X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=blobdiff_plain;f=ext%2FEncode%2FEncode.pm;h=b502e8fdc469a5a8570ac4f7af7e60ae9ce6499b;hb=7e19fb92789b07f9ae6ba1ee1b4f5fbb72612161;hp=2d498654917281ad6a147b179d8e7114c3d11d5c;hpb=4edaa979293b3e482a715be9ab66acf7eb848c46;p=p5sagit%2Fp5-mst-13.2.git diff --git a/ext/Encode/Encode.pm b/ext/Encode/Encode.pm index 2d49865..b502e8f 100644 --- a/ext/Encode/Encode.pm +++ b/ext/Encode/Encode.pm @@ -1,414 +1,279 @@ package Encode; +use strict; +our $VERSION = do { my @r = (q$Revision: 1.61 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r }; +our $DEBUG = 0; +use XSLoader (); +XSLoader::load 'Encode'; -$VERSION = 0.01; - -require DynaLoader; require Exporter; - -@ISA = qw(Exporter DynaLoader); +use base qw/Exporter/; # Public, encouraged API is exported by default -@EXPORT = qw ( - encode - decode - encode_utf8 - decode_utf8 - find_encoding + +our @EXPORT = qw( + decode decode_utf8 encode encode_utf8 + encodings find_encoding ); -@EXPORT_OK = - qw( - encodings - from_to - is_utf8 - is_8bit - is_16bit - utf8_upgrade - utf8_downgrade - _utf8_on - _utf8_off - ); - -bootstrap Encode (); +our @FB_FLAGS = qw(DIE_ON_ERR WARN_ON_ERR RETURN_ON_ERR LEAVE_SRC + PERLQQ HTMLCREF XMLCREF); +our @FB_CONSTS = qw(FB_DEFAULT FB_CROAK FB_QUIET FB_WARN + FB_PERLQQ FB_HTMLCREF FB_XMLCREF); + +our @EXPORT_OK = + ( + qw( + _utf8_off _utf8_on define_encoding from_to is_16bit is_8bit + is_utf8 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; -# The global hash is declared in XS code -$encoding{Unicode} = bless({},'Encode::Unicode'); -$encoding{utf8} = bless({},'Encode::utf8'); -$encoding{'iso10646-1'} = bless({},'Encode::iso10646_1'); +our $ON_EBCDIC = (ord("A") == 193); + +use Encode::Alias; + +# Make a %Encoding package variable to allow a certain amount of cheating +our %Encoding; +our %ExtModule; +require Encode::Config; +eval { require Encode::ConfigLocal }; sub encodings { - my ($class) = @_; - foreach my $dir (@INC) - { - if (opendir(my $dh,"$dir/Encode")) - { - while (defined(my $name = readdir($dh))) - { - if ($name =~ /^(.*)\.enc$/) - { - next if exists $encoding{$1}; - $encoding{$1} = "$dir/$name"; - } - } - closedir($dh); + my $class = shift; + my @modules = (@_ and $_[0] eq ":all") ? values %ExtModule : @_; + for my $mod (@modules){ + $mod =~ s,::,/,g or $mod = "Encode/$mod"; + $mod .= '.pm'; + $DEBUG and warn "about to require $mod;"; + eval { require $mod; }; } - } - return keys %encoding; + my %modules = map {$_ => 1} @modules; + return + sort { lc $a cmp lc $b } + grep {!/^(?:Internal|Unicode)$/o} keys %Encoding; +} + +sub perlio_ok{ + my $obj = ref($_[0]) ? $_[0] : find_encoding($_[0]); + $obj->can("perlio_ok") and return $obj->perlio_ok(); + return 0; # safety net } -sub loadEncoding +sub define_encoding { - my ($class,$name,$file) = @_; - if (open(my $fh,$file)) - { - my $type; - while (1) + my $obj = shift; + my $name = shift; + $Encoding{$name} = $obj; + my $lc = lc($name); + define_alias($lc => $obj) unless $lc eq $name; + while (@_) { - my $line = <$fh>; - $type = substr($line,0,1); - last unless $type eq '#'; + my $alias = shift; + define_alias($alias,$obj); } - $class .= ('::'.(($type eq 'E') ? 'Escape' : 'Table')); - #warn "Loading $file"; - return $class->read($fh,$name,$type); - } - else - { - return undef; - } + return $obj; } sub getEncoding { - my ($class,$name) = @_; - my $enc; - unless (ref($enc = $encoding{$name})) - { - $enc = $class->loadEncoding($name,$enc) if defined $enc; - unless (ref($enc)) + my ($class,$name,$skip_external) = @_; + my $enc; + if (ref($name) && $name->can('new_sequence')) { - foreach my $dir (@INC) - { - last if ($enc = $class->loadEncoding($name,"$dir/Encode/$name.enc")); - } + return $name; + } + my $lc = lc $name; + if (exists $Encoding{$name}) + { + return $Encoding{$name}; + } + if (exists $Encoding{$lc}) + { + return $Encoding{$lc}; } - $encoding{$name} = $enc; - } - return $enc; -} -sub find_encoding -{ - my ($name) = @_; - return __PACKAGE__->getEncoding($name); -} + my $oc = $class->find_alias($name); + return $oc if defined $oc; -sub encode -{ - my ($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; -} + $oc = $class->find_alias($lc) if $lc ne $name; + return $oc if defined $oc; -sub decode -{ - my ($name,$octets,$check) = @_; - my $enc = find_encoding($name); - croak("Unknown encoding '$name'") unless defined $enc; - my $string = $enc->decode($octets,$check); - return undef if ($check && length($octets)); - return $string; + unless ($skip_external) + { + if (my $mod = $ExtModule{$name} || $ExtModule{$lc}){ + $mod =~ s,::,/,g ; $mod .= '.pm'; + eval{ require $mod; }; + return $Encoding{$name} if exists $Encoding{$name}; + } + } + 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($$;$) { - my ($str) = @_; - return undef unless utf8_decode($str); - return $str; + my ($name,$string,$check) = @_; + $check ||=0; + my $enc = find_encoding($name); + croak("Unknown encoding '$name'") unless defined $enc; + my $octets = $enc->encode($string,$check); + return undef if ($check && length($string)); + return $octets; } -package Encode::Encoding; -# Base class for classes which implement encodings - -# Temporary legacy methods -sub toUnicode { shift->decode(@_) } -sub fromUnicode { shift->encode(@_) } - -sub new_sequence { return $_[0] } - -package Encode::XS; -use base 'Encode::Encoding'; - -package Encode::Unicode; -use base 'Encode::Encoding'; - -# Dummy package that provides the encode interface but leaves data -# as UTF-8 encoded. It is here so that from_to() works. - -sub name { 'Unicode' } - -sub decode -{ - my ($obj,$str,$chk) = @_; - Encode::utf8_upgrade($str); - $_[1] = '' if $chk; - return $str; -} - -*encode = \&decode; - -package Encode::utf8; -use base 'Encode::Encoding'; - -# package to allow long-hand -# $octets = encode( utf8 => $string ); -# - -sub name { 'utf8' } - -sub decode +sub decode($$;$) { - my ($obj,$octets,$chk) = @_; - my $str = Encode::decode_utf8($octets); - if (defined $str) - { - $_[1] = '' if $chk; - return $str; - } - return undef; + my ($name,$octets,$check) = @_; + $check ||=0; + 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 encode +sub from_to($$$;$) { - my ($obj,$string,$chk) = @_; - my $octets = Encode::encode_utf8($string); - $_[1] = '' if $chk; - return $octets; + my ($string,$from,$to,$check) = @_; + $check ||=0; + 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($uni)); + return defined($_[0] = $string) ? length($string) : undef ; } -package Encode::Table; -use base 'Encode::Encoding'; - -sub read +sub encode_utf8($) { - my ($class,$fh,$name,$type) = @_; - my $rep = $class->can("rep_$type"); - my ($def,$sym,$pages) = split(/\s+/,scalar(<$fh>)); - my @touni; - my %fmuni; - my $count = 0; - $def = hex($def); - while ($pages--) - { - my $line = <$fh>; - chomp($line); - my $page = hex($line); - my @page; - my $ch = $page * 256; - for (my $i = 0; $i < 16; $i++) - { - my $line = <$fh>; - for (my $j = 0; $j < 16; $j++) - { - my $val = hex(substr($line,0,4,'')); - if ($val || !$ch) - { - my $uch = chr($val); - push(@page,$uch); - $fmuni{$uch} = $ch; - $count++; - } - else - { - push(@page,undef); - } - $ch++; - } - } - $touni[$page] = \@page; - } - - return bless {Name => $name, - Rep => $rep, - ToUni => \@touni, - FmUni => \%fmuni, - Def => $def, - Num => $count, - },$class; + my ($str) = @_; + utf8::encode($str); + return $str; } -sub name { shift->{'Name'} } - -sub rep_S { 'C' } - -sub rep_D { 'n' } - -sub rep_M { ($_[0] > 255) ? 'n' : 'C' } - -sub representation +sub decode_utf8($) { - my ($obj,$ch) = @_; - $ch = 0 unless @_ > 1; - $obj-{'Rep'}->($ch); + my ($str) = @_; + return undef unless utf8::decode($str); + return $str; } -sub decode -{ - my ($obj,$str,$chk) = @_; - my $rep = $obj->{'Rep'}; - my $touni = $obj->{'ToUni'}; - my $uni = ''; - while (length($str)) - { - my $ch = ord(substr($str,0,1,'')); - my $x; - if (&$rep($ch) eq 'C') - { - $x = $touni->[0][$ch]; - } - else - { - $x = $touni->[$ch][ord(substr($str,0,1,''))]; - } - unless (defined $x) - { - last if $chk; - # What do we do here ? - $x = ''; - } - $uni .