9 our @ISA = qw(Exporter DynaLoader);
11 # Public, encouraged API is exported by default
37 # Documentation moved after __END__ for speed - NI-S
41 # Make a %encoding package variable to allow a certain amount of cheating
43 my @alias; # ordered matching list
44 my %alias; # cached known aliases
45 # 0 1 2 3 4 5 6 7 8 9 10
46 our @latin2iso_num = ( 0, 1, 2, 3, 4, 9, 10, 13, 14, 15, 16 );
52 return keys %encoding;
59 unless (exists $alias{$_})
61 for (my $i=0; $i < @alias; $i += 2)
63 my $alias = $alias[$i];
64 my $val = $alias[$i+1];
66 if (ref($alias) eq 'Regexp' && $_ =~ $alias)
70 elsif (ref($alias) eq 'CODE')
72 $new = &{$alias}($val)
74 elsif (lc($_) eq lc($alias))
80 next if $new eq $_; # avoid (direct) recursion on bugs
81 my $enc = (ref($new)) ? $new : find_encoding($new);
97 my ($alias,$name) = splice(@_,0,2);
98 push(@alias, $alias => $name);
102 # Allow variants of iso-8859-1 etc.
103 define_alias( qr/^iso[-_]?(\d+)[-_](\d+)$/i => '"iso-$1-$2"' );
105 # At least HP-UX has these.
106 define_alias( qr/^iso8859(\d+)$/i => '"iso-8859-$1"' );
108 # This is a font issue, not an encoding issue.
109 # (The currency symbol of the Latin 1 upper half
110 # has been redefined as the euro symbol.)
111 define_alias( qr/^(.+)\@euro$/i => '"$1"' );
113 # Allow latin-1 style names as well
114 define_alias( qr/^(?:iso[-_]?)?latin[-_]?(\d+)$/i => '"iso-8859-$latin2iso_num[$1]"' );
116 # Common names for non-latin prefered MIME names
117 define_alias( 'ascii' => 'US-ascii',
118 'cyrillic' => 'iso-8859-5',
119 'arabic' => 'iso-8859-6',
120 'greek' => 'iso-8859-7',
121 'hebrew' => 'iso-8859-8');
123 # At least AIX has IBM-NNN (surprisingly...) instead of cpNNN.
124 define_alias( qr/^ibm[-_]?(\d\d\d\d?)$/i => '"cp$1"');
126 # Standardize on the dashed versions.
127 define_alias( qr/^utf8$/i => 'utf-8' );
128 define_alias( qr/^koi8r$/i => 'koi8-r' );
130 # TODO: the HP-UX '8' encodings: arabic8 greek8 hebrew8 roman8 turkish8
131 # TODO: the Thai Encoding tis620
132 # TODO: the Chinese Encoding gb18030
133 # TODO: what is the Japanese 'ujis' encoding seen in some Linuxes?
135 # Map white space and _ to '-'
136 define_alias( qr/^(\S+)[\s_]+(.*)$/i => '"$1-$2"' );
142 $encoding{$name} = $obj;
144 define_alias($lc => $obj) unless $lc eq $name;
148 define_alias($alias,$obj);
155 my ($class,$name) = @_;
157 if (ref($name) && $name->can('new_sequence'))
161 if (exists $encoding{$name})
163 return $encoding{$name};
167 return $class->findAlias($name);
174 return __PACKAGE__->getEncoding($name);
179 my ($name,$string,$check) = @_;
180 my $enc = find_encoding($name);
181 croak("Unknown encoding '$name'") unless defined $enc;
182 my $octets = $enc->encode($string,$check);
183 return undef if ($check && length($string));
189 my ($name,$octets,$check) = @_;
190 my $enc = find_encoding($name);
191 croak("Unknown encoding '$name'") unless defined $enc;
192 my $string = $enc->decode($octets,$check);
193 return undef if ($check && length($octets));
199 my ($string,$from,$to,$check) = @_;
200 my $f = find_encoding($from);
201 croak("Unknown encoding '$from'") unless defined $f;
202 my $t = find_encoding($to);
203 croak("Unknown encoding '$to'") unless defined $t;
204 my $uni = $f->decode($string,$check);
205 return undef if ($check && length($string));
206 $string = $t->encode($uni,$check);
207 return undef if ($check && length($uni));
208 return length($_[0] = $string);
221 return undef unless utf8::decode($str);
225 package Encode::Encoding;
226 # Base class for classes which implement encodings
231 my $canonical = shift;
232 $obj = bless { Name => $canonical },$obj unless ref $obj;
233 # warn "$canonical => $obj\n";
234 Encode::define_encoding($obj, $canonical, @_);
237 sub name { shift->{'Name'} }
239 # Temporary legacy methods
240 sub toUnicode { shift->decode(@_) }
241 sub fromUnicode { shift->encode(@_) }
243 sub new_sequence { return $_[0] }
246 use base 'Encode::Encoding';
248 package Encode::Internal;
249 use base 'Encode::Encoding';
251 # Dummy package that provides the encode interface but leaves data
252 # as UTF-X encoded. It is here so that from_to() works.
