X-Git-Url: https://perl5.git.perl.org/perl5.git/blobdiff_plain/037b88d659e9f3d508c92490dc68052a82a1cbd6..63b38b604ef39ee14b693bccd8b54d416e832d2c:/ext/Encode/Encode.pm diff --git a/ext/Encode/Encode.pm b/ext/Encode/Encode.pm index d07bfea..fb80200 100644 --- a/ext/Encode/Encode.pm +++ b/ext/Encode/Encode.pm @@ -1,117 +1,74 @@ package Encode; use strict; -our $VERSION = do { my @r = (q$Revision: 1.1 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r }; +our $VERSION = do { my @r = (q$Revision: 1.52 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r }; our $DEBUG = 0; +use XSLoader (); +XSLoader::load 'Encode'; -require DynaLoader; require Exporter; - -our @ISA = qw(Exporter DynaLoader); +our @ISA = qw(Exporter); # Public, encouraged API is exported by default -our @EXPORT = qw ( - encode - decode - encode_utf8 - decode_utf8 - find_encoding - encodings + +our @EXPORT = qw( + decode decode_utf8 encode encode_utf8 + encodings find_encoding ); +our @FB_FLAGS = qw(DIE_ON_ERR WARN_ON_ERR RETURN_ON_ERR LEAVE_SRC PERLQQ); +our @FB_CONSTS = qw(FB_DEFAULT FB_QUIET FB_WARN FB_PERLQQ FB_CROAK); + our @EXPORT_OK = - qw( - define_encoding - from_to - is_utf8 - is_8bit - is_16bit - utf8_upgrade - utf8_downgrade - _utf8_on - _utf8_off - ); - -bootstrap Encode (); + ( + 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, + ); + +our %EXPORT_TAGS = + ( + all => [ @EXPORT, @EXPORT_OK ], + fallbacks => [ @FB_CONSTS ], + fallback_all => [ @FB_CONSTS, @FB_FLAGS ], + ); # Documentation moved after __END__ for speed - NI-S use Carp; 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 = - ( - viscii => 'Encode/Byte.pm', - 'koi8-r' => 'Encode/Byte.pm', - cp1047 => 'Encode/EBCDIC.pm', - cp37 => 'Encode/EBCDIC.pm', - 'posix-bc' => 'Encode/EBCDIC.pm', - symbol => 'Encode/Symbol.pm', - dingbats => 'Encode/Symbol.pm', - ); - -for my $k (2..11,13..16){ - $ExtModule{"iso-8859-$k"} = 'Encode/Byte.pm'; -} - -for my $k (1250..1258){ - $ExtModule{"cp$k"} = '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', - macjapan => 'Encode/JP.pm', - cp932 => 'Encode/JP.pm', - 'euc-kr' => 'Encode/KR.pm', - ksc5601 => 'Encode/KR.pm', - cp949 => 'Encode/KR.pm', - big5 => 'Encode/TW.pm', - 'big5-hkscs' => 'Encode/TW.pm', - cp950 => 'Encode/TW.pm', - gb18030 => 'Encode/HanExtra.pm', - big5plus => 'Encode/HanExtra.pm', - 'euc-tw' => 'Encode/HanExtra.pm', - ); -} - -for my $k (qw(centeuro croatian cyrillic dingbats greek - iceland roman rumanian sami - thai turkish ukraine)) -{ - $ExtModule{"mac$k"} = 'Encode/Byte.pm'; -} - +our %ExtModule; +require Encode::Config; +eval { require Encode::ConfigLocal }; sub encodings { my $class = shift; my @modules = (@_ and $_[0] eq ":all") ? values %ExtModule : @_; - for my $m (@modules) - { - $DEBUG and warn "about to require $m;"; - eval { require $m; }; + for my $mod (@modules){ + $mod =~ s,::,/,g or $mod = "Encode/$mod"; + $mod .= '.pm'; + $DEBUG and warn "about to require $mod;"; + eval { require $mod; }; } + my %modules = map {$_ => 1} @modules; return - map({$_->[0]} - sort({$a->[1] cmp $b->[1]} - map({[$_, lc $_]} - grep({ $_ ne 'Internal' } keys %Encoding)))); + sort { lc $a cmp lc $b } + grep {!/^(?:Internal|Unicode)$/o} keys %Encoding; +} + +sub perlio_ok{ + exists $INC{"PerlIO/encoding.pm"} or return 0; + my $stash = ref($_[0]); + $stash ||= ref(find_encoding($_[0])); + return ($stash eq "Encode::XS" || $stash eq "Encode::Unicode"); } sub define_encoding @@ -153,12 +110,14 @@ sub getEncoding $oc = $class->find_alias($lc) if $lc ne $name; return $oc if defined $oc; - if (!$skip_external and exists $ExtModule{$lc}) + unless ($skip_external) { - eval{ require $ExtModule{$lc}; }; - return $Encoding{$name} if exists $Encoding{$name}; + if (my $mod = $ExtModule{$name} || $ExtModule{$lc}){ + $mod =~ s,::,/,g ; $mod .