= $x; - } - $_[1] = $str if $chk; - return $uni; -} +predefine_encodings(); -sub encode -{ - my ($obj,$uni,$chk) = @_; - my $fmuni = $obj->{'FmUni'}; - my $str = ''; - my $def = $obj->{'Def'}; - my $rep = $obj->{'Rep'}; - while (length($uni)) - { - my $ch = substr($uni,0,1,''); - my $x = $fmuni->{chr(ord($ch))}; - unless (defined $x) - { - last if ($chk); - $x = $def; +# +# This is to restore %Encoding if really needed; +# +sub predefine_encodings{ + if ($ON_EBCDIC) { + # was in Encode::UTF_EBCDIC + package Encode::UTF_EBCDIC; + *name = sub{ shift->{'Name'} }; + *new_sequence = sub{ return $_[0] }; + *needs_lines = sub{ 0 }; + *perlio_ok = sub { + eval{ require PerlIO::encoding }; + return $@ ? 0 : 1; + }; + *decode = sub{ + my ($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] }; + *needs_lines = sub{ 0 }; + *perlio_ok = sub { + eval{ require PerlIO::encoding }; + return $@ ? 0 : 1; + }; + *decode = sub{ + my ($obj,$str,$chk) = @_; + utf8::upgrade($str); + $_[1] = '' if $chk; + return $str; + }; + *encode = \&decode; + $Encode::Encoding{Unicode} = + bless {Name => "Internal"} => "Encode::Internal"; } - $str .= pack(&$rep($x),$x); - } - $_[1] = $uni if $chk; - return $str; -} - -package Encode::iso10646_1; -use base 'Encode::Encoding'; -# Encoding is 16-bit network order Unicode -# Used for X font encodings - -sub name { 'iso10646-1' } - -sub decode -{ - my ($obj,$str,$chk) = @_; - my $uni = ''; - while (length($str)) - { - my $code = unpack('n',substr($str,0,2,'')) & 0xffff; - $uni .= chr($code); - } - $_[1] = $str if $chk; - Encode::utf8_upgrade($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; + # was in Encode::utf8 + package Encode::utf8; + *name = sub{ shift->{'Name'} }; + *new_sequence = sub{ return $_[0] }; + *needs_lines = sub{ 0 }; + *perlio_ok = sub { + eval{ require PerlIO::encoding }; + return $@ ? 0 : 1; + }; + *decode = sub{ + my ($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"; } - $str .= pack('n',$x); - } - $_[1] = $uni if $chk; - return $str; -} - - -package Encode::Escape; -use base 'Encode::Encoding'; - -use Carp; - -sub read -{ - my ($class,$fh,$name) = @_; - my %self = (Name => $name, Num => 0); - while (<$fh>) - { - my ($key,$val) = /^(\S+)\s+(.*)$/; - $val =~ s/^\{(.*?)\}/$1/g; - $val =~ s/\\x([0-9a-f]{2})/chr(hex($1))/ge; - $self{$key} = $val; - } - return bless \%self,$class; -} - -sub name { shift->{'Name'} } - -sub decode -{ - croak("Not implemented yet"); -} - -sub encode -{ - croak("Not implemented yet"); } -# switch back to Encode package in case we ever add AutoLoader -package Encode; - 1; __END__ @@ -421,47 +286,67 @@ 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. +The C module provides the interfaces between Perl's strings +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 values -of the characters (as returned by C) 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). +defined by the Unicode Consortium. On most platforms the ordinal +values of the characters (as returned by C) 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). -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 +=over 2 =item * I: a character in the range 0..(2**32-1) (or more). -(What perl's strings are made of.) +(What Perl's strings are made of.) =item * I: a character in the range 0..255 -(A special case of a perl character.) +(A special case of a Perl character.) =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 @@ -469,497 +354,393 @@ 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 +=head1 PERL ENCODING API -Encodings can be divided into the following types: +=over 2 -=over 4 +=item $octets = encode(ENCODING, $string[, CHECK]) -=item * Fixed length 8-bit (or less) encodings. +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. -Each character is a single octet so may have a repertoire of up to -256 characters. ASCII and iso-8859-* are typical examples. +For example, to convert (internally UTF-8 encoded) Unicode string to +iso-8859-1 (also known as Latin1), -=item * Fixed length 16-bit encodings + $octets = encode("iso-8859-1", $utf8); -Each character is two octets so may have a repertoire of up to -65,536 characters. Unicode's UCS-2 is an example. Also used for -encodings for East Asian languages. +B: When you C<$octets = encode("utf8", $utf8)>, then $octets +B $utf8. 