X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=blobdiff_plain;f=ext%2FEncode%2FEncode.pm;h=b502e8fdc469a5a8570ac4f7af7e60ae9ce6499b;hb=7e19fb92789b07f9ae6ba1ee1b4f5fbb72612161;hp=267df8ecae7702b1d091fe5841d86f9634406441;hpb=48e3bbddf569369fe6921f305df6ab7290c91152;p=p5sagit%2Fp5-mst-13.2.git diff --git a/ext/Encode/Encode.pm b/ext/Encode/Encode.pm index 267df8e..b502e8f 100644 --- a/ext/Encode/Encode.pm +++ b/ext/Encode/Encode.pm @@ -1,117 +1,75 @@ package Encode; use strict; -our $VERSION = do { my @r = (q$Revision: 1.0 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r }; +our $VERSION = do { my @r = (q$Revision: 1.61 $ =~ /\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); +use base 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 HTMLCREF XMLCREF); +our @FB_CONSTS = qw(FB_DEFAULT FB_CROAK FB_QUIET FB_WARN + FB_PERLQQ FB_HTMLCREF FB_XMLCREF); + 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{ + my $obj = ref($_[0]) ? $_[0] : find_encoding($_[0]); + $obj->can("perlio_ok") and return $obj->perlio_ok(); + return 0; # safety net } sub define_encoding @@ -153,12 +111,14 @@ 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 +128,16 @@ 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($$;$) { my ($name,$string,$check) = @_; + $check ||=0; my $enc = find_encoding($name); croak("Unknown encoding '$name'") unless defined $enc; my $octets = $enc->encode($string,$check); @@ -178,9 +145,10 @@ sub encode return $octets; } -sub decode +sub decode($$;$) { my ($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 +156,123 @@ 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 $str; } -require Encode::Encoding; -require Encode::XS; -require Encode::Internal; -require Encode::Unicode; -require Encode::utf8; -require Encode::10646_1; -require Encode::ucs2_le; +predefine_encodings(); + +# +# This is to restore %Encoding if really needed; +# +sub predefine_encodings{ + if ($ON_EBCDIC) { + # was in Encode::UTF_EBCDIC + package Encode::UTF_EBCDIC; + *name = sub{ shift->{'Name'} }; + *new_sequence = sub{ return $_[0] }; + *needs_lines = sub{ 0 }; + *perlio_ok = sub { + eval{ require PerlIO::encoding }; + return $@ ? 0 : 1; + }; + *decode = sub{ + my ($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] }; + *needs_lines = sub{ 0 }; + *perlio_ok = sub { + eval{ require PerlIO::encoding }; + return $@ ? 0 : 1; + }; + *decode = sub{ + my ($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] }; + *needs_lines = sub{ 0 }; + *perlio_ok = sub { + eval{ require PerlIO::encoding }; + return $@ ? 0 : 1; + }; + *decode = sub{ + my ($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"; + } +} 1; @@ -236,17 +286,16 @@ Encode - character encodings use Encode; - =head2 Table of Contents -Encode consists of a collection of modules which details are too big +Encode consists of a collection of modules whose 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; +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 @@ -268,21 +317,21 @@ 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). -Traditionally 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 +languages but also "binary" data being the machine's representation of numbers, pixels in an image - or just about anything. -When Perl is processing "binary data" the programmer wants Perl to +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 +byte has 256 possible values, it easily fits in Perl's much larger "logical character". =head2 TERMINOLOGY -=over 4 +=over 2 =item * @@ -297,7 +346,7 @@ I: a character in the range 0..255 =item * I: 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. a disk file.) =back @@ -307,50 +356,89 @@ and such details may change in future releases. =head1 PERL ENCODING API -=over 4 +=over 2 -=item $bytes = encode(ENCODING, $string[, CHECK]) +=item $octets = encode(ENCODING, $string[, CHECK]) -Encodes string from Perl's internal form into I and returns +Encodes a string from Perl's internal form into I and returns a sequence of octets. ENCODING can be either a canonical name or -alias. For encoding names and aliases, see L. -For CHECK see L. +an 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), -For example to convert (internally UTF-8 encoded) Unicode string to -iso-8859-1 (also known as Latin1), + $octets = encode("iso-8859-1", $utf8); - $octets = encode("iso-8859-1", $unicode); +B: When you C<$octets = encode("utf8", $utf8)>, then $octets +B $utf8. Though they both contain the same data, the utf8 flag +for $octets is B off. When you encode anything, utf8 flag of +the result is always off, even when it contains completely valid utf8 +string. See L below. -=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(), -ENCODING can be either a canonical name or alias. For encoding names -and aliases, see L. For CHECK see +Decodes a sequence