254 __PACKAGE__->Define('Internal');
256 Encode::define_alias( 'Unicode' => 'Internal' ) if ord('A') == 65;
260 my ($obj,$str,$chk) = @_;
268 package Encoding::Unicode;
269 use base 'Encode::Encoding';
271 __PACKAGE__->Define('Unicode') unless ord('A') == 65;
275 my ($obj,$str,$chk) = @_;
277 for (my $i = 0; $i < length($str); $i++)
279 $res .= chr(utf8::unicode_to_native(ord(substr($str,$i,1))));
287 my ($obj,$str,$chk) = @_;
289 for (my $i = 0; $i < length($str); $i++)
291 $res .= chr(utf8::native_to_unicode(ord(substr($str,$i,1))));
298 package Encode::utf8;
299 use base 'Encode::Encoding';
300 # package to allow long-hand
301 # $octets = encode( utf8 => $string );
304 __PACKAGE__->Define(qw(UTF-8 utf8));
308 my ($obj,$octets,$chk) = @_;
309 my $str = Encode::decode_utf8($octets);
320 my ($obj,$string,$chk) = @_;
321 my $octets = Encode::encode_utf8($string);
326 package Encode::iso10646_1;
327 use base 'Encode::Encoding';
328 # Encoding is 16-bit network order Unicode (no surogates)
329 # Used for X font encodings
331 __PACKAGE__->Define(qw(UCS-2 iso-10646-1));
335 my ($obj,$str,$chk) = @_;
339 my $code = unpack('n',substr($str,0,2,'')) & 0xffff;
342 $_[1] = $str if $chk;
349 my ($obj,$uni,$chk) = @_;
353 my $ch = substr($uni,0,1,'');
360 $str .= pack('n',$x);
362 $_[1] = $uni if $chk;
366 package Encode::ucs_2le;
367 use base 'Encode::Encoding';
369 __PACKAGE__->Define(qw(UCS-2le UCS-2LE ucs-2le));
373 my ($obj,$str,$chk) = @_;
377 my $code = unpack('v',substr($str,0,2,'')) & 0xffff;
380 $_[1] = $str if $chk;
387 my ($obj,$uni,$chk) = @_;
391 my $ch = substr($uni,0,1,'');
398 $str .= pack('v',$x);
400 $_[1] = $uni if $chk;
404 # switch back to Encode package in case we ever add AutoLoader
413 Encode - character encodings
421 The C<Encode> module provides the interfaces between Perl's strings
422 and the rest of the system. Perl strings are sequences of B<characters>.
424 The repertoire of characters that Perl can represent is at least that
425 defined by the Unicode Consortium. On most platforms the ordinal
426 values of the characters (as returned by C<ord(ch)>) is the "Unicode
427 codepoint" for the character (the exceptions are those platforms where
428 the legacy encoding is some variant of EBCDIC rather than a super-set
429 of ASCII - see L<perlebcdic>).
431 Traditionaly computer data has been moved around in 8-bit chunks
432 often called "bytes". These chunks are also known as "octets" in
433 networking standards. Perl is widely used to manipulate data of
434 many types - not only strings of characters representing human or
435 computer languages but also "binary" data being the machines representation
436 of numbers, pixels in an image - or just about anything.
438 When Perl is processing "binary data" the programmer wants Perl to process
439 "sequences of bytes". This is not a problem for Perl - as a byte has 256
440 possible values it easily fits in Perl's much larger "logical character".
448 I<character>: a character in the range 0..(2**32-1) (or more).
449 (What Perl's strings are made of.)
453 I<byte>: a character in the range 0..255
454 (A special case of a Perl character.)
458 I<octet>: 8 bits of data, with ordinal values 0..255
459 (Term for bytes passed to or from a non-Perl context, e.g. disk file.)
463 The marker [INTERNAL] marks Internal Implementation Details, in
464 general meant only for those who think they know what they are doing,
465 and such details may change in future releases.
