X-Git-Url: https://perl5.git.perl.org/perl5.git/blobdiff_plain/fdd579e2dc5d0da16b7e86246a01f0d838120df7..f0a41339d8cc9b81101f492ab383301252ea41fd:/ext/Encode/Encode.pm diff --git a/ext/Encode/Encode.pm b/ext/Encode/Encode.pm index a828d46..0f57a03 100644 --- a/ext/Encode/Encode.pm +++ b/ext/Encode/Encode.pm @@ -1,63 +1,80 @@ +# +# $Id: Encode.pm,v 1.74 2002/05/28 18:33:54 dankogai Exp dankogai $ +# package Encode; use strict; -our $VERSION = do { my @r = (q$Revision: 1.31 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r }; +our $VERSION = do { my @r = (q$Revision: 1.74 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r }; our $DEBUG = 0; +use XSLoader (); +XSLoader::load(__PACKAGE__, $VERSION); -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; -use Encode::Config; +our %ExtModule; +require Encode::Config; +eval { require Encode::ConfigLocal }; sub encodings { my $class = shift; - my @modules = (@_ and $_[0] eq ":all") ? values %ExtModule : @_; - for my $mod (@modules){ - $mod =~ s,::,/,g or $mod = "Encode/$mod"; - $mod .= '.pm'; - $DEBUG and warn "about to require $mod;"; - eval { require $mod; }; + 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} = $mod; + } + } } - my %modules = map {$_ => 1} @modules; return - sort grep {!/^(?:Internal|Unicode)$/o} keys %Encoding; + sort { lc $a cmp lc $b } + grep {!/^(?:Internal|Unicode|Guess)$/o} keys %enc; +} + +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 @@ -67,44 +84,33 @@ sub define_encoding $Encoding{$name} = $obj; my $lc = lc($name); define_alias($lc => $obj) unless $lc eq $name; - while (@_) - { + while (@_){ my $alias = shift; - define_alias($alias,$obj); + define_alias($alias, $obj); } return $obj; } sub getEncoding { - my ($class,$name,$skip_external) = @_; - my $enc; - if (ref($name) && $name->can('new_sequence')) - { - return $name; - } + my ($class, $name, $skip_external) = @_; + + ref($name) && $name->can('new_sequence') and return $name; + exists $Encoding{$name} and return $Encoding{$name}; my $lc = lc $name; - if (exists $Encoding{$name}) - { - return $Encoding{$name}; - } - if (exists $Encoding{$lc}) - { - return $Encoding{$lc}; - } + exists $Encoding{$lc} and return $Encoding{$lc}; my $oc = $class->find_alias($name); - return $oc if defined $oc; - - $oc = $class->find_alias($lc) if $lc ne $name; - return $oc if defined $oc; + defined($oc) and return $oc; + $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; }; - return $Encoding{$name} if exists $Encoding{$name}; + exists $Encoding{$name} and return $Encoding{$name}; } } return; @@ -112,37 +118,58 @@ sub getEncoding sub find_encoding { - my ($name,$skip_external) = @_; + my ($name, $skip_external) = @_; return __PACKAGE__->getEncoding($name,$skip_external); } -sub encode +sub resolve_alias { + my $obj = find_encoding(shift); + defined $obj and return $obj->name; + return; +} + +sub encode($$;$) { - my ($name,$string,$check) = @_; + my ($name, $string, $check) = @_; + $check ||=0; my $enc = find_encoding($name); - croak("Unknown encoding '$name'") unless defined $enc; + unless(defined $enc){ + require Carp; + Carp::croak("Unknown encoding '$name'"); + } my $octets = $enc->encode($string,$check); return undef if ($check && length($string)); return $octets; } -sub decode +sub decode($$;$) { my ($name,$octets,$check) = @_; + $check ||=0; my $enc = find_encoding($name); - croak("Unknown encoding '$name'") unless defined $enc; + unless(defined $enc){ + require Carp; + Carp::croak("Unknown encoding '$name'"); + } my $string = $enc->decode($octets,$check); $_[1] = $octets if $check; 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; + unless (defined $f){ + require Carp; + Carp::croak("Unknown encoding '$from'"); + } my $t = find_encoding($to); - croak("Unknown encoding '$to'") unless defined $t; + 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,$check); @@ -150,14 +177,14 @@ sub from_to return