package Encode;
use strict;
-our $VERSION = 0.02;
+our $VERSION = '0.02';
require DynaLoader;
require Exporter;
my @alias; # ordered matching list
my %alias; # cached known aliases
+ # 0 1 2 3 4 5 6 7 8 9 10
+our @latin2iso_num = ( 0, 1, 2, 3, 4, 9, 10, 13, 14, 15, 16 );
+
+our %winlatin2cp = (
+ 'Latin1' => 1252,
+ 'Latin2' => 1250,
+ 'Cyrillic' => 1251,
+ 'Greek' => 1253,
+ 'Turkish' => 1254,
+ 'Hebrew' => 1255,
+ 'Arabic' => 1256,
+ 'Baltic' => 1257,
+ 'Vietnamese' => 1258,
+ );
+
sub encodings
{
my ($class) = @_;
{
my $class = shift;
local $_ = shift;
+ # print "# findAlias $_\n";
unless (exists $alias{$_})
{
for (my $i=0; $i < @alias; $i += 2)
{
$new = &{$alias}($val)
}
- elsif (lc($_) eq $alias)
+ elsif (lc($_) eq lc($alias))
{
$new = $val;
}
# Allow variants of iso-8859-1 etc.
define_alias( qr/^iso[-_]?(\d+)[-_](\d+)$/i => '"iso-$1-$2"' );
+# At least HP-UX has these.
+define_alias( qr/^iso8859(\d+)$/i => '"iso-8859-$1"' );
+
+# More HP stuff.
+define_alias( qr/^(?:hp-)?(arabic|greek|hebrew|kana|roman|thai|turkish)8$/i => '"${1}8"' );
+
+# The Official name of ASCII.
+define_alias( qr/^ANSI[-_]?X3\.4[-_]?1968$/i => '"ascii"' );
+
+# This is a font issue, not an encoding issue.
+# (The currency symbol of the Latin 1 upper half
+# has been redefined as the euro symbol.)
+define_alias( qr/^(.+)\@euro$/i => '"$1"' );
+
# Allow latin-1 style names as well
- # 0 1 2 3 4 5 6 7 8 9 10
-my @latin2iso_num = ( 0, 1, 2, 3, 4, 9, 10, 13, 14, 15, 16 );
-define_alias( qr/^latin[-_]?(\d+)$/i => '"iso-8859-$latin2iso_num[$1]"' );
+define_alias( qr/^(?:iso[-_]?)?latin[-_]?(\d+)$/i => '"iso-8859-$latin2iso_num[$1]"' );
+
+# Allow winlatin1 style names as well
+define_alias( qr/^win(latin[12]|cyrillic|baltic|greek|turkish|hebrew|arabic|baltic|vietnamese)$/i => '"cp$winlatin2cp{\u$1}"' );
# Common names for non-latin prefered MIME names
define_alias( 'ascii' => 'US-ascii',
'cyrillic' => 'iso-8859-5',
'arabic' => 'iso-8859-6',
'greek' => 'iso-8859-7',
- 'hebrew' => 'iso-8859-8');
-
-define_alias( 'ibm-1047' => 'cp1047');
+ 'hebrew' => 'iso-8859-8',
+ 'thai' => 'iso-8859-11',
+ 'tis620' => 'iso-8859-11',
+ );
+
+# At least AIX has IBM-NNN (surprisingly...) instead of cpNNN.
+define_alias( qr/^ibm[-_]?(\d\d\d\d?)$/i => '"cp$1"');
+
+# Standardize on the dashed versions.
+define_alias( qr/^utf8$/i => 'utf-8' );
+define_alias( qr/^koi8r$/i => 'koi8-r' );
+define_alias( qr/^koi8u$/i => 'koi8-u' );
+
+# TODO: HP-UX '8' encodings arabic8 greek8 hebrew8 kana8 thai8 turkish8
+# TODO: HP-UX '15' encodings japanese15 korean15 roi15
+# TODO: Cyrillic encoding ISO-IR-111 (useful?)
