3 our $VERSION = do { my @r = (q$Revision: 1.31 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
9 our @ISA = qw(Exporter DynaLoader);
11 # Public, encouraged API is exported by default
36 # Documentation moved after __END__ for speed - NI-S
40 our $ON_EBCDIC = (ord("A") == 193);
44 # Make a %Encoding package variable to allow a certain amount of cheating
51 my @modules = (@_ and $_[0] eq ":all") ? values %ExtModule : @_;
52 for my $mod (@modules){
53 $mod =~ s,::,/,g or $mod = "Encode/$mod";
55 $DEBUG and warn "about to require $mod;";
56 eval { require $mod; };
58 my %modules = map {$_ => 1} @modules;
60 sort { lc $a cmp lc $b }
61 grep {!/^(?:Internal|Unicode)$/o} keys %Encoding;
68 $Encoding{$name} = $obj;
70 define_alias($lc => $obj) unless $lc eq $name;
74 define_alias($alias,$obj);
81 my ($class,$name,$skip_external) = @_;
83 if (ref($name) && $name->can('new_sequence'))
88 if (exists $Encoding{$name})
90 return $Encoding{$name};
92 if (exists $Encoding{$lc})
94 return $Encoding{$lc};
97 my $oc = $class->find_alias($name);
98 return $oc if defined $oc;
100 $oc = $class->find_alias($lc) if $lc ne $name;
101 return $oc if defined $oc;
103 unless ($skip_external)
105 if (my $mod = $ExtModule{$name} || $ExtModule{$lc}){
106 $mod =~ s,::,/,g ; $mod .= '.pm';
107 eval{ require $mod; };
108 return $Encoding{$name} if exists $Encoding{$name};
116 my ($name,$skip_external) = @_;
117 return __PACKAGE__->getEncoding($name,$skip_external);
122 my ($name,$string,$check) = @_;
123 my $enc = find_encoding($name);
124 croak("Unknown encoding '$name'") unless defined $enc;
125 my $octets = $enc->encode($string,$check);
126 return undef if ($check && length($string));
132 my ($name,$octets,$check) = @_;
133 my $enc = find_encoding($name);
134 croak("Unknown encoding '$name'") unless defined $enc;
135 my $string = $enc->decode($octets,$check);
136 $_[1] = $octets if $check;
142 my ($string,$from,$to,$check) = @_;
143 my $f = find_encoding($from);
144 croak("Unknown encoding '$from'") unless defined $f;
145 my $t = find_encoding($to);
146 croak("Unknown encoding '$to'") unless defined $t;
147 my $uni = $f->decode($string,$check);
148 return undef if ($check && length($string));
149 $string = $t->encode($uni,$check);
150 return undef if ($check && length($uni));
151 return defined($_[0] = $string) ? length($string) : undef ;
164 return undef unless utf8::decode($str);
168 predefine_encodings();
171 # This is to restore %Encoding if really needed;
173 sub predefine_encodings{
175 # was in Encode::UTF_EBCDIC
176 package Encode::UTF_EBCDIC;
177 *name = sub{ shift->{'Name'} };
178 *new_sequence = sub{ return $_[0] };
180 my ($obj,$str,$chk) = @_;
182 for (my $i = 0; $i < length($str); $i++) {
184 chr(utf8::unicode_to_native(ord(substr($str,$i,1))));
190 my ($obj,$str,$chk) = @_;
192 for (my $i = 0; $i < length($str); $i++) {
194 chr(utf8::native_to_unicode(ord(substr($str,$i,1))));
199 $Encode::Encoding{Internal} =
200 bless {Name => "UTF_EBCDIC"} => "Encode::UTF_EBCDIC";
202 # was in Encode::UTF_EBCDIC
203 package Encode::Internal;
204 *name = sub{ shift->{'Name'} };
205 *new_sequence = sub{ return $_[0] };
207 my ($obj,$str,$chk) = @_;
213 $Encode::Encoding{Unicode} =
214 bless {Name => "Internal"} => "Encode::Internal";
218 # was in Encode::utf8
219 package Encode::utf8;
220 *name = sub{ shift->{'Name'} };
221 *new_sequence = sub{ return $_[0] };
223 my ($obj,$octets,$chk) = @_;
224 my $str = Encode::decode_utf8($octets);
232 my ($obj,$string,$chk) = @_;
233 my $octets = Encode::encode_utf8($string);
237 $Encode::Encoding{utf8} =
238 bless {Name => "utf8"} => "Encode::utf8";
240 # do externals if necessary
241 require File::Basename;
245 File::Spec->catfile(File::Basename::dirname($INC{'Encode.pm'}),
246 "Encode", "$ext.pm");
251 require Encode::Encoding;
260 Encode - character encodings
267 =head2 Table of Contents
269 Encode consists of a collection of modules which details are too big
270 to fit in one document. This POD itself explains the top-level APIs
271 and general topics at a glance. For other topics and more details,
275 --------------------------------------------------------
276 Encode::Alias Alias defintions to encodings
277 Encode::Encoding Encode Implementation Base Class
278 Encode::Supported List of Supported Encodings
279 Encode::CN Simplified Chinese Encodings
280 Encode::JP Japanese Encodings
281 Encode::KR Korean Encodings
282 Encode::TW Traditional Chinese Encodings
283 --------------------------------------------------------
287 The C<Encode> module provides the interfaces between Perl's strings
288 and the rest of the system. Perl strings are sequences of
291 The repertoire of characters that Perl can represent is at least that
292 defined by the Unicode Consortium. On most platforms the ordinal
293 values of the characters (as returned by C<ord(ch)>) is the "Unicode
294 codepoint" for the character (the exceptions are those platforms where
295 the legacy encoding is some variant of EBCDIC rather than a super-set
296 of ASCII - see L<perlebcdic>).
