package Encode;
-
-$VERSION = 0.01;
+use strict;
+our $VERSION = do { my @r = (q$Revision: 1.26 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
+our $DEBUG = 0;
require DynaLoader;
require Exporter;
-@ISA = qw(Exporter DynaLoader);
+our @ISA = qw(Exporter DynaLoader);
+
+# Public, encouraged API is exported by default
+our @EXPORT = qw (
+ encode
+ decode
+ encode_utf8
+ decode_utf8
+ find_encoding
+ encodings
+);
-@EXPORT_OK =
+our @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
+ define_encoding
from_to
is_utf8
- on_utf8
- off_utf8
- utf_to_utf
- encodings
+ is_8bit
+ is_16bit
+ utf8_upgrade
+ utf8_downgrade
+ _utf8_on
+ _utf8_off
);
bootstrap Encode ();
-=pod
-
-=head1 NAME
+# Documentation moved after __END__ for speed - NI-S
-Encode - character encodings
+use Carp;
-=head2 TERMINOLOGY
+our $ON_EBCDIC = (ord("A") == 193);
-=over
+use Encode::Alias;
-=item *
+# Make a %Encoding package variable to allow a certain amount of cheating
+our %Encoding;
+our %ExtModule;
-I<char>: a character in the range 0..maxint (at least 2**32-1)
+my @codepages = qw(
+ 37 424 437 500 737 775 850 852 855
+ 856 857 860 861 862 863 864 865 866
+ 869 874 875 932 936 949 950 1006 1026
+ 1047 1250 1251 1252 1253 1254 1255 1256 1257
+ 1258
+ );
-=item *
+my @macintosh = qw(
+ CentralEurRoman Croatian Cyrillic Greek
+ Iceland Roman Rumanian Sami
+ Thai Turkish Ukrainian
+ );
-I<byte>: a character in the range 0..255
+for my $k (2..11,13..16){
+ $ExtModule{"iso-8859-$k"} = 'Encode/Byte.pm';
+}
-=back
+for my $k (@codepages){
+ $ExtModule{"cp$k"} = 'Encode/Byte.pm';
+}
-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.
+for my $k (@macintosh)
+{
+ $ExtModule{"mac$k"} = 'Encode/Byte.pm';
+}
-=head2 bytes
+%ExtModule =
+ (%ExtModule,
+ 'koi8-r' => 'Encode/Byte.pm',
+ 'posix-bc' => 'Encode/EBCDIC.pm',
+ cp037 => 'Encode/EBCDIC.pm',
+ cp1026 => 'Encode/EBCDIC.pm',
+ cp1047 => 'Encode/EBCDIC.pm',
+ cp500 => 'Encode/EBCDIC.pm',
+ cp875 => 'Encode/EBCDIC.pm',
+ dingbats => 'Encode/Symbol.pm',
+ macDingbats => 'Encode/Symbol.pm',
+ macSymbol => 'Encode/Symbol.pm',
+ symbol => 'Encode/Symbol.pm',
+ viscii => 'Encode/Byte.pm',
+);
+
+unless ($ON_EBCDIC) { # CJK added to autoload unless EBCDIC env
+%ExtModule =
+ (%ExtModule,
+
+ 'cp936' => 'Encode/CN.pm',
+ 'euc-cn' => 'Encode/CN.pm',
+ 'gb12345-raw' => 'Encode/CN.pm',
+ 'gb2312-raw' => 'Encode/CN.pm',
+ 'gbk' => 'Encode/CN.pm',
+ 'iso-ir-165' => 'Encode/CN.pm',
+
+ '7bit-jis' => 'Encode/JP.pm',
+ 'cp932' => 'Encode/JP.pm',
+ 'euc-jp' => 'Encode/JP.pm',
+ 'iso-2022-jp' => 'Encode/JP.pm',
+ 'iso-2022-jp-1' => 'Encode/JP.pm',
+ 'jis0201-raw' => 'Encode/JP.pm',
+ 'jis0208-raw' => 'Encode/JP.pm',
+ 'jis0212-raw' => 'Encode/JP.pm',
+ 'macJapanese' => 'Encode/JP.pm',
+ 'shiftjis' => 'Encode/JP.pm',
+
+ 'cp949' => 'Encode/KR.pm',
+ 'euc-kr' => 'Encode/KR.pm',
+ 'ksc5601' => 'Encode/KR.pm',
+ 'macKorean' => 'Encode/KR.pm',
+
+ 'big5' => 'Encode/TW.pm',
+ 'big5-hkscs' => 'Encode/TW.pm',
+ 'cp950' => 'Encode/TW.pm',
+
+ 'big5plus' => 'Encode/HanExtra.pm',
+ 'euc-tw' => 'Encode/HanExtra.pm',
+ 'gb18030' => 'Encode/HanExtra.pm',
+ );
+}
-=over 4
+sub encodings
+{
+ my $class = shift;
+ my @modules = (@_ and $_[0] eq ":all") ? values %ExtModule : @_;
+ for my $m (@modules)
+ {
+ $DEBUG and warn "about to require $m;";
+ eval { require $m; };
+ }
+ return
+ map({$_->[0]}
+ sort({$a->[1] cmp $b->[1]}
+ map({[$_, lc $_]}
+ grep({ $_ ne 'Internal' } keys %Encoding))));
+}
-=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<undef> 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 $oc;
-=item *
+ if (!$skip_external and exists $ExtModule{$lc})
+ {
+ eval{ require $ExtModule{$lc}; };
+ return $Encoding{$name} if exists $Encoding{$name};
+ }
- utf8_to_bytes(STRING [, TO [, CHECK]])
+ return;
+}
-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.