469 =head2 Characteristics of an Encoding
471 An encoding has a "repertoire" of characters that it can represent,
472 and for each representable character there is at least one sequence of
473 octets that represents it.
475 =head2 Types of Encodings
477 Encodings can be divided into the following types:
481 =item * Fixed length 8-bit (or less) encodings.
483 Each character is a single octet so may have a repertoire of up to
484 256 characters. ASCII and iso-8859-* are typical examples.
486 =item * Fixed length 16-bit encodings
488 Each character is two octets so may have a repertoire of up to
489 65 536 characters. Unicode's UCS-2 is an example. Also used for
490 encodings for East Asian languages.
492 =item * Fixed length 32-bit encodings.
494 Not really very "encoded" encodings. The Unicode code points
495 are just represented as 4-octet integers. None the less because
496 different architectures use different representations of integers
497 (so called "endian") there at least two disctinct encodings.
499 =item * Multi-byte encodings
501 The number of octets needed to represent a character varies.
502 UTF-8 is a particularly complex but regular case of a multi-byte
503 encoding. Several East Asian countries use a multi-byte encoding
504 where 1-octet is used to cover western roman characters and Asian
505 characters get 2-octets.
506 (UTF-16 is strictly a multi-byte encoding taking either 2 or 4 octets
507 to represent a Unicode code point.)
509 =item * "Escape" encodings.
511 These encodings embed "escape sequences" into the octet sequence
512 which describe how the following octets are to be interpreted.
513 The iso-2022-* family is typical. Following the escape sequence
514 octets are encoded by an "embedded" encoding (which will be one
515 of the above types) until another escape sequence switches to
516 a different "embedded" encoding.
518 These schemes are very flexible and can handle mixed languages but are
519 very complex to process (and have state). No escape encodings are
520 implemented for Perl yet.
524 =head2 Specifying Encodings
526 Encodings can be specified to the API described below in two ways:
532 Encoding names are strings with characters taken from a restricted
533 repertoire. See L</"Encoding Names">.
535 =item 2. As an object
537 Encoding objects are returned by C<find_encoding($name)>.
541 =head2 Encoding Names
543 Encoding names are case insensitive. White space in names is ignored.
544 In addition an encoding may have aliases. Each encoding has one
545 "canonical" name. The "canonical" name is chosen from the names of
546 the encoding by picking the first in the following sequence:
550 =item * The MIME name as defined in IETF RFC-XXXX.
552 =item * The name in the IANA registry.
554 =item * The name used by the the organization that defined it.
558 Because of all the alias issues, and because in the general case
559 encodings have state C<Encode> uses the encoding object internally
560 once an operation is in progress.
562 =head1 PERL ENCODING API
564 =head2 Generic Encoding Interface
570 $bytes = encode(ENCODING, $string[, CHECK])
572 Encodes string from Perl's internal form into I<ENCODING> and returns
573 a sequence of octets. For CHECK see L</"Handling Malformed Data">.
577 $string = decode(ENCODING, $bytes[, CHECK])
579 Decode sequence of octets assumed to be in I<ENCODING> into Perl's
580 internal form and returns the resulting string. For CHECK see
581 L</"Handling Malformed Data">.
585 from_to($string, FROM_ENCODING, TO_ENCODING[, CHECK])
587 Convert B<in-place> the data between two encodings. How did the data
588 in $string originally get to be in FROM_ENCODING? Either using
589 encode() or through PerlIO: See L</"Encoding and IO">. For CHECK
590 see L</"Handling Malformed Data">.
592 For example to convert ISO 8859-1 data to UTF-8:
594 from_to($data, "iso-8859-1", "utf-8");
596 and to convert it back:
598 from_to($data, "utf-8", "iso-8859-1");
600 Note that because the conversion happens in place, the data to be
601 converted cannot be a string constant, it must be a scalar variable.
605 =head2 Handling Malformed Data
607 If CHECK is not set, C<undef> is returned. If the data is supposed to
608 be UTF-8, an optional lexical warning (category utf8) is given. If
609 CHECK is true but not a code reference, dies.
611 It would desirable to have a way to indicate that transform should use
612 the encodings "replacement character" - no such mechanism is defined yet.
614 It is also planned to allow I<CHECK> to be a code reference.
616 This is not yet implemented as there are design issues with what its
617 arguments should be and how it returns its results.
623 Passed remaining fragment of string being processed.
624 Modifies it in place to remove bytes/characters it can understand
625 and returns a string used to represent them.
