X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=blobdiff_plain;f=ext%2FEncode%2FEncode.pm;h=4a4edfcd961c09bd5a6b378986e030ba79a3b3a7;hb=b0b300a384d843083e544b5c41bee6f597f2a144;hp=db471cb059efdc4506b47cb9b91fce6f76dcd0ed;hpb=2f2b4ff2c154a8e461857f2e82cb815c238d0d94;p=p5sagit%2Fp5-mst-13.2.git diff --git a/ext/Encode/Encode.pm b/ext/Encode/Encode.pm index db471cb..4a4edfc 100644 --- a/ext/Encode/Encode.pm +++ b/ext/Encode/Encode.pm @@ -1,604 +1,639 @@ package Encode; - -$VERSION = 0.01; +use strict; +our $VERSION = do { my @r = (q$Revision: 1.51 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r }; +our $DEBUG = 0; require DynaLoader; require Exporter; -@ISA = qw(Exporter DynaLoader); - -@EXPORT_OK = - qw( - bytes_to_utf8 - utf8_to_bytes - chars_to_utf8 - utf8_to_chars - utf8_to_chars_check - bytes_to_chars - chars_to_bytes - from_to - is_utf8 - on_utf8 - off_utf8 - utf_to_utf - encodings - ); +our @ISA = qw(Exporter DynaLoader); -bootstrap Encode (); +# Public, encouraged API is exported by default -=pod +our @EXPORT = qw( + decode decode_utf8 encode encode_utf8 + encodings find_encoding +); -=head1 NAME +our @FB_FLAGS = qw(DIE_ON_ERR WARN_ON_ERR RETURN_ON_ERR LEAVE_SRC PERLQQ); +our @FB_CONSTS = qw(FB_DEFAULT FB_QUIET FB_WARN FB_PERLQQ FB_CROAK); -Encode - character encodings +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, + ); -=head2 TERMINOLOGY +our %EXPORT_TAGS = + ( + all => [ @EXPORT, @EXPORT_OK ], + fallbacks => [ @FB_CONSTS ], + fallback_all => [ @FB_CONSTS, @FB_FLAGS ], + ); -=over -=item * +bootstrap Encode (); -I: a character in the range 0..maxint (at least 2**32-1) +# Documentation moved after __END__ for speed - NI-S -=item * +use Carp; -I: a character in the range 0..255 +our $ON_EBCDIC = (ord("A") == 193); -=back +use Encode::Alias; -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. +# Make a %Encoding package variable to allow a certain amount of cheating +our %Encoding; +our %ExtModule; +require Encode::Config; +eval { require Encode::ConfigLocal }; -=head2 bytes +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 $mod; }; + } + my %modules = map {$_ => 1} @modules; + return + sort { lc $a cmp lc $b } + grep {!/^(?:Internal|Unicode)$/o} keys %Encoding; +} -=over 4 +sub perlio_ok{ + exists $INC{"PerlIO/encoding.pm"} or return 0; + my $stash = ref($_[0]); + $stash ||= ref(find_encoding($_[0])); + return ($stash eq "Encode::XS" || $stash eq "Encode::Unicode"); +} -=item * +sub define_encoding +{ + my $obj = shift; + my $name = shift; + $Encoding{$name} = $obj; + my $lc = lc($name); + define_alias($lc => $obj) unless $lc eq $name; + while (@_) + { + my $alias = shift; + define_alias($alias,$obj); + } + return $obj; +} - bytes_to_utf8(STRING [, FROM]) +sub getEncoding +{ + my ($class,$name,$skip_external) = @_; + my $enc; + if (ref($name) && $name->can('new_sequence')) + { + return $name; + } + my $lc = lc $name; + if (exists $Encoding{$name}) + { + return $Encoding{$name}; + } + if (exists $Encoding{$lc}) + { + return $Encoding{$lc}; + } -The bytes in STRING are recoded in-place into UTF-8. If no FROM is -specified the bytes are expected to be encoded in US-ASCII or ISO -8859-1 (Latin 1). Returns the new size of STRING, or C if -there's a failure. + my $oc = $class->find_alias($name); + return $oc if defined $oc; -[INTERNAL] Also the UTF-8 flag of STRING is turned on. + $oc = $class->find_alias($lc) if $lc ne $name; + return $oc if defined $oc; -=item * + unless ($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; +} - utf8_to_bytes(STRING [, TO [, CHECK]]) +sub find_encoding +{ + my ($name,$skip_external) = @_; + return __PACKAGE__->getEncoding($name,$skip_external); +} -The UTF-8 in STRING is decoded in-place into bytes. If no TO encoding -is specified the bytes are expected to be encoded in US-ASCII or ISO -8859-1 (Latin 1). Returns the new size of STRING, or C if -there's a failure. +sub resolve_alias { + my $obj = find_encoding(shift); + defined $obj and return $obj->name; + return; +} -What if there are characters > 255? What if the UTF-8 in STRING is -malformed? See L. +sub encode($$;$) +{ + my ($name,$string,$check) = @_; + $check ||=0; + my $enc = find_encoding($name); + croak("Unknown encoding '$name'") unless defined $enc; + my $octets = $enc->encode($string,$check); + return undef if ($check && length($string)); + return $octets; +} -[INTERNAL] The UTF-8 flag of STRING is not checked. +sub decode($$;$) +{ + my ($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; +} -=back +sub from_to($$$;$) +{ + my ($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 ; +} -=head2 chars +sub encode_utf8($) +{ + my ($str) = @_; + utf8::encode($str); + return $str; +} -=over 4 +sub decode_utf8($) +{ + my ($str) = @_; + return undef unless utf8::decode($str); + return $str; +} -=item * +predefine_encodings(); + +# +# This is to restore %Encoding if really needed; +# +sub predefine_encodings{ + if ($ON_EBCDIC) { + # was in Encode::UTF_EBCDIC + package Encode::UTF_EBCDIC; + *name = sub{ shift->{'Name'} }; + *new_sequence = sub{ return $_[0] }; + *decode = sub{ + my ($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 $_[0] }; + *decode = sub{ + my ($obj,$str,$chk) = @_; + utf8::upgrade($str); + $_[1] = '' if $chk; + return $str; + }; + *encode = \&decode; + $Encode::Encoding{Unicode} = + bless {Name => "Internal"} => "Encode::Internal"; + } - chars_to_utf8(STRING) + { + # was in Encode::utf8 + package Encode::utf8; + *name = sub{ shift->{'Name'} }; + *new_sequence = sub{ return $_[0] }; + *decode = sub{ + my ($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"; + } +} -The chars in STRING are encoded in-place into UTF-8. Returns the new -size of STRING, or C if there's a failure. +require Encode::Encoding; -No assumptions are made on the encoding of the chars. If you want to -assume that the chars are Unicode and to trap illegal Unicode -characters, you must use C. +eval { + require PerlIO::encoding; + unless (PerlIO::encoding->VERSION >= 0.02){ + delete $INC{"PerlIO/encoding.pm"}; + } +}; +# warn $@ if $@; -[INTERNAL] Also the UTF-8 flag of STRING is turned on. +1; -=over 4 +__END__ -=item * +=head1 NAME + +Encode - character encodings - utf8_to_chars(STRING) +=head1 SYNOPSIS -The UTF-8 in STRING is decoded in-place into chars. Returns the new -size of STRING, or C if there's a failure. + use Encode; -If the UTF-8 in STRING is malformed C is returned, and also an -optional lexical warning (category utf8) is given. -[INTERNAL] The UTF-8 flag of STRING is not checked. +=head2 Table of Contents -=item * +Encode consists of a collection of modules which 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; - utf8_to_chars_check(STRING [, CHECK]) + Name Description + -------------------------------------------------------- + Encode::Alias Alias defintions 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 + -------------------------------------------------------- -(Note that special naming of this interface since a two-argument -utf8_to_chars() has different semantics.) +=head1 DESCRIPTION -The UTF-8 in STRING is decoded in-place into chars. Returns the new -size of STRING, or C if there is a failure. +The C module provides the interfaces between Perl's strings +and the rest of the system. Perl strings are sequences of +B. -If the UTF-8 in STRING is malformed? See L. +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). -[INTERNAL] The UTF-8 flag of STRING is not checked. +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. -=back +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 chars With Encoding +=head2 TERMINOLOGY =over 4 =item * - chars_to_utf8(STRING, FROM [, CHECK]) - -The chars in STRING encoded in FROM are recoded in-place into UTF-8. -Returns the new size of STRING, or C if there's a failure. - -No assumptions are made on the encoding of the chars. If you want to -assume that the chars are Unicode and to trap illegal Unicode -characters, you must use C. - -[INTERNAL] Also the UTF-8 flag of STRING is turned on. +I: a character in the range 0..