X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=blobdiff_plain;f=ext%2FEncode%2FEncode.pm;h=ae047553bdbe8ee220e7676363f606c51087faf8;hb=2a5d9b1d41e4bafaa26126c5dea2f6ff0b72b6a7;hp=9b45b7b120a3bd11bcc80dd95e2010b265f0b616;hpb=56ff73747e9362a483df0d73a430e0cb83ff0e6b;p=p5sagit%2Fp5-mst-13.2.git diff --git a/ext/Encode/Encode.pm b/ext/Encode/Encode.pm index 9b45b7b..ae04755 100644 --- a/ext/Encode/Encode.pm +++ b/ext/Encode/Encode.pm @@ -1,12 +1,13 @@ # -# $Id: Encode.pm,v 2.11 2005/08/05 10:58:25 dankogai Exp dankogai $ +# $Id: Encode.pm,v 2.18 2006/06/03 20:28:48 dankogai Exp dankogai $ # package Encode; use strict; -our $VERSION = sprintf "%d.%02d", q$Revision: 2.11 $ =~ /(\d+)/g; +use warnings; +our $VERSION = "2.18_01"; sub DEBUG () { 0 } use XSLoader (); -XSLoader::load(__PACKAGE__, $VERSION); +XSLoader::load( __PACKAGE__, $VERSION ); require Exporter; use base qw/Exporter/; @@ -14,34 +15,34 @@ use base qw/Exporter/; # Public, encouraged API is exported by default our @EXPORT = qw( - decode decode_utf8 encode encode_utf8 + decode decode_utf8 encode encode_utf8 str2bytes bytes2str encodings find_encoding clone_encoding ); - -our @FB_FLAGS = qw(DIE_ON_ERR WARN_ON_ERR RETURN_ON_ERR LEAVE_SRC - PERLQQ HTMLCREF XMLCREF STOP_AT_PARTIAL); -our @FB_CONSTS = qw(FB_DEFAULT FB_CROAK FB_QUIET FB_WARN - FB_PERLQQ FB_HTMLCREF FB_XMLCREF); - -our @EXPORT_OK = - ( - qw( - _utf8_off _utf8_on define_encoding from_to is_16bit is_8bit - is_utf8 perlio_ok resolve_alias utf8_downgrade utf8_upgrade +our @FB_FLAGS = qw( + DIE_ON_ERR WARN_ON_ERR RETURN_ON_ERR LEAVE_SRC + PERLQQ HTMLCREF XMLCREF STOP_AT_PARTIAL +); +our @FB_CONSTS = qw( + FB_DEFAULT FB_CROAK FB_QUIET FB_WARN + FB_PERLQQ FB_HTMLCREF FB_XMLCREF +); +our @EXPORT_OK = ( + qw( + _utf8_off _utf8_on define_encoding from_to is_16bit is_8bit + is_utf8 perlio_ok resolve_alias utf8_downgrade utf8_upgrade ), - @FB_FLAGS, @FB_CONSTS, - ); + @FB_FLAGS, @FB_CONSTS, +); -our %EXPORT_TAGS = - ( - all => [ @EXPORT, @EXPORT_OK ], - fallbacks => [ @FB_CONSTS ], - fallback_all => [ @FB_CONSTS, @FB_FLAGS ], - ); +our %EXPORT_TAGS = ( + all => [ @EXPORT, @EXPORT_OK ], + fallbacks => [@FB_CONSTS], + fallback_all => [ @FB_CONSTS, @FB_FLAGS ], +); # Documentation moved after __END__ for speed - NI-S -our $ON_EBCDIC = (ord("A") == 193); +our $ON_EBCDIC = ( ord("A") == 193 ); use Encode::Alias; @@ -51,49 +52,46 @@ our %ExtModule; require Encode::Config; eval { require Encode::ConfigLocal }; -sub encodings -{ +sub encodings { my $class = shift; my %enc; - if (@_ and $_[0] eq ":all"){ - %enc = ( %Encoding, %ExtModule ); - }else{ - %enc = %Encoding; - for my $mod (map {m/::/o ? $_ : "Encode::$_" } @_){ - DEBUG and warn $mod; - for my $enc (keys %ExtModule){ - $ExtModule{$enc} eq $mod and $enc{$enc} = $mod; - } - } + if ( @_ and $_[0] eq ":all" ) { + %enc = ( %Encoding, %ExtModule ); + } + else { + %enc = %Encoding; + for my $mod ( map { m/::/o ? $_ : "Encode::$_" } @_ ) { + DEBUG and warn $mod; + for my $enc ( keys %ExtModule ) { + $ExtModule{$enc} eq $mod and $enc{$enc} = $mod; + } + } } - return - sort { lc $a cmp lc $b } - grep {!/^(?:Internal|Unicode|Guess)$/o} keys %enc; + return sort { lc $a cmp lc $b } + grep { !/^(?:Internal|Unicode|Guess)$/o } keys %enc; } -sub perlio_ok{ - my $obj = ref($_[0]) ? $_[0] : find_encoding($_[0]); +sub perlio_ok { + my $obj = ref( $_[0] ) ? $_[0] : find_encoding( $_[0] ); $obj->can("perlio_ok") and return $obj->perlio_ok(); - return 0; # safety net + return 0; # safety net } -sub define_encoding -{ +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); + define_alias( $lc => $obj ) unless $lc eq $name; + while (@_) { + my $alias = shift; + define_alias( $alias, $obj ); } return $obj; } -sub getEncoding -{ - my ($class, $name, $skip_external) = @_; +sub getEncoding { + my ( $class, $name, $skip_external ) = @_; ref($name) && $name->can('renew') and return $name; exists $Encoding{$name} and return $Encoding{$name}; @@ -105,30 +103,29 @@ sub getEncoding $lc ne $name and $oc = $class->find_alias($lc); defined($oc) and return $oc; - unless ($skip_external) - { - if (my $mod = $ExtModule{$name} || $ExtModule{$lc}){ - $mod =~ s,::,/,g ; $mod .