629 my $ch = substr($_[0],0,1,'');
630 return sprintf("\x{%02X}",ord($ch);
633 This scheme is close to how underlying C code for Encode works, but gives
634 the fixup routine very little context.
638 Passed original string, and an index into it of the problem area, and
639 output string so far. Appends what it will to output string and
640 returns new index into original string. For example:
643 # my ($s,$i,$d) = @_;
644 my $ch = substr($_[0],$_[1],1);
645 $_[2] .= sprintf("\x{%02X}",ord($ch);
649 This scheme gives maximal control to the fixup routine but is more
650 complicated to code, and may need internals of Encode to be tweaked to
651 keep original string intact.
657 Multiple return values rather than in-place modifications.
659 Index into the string could be pos($str) allowing s/\G...//.
665 The Unicode consortium defines the UTF-8 standard as a way of encoding
666 the entire Unicode repertiore as sequences of octets. This encoding is
667 expected to become very widespread. Perl can use this form internaly
668 to represent strings, so conversions to and from this form are
669 particularly efficient (as octets in memory do not have to change,
670 just the meta-data that tells Perl how to treat them).
676 $bytes = encode_utf8($string);
678 The characters that comprise string are encoded in Perl's superset of UTF-8
679 and the resulting octets returned as a sequence of bytes. All possible
680 characters have a UTF-8 representation so this function cannot fail.
684 $string = decode_utf8($bytes [,CHECK]);
686 The sequence of octets represented by $bytes is decoded from UTF-8
687 into a sequence of logical characters. Not all sequences of octets
688 form valid UTF-8 encodings, so it is possible for this call to fail.
689 For CHECK see L</"Handling Malformed Data">.
693 =head2 Other Encodings of Unicode
695 UTF-16 is similar to UCS-2, 16 bit or 2-byte chunks. UCS-2 can only
696 represent 0..0xFFFF, while UTF-16 has a "surrogate pair" scheme which
697 allows it to cover the whole Unicode range.
699 Encode implements big-endian UCS-2 aliased to "iso-10646-1" as that
700 happens to be the name used by that representation when used with X11
703 UTF-32 or UCS-4 is 32-bit or 4-byte chunks. Perl's logical characters
704 can be considered as being in this form without encoding. An encoding
705 to transfer strings in this form (e.g. to write them to a file) would
708 pack('L*', unpack('U*', $string)); # native
710 pack('V*', unpack('U*', $string)); # little-endian
712 pack('N*', unpack('U*', $string)); # big-endian
714 depending on the endianness required.
716 No UTF-32 encodings are implemented yet.
718 Both UCS-2 and UCS-4 style encodings can have "byte order marks" by
719 representing the code point 0xFFFE as the very first thing in a file.
721 =head2 Listing available encodings
723 use Encode qw(encodings);
726 Returns a list of the canonical names of the available encodings.
728 =head2 Defining Aliases
730 use Encode qw(define_alias);
731 define_alias( newName => ENCODING);
733 Allows newName to be used as am alias for ENCODING. ENCODING may be
734 either the name of an encoding or and encoding object (as above).
736 Currently I<newName> can be specified in the following ways:
740 =item As a simple string.
742 =item As a qr// compiled regular expression, e.g.:
744 define_alias( qr/^iso8859-(\d+)$/i => '"iso-8859-$1"' );
746 In this case if I<ENCODING> is not a reference it is C<eval>-ed to
747 allow C<$1> etc. to be subsituted. The example is one way to names as
748 used in X11 font names to alias the MIME names for the iso-8859-*
751 =item As a code reference, e.g.:
753 define_alias( sub { return /^iso8859-(\d+)$/i ? "iso-8859-$1" : undef } , '');
755 In this case C<$_> will be set to the name that is being looked up and
756 I<ENCODING> is passed to the sub as its first argument. The example
757 is another way to names as used in X11 font names to alias the MIME
758 names for the iso-8859-* family.
762 =head2 Defining Encodings
764 use Encode qw(define_alias);
765 define_encoding( $object, 'canonicalName' [,alias...]);
767 Causes I<canonicalName> to be associated with I<$object>. The object
768 should provide the interface described in L</"IMPLEMENTATION CLASSES">
769 below. If more than two arguments are provided then additional
770 arguments are taken as aliases for I<$object> as for C<define_alias>.
772 =head1 Encoding and IO
774 It is very common to want to do encoding transformations when
775 reading or writing files, network connections, pipes etc.