+# TODO: Chinese encodings GB18030 GBK Big5-HSKCS EUC-TW
+# TODO: Armenian encoding ARMSCII-8
+# TODO: Hebrew encoding ISO-8859-8-1
+# TODO: Thai encoding TCVN
+# TODO: Korean encoding Johab
+# TODO: Vietnamese encodings VPS
+# TODO: Japanese encoding JIS (not the same as SJIS)
+# TODO: Mac Asian+African encodings: Arabic Armenian Bengali Burmese
+# ChineseSimp ChineseTrad Devanagari Ethiopic ExtArabic
+# Farsi Georgian Gujarati Gurmukhi Hebrew Japanese
+# Kannada Khmer Korean Laotian Malayalam Mongolian
+# Oriya Sinhalese Symbol Tamil Telugu Tibetan Vietnamese
+# TODO: what is the Japanese 'UJIS' encoding seen in some Linuxes?
# Map white space and _ to '-'
define_alias( qr/^(\S+)[\s_]+(.*)$/i => '"$1-$2"' );
{
my ($class,$name) = @_;
my $enc;
+ if (ref($name) && $name->can('new_sequence'))
+ {
+ return $name;
+ }
+ my $lc = lc $name;
if (exists $encoding{$name})
{
return $encoding{$name};
}
- else
+ if (exists $encoding{$lc})
{
- return $class->findAlias($name);
+ return $encoding{$lc};
}
+
+ my $oc = $class->findAlias($name);
+ return $oc if defined $oc;
+ return $class->findAlias($lc) if $lc ne $name;
+
+ return;
}
sub find_encoding
my $enc = find_encoding($name);
croak("Unknown encoding '$name'") unless defined $enc;
my $string = $enc->decode($octets,$check);
- return undef if ($check && length($octets));
+ $_[1] = $octets if $check;
return $string;
}
sub encode_utf8
{
my ($str) = @_;
- utf8_encode($str);
+ utf8::encode($str);
return $str;
}
sub decode_utf8
{
my ($str) = @_;
- return undef unless utf8_decode($str);
+ return undef unless utf8::decode($str);
return $str;
}
package Encode::XS;
use base 'Encode::Encoding';
-package Encode::Unicode;
+package Encode::Internal;
use base 'Encode::Encoding';
# Dummy package that provides the encode interface but leaves data
-# as UTF-8 encoded. It is here so that from_to() works.
+# as UTF-X encoded. It is here so that from_to() works.
-__PACKAGE__->Define('Unicode');
+__PACKAGE__->Define('Internal');
+
+Encode::define_alias( 'Unicode' => 'Internal' ) if ord('A') == 65;
sub decode
{
my ($obj,$str,$chk) = @_;
- Encode::utf8_upgrade($str);
+ utf8::upgrade($str);
$_[1] = '' if $chk;
return $str;
}
*encode = \&decode;
+package Encoding::Unicode;
+use base 'Encode::Encoding';
+
+__PACKAGE__->Define('Unicode') unless ord('A') == 65;
+
+sub decode
+{
+ my ($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 $res;
+}
+
+sub encode
+{
+ my ($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;
+}
+
+
package Encode::utf8;
use base 'Encode::Encoding';
# package to allow long-hand
# Encoding is 16-bit network order Unicode (no surogates)
# Used for X font encodings
-__PACKAGE__->Define(qw(UCS-2 iso10646-1));
+__PACKAGE__->Define(qw(UCS-2 iso-10646-1));
sub decode
{
$uni .= chr($code);
}
$_[1] = $str if $chk;
- Encode::utf8_upgrade($uni);
+ utf8::upgrade($uni);
return $uni;
}
return $str;
}
+package Encode::ucs_2le;
+use base 'Encode::Encoding';
+
+__PACKAGE__->Define(qw(UCS-2le UCS-2LE ucs-2le));
+
+sub decode
+{
+ my ($obj,$str,$chk) = @_;
+ my $uni = '';
+ while (length($str))
+ {
+ my $code = unpack('v',substr($str,0,2,'')) & 0xffff;
+ $uni .= chr($code);
+ }
+ $_[1] = $str if $chk;
+ utf8::upgrade($uni);
+ return $uni;
+}
+
+sub encode
+{
+ my ($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;
+ }
+ $str .= pack('v',$x);
+ }
+ $_[1] = $uni if $chk;
+ return $str;
+}
+
# switch back to Encode package in case we ever add AutoLoader
package Encode;
=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 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>).
