package Encode;
use strict;
-our $VERSION = '0.40';
+our $VERSION = do { my @r = (q$Revision: 1.20 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
+our $DEBUG = 0;
require DynaLoader;
require Exporter;
our @EXPORT_OK =
qw(
define_encoding
- define_alias
from_to
is_utf8
is_8bit
use Carp;
-# Make a %encoding package variable to allow a certain amount of cheating
-our %encoding;
-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,
- );
+our $ON_EBCDIC = (ord("A") == 193);
+use Encode::Alias;
+
+# Make a %Encoding package variable to allow a certain amount of cheating
+our %Encoding;
+our %ExtModule;
+
+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
+ );
+
+my @macintosh = qw(
+ CentralEurRoman Croatian Cyrillic Greek
+ Iceland Roman Rumanian Sami
+ Thai Turkish Ukrainian
+ );
+
+for my $k (2..11,13..16){
+ $ExtModule{"iso-8859-$k"} = 'Encode/Byte.pm';
+}
-sub encodings
-{
- my ($class) = @_;
- return
- map { $_->[0] }
- sort { $a->[1] cmp $b->[1] }
- map { [$_, lc $_] }
- grep { $_ ne 'Internal' }
- keys %encoding;
+for my $k (@codepages){
+ $ExtModule{"cp$k"} = 'Encode/Byte.pm';
}
-sub findAlias
+for my $k (@macintosh)
{
- my $class = shift;
- local $_ = shift;
- # print "# findAlias $_\n";
- unless (exists $alias{$_})
- {
- for (my $i=0; $i < @alias; $i += 2)
- {
- my $alias = $alias[$i];
- my $val = $alias[$i+1];
- my $new;
- if (ref($alias) eq 'Regexp' && $_ =~ $alias)
- {
- $new = eval $val;
- }
- elsif (ref($alias) eq 'CODE')
- {
- $new = &{$alias}($val)
- }
- elsif (lc($_) eq lc($alias))
- {
- $new = $val;
- }
- if (defined($new))
- {
- next if $new eq $_; # avoid (direct) recursion on bugs
- my $enc = (ref($new)) ? $new : find_encoding($new);
- if ($enc)
- {
- $alias{$_} = $enc;
- last;
- }
- }
- }
- }
- return $alias{$_};
+ $ExtModule{"mac$k"} = 'Encode/Byte.pm';
+}
+
+%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,
+ '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',
+ macJapanese => 'Encode/JP.pm',
+ cp932 => 'Encode/JP.pm',
+ 'euc-kr' => 'Encode/KR.pm',
+ ksc5601 => 'Encode/KR.pm',
+ macKorean => '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',
+ );
}
-sub define_alias
+
+
+
+sub encodings
{
- while (@_)
+ my $class = shift;
+ my @modules = (@_ and $_[0] eq ":all") ? values %ExtModule : @_;
+ for my $m (@modules)
{
- my ($alias,$name) = splice(@_,0,2);
- push(@alias, $alias => $name);
+ $DEBUG and warn "about to require $m;";
+ eval { require $m; };
}
+ return
+ map({$_->[0]}
+ sort({$a->[1] cmp $b->[1]}
+ map({[$_, lc $_]}
+ grep({ $_ ne 'Internal' } keys %Encoding))));
}
-# Allow variants of iso-8859-1 etc.
-define_alias( qr/^iso[-_]?(\d+)[-_](\d+)$/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 => '"$1"' );
-
-# Allow latin-1 style names as well
-define_alias( qr/^(?:iso[-_]?)?latin[-_]?(\d+)$/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$1}"' );
-
-# Common names for non-latin prefered MIME names
-define_alias( 'ascii' => 'US-ascii',
- 'cyrillic' => 'iso-8859-5',
- 'arabic' => 'iso-8859-6',
- 'greek' => 'iso-8859-7',
- 'hebrew' => 'iso-8859-8',
- 'thai' => 'iso-8859-11',
- 'tis620' => 'iso-8859-11',
- );
-
-# At least AIX has IBM-NNN (surprisingly...) instead of cpNNN.
-define_alias( qr/^ibm[-_]?(\d\d\d\d?)$/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?