+sub find_encoding
+{
+ my ($name,$skip_external) = @_;
+ return __PACKAGE__->getEncoding($name,$skip_external);
+}
-What if there are characters > 255? What if the UTF-8 in STRING is
-malformed? See L</"Handling Malformed Data">.
+sub encode
+{
+ my ($name,$string,$check) = @_;
+ 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) = @_;
+ 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) = @_;
+ 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";
+ }
+ # do externals if necessary
+ require File::Basename;
+ require File::Spec;
+ for my $ext (qw(Unicode)){
+ my $pm =
+ File::Spec->catfile(File::Basename::dirname($INC{'Encode.pm'}),
+ "Encode", "$ext.pm");
+ do $pm;
+ }
+}
-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.
+require Encode::Encoding;
+require Encode::XS;
-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', ...)>.
+1;
-[INTERNAL] Also the UTF-8 flag of STRING is turned on.
+__END__
-=over 4
+=head1 NAME
-=item *
+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<undef> if there's a failure.
+ use Encode;
-If the UTF-8 in STRING is malformed C<undef> 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<undef> if there is a failure.
+The C<Encode> module provides the interfaces between Perl's strings
+and the rest of the system. Perl strings are sequences of
+B<characters>.
-If the UTF-8 in STRING is malformed? See L</"Handling Malformed Data">.
+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>).
-[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<undef> 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<from_to('Unicode', ...)>.
-
-[INTERNAL] Also the UTF-8 flag of STRING is turned on.
+I<character>: 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])
+I<byte>: a character in the range 0..255
+(A special case of a Perl character.)
-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.
+=item *
-If the UTF-8 in STRING is malformed? See L</"Handling Malformed Data">.
+I<octet>: 8 bits of data, with ordinal values 0..255
+(Term for bytes passed to or from a non-Perl context, e.g. disk file.)
-[INTERNAL] The UTF-8 flag of STRING is not checked.
+=back
-=item *
+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.
- bytes_to_chars(STRING, FROM [, CHECK])
+=head1 PERL ENCODING API
-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.
+=over 4
-If the mapping is impossible? See L</"Handling Malformed Data">.
+=item $octets = encode(ENCODING, $string[, CHECK])
-=item *
+Encodes string from Perl's internal form into I<ENCODING> and returns
+a sequence of octets. ENCODING can be either a canonical name or
+alias. For encoding names and aliases, see L</"Defining Aliases">.
+For CHECK see L</"Handling Malformed Data">.
- chars_to_bytes(STRING, TO [, CHECK])
+For example to convert (internally UTF-8 encoded) Unicode string to
+iso-8859-1 (also known as Latin1),
-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.
+ $octets = encode("iso-8859-1", $unicode);
-If the mapping is impossible? See L</"Handling Malformed Data">.
+=item $string = decode(ENCODING, $octets[, CHECK])
-=item *
+Decode 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 alias. For encoding names
+and aliases, see L</"Defining Aliases">. For CHECK see
+L</"Handling Malformed Data">.
- from_to(STRING, FROM, TO [, CHECK])
+For example to convert ISO-8859-1 data to UTF-8:
-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.
+ $utf8 = decode("iso-8859-1", $latin1);
-If mapping between the encodings is impossible?
-See L</"Handling Malformed Data">.
+=item [$length =] from_to($string, FROM_ENCODING, TO_ENCODING [,CHECK])
-[INTERNAL] If TO is UTF-8, also the UTF-8 flag of STRING is turned on.
+Convert B<in-place> the data between two encodings. How did the data
+in $string originally get to be in FROM_ENCODING? Either using
+encode() or through PerlIO: See L</"Encoding and IO">.
+For encoding names and aliases, see L</"Defining Aliases">.
+For CHECK see L</"Handling Malformed Data">.
-=back
+For example to convert ISO-8859-1 data to UTF-8:
-=head2 Testing For UTF-8
+ from_to($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<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.