+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>).
Traditionaly computer data has been moved around in 8-bit chunks
often called "bytes". These chunks are also known as "octets" in
computer languages but also "binary" data being the machines 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".
+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
=item *
I<character>: a character in the range 0..(2**32-1) (or more).
-(What perl's strings are made of.)
+(What Perl's strings are made of.)
=item *
I<byte>: a character in the range 0..255
-(A special case of a perl character.)
+(A special case of a Perl character.)
=item *
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.)
+(Term for bytes passed to or from a non-Perl context, e.g. disk file.)
=back
=item * Fixed length 16-bit encodings
Each character is two octets so may have a repertoire of up to
-65,536 characters. Unicode's UCS-2 is an example. Also used for
+65 536 characters. Unicode's UCS-2 is an example. Also used for
encodings for East Asian languages.
=item * Fixed length 32-bit encodings.
a different "embedded" encoding.
These schemes are very flexible and can handle mixed languages but are
-very complex to process (and have state).
-No escape encodings are implemented for perl yet.
+very complex to process (and have state). No escape encodings are
+implemented for Perl yet.
=back
=item 1. By name
-Encoding names are strings with characters taken from a restricted repertoire.
-See L</"Encoding Names">.
+Encoding names are strings with characters taken from a restricted
+repertoire. See L</"Encoding Names">.
=item 2. As an object
=head2 Encoding Names
Encoding names are case insensitive. White space in names is ignored.
-In addition an encoding may have aliases. Each encoding has one "canonical" name.
-The "canonical" name is chosen from the names of the encoding by picking
-the first in the following sequence:
+In addition an encoding may have aliases. Each encoding has one
+"canonical" name. The "canonical" name is chosen from the names of
+the encoding by picking the first in the following sequence:
=over 4
-=item * The MIME name as defined in IETF RFC-XXXX.
+=item * The MIME name as defined in IETF RFCs.
=item * The name in the IANA registry.
-=item * The name used by the the organization that defined it.
+=item * The name used by the organization that defined it.
=back
encodings have state C<Encode> uses the encoding object internally
once an operation is in progress.
+As of Perl 5.8.0, at least the following encodings are recognized
+(the => marks aliases):
+
+ ASCII
+
+ US-ASCII => ASCII
+
+The Unicode:
+
+ UTF-8
+ UTF-16
+ UCS-2
+
+ ISO 10646-1 => UCS-2
+
+The ISO 8859 and KOI:
+
+ ISO 8859-1 ISO 8859-6 ISO 8859-11 KOI8-F
+ ISO 8859-2 ISO 8859-7 (12 doesn't exist) KOI8-R
+ ISO 8859-3 ISO 8859-8 ISO 8859-13 KOI8-U
+ ISO 8859-4 ISO 8859-9 ISO 8859-14
+ ISO 8859-5 ISO 8859-10 ISO 8859-15
+ ISO 8859-16
+
+ Latin1 => 8859-1 Latin6 => 8859-10
+ Latin2 => 8859-2 Latin7 => 8859-13
+ Latin3 => 8859-3 Latin8 => 8859-14
+ Latin4 => 8859-4 Latin9 => 8859-15
+ Latin5 => 8859-9 Latin10 => 8859-16
+
+ Cyrillic => 8859-5
+ Arabic => 8859-6
+ Greek => 8859-7
+ Hebrew => 8859-8
+ Thai => 8859-11
+ TIS620 => 8859-11
+
+The CJKV: Chinese, Japanese, Korean, Vietnamese:
+
+ ISO 2022 ISO 2022 JP-1 JIS 0201 GB 1988 Big5 EUC-CN
+ ISO 2022 CN ISO 2022 JP-2 JIS 0208 GB 2312 HZ EUC-JP
+ ISO 2022 JP ISO 2022 KR JIS 0210 GB 12345 CNS 11643 EUC-JP-0212
+ Shift-JIS EUC-KR
+ VISCII
+
+The PC codepages:
+
+ CP37 CP852 CP861 CP866 CP949 CP1251 CP1256
+ CP424 CP855 CP862 CP869 CP950 CP1252 CP1257
+ CP737 CP856 CP863 CP874 CP1006 CP1253 CP1258
+ CP775 CP857 CP864 CP932 CP1047 CP1254
+ CP850 CP860 CP865 CP936 CP1250 CP1255
+
+ WinLatin1 => CP1252
+ WinLatin2 => CP1250
+ WinCyrillic => CP1251
+ WinGreek => CP1253
+ WinTurkiskh => CP1254
+ WinHebrew => CP1255
+ WinArabic => CP1256
+ WinBaltic => CP1257
+ WinVietnamese => CP1258
+
+(All the CPI<NNN...> are available also as IBMI<NNN...>.)