-# Answer: euc-jp <dankogai@dan.co.jp>
-# Map white space and _ to '-'
-
-define_alias( qr/^(\S+)[\s_]+(.*)$/i => '"$1-$2"' );
-
sub define_encoding
{
my $obj = shift;
my $name = shift;
- $encoding{$name} = $obj;
+ $Encoding{$name} = $obj;
my $lc = lc($name);
define_alias($lc => $obj) unless $lc eq $name;
while (@_)
sub getEncoding
{
- my ($class,$name) = @_;
+ my ($class,$name,$skip_external) = @_;
my $enc;
if (ref($name) && $name->can('new_sequence'))
{
return $name;
}
my $lc = lc $name;
- if (exists $encoding{$name})
+ if (exists $Encoding{$name})
{
- return $encoding{$name};
+ return $Encoding{$name};
}
- if (exists $encoding{$lc})
+ if (exists $Encoding{$lc})
{
- return $encoding{$lc};
+ return $Encoding{$lc};
}
- my $oc = $class->findAlias($name);
+ 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;
- return $class->findAlias($lc) if $lc ne $name;
+
+ if (!$skip_external and exists $ExtModule{$lc})
+ {
+ eval{ require $ExtModule{$lc}; };
+ return $Encoding{$name} if exists $Encoding{$name};
+ }
return;
}
sub find_encoding
{
- my ($name) = @_;
- return __PACKAGE__->getEncoding($name);
+ my ($name,$skip_external) = @_;
+ return __PACKAGE__->getEncoding($name,$skip_external);
}
sub encode
croak("Unknown encoding '$to'") unless defined $t;
my $uni = $f->decode($string,$check);
return undef if ($check && length($string));
- $string = $t->encode($uni,$check);
+ $string = $t->encode($uni,$check);
return undef if ($check && length($uni));
- return length($_[0] = $string);
+ return defined($_[0] = $string) ? length($string) : undef ;
}
sub encode_utf8
require Encode::Internal;
require Encode::Unicode;
require Encode::utf8;
-require Encode::iso10646_1;
+require Encode::10646_1;
require Encode::ucs2_le;
1;
use Encode;
+
+=head2 Table of Contents
+
+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;
+
+ 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
+ --------------------------------------------------------
+
=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>.
+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
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
+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.
+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.
-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
general meant only for those who think they know what they are doing,
and such details may change in future releases.
-=head1 ENCODINGS
-
-=head2 Characteristics of an Encoding
-
-An encoding has a "repertoire" of characters that it can represent,
-and for each representable character there is at least one sequence of
-octets that represents it.
-
-=head2 Types of Encodings
-
-Encodings can be divided into the following types:
+=head1 PERL ENCODING API
=over 4
-=item * Fixed length 8-bit (or less) encodings.
-
-Each character is a single octet so may have a repertoire of up to
-256 characters. ASCII and iso-8859-* are typical examples.
-
-=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
-encodings for East Asian languages.
-
-=item * Fixed length 32-bit encodings.
-
-Not really very "encoded" encodings. The Unicode code points
-are just represented as 4-octet integers. None the less because
-different architectures use different representations of integers
-(so called "endian") there at least two disctinct encodings.
-
-=item * Multi-byte encodings
-
-The number of octets needed to represent a character varies.
-UTF-8 is a particularly complex but regular case of a multi-byte
-encoding. Several East Asian countries use a multi-byte encoding
-where 1-octet is used to cover western roman characters and Asian
-characters get 2-octets.
-(UTF-16 is strictly a multi-byte encoding taking either 2 or 4 octets
-to represent a Unicode code point.)
+=item $bytes = encode(ENCODING, $string[, CHECK])
-=item * "Escape" encodings.
-
-These encodings embed "escape sequences" into the octet sequence
-which describe how the following octets are to be interpreted.
-The iso-2022-* family is typical. Following the escape sequence
-octets are encoded by an "embedded" encoding (which will be one
-of the above types) until another escape sequence switches to
-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.
-
-=back
+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">.