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 32-bit encodings. +=item $string = decode(ENCODING, $octets[, CHECK]) -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. +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. -=item * Multi-byte encodings +For example, to convert ISO-8859-1 data to UTF-8: -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.) + $utf8 = decode("iso-8859-1", $latin1); -=item * "Escape" encodings. +B: When you C<$utf8 = encode("utf8", $octets)>, then $utf8 +B $utf8. Though they both contain the same data, +the utf8 flag for $utf8 is on unless $octets entirely conststs of +ASCII data (or EBCDIC on EBCDIC machines). See L +below. -These encodings embed "escape sequences" into the octet sequence -which describe how the following octets are to be interpreted. -The iso-2022-* family is typical. Following the escape sequence -octets are encoded by an "embedded" encoding (which will be one -of the above types) until another escape sequence switches to -a different "embedded" encoding. +=item [$length =] from_to($string, FROM_ENC, TO_ENC [, CHECK]) -These schemes are very flexible and can handle mixed languages but are -very complex to process (and have state). -No escape encodings are implemented for perl yet. +Converts B data between two encodings. For example, to +convert ISO-8859-1 data to UTF-8: -=back + from_to($data, "iso-8859-1", "utf8"); -=head2 Specifying Encodings +and to convert it back: -Encodings can be specified to the API described below in two ways: + from_to($data, "utf8", "iso-8859-1"); -=over 4 +Note that because the conversion happens in place, the data to be +converted cannot be a string constant; it must be a scalar variable. -=item 1. By name +from_to() returns the length of the converted string on success, undef +otherwise. -Encoding names are strings with characters taken from a restricted repertoire. -See L. +B: The following operations look the same but not quite so; -=item 2. As an object + from_to($data, "iso-8859-1", "utf8"); #1 + $data = decode("iso-8859-1", $data); #2 -Encoding objects are returned by C. +Both #1 and #2 makes $data consists of 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 superset of UTF-8 and the +resulting octets are returned as a sequence of bytes. All possible +characters have a UTF-8 representation so this function cannot fail. -=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", $octets [, CHECK])>. +decode_utf8($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. +=head2 Listing available encodings -I + use Encode; + @list = Encode->encodings(); -=head1 PERL ENCODING API +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 -=head2 Generic Encoding Interface + @all_encodings = Encode->encodings(":all"); -=over 4 +Or you can give the name of a specific module. -=item * + @with_jp = Encode->encodings("Encode::JP"); - $bytes = encode(ENCODING, $string[, CHECK]) +When "::" is not in the name, "Encode::" is assumed. -Encodes string from perl's internal form into I and returns a -sequence of octets. -See L. + @ebcdic = Encode->encodings("EBCDIC"); -=item * +To find out in detail which encodings are supported by this package, +see L. - $string = decode(ENCODING, $bytes[, CHECK]) +=head2 Defining Aliases -Decode sequence of octets assumed to be in I into perls internal -form and returns the resuting string. -See L. +To add a new alias to a given encoding, use: -=back + use Encode; + use Encode::Alias; + define_alias(newName => ENCODING); -=head2 Handling Malformed Data +After that, newName can be used as