X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=blobdiff_plain;f=ext%2FEncode%2FEncode.pm;h=ac0123c89ec2083090bde1638f91819f743a2da4;hb=a19d7498e238ac7c03cb96036dee4a734a2a0356;hp=3dd0ed32f0e8103cb846213ee2c6d742e571dbb9;hpb=a999c27c2ea2bb1e0c2a144cb34d484858a577d3;p=p5sagit%2Fp5-mst-13.2.git diff --git a/ext/Encode/Encode.pm b/ext/Encode/Encode.pm index 3dd0ed3..ac0123c 100644 --- a/ext/Encode/Encode.pm +++ b/ext/Encode/Encode.pm @@ -1,137 +1,80 @@ +# +# $Id: Encode.pm,v 2.12 2005/09/08 14:17:17 dankogai Exp dankogai $ +# package Encode; use strict; -our $VERSION = do { my @r = (q$Revision: 1.20 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r }; -our $DEBUG = 0; +our $VERSION = sprintf "%d.%02d", q$Revision: 2.12 $ =~ /(\d+)/g; +sub DEBUG () { 0 } +use XSLoader (); +XSLoader::load(__PACKAGE__, $VERSION); -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 clone_encoding ); +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( - define_encoding - 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; - 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; - -my @codepages = qw( - 37 424 437 500 737 775 850 852 855 - 856 857 860 861 862 863 864 865 866 - 869 874 875 932 936 949 950 1006 1026 - 1047 1250 1251 1252 1253 1254 1255 1256 1257 - 1258 - ); - -my @macintosh = qw( - CentralEurRoman Croatian Cyrillic Greek - Iceland Roman Rumanian Sami - Thai Turkish Ukrainian - ); - -for my $k (2..11,13..16){ - $ExtModule{"iso-8859-$k"} = 'Encode/Byte.pm'; -} - -for my $k (@codepages){ - $ExtModule{"cp$k"} = 'Encode/Byte.pm'; -} - -for my $k (@macintosh) -{ - $ExtModule{"mac$k"} = 'Encode/Byte.pm'; -} - -%ExtModule = - (%ExtModule, - 'koi8-r' => 'Encode/Byte.pm', - 'posix-bc' => 'Encode/EBCDIC.pm', - cp037 => 'Encode/EBCDIC.pm', - cp1026 => 'Encode/EBCDIC.pm', - cp1047 => 'Encode/EBCDIC.pm', - cp500 => 'Encode/EBCDIC.pm', - cp875 => 'Encode/EBCDIC.pm', - dingbats => 'Encode/Symbol.pm', - macDingbats => 'Encode/Symbol.pm', - macSymbol => 'Encode/Symbol.pm', - symbol => 'Encode/Symbol.pm', - viscii => 'Encode/Byte.pm', -); - -unless ($ON_EBCDIC) { # CJK added to autoload unless EBCDIC env -%ExtModule =(%ExtModule, - 'euc-cn' => 'Encode/CN.pm', - gb2312 => 'Encode/CN.pm', - gb12345 => 'Encode/CN.pm', - gbk => 'Encode/CN.pm', - cp936 => 'Encode/CN.pm', - 'iso-ir-165' => 'Encode/CN.pm', - 'euc-jp' => 'Encode/JP.pm', - 'iso-2022-jp' => 'Encode/JP.pm', - 'iso-2022-jp-1' => 'Encode/JP.pm', - '7bit-jis' => 'Encode/JP.pm', - shiftjis => 'Encode/JP.pm', - macJapanese => 'Encode/JP.pm', - cp932 => 'Encode/JP.pm', - 'euc-kr' => 'Encode/KR.pm', - ksc5601 => 'Encode/KR.pm', - macKorean => 'Encode/KR.pm', - cp949 => 'Encode/KR.pm', - big5 => 'Encode/TW.pm', - 'big5-hkscs' => 'Encode/TW.pm', - cp950 => 'Encode/TW.pm', - gb18030 => 'Encode/HanExtra.pm', - big5plus => 'Encode/HanExtra.pm', - 'euc-tw' => 'Encode/HanExtra.pm', - ); -} - - - +require Encode::Config; +eval { require Encode::ConfigLocal }; sub encodings { my $class = shift; - my @modules = (@_ and $_[0] eq ":all") ? values %ExtModule : @_; - for my $m (@modules) - { - $DEBUG and warn "about to require $m;"; - eval { require $m; }; + 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} = $mod; + } + } } return - map({$_->[0]} - sort({$a->[1] cmp $b->[1]} - map({[$_, lc $_]} - grep({ $_ ne 'Internal' } keys %Encoding)))); + sort { lc $a cmp lc $b } + grep {!/^(?:Internal|Unicode|Guess)$/o} keys %enc; +} + +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 define_encoding @@ -141,80 +84,105 @@ sub define_encoding $Encoding{$name} = $obj; my $lc = lc($name); define_alias($lc => $obj) unless $lc eq $name; - while (@_) - { + while (@_){ my $alias = shift; - define_alias($alias,$obj); + define_alias($alias, $obj); } return $obj; } sub getEncoding { - my ($class,$name,$skip_external) = @_; - my $enc; - if (ref($name) && $name->can('new_sequence')) - { - return $name; - } + my ($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 $oc; + defined($oc) and return $oc; + $lc ne $name and $oc = $class->find_alias($lc); + defined($oc) and return $oc; - $oc = $class->find_alias($lc) if $lc ne $name; - return $oc if defined $oc; - - if (!