-=head2 Specifying Encodings
+For example to convert (internally UTF-8 encoded) Unicode string to
+iso-8859-1 (also known as Latin1),
-Encodings can be specified to the API described below in two ways:
+ $octets = encode("iso-8859-1", $unicode);
-=over 4
+=item $string = decode(ENCODING, $bytes[, CHECK])
-=item 1. By name
+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">.
-Encoding names are strings with characters taken from a restricted
-repertoire. See L</"Encoding Names">.
+For example to convert ISO-8859-1 data to UTF-8:
-=item 2. As an object
+ $utf8 = decode("iso-8859-1", $latin1);
-Encoding objects are returned by C<find_encoding($name)>.
+=item [$length =] from_to($string, FROM_ENCODING, TO_ENCODING[, CHECK])
-=back
+Convert B<in-place> the data between two encodings. How did the data
+in $string originally get to be in FROM_ENCODING? Either using
+encode() or through PerlIO: See L</"Encoding and IO">.
+For encoding names and aliases, see L</"Defining Aliases">.
+For CHECK see L</"Handling Malformed Data">.
-=head2 Encoding Names
+For example to convert ISO-8859-1 data to UTF-8:
-Encoding names are case insensitive. White space in names is ignored.
-In addition an encoding may have aliases. Each encoding has one
-"canonical" name. The "canonical" name is chosen from the names of
-the encoding by picking the first in the following sequence:
+ from_to($data, "iso-8859-1", "utf-8");
-=over 4
+and to convert it back:
-=item * The MIME name as defined in IETF RFCs.
+ from_to($data, "utf-8", "iso-8859-1");
-=item * The name in the IANA registry.
+Note that because the conversion happens in place, the data to be
+converted cannot be a string constant, it must be a scalar variable.
-=item * The name used by the organization that defined it.
+from_to() return the length of the converted string on success, undef
+otherwise.
=back
-Because of all the alias issues, and because in the general case
-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
+=head2 Listing available encodings
-The CJKV: Chinese, Japanese, Korean, Vietnamese:
+ use Encode;
+ @list = Encode->encodings();
- 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
+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
-The PC codepages:
+ @all_encodings = Encode->encodings(":all");
- 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
+Or you can give the name of specific module.
- WinLatin1 => CP1252
- WinLatin2 => CP1250
- WinCyrillic => CP1251
- WinGreek => CP1253
- WinTurkiskh => CP1254
- WinHebrew => CP1255
- WinArabic => CP1256
- WinBaltic => CP1257
- WinVietnamese => CP1258
+ @with_jp = Encode->encodings("Encode/JP.pm");
-(All the CPI<NNN...> are available also as IBMI<NNN...>.)
+Note in this case you have to say C<"Encode/JP.pm"> instead of
+C<"Encode::JP">.
-The Mac codepages:
+To find which encodings are supported by this package in details,
+see L<Encode::Supported>.
- MacCentralEuropean MacJapanese
- MacCroatian MacRoman
- MacCyrillic MacRumanian
- MacDingbats MacSami
- MacGreek MacThai
- MacIcelandic MacTurkish
- MacUkraine
-Miscellaneous:
+=head2 Defining Aliases
- 7bit-greek IR-197
- 7bit-kana NeXTstep
- 7bit-latin1 POSIX-BC
- DingBats Roman8
- GSM 0338 Symbol
+To add new alias to a given encoding, Use;
-=head1 PERL ENCODING API
+ use Encode;
+ use Encode::Alias;
+ define_alias(newName => ENCODING);
-=head2 Generic Encoding Interface
+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>
-=over 4
+See L<Encode::Alias> on details.
-=item *
-
- $bytes = encode(ENCODING, $string[, CHECK])
-
-Encodes string from Perl's internal form into I<ENCODING> and returns
-a sequence of octets. For CHECK see L</"Handling Malformed Data">.
+=head1 Encoding and IO
-For example to convert (internally UTF-8 encoded) Unicode data
-to octets:
+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.
- $octets = encode("utf8", $unicode);
+Here is how the blind poet would modernise the encoding:
-=item *
+ 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);
- $string = decode(ENCODING, $bytes[, CHECK])
+In addition the new IO system can also be configured to read/write
+UTF-8 encoded characters (as noted above this is efficient):
-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">.