+
+The Mac codepages:
+
+ MacCentralEuropean MacJapanese
+ MacCroatian MacRoman
+ MacCyrillic MacRumanian
+ MacDingbats MacSami
+ MacGreek MacThai
+ MacIcelandic MacTurkish
+ MacUkraine
+
+Miscellaneous:
+
+ 7bit-greek IR-197
+ 7bit-kana NeXTstep
+ 7bit-latin1 POSIX-BC
+ DingBats Roman8
+ GSM 0338 Symbol
+
=head1 PERL ENCODING API
=head2 Generic Encoding Interface
$bytes = encode(ENCODING, $string[, CHECK])
-Encodes string from perl's internal form into I<ENCODING> and returns a
-sequence of octets.
-See L</"Handling Malformed Data">.
+Encodes string from Perl's internal form into I<ENCODING> and returns
+a sequence of octets. For CHECK see L</"Handling Malformed Data">.
=item *
$string = decode(ENCODING, $bytes[, CHECK])
-Decode sequence of octets assumed to be in I<ENCODING> into perls internal
-form and returns the resuting string.
-See L</"Handling Malformed Data">.
+Decode sequence of octets assumed to be in I<ENCODING> into Perl's
+internal form and returns the resulting string. For CHECK see
+L</"Handling Malformed Data">.
+
+=item *
+
+ from_to($string, FROM_ENCODING, TO_ENCODING[, CHECK])
+
+Convert B<in-place> the data between two encodings. How did the data
+in $string originally get to be in FROM_ENCODING? Either using
+encode() or through PerlIO: See L</"Encoding and IO">. For CHECK
+see L</"Handling Malformed Data">.
+
+For example to convert ISO 8859-1 data to UTF-8:
+
+ from_to($data, "iso-8859-1", "utf-8");
+
+and to convert it back:
+
+ from_to($data, "utf-8", "iso-8859-1");
+
+Note that because the conversion happens in place, the data to be
+converted cannot be a string constant, it must be a scalar variable.
=back
=head2 Handling Malformed Data
If CHECK is not set, C<undef> is returned. If the data is supposed to
-be UTF-8, an optional lexical warning (category utf8) is given.
-If CHECK is true but not a code reference, dies.
+be UTF-8, an optional lexical warning (category utf8) is given. If
+CHECK is true but not a code reference, dies.
-It would desirable to have a way to indicate that transform should use the
-encodings "replacement character" - no such mechanism is defined yet.
+It would desirable to have a way to indicate that transform should use
+the encodings "replacement character" - no such mechanism is defined yet.
It is also planned to allow I<CHECK> to be a code reference.
-This is not yet implemented as there are design issues with what its arguments
-should be and how it returns its results.
+This is not yet implemented as there are design issues with what its
+arguments should be and how it returns its results.
=over 4
=item Scheme 2
-Passed original string, and an index into it of the problem area,
-and output string so far.
-Appends what it will to output string and returns new index into
-original string.
-e.g.
+Passed original string, and an index into it of the problem area, and
+output string so far. Appends what it will to output string and
+returns new index into original string. For example:
sub fixup {
# my ($s,$i,$d) = @_;
return $_[1]+1;
}
-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.
+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.