$skip_external and exists $ExtModule{$lc}) + unless ($skip_external) { - eval{ require $ExtModule{$lc}; }; - return $Encoding{$name} if exists $Encoding{$name}; + 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 +sub find_encoding($;$) { - my ($name,$skip_external) = @_; + my ($name, $skip_external) = @_; return __PACKAGE__->getEncoding($name,$skip_external); } -sub encode +sub resolve_alias($){ + my $obj = find_encoding(shift); + defined $obj and return $obj->name; + return; +} + +sub clone_encoding($){ + my $obj = find_encoding(shift); + ref $obj or return; + eval { require Storable }; + $@ and return; + return Storable::dclone($obj); +} + +sub encode($$;$) { - my ($name,$string,$check) = @_; + my ($name, $string, $check) = @_; + return undef unless defined $string; + $string .= '' if ref $string; # stringify; + $check ||=0; my $enc = find_encoding($name); - croak("Unknown encoding '$name'") unless defined $enc; + unless(defined $enc){ + require Carp; + Carp::croak("Unknown encoding '$name'"); + } my $octets = $enc->encode($string,$check); - return undef if ($check && length($string)); + $_[1] = $string if $check and !($check & LEAVE_SRC()); return $octets; } -sub decode +sub decode($$;$) { my ($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; + unless(defined $enc){ + require Carp; + Carp::croak("Unknown encoding '$name'"); + } my $string = $enc->decode($octets,$check); - $_[1] = $octets if $check; + $_[1] = $octets if $check and !($check & LEAVE_SRC()); return $string; } -sub from_to +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; + 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); @@ -222,27 +190,120 @@ sub from_to return defined($_[0] = $string) ? length($string) : undef ; } -sub encode_utf8 +sub encode_utf8($) { my ($str) = @_; - utf8::encode($str); + utf8::encode($str); return $str; } -sub decode_utf8 +sub decode_utf8($;$) { - my ($str) = @_; - return undef unless utf8::decode($str); - return $str; + my ($str, $check) = @_; + if ($check){ + return decode("utf8", $str, $check); + }else{ + return decode("utf8", $str); + return $str; + } } -require Encode::Encoding; -require Encode::XS; -require Encode::Internal; -require Encode::Unicode; -require Encode::utf8; -require Encode::10646_1; -require Encode::ucs2_le; +predefine_encodings(1); + +# +# This is to restore %Encoding if really needed; +# + +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"; + } + + { + # 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) + 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"; + $Encode::Encoding{"utf-8-strict"} = + bless {Name => "utf-8-strict", strict_utf8 => 1 } => "Encode::utf8"; + } +} 1; @@ -256,17 +317,16 @@ Encode - character encodings use Encode; - =head2 Table of Contents -Encode consists of a collection of modules which details are too big +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; +and general topics at a glance. For other topics and more details, +see the PODs below: Name Description -------------------------------------------------------- - Encode::Alias Alias defintions to encodings + Encode::Alias Alias definitions to encodings Encode::Encoding Encode Implementation Base Class Encode::Supported List of Supported Encodings Encode::CN Simplified Chinese Encodings @@ -288,21 +348,21 @@ 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). -Traditionally 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 +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 +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 +byte has 256 possible values, it easily fits in Perl's much larger "logical character". =head2 TERMINOLOGY -=over 4 +=over 2 =item * @@ -317,63 +377,101 @@ 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 PERL ENCODING API -=over 4 +=over 2 -=item $bytes = encode(ENCODING, $string[, CHECK]) +=item $octets = encode(ENCODING, $string [, CHECK]) -Encodes string from Perl's internal form into I and returns +Encodes a string from Perl's internal form into I and returns a sequence of octets. ENCODING can be either a canonical name or -alias. For encoding