#
-# $Id: Encode.pm,v 1.71 2002/05/07 16:23:08 dankogai Exp dankogai $
+# $Id: Encode.pm,v 2.12 2005/09/08 14:17:17 dankogai Exp dankogai $
#
package Encode;
use strict;
-our $VERSION = do { my @r = (q$Revision: 1.71 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
-our $DEBUG = 0;
+our $VERSION = sprintf "%d.%02d", q$Revision: 2.12 $ =~ /(\d+)/g;
+sub DEBUG () { 0 }
use XSLoader ();
XSLoader::load(__PACKAGE__, $VERSION);
our @EXPORT = qw(
decode decode_utf8 encode encode_utf8
- encodings find_encoding
+ encodings find_encoding clone_encoding
);
our @FB_FLAGS = qw(DIE_ON_ERR WARN_ON_ERR RETURN_ON_ERR LEAVE_SRC
- PERLQQ HTMLCREF XMLCREF);
+ PERLQQ HTMLCREF XMLCREF STOP_AT_PARTIAL);
our @FB_CONSTS = qw(FB_DEFAULT FB_CROAK FB_QUIET FB_WARN
FB_PERLQQ FB_HTMLCREF FB_XMLCREF);
}else{
%enc = %Encoding;
for my $mod (map {m/::/o ? $_ : "Encode::$_" } @_){
- $DEBUG and warn $mod;
+ DEBUG and warn $mod;
for my $enc (keys %ExtModule){
$ExtModule{$enc} eq $mod and $enc{$enc} = $mod;
}
{
my ($class, $name, $skip_external) = @_;
- ref($name) && $name->can('new_sequence') and return $name;
+ ref($name) && $name->can('renew') and return $name;
exists $Encoding{$name} and return $Encoding{$name};
my $lc = lc $name;
exists $Encoding{$lc} and return $Encoding{$lc};
return;
}
-sub find_encoding
+sub find_encoding($;$)
{
my ($name, $skip_external) = @_;
return __PACKAGE__->getEncoding($name,$skip_external);
}
-sub resolve_alias {
+sub resolve_alias($){
my $obj = find_encoding(shift);
defined $obj and return $obj->name;
return;
}
+sub clone_encoding($){
+ my $obj = find_encoding(shift);
+ ref $obj or return;
+ eval { require Storable };
+ $@ and return;
+ return Storable::dclone($obj);
+}
+
sub encode($$;$)
{
my ($name, $string, $check) = @_;
+ return undef unless defined $string;
+ $string .= '' if ref $string; # stringify;
$check ||=0;
my $enc = find_encoding($name);
unless(defined $enc){
Carp::croak("Unknown encoding '$name'");
}
my $octets = $enc->encode($string,$check);
- return undef if ($check && length($string));
+ $_[1] = $string if $check and !($check & LEAVE_SRC());
return $octets;
}
sub decode($$;$)
{
my ($name,$octets,$check) = @_;
+ return undef unless defined $octets;
+ $octets .= '' if ref $octets;
$check ||=0;
my $enc = find_encoding($name);
unless(defined $enc){
Carp::croak("Unknown encoding '$name'");
}
my $string = $enc->decode($octets,$check);
- $_[1] = $octets if $check;
+ $_[1] = $octets if $check and !($check & LEAVE_SRC());
return $string;
}
sub from_to($$$;$)
{
my ($string,$from,$to,$check) = @_;
+ return undef unless defined $string;
$check ||=0;
my $f = find_encoding($from);
unless (defined $f){
return $str;
}
-sub decode_utf8($)
+sub decode_utf8($;$)
{
- my ($str) = @_;
- return undef unless utf8::decode($str);
- return $str;
+ my ($str, $check) = @_;
+ if ($check){
+ return decode("utf8", $str, $check);
+ }else{
+ return decode("utf8", $str);
+ return $str;
+ }
}
-predefine_encodings();
+predefine_encodings(1);
#
# This is to restore %Encoding if really needed;
sub predefine_encodings{
use Encode::Encoding;
+ no warnings 'redefine';
+ my $use_xs = shift;
if ($ON_EBCDIC) {
