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;
+use base qw/Exporter/;
+
+# Public, encouraged API is exported by default
+
+our @EXPORT = qw(
+ decode decode_utf8 encode encode_utf8
+ encodings find_encoding
+);
+
+our @FB_FLAGS = qw(DIE_ON_ERR WARN_ON_ERR RETURN_ON_ERR LEAVE_SRC
+ PERLQQ HTMLCREF XMLCREF);
+our @FB_CONSTS = qw(FB_DEFAULT FB_CROAK FB_QUIET FB_WARN
+ FB_PERLQQ FB_HTMLCREF FB_XMLCREF);
+
+our @EXPORT_OK =
+ (
+ qw(
+ _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
-@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
- );
-
-bootstrap Encode ();
-
-=pod
+use Carp;
-=head1 NAME
+our $ON_EBCDIC = (ord("A") == 193);
-Encode - character encodings
+use Encode::Alias;
-=head2 TERMINOLOGY
+# Make a %Encoding package variable to allow a certain amount of cheating
+our %Encoding;
+our %ExtModule;
+require Encode::Config;
+eval { require Encode::ConfigLocal };
-=over
+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;
+}
-=item *
+sub perlio_ok{
+ my $obj = ref($_[0]) ? $_[0] : find_encoding($_[0]);
+ $obj->can("perlio_ok") and return $obj->perlio_ok();
+ return 0; # safety net
+}
-I<char>: a character in the range 0..maxint (at least 2**32-1)
+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 $obj;
+}
-=item *
+sub getEncoding
+{
+ my ($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};
+ }
-I<byte>: a character in the range 0..255
+ my $oc = $class->find_alias($name);
+ return $oc if defined $oc;
-=back
+ $oc = $class->find_alias($lc) if $lc ne $name;
+ return $oc if defined $oc;
-The marker [INTERNAL] marks Internal Implementation Details, in
-general meant only for those who think they know what they are doing,
-and such details may change in future releases.
+ unless ($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;
+}
-=head2 bytes
+sub find_encoding
+{
+ my ($name,$skip_external) = @_;
+ return __PACKAGE__->getEncoding($name,$skip_external);
+}
-=over 4
+sub resolve_alias {
+ my $obj = find_encoding(shift);
+ defined $obj and return $obj->name;
+ return;
+}
-=item *
+sub encode($$;$)
+{
+ my ($name,$string,$check) = @_;
+ $check ||=0;
+ my $enc = find_encoding($name);
+ croak("Unknown encoding '$name'") unless defined $enc;
+ my $octets = $enc->encode($string,$check);
+ return undef if ($check && length($string));
+ return $octets;
+}
- bytes_to_utf8(STRING [, FROM])
+sub decode($$;$)
+{
+ my ($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;
+}
-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<undef> if
-there's a failure.
+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 ;
+}
-[INTERNAL] Also the UTF-8 flag of STRING is turned on.
+sub encode_utf8($)
+{
+ my ($str) = @_;
+ utf8::encode($str);
+ return $str;
+}
+
+sub decode_utf8($)
+{
+ my ($str) = @_;
+ return undef unless utf8::decode($str);
+ return $str;
+}
+
+predefine_encodings();
+
+#
+# This is to restore %Encoding if really needed;
+#
+sub predefine_encodings{
+ if ($ON_EBCDIC) {
+ # was in Encode::UTF_EBCDIC
+ package Encode::UTF_EBCDIC;
+ *name = sub{ shift->{'Name'} };
+ *new_sequence = sub{ return $_[0] };
+ *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::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";
+ }
+}
+
+1;
+
+__END__
+
+=head1 NAME
+
+Encode - character encodings
+
+=head1 SYNOPSIS
+
+ 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<Encode> module provides the interfaces between Perl's strings
+and the rest of the system. Perl strings are sequences of
+B<characters>.
+
+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<ord(ch)>) 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<perlebcdic>).
+
+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 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".
+
+=head2 TERMINOLOGY
+
+=over 2
=item *
- utf8_to_bytes(STRING [, TO [, CHECK]])
+I<character>: a character in the range 0..(2**32-1) (or more).
+(What Perl's strings are made of.)
-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<undef> if
-there's a failure.
+=item *
-What if there are characters > 255? What if the UTF-8 in STRING is
-malformed? See L</"Handling Malformed Data">.
+I<byte>: a character in the range 0..255
+(A special case of a Perl character.)