of octets assumed to be in I into Perl's +internal form and returns the resulting string. As in encode(), +ENCODING can be either a canonical name or an alias. For encoding names +and aliases, see L. For CHECK, see L. -For example to convert ISO-8859-1 data to UTF-8: +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]) +B: When you C<$utf8 = encode("utf8", $octets)>, then $utf8 +B $utf8. Though they both contain the same data, +the utf8 flag for $utf8 is on unless $octets entirely conststs of +ASCII data (or EBCDIC on EBCDIC machines). See L +below. -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($string, FROM_ENC, TO_ENC [, CHECK]) -For example to convert ISO-8859-1 data to UTF-8: +Converts B data between two encodings. For example, to +convert ISO-8859-1 data to UTF-8: - from_to($data, "iso-8859-1", "utf-8"); + from_to($data, "iso-8859-1", "utf8"); and to convert it back: - from_to($data, "utf-8", "iso-8859-1"); + from_to($data, "utf8", "iso-8859-1"); Note that because the conversion happens in place, the data to be -converted cannot be a string constant, it must be a scalar variable. +converted cannot be a string constant; it must be a scalar variable. + +from_to() returns the length of the converted string on success, undef +otherwise. + +B: The following operations look the same but not quite so; + + from_to($data, "iso-8859-1", "utf8"); #1 + $data = decode("iso-8859-1", $data); #2 + +Both #1 and #2 makes $data consists of completely valid UTF-8 string +but only #2 turns utf8 flag on. #1 is equivalent to + + $data = encode("utf8", decode("iso-8859-1", $data)); + +See L below. + +=item $octets = encode_utf8($string); + +Equivalent to C<$octets = encode("utf8", $string);> The characters +that comprise $string are encoded in Perl's superset of UTF-8 and the +resulting octets are 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]); + +equivalent to C<$string = decode("utf8", $octets [, CHECK])>. +decode_utf8($octets [, CHECK]); The sequence of octets represented by +$octets is decoded from UTF-8 into a sequence of logical +characters. Not all sequences of octets form valid UTF-8 encodings, so +it is possible for this call to fail. For CHECK, see +L. =back @@ -365,219 +453,273 @@ ones that are not loaded yet, say @all_encodings = Encode->encodings(":all"); -Or you can give the name of specific module. +Or you can give the name of a specific module. - @with_jp = Encode->encodings("Encode/JP.pm"); + @with_jp = Encode->encodings("Encode::JP"); -Note in this case you have to say C<"Encode/JP.pm"> instead of -C<"Encode::JP">. +When "::" is not in the name, "Encode::" is assumed. -To find which encodings are supported by this package in details, -see L. + @ebcdic = Encode->encodings("EBCDIC"); +To find out in detail which encodings are supported by this package, +see L. =head2 Defining Aliases -To add new alias to a given encoding, Use; +To add a new alias to a given encoding, use: use Encode; use Encode::Alias; define_alias(newName => ENCODING); -After that, newName can be to be used as am alias for ENCODING. -ENCODING may be either the name of an encoding or and I +After that, newName can be used as an alias for ENCODING. +ENCODING may be either the name of an encoding or an +I -See L on details. +But before you do so, make sure the alias is nonexistent with +C, which returns the canonical name thereof. +i.e. -=head1 Encoding and IO + Encode::resolve_alias("latin1") eq "iso-8859-1" # true + Encode::resolve_alias("iso-8859-12") # false; nonexistent + Encode::resolve_alias($name) eq $name # true if $name is canonical -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. +resolve_alias() does not need C; it can be +exported via C. -Here is how the blind poet would modernise the encoding: +See L for details. - 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); +=head1 Encoding via PerlIO -In addition the new IO system can also be configured to read/write -UTF-8 encoded characters (as noted above this is efficient): +If your perl supports I, you can use a PerlIO layer to decode +and encode directly via a filehandle. The following two examples +are totally identical in their functionality. - open(my $fh,'>:utf8','anything'); - print $fh "Any \x{0021} string \N{SMILEY FACE}\n"; + # via PerlIO + open my $in, "<:encoding(shiftjis)", $infile or die; + open my $out, ">:encoding(euc-jp)", $outfile or die; + while(<>){ print; } -Either of the above forms of "layer" specifications can be made the default -for a lexical scope with the C pragma. See L. + # via from_to + open my $in, "<", $infile or die; + open my $out, ">", $outfile or die; + while(<>){ + from_to($_, "shiftjis", "euc-jp", 1); + } -Once a handle is open is layers can be altered using C. +Unfortunately, there may be encodings are PerlIO-savvy. You can check +if your encoding