(2**32-1) (or more). +(What Perl's strings are made of.) =item * - utf8_to_chars(STRING, TO [, CHECK]) - -The UTF-8 in STRING is decoded in-place into chars encoded in TO. -Returns the new size of STRING, or C if there's a failure. +I: a character in the range 0..255 +(A special case of a Perl character.) -If the UTF-8 in STRING is malformed? See L. +=item * -[INTERNAL] The UTF-8 flag of STRING is not checked. +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.) -=item * +=back - bytes_to_chars(STRING, FROM [, CHECK]) +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. -The bytes in STRING encoded in FROM are recoded in-place into chars. -Returns the new size of STRING in bytes, or C if there's a -failure. +=head1 PERL ENCODING API -If the mapping is impossible? See L. +=over 4 -=item * +=item $octets = encode(ENCODING, $string[, CHECK]) - chars_to_bytes(STRING, TO [, CHECK]) +Encodes 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. -The chars in STRING are recoded in-place to bytes encoded in TO. -Returns the new size of STRING in bytes, or C if there's a -failure. +For example to convert (internally UTF-8 encoded) Unicode string to +iso-8859-1 (also known as Latin1), -If the mapping is impossible? See L. + $octets = encode("iso-8859-1", $unicode); -=item * +=item $string = decode(ENCODING, $octets[, CHECK]) - from_to(STRING, FROM, TO [, CHECK]) +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 +L. -The chars in STRING encoded in FROM are recoded in-place into TO. -Returns the new size of STRING, or C if there's a failure. +For example to convert ISO-8859-1 data to UTF-8: -If mapping between the encodings is impossible? -See L. + $utf8 = decode("iso-8859-1", $latin1); -[INTERNAL] If TO is UTF-8, also the UTF-8 flag of STRING is turned on. +=item [$length =] from_to($string, FROM_ENCODING, TO_ENCODING [,CHECK]) -=back +Convert B the data between two encodings. +For example to convert ISO-8859-1 data to UTF-8: -=head2 Testing For UTF-8 + from_to($data, "iso-8859-1", "utf-8"); -=over 4 +and to convert it back: -=item * + from_to($data, "utf-8", "iso-8859-1"); - is_utf8(STRING [, CHECK]) +Note that because the conversion happens in place, the data to be +converted cannot be a string constant, it must be a scalar variable. -[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. +from_to() return the length of the converted string on success, undef +otherwise. =back -=head2 Toggling UTF-8-ness +=head2 UTF-8 / utf8 + +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). =over 4 -=item * +=item $octets = encode_utf8($string); - on_utf8(STRING) +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. -[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. +=item $string = decode_utf8($octets [, CHECK]); -=item * +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. - off_utf8(STRING) +=back -[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. +=head2 Listing available encodings -=back + use Encode; + @list = Encode->encodings(); -=head2 UTF-16 and UTF-32 Encodings +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 -=over 4 + @all_encodings = Encode->encodings(":all"); -=item * +Or you can give the name of specific module. - utf_to_utf(STRING, FROM, TO [, CHECK]) + @with_jp = Encode->encodings("Encode::JP"); -The data in STRING is converted from Unicode Transfer Encoding FROM to -Unicode Transfer Encoding TO. Both FROM and TO may be any of the -following tags (case-insensitive, with or without 'utf' or 'utf-' prefix): +When "::" is not in the name, "Encode::" is assumed. - tag meaning + @ebcdic = Encode->encodings("EBCDIC"); - '7' UTF-7 - '8' UTF-8 - '16be' UTF-16 big-endian - '16le' UTF-16 little-endian - '16' UTF-16 native-endian - '32be' UTF-32 big-endian - '32le' UTF-32 little-endian - '32' UTF-32 native-endian +To find which encodings are supported by this package in details, +see L. -UTF-16 is also known as UCS-2, 16 bit or 2-byte chunks, and UTF-32 as -UCS-4, 32-bit or 4-byte chunks. Returns the new size of STRING, or -C is there's a failure. +=head2 Defining Aliases -If FROM is UTF-8 and the UTF-8 in STRING is malformed? See -L. +To add new alias to a given encoding, Use; -[INTERNAL] Even if CHECK is true and FROM is UTF-8, the UTF-8 flag of -STRING is not checked. If TO is UTF-8, also the UTF-8 flag of STRING is -turned on. Identical FROM and TO are fine. + use Encode; + use Encode::Alias; + define_alias(newName => ENCODING); -=back +After that, newName can be used as an alias for ENCODING. +ENCODING may be either the name of an encoding or an +I -=head2 Handling Malformed Data +But