776 If Perl is configured to use the new 'perlio' IO system then
777 C<Encode> provides a "layer" (See L<perliol>) which can transform
778 data as it is read or written.
780 Here is how the blind poet would modernise the encoding:
783 open(my $iliad,'<:encoding(iso-8859-7)','iliad.greek');
784 open(my $utf8,'>:utf8','iliad.utf8');
790 In addition the new IO system can also be configured to read/write
791 UTF-8 encoded characters (as noted above this is efficient):
793 open(my $fh,'>:utf8','anything');
794 print $fh "Any \x{0021} string \N{SMILEY FACE}\n";
796 Either of the above forms of "layer" specifications can be made the default
797 for a lexical scope with the C<use open ...> pragma. See L<open>.
799 Once a handle is open is layers can be altered using C<binmode>.
801 Without any such configuration, or if Perl itself is built using
802 system's own IO, then write operations assume that file handle accepts
803 only I<bytes> and will C<die> if a character larger than 255 is
804 written to the handle. When reading, each octet from the handle
805 becomes a byte-in-a-character. Note that this default is the same
806 behaviour as bytes-only languages (including Perl before v5.6) would
807 have, and is sufficient to handle native 8-bit encodings
808 e.g. iso-8859-1, EBCDIC etc. and any legacy mechanisms for handling
809 other encodings and binary data.
811 In other cases it is the programs responsibility to transform
812 characters into bytes using the API above before doing writes, and to
813 transform the bytes read from a handle into characters before doing
814 "character operations" (e.g. C<lc>, C</\W+/>, ...).
816 You can also use PerlIO to convert larger amounts of data you don't
817 want to bring into memory. For example to convert between ISO 8859-1
818 (Latin 1) and UTF-8 (or UTF-EBCDIC in EBCDIC machines):
820 open(F, "<:encoding(iso-8859-1)", "data.txt") or die $!;
821 open(G, ">:utf8", "data.utf") or die $!;
822 while (<F>) { print G }
824 # Could also do "print G <F>" but that would pull
825 # the whole file into memory just to write it out again.
829 open(my $f, "<:encoding(cp1252)")
830 open(my $g, ">:encoding(iso-8859-2)")
831 open(my $h, ">:encoding(latin9)") # iso-8859-15
833 See L<PerlIO> for more information.
835 =head1 Encoding How to ...
841 =item * IO with mixed content (faking iso-2020-*)
843 =item * MIME's Content-Length:
845 =item * UTF-8 strings in binary data.
847 =item * Perl/Encode wrappers on non-Unicode XS modules.
851 =head1 Messing with Perl's Internals
853 The following API uses parts of Perl's internals in the current
854 implementation. As such they are efficient, but may change.
858 =item * is_utf8(STRING [, CHECK])
860 [INTERNAL] Test whether the UTF-8 flag is turned on in the STRING.
861 If CHECK is true, also checks the data in STRING for being well-formed
862 UTF-8. Returns true if successful, false otherwise.
864 =item * valid_utf8(STRING)
866 [INTERNAL] Test whether STRING is in a consistent state. Will return
867 true if string is held as bytes, or is well-formed UTF-8 and has the
868 UTF-8 flag on. Main reason for this routine is to allow Perl's
869 testsuite to check that operations have left strings in a consistent
876 [INTERNAL] Turn on the UTF-8 flag in STRING. The data in STRING is
877 B<not> checked for being well-formed UTF-8. Do not use unless you
878 B<know> that the STRING is well-formed UTF-8. Returns the previous
879 state of the UTF-8 flag (so please don't test the return value as
880 I<not> success or failure), or C<undef> if STRING is not a string.
886 [INTERNAL] Turn off the UTF-8 flag in STRING. Do not use frivolously.
887 Returns the previous state of the UTF-8 flag (so please don't test the
888 return value as I<not> success or failure), or C<undef> if STRING is
893 =head1 IMPLEMENTATION CLASSES
895 As mentioned above encodings are (in the current implementation at least)
896 defined by objects. The mapping of encoding name to object is via the
899 The values of the hash can currently be either strings or objects.
900 The string form may go away in the future. The string form occurs
901 when C<encodings()> has scanned C<@INC> for loadable encodings but has
902 not actually loaded the encoding in question. This is because the
903 current "loading" process is all Perl and a bit slow.
905 Once an encoding is loaded then value of the hash is object which
906 implements the encoding. The object should provide the following
913 Should return the string representing the canonical name of the encoding.
915 =item -E<gt>new_sequence
917 This is a placeholder for encodings with state. It should return an
918 object which implements this interface, all current implementations
919 return the original object.