is supported by PerlIO by calling the C +method. -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. + Encode::perlio_ok("hz"); # False + find_encoding("euc-cn")->perlio_ok; # True where PerlIO is available -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, ...). + use Encode qw(perlio_ok); # exported upon request + perlio_ok("euc-jp") -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): +Fortunately, all encodings that come with Encode core are PerlIO-savvy +except for hz and ISO-2022-kr. See L for details. - open(F, "<:encoding(iso-8859-1)", "data.txt") or die $!; - open(G, ">:utf8", "data.utf") or die $!; - while () { print G } +For gory details, see L. - # Could also do "print G " but that would pull - # the whole file into memory just to write it out again. +=head1 Handling Malformed Data -More examples: +=over 2 - open(my $f, "<:encoding(cp1252)") - open(my $g, ">:encoding(iso-8859-2)") - open(my $h, ">:encoding(latin9)") # iso-8859-15 +The I 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. -See L for more information. +=item I = Encode::FB_DEFAULT ( == 0) -See also L for how to change the default encoding of the -data in your script. +If I is 0, (en|de)code will put a I +in place of a malformed character. For UCM-based encodings, +EsubcharE will be used. For Unicode, "\x{FFFD}" is used. +If the data is supposed to be UTF-8, an optional lexical warning +(category utf8) is given. -=head1 Handling Malformed Data +=item I = Encode::FB_CROAK ( == 1) -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. +If I is 1, methods will die immediately with an error +message. Therefore, when I is set to 1, you should trap the +fatal error with eval{} unless you really want to let it die on error. -It would desirable to have a way to indicate that transform should use -the encodings "replacement character" - no such mechanism is defined yet. +=item I = Encode::FB_QUIET -It is also planned to allow I to be a code reference. +If I 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: -This is not yet implemented as there are design issues with what its -arguments should be and how it returns its results. + my $data = ''; + 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 + } -=over 4 +=item I = Encode::FB_WARN -=item Scheme 1 +This is the same as above, except that it warns on error. Handy when +you are debugging the mode above. -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 perlqq mode (I = Encode::FB_PERLQQ) - sub fixup { - my $ch = substr($_[0],0,1,''); - return sprintf("\x{%02X}",ord($ch); - } +=item HTML charref mode (I = Encode::FB_HTMLCREF) -This scheme is close to how underlying C code for Encode works, but gives -the fixup routine very little context. +=item XML charref mode (I = Encode::FB_XMLCREF) -=item Scheme 2 +For encodings that are implemented by Encode::XS, CHECK == +Encode::FB_PERLQQ turns (en|de)code into C fallback mode. -Passed original string, and an index into it of the problem area, and -output string so far. Appends what it will to output string and -returns new index into original string. For example: +When you decode, '\xI' will be inserted for a malformed character, +where I is the hex representation of the octet that could not be +decoded to utf8. And when you encode, '\x{I}' will be inserted, +where I is the Unicode ID of the character that cannot be found +in the character repertoire of the encoding. - sub fixup { - # my ($s,$i,$d) = @_; - my $ch = substr($_[0],$_[1],1); - $_[2] .= sprintf("\x{%02X}",ord($ch); - return $_[1]+1; - } +HTML/XML character reference modes are about the same, in place of +\x{I}, HTML uses &#I<1234>; where I<1234> is a decimal digit and +XML uses &#xI; where I is the hexadecimal digit. -This scheme gives maximal control to the fixup routine but is more -complicated to code, and may need internals of Encode to be tweaked to -keep original string intact. +=item The bitmask -=item Other Schemes +These modes are actually set via a bitmask. Here is how the FB_XX +constants are laid out. You can import the FB_XX constants via +C; you can import the generic bitmask +constants via C. -Hybrids of above. + FB_DEFAULT FB_CROAK FB_QUIET FB_WARN FB_PERLQQ + DIE_ON_ERR 0x0001 X + WARN_ON_ER 0x0002 X + RETURN_ON_ERR 0x0004 X X + LEAVE_SRC 0x0008 + PERLQQ 0x0100 X + HTMLCREF 0x0200 + XMLCREF 0x0400 -Multiple return values rather than in-place modifications. +=head2 Unimplemented fallback schemes -Index into the string could be C allowing C. +In the future, you will be able to use a code reference to a callback +function for the value of I but its API is still undecided. -=back +=head1 Defining Encodings -=head2 UTF-8 / utf8 +To define a new encoding, use: -The Unicode consortium defines the UTF-8 standard as a way of encoding -the entire Unicode repertoire as sequences of