= '.pm'; - eval{ require $mod; }; - exists $Encoding{$name} and return $Encoding{$name}; - } + unless ($skip_external) { + if ( my $mod = $ExtModule{$name} || $ExtModule{$lc} ) { + $mod =~ s,::,/,g; + $mod .= '.pm'; + eval { require $mod; }; + exists $Encoding{$name} and return $Encoding{$name}; + } } return; } -sub find_encoding($;$) -{ - my ($name, $skip_external) = @_; - return __PACKAGE__->getEncoding($name,$skip_external); +sub find_encoding($;$) { + 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 $obj->name; return; } -sub clone_encoding($){ +sub clone_encoding($) { my $obj = find_encoding(shift); ref $obj or return; eval { require Storable }; @@ -136,75 +133,73 @@ sub clone_encoding($){ return Storable::dclone($obj); } -sub encode($$;$) -{ - my ($name, $string, $check) = @_; +sub encode($$;$) { + my ( $name, $string, $check ) = @_; return undef unless defined $string; - $string .= '' if ref $string; # stringify; - $check ||=0; + $string .= '' if ref $string; # stringify; + $check ||= 0; my $enc = find_encoding($name); - unless(defined $enc){ - require Carp; - Carp::croak("Unknown encoding '$name'"); + unless ( defined $enc ) { + require Carp; + Carp::croak("Unknown encoding '$name'"); } - my $octets = $enc->encode($string,$check); - $_[1] = $string if $check and !($check & LEAVE_SRC()); + my $octets = $enc->encode( $string, $check ); + $_[1] = $string if $check and !( $check & LEAVE_SRC() ); return $octets; } +*str2bytes = \&encode; -sub decode($$;$) -{ - my ($name,$octets,$check) = @_; +sub decode($$;$) { + my ( $name, $octets, $check ) = @_; return undef unless defined $octets; $octets .= '' if ref $octets; - $check ||=0; + $check ||= 0; my $enc = find_encoding($name); - unless(defined $enc){ - require Carp; - Carp::croak("Unknown encoding '$name'"); + unless ( defined $enc ) { + require Carp; + Carp::croak("Unknown encoding '$name'"); } - my $string = $enc->decode($octets,$check); - $_[1] = $octets if $check and !($check & LEAVE_SRC()); + my $string = $enc->decode( $octets, $check ); + $_[1] = $octets if $check and !( $check & LEAVE_SRC() ); return $string; } +*bytes2str = \&decode; -sub from_to($$$;$) -{ - my ($string,$from,$to,$check) = @_; +sub from_to($$$;$) { + my ( $string, $from, $to, $check ) = @_; return undef unless defined $string; - $check ||=0; + $check ||= 0; my $f = find_encoding($from); - unless (defined $f){ - require Carp; - Carp::croak("Unknown encoding '$from'"); + unless ( defined $f ) { + require Carp; + Carp::croak("Unknown encoding '$from'"); } my $t = find_encoding($to); - unless (defined $t){ - require Carp; - Carp::croak("Unknown encoding '$to'"); + unless ( defined $t ) { + require Carp; + Carp::croak("Unknown encoding '$to'"); } - my $uni = $f->decode($string,$check); - return undef if ($check && length($string)); - $string = $t->encode($uni,$check); - return undef if ($check && length($uni)); - return defined($_[0] = $string) ? length($string) : undef ; + my $uni = $f->decode($string); + $_[0] = $string = $t->encode( $uni, $check ); + return undef if ( $check && length($uni) ); + return defined( $_[0] ) ? length($string) : undef; } -sub encode_utf8($) -{ +sub encode_utf8($) { my ($str) = @_; utf8::encode($str); return $str; } -sub decode_utf8($;$) -{ - my ($str, $check) = @_; - if ($check){ - return decode("utf8", $str, $check); - }else{ - return decode("utf8", $str); - return $str; +sub decode_utf8($;$) { + my ( $str, $check ) = @_; + return $str if is_utf8($str); + if ($check) { + return decode( "utf8", $str, $check ); + } + else { + return decode( "utf8", $str ); + return $str; } } @@ -214,94 +209,107 @@ predefine_encodings(1); # This is to restore %Encoding if really needed; # -sub predefine_encodings{ +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; - push @Encode::UTF_EBCDIC::ISA, 'Encode::Encoding'; - *decode = sub{ - my ($obj,$str,$chk) = @_; - my $res = ''; - for (my $i = 0; $i < length($str); $i++) { - $res .