=item Other Schemes
=head2 UTF-8 / utf8
The Unicode consortium defines the UTF-8 standard as a way of encoding
-the entire Unicode repertiore as sequences of octets. This encoding
-is expected to become very widespread. Perl can use this form internaly
-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).
+the entire Unicode repertiore as sequences of octets. This encoding is
+expected to become very widespread. Perl can use this form internaly
+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
$bytes = encode_utf8($string);
-The characters that comprise string are encoded in perl's superset of UTF-8
+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.
$string = decode_utf8($bytes [,CHECK]);
-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.
-See L</"Handling Malformed Data">.
+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 Other Encodings of Unicode
-UTF-16 is similar to UCS-2, 16 bit or 2-byte chunks.
-UCS-2 can only represent 0..0xFFFF, while UTF-16 has a "surogate pair"
-scheme which allows it to cover the whole Unicode range.
+UTF-16 is similar to UCS-2, 16 bit or 2-byte chunks. UCS-2 can only
+represent 0..0xFFFF, while UTF-16 has a I<surrogate pair> scheme which
+allows it to cover the whole Unicode range.
+
+Surrogates are code points set aside to encode the 0x01000..0x10FFFF
+range of Unicode code points in pairs of 16-bit units. The I<high
+surrogates> are the range 0xD800..0xDBFF, and the I<low surrogates>
+are the range 0xDC00..0xDFFFF. The surrogate encoding is
+
+ $hi = ($uni - 0x10000) / 0x400 + 0xD800;
+ $lo = ($uni - 0x10000) % 0x400 + 0xDC00;
+
+and the decoding is
-Encode implements big-endian UCS-2 aliased to "iso10646-1" as that
-happens to be the name used by that representation when used with X11 fonts.
+ $uni = 0x10000 + ($hi - 0xD8000) * 0x400 + ($lo - 0xDC00);
+
+Encode implements big-endian UCS-2 aliased to "iso-10646-1" as that
+happens to be the name used by that representation when used with X11
+fonts.
UTF-32 or UCS-4 is 32-bit or 4-byte chunks. Perl's logical characters
can be considered as being in this form without encoding. An encoding
-to transfer strings in this form (e.g. to write them to a file) would need to
+to transfer strings in this form (e.g. to write them to a file) would
+need to
- pack('L',map(chr($_),split(//,$string))); # native
+ pack('L*', unpack('U*', $string)); # native
or
- pack('V',map(chr($_),split(//,$string))); # little-endian
+ pack('V*', unpack('U*', $string)); # little-endian
or
- pack('N',map(chr($_),split(//,$string))); # big-endian
+ pack('N*', unpack('U*', $string)); # big-endian
-depending on the endian required.
+depending on the endianness required.
No UTF-32 encodings are implemented yet.
-Both UCS-2 and UCS-4 style encodings can have "byte order marks" by representing
-the code point 0xFFFE as the very first thing in a file.
+Both UCS-2 and UCS-4 style encodings can have "byte order marks" by
+representing the code point 0xFFFE as the very first thing in a file.
=head2 Listing available encodings
use Encode qw(define_alias);
define_alias( newName => ENCODING);
-Allows newName to be used as am alias for ENCODING. ENCODING may be either the
-name of an encoding or and encoding object (as above).
+Allows newName to be used as am alias for ENCODING. ENCODING may be
+either the name of an encoding or and encoding object (as above).
Currently I<newName> can be specified in the following ways:
define_alias( qr/^iso8859-(\d+)$/i => '"iso-8859-$1"' );
-In this case if I<ENCODING> is not a reference it is C<eval>-ed to allow
-C<$1> etc. to be subsituted.
-The example is one way to names as used in X11 font names to alias the MIME names for the
-iso-8859-* family.
+In this case if I<ENCODING> is not a reference it is C<eval>-ed to
+allow C<$1> etc. to be subsituted. The example is one way to names as
+used in X11 font names to alias the MIME names for the iso-8859-*
+family.
=item As a code reference, e.g.:
define_alias( sub { return /^iso8859-(\d+)$/i ? "iso-8859-$1" : undef } , '');
In this case C<$_> will be set to the name that is being looked up and
-I<ENCODING> is passed to the sub as its first argument.