+
+=item *
-[INTERNAL] The UTF-8 flag of STRING is not checked.
+I<octet>: 8 bits of data, with ordinal values 0..255
+(Term for bytes passed to or from a non-Perl context, e.g. a disk file.)
=back
-=head2 chars
+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.
-=over 4
+=head1 PERL ENCODING API
-=item *
+=over 2
- chars_to_utf8(STRING)
+=item $octets = encode(ENCODING, $string[, CHECK])
-The chars in STRING are encoded in-place into UTF-8. Returns the new
-size of STRING, or C<undef> if there's a failure.
+Encodes a string from Perl's internal form into I<ENCODING> and returns
+a sequence of octets. ENCODING can be either a canonical name or
+an alias. For encoding names and aliases, see L</"Defining Aliases">.
+For CHECK, see L</"Handling Malformed Data">.
-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<from_to('Unicode', ...)>.
+For example, to convert (internally UTF-8 encoded) Unicode string to
+iso-8859-1 (also known as Latin1),
-[INTERNAL] Also the UTF-8 flag of STRING is turned on.
+ $octets = encode("iso-8859-1", $utf8);
-=over 4
+B<CAVEAT>: When you C<$octets = encode("utf8", $utf8)>, then $octets
+B<ne> $utf8. Though they both contain the same data, the utf8 flag
+for $octets is B<always> off. When you encode anything, utf8 flag of
+the result is always off, even when it contains completely valid utf8
+string. See L</"The UTF-8 flag"> below.
-=item *
+=item $string = decode(ENCODING, $octets[, CHECK])
- utf8_to_chars(STRING)
+Decodes a sequence of octets assumed to be in I<ENCODING> 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</"Defining Aliases">. For CHECK, see
+L</"Handling Malformed Data">.
-The UTF-8 in STRING is decoded in-place into chars. Returns the new
-size of STRING, or C<undef> if there's a failure.
+For example, to convert ISO-8859-1 data to UTF-8:
-If the UTF-8 in STRING is malformed C<undef> is returned, and also an
-optional lexical warning (category utf8) is given.
+ $utf8 = decode("iso-8859-1", $latin1);
-[INTERNAL] The UTF-8 flag of STRING is not checked.
+B<CAVEAT>: When you C<$utf8 = encode("utf8", $octets)>, then $utf8
+B<may not be equal to> $utf8. Though they both contain the same data,
+the utf8 flag for $utf8 is on unless $octets entirely conststs of
+ASCII data (or EBCDIC on EBCDIC machines). See L</"The UTF-8 flag">
+below.
-=item *
+=item [$length =] from_to($string, FROM_ENC, TO_ENC [, CHECK])
- utf8_to_chars_check(STRING [, CHECK])
+Converts B<in-place> data between two encodings. For example, to
+convert ISO-8859-1 data to UTF-8:
-(Note that special naming of this interface since a two-argument
-utf8_to_chars() has different semantics.)
+ from_to($data, "iso-8859-1", "utf8");
-The UTF-8 in STRING is decoded in-place into chars. Returns the new
-size of STRING, or C<undef> if there is a failure.
+and to convert it back:
-If the UTF-8 in STRING is malformed? See L</"Handling Malformed Data">.
+ from_to($data, "utf8", "iso-8859-1");
-[INTERNAL] The UTF-8 flag of STRING is not checked.
+Note that because the conversion happens in place, the data to be
+converted cannot be a string constant; it must be a scalar variable.
-=back
+from_to() returns the length of the converted string on success, undef
+otherwise.
-=head2 chars With Encoding
+B<CAVEAT>: The following operations look the same but not quite so;
-=over 4
+ from_to($data, "iso-8859-1", "utf8"); #1
+ $data = decode("iso-8859-1", $data); #2
-=item *
+Both #1 and #2 makes $data consists of completely valid UTF-8 string
+but only #2 turns utf8 flag on. #1 is equivalent to
- chars_to_utf8(STRING, FROM [, CHECK])
+ $data = encode("utf8", decode("iso-8859-1", $data));
-The chars in STRING encoded in FROM are recoded in-place into UTF-8.
-Returns the new size of STRING, or C<undef> if there's a failure.
+See L</"The UTF-8 flag"> below.
-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<from_to('Unicode', ...)>.
+=item $octets = encode_utf8($string);
-[INTERNAL] Also the UTF-8 flag of STRING is turned on.
