package Encode;
-
-$VERSION = 0.01;
+use strict;
+our $VERSION = do { my @r = (q$Revision: 0.99 $ =~ /\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
+ is_8bit
+ is_16bit
+ utf8_upgrade
+ utf8_downgrade
+ _utf8_on
+ _utf8_off
);
bootstrap Encode ();
-=pod
+# Documentation moved after __END__ for speed - NI-S
-=head1 NAME
+use Carp;
-Encode - character encodings
+our $ON_EBCDIC = (ord("A") == 193);
+use Encode::Alias;
-=head2 TERMINOLOGY
+# Make a %Encoding package variable to allow a certain amount of cheating
+our %Encoding;
-=over
+our %ExtModule =
+ (
+ viscii => 'Encode/Byte.pm',
+ 'koi8-r' => 'Encode/Byte.pm',
+ cp1047 => 'Encode/EBCDIC.pm',
+ cp37 => 'Encode/EBCDIC.pm',
+ 'posix-bc' => 'Encode/EBCDIC.pm',
+ symbol => 'Encode/Symbol.pm',
+ dingbats => 'Encode/Symbol.pm',
+ );
-=item *
+for my $k (2..11,13..16){
+ $ExtModule{"iso-8859-$k"} = 'Encode/Byte.pm';
+}
-I<char>: a character in the range 0..maxint (at least 2**32-1)
+for my $k (1250..1258){
+ $ExtModule{"cp$k"} = 'Encode/Byte.pm';
+}
-=item *
+unless ($ON_EBCDIC) { # CJK added to autoload unless EBCDIC env
+%ExtModule =(
+ %ExtModule,
+ 'euc-cn' => 'Encode/CN.pm',
+ gb2312 => 'Encode/CN.pm',
+ gb12345 => 'Encode/CN.pm',
+ gbk => 'Encode/CN.pm',
+ cp936 => 'Encode/CN.pm',
+ 'iso-ir-165' => 'Encode/CN.pm',
+ 'euc-jp' => 'Encode/JP.pm',
+ 'iso-2022-jp' => 'Encode/JP.pm',
+ 'iso-2022-jp-1' => 'Encode/JP.pm',
+ '7bit-jis' => 'Encode/JP.pm',
+ shiftjis => 'Encode/JP.pm',
+ macjapan => 'Encode/JP.pm',
+ cp932 => 'Encode/JP.pm',
+ 'euc-kr' => 'Encode/KR.pm',
+ ksc5601 => 'Encode/KR.pm',
+ cp949 => 'Encode/KR.pm',
+ big5 => 'Encode/TW.pm',
+ 'big5-hkscs' => 'Encode/TW.pm',
+ cp950 => 'Encode/TW.pm',
+ gb18030 => 'Encode/HanExtra.pm',
+ big5plus => 'Encode/HanExtra.pm',
+ 'euc-tw' => 'Encode/HanExtra.pm',
+ );
+}
-I<byte>: a character in the range 0..255
+for my $k (qw(centeuro croatian cyrillic dingbats greek
+ iceland roman rumanian sami
+ thai turkish ukraine))
+{
+ $ExtModule{"mac$k"} = 'Encode/Byte.pm';
+}
-=back
-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.
+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))));
+}
-=head2 bytes
+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 $obj;
+}
-=over 4
+sub getEncoding
+{
+ my ($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};
+ }
+
+ my $oc = $class->find_alias($name);
+ return $oc if defined $oc;
+
+ $oc = $class->find_alias($lc) if $lc ne $name;
+ return $oc if defined $oc;
+
+ if (!$skip_external and exists $ExtModule{$lc})
+ {
+ eval{ require $ExtModule{$lc}; };
+ return $Encoding{$name} if exists $Encoding{$name};
+ }
+
+ return;
+}
-=item *
+sub find_encoding
+{
+ my ($name,$skip_external) = @_;
+ return __PACKAGE__->getEncoding($name,$skip_external);
+}
- bytes_to_utf8(STRING [, FROM])
+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 $octets;
+}
-The bytes in STRING are recoded in-place into UTF-8. If no FROM is
-specified the bytes are expected to be encoded in US-ASCII or ISO
-8859-1 (Latin 1). Returns the new size of STRING, or C<undef> if
-there's a failure.
+sub decode
+{
+ my ($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 $string;
+}
-[INTERNAL] Also the UTF-8 flag of STRING is turned on.
+sub from_to
+{
+ my ($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($uni));
+ return length($_[0] = $string);
+}
-=item *
+sub encode_utf8
+{
+ my ($str) = @_;
+ utf8::encode($str);
+ return $str;
+}
- utf8_to_bytes(STRING [, TO [, CHECK]])
+sub decode_utf8
+{
+ my ($str) = @_;
+ return undef unless utf8::decode($str);
+ return $str;
+}
-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.