= '.pm'; + eval{ require $mod; }; + return $Encoding{$name} if exists $Encoding{$name}; + } } - return; } @@ -168,9 +127,16 @@ sub find_encoding return __PACKAGE__->getEncoding($name,$skip_external); } -sub encode +sub resolve_alias { + my $obj = find_encoding(shift); + defined $obj and return $obj->name; + return; +} + +sub encode($$;$) { my ($name,$string,$check) = @_; + $check ||=0; my $enc = find_encoding($name); croak("Unknown encoding '$name'") unless defined $enc; my $octets = $enc->encode($string,$check); @@ -178,9 +144,10 @@ sub encode return $octets; } -sub decode +sub decode($$;$) { my ($name,$octets,$check) = @_; + $check ||=0; my $enc = find_encoding($name); croak("Unknown encoding '$name'") unless defined $enc; my $string = $enc->decode($octets,$check); @@ -188,41 +155,123 @@ sub decode return $string; } -sub from_to +sub from_to($$$;$) { my ($string,$from,$to,$check) = @_; + $check ||=0; my $f = find_encoding($from); croak("Unknown encoding '$from'") unless defined $f; my $t = find_encoding($to); croak("Unknown encoding '$to'") unless defined $t; my $uni = $f->decode($string,$check); return undef if ($check && length($string)); - $string = $t->encode($uni,$check); + $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 +sub encode_utf8($) { my ($str) = @_; - utf8::encode($str); + utf8::encode($str); return $str; } -sub decode_utf8 +sub decode_utf8($) { my ($str) = @_; return undef unless utf8::decode($str); return $str; } +predefine_encodings(); + +# +# This is to restore %Encoding if really needed; +# +sub predefine_encodings{ + if ($ON_EBCDIC) { + # was in Encode::UTF_EBCDIC + package Encode::UTF_EBCDIC; + *name = sub{ shift->{'Name'} }; + *new_sequence = sub{ return $_[0] }; + *decode = sub{ + my ($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 { + # was in Encode::UTF_EBCDIC + package Encode::Internal; + *name = sub{ shift->{'Name'} }; + *new_sequence = sub{ return $_[0] }; + *decode = sub{ + my ($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; + *name = sub{ shift->{'Name'} }; + *new_sequence = sub{ return $_[0] }; + *decode = sub{ + my ($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; + }; + $Encode::Encoding{utf8} = + bless {Name => "utf8"} => "Encode::utf8"; + } +} + require Encode::Encoding; -require Encode::XS; -require Encode::Internal; -require Encode::Unicode; -require Encode::utf8; -require Encode::10646_1; -require Encode::ucs2_le; +@Encode::XS::ISA = qw(Encode::Encoding); + +# This is very dodgy - PerlIO::encoding does "use Encode" and _BEFORE_ it gets a +# chance to set its VERSION we potentially delete it from %INC so it will be re-loaded +# NI-S +eval { + require PerlIO::encoding; + unless (PerlIO::encoding->VERSION >= 0.02){ + delete $INC{"PerlIO/encoding.pm"}; + } +}; +# warn $@ if $@; +@Encode::XS::ISA = qw(Encode::Encoding); 1; @@ -239,14 +288,14 @@ Encode - character encodings =head2 Table of Contents -Encode consists of a collection of modules which details are too big +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, +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::Alias Alias definitions to encodings Encode::Encoding Encode Implementation Base Class Encode::Supported List of Supported Encodings Encode::CN Simplified Chinese Encodings @@ -309,7 +358,7 @@ and such details may change in future releases. =over 4 -=item $bytes = encode(ENCODING, $string[, CHECK]) +=item $octets = encode(ENCODING, $string[, CHECK]) Encodes string from Perl's internal form into I and returns a sequence of octets. ENCODING can be either a canonical name or @@ -317,11 +366,11 @@ alias. For encoding names and aliases, see L. For CHECK see L. For example to convert (internally UTF-8 encoded) Unicode string to -iso-8859-1 (also known as Latin1), +iso-8859-1 (also known as Latin1), $octets = encode("iso-8859-1", $unicode); -=item $string = decode(ENCODING, $bytes[, CHECK]) +=item $string = decode(ENCODING, $octets[, CHECK]) Decode sequence of octets assumed to be in I into Perl's internal form and returns the resulting string. as in encode(), @@ -333,14 +382,9 @@ For example to convert ISO-8859-1 data to UTF-8: $utf8 = decode("iso-8859-1", $latin1); -=item from_to($string, FROM_ENCODING, TO_ENCODING[, CHECK]) - -Convert B the data between two encodings. How did the data -in $string originally get to be in FROM_ENCODING? Either using -encode() or through PerlIO: See L. -For encoding names and aliases, see L. -For CHECK see L. +=item [$length =] from_to($string, FROM_ENCODING, TO_ENCODING [,CHECK]) +Convert B the data between two encodings. For example to convert ISO-8859-1 data to UTF-8: from_to($data, "iso-8859-1", "utf-8"); @@ -352,6 +396,35 @@ and to convert it back: 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() return the length of the converted string on success, undef +otherwise. + +=back + +=head2 UTF-8 / utf8 + +The Unicode consortium defines the UTF-8 standard as a way of encoding +the entire Unicode repertoire as sequences