# was in Encode::UTF_EBCDIC
package Encode::UTF_EBCDIC;
# was in Encode::utf8
package Encode::utf8;
push @Encode::utf8::ISA, 'Encode::Encoding';
- *decode = sub{
- my ($obj,$octets,$chk) = @_;
- my $str = Encode::decode_utf8($octets);
- if (defined $str) {
+ #
+ if ($use_xs){
+ Encode::DEBUG and warn __PACKAGE__, " XS on";
+ *decode = \&decode_xs;
+ *encode = \&encode_xs;
+ }else{
+ Encode::DEBUG and warn __PACKAGE__, " XS off";
+ *decode = sub{
+ my ($obj,$octets,$chk) = @_;
+ my $str = Encode::decode_utf8($octets);
+ if (defined $str) {
+ $_[1] = '' if $chk;
+ return $str;
+ }
+ return undef;
+ };
+ *encode = sub {
+ my ($obj,$string,$chk) = @_;
+ my $octets = Encode::encode_utf8($string);
$_[1] = '' if $chk;
- return $str;
+ return $octets;
+ };
+ }
+ *cat_decode = sub{ # ($obj, $dst, $src, $pos, $trm, $chk)
+ my ($obj, undef, undef, $pos, $trm) = @_; # currently ignores $chk
+ my ($rdst, $rsrc, $rpos) = \@_[1,2,3];
+ use bytes;
+ if ((my $npos = index($$rsrc, $trm, $pos)) >= 0) {
+ $$rdst .= substr($$rsrc, $pos, $npos - $pos + length($trm));
+ $$rpos = $npos + length($trm);
+ return 1;
}
- return undef;
- };
- *encode = sub {
- my ($obj,$string,$chk) = @_;
- my $octets = Encode::encode_utf8($string);
- $_[1] = '' if $chk;
- return $octets;
+ $$rdst .= substr($$rsrc, $pos);
+ $$rpos = length($$rsrc);
+ return '';
};
$Encode::Encoding{utf8} =
bless {Name => "utf8"} => "Encode::utf8";
+ $Encode::Encoding{"utf-8-strict"} =
+ bless {Name => "utf-8-strict", strict_utf8 => 1 } => "Encode::utf8";
}
}
the result is always off, even when it contains completely valid utf8
string. See L</"The UTF-8 flag"> below.
-encode($valid_encoding, undef) is harmless but warns you for
-C<Use of uninitialized value in subroutine entry>.
-encode($valid_encoding, '') is harmless and warnless.
+If the $string is C<undef> then C<undef> is returned.
=item $string = decode(ENCODING, $octets [, CHECK])
ASCII data (or EBCDIC on EBCDIC machines). See L</"The UTF-8 flag">
below.
-decode($valid_encoding, undef) is harmless but warns you for
-C<Use of uninitialized value in subroutine entry>.
-decode($valid_encoding, '') is harmless and warnless.
+If the $string is C<undef> then C<undef> is returned.
=item [$length =] from_to($octets, FROM_ENC, TO_ENC [, CHECK])
Converts B<in-place> data between two encodings. The data in $octets
must be encoded as octets and not as characters in Perl's internal
-format. For example, to convert ISO-8859-1 data to Microsoft's CP1250 encoding:
+format. For example, to convert ISO-8859-1 data to Microsoft's CP1250
+encoding:
from_to($octets, "iso-8859-1", "cp1250");
Note that because the conversion happens in place, the data to be
converted cannot be a string constant; it must be a scalar variable.
-from_to() returns the length of the converted string in octets on success, undef
-otherwise.
+from_to() returns the length of the converted string in octets on
+success, I<undef> on error.
B<CAVEAT>: The following operations look the same but are not quite so;
perlio_ok("euc-jp")
Fortunately, all encodings that come with Encode core are PerlIO-savvy
-except for hz and ISO-2022-kr. For gory details, see L<Encode::Encoding> and L<Encode::PerlIO>.