+ open(my $fh,'>:utf8','anything');
+ print $fh "Any \x{0021} string \N{SMILEY FACE}\n";
-For example to convert ISO 8859-1 data to UTF-8:
+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>.
- $utf8 = decode("latin1", $latin1);
+Once a handle is open is layers can be altered using C<binmode>.
-=item *
+Without any such configuration, or if Perl itself is built using
+system's own IO, then write operations assume that file handle accepts
+only I<bytes> and will C<die> if a character larger than 255 is
+written to the handle. When reading, each octet from the handle
+becomes a byte-in-a-character. Note that this default is the same
+behaviour as bytes-only languages (including Perl before v5.6) would
+have, and is sufficient to handle native 8-bit encodings
+e.g. iso-8859-1, EBCDIC etc. and any legacy mechanisms for handling
+other encodings and binary data.
- from_to($string, FROM_ENCODING, TO_ENCODING[, CHECK])
+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+/>, ...).
-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">.
+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):
-For example to convert ISO 8859-1 data to UTF-8:
+ open(F, "<:encoding(iso-8859-1)", "data.txt") or die $!;
+ open(G, ">:utf8", "data.utf") or die $!;
+ while (<F>) { print G }
- from_to($data, "iso-8859-1", "utf-8");
+ # Could also do "print G <F>" but that would pull
+ # the whole file into memory just to write it out again.
-and to convert it back:
+More examples:
- from_to($data, "utf-8", "iso-8859-1");
+ open(my $f, "<:encoding(cp1252)")
+ open(my $g, ">:encoding(iso-8859-2)")
+ open(my $h, ">:encoding(latin9)") # iso-8859-15
-Note that because the conversion happens in place, the data to be
-converted cannot be a string constant, it must be a scalar variable.
+See L<PerlIO> for more information.
-=back
+See also L<encoding> for how to change the default encoding of the
+data in your script.
-=head2 Handling Malformed Data
+=head1 Handling Malformed Data
If CHECK is not set, C<undef> is returned. If the data is supposed to
be UTF-8, an optional lexical warning (category utf8) is given. If
Multiple return values rather than in-place modifications.
-Index into the string could be pos($str) allowing s/\G...//.
+Index into the string could be C<pos($str)> allowing C<s/\G...//>.
=back
=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
+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 *
-
- $bytes = encode_utf8($string);
+=item $bytes = encode_utf8($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.
-=item *
-
- $string = decode_utf8($bytes [,CHECK]);
+=item $string = decode_utf8($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
=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 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
-
- $uni = 0x10000 + ($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
-
- pack('L*', unpack('U*', $string)); # native
- or
- pack('V*', unpack('U*', $string)); # little-endian
- or
- pack('N*', unpack('U*', $string)); # big-endian
-
-depending on the endianness required.
-
-No UTF-32 encodings are implemented yet.
-
-Both UCS-2 and UCS-4 style encodings can have "byte order marks" by
-representing the code point 0xFFFE as the very first thing in a file.
-
-=head2 Listing available encodings
-
- use Encode qw(encodings);
- @list = encodings();
-
-Returns a list of the canonical names of the available encodings.
-
-=head2 Defining Aliases
-
- use Encode qw(define_alias);
- define_alias( newName => ENCODING);
-
-Allows newName to be used as am alias for ENCODING. ENCODING may be
-either the name of an encoding or and encoding object (as above).
-
-Currently I<newName> can be specified in the following ways:
-
-=over 4
-
-=item As a simple string.
-
-=item As a qr// compiled regular expression, e.g.:
-
- define_alias( qr/^iso8859-(\d+)$/i => '"iso-8859-$1"' );
-
-In this case if I<ENCODING> is not a reference it is C<eval>-ed to
-allow C<$1> etc. to be subsituted. The example is one way to names as
-used in X11 font names to alias the MIME names for the iso-8859-*
-family.
-
-=item As a code reference, e.g.:
-
- define_alias( sub { return /^iso8859-(\d+)$/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.