of octets. This encoding is +expected to become very widespread. Perl can use this form internally +to represent strings, so conversions to and from this form are +particularly efficient (as octets in memory do not have to change, +just the meta-data that tells Perl how to treat them). + +=over 4 + +=item $octets = encode_utf8($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 $string = decode_utf8($octets [, CHECK]); + +The sequence of octets represented by $octets 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. + =back =head2 Listing available encodings @@ -367,14 +440,14 @@ ones that are not loaded yet, say Or you can give the name of specific module. - @with_jp = Encode->encodings("Encode/JP.pm"); + @with_jp = Encode->encodings("Encode::JP"); -Note in this case you have to say C<"Encode/JP.pm"> instead of -C<"Encode::JP">. +When "::" is not in the name, "Encode::" is assumed. -To find which encodings are supported by this package in details, -see L. + @ebcdic = Encode->encodings("EBCDIC"); +To find which encodings are supported by this package in details, +see L. =head2 Defining Aliases @@ -384,161 +457,123 @@ To add new alias to a given encoding, Use; use Encode::Alias; define_alias(newName => ENCODING); -After that, newName can be to be used as am alias for ENCODING. -ENCODING may be either the name of an encoding or and I - -See L on details. - -=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 provides a "layer" (See L) which can transform -data as it is read or written. - -Here is how the blind poet would modernise the encoding: +After that, newName can be used as an alias for ENCODING. +ENCODING may be either the name of an encoding or an +I - 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 $fh "Any \x{0021} string \N{SMILEY FACE}\n"; +But before you do so, make sure the alias is nonexistent with +C, which returns the canonical name thereof. +i.e. -Either of the above forms of "layer" specifications can be made the default -for a lexical scope with the C pragma. See L. + Encode::resolve_alias("latin1") eq "iso-8859-1" # true + Encode::resolve_alias("iso-8859-12") # false; nonexistent + Encode::resolve_alias($name) eq $name # true if $name is canonical -Once a handle is open is layers can be altered using C. +This resolve_alias() does not need C and is +exported via C. -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 and will C 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, C, ...). +See L on details. -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): +=head1 Encoding via PerlIO - open(F, "<:encoding(iso-8859-1)", "data.txt") or die $!; - open(G, ">:utf8", "data.utf") or die $!; - while () { print G } +If your perl supports I, you can use PerlIO layer to directly +decode and encode via filehandle. The following two examples are +totally identical by functionality. - # Could also do "print G " but that would pull - # the whole file into memory just to write it out again. + # via PerlIO + open my $in, "<:encoding(shiftjis)", $infile or die; + open my $out, ">:encoding(euc-jp)", $outfile or die; + while(<>){ print; } -More examples: + # via from_to + open my $in, $infile or die; + open my $out, $outfile or die; + while(<>){ + from_to($_, "shiftjis", "euc", 1); + } - open(my $f, "<:encoding(cp1252)") - open(my $g, ">:encoding(iso-8859-2)") - open(my $h, ">:encoding(latin9)") # iso-8859-15 +Unfortunately, not all encodings are PerlIO-savvy. You can check if +your encoding is supported by PerlIO by C method. -See L for more information. + Encode::perlio_ok("iso-20220jp"); # false + find_encoding("iso-2022-jp")->perlio_ok; # false + use Encode qw(perlio_ok); # exported upon request + perlio_ok("euc-jp") # true if PerlIO is enabled -See also L for how to change the default encoding of the -data in your script. +For gory details, see L; =head1 Handling Malformed Data -If CHECK is not set, C 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. - -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 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. - =over 4 -=item Scheme 1 +THE I argument is used as follows. When you omit it, it is +identical to I = 0. -Passed remaining fragment of string being processed. -Modifies it in place to remove bytes/characters it can understand -and returns a string used to represent them. -e.g. +=item I = Encode::FB_DEFAULT ( == 