298 Traditionally computer data has been moved around in 8-bit chunks
299 often called "bytes". These chunks are also known as "octets" in
300 networking standards. Perl is widely used to manipulate data of many
301 types - not only strings of characters representing human or computer
302 languages but also "binary" data being the machines representation of
303 numbers, pixels in an image - or just about anything.
305 When Perl is processing "binary data" the programmer wants Perl to
306 process "sequences of bytes". This is not a problem for Perl - as a
307 byte has 256 possible values it easily fits in Perl's much larger
316 I<character>: a character in the range 0..(2**32-1) (or more).
317 (What Perl's strings are made of.)
321 I<byte>: a character in the range 0..255
322 (A special case of a Perl character.)
326 I<octet>: 8 bits of data, with ordinal values 0..255
327 (Term for bytes passed to or from a non-Perl context, e.g. disk file.)
331 The marker [INTERNAL] marks Internal Implementation Details, in
332 general meant only for those who think they know what they are doing,
333 and such details may change in future releases.
335 =head1 PERL ENCODING API
339 =item $octets = encode(ENCODING, $string[, CHECK])
341 Encodes string from Perl's internal form into I<ENCODING> and returns
342 a sequence of octets. ENCODING can be either a canonical name or
343 alias. For encoding names and aliases, see L</"Defining Aliases">.
344 For CHECK see L</"Handling Malformed Data">.
346 For example to convert (internally UTF-8 encoded) Unicode string to
347 iso-8859-1 (also known as Latin1),
349 $octets = encode("iso-8859-1", $unicode);
351 =item $string = decode(ENCODING, $octets[, CHECK])
353 Decode sequence of octets assumed to be in I<ENCODING> into Perl's
354 internal form and returns the resulting string. as in encode(),
355 ENCODING can be either a canonical name or alias. For encoding names
356 and aliases, see L</"Defining Aliases">. For CHECK see
357 L</"Handling Malformed Data">.
359 For example to convert ISO-8859-1 data to UTF-8:
361 $utf8 = decode("iso-8859-1", $latin1);
363 =item [$length =] from_to($string, FROM_ENCODING, TO_ENCODING [,CHECK])
365 Convert B<in-place> the data between two encodings. How did the data
366 in $string originally get to be in FROM_ENCODING? Either using
367 encode() or through PerlIO: See L</"Encoding and IO">.
368 For encoding names and aliases, see L</"Defining Aliases">.
369 For CHECK see L</"Handling Malformed Data">.
371 For example to convert ISO-8859-1 data to UTF-8:
373 from_to($data, "iso-8859-1", "utf-8");
375 and to convert it back:
377 from_to($data, "utf-8", "iso-8859-1");
379 Note that because the conversion happens in place, the data to be
380 converted cannot be a string constant, it must be a scalar variable.
382 from_to() return the length of the converted string on success, undef
389 The Unicode consortium defines the UTF-8 standard as a way of encoding
390 the entire Unicode repertoire as sequences of octets. This encoding is
391 expected to become very widespread. Perl can use this form internally
392 to represent strings, so conversions to and from this form are
393 particularly efficient (as octets in memory do not have to change,
394 just the meta-data that tells Perl how to treat them).
398 =item $octets = encode_utf8($string);
400 The characters that comprise string are encoded in Perl's superset of UTF-8
401 and the resulting octets returned as a sequence of bytes. All possible
402 characters have a UTF-8 representation so this function cannot fail.
404 =item $string = decode_utf8($octets [, CHECK]);
406 The sequence of octets represented by $octets is decoded from UTF-8
407 into a sequence of logical characters. Not all sequences of octets
408 form valid UTF-8 encodings, so it is possible for this call to fail.
409 For CHECK see L</"Handling Malformed Data">.
413 =head2 Listing available encodings
416 @list = Encode->encodings();
418 Returns a list of the canonical names of the available encodings that
419 are loaded. To get a list of all available encodings including the
420 ones that are not loaded yet, say
422 @all_encodings = Encode->encodings(":all");
424 Or you can give the name of specific module.
426 @with_jp = Encode->encodings("Encode::JP");
428 When "::" is not in the name, "Encode::" is assumed.
430 @ebcdic = Encode->encodings("EBCDIC");
432 To find which encodings are supported by this package in details,
433 see L<Encode::Supported>.