921 =item -E<gt>encode($string,$check)
923 Should return the octet sequence representing I<$string>. If I<$check>
924 is true it should modify I<$string> in place to remove the converted
925 part (i.e. the whole string unless there is an error). If an error
926 occurs it should return the octet sequence for the fragment of string
927 that has been converted, and modify $string in-place to remove the
928 converted part leaving it starting with the problem fragment.
930 If check is is false then C<encode> should make a "best effort" to
931 convert the string - for example by using a replacement character.
933 =item -E<gt>decode($octets,$check)
935 Should return the string that I<$octets> represents. If I<$check> is
936 true it should modify I<$octets> in place to remove the converted part
937 (i.e. the whole sequence unless there is an error). If an error
938 occurs it should return the fragment of string that has been
939 converted, and modify $octets in-place to remove the converted part
940 leaving it starting with the problem fragment.
942 If check is is false then C<decode> should make a "best effort" to
943 convert the string - for example by using Unicode's "\x{FFFD}" as a
944 replacement character.
948 It should be noted that the check behaviour is different from the
949 outer public API. The logic is that the "unchecked" case is useful
950 when encoding is part of a stream which may be reporting errors
951 (e.g. STDERR). In such cases it is desirable to get everything
952 through somehow without causing additional errors which obscure the
953 original one. Also the encoding is best placed to know what the
954 correct replacement character is, so if that is the desired behaviour
955 then letting low level code do it is the most efficient.
957 In contrast if check is true, the scheme above allows the encoding to
958 do as much as it can and tell layer above how much that was. What is
959 lacking at present is a mechanism to report what went wrong. The most
960 likely interface will be an additional method call to the object, or
961 perhaps (to avoid forcing per-stream objects on otherwise stateless
962 encodings) and additional parameter.
964 It is also highly desirable that encoding classes inherit from
965 C<Encode::Encoding> as a base class. This allows that class to define
966 additional behaviour for all encoding objects. For example built in
967 Unicode, UCS-2 and UTF-8 classes use :
969 package Encode::MyEncoding;
970 use base qw(Encode::Encoding);
972 __PACKAGE__->Define(qw(myCanonical myAlias));
974 To create an object with bless {Name => ...},$class, and call
975 define_encoding. They inherit their C<name> method from
978 =head2 Compiled Encodings
980 F<Encode.xs> provides a class C<Encode::XS> which provides the
981 interface described above. It calls a generic octet-sequence to
982 octet-sequence "engine" that is driven by tables (defined in
983 F<encengine.c>). The same engine is used for both encode and
984 decode. C<Encode:XS>'s C<encode> forces Perl's characters to their
985 UTF-8 form and then treats them as just another multibyte
986 encoding. C<Encode:XS>'s C<decode> transforms the sequence and then
987 turns the UTF-8-ness flag as that is the form that the tables are
988 defined to produce. For details of the engine see the comments in
991 The tables are produced by the Perl script F<compile> (the name needs
992 to change so we can eventually install it somewhere). F<compile> can
993 currently read two formats:
999 This is a coined format used by Tcl. It is documented in
1000 Encode/EncodeFormat.pod.
1004 This is the semi-standard format used by IBM's ICU package.
1008 F<compile> can write the following forms:
1014 See above - the F<Encode/*.ucm> files provided with the distribution have
1015 been created from the original Tcl .enc files using this approach.
1019 Produces tables as C data structures - this is used to build in encodings
1020 into F<Encode.so>/F<Encode.dll>.
1024 In theory this allows encodings to be stand-alone loadable Perl
1025 extensions. The process has not yet been tested. The plan is to use
1026 this approach for large East Asian encodings.
1030 The set of encodings built-in to F<Encode.so>/F<Encode.dll> is
1031 determined by F<Makefile.PL>. The current set is as follows:
1035 =item ascii and iso-8859-*
1037 That is all the common 8-bit "western" encodings.
1039 =item IBM-1047 and two other variants of EBCDIC.
1041 These are the same variants that are supported by EBCDIC Perl as
1042 "native" encodings. They are included to prove "reversibility" of
1043 some constructs in EBCDIC Perl.
1045 =item symbol and dingbats as used by Tk on X11.
1047 (The reason Encode got started was to support Perl/Tk.)
1051 That set is rather ad hoc and has been driven by the needs of the
1052 tests rather than the needs of typical applications. It is likely
1057 L<perlunicode>, L<perlebcdic>, L<perlfunc/open>, L<PerlIO>