defined($_[0] = $string) ? length($string) : undef ; } -sub encode_utf8 +sub encode_utf8($) { my ($str) = @_; utf8::encode($str); return $str; } -sub decode_utf8 +sub decode_utf8($) { my ($str) = @_; return undef unless utf8::decode($str); @@ -169,17 +196,18 @@ predefine_encodings(); # # This is to restore %Encoding if really needed; # + sub predefine_encodings{ - if ($ON_EBCDIC) { + use Encode::Encoding; + if ($ON_EBCDIC) { # was in Encode::UTF_EBCDIC package Encode::UTF_EBCDIC; - *name = sub{ shift->{'Name'} }; - *new_sequence = sub{ return $_[0] }; + push @Encode::UTF_EBCDIC::ISA, 'Encode::Encoding'; *decode = sub{ my ($obj,$str,$chk) = @_; my $res = ''; for (my $i = 0; $i < length($str); $i++) { - $res .= + $res .= chr(utf8::unicode_to_native(ord(substr($str,$i,1)))); } $_[1] = '' if $chk; @@ -189,19 +217,17 @@ sub predefine_encodings{ my ($obj,$str,$chk) = @_; my $res = ''; for (my $i = 0; $i < length($str); $i++) { - $res .= + $res .= chr(utf8::native_to_unicode(ord(substr($str,$i,1)))); } $_[1] = '' if $chk; return $res; }; - $Encode::Encoding{Internal} = + $Encode::Encoding{Unicode} = bless {Name => "UTF_EBCDIC"} => "Encode::UTF_EBCDIC"; - } else { - # was in Encode::UTF_EBCDIC + } else { package Encode::Internal; - *name = sub{ shift->{'Name'} }; - *new_sequence = sub{ return $_[0] }; + push @Encode::Internal::ISA, 'Encode::Encoding'; *decode = sub{ my ($obj,$str,$chk) = @_; utf8::upgrade($str); @@ -209,15 +235,14 @@ sub predefine_encodings{ return $str; }; *encode = \&decode; - $Encode::Encoding{Unicode} = + $Encode::Encoding{Unicode} = bless {Name => "Internal"} => "Encode::Internal"; } { # was in Encode::utf8 package Encode::utf8; - *name = sub{ shift->{'Name'} }; - *new_sequence = sub{ return $_[0] }; + push @Encode::utf8::ISA, 'Encode::Encoding'; *decode = sub{ my ($obj,$octets,$chk) = @_; my $str = Encode::decode_utf8($octets); @@ -233,23 +258,11 @@ sub predefine_encodings{ $_[1] = '' if $chk; return $octets; }; - $Encode::Encoding{utf8} = + $Encode::Encoding{utf8} = bless {Name => "utf8"} => "Encode::utf8"; } - # do externals if necessary - require File::Basename; - require File::Spec; - for my $ext (qw()){ - my $pm = - File::Spec->catfile(File::Basename::dirname($INC{'Encode.pm'}), - "Encode", "$ext.pm"); - do $pm; - } } -require Encode::Encoding; -require Encode::XS; - 1; __END__ @@ -262,17 +275,16 @@ 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 @@ -294,21 +306,21 @@ 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 * @@ -323,89 +335,104 @@ 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 -The marker [INTERNAL] marks Internal Implementation Details, in -general meant only for those who think they know what they are doing, -and such details may change in future releases. - =head1 PERL ENCODING API -=over 4 +=over 2 -=item $octets = 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 a string from Perl's internal format 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", $string); - $octets = encode("iso-8859-1", $unicode); +B: When you run C<$octets = encode("utf8", $string)>, then $octets +B $string. 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, $octets[, CHECK]) +encode($valid_encoding, undef) is harmless but warns you for +C. +encode($valid_encoding, '') is harmless and warnless. -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 +=item $string = decode(ENCODING, $octets [, CHECK]) + +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 a string in Perl's internal format: + + $string = decode("iso-8859-1", $octets); - $utf8 = decode("iso-8859-1", $latin1); +B: When you run C<$string = decode("utf8", $octets)>, then $string +B $octets. Though they both contain the same data, +the utf8 flag for $string is on unless $octets entirely consists of +ASCII data (or EBCDIC on EBCDIC machines). See L +below. -=item [$length =] from_to($string, FROM_ENCODING, TO_ENCODING [,CHECK]) +decode($valid_encoding, undef) is harmless but warns you for +C. +decode($valid_encoding, '') is harmless and warnless. -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($octets, FROM_ENC, TO_ENC [, CHECK]) -For example to convert ISO-8859-1 data to UTF-8: +Converts B data between two encodings. The data in $octets +must be encoded as octets and not as characters in Perl's internal +format. For example, to convert ISO-8859-1 data to Microsoft's CP1250 encoding: - from_to($data, "iso-8859-1", "utf-8"); + from_to($octets, "iso-8859-1", "cp1250"); and to convert it back: - from_to($data, "utf-8", "iso-8859-1"); + from_to($octets, "cp1250", "iso-8859-1"); Note that because the conversion happens in place, the data to be -converted cannot be a string constant, it must be a scalar variable. +converted cannot be a string constant; it must be a scalar variable. -from_to() return the length of the converted string on success, undef +from_to() returns the length of the converted string in octets on success, undef otherwise. -=back +B: The following operations look the same but are not quite so; -=head2 UTF-8 / utf8 + from_to($data, "iso-8859-1", "utf8"); #1 + $data = decode("iso-8859-1", $data); #2 -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). +Both #1 and #2 make $data consist of a completely valid UTF-8 string +but only #2 turns utf8 flag on. #1 is equivalent to -=over 4 + $data = encode("utf8", decode("iso-8859-1", $data)); + +See L below. =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 +Equivalent to C<$octets = encode("utf8", $string);> The characters +that comprise $string are encoded in Perl's internal format and the +result is returned as a sequence of octets. 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 $octets is decoded from UTF-8 -into a sequence of logical characters. Not all sequences of octets -form valid UTF-8 encodings, so it is possible for this call to fail. -For CHECK see L. +equivalent to C<$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 @@ -420,7 +447,7 @@ 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"); @@ -428,12 +455,12 @@ When "::" is not in the name, "Encode::" is assumed. @ebcdic = Encode->encodings("EBCDIC"); -To find which encodings are supported by this package in details, +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; @@ -443,127 +470,252 @@ 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 (which is the default), 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)", $outfile or die; + while(<$in>){ print $out $_; } -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, ">", $outfile or die; + while(<$in>){ + from_to($_, "shiftjis", "euc-jp", 1); + print $out $_; + } -Once a handle is open is layers can be altered using C. +Unfortunately, it may be that 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. For gory details, see L and L. - open(F, "<:encoding(iso-8859-1)", "data.txt") or die $!; - open(G, ">:utf8", "data.utf") or die $!; - while () { print G } +=head1 Handling Malformed Data - # Could also do "print G " but that would pull - # the whole file into memory just to write it out again. +=over 2 -More examples: +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. - open(my $f, "<:encoding(cp1252)") - open(my $g, ">:encoding(iso-8859-2)") - open(my $h, ">:encoding(latin9)") # iso-8859-15 +=item I = Encode::FB_DEFAULT ( == 0) -See L for more information. +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, the code point C<0xFFFD> is used. +If the data is supposed to be UTF-8, an optional lexical warning +(category utf8) is given. -See also L for how to change the default encoding of the -data in your script. +=item I = Encode::FB_CROAK ( == 1) -=head1 Handling Malformed Data +If I is 1, methods will die on error 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. + +=item I = Encode::FB_QUIET -If I is not set, (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. +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: -If I is true but not a code reference, dies with an error message. + 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); + # $data now contains the unprocessed partial character + } -In future you will be able to use a code reference to a callback +=item I = Encode::FB_WARN + +This is the same as above, except that it warns on error. Handy when +you are debugging the mode above. + +=item perlqq mode (I = Encode::FB_PERLQQ) + +=item HTML charref mode (I = Encode::FB_HTMLCREF) + +=item XML charref mode (I = Encode::FB_XMLCREF) + +For encodings that are implemented by Encode::XS, CHECK == +Encode::FB_PERLQQ turns (en|de)code into C fallback mode. + +When you decode, C<\xI> will be inserted for a malformed character, +where I is the hex representation of the octet that could not be +decoded to utf8. And when you encode, C<\x{I}> will be inserted, +where I is the Unicode ID of the character that cannot be found +in the character repertoire of the encoding. + +HTML/XML character reference modes are about the same, in place of +C<\x{I}>, HTML uses C<&#I>; where I is a decimal digit and +XML uses C<&#xI>; where I is the hexadecimal digit. + +=item The bitmask + +These modes are actually set via a bitmask. Here is how the FB_XX +constants are laid out. You can import the FB_XX constants via +C; you can import the generic bitmask +constants via C. + + FB_DEFAULT FB_CROAK FB_QUIET FB_WARN FB_PERLQQ + DIE_ON_ERR 0x0001 X + WARN_ON_ERR 0x0002 X + RETURN_ON_ERR 0x0004 X X + LEAVE_SRC 0x0008 + PERLQQ 0x0100 X + HTMLCREF 0x0200 + XMLCREF 0x0400 + +=head2 Unimplemented fallback schemes + +In the future, you will be able to use a code reference to a callback function for the value of I but its API is still undecided. +The fallback scheme does not work on EBCDIC platforms. + =head1 Defining Encodings To define a new encoding, use: - use Encode qw(define_alias); + use Encode qw(define_encoding); define_encoding($object, 'canonicalName' [, alias...]); I will be associated with I<$object>. The object -should provide the interface described in L +should provide the interface described in L. If more than two arguments are provided then additional -arguments are taken as aliases for I<$object> as for C. +arguments are taken as aliases for I<$object>. See L for more details. -=head1 Messing with Perl's Internals +=head1 The UTF-8 flag + +Before the introduction of utf8 support in perl, The C operator +just compared the strings represented by two scalars. Beginning with +perl 5.8, C compares two strings with simultaneous consideration +of I. To explain why we made it so, I will quote page +402 of C + +=over 2 + +=item Goal #1: + +Old byte-oriented programs should not spontaneously break on the old +byte-oriented data they used to work on. + +=item Goal #2: + +Old byte-oriented programs should magically start working on the new +character-oriented data when appropriate. + +=item Goal #3: + +Programs should run just as fast in the new character-oriented mode +as in the old byte-oriented mode. + +=item Goal #4: + +Perl should remain one language, rather than forking into a +byte-oriented Perl and a character-oriented Perl. + +=back + +Back when C was written, not even Perl 5.6.0 +was born and many features documented in the book remained +unimplemented for a long time. Perl 5.8 corrected this and the introduction +of the UTF-8 flag is one of them. You can think of this perl notion as of a +byte-oriented mode (utf8 flag off) and a character-oriented mode (utf8 +flag on). + +Here is how Encode takes care of the utf8 flag. + +=over 2 + +=item * + +When you encode, the resulting utf8 flag is always off. + +=item + +When you decode, the resulting utf8 flag is on unless you can +unambiguously represent data. Here is the definition of +dis-ambiguity. + +After C<$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 @@ -572,12 +724,19 @@ 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. + =cut