435 =head2 Defining Aliases
437 To add new alias to a given encoding, Use;
441 define_alias(newName => ENCODING);
443 After that, newName can be used as an alias for ENCODING.
444 ENCODING may be either the name of an encoding or an
447 See L<Encode::Alias> on details.
449 =head1 Encoding and IO
451 It is very common to want to do encoding transformations when
452 reading or writing files, network connections, pipes etc.
453 If Perl is configured to use the new 'perlio' IO system then
454 C<Encode> provides a "layer" (See L<perliol>) which can transform
455 data as it is read or written.
457 Here is how the blind poet would modernise the encoding:
460 open(my $iliad,'<:encoding(iso-8859-7)','iliad.greek');
461 open(my $utf8,'>:utf8','iliad.utf8');
467 In addition the new IO system can also be configured to read/write
468 UTF-8 encoded characters (as noted above this is efficient):
470 open(my $fh,'>:utf8','anything');
471 print $fh "Any \x{0021} string \N{SMILEY FACE}\n";
473 Either of the above forms of "layer" specifications can be made the default
474 for a lexical scope with the C<use open ...> pragma. See L<open>.
476 Once a handle is open is layers can be altered using C<binmode>.
478 Without any such configuration, or if Perl itself is built using
479 system's own IO, then write operations assume that file handle accepts
480 only I<bytes> and will C<die> if a character larger than 255 is
481 written to the handle. When reading, each octet from the handle
482 becomes a byte-in-a-character. Note that this default is the same
483 behaviour as bytes-only languages (including Perl before v5.6) would
484 have, and is sufficient to handle native 8-bit encodings
485 e.g. iso-8859-1, EBCDIC etc. and any legacy mechanisms for handling
486 other encodings and binary data.
488 In other cases it is the programs responsibility to transform
489 characters into bytes using the API above before doing writes, and to
490 transform the bytes read from a handle into characters before doing
491 "character operations" (e.g. C<lc>, C</\W+/>, ...).
493 You can also use PerlIO to convert larger amounts of data you don't
494 want to bring into memory. For example to convert between ISO-8859-1
495 (Latin 1) and UTF-8 (or UTF-EBCDIC in EBCDIC machines):
497 open(F, "<:encoding(iso-8859-1)", "data.txt") or die $!;
498 open(G, ">:utf8", "data.utf") or die $!;
499 while (<F>) { print G }
501 # Could also do "print G <F>" but that would pull
502 # the whole file into memory just to write it out again.
506 open(my $f, "<:encoding(cp1252)")
507 open(my $g, ">:encoding(iso-8859-2)")
508 open(my $h, ">:encoding(latin9)") # iso-8859-15
510 See L<PerlIO> for more information.
512 See also L<encoding> for how to change the default encoding of the
515 =head1 Handling Malformed Data
517 If I<CHECK> is not set, (en|de)code will put I<substitution character> in
518 place of the malformed character. for UCM-based encodings,
519 E<lt>subcharE<gt> will be used. For Unicode, \xFFFD is used. If the
520 data is supposed to be UTF-8, an optional lexical warning (category
523 If I<CHECK> is true but not a code reference, dies with an error message.
525 In future you will be able to use a code reference to a callback
526 function for the value of I<CHECK> but its API is still undecided.
528 =head1 Defining Encodings
530 To define a new encoding, use:
532 use Encode qw(define_alias);
533 define_encoding($object, 'canonicalName' [, alias...]);
535 I<canonicalName> will be associated with I<$object>. The object
536 should provide the interface described in L<Encode::Encoding>
537 If more than two arguments are provided then additional
538 arguments are taken as aliases for I<$object> as for C<define_alias>.
540 See L<Encode::Encoding> for more details.
542 =head1 Messing with Perl's Internals
544 The following API uses parts of Perl's internals in the current
545 implementation. As such they are efficient, but may change.
549 =item is_utf8(STRING [, CHECK])
551 [INTERNAL] Test whether the UTF-8 flag is turned on in the STRING.
552 If CHECK is true, also checks the data in STRING for being well-formed
553 UTF-8. Returns true if successful, false otherwise.
555 =item _utf8_on(STRING)
557 [INTERNAL] Turn on the UTF-8 flag in STRING. The data in STRING is
558 B<not> checked for being well-formed UTF-8. Do not use unless you
559 B<know> that the STRING is well-formed UTF-8. Returns the previous
560 state of the UTF-8 flag (so please don't test the return value as
561 I<not> success or failure), or C<undef> if STRING is not a string.
563 =item _utf8_off(STRING)
565 [INTERNAL] Turn off the UTF-8 flag in STRING. Do not use frivolously.
566 Returns the previous state of the UTF-8 flag (so please don't test the
567 return value as I<not> success or failure), or C<undef> if STRING is
575 L<Encode::Supported>,
582 the Perl Unicode Mailing List E<lt>perl-unicode@perl.orgE<gt>