+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 *
- utf8_to_chars(STRING, TO [, CHECK])
+=item $string = decode_utf8($octets [, CHECK]);
-The UTF-8 in STRING is decoded in-place into chars encoded in TO.
-Returns the new size of STRING, or C<undef> if there's a failure.
+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</"Handling Malformed Data">.
-If the UTF-8 in STRING is malformed? See L</"Handling Malformed Data">.
+=back
-[INTERNAL] The UTF-8 flag of STRING is not checked.
+=head2 Listing available encodings
-=item *
+ use Encode;
+ @list = Encode->encodings();
- bytes_to_chars(STRING, FROM [, CHECK])
+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
-The bytes in STRING encoded in FROM are recoded in-place into chars.
-Returns the new size of STRING in bytes, or C<undef> if there's a
-failure.
+ @all_encodings = Encode->encodings(":all");
-If the mapping is impossible? See L</"Handling Malformed Data">.
+Or you can give the name of a specific module.
-=item *
+ @with_jp = Encode->encodings("Encode::JP");
- chars_to_bytes(STRING, TO [, CHECK])
+When "::" is not in the name, "Encode::" is assumed.
-The chars in STRING are recoded in-place to bytes encoded in TO.
-Returns the new size of STRING in bytes, or C<undef> if there's a
-failure.
+ @ebcdic = Encode->encodings("EBCDIC");
-If the mapping is impossible? See L</"Handling Malformed Data">.
+To find out in detail which encodings are supported by this package,
+see L<Encode::Supported>.
-=item *
+=head2 Defining Aliases
- from_to(STRING, FROM, TO [, CHECK])
+To add a new alias to a given encoding, use:
-The chars in STRING encoded in FROM are recoded in-place into TO.
-Returns the new size of STRING, or C<undef> if there's a failure.
+ use Encode;
+ use Encode::Alias;
+ define_alias(newName => ENCODING);
-If mapping between the encodings is impossible?
-See L</"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<encoding object>
-[INTERNAL] If TO is UTF-8, also the UTF-8 flag of STRING is turned on.
+But before you do so, make sure the alias is nonexistent with
+C<resolve_alias()>, which returns the canonical name thereof.
+i.e.
-=back
+ Encode::resolve_alias("latin1") eq "iso-8859-1" # true
+ Encode::resolve_alias("iso-8859-12") # false; nonexistent
+ Encode::resolve_alias($name) eq $name # true if $name is canonical
-=head2 Testing For UTF-8
+resolve_alias() does not need C<use Encode::Alias>; it can be
+exported via C<use Encode qw(resolve_alias)>.
-=over 4
+See L<Encode::Alias> for details.
-=item *
+=head1 Encoding via PerlIO
- is_utf8(STRING [, CHECK])
+If your perl supports I<PerlIO>, you can use a PerlIO layer to decode
+and encode directly via a filehandle. The following two examples
+are totally identical in their functionality.
-[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.
+ # via PerlIO
+ open my $in, "<:encoding(shiftjis)", $infile or die;
+ open my $out, ">:encoding(euc-jp)", $outfile or die;
+ while(<>){ print; }
-=back
+ # via from_to
+ open my $in, "<", $infile or die;
+ open my $out, ">", $outfile or die;
+ while(<>){
+ from_to($_, "shiftjis", "euc-jp", 1);
+ }
-=head2 Toggling UTF-8-ness
+Unfortunately, there may be encodings are PerlIO-savvy. You can check
+if your encoding is supported by PerlIO by calling the C<perlio_ok>
+method.
-=over 4
+ Encode::perlio_ok("hz"); # False
+ find_encoding("euc-cn")->perlio_ok; # True where PerlIO is available
-=item *
+ use Encode qw(perlio_ok); # exported upon request
+ perlio_ok("euc-jp")
- on_utf8(STRING)
+Fortunately, all encodings that come with Encode core are PerlIO-savvy
+except for hz and ISO-2022-kr. See L<Encode::Encoding> for details.
-[INTERNAL] Turn on the UTF-8 flag in STRING. The data in STRING is
-B<not> checked for being well-formed UTF-8. Do not use unless you
-B<know> 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<not> success or failure), or C<undef> if STRING is not a string.
+For gory details, see L<Encode::PerlIO>.
-=item *
+=head1 Handling Malformed Data
- off_utf8(STRING)
+=over 2
-[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<not> success or failure), or C<undef> if STRING is
-not a string.
+The I<CHECK> 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<CHECK>.