before you do so, make sure the alias is nonexistent with +C, which returns the canonical name thereof. +i.e. -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. If CHECK is a code -reference, it is called with the arguments + 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 - (MALFORMED_STRING, STRING_FROM_SO_FAR, STRING_TO_SO_FAR) +This resolve_alias() does not need C and is +exported via C. -Two return values are expected from the call: the string to be used in -the result string in place of the malformed section, and the length of -the malformed section in bytes. +See L on details. -=cut +=head1 Encoding via PerlIO -sub bytes_to_utf8 { - &_bytes_to_utf8; -} +If your perl supports I, you can use PerlIO layer to directly +decode and encode via filehandle. The following two examples are +totally identical by functionality. -sub utf8_to_bytes { - &_utf8_to_bytes; -} + # via PerlIO + open my $in, "<:encoding(shiftjis)", $infile or die; + open my $out, ">:encoding(euc-jp)", $outfile or die; + while(<>){ print; } -sub chars_to_utf8 { - &C_to_utf8; -} + # via from_to + open my $in, $infile or die; + open my $out, $outfile or die; + while(<>){ + from_to($_, "shiftjis", "euc", 1); + } -sub utf8_to_chars { - &_utf8_to_chars; -} +Unfortunately, not all encodings are PerlIO-savvy. You can check if +your encoding is supported by PerlIO by C method. -sub utf8_to_chars_check { - &_utf8_to_chars_check; -} + Encode::perlio_ok("iso-20220jp"); # false + find_encoding("iso-2022-jp")->perlio_ok; # false + use Encode qw(perlio_ok); # exported upon request + perlio_ok("euc-jp") # true if PerlIO is enabled -sub bytes_to_chars { - &_bytes_to_chars; -} +For gory details, see L; -sub chars_to_bytes { - &_chars_to_bytes; -} +=head1 Handling Malformed Data -sub is_utf8 { - &_is_utf8; -} +=over 4 -sub on_utf8 { - &_on_utf8; -} +THE I argument is used as follows. When you omit it, it is +identical to I = 0. -sub off_utf8 { - &_off_utf8; -} +=item I = Encode::FB_DEFAULT ( == 0) -sub utf_to_utf { - &_utf_to_utf; -} +If I is 0, (en|de)code will put I in +place of the malformed character. for UCM-based encodings, +EsubcharE will be used. For Unicode, \xFFFD is used. If the +data is supposed to be UTF-8, an optional lexical warning (category +utf8) is given. -use Carp; +=item I = Encode::DIE_ON_ERROR (== 1) -sub from_to -{ - my ($string,$from,$to,$check) = @_; - my $f = __PACKAGE__->getEncoding($from); - croak("Unknown encoding '$from'") unless $f; - my $t = __PACKAGE__->getEncoding($to); - croak("Unknown encoding '$to'") unless $t; - my $uni = $f->toUnicode($string,$check); - return undef if ($check && length($string)); - $string = $t->fromUnicode($uni,$check); - return undef if ($check && length($uni)); - return length($_[0] = $string); -} +If I is 1, methods will die immediately with an error +message. so when I is set, you should trap the fatal error +with eval{} unless you really want to let it die on error. -# The global hash is declared in XS code -$encoding{Unicode} = bless({},'Encode::Unicode'); -$encoding{iso10646-1} = bless({},'Encode::iso10646_1'); +=item I = Encode::FB_QUIET -sub encodings -{ - my ($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); - } - } - return keys %encoding; -} +If I is set to Encode::FB_QUIET, (en|de)code will immediately +return proccessed part on error, with data passed via argument +overwritten with unproccessed part. This is handy when have to +repeatedly call because the source data is chopped in the middle for +some reasons, such as fixed-width buffer. Here is a sample code that +just does this. -sub loadEncoding -{ - my ($class,$name,$file) = @_; - if (open(my $fh,$file)) - { - my $type; - while (1) - { - my $line = <$fh>; - $type = substr($line,0,1); - last unless $type eq '#'; - } - $class .= ('::'.(($type eq 'E') ? 'Escape' : 'Table')); - warn "Loading $file"; - return $class->read($fh,$name,$type); - } - else - { - return undef; + my $data = ''; + while(defined(read $fh, $buffer, 256)){ + # buffer may end in partial character so we append + $data .= $buffer; + $utf8 .