octets. This encoding is -expected to become very widespread. Perl can use this form internally -to represent strings, so conversions to and from this form are -particularly efficient (as octets in memory do not have to change, -just the meta-data that tells Perl how to treat them). + use Encode qw(define_alias); + define_encoding($object, 'canonicalName' [, alias...]); -=over 4 +I will be associated with I<$object>. The object +should provide the interface described in L. +If more than two arguments are provided then additional +arguments are taken as aliases for I<$object>, as for C. -=item $bytes = encode_utf8($string); +See L for more details. -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. +=head1 The UTF-8 flag + +Before the introduction of utf8 support in perl, The C operator +just compares internal data of the scalars. Now C means internal +data equality AND I. To explain why we made it so, I +will quote page 402 of C + +=over 2 + +=item Goal #1: + +Old byte-oriented programs should not spontaneously break on the old +byte-oriented data they used to work on. -=item $string = decode_utf8($bytes [, CHECK]); +=item Goal #2: -The sequence of octets represented by $bytes is decoded from UTF-8 -into a sequence of logical characters. Not all sequences of octets -form valid UTF-8 encodings, so it is possible for this call to fail. -For CHECK see L. +Old byte-oriented programs should magically start working on the new +character-oriented data when appropriate. + +=item Goal #3: + +Programs should run just as fast in the new character-oriented mode +as in the old byte-oriented mode. + +=item Goal #4: + +Perl should remain one language, rather than forking into a +byte-oriented Perl and a character-oriented Perl. =back -=head1 Defining Encodings +Back when C was written, not even Perl 5.6.0 +was born and many features documented in the book remained +unimplemented. Perl 5.8 hopefully correct this and the introduction +of UTF-8 flag is one of them. You can think this perl notion of +byte-oriented mode (utf8 flag off) and character-oriented mode (utf8 +flag on). -To define a new encoding, use: +Here is how Encode takes care of the utf8 flag. - use Encode qw(define_alias); - define_encoding($object, 'canonicalName' [, alias...]); +=over2 -I will be associated with I<$object>. The object -should provide the interface described in L -If more than two arguments are provided then additional -arguments are taken as aliases for I<$object> as for C. +=item * -=head1 Messing with Perl's Internals +When you encode, the resulting utf8 flag is always off. + +=item + +When you decode, the resuting utf8 flag is on unless you can +unambiguously represent data. Here is the definition of +dis-ambiguity. + + After C<$utf8 = decode('foo', $octet);>, + + When $octet is... The utf8 flag in $utf8 is + --------------------------------------------- + In ASCII only (or EBCDIC only) OFF + In ISO-8859-1 ON + In any other Encoding ON + --------------------------------------------- + +As you see, there is one exception, In ASCII. That way you can assue +Goal #1. And with Encode Goal #2 is assumed but you still have to be +careful in such cases mentioned in B paragraphs. + +This utf8 flag is not visible in perl scripts, exactly for the same +reason you cannot (or you I) see if a scalar contains a +string, integer, or floating point number. But you can still peek +and poke these if you will. See the section below. + +=back + +=head2 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. +implementation. As such, they are efficient but may change. -=over 4 +=over 2 =item is_utf8(STRING [, CHECK]) -[INTERNAL] Test whether the UTF-8 flag is turned on in the STRING. +[INTERNAL] Tests 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 _utf8_on(STRING) -[INTERNAL] Turn on the UTF-8 flag in STRING. The data in STRING is +[INTERNAL] Turns on the UTF-8 flag in STRING. The data in STRING is B checked for being well-formed UTF-8. Do not use unless you B that the STRING is well-formed UTF-8. Returns the previous -state of the UTF-8 flag (so please don't test the return value as -I success or failure), or C if STRING is not a string. +state of the UTF-8 flag (so please don't treat the return value as +indicating success or failure), or C if STRING is not a 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 -return value as I success or failure), or C if STRING is +[INTERNAL] Turns off the UTF-8 flag in STRING. Do not use frivolously. +Returns the previous state of the UTF-8 flag (so please don't treat the +return value as indicating success or failure), or C if STRING is not a string. =back @@ -586,12 +728,19 @@ 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 a full +list of people involved. For any questions, use +Eperl-unicode@perl.orgE so we can all share share. + =cut