-=back
+=item I<CHECK> = Encode::FB_DEFAULT ( == 0)
-=head2 UTF-16 and UTF-32 Encodings
+If I<CHECK> is 0, (en|de)code will put a I<substitution character>
+in place of a malformed character. For UCM-based encodings,
+E<lt>subcharE<gt> 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.
-=over 4
+=item I<CHECK> = Encode::FB_CROAK ( == 1)
-=item *
+If I<CHECK> is 1, methods will die immediately with an error
+message. Therefore, when I<CHECK> is set to 1, you should trap the
+fatal error with eval{} unless you really want to let it die on error.
- utf_to_utf(STRING, FROM, TO [, CHECK])
+=item I<CHECK> = Encode::FB_QUIET
-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):
+If I<CHECK> 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:
- tag meaning
+ 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
+ }
- '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
+=item I<CHECK> = Encode::FB_WARN
-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<undef> is there's a failure.
+This is the same as above, except that it warns on error. Handy when
+you are debugging the mode above.
-If FROM is UTF-8 and the UTF-8 in STRING is malformed? See
-L</"Handling Malformed Data">.
+=item perlqq mode (I<CHECK> = Encode::FB_PERLQQ)
-[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.
+=item HTML charref mode (I<CHECK> = Encode::FB_HTMLCREF)
-=back
+=item XML charref mode (I<CHECK> = Encode::FB_XMLCREF)
-=head2 Handling Malformed Data
+For encodings that are implemented by Encode::XS, CHECK ==
+Encode::FB_PERLQQ turns (en|de)code into C<perlqq> fallback mode.
-If CHECK is not set, C<undef> 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
+When you decode, '\xI<XX>' will be inserted for a malformed character,
+where I<XX> is the hex representation of the octet that could not be
+decoded to utf8. And when you encode, '\x{I<xxxx>}' will be inserted,
+where I<xxxx> is the Unicode ID of the character that cannot be found
+in the character repertoire of the encoding.
- (MALFORMED_STRING, STRING_FROM_SO_FAR, STRING_TO_SO_FAR)
+HTML/XML character reference modes are about the same, in place of
+\x{I<xxxx>}, HTML uses &#I<1234>; where I<1234> is a decimal digit and
+XML uses &#xI<abcd>; where I<abcd> is the hexadecimal digit.
-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.
+=item The bitmask
-=cut
+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<use Encode qw(:fallbacks)>; you can import the generic bitmask
+constants via C<use Encode qw(:fallback_all)>.
-sub bytes_to_utf8 {
- &_bytes_to_utf8;
-}
+ 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
-sub utf8_to_bytes {
- &_utf8_to_bytes;
-}
+=head2 Unimplemented fallback schemes
-sub chars_to_utf8 {
- &C_to_utf8;
-}
+In the future, you will be able to use a code reference to a callback
+function for the value of I<CHECK> but its API is still undecided.
-sub utf8_to_chars {
- &_utf8_to_chars;
-}
+=head1 Defining Encodings
-sub utf8_to_chars_check {
- &_utf8_to_chars_check;
-}
+To define a new encoding, use:
-sub bytes_to_chars {
- &_bytes_to_chars;
-}
+ use Encode qw(define_alias);
+ define_encoding($object, 'canonicalName' [, alias...]);
-sub chars_to_bytes {
- &_chars_to_bytes;
-}
+I<canonicalName> will be associated with I<$object>. The object
+should provide the interface described in L<Encode::Encoding>.
+If more than two arguments are provided then additional
+arguments are taken as aliases for I<$object>, as for C<define_alias>.
-sub is_utf8 {
- &_is_utf8;
-}
+See L<Encode::Encoding> for more details.
-sub on_utf8 {
- &_on_utf8;
-}
+=head1 The UTF-8 flag
-sub off_utf8 {
- &_off_utf8;
-}
+Before the introduction of utf8 support in perl, The C<eq> operator
+just compares internal data of the scalars. Now C<eq> means internal
+data equality AND I<the utf8 flag>. To explain why we made it so, I
+will quote page 402 of C<Programming Perl, 3rd ed.>
-sub utf_to_utf {
- &_utf_to_utf;
-}
+=over 2
-use Carp;
+=item Goal #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] = $string);
-}
+Old byte-oriented programs should not spontaneously break on the old
+byte-oriented data they used to work on.
