X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=blobdiff_plain;f=ext%2FEncode%2FEncode.pm;h=ae047553bdbe8ee220e7676363f606c51087faf8;hb=2a5d9b1d41e4bafaa26126c5dea2f6ff0b72b6a7;hp=b502e8fdc469a5a8570ac4f7af7e60ae9ce6499b;hpb=7e19fb92789b07f9ae6ba1ee1b4f5fbb72612161;p=p5sagit%2Fp5-mst-13.2.git diff --git a/ext/Encode/Encode.pm b/ext/Encode/Encode.pm index b502e8f..ae04755 100644 --- a/ext/Encode/Encode.pm +++ b/ext/Encode/Encode.pm @@ -1,9 +1,13 @@ +# +# $Id: Encode.pm,v 2.18 2006/06/03 20:28:48 dankogai Exp dankogai $ +# 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 warnings; +our $VERSION = "2.18_01"; +sub DEBUG () { 0 } use XSLoader (); -XSLoader::load 'Encode'; +XSLoader::load( __PACKAGE__, $VERSION ); require Exporter; use base qw/Exporter/; @@ -11,36 +15,34 @@ use base qw/Exporter/; # Public, encouraged API is exported by default our @EXPORT = qw( - decode decode_utf8 encode encode_utf8 - encodings find_encoding + decode decode_utf8 encode encode_utf8 str2bytes bytes2str + encodings find_encoding clone_encoding ); - -our @FB_FLAGS = qw(DIE_ON_ERR WARN_ON_ERR RETURN_ON_ERR LEAVE_SRC - PERLQQ HTMLCREF XMLCREF); -our @FB_CONSTS = qw(FB_DEFAULT FB_CROAK FB_QUIET FB_WARN - FB_PERLQQ FB_HTMLCREF FB_XMLCREF); - -our @EXPORT_OK = - ( - qw( - _utf8_off _utf8_on define_encoding from_to is_16bit is_8bit - is_utf8 perlio_ok resolve_alias utf8_downgrade utf8_upgrade +our @FB_FLAGS = qw( + DIE_ON_ERR WARN_ON_ERR RETURN_ON_ERR LEAVE_SRC + PERLQQ HTMLCREF XMLCREF STOP_AT_PARTIAL +); +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, - ); + @FB_FLAGS, @FB_CONSTS, +); -our %EXPORT_TAGS = - ( - all => [ @EXPORT, @EXPORT_OK ], - fallbacks => [ @FB_CONSTS ], - fallback_all => [ @FB_CONSTS, @FB_FLAGS ], - ); +our %EXPORT_TAGS = ( + all => [ @EXPORT, @EXPORT_OK ], + fallbacks => [@FB_CONSTS], + fallback_all => [ @FB_CONSTS, @FB_FLAGS ], +); # Documentation moved after __END__ for speed - NI-S -use Carp; - -our $ON_EBCDIC = (ord("A") == 193); +our $ON_EBCDIC = ( ord("A") == 193 ); use Encode::Alias; @@ -50,227 +52,264 @@ our %ExtModule; require Encode::Config; eval { require Encode::ConfigLocal }; -sub encodings -{ +sub encodings { my $class = shift; - my @modules = (@_ and $_[0] eq ":all") ? values %ExtModule : @_; - for my $mod (@modules){ - $mod =~ s,::,/,g or $mod = "Encode/$mod"; - $mod .= '.pm'; - $DEBUG and warn "about to require $mod;"; - eval { require $mod; }; + my %enc; + if ( @_ and $_[0] eq ":all" ) { + %enc = ( %Encoding, %ExtModule ); + } + else { + %enc = %Encoding; + for my $mod ( map { m/::/o ? $_ : "Encode::$_" } @_ ) { + DEBUG and warn $mod; + for my $enc ( keys %ExtModule ) { + $ExtModule{$enc} eq $mod and $enc{$enc} = $mod; + } + } } - my %modules = map {$_ => 1} @modules; - return - sort { lc $a cmp lc $b } - grep {!/^(?:Internal|Unicode)$/o} keys %Encoding; + return sort { lc $a cmp lc $b } + grep { !/^(?:Internal|Unicode|Guess)$/o } keys %enc; } -sub perlio_ok{ - my $obj = ref($_[0]) ? $_[0] : find_encoding($_[0]); +sub perlio_ok { + my $obj = ref( $_[0] ) ? $_[0] : find_encoding( $_[0] ); $obj->can("perlio_ok") and return $obj->perlio_ok(); - return 0; # safety net + return 0; # safety net } -sub define_encoding -{ +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); + define_alias( $lc => $obj ) unless $lc eq $name; + while (@_) { + my $alias = shift; + define_alias( $alias, $obj ); } return $obj; } -sub getEncoding -{ - my ($class,$name,$skip_external) = @_; - my $enc; - if (ref($name) && $name->can('new_sequence')) - { - return $name; - } +sub getEncoding { + my ( $class, $name, $skip_external ) = @_; + + ref($name) && $name->can('renew') and return $name; + exists $Encoding{$name} and return $Encoding{$name}; my $lc = lc $name; - if (exists $Encoding{$name}) - { - return $Encoding{$name}; - } - if (exists $Encoding{$lc}) - { - return $Encoding{$lc}; - } + exists $Encoding{$lc} and return $Encoding{$lc}; my $oc = $class->find_alias($name); - return $oc if defined $oc; - - $oc = $class->find_alias($lc) if $lc ne $name; - return $oc if defined $oc; - - unless ($skip_external) - { - if (my $mod = $ExtModule{$name} || $ExtModule{$lc}){ - $mod =~ s,::,/,g ; $mod .