-The example is another way to names as used in X11 font names to alias the MIME names for
-the iso-8859-* family.
+I<ENCODING> is passed to the sub as its first argument. The example
+is another way to names as used in X11 font names to alias the MIME
+names for the iso-8859-* family.
=back
=head2 Defining Encodings
- use Encode qw(define_alias);
- define_encoding( $object, 'canonicalName' [,alias...]);
+ use Encode qw(define_alias);
+ define_encoding( $object, 'canonicalName' [,alias...]);
-Causes I<canonicalName> to be associated with I<$object>.
-The object should provide the interface described in L</"IMPLEMENTATION CLASSES"> below.
-If more than two arguments are provided then additional arguments are taken
-as aliases for I<$object> as for C<define_alias>.
+Causes I<canonicalName> to be associated with I<$object>. The object
+should provide the interface described in L</"IMPLEMENTATION CLASSES">
+below. If more than two arguments are provided then additional
+arguments are taken as aliases for I<$object> as for C<define_alias>.
=head1 Encoding and IO
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
+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.
- open(my $ilyad,'>:encoding(iso-8859-7)','ilyad.greek');
- print $ilyad @epic;
+Here is how the blind poet would modernise the encoding:
+
+ 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);
In addition the new IO system can also be configured to read/write
UTF-8 encoded characters (as noted above this is efficient):
- open(my $fh,'>:utf8','anything');
- print $fh "Any \x{0021} string \N{SMILEY FACE}\n";
+ open(my $fh,'>:utf8','anything');
+ print $fh "Any \x{0021} string \N{SMILEY FACE}\n";
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>.
Once a handle is open is layers can be altered using C<binmode>.
-Without any such configuration, or if perl itself is built using
+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.
+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.
+
+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+/>, ...).
+
+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):
+
+ open(F, "<:encoding(iso-8859-1)", "data.txt") or die $!;
+ open(G, ">:utf8", "data.utf") or die $!;
+ while (<F>) { print G }
-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+/>, ...).
+ # Could also do "print G <F>" but that would pull
+ # the whole file into memory just to write it out again.
+
+More examples:
+
+ open(my $f, "<:encoding(cp1252)")
+ open(my $g, ">:encoding(iso-8859-2)")
+ open(my $h, ">:encoding(latin9)") # iso-8859-15
+
+See L<PerlIO> for more information.
+
+See also L<encoding> for how to change the default encoding of the
+data in your script.
=head1 Encoding How to ...
=item * UTF-8 strings in binary data.
-=item * perl/Encode wrappers on non-Unicode XS modules.
+=item * Perl/Encode wrappers on non-Unicode XS modules.
=back
=head1 Messing with Perl's Internals
-The following API uses parts of perl's internals in the current implementation.
-As such they are efficient, but may change.
+The following API uses parts of Perl's internals in the current
+implementation. As such they are efficient, but may change.
=over 4
-=item *
-
- $num_octets = utf8_upgrade($string);
-
-Converts internal representation of string to the UTF-8 form.
-Returns the number of octets necessary to represent the string as UTF-8.
-
-=item * utf8_downgrade($string[, CHECK])
-
-Converts internal representation of string to be un-encoded bytes.
-
=item * is_utf8(STRING [, CHECK])
[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.
+If CHECK is true, also checks the data in STRING for being well-formed
+UTF-8. Returns true if successful, false otherwise.
=item * valid_utf8(STRING)
-[INTERNAL] Test whether STRING is in a consistent state.
-Will return true if string is held as bytes, or is well-formed UTF-8
-and has the UTF-8 flag on.
-Main reason for this routine is to allow perl's testsuite to check
-that operations have left strings in a consistent state.
+[INTERNAL] Test whether STRING is in a consistent state. Will return
+true if string is held as bytes, or is well-formed UTF-8 and has the
+UTF-8 flag on. Main reason for this routine is to allow Perl's
+testsuite to check that operations have left strings in a consistent
+state.