-my %encoding = ( Unicode => bless({},'Encode::Unicode'),
- 'iso10646-1' => bless({},'Encode::iso10646_1'),
- );
+=item Goal #2:
-sub encodings
-{
- my ($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;
-}
+Old byte-oriented programs should magically start working on the new
+character-oriented data when appropriate.
-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'));
- return $class->read($fh,$name,$type);
- }
- else
- {
- return undef;
- }
-}
+=item Goal #3:
-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;
-}
+Programs should run just as fast in the new character-oriented mode
+as in the old byte-oriented mode.
-package Encode::Unicode;
+=item Goal #4:
-# Dummy package that provides the encode interface
+Perl should remain one language, rather than forking into a
+byte-oriented Perl and a character-oriented Perl.
-sub name { 'Unicode' }
+=back
-sub toUnicode { $_[1] }
+Back when C<Programming Perl, 3rd ed.> 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).
-sub fromUnicode { $_[1] }
+Here is how Encode takes care of the utf8 flag.
-package Encode::Table;
+=over2
-sub read
-{
- my ($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;
- }
+=item *
- return bless {Name => $name,
- Rep => $rep,
- ToUni => \@touni,
- FmUni => \%fmuni,
- Def => $def,
- Num => $count,
- },$class;
-}
+When you encode, the resulting utf8 flag is always off.
-sub name { shift->{'Name'} }
+=item
-sub rep_S { 'C' }
+When you decode, the resuting utf8 flag is on unless you can
+unambiguously represent data. Here is the definition of
+dis-ambiguity.
-sub rep_D { 'n' }
+ After C<$utf8 = decode('foo', $octet);>,
-sub rep_M { ($_[0] > 255) ? 'n' : 'C' }
+ When $octet is... The utf8 flag in $utf8 is
+ ---------------------------------------------
+ In ASCII only (or EBCDIC only) OFF
+ In ISO-8859-1 ON
+ In any other Encoding ON
+ ---------------------------------------------
-sub representation
-{
- my ($obj,$ch) = @_;
- $ch = 0 unless @_ > 1;
- $obj-{'Rep'}->($ch);
-}
+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<CAVEAT> paragraphs.
-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 $uni;
-}
+This utf8 flag is not visible in perl scripts, exactly for the same
+reason you cannot (or you I<don't have to>) see if a scalar contains a
+string, integer, or floating point number. But you can still peek
+and poke these if you will. See the section below.
-sub fromUnicode
-{
- my ($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 $str;
-}
+=back
-package Encode::iso10646_1;#
+=head2 Messing with Perl's Internals
-sub name { 'iso10646-1' }
+The following API uses parts of Perl's internals in the current
+implementation. As such, they are efficient but may change.
-sub toUnicode
-{
- my ($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 $uni;
-}
+=over 2
-sub fromUnicode
-{
- my ($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 $str;
-}
+=item is_utf8(STRING [, CHECK])
-package Encode::Escape;
-use Carp;
+[INTERNAL] Tests whether the UTF-8 flag is turned on in the STRING.
+If CHECK is true, also checks the data in STRING for being well-formed
+UTF-8. Returns true if successful, false otherwise.
-sub read
-{
- my ($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_on(STRING)
-sub name { shift->{'Name'} }
+[INTERNAL] Turns on the UTF-8 flag in STRING. The data in STRING is
+B<not> checked for being well-formed UTF-8. Do not use unless you
+B<know> 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<undef> if STRING is not a string.
-sub toUnicode
-{
- croak("Not implemented yet");
-}
+=item _utf8_off(STRING)
-sub fromUnicode
-{
- croak("Not implemented yet");
-}
+[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<undef> if STRING is
+not a string.
-1;
+=back
-__END__
+=head1 SEE ALSO
+
+L<Encode::Encoding>,
+L<Encode::Supported>,
+L<Encode::PerlIO>,
+L<encoding>,
+L<perlebcdic>,
+L<perlfunc/open>,
+L<perlunicode>,
+L<utf8>,
+the Perl Unicode Mailing List E<lt>perl-unicode@perl.orgE<gt>
+
+=head1 MAINTAINER
+
+This project was originated by Nick Ing-Simmons and later maintained
+by Dan Kogai E<lt>dankogai@dan.co.jpE<gt>. See AUTHORS for a full
+list of people involved. For any questions, use
+E<lt>perl-unicode@perl.orgE<gt> so we can all share share.
+
+=cut
projects / p5sagit/p5-mst-13.2.git / blobdiff