= '.pm'; - eval{ require $mod; }; - return $Encoding{$name} if exists $Encoding{$name}; - } + defined($oc) and return $oc; + $lc ne $name and $oc = $class->find_alias($lc); + defined($oc) and return $oc; + + unless ($skip_external) { + if ( my $mod = $ExtModule{$name} || $ExtModule{$lc} ) { + $mod =~ s,::,/,g; + $mod .= '.pm'; + eval { require $mod; }; + exists $Encoding{$name} and return $Encoding{$name}; + } } return; } -sub find_encoding -{ - my ($name,$skip_external) = @_; - return __PACKAGE__->getEncoding($name,$skip_external); +sub find_encoding($;$) { + my ( $name, $skip_external ) = @_; + return __PACKAGE__->getEncoding( $name, $skip_external ); } -sub resolve_alias { +sub resolve_alias($) { my $obj = find_encoding(shift); defined $obj and return $obj->name; return; } -sub encode($$;$) -{ - my ($name,$string,$check) = @_; - $check ||=0; +sub clone_encoding($) { + my $obj = find_encoding(shift); + ref $obj or return; + eval { require Storable }; + $@ and return; + return Storable::dclone($obj); +} + +sub encode($$;$) { + my ( $name, $string, $check ) = @_; + return undef unless defined $string; + $string .= '' if ref $string; # stringify; + $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)); + unless ( defined $enc ) { + require Carp; + Carp::croak("Unknown encoding '$name'"); + } + my $octets = $enc->encode( $string, $check ); + $_[1] = $string if $check and !( $check & LEAVE_SRC() ); return $octets; } +*str2bytes = \&encode; -sub decode($$;$) -{ - my ($name,$octets,$check) = @_; - $check ||=0; +sub decode($$;$) { + my ( $name, $octets, $check ) = @_; + return undef unless defined $octets; + $octets .= '' if ref $octets; + $check ||= 0; my $enc = find_encoding($name); - croak("Unknown encoding '$name'") unless defined $enc; - my $string = $enc->decode($octets,$check); - $_[1] = $octets if $check; + unless ( defined $enc ) { + require Carp; + Carp::croak("Unknown encoding '$name'"); + } + my $string = $enc->decode( $octets, $check ); + $_[1] = $octets if $check and !( $check & LEAVE_SRC() ); return $string; } +*bytes2str = \&decode; -sub from_to($$$;$) -{ - my ($string,$from,$to,$check) = @_; - $check ||=0; +sub from_to($$$;$) { + my ( $string, $from, $to, $check ) = @_; + return undef unless defined $string; + $check ||= 0; my $f = find_encoding($from); - croak("Unknown encoding '$from'") unless defined $f; + unless ( defined $f ) { + require Carp; + Carp::croak("Unknown encoding '$from'"); + } my $t = find_encoding($to); - croak("Unknown encoding '$to'") unless defined $t; - 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 ; + unless ( defined $t ) { + require Carp; + Carp::croak("Unknown encoding '$to'"); + } + my $uni = $f->decode($string); + $_[0] = $string = $t->encode( $uni, $check ); + return undef if ( $check && length($uni) ); + return defined( $_[0] ) ? length($string) : undef; } -sub encode_utf8($) -{ +sub encode_utf8($) { my ($str) = @_; utf8::encode($str); return $str; } -sub decode_utf8($) -{ - my ($str) = @_; - return undef unless utf8::decode($str); - return $str; +sub decode_utf8($;$) { + my ( $str, $check ) = @_; + return $str if is_utf8($str); + if ($check) { + return decode( "utf8", $str, $check ); + } + else { + return decode( "utf8", $str ); + return $str; + } } -predefine_encodings(); +predefine_encodings(1); # # This is to restore %Encoding if really needed; # -sub predefine_encodings{ + +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; - *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"; + + # 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"; } { - # 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; - }; - $Encode::Encoding{utf8} = - bless {Name => "utf8"} => "Encode::utf8"; + + # was in Encode::utf8 + package Encode::utf8; + push @Encode::utf8::ISA, 'Encode::Encoding'; + + # + if ($use_xs) { + Encode::DEBUG and warn __PACKAGE__, " XS on"; + *decode = \&decode_xs; + *encode = \&encode_xs; + } + else { + Encode::DEBUG and warn __PACKAGE__, " XS off"; + *decode = sub { + my ( $obj, $octets, $chk ) = @_; + my $str = Encode::decode_utf8($octets); + if ( defined $str ) { + $_[1] = '' if $chk; + return $str; + } + return undef; + }; + *encode = sub { + my ( $obj, $string, $chk ) = @_; + my $octets = Encode::encode_utf8($string); + $_[1] = '' if $chk; + return $octets; + }; + } + *cat_decode = sub { # ($obj, $dst, $src, $pos, $trm, $chk) + # currently ignores $chk + my ( $obj, undef, undef, $pos, $trm ) = @_; + 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"; + $Encode::Encoding{"utf-8-strict"} = + bless { Name => "utf-8-strict", strict_utf8 => 1 } => + "Encode::utf8"; } } @@ -350,33 +389,31 @@ I: 8 bits of data, with ordinal values 0..255 =back -The marker [INTERNAL] marks Internal Implementation Details, in -general meant only for those who think they know what they are doing, -and such details may change in future releases. - =head1 PERL ENCODING API =over 2 -=item $octets = encode(ENCODING, $string[, CHECK]) +=item $octets = encode(ENCODING, $string [, CHECK]) 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. -For example, to convert (internally UTF-8 encoded) Unicode string to +For example, to convert a string from Perl's internal format to iso-8859-1 (also known as Latin1), - $octets = encode("iso-8859-1", $utf8); + $octets = encode("iso-8859-1", $string); -B: When you C<$octets = encode("utf8", $utf8)>, then $octets -B $utf8. Though they both contain the same data, the utf8 flag +B: When you run C<$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 $string = decode(ENCODING, $octets[, CHECK]) +If the $string is C then C is returned. + +=item $string = decode(ENCODING, $octets [, CHECK]) Decodes a sequence of octets assumed to be in I into Perl's internal form and returns the resulting string. As in encode(), @@ -384,39 +421,43 @@ ENCODING can be either a canonical name or an alias. For encoding names and aliases, see L. For CHECK, see L. -For example, to convert ISO-8859-1 data to UTF-8: +For example, to convert ISO-8859-1 data to a string in Perl's internal format: - $utf8 = decode("iso-8859-1", $latin1); + $string = decode("iso-8859-1", $octets); -B: When you C<$utf8 = encode("utf8", $octets)>, then $utf8 -B $utf8. Though they both contain the same data, -the utf8 flag for $utf8 is on unless $octets entirely conststs of +B: When you run C<$string = decode("utf8", $octets)>, then $string +B $octets. Though they both contain the same data, +the utf8 flag for $string is on unless $octets entirely consists of ASCII data (or EBCDIC on EBCDIC machines). See L below. -=item [$length =] from_to($string, FROM_ENC, TO_ENC [, CHECK]) +If the $string is C then C is returned. + +=item [$length =] from_to($octets, FROM_ENC, TO_ENC [, CHECK]) -Converts B data between two encodings. For example, to -convert ISO-8859-1 data to UTF-8: +Converts B data between two encodings. The data in $octets +must be encoded as octets and not as characters in Perl's internal +format. For example, to convert ISO-8859-1 data to Microsoft's CP1250 +encoding: - from_to($data, "iso-8859-1", "utf8"); + from_to($octets, "iso-8859-1", "cp1250"); and to convert it back: - from_to($data, "utf8", "iso-8859-1"); + from_to($octets, "cp1250", "iso-8859-1"); Note that because the conversion happens in place, the data to be converted cannot be a string constant; it must be a scalar variable. -from_to() returns the length of the converted string on success, undef -otherwise. +from_to() returns the length of the converted string in octets on +success, I on error. -B: The following operations look the same but not quite so; +B: The following operations look the same but are not quite so; - from_to($data, "iso-8859-1", "utf8"); #1 + from_to($data, "iso-8859-1", "utf8"); #1 $data = decode("iso-8859-1", $data); #2 -Both #1 and #2 makes $data consists of completely valid UTF-8 string +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 $data = encode("utf8", decode("iso-8859-1", $data)); @@ -426,15 +467,15 @@ See L below. =item $octets = encode_utf8($string); 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 +that comprise $string are encoded in Perl's internal format and the +result is returned as a sequence of octets. All possible characters have a UTF-8 representation so this function cannot fail. =item $string = decode_utf8($octets [, CHECK]); equivalent to C<$string = decode("utf8", $octets [, CHECK])>. -decode_utf8($octets [, CHECK]); The sequence of octets represented by +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 @@ -491,23 +532,24 @@ See L for details. =head1 Encoding via PerlIO -If your perl supports I, you can use a PerlIO layer to decode +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. # via PerlIO open my $in, "<:encoding(shiftjis)", $infile or die; open my $out, ">:encoding(euc-jp)", $outfile or die; - while(<>){ print; } + while(<$in>){ print $out $_; } # via from_to open my $in, "<", $infile or die; open my $out, ">", $outfile or die; - while(<>){ + while(<$in>){ from_to($_, "shiftjis", "euc-jp", 1); + print $out $_; } -Unfortunately, there may be encodings are PerlIO-savvy. You can check +Unfortunately, it may be that encodings are PerlIO-savvy. You can check if your encoding is supported by PerlIO by calling the C method. @@ -518,49 +560,59 @@ method. perlio_ok("euc-jp") Fortunately, all encodings that come with Encode core are PerlIO-savvy -except for hz and ISO-2022-kr. See L for details. - -For gory details, see L. +except for hz and ISO-2022-kr. For gory details, see +L and L. =head1 Handling Malformed Data +The optional I argument tells Encode what to do when it +encounters malformed data. Without CHECK, Encode::FB_DEFAULT ( == 0 ) +is assumed. + +As of version 2.12 Encode supports coderef values for CHECK. See below. + =over 2 -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. +=item B Not all encoding support this feature + +Some encodings ignore I argument. For example, +L ignores I and it always croaks on error. + +=back + +Now here is the list of I values available + +=over 2 =item I = Encode::FB_DEFAULT ( == 0) -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 +If I is 0, (en|de)code will put a I in +place of a malformed character. When you encode, EsubcharE +will be used. When you decode the code point C<0xFFFD> is used. If +the data is supposed to be