an alias for ENCODING. +ENCODING may be either the name of an encoding or an +I -If CHECK is not set, C is returned. If the data is supposed to -be UTF-8, an optional lexical warning (category utf8) is given. -If CHECK is true but not a code reference, dies. +But before you do so, make sure the alias is nonexistent with +C, which returns the canonical name thereof. +i.e. -It would desirable to have a way to indicate that transform should use the -encodings "replacement character" - no such mechanism is defined yet. + Encode::resolve_alias("latin1") eq "iso-8859-1" # true + Encode::resolve_alias("iso-8859-12") # false; nonexistent + Encode::resolve_alias($name) eq $name # true if $name is canonical -It is also planned to allow I to be a code reference. +resolve_alias() does not need C; it can be +exported via C. -This is not yet implemented as there are design issues with what its arguments -should be and how it returns its results. +See L for details. -=over 4 +=head1 Encoding via PerlIO -=item Scheme 1 +If your perl supports I, you can use a PerlIO layer to decode +and encode directly via a filehandle. The following two examples +are totally identical in their functionality. -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. + # via PerlIO + open my $in, "<:encoding(shiftjis)", $infile or die; + open my $out, ">:encoding(euc-jp)", $outfile or die; + while(<>){ print; } - sub fixup { - my $ch = substr($_[0],0,1,''); - return sprintf("\x{%02X}",ord($ch); - } + # via from_to + open my $in, "<", $infile or die; + open my $out, ">", $outfile or die; + while(<>){ + from_to($_, "shiftjis", "euc-jp", 1); + } -This scheme is close to how underlying C code for Encode works, but gives -the fixup routine very little context. +Unfortunately, there may be encodings are PerlIO-savvy. You can check +if your encoding is supported by PerlIO by calling the C +method. -=item Scheme 2 + Encode::perlio_ok("hz"); # False + find_encoding("euc-cn")->perlio_ok; # True where PerlIO is available -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. -e.g. + use Encode qw(perlio_ok); # exported upon request + perlio_ok("euc-jp") - sub fixup { - # my ($s,$i,$d) = @_; - my $ch = substr($_[0],$_[1],1); - $_[2] .= sprintf("\x{%02X}",ord($ch); - return $_[1]+1; - } +Fortunately, all encodings that come with Encode core are PerlIO-savvy +except for hz and ISO-2022-kr. See L for details. -This scheme gives maximal control to the fixup routine but is more complicated -to code, and may need internals of Encode to be tweaked to keep original -string intact. +For gory details, see L. -=item Other Schemes +=head1 Handling Malformed Data -Hybrids of above. +=over 2 -Multiple return values rather than in-place modifications. +The I argument is used as follows. When you omit it, +the behaviour is the same as if you had passed a value of 0 for +I. -Index into the string could be pos($str) allowing s/\G...//. +=item I = Encode::FB_DEFAULT ( == 0) -=back +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, "\x{FFFD}" is used. +If the data is supposed to be UTF-8, an optional lexical warning +(category utf8) is given. -=head2 UTF-8 / utf8 +=item I = Encode::FB_CROAK ( == 1) -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). +If I is 1, methods will die 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. -=over 4 +=item I = Encode::FB_QUIET -=item * +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: - $bytes = encode_utf8($string); + my $data = ''; + 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 + } -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 I = Encode::FB_WARN -=item * +This is the same as above, except that it warns on error. Handy when +you are debugging the mode above. - $string = decode_utf8($bytes [,CHECK]); +=item perlqq mode (I = Encode::FB_PERLQQ) -The sequence of octets represented by $bytes is decoded from UTF-8 into -a sequence of logical characters. Not all sequences of octets form valid -UTF-8 encodings, so it is