names and aliases, see L. -For CHECK see L. +an alias. For encoding names and aliases, see L. +For CHECK, see L. + +For example, to convert a string from Perl's internal format to +iso-8859-1 (also known as Latin1), -For example to convert (internally UTF-8 encoded) Unicode string to -iso-8859-1 (also known as Latin1), + $octets = encode("iso-8859-1", $string); - $octets = encode("iso-8859-1", $unicode); +B: When you run C<$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, $bytes[, CHECK]) +If the $string is C then C is returned. -Decode 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 alias. For encoding names -and aliases, see L. For CHECK see +=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(), +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: + + $string = decode("iso-8859-1", $octets); - $utf8 = decode("iso-8859-1", $latin1); +B: When you run C<$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_ENCODING, TO_ENCODING[, CHECK]) +If the $string is C then C is returned. -Convert B the data between two encodings. How did the data -in $string originally get to be in FROM_ENCODING? Either using -encode() or through PerlIO: See L. -For encoding names and aliases, see L. -For CHECK see L. +=item [$length =] from_to($octets, FROM_ENC, TO_ENC [, CHECK]) -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", "utf-8"); + from_to($octets, "iso-8859-1", "cp1250"); and to convert it back: - from_to($data, "utf-8", "iso-8859-1"); + from_to($octets, "cp1250", "iso-8859-1"); Note that because the conversion happens in place, the data to be -converted cannot be a string constant, it must be a scalar variable. +converted cannot be a string constant; it must be a scalar variable. + +from_to() returns the length of the converted string in octets on +success, I on error. -from_to() return the length of the converted string on success, undef -otherwise. +B: The following operations look the same but are not quite so; + + from_to($data, "iso-8859-1", "utf8"); #1 + $data = decode("iso-8859-1", $data); #2 + +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)); + +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 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", $octets [, CHECK])>. +The sequence of octets represented by +$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 @@ -388,233 +486,366 @@ ones that are not loaded yet, say @all_encodings = Encode->encodings(":all"); -Or you can give the name of specific module. +Or you can give the name of a specific module. - @with_jp = Encode->encodings("Encode/JP.pm"); + @with_jp = Encode->encodings("Encode::JP"); -Note in this case you have to say C<"Encode/JP.pm"> instead of -C<"Encode::JP">. +When "::" is not in the name, "Encode::" is assumed. -To find which encodings are supported by this package in details, -see L. + @ebcdic = Encode->encodings("EBCDIC"); +To find out in detail which encodings are supported by this package, +see L. =head2 Defining Aliases -To add new alias to a given encoding, Use; +To add a new alias to a given encoding, use: use Encode; use Encode::Alias; define_alias(newName => ENCODING); After that, newName can be used as an alias for ENCODING. -ENCODING may be either the name of an encoding or an I +ENCODING may be either the name of an encoding or an +I -See L on details. +But before you do so, make sure the alias is nonexistent with +C, which returns the canonical name thereof. +i.e. -=head1 Encoding and IO + 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 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. +resolve_alias() does not need C; it can be +exported via C. -Here is how the blind poet would modernise the encoding: +See L for details. - 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); +=head1 Encoding via PerlIO -In addition the new IO system can also be configured to read/write -UTF-8 encoded characters (as noted above this is efficient): +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. - open(my $fh,'>:utf8','anything'); - print $fh "Any \x{0021} string \N{SMILEY FACE}\n"; + # via PerlIO + open my $in, "<:encoding(shiftjis)", $infile