= decode($encoding, $data, ENCODE::FB_QUIET); + # $data now contains unprocessed partial character } -} -sub getEncoding -{ - my ($class,$name) = @_; - my $enc; - unless (ref($enc = $encoding{$name})) - { - $enc = $class->loadEncoding($name,$enc) if defined $enc; - unless (ref($enc)) - { - foreach my $dir (@INC) - { - last if ($enc = $class->loadEncoding($name,"$dir/Encode/$name.enc")); - } - } - $encoding{$name} = $enc; - } - return $enc; -} +=item I = Encode::FB_WARN -package Encode::Unicode; +This is the same as above, except it warns on error. Handy when you +are debugging the mode above. -# Dummy package that provides the encode interface +=item perlqq mode (I = Encode::FB_PERLQQ) -sub name { 'Unicode' } +For encodings that are implemented by Encode::XS, CHECK == +Encode::FB_PERLQQ turns (en|de)code into C fallback mode. -sub toUnicode { $_[1] } +When you decode, '\xI' will be placed where I is the hex +representation of the octet that could not be decoded to utf8. And +when you encode, '\x{I}' will be placed where I is the +Unicode ID of the character that cannot be found in the character +repartoire of the encoding. -sub fromUnicode { $_[1] } +=item The bitmask -package Encode::Table; +These modes are actually set via bitmask. here is how FB_XX are laid +out. for FB_XX you can import via C for +generic bitmask constants, you can import via + C. -sub read -{ - my ($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; - } + 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 - return bless {Name => $name, - Rep => $rep, - ToUni => \@touni, - FmUni => \%fmuni, - Def => $def, - Num => $count, - },$class; -} +=head2 Unemplemented fallback schemes -sub name { shift->{'Name'} } +In 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. -sub rep_S { 'C' } +=head1 Defining Encodings -sub rep_D { 'n' } +To define a new encoding, use: -sub rep_M { ($_[0] > 255) ? 'n' : 'C' } + use Encode qw(define_alias); + define_encoding($object, 'canonicalName' [, alias...]); -sub representation -{ - my ($obj,$ch) = @_; - $ch = 0 unless @_ > 1; - $obj-{'Rep'}->($ch); -} +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. -sub toUnicode -{ - 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 $uni; -} +See L for more details. -sub fromUnicode -{ - my ($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; - } - $str .= pack(&$rep($x),$x); - } - $_[1] = $uni if $chk; - return $str; -} +=head1 Messing with Perl's Internals -package Encode::iso10646_1;# +The following API uses parts of Perl's internals in the current +implementation. As such they are efficient, but may change. -sub name { 'iso10646-1' } +=over 4 -sub toUnicode -{ - my ($obj,$str,$chk) = @_; - my $uni = ''; - while (length($str)) - { - my $code = unpack('n',substr($str,0,2,'')) & 0xffff; - $uni .= chr($code); - } - $_[1] = $str if $chk; - return $uni; -} +=item is_utf8(STRING [, CHECK]) -sub fromUnicode -{ - my ($obj,$uni,$chk) = @_; - my $str = ''; - while (length($uni)) - { - my $ch = substr($uni,0,1,''); - my $x = ord($ch); - unless ($x < 32768) - { - last if ($chk); - $x = 0; - } - $str .= pack('n',$x); - } - $_[1] = $uni if $chk; - return $str; -} +[INTERNAL] Test whether the UTF-8 flag is turned on in the STRING. +If CHECK is true, also checks the data in STRING for being well-formed +UTF-8. Returns true if successful, false otherwise. +=item _utf8_on(STRING) -package Encode::Escape; -use Carp; +[INTERNAL] Turn on the UTF-8 flag in STRING. The data in STRING is +B checked for being well-formed UTF-8. Do not use unless you +B that the STRING is well-formed UTF-8. Returns the previous +state of the UTF-8 flag (so please don't test the return value as +I success or failure), or C if STRING is not a string. -sub read -{ - my ($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; -} +=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. -sub name { shift->{'Name'} } +=back -sub toUnicode -{ - croak("Not implemented yet"); -} +=head1 SEE ALSO -sub fromUnicode -{ - croak("Not implemented yet"); -} +L, +L, +L, +L, +L, +L, +L, +L, +the Perl Unicode Mailing List Eperl-unicode@perl.orgE -1; +=head1 MAINTAINER -__END__ +This project was originated by Nick Ing-Simmons and later maintained +by Dan Kogai Edankogai@dan.co.jpE. See AUTHORS for full list +of people involved. For any questions, use +Eperl-unicode@perl.orgE so others can share. + +=cut