0) - sub fixup { - my $ch = substr($_[0],0,1,''); - return sprintf("\x{%02X}",ord($ch); - } +If I is 0, (en|de)code will put I in +place of the malformed character. for UCM-based encodings, +EsubcharE will be used. For Unicode, \xFFFD is used. If the +data is supposed to be UTF-8, an optional lexical warning (category +utf8) is given. -This scheme is close to how underlying C code for Encode works, but gives -the fixup routine very little context. +=item I = Encode::DIE_ON_ERROR (== 1) -=item Scheme 2 +If I is 1, methods will die immediately with an error +message. so when I is set, you should trap the fatal error +with eval{} unless you really want to let it die on error. -Passed original string, and an index into it of the problem area, and -output string so far. Appends what it will to output string and -returns new index into original string. For example: +=item I = Encode::FB_QUIET - sub fixup { - # my ($s,$i,$d) = @_; - my $ch = substr($_[0],$_[1],1); - $_[2] .= sprintf("\x{%02X}",ord($ch); - return $_[1]+1; - } +If I is set to Encode::FB_QUIET, (en|de)code will immediately +return processed part on error, with data passed via argument +overwritten with unprocessed part. This is handy when have to +repeatedly call because the source data is chopped in the middle for +some reasons, such as fixed-width buffer. Here is a sample code that +just does this. -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. + my $data = ''; + while(defined(read $fh, $buffer, 256)){ + # buffer may end in partial character so we append + $data .= $buffer; + $utf8 .= decode($encoding, $data, ENCODE::FB_QUIET); + # $data now contains unprocessed partial character + } -=item Other Schemes +=item I = Encode::FB_WARN -Hybrids of above. +This is the same as above, except it warns on error. Handy when you +are debugging the mode above. -Multiple return values rather than in-place modifications. +=item perlqq mode (I = Encode::FB_PERLQQ) -Index into the string could be C allowing C. +For encodings that are implemented by Encode::XS, CHECK == +Encode::FB_PERLQQ turns (en|de)code into C fallback mode. -=back +When you decode, '\xI' will be placed where I is the hex +representation of the octet that could not be decoded to utf8. And +when you encode, '\x{I}' will be placed where I is the +Unicode ID of the character that cannot be found in the character +repertoire of the encoding. -=head2 UTF-8 / utf8 +=item The bitmask -The Unicode consortium defines the UTF-8 standard as a way of encoding -the entire Unicode repertoire as sequences of octets. This encoding is -expected to become very widespread. Perl can use this form internally -to represent strings, so conversions to and from this form are -particularly efficient (as octets in memory do not have to change, -just the meta-data that tells Perl how to treat them). +These modes are actually set via bitmask. here is how FB_XX are laid +out. for FB_XX you can import via C for +generic bitmask constants, you can import via + C. -=over 4 + FB_DEFAULT FB_CROAK FB_QUIET FB_WARN FB_PERLQQ + DIE_ON_ERR 0x0001 X + WARN_ON_ER 0x0002 X + RETURN_ON_ERR 0x0004 X X + LEAVE_SRC 0x0008 + PERLQQ 0x0100 X -=item $bytes = encode_utf8($string); +=head2 Unemplemented fallback schemes -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]); - -The sequence of octets represented by $bytes is decoded from UTF-8 -into a sequence of logical characters. Not all sequences of octets -form valid UTF-8 encodings, so it is possible for this call to fail. -For CHECK see L. - -=back +In future you will be able to use a code reference to a callback +function for the value of I but its API is still undecided. =head1 Defining Encodings @@ -552,6 +587,8 @@ should provide the interface described in L If more than two arguments are provided then additional arguments are taken as aliases for I<$object> as for C. +See L for more details. + =head1 Messing with Perl's Internals The following API uses parts of Perl's internals in the current @@ -586,12 +623,19 @@ not a string. L, L, -L, +L, L, -L, -L, -L, -L, +L, +L, +L, +L, the Perl Unicode Mailing List Eperl-unicode@perl.orgE +=head1 MAINTAINER + +This project was originated by Nick Ing-Simmons and later maintained +by Dan Kogai Edankogai@dan.co.jpE. See AUTHORS for full list +of people involved. For any questions, use +Eperl-unicode@perl.orgE so others can share. + =cut