or die; + open my $out, ">:encoding(euc-jp)", $outfile or die; + while(<$in>){ print $out $_; } -Either of the above forms of "layer" specifications can be made the default -for a lexical scope with the C pragma. See L. + # 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 $_; + } -Once a handle is open is layers can be altered using C. +Unfortunately, it may be that encodings are PerlIO-savvy. You can check +if your encoding is supported by PerlIO by calling the C +method. -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. + Encode::perlio_ok("hz"); # False + find_encoding("euc-cn")->perlio_ok; # True where PerlIO is available -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, ...). + use Encode qw(perlio_ok); # exported upon request + perlio_ok("euc-jp") -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): +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. - open(F, "<:encoding(iso-8859-1)", "data.txt") or die $!; - open(G, ">:utf8", "data.utf") or die $!; - while () { print G } +=head1 Handling Malformed Data - # Could also do "print G " but that would pull - # the whole file into memory just to write it out again. +The optional I argument tells Encode what to do when it +encounters malformed data. Without CHECK, Encode::FB_DEFAULT ( == 0 ) +is assumed. -More examples: +As of version 2.12 Encode supports coderef values for CHECK. See below. - open(my $f, "<:encoding(cp1252)") - open(my $g, ">:encoding(iso-8859-2)") - open(my $h, ">:encoding(latin9)") # iso-8859-15 +=over 2 -See L for more information. +=item B Not all encoding support this feature -See also L for how to change the default encoding of the -data in your script. +Some encodings ignore I argument. For example, +L ignores I and it always croaks on error. -=head1 Handling Malformed Data +=back -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. +Now here is the list of I values available -It would desirable to have a way to indicate that transform should use -the encodings "replacement character" - no such mechanism is defined yet. +=over 2 -It is also planned to allow I to be a code reference. +=item I = Encode::FB_DEFAULT ( == 0) -This is not yet implemented as there are design issues with what its -arguments should be and how it returns its results. +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. -=over 4 +=item I = Encode::FB_CROAK ( == 1) -=item Scheme 1 +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 +error with eval{} unless you really want to let it die. -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. +=item I = Encode::FB_QUIET - sub fixup { - my $ch = substr($_[0],0,1,''); - return sprintf("\x{%02X}",ord($ch); - } +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, +(i.e. you are reading with a fixed-width buffer). Here is a sample +code that does exactly this: -This scheme is close to how underlying C code for Encode works, but gives -the fixup routine very little context. + my $buffer = ''; my $string = ''; + while(read $fh, $buffer, 256, length($buffer)){ + $string .= decode($encoding, $buffer, Encode::FB_QUIET); + # $buffer now contains the unprocessed partial character + } -=item Scheme 2 +=item I = Encode::FB_WARN -Passed original string, and an index into it of the problem area, and -output string so far. Appends what it will to output string and -returns new index into original string. For example: +This is the same as above, except that it warns on error. Handy when +you are debugging the mode above. - sub fixup { - # my ($s,$i,$d) = @_; - my $ch = substr($_[0],$_[1],1); - $_[2] .