possible for this call to fail. -See L. +=item HTML charref mode (I = Encode::FB_HTMLCREF) -=back +=item XML charref mode (I = Encode::FB_XMLCREF) -=head2 Other Encodings of Unicode +For encodings that are implemented by Encode::XS, CHECK == +Encode::FB_PERLQQ turns (en|de)code into C fallback mode. -UTF-16 is similar to UCS-2, 16 bit or 2-byte chunks. -UCS-2 can only represent 0..0xFFFF, while UTF-16 has a "surogate pair" -scheme which allows it to cover the whole Unicode range. +When you decode, '\xI' will be inserted for a malformed character, +where I is the hex representation of the octet that could not be +decoded to utf8. And when you encode, '\x{I}' will be inserted, +where I is the Unicode ID of the character that cannot be found +in the character repertoire of the encoding. -Encode implements big-endian UCS-2 as the encoding "iso10646-1" as that -happens to be the name used by that representation when used with X11 fonts. +HTML/XML character reference modes are about the same, in place of +\x{I}, HTML uses &#I<1234>; where I<1234> is a decimal digit and +XML uses &#xI; where I is the hexadecimal digit. -UTF-32 or UCS-4 is 32-bit or 4-byte chunks. Perl's logical characters -can be considered as being in this form without encoding. An encoding -to transfer strings in this form (e.g. to write them to a file) would need to +=item The bitmask - pack('L',map(chr($_),split(//,$string))); # native - or - pack('V',map(chr($_),split(//,$string))); # little-endian - or - pack('N',map(chr($_),split(//,$string))); # big-endian +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. -depending on the endian required. + FB_DEFAULT FB_CROAK FB_QUIET FB_WARN FB_PERLQQ + DIE_ON_ERR 0x0001 X + WARN_ON_ER 0x0002 X + RETURN_ON_ERR 0x0004 X X + LEAVE_SRC 0x0008 + PERLQQ 0x0100 X + HTMLCREF 0x0200 + XMLCREF 0x0400 -No UTF-32 encodings are not yet implemented. +=head2 Unimplemented fallback schemes -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. +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. -=head1 Encoding and IO +=head1 Defining Encodings -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. +To define a new encoding, use: - open(my $ilyad,'>:encoding(iso8859-7)','ilyad.greek'); - print $ilyad @epic; + use Encode qw(define_alias); + define_encoding($object, 'canonicalName' [, alias...]); -In addition the new IO system can also be configured to read/write -UTF-8 encoded characters (as noted above this is efficient): +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>, as for C. - open(my $fh,'>:utf8','anything'); - print $fh "Any \x{0021} string \N{SMILEY FACE}\n"; +See L for more details. -Either of the above forms of "layer" specifications can be made the default -for a lexical scope with the C pragma. See L. +=head1 The UTF-8 flag -Once a handle is open is layers can be altered using C. +Before the introduction of utf8 support in perl, The C operator +just compares internal data of the scalars. Now C means internal +data equality AND I. To explain why we made it so, I +will quote page 402 of 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. +=over 2 -In other cases it is the programs responsibility -to transform characters into bytes using the API above before -doing writes, and to transform the bytes read from a handle into characters -before doing "character operations" (e.g. C, C, ...). +=item Goal #1: -=head1 Encoding How to ... +Old byte-oriented programs should not spontaneously break on the old +byte-oriented data they used to work on. -To do: +=item Goal #2: -=over 4 +Old byte-oriented programs should magically start working on the new +character-oriented data when appropriate. -=item * IO with mixed content (faking iso-2020-*) +=item Goal #3: -=item * MIME's Content-Length: +Programs should run just as fast in the new character-oriented mode +as in the old byte-oriented mode. -=item * UTF-8 strings in binary data. +=item Goal #4: -=item * perl/Encode wrappers on non-Unicode XS modules. +Perl should remain