UTF-8, an optional lexical warning (category utf8) is given. =item I = Encode::FB_CROAK ( == 1) -If I is 1, methods will die immediately with an error +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. +error with eval{} unless you really want to let it die. =item I = Encode::FB_QUIET 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: - - 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 +return the portion of the data that has been processed so far when an +error occurs. The data argument will be overwritten with everything +after that point (that is, the unprocessed part of data). This is +handy when you have to call decode repeatedly in the case where your +source data may contain partial multi-byte character sequences, +(i.e. you are reading with a fixed-width buffer). Here is a sample +code that does exactly this: + + my $buffer = ''; my $string = ''; + while(read $fh, $buffer, 256, length($buffer)){ + $string .= decode($encoding, $buffer, Encode::FB_QUIET); + # $buffer now contains the unprocessed partial character } =item I = Encode::FB_WARN @@ -577,15 +629,17 @@ you are debugging the mode above. For encodings that are implemented by Encode::XS, CHECK == Encode::FB_PERLQQ turns (en|de)code into C fallback mode. -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 +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. 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. +C<\x{I}>, HTML uses C<&#I;> where I is a decimal number and +XML uses C<&#xI;> where I is the hexadecimal number. + +In Encode 2.10 or later, C is also implied. =item The bitmask @@ -596,38 +650,47 @@ constants via C. FB_DEFAULT FB_CROAK FB_QUIET FB_WARN FB_PERLQQ DIE_ON_ERR 0x0001 X - WARN_ON_ER 0x0002 X + WARN_ON_ERR 0x0002 X RETURN_ON_ERR 0x0004 X X - LEAVE_SRC 0x0008 + LEAVE_SRC 0x0008 X PERLQQ 0x0100 X - HTMLCREF 0x0200 - XMLCREF 0x0400 + HTMLCREF 0x0200 + XMLCREF 0x0400 + +=back -=head2 Unimplemented fallback schemes +=head2 coderef for CHECK -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. +As of Encode 2.12 CHECK can also be a code reference which takes the +ord value of unmapped caharacter as an argument and returns a string +that represents the fallback character. For instance, + + $ascii = encode("ascii", $utf8, sub{ sprintf "", shift }); + +Acts like FB_PERLQQ but EU+IE is used instead of +\x{I}. =head1 Defining Encodings To define a new encoding, use: - use Encode qw(define_alias); + use Encode qw(define_encoding); define_encoding($object, 'canonicalName' [, alias...]); I 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. +arguments are taken as aliases for I<$object>. See L for more details. =head1 The UTF-8 flag Before the introduction of utf8 support in perl, The C operator -just compares internal data of the scalars. Now C means internal -data equality AND I. To explain why we made it so, I -will quote page 402 of C +just compared the strings represented by two scalars. Beginning with +perl 5.8, C compares two strings with simultaneous consideration +of I. To explain why we made it so, I will quote page +402 of C =over 2 @@ -655,26 +718,26 @@ byte-oriented Perl and a character-oriented Perl. Back when C was written, not even Perl 5.6.0 was born and many features documented in the book remained -unimplemented. Perl 5.8 hopefully correct this and the introduction -of UTF-8 flag is one of them. You can think this perl notion of -byte-oriented mode (utf8 flag off) and character-oriented mode (utf8 +unimplemented for a long time. Perl 5.8 corrected this and the introduction +of the UTF-8 flag is one of them. You can think of this perl notion as of a +byte-oriented mode (utf8 flag off) and a character-oriented mode (utf8 flag on). Here is how Encode takes care of the utf8 flag. -=over2 +=over 2 =item * When you encode, the resulting utf8 flag is always off. -=item +=item * -When you decode, the resuting utf8 flag is on unless you can +When you decode, the resulting utf8 flag is on unless you can unambiguously represent data. Here is the definition of dis-ambiguity. - After C<$utf8 = decode('foo', $octet);>, +After C<$utf8 = decode('foo', $octet);>, When $octet is... The utf8 flag in $utf8 is --------------------------------------------- @@ -683,7 +746,7 @@ dis-ambiguity. In any other Encoding ON --------------------------------------------- -As you see, there is one exception, In ASCII. That way you can assue +As you see, there is one exception, In ASCII. That way you can assume Goal #1. And with Encode Goal #2 is assumed but you still have to be careful in such cases mentioned in B paragraphs. @@ -707,6 +770,8 @@ implementation. As such, they are efficient but may change. If CHECK is true, also checks the data in STRING for being well-formed UTF-8. Returns true if successful, false otherwise. +As of perl 5.8.1, L also has utf8::is_utf8(). + =item _utf8_on(STRING) [INTERNAL] Turns on the UTF-8 flag in STRING. The data in STRING is @@ -724,6 +789,54 @@ not a string. =back +=head1 UTF-8 vs. utf8 + + ....We now view strings not as sequences of bytes, but as sequences + of numbers in the range 0 .. 2**32-1 (or in the case of 64-bit + computers, 0 .. 2**64-1) -- Programming Perl, 3rd ed. + +That has been the perl's notion of UTF-8 but official UTF-8 is more +strict; Its ranges is much narrower (0 .. 10FFFF), some sequences are +not allowed (i.e. Those used in the surrogate pair, 0xFFFE, et al). + +Now that is overruled by Larry Wall himself. + + From: Larry Wall + Date: December 04, 2004 11:51:58 JST + To: perl-unicode@perl.org + Subject: Re: Make Encode.pm support the real UTF-8 + Message-Id: <20041204025158.GA28754@wall.org> + + On Fri, Dec 03, 2004 at 10:12:12PM +0000, Tim Bunce wrote: + : I've no problem with 'utf8' being perl's unrestricted uft8 encoding, + : but "UTF-8" is the name of the standard and should give the + : corresponding behaviour. + + For what it's worth, that's how I've always kept them straight in my + head. + + Also for what it's worth, Perl 6 will mostly default to strict but + make it easy to switch back to lax. + + Larry + +Do you copy? As of Perl 5.8.7, B means strict, official UTF-8 +while B means liberal, lax, version thereof. And Encode version +2.10 or later thus groks the difference between C and C"utf8". + + encode("utf8", "\x{FFFF_FFFF}", 1); # okay + encode("UTF-8", "\x{FFFF_FFFF}", 1); # croaks + +C in Encode is actually a canonical name for C. +Yes, the hyphen between "UTF" and "8" is important. Without it Encode +goes "liberal" + + find_encoding("UTF-8")->name # is 'utf-8-strict' + find_encoding("utf-8")->name # ditto. names are case insensitive + find_encoding("utf_8")->name # ditto. "_" are treated as "-" + find_encoding("UTF8")->name # is 'utf8'. + + =head1 SEE ALSO L, @@ -741,6 +854,17 @@ the Perl Unicode Mailing List Eperl-unicode@perl.orgE 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. +Eperl-unicode@perl.orgE so we can all share. + +While Dan Kogai retains the copyright as a maintainer, the credit +should go to all those involoved. See AUTHORS for those submitted +codes. + +=head1 COPYRIGHT + +Copyright 2002-2006 Dan Kogai Edankogai@dan.co.jpE + +This library is free software; you can redistribute it and/or modify +it under the same terms as Perl itself. =cut