+require Encode::Encoding;
+require Encode::XS;
+require Encode::Internal;
+require Encode::Unicode;
+require Encode::utf8;
+require Encode::10646_1;
+require Encode::ucs2_le;
-What if there are characters > 255? What if the UTF-8 in STRING is
-malformed? See L</"Handling Malformed Data">.
+1;
-[INTERNAL] The UTF-8 flag of STRING is not checked.
+__END__
-=back
+=head1 NAME
-=head2 chars
+Encode - character encodings
-=over 4
+=head1 SYNOPSIS
+
+ use Encode;
-=item *
+=head1 DESCRIPTION
- chars_to_utf8(STRING)
+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 chars in STRING are encoded in-place into UTF-8. Returns the new
-size of STRING, or C<undef> if there's a failure.
+To find more about character encodings, please consult
+L<Encode::Details>. This document focuses on programming references.
-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', ...)>.
+=head1 PERL ENCODING API
-[INTERNAL] Also the UTF-8 flag of STRING is turned on.
+=head2 Generic Encoding Interface
=over 4
-=item *
+=item $bytes = encode(ENCODING, $string[, CHECK])
- utf8_to_chars(STRING)
+Encodes string from Perl's internal form into I<ENCODING> and returns
+a sequence of octets. 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 (internally UTF-8 encoded) Unicode data
+to octets:
-If the UTF-8 in STRING is malformed C<undef> is returned, and also an
-optional lexical warning (category utf8) is given.
+ $octets = encode("utf8", $unicode);
+
+=item $string = decode(ENCODING, $bytes[, CHECK])
+
+Decode sequence of octets assumed to be in I<ENCODING> into Perl's
+internal form and returns the resulting string. For CHECK see
+L</"Handling Malformed Data">.
-[INTERNAL] The UTF-8 flag of STRING is not checked.
+For example to convert ISO-8859-1 data to UTF-8:
-=item *
+ $utf8 = decode("latin1", $latin1);
- utf8_to_chars_check(STRING [, CHECK])
+=item from_to($string, FROM_ENCODING, TO_ENCODING[, CHECK])
-(Note that special naming of this interface since a two-argument
-utf8_to_chars() has different semantics.)
+Convert B<in-place> the data between two encodings. How did the data
+in $string originally get to be in FROM_ENCODING? Either using
+encode() or through PerlIO: See L</"Encoding and IO">. For CHECK
+see L</"Handling Malformed Data">.
-The UTF-8 in STRING is decoded in-place into chars. Returns the new
-size of STRING, or C<undef> if there is a failure.
+For example to convert ISO-8859-1 data to UTF-8:
-If the UTF-8 in STRING is malformed? See L</"Handling Malformed Data">.
+ from_to($data, "iso-8859-1", "utf-8");
-[INTERNAL] The UTF-8 flag of STRING is not checked.
+and to convert it back:
+
+ from_to($data, "utf-8", "iso-8859-1");
+
+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
-=head2 chars With Encoding
+=head2 Handling Malformed Data
-=over 4
+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.
-=item *
+It would desirable to have a way to indicate that transform should use
+the encodings "replacement character" - no such mechanism is defined yet.
- chars_to_utf8(STRING, FROM [, CHECK])
+It is also planned to allow I<CHECK> to be a code reference.
-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.
+This is not yet implemented as there are design issues with what its
+arguments should be and how it returns its results.
-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', ...)>.
+=over 4
-[INTERNAL] Also the UTF-8 flag of STRING is turned on.
+=item Scheme 1
-=item *
+Passed remaining fragment of string being processed.
+Modifies it in place to remove bytes/characters it can understand
+and returns a string used to represent them.
+e.g.
- utf8_to_chars(STRING, TO [, CHECK])
+ sub fixup {
+ my $ch = substr($_[0],0,1,'');
+ return sprintf("\x{%02X}",ord($ch);
+ }
-The UTF-8 in STRING is decoded in-place into chars encoded in TO.
-Returns the new size of STRING, or C<undef> if there's a failure.
+This scheme is close to how underlying C code for Encode works, but gives
+the fixup routine very little context.
-If the UTF-8 in STRING is malformed? See L</"Handling Malformed Data">.
+=item Scheme 2
-[INTERNAL] The UTF-8 flag of STRING is not checked.
+Passed original string, and an index into it of the problem area, and
+output string so far. Appends what it will to output string and
+returns new index into original string. For example:
-=item *
+ sub fixup {
+ # my ($s,$i,$d) = @_;
+ my $ch = substr($_[0],$_[1],1);
+ $_[2] .= sprintf("\x{%02X}",ord($ch);
+ return $_[1]+1;
+ }
- bytes_to_chars(STRING, FROM [, CHECK])
+This scheme gives maximal control to the fixup routine but is more
+complicated to code, and may need internals of Encode to be tweaked to
+keep original string intact.
-The bytes in STRING encoded in FROM are recoded in-place into chars.
-Returns the new size of STRING in bytes, or C<undef> if there's a
-failure.
+=item Other Schemes
-If the mapping is impossible? See L</"Handling Malformed Data">.