+except for hz and ISO-2022-kr. For gory details, see
+L<Encode::Encoding> and L<Encode::PerlIO>.
=head1 Handling Malformed Data
+The optional I<CHECK> argument tells Encode what to do when it
+encounters malformed data. Without CHECK, Encode::FB_DEFAULT ( == 0 )
+is assumed.
+
+As of version 2.12 Encode supports coderef values for CHECK. See below.
+
=over 2
-The I<CHECK> argument is used as follows. When you omit it,
-the behaviour is the same as if you had passed a value of 0 for
-I<CHECK>.
+=item B<NOTE:> Not all encoding support this feature
+
+Some encodings ignore I<CHECK> argument. For example,
+L<Encode::Unicode> ignores I<CHECK> and it always croaks on error.
+
+=back
+
+Now here is the list of I<CHECK> values available
+
+=over 2
=item I<CHECK> = Encode::FB_DEFAULT ( == 0)
-If I<CHECK> is 0, (en|de)code will put a I<substitution character>
-in place of a malformed character. For UCM-based encodings,
-E<lt>subcharE<gt> will be used. For Unicode, the code point C<0xFFFD> is used.
-If the data is supposed to be UTF-8, an optional lexical warning
+If I<CHECK> is 0, (en|de)code will put a I<substitution character> in
+place of a malformed character. When you encode, E<lt>subcharE<gt>
+will be used. When you decode the code point C<0xFFFD> is used. If
+the data is supposed to be UTF-8, an optional lexical warning
(category utf8) is given.
=item I<CHECK> = Encode::FB_CROAK ( == 1)
If I<CHECK> is 1, methods will die on error immediately with an error
message. Therefore, when I<CHECK> is set to 1, you should trap the
-fatal error with eval{} unless you really want to let it die on error.
+error with eval{} unless you really want to let it die.
=item I<CHECK> = Encode::FB_QUIET
If I<CHECK> is set to Encode::FB_QUIET, (en|de)code will immediately
-return the portion of the data that has been processed so far when
-an error occurs. The data argument will be overwritten with
-everything after that point (that is, the unprocessed part of data).
-This is handy when you have to call decode repeatedly in the case
-where your source data may contain partial multi-byte character
-sequences, for example because you are reading with a fixed-width
-buffer. Here is some sample code that does exactly this:
-
- my $data = ''; my $utf8 = '';
- while(defined(read $fh, $buffer, 256)){
- # buffer may end in a partial character so we append
- $data .= $buffer;
- $utf8 .= decode($encoding, $data, ENCODE::FB_QUIET);
- # $data now contains the unprocessed partial character
+return the portion of the data that has been processed so far when an
+error occurs. The data argument will be overwritten with everything
+after that point (that is, the unprocessed part of data). This is
+handy when you have to call decode repeatedly in the case where your
+source data may contain partial multi-byte character sequences,
+(i.e. you are reading with a fixed-width buffer). Here is a sample
+code that does exactly this:
+
+ my $buffer = ''; my $string = '';
+ while(read $fh, $buffer, 256, length($buffer)){
+ $string .= decode($encoding, $buffer, Encode::FB_QUIET);
+ # $buffer now contains the unprocessed partial character
}
=item I<CHECK> = Encode::FB_WARN
in the character repertoire of the encoding.
HTML/XML character reference modes are about the same, in place of
-C<\x{I<HHHH>}>, HTML uses C<&#I<NNNN>>; where I<NNNN> is a decimal digit and
-XML uses C<&#xI<HHHH>>; where I<HHHH> is the hexadecimal digit.
+C<\x{I<HHHH>}>, HTML uses C<&#I<NNN>;> where I<NNN> is a decimal number and
+XML uses C<&#xI<HHHH>;> where I<HHHH> is the hexadecimal number.
+
+In Encode 2.10 or later, C<LEAVE_SRC> is also implied.