-
-=back
+=head1 Defining Encodings
-=head2 Defining Encodings
+To define a new encoding, use:
use Encode qw(define_alias);
- define_encoding( $object, 'canonicalName' [,alias...]);
+ define_encoding($object, 'canonicalName' [, alias...]);
-Causes I<canonicalName> to be associated with I<$object>. The object
-should provide the interface described in L</"IMPLEMENTATION CLASSES">
-below. If more than two arguments are provided then additional
+I<canonicalName> will be associated with I<$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>.
-=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
-C<Encode> provides a "layer" (See L<perliol>) which can transform
-data as it is read or written.
-
-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";
-
-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
-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.
-
-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 }
-
- # 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 ...
-
-To do:
-
-=over 4
-
-=item * IO with mixed content (faking iso-2020-*)
-
-=item * MIME's Content-Length:
-
-=item * UTF-8 strings in binary data.
-
-=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
=over 4
-=item * is_utf8(STRING [, CHECK])
+=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.
-=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.
-
-=item *
-
- _utf8_on(STRING)
+=item _utf8_on(STRING)
[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
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 *
-
- _utf8_off(STRING)
+=item _utf8_off(STRING)
[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
=back
-=head1 IMPLEMENTATION CLASSES
-
-As mentioned above encodings are (in the current implementation at least)
-defined by objects. The mapping of encoding name to object is via the
-C<%encodings> hash.
-
-The values of the hash can currently be either strings or objects.
-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.
-
-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>name
-
-Should return the string representing the canonical name of the encoding.
-
-=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.
-
-=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 $string in-place to remove the
-converted part leaving it starting with the problem fragment.
-
-If check is is false then C<encode> should make a "best effort" to
-convert the string - for example by using a replacement character.
-
-=item -E<gt>decode($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 $octets in-place to remove the converted part
-leaving it starting with the problem fragment.
-
-If check is is false then C<decode> should make a "best effort" to
-convert the string - for example by using Unicode's "\x{FFFD}" as a
-replacement character.
-
-=back
-
-It should be noted that the check behaviour is different from the
-outer public API. The logic is that the "unchecked" case is useful
-when encoding is part of a stream which may be reporting errors
-(e.g. STDERR). In such cases it is desirable to get everything
-through somehow without causing additional errors which obscure the
-original one. Also the encoding is best placed to know what the
-correct replacement character is, so if that is the desired behaviour
-then letting low level code do it is the most efficient.
-
-In contrast if check is true, the scheme above allows the encoding to
-do as much as it can and tell layer above how much that was. What is
-lacking at present is a mechanism to report what went wrong. The most
-likely interface will be an additional method call to the object, or
-perhaps (to avoid forcing per-stream objects on otherwise stateless
-encodings) and additional parameter.
-
-It is also highly desirable that encoding classes inherit from
-C<Encode::Encoding> as a base class. This allows that class to define
-additional behaviour for all encoding objects. For example built in
-Unicode, UCS-2 and UTF-8 classes use :
-
- package Encode::MyEncoding;
- use base qw(Encode::Encoding);
-
- __PACKAGE__->Define(qw(myCanonical myAlias));
-
-To create an object with bless {Name => ...},$class, and call
-define_encoding. They inherit their C<name> method from
-C<Encode::Encoding>.
-
-=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:
-
-=over 4
-
-=item *.enc
-
-This is a coined format used by Tcl. It is documented in
-Encode/EncodeFormat.pod.
-
-=item *.ucm
-
-This is the semi-standard format used by IBM's ICU package.
-
-=back
-
-F<compile> can write the following forms:
-
-=over 4
-
-=item *.ucm
-
-See above - the F<Encode/*.ucm> files provided with the distribution have
-been created from the original Tcl .enc files using this approach.
-
-=item *.c
-
-Produces tables as C data structures - this is used to build in encodings
-into F<Encode.so>/F<Encode.dll>.
-
-=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.
-
-=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:
-
-=over 4
-
-=item ascii and iso-8859-*
-
-That is all the common 8-bit "western" encodings.
-
-=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.
-
-=item symbol and dingbats as used by Tk on X11.
-
-(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.
-
=head1 SEE ALSO
-L<perlunicode>, L<perlebcdic>, L<perlfunc/open>, L<PerlIO>, L<encoding>
+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
-
https://perl5.git.perl.org / perl5.git / blobdiff