=item *
The string form may go away in the future. The string form occurs
when C<encodings()> has scanned C<@INC> for loadable encodings but has
not actually loaded the encoding in question. This is because the
-current "loading" process is all perl and a bit slow.
+current "loading" process is all Perl and a bit slow.
-Once an encoding is loaded then value of the hash is object which implements
-the encoding. The object should provide the following interface:
+Once an encoding is loaded then value of the hash is object which
+implements the encoding. The object should provide the following
+interface:
=over 4
=item -E<gt>new_sequence
-This is a placeholder for encodings with state. It should return an object
-which implements this interface, all current implementations return the
-original object.
+This is a placeholder for encodings with state. It should return an
+object which implements this interface, all current implementations
+return the original object.
=item -E<gt>encode($string,$check)
-Should return the octet sequence representing I<$string>. If I<$check> is true
-it should modify I<$string> in place to remove the converted part (i.e.
-the whole string unless there is an error).
-If an error occurs it should return the octet sequence for the
-fragment of string that has been converted, and modify $string in-place
-to remove the converted part leaving it starting with the problem fragment.
+Should return the octet sequence representing I<$string>. If I<$check>
+is true it should modify I<$string> in place to remove the converted
+part (i.e. the whole string unless there is an error). If an error
+occurs it should return the octet sequence for the fragment of string
+that has been converted, and modify $string in-place to remove the
+converted part leaving it starting with the problem fragment.
-If check is is false then C<encode> should make a "best effort" to convert
-the string - for example by using a replacement character.
+If check is is false then C<encode> should make a "best effort" to
+convert the string - for example by using a replacement character.
=item -E<gt>decode($octets,$check)
-Should return the string that I<$octets> represents. If I<$check> is true
-it should modify I<$octets> in place to remove the converted part (i.e.
-the whole sequence unless there is an error).
-If an error occurs it should return the fragment of string
-that has been converted, and modify $octets in-place to remove the converted part
+Should return the string that I<$octets> represents. If I<$check> is
+true it should modify I<$octets> in place to remove the converted part
+(i.e. the whole sequence unless there is an error). If an error
+occurs it should return the fragment of string that has been
+converted, and modify $octets in-place to remove the converted part
leaving it starting with the problem fragment.
-If check is is false then C<decode> should make a "best effort" to convert
-the string - for example by using Unicode's "\x{FFFD}" as a replacement character.
+If check is is false then C<decode> should make a "best effort" to
+convert the string - for example by using Unicode's "\x{FFFD}" as a
+replacement character.
=back
-It should be noted that the check behaviour is different from the outer
-public API. The logic is that the "unchecked" case is useful when
-encoding is part of a stream which may be reporting errors (e.g. STDERR).
-In such cases it is desirable to get everything through somehow without
-causing additional errors which obscure the original one. Also the encoding
-is best placed to know what the correct replacement character is, so if that
-is the desired behaviour then letting low level code do it is the most efficient.
-
-In contrast if check is true, the scheme above allows the encoding to do as
-much as it can and tell layer above how much that was. What is lacking
-at present is a mechanism to report what went wrong. The most likely interface
-will be an additional method call to the object, or perhaps
-(to avoid forcing per-stream objects on otherwise stateless encodings)
-and additional parameter.
-
-It is also highly desirable that encoding classes inherit from C<Encode::Encoding>
-as a base class. This allows that class to define additional behaviour for
-all encoding objects. For example built in Unicode, UCS-2 and UTF-8 classes
-use :
+It should be noted that the check behaviour is different from the
+outer public API. The logic is that the "unchecked" case is useful
+when encoding is part of a stream which may be reporting errors
+(e.g. STDERR). In such cases it is desirable to get everything
+through somehow without causing additional errors which obscure the
+original one. Also the encoding is best placed to know what the
+correct replacement character is, so if that is the desired behaviour
+then letting low level code do it is the most efficient.
+
+In contrast if check is true, the scheme above allows the encoding to
+do as much as it can and tell layer above how much that was. What is
+lacking at present is a mechanism to report what went wrong. The most
+likely interface will be an additional method call to the object, or
+perhaps (to avoid forcing per-stream objects on otherwise stateless
+encodings) and additional parameter.