=item The bitmask
DIE_ON_ERR 0x0001 X
WARN_ON_ERR 0x0002 X
RETURN_ON_ERR 0x0004 X X
- LEAVE_SRC 0x0008
+ LEAVE_SRC 0x0008 X
PERLQQ 0x0100 X
HTMLCREF 0x0200
XMLCREF 0x0400
-=head2 Unimplemented fallback schemes
+=back
+
+=head2 coderef for CHECK
-In the future, you will be able to use a code reference to a callback
-function for the value of I<CHECK> but its API is still undecided.
+As of Encode 2.12 CHECK can also be a code reference which takes the
+ord value of unmapped caharacter as an argument and returns a string
+that represents the fallback character. For instance,
-The fallback scheme does not work on EBCDIC platforms.
+ $ascii = encode("ascii", $utf8, sub{ sprintf "<U+%04X>", shift });
+
+Acts like FB_PERLQQ but E<lt>U+I<XXXX>E<gt> is used instead of
+\x{I<XXXX>}.
=head1 Defining Encodings
When you encode, the resulting utf8 flag is always off.
-=item
+=item *
When you decode, the resulting utf8 flag is on unless you can
unambiguously represent data. Here is the definition of
In any other Encoding ON
---------------------------------------------
-As you see, there is one exception, In ASCII. That way you can assue
+As you see, there is one exception, In ASCII. That way you can assume
Goal #1. And with Encode Goal #2 is assumed but you still have to be
careful in such cases mentioned in B<CAVEAT> paragraphs.
If CHECK is true, also checks the data in STRING for being well-formed
UTF-8. Returns true if successful, false otherwise.
+As of perl 5.8.1, L<utf8> also has utf8::is_utf8().
+
=item _utf8_on(STRING)
[INTERNAL] Turns on the UTF-8 flag in STRING. The data in STRING is
=back
+=head1 UTF-8 vs. utf8
+
+ ....We now view strings not as sequences of bytes, but as sequences
+ of numbers in the range 0 .. 2**32-1 (or in the case of 64-bit
+ computers, 0 .. 2**64-1) -- Programming Perl, 3rd ed.
+
+That has been the perl's notion of UTF-8 but official UTF-8 is more
+strict; Its ranges is much narrower (0 .. 10FFFF), some sequences are
+not allowed (i.e. Those used in the surrogate pair, 0xFFFE, et al).
+
+Now that is overruled by Larry Wall himself.
+
+ From: Larry Wall <larry@wall.org>
+ Date: December 04, 2004 11:51:58 JST
+ To: perl-unicode@perl.org
+ Subject: Re: Make Encode.pm support the real UTF-8
+ Message-Id: <20041204025158.GA28754@wall.org>
+
+ On Fri, Dec 03, 2004 at 10:12:12PM +0000, Tim Bunce wrote:
+ : I've no problem with 'utf8' being perl's unrestricted uft8 encoding,
+ : but "UTF-8" is the name of the standard and should give the
+ : corresponding behaviour.
+
+ For what it's worth, that's how I've always kept them straight in my
+ head.
+
+ Also for what it's worth, Perl 6 will mostly default to strict but
+ make it easy to switch back to lax.
+
+ Larry
+
+Do you copy? As of Perl 5.8.7, B<UTF-8> means strict, official UTF-8
+while B<utf8> means liberal, lax, version thereof. And Encode version
+2.10 or later thus groks the difference between C<UTF-8> and C"utf8".
+
+ encode("utf8", "\x{FFFF_FFFF}", 1); # okay
+ encode("UTF-8", "\x{FFFF_FFFF}", 1); # croaks
+
+C<UTF-8> in Encode is actually a canonical name for C<utf-8-strict>.
+Yes, the hyphen between "UTF" and "8" is important. Without it Encode
+goes "liberal"
+
+ find_encoding("UTF-8")->name # is 'utf-8-strict'
+ find_encoding("utf-8")->name # ditto. names are case insensitive
+ find_encoding("utf8")->name # ditto. "_" are treated as "-"
+ find_encoding("UTF8")->name # is 'utf8'.
+
+
=head1 SEE ALSO
L<Encode::Encoding>,