one language, rather than forking into a +byte-oriented Perl and a character-oriented Perl. =back -=head1 Messing with Perl's Internals - -The following API uses parts of perl's internals in the current implementation. -As such they are efficient, but may change. - -=over 4 - -=item * - - $num_octets = utf8_upgrade($string); +Back when C was written, not even Perl 5.6.0 +was born and many features documented in the book remained +unimplemented. Perl 5.8 hopefully correct this and the introduction +of UTF-8 flag is one of them. You can think this perl notion of +byte-oriented mode (utf8 flag off) and character-oriented mode (utf8 +flag on). -Converts internal representation of string to the UTF-8 form. -Returns the number of octets necessary to represent the string as UTF-8. +Here is how Encode takes care of the utf8 flag. -=item * utf8_downgrade($string[, CHECK]) - -Converts internal representation of string to be un-encoded bytes. - -=item * is_utf8(STRING [, CHECK]) - -[INTERNAL] Test 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) - -[INTERNAL] Turn 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. +=over2 =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 -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<%Encode::encodings> hash. (It is a package hash to allow XS code to get -at it.) - -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 +When you encode, the resulting utf8 flag is always off. -Should return the string representing the canonical name of the encoding. +=item -=item -Enew_sequence +When you decode, the resuting utf8 flag is on unless you can +unambiguously represent data. Here is the definition of +dis-ambiguity. -This is a placeholder for encodings with state. It should return an object -which implements this interface, all current implementations return the -original object. + After C<$utf8 = decode('foo', $octet);>, -=item -Eencode($string,$check) + When $octet is... The utf8 flag in $utf8 is + --------------------------------------------- + In ASCII only (or EBCDIC only) OFF + In ISO-8859-1 ON + In any other Encoding ON + --------------------------------------------- -Should return the octet sequence representing I<$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 $string in-place -to remove the converted part leaving it starting with the problem fragment. +As you see, there is one exception, In ASCII. That way you can assue +Goal #1. And with Encode Goal #2 is assumed but you still have to be +careful in such cases mentioned in B paragraphs. -If check is is false then C should make a "best effort" to convert -the string - for example by using a replacement character. - -=item -Edecode($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. +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 -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. - -=head2 Compiled Encodings +=head2 Messing with Perl's Internals -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 following API uses parts of Perl's internals in the current +implementation. As such, they are efficient but may change. -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 2 -=over 4 +=item is_utf8(STRING [, CHECK]) -=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 +[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. -F can write the following forms: +=item _utf8_on(STRING) -=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. +[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 treat the return value as +indicating success or failure), or C if STRING is not a string. -=item symbol and dingbats as used by Tk on X11. +=item _utf8_off(STRING) -(The reason Encode got started was to support perl/Tk.) +[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 -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, L, L - -=cut +L, +L, +L, +L, +L, +L, +L, +L, +the Perl Unicode Mailing List Eperl-unicode@perl.orgE +=head1 MAINTAINER +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 share. +=cut