= sprintf("\x{%02X}",ord($ch); - return $_[1]+1; - } +=item perlqq mode (I = Encode::FB_PERLQQ) -This scheme gives maximal control to the fixup routine but is more -complicated to code, and may need internals of Encode to be tweaked to -keep original string intact. +=item HTML charref mode (I = Encode::FB_HTMLCREF) -=item Other Schemes +=item XML charref mode (I = Encode::FB_XMLCREF) -Hybrids of above. +For encodings that are implemented by Encode::XS, CHECK == +Encode::FB_PERLQQ turns (en|de)code into C fallback mode. -Multiple return values rather than in-place modifications. +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. -Index into the string could be C allowing C. +HTML/XML character reference modes are about the same, in place of +C<\x{I}>, HTML uses C<&#I;> where I is a decimal number and +XML uses C<&#xI;> where I is the hexadecimal number. -=back +In Encode 2.10 or later, C is also implied. -=head2 UTF-8 / utf8 +=item The bitmask -The Unicode consortium defines the UTF-8 standard as a way of encoding -the entire Unicode repertoire as sequences of octets. This encoding is -expected to become very widespread. Perl can use this form internally -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). +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. -=over 4 + 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 X + PERLQQ 0x0100 X + HTMLCREF 0x0200 + XMLCREF 0x0400 -=item $bytes = encode_utf8($string); +=back -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. +=head2 coderef for CHECK -=item $string = decode_utf8($bytes [, CHECK]); +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, -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. + $ascii = encode("ascii", $utf8, sub{ sprintf "", shift }); -=back +Acts like FB_PERLQQ but EU+IE is used instead of +\x{I}. =head1 Defining Encodings To define a new encoding, use: - use Encode qw(define_alias); + use Encode qw(define_encoding); define_encoding($object, 'canonicalName' [, alias...]); I will be associated with I<$object>. The object -should provide the interface described in L +should provide the interface described in L. If more than two arguments are provided then additional -arguments are taken as aliases for I<$object> as for C. +arguments are taken as aliases for I<$object>. + +See L for more details. + +=head1 The UTF-8 flag + +Before the introduction of utf8 support in perl, The C operator +just compared the strings represented by two scalars. Beginning with +perl 5.8, C compares two strings with simultaneous consideration +of I. To explain why we made it so, I will quote page +402 of C + +=over 2 + +=item Goal #1: + +Old byte-oriented programs should not spontaneously break on the old +byte-oriented data they used to work on. + +=item Goal #2: -=head1 Messing with Perl's Internals +Old byte-oriented programs should magically start working on the new +character-oriented data when appropriate. + +=item Goal #3: + +Programs should run just as fast in the new character-oriented mode +as in the old byte-oriented mode. + +=item Goal #4: + +Perl should remain one language, rather than forking into a +byte-oriented Perl and a character-oriented Perl. + +=back + +Back when C was written, not even Perl 5.6.0 +was born and many features documented in the book remained +unimplemented for a long time. Perl 5.8 corrected this and the introduction +of the UTF-8 flag is one of them. You can think of this perl notion as of a +byte-oriented mode (utf8 flag off) and a character-oriented mode (utf8 +flag on). + +Here is how Encode takes care of the utf8 flag. + +=over 2 + +=item * + +When you encode, the resulting utf8 flag is always off. + +=item * + +When you decode, the resulting utf8 flag is on unless you can +unambiguously represent data. Here is the definition of +dis-ambiguity. + +After C<$utf8 = decode('foo', $octet);>, + + 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 + --------------------------------------------- + +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. + +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 + +=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]) -[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. +As of perl 5.8.1, L also has utf8::is_utf8(). + =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. +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 _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 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("utf8")->name # ditto. "_" are treated as "-" + find_encoding("UTF8")->name # is 'utf8'. + + =head1 SEE ALSO L, L, -L, +L, L, -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. + =cut