classes inherit from -C as a base class. This allows that class to define -additional behaviour for all encoding objects. For example built in -Unicode, UCS-2 and UTF-8 classes use : - - package Encode::MyEncoding; - use base qw(Encode::Encoding); - - __PACKAGE__->Define(qw(myCanonical myAlias)); - -To create an object with bless {Name => ...},$class, and call -define_encoding. They inherit their C method from -C. - -=head2 Compiled Encodings - -F provides a class C which provides the -interface described above. It calls a generic octet-sequence to -octet-sequence "engine" that is driven by tables (defined in -F). The same engine is used for both encode and -decode. C's C forces Perl's characters to their -UTF-8 form and then treats them as just another multibyte -encoding. C's C 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. - -The tables are produced by the Perl script F (the name needs -to change so we can eventually install it somewhere). F 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 can write the following forms: - -=over 4 - -=item *.ucm - -See above - the F 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/F. - -=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/F is -determined by F. 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 +=head1 SEE ALSO -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. +L, +L, +L, +L, +L, +L, +L, +L, +the Perl Unicode Mailing List Eperl-unicode@perl.orgE -=head1 SEE ALSO +=head1 MAINTAINER -L, L, L, L, L +This project was originated by Nick Ing-Simmons and later maintained +by Dan Kogai Edankogai@dan.co.jpE. See AUTHORS for a full +list of people involved. For any questions, use +Eperl-unicode@perl.orgE so we can all share. =cut -