+Hybrids of above.
-=item *
+Multiple return values rather than in-place modifications.
- chars_to_bytes(STRING, TO [, CHECK])
+Index into the string could be C<pos($str)> allowing C<s/\G...//>.
-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.
+=back
-If the mapping is impossible? See L</"Handling Malformed Data">.
+=head2 UTF-8 / utf8
-=item *
+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
- from_to(STRING, FROM, TO [, CHECK])
+=item $bytes = encode_utf8($string);
-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.
+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.
-If mapping between the encodings is impossible?
-See L</"Handling Malformed Data">.
+=item $string = decode_utf8($bytes [, CHECK]);
-[INTERNAL] If TO is UTF-8, also the UTF-8 flag of STRING is turned on.
+The sequence of octets represented by $bytes 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 Testing For UTF-8
+=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
- is_utf8(STRING [, CHECK])
+ @all_encodings = Encode->encodings(":all");
-[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.
+Or you can give the name of specific module.
-=back
+ @with_jp = Encode->encodings("Encode/JP.pm");
-=head2 Toggling UTF-8-ness
+Note in this case you have to say C<"Encode/JP.pm"> instead of
+C<"Encode::JP">.
-=over 4
+To find which encodings are supported by this package in details,
+see L<Encode::Supported>.
-=item *
+=head2 Defining Aliases
- on_utf8(STRING)
+ use Encode;
+ use Encode::Alias;
+ define_alias(newName => ENCODING);
-[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.
+Allows newName to be used as am alias for ENCODING. ENCODING may be
+either the name of an encoding or and encoding object (as above).
-=item *
+See L<Encode::Alias> on details.
- off_utf8(STRING)
+=head1 Defining Encodings
-[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.
+ use Encode qw(define_alias);
+ define_encoding($object, 'canonicalName' [, alias...]);
-=back
+Causes I<canonicalName> to be associated with I<$object>. The object
+should provide the interface described in L<Encode::Encoding>
+below. If more than two arguments are provided then additional
+arguments are taken as aliases for I<$object> as for C<define_alias>.
-=head2 UTF-16 and UTF-32 Encodings
+=head1 Encoding and IO
-=over 4
+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.
-=item *
+Here is how the blind poet would modernise the encoding:
- utf_to_utf(STRING, FROM, TO [, CHECK])
+ 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);
-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):
+In addition the new IO system can also be configured to read/write
+UTF-8 encoded characters (as noted above this is efficient):
- tag meaning
+ open(my $fh,'>:utf8','anything');
+ print $fh "Any \x{0021} string \N{SMILEY FACE}\n";
- '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
+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>.
-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.
+Once a handle is open is layers can be altered using C<binmode>.
-If FROM is UTF-8 and the UTF-8 in STRING is malformed? See
-L</"Handling Malformed Data">.
+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.
-[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.
+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+/>, ...).
-=back
+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):
-=head2 Handling Malformed Data
+ open(F, "<:encoding(iso-8859-1)", "data.txt") or die $!;
+ open(G, ">:utf8", "data.utf") or die $!;
+ while (<F>) { print G }
-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
+ # Could also do "print G <F>" but that would pull
+ # the whole file into memory just to write it out again.
- (MALFORMED_STRING, STRING_FROM_SO_FAR, STRING_TO_SO_FAR)
+More examples:
-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.
+ open(my $f, "<:encoding(cp1252)")
+ open(my $g, ">:encoding(iso-8859-2)")
+ open(my $h, ">:encoding(latin9)") # iso-8859-15
-=cut
+See L<PerlIO> for more information.
-sub bytes_to_utf8 {
- &_bytes_to_utf8;
-}
+See also L<encoding> for how to change the default encoding of the
+data in your script.
-sub utf8_to_bytes {
- &_utf8_to_bytes;
-}
+=head1 Messing with Perl's Internals
-sub chars_to_utf8 {
- &C_to_utf8;
-}
+The following API uses parts of Perl's internals in the current
+implementation. As such they are efficient, but may change.
-sub utf8_to_chars {
- &_utf8_to_chars;
-}
+=over 4
-sub utf8_to_chars_check {
- &_utf8_to_chars_check;
-}
+=item is_utf8(STRING [, CHECK])
-sub bytes_to_chars {
- &_bytes_to_chars;
-}
+[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 chars_to_bytes {
- &_chars_to_bytes;
-}
+=item _utf8_on(STRING)
-sub from_to {
- &_from_to;
-}
+[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 is_utf8 {
- &_is_utf8;
-}
+=item _utf8_off(STRING)
-sub on_utf8 {
- &_on_utf8;
-}
+[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 off_utf8 {
- &_off_utf8;
-}
+=back
-sub utf_to_utf {
- &_utf_to_utf;
-}
+=head1 SEE ALSO
+L<Encode::Details>,
+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>
+
+=cut
projects / p5sagit/p5-mst-13.2.git / blobdiff