+
+It is also highly desirable that encoding classes inherit from
+C<Encode::Encoding> as a base class. This allows that class to define
+additional behaviour for all encoding objects. For example built in
+Unicode, UCS-2 and UTF-8 classes use :
package Encode::MyEncoding;
use base qw(Encode::Encoding);
__PACKAGE__->Define(qw(myCanonical myAlias));
-To create an object with bless {Name => ...},$class, and call define_encoding.
-They inherit their C<name> method from C<Encode::Encoding>.
+To create an object with bless {Name => ...},$class, and call
+define_encoding. They inherit their C<name> method from
+C<Encode::Encoding>.
=head2 Compiled Encodings
-F<Encode.xs> provides a class C<Encode::XS> which provides the interface described
-above. It calls a generic octet-sequence to octet-sequence "engine" that is
-driven by tables (defined in F<encengine.c>). The same engine is used for both
-encode and decode. C<Encode:XS>'s C<encode> forces perl's characters to their UTF-8 form
-and then treats them as just another multibyte encoding. C<Encode:XS>'s C<decode> transforms
-the sequence and then turns the UTF-8-ness flag as that is the form that the tables
-are defined to produce. For details of the engine see the comments in F<encengine.c>.
-
-The tables are produced by the perl script F<compile> (the name needs to change so
-we can eventually install it somewhere). F<compile> can currently read two formats:
+F<Encode.xs> provides a class C<Encode::XS> which provides the
+interface described above. It calls a generic octet-sequence to
+octet-sequence "engine" that is driven by tables (defined in
+F<encengine.c>). The same engine is used for both encode and
+decode. C<Encode:XS>'s C<encode> forces Perl's characters to their
+UTF-8 form and then treats them as just another multibyte
+encoding. C<Encode:XS>'s C<decode> transforms the sequence and then
+turns the UTF-8-ness flag as that is the form that the tables are
+defined to produce. For details of the engine see the comments in
+F<encengine.c>.
+
+The tables are produced by the Perl script F<compile> (the name needs
+to change so we can eventually install it somewhere). F<compile> can
+currently read two formats:
=over 4
=item *.enc
-This is a coined format used by Tcl. It is documented in Encode/EncodeFormat.pod.
+This is a coined format used by Tcl. It is documented in
+Encode/EncodeFormat.pod.
=item *.ucm
=item *.xs
-In theory this allows encodings to be stand-alone loadable perl extensions.
-The process has not yet been tested. The plan is to use this approach
-for large East Asian encodings.
+In theory this allows encodings to be stand-alone loadable Perl
+extensions. The process has not yet been tested. The plan is to use
+this approach for large East Asian encodings.
=back
-The set of encodings built-in to F<Encode.so>/F<Encode.dll> is determined by
-F<Makefile.PL>. The current set is as follows:
+The set of encodings built-in to F<Encode.so>/F<Encode.dll> is
+determined by F<Makefile.PL>. The current set is as follows:
=over 4
=item IBM-1047 and two other variants of EBCDIC.
-These are the same variants that are supported by EBCDIC perl as "native" encodings.
-They are included to prove "reversibility" of some constructs in EBCDIC perl.
+These are the same variants that are supported by EBCDIC Perl as
+"native" encodings. They are included to prove "reversibility" of
+some constructs in EBCDIC Perl.
=item symbol and dingbats as used by Tk on X11.
-(The reason Encode got started was to support perl/Tk.)
+(The reason Encode got started was to support Perl/Tk.)
=back
-That set is rather ad. hoc. and has been driven by the needs of the tests rather
-than the needs of typical applications. It is likely to be rationalized.
+That set is rather ad hoc and has been driven by the needs of the
+tests rather than the needs of typical applications. It is likely
+to be rationalized.
=head1 SEE ALSO
-L<perlunicode>, L<perlebcdic>, L<perlfunc/open>
+L<perlunicode>, L<perlebcdic>, L<perlfunc/open>, L<PerlIO>, L<encoding>
=cut
-
-
projects / p5sagit/p5-mst-13.2.git / blobdiff