-
-=item *
-
- off_utf8(STRING)
+=item $string = decode_utf8($octets [, CHECK]);
-[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 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">.
=back
-=head2 UTF-16 and UTF-32 Encodings
+=head2 Listing available encodings
-=over 4
+ use Encode;
+ @list = Encode->encodings();
-=item *
+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
- utf_to_utf(STRING, FROM, TO [, CHECK])
+ @all_encodings = Encode->encodings(":all");
-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):
+Or you can give the name of specific module.
- tag meaning
+ @with_jp = Encode->encodings("Encode/JP.pm");
- '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
+Note in this case you have to say C<"Encode/JP.pm"> instead of
+C<"Encode::JP">.
-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.
+To find which encodings are supported by this package in details,
+see L<Encode::Supported>.
-If FROM is UTF-8 and the UTF-8 in STRING is malformed? See
-L</"Handling Malformed Data">.
+=head2 Defining Aliases
-[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.
+To add new alias to a given encoding, Use;
-=back
+ use Encode;
+ use Encode::Alias;
+ define_alias(newName => ENCODING);
-=head2 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>
-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
+See L<Encode::Alias> on details.
- (MALFORMED_STRING, STRING_FROM_SO_FAR, STRING_TO_SO_FAR)
+=head1 Encoding and IO
-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.
+It is very common to want to do encoding transformations when
+reading or writing files, network connections, pipes etc.
+If Perl is configured to use the new 'perlio' IO system then
+C<Encode> provides a "layer" (See L<perliol>) which can transform
+data as it is read or written.
-=cut
+Here is how the blind poet would modernise the encoding:
-sub bytes_to_utf8 {
- &_bytes_to_utf8;
-}
+ use Encode;
+ open(my $iliad,'<:encoding(iso-8859-7)','iliad.greek');
+ open(my $utf8,'>:utf8','iliad.utf8');
+ my @epic = <$iliad>;
+ print $utf8 @epic;
+ close($utf8);
+ close($illiad);
-sub utf8_to_bytes {
- &_utf8_to_bytes;
-}
+In addition the new IO system can also be configured to read/write
+UTF-8 encoded characters (as noted above this is efficient):
-sub chars_to_utf8 {
- &C_to_utf8;
-}
+ open(my $fh,'>:utf8','anything');
+ print $fh "Any \x{0021} string \N{SMILEY FACE}\n";
-sub utf8_to_chars {
- &_utf8_to_chars;
-}
+Either of the above forms of "layer" specifications can be made the default
+for a lexical scope with the C<use open ...> pragma. See L<open>.
-sub utf8_to_chars_check {
- &_utf8_to_chars_check;
-}
+Once a handle is open is layers can be altered using C<binmode>.
-sub bytes_to_chars {
- &_bytes_to_chars;
-}
+Without any such configuration, or if Perl itself is built using
+system's own IO, then write operations assume that file handle accepts
+only I<bytes> and will C<die> if a character larger than 255 is
+written to the handle. When reading, each octet from the handle
+becomes a byte-in-a-character. Note that this default is the same
+behaviour as bytes-only languages (including Perl before v5.6) would
+have, and is sufficient to handle native 8-bit encodings
+e.g. iso-8859-1, EBCDIC etc. and any legacy mechanisms for handling
+other encodings and binary data.
-sub chars_to_bytes {
- &_chars_to_bytes;
-}
+In other cases it is the programs responsibility to transform
+characters into bytes using the API above before doing writes, and to
+transform the bytes read from a handle into characters before doing
+"character operations" (e.g. C<lc>, C</\W+/>, ...).
-sub is_utf8 {
- &_is_utf8;
-}
+You can also use PerlIO to convert larger amounts of data you don't
+want to bring into memory. For example to convert between ISO-8859-1
+(Latin 1) and UTF-8 (or UTF-EBCDIC in EBCDIC machines):
-sub on_utf8 {
- &_on_utf8;
-}
+ open(F, "<:encoding(iso-8859-1)", "data.txt") or die $!;
+ open(G, ">:utf8", "data.utf") or die $!;
+ while (<F>) { print G }
-sub off_utf8 {
- &_off_utf8;
-}
+ # Could also do "print G <F>" but that would pull
+ # the whole file into memory just to write it out again.