= - chr(utf8::unicode_to_native(ord(substr($str,$i,1)))); - } - $_[1] = '' if $chk; - return $res; - }; - *encode = sub{ - my ($obj,$str,$chk) = @_; - my $res = ''; - for (my $i = 0; $i < length($str); $i++) { - $res .= - chr(utf8::native_to_unicode(ord(substr($str,$i,1)))); - } - $_[1] = '' if $chk; - return $res; - }; - $Encode::Encoding{Unicode} = - bless {Name => "UTF_EBCDIC"} => "Encode::UTF_EBCDIC"; - } else { - package Encode::Internal; - push @Encode::Internal::ISA, 'Encode::Encoding'; - *decode = sub{ - my ($obj,$str,$chk) = @_; - utf8::upgrade($str); - $_[1] = '' if $chk; - return $str; - }; - *encode = \&decode; - $Encode::Encoding{Unicode} = - bless {Name => "Internal"} => "Encode::Internal"; + + # was in Encode::UTF_EBCDIC + package Encode::UTF_EBCDIC; + push @Encode::UTF_EBCDIC::ISA, 'Encode::Encoding'; + *decode = sub { + my ( $obj, $str, $chk ) = @_; + my $res = ''; + for ( my $i = 0 ; $i < length($str) ; $i++ ) { + $res .= + chr( + utf8::unicode_to_native( ord( substr( $str, $i, 1 ) ) ) + ); + } + $_[1] = '' if $chk; + return $res; + }; + *encode = sub { + my ( $obj, $str, $chk ) = @_; + my $res = ''; + for ( my $i = 0 ; $i < length($str) ; $i++ ) { + $res .= + chr( + utf8::native_to_unicode( ord( substr( $str, $i, 1 ) ) ) + ); + } + $_[1] = '' if $chk; + return $res; + }; + $Encode::Encoding{Unicode} = + bless { Name => "UTF_EBCDIC" } => "Encode::UTF_EBCDIC"; + } + else { + + package Encode::Internal; + push @Encode::Internal::ISA, 'Encode::Encoding'; + *decode = sub { + my ( $obj, $str, $chk ) = @_; + utf8::upgrade($str); + $_[1] = '' if $chk; + return $str; + }; + *encode = \&decode; + $Encode::Encoding{Unicode} = + bless { Name => "Internal" } => "Encode::Internal"; } { - # was in Encode::utf8 - package Encode::utf8; - push @Encode::utf8::ISA, 'Encode::Encoding'; - # - if ($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 $octets; - }; - } - *cat_decode = sub{ # ($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; - } - $$rdst .= substr($$rsrc, $pos); - $$rpos = length($$rsrc); - return ''; - }; - $Encode::Encoding{utf8} = - bless {Name => "utf8"} => "Encode::utf8"; - $Encode::Encoding{"utf-8-strict"} = - bless {Name => "utf-8-strict", strict_utf8 => 1 } => "Encode::utf8"; + + # was in Encode::utf8 + package Encode::utf8; + push @Encode::utf8::ISA, 'Encode::Encoding'; + + # + if ($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 $octets; + }; + } + *cat_decode = sub { # ($obj, $dst, $src, $pos, $trm, $chk) + # currently ignores $chk + my ( $obj, undef, undef, $pos, $trm ) = @_; + 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; + } + $$rdst .= substr( $$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"; } } @@ -557,8 +565,11 @@ L and L. =head1 Handling Malformed Data -The optional I argument is used as follows. When you omit it, -Encode::FB_DEFAULT ( == 0 ) is assumed. +The optional I 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 @@ -648,12 +659,16 @@ constants via C. =back -=head2 Unimplemented fallback schemes +=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 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 "", shift }); + +Acts like FB_PERLQQ but EU+IE is used instead of +\x{I}. =head1 Defining Encodings @@ -799,7 +814,7 @@ Now that is overruled by Larry Wall himself. 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. @@ -818,7 +833,7 @@ 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("utf_8")->name # ditto. "_" are treated as "-" find_encoding("UTF8")->name # is 'utf8'. @@ -841,4 +856,15 @@ by Dan Kogai Edankogai@dan.co.jpE. See AUTHORS for a full list of people involved. For any questions, use Eperl-unicode@perl.orgE so we can all share. +While Dan Kogai retains the copyright as a maintainer, the credit +should go to all those involoved. See AUTHORS for those submitted +codes. + +=head1 COPYRIGHT + +Copyright 2002-2006 Dan Kogai Edankogai@dan.co.jpE + +This library is free software; you can redistribute it and/or modify +it under the same terms as Perl itself. + =cut