-sub utf_to_utf {
- &_utf_to_utf;
-}
-
-use Carp;
-
-sub from_to
-{
- my ($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] = $string);
-}
-
-sub encodings
-{
- my ($class) = @_;
- my ($dir) = __FILE__ =~ /^(.*)\.pm$/;
- my @names = ('Unicode');
- if (opendir(my $dh,$dir))
- {
- while (defined(my $name = readdir($dh)))
- {
- push(@names,$1) if ($name =~ /^(.*)\.enc$/);
- }
- closedir($dh);
- }
- else
- {
- die "Cannot open $dir:$!";
- }
- return @names;
-}
-
-my %encoding = ( Unicode => bless({},'Encode::Unicode'),
- 'iso10646-1' => bless({},'Encode::iso10646_1'),
- );
-
-sub getEncoding
-{
- my ($class,$name) = @_;
- unless (exists $encoding{$name})
- {
- my $file;
- foreach my $dir (@INC)
- {
- last if -f ($file = "$dir/Encode/$name.enc");
- }
- 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'));
- $encoding{$name} = $class->read($fh,$name,$type);
- }
- else
- {
- $encoding{$name} = undef;
- }
- }
- return $encoding{$name};
-}
+More examples:
-package Encode::Unicode;
+ open(my $f, "<:encoding(cp1252)")
+ open(my $g, ">:encoding(iso-8859-2)")
+ open(my $h, ">:encoding(latin9)") # iso-8859-15
-# Dummy package that provides the encode interface
+See L<PerlIO> for more information.
-sub name { 'Unicode' }
+See also L<encoding> for how to change the default encoding of the
+data in your script.
-sub toUnicode { $_[1] }
+=head1 Handling Malformed Data
-sub fromUnicode { $_[1] }
+If I<CHECK> is not set, (en|de)code will put I<substitution character> in
+place of the malformed character. for UCM-based encodings,
+E<lt>subcharE<gt> will be used. For Unicode, \xFFFD is used. If the
+data is supposed to be UTF-8, an optional lexical warning (category
+utf8) is given.
-package Encode::Table;
+If I<CHECK> is true but not a code reference, dies with an error message.
-sub read
-{
- my ($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;
- }
-
- return bless {Name => $name,
- Rep => $rep,
- ToUni => \@touni,
- FmUni => \%fmuni,
- Def => $def,
- Num => $count,
- },$class;
-}
+In 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 name { shift->{'Name'} }
+=head1 Defining Encodings
-sub rep_S { 'C' }
+To define a new encoding, use:
-sub rep_D { 'S' }
+ use Encode qw(define_alias);
+ define_encoding($object, 'canonicalName' [, alias...]);
-sub rep_M { ($_[0] > 255) ? 'S' : 'C' }
+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 representation
-{
- my ($obj,$ch) = @_;
- $ch = 0 unless @_ > 1;
- $obj-{'Rep'}->($ch);
-}
+See L<Encode::Encoding> for more details.
-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 $uni;
-}
+=head1 Messing with Perl's Internals
-sub fromUnicode
-{
- my ($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 = $fmuni->{$ch};
- unless (defined $x)
- {
- last if ($chk);
- $x = $def;
- }
- $str .= pack(&$rep($x),$x);
- }
- $_[1] = $uni if $chk;
- return $str;
-}
+The following API uses parts of Perl's internals in the current
+implementation. As such they are efficient, but may change.
-package Encode::iso10646_1;#
+=over 4
-sub name { 'iso10646-1' }
+=item is_utf8(STRING [, CHECK])
-sub toUnicode
-{
- my ($obj,$str,$chk) = @_;
- my $uni = '';
- while (length($str))
- {
- my $code = unpack('S',substr($str,0,2,''));
- $uni .= chr($code);
- }
- $_[1] = $str if $chk;
- return $uni;
-}
+[INTERNAL] Test whether the UTF-8 flag is turned on in the STRING.
+If CHECK is true, also checks the data in STRING for being well-formed
+UTF-8. Returns true if successful, false otherwise.
-sub fromUnicode
-{
- my ($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;
- }
- $str .= pack('S',$x);
- }
- $_[1] = $uni if $chk;
- return $str;
-}
+=item _utf8_on(STRING)
-package Encode::Escape;
-use Carp;
+[INTERNAL] Turn on the UTF-8 flag in STRING. The data in STRING is
+B<not> checked for being well-formed UTF-8. Do not use unless you
+B<know> that the STRING is well-formed UTF-8. Returns the previous
+state of the UTF-8 flag (so please don't test the return value as
+I<not> success or failure), or C<undef> if STRING is not a string.
-sub read
-{
- my ($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)
-sub name { shift->{'Name'} }
+[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.
-sub toUnicode
-{
- croak("Not implemented yet");
-}
+=back
-sub fromUnicode
-{
- croak("Not implemented yet");
-}
+=head1 SEE ALSO
-1;
+L<Encode::Encoding>,
+L<Encode::Supported>,
+L<PerlIO>,
+L<encoding>,
+L<perlebcdic>,
+L<perlfunc/open>,
+L<perlunicode>,
+L<utf8>,
+the Perl Unicode Mailing List E<lt>perl-unicode@perl.orgE<gt>
-__END__
+=cut