X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=blobdiff_plain;f=ext%2FEncode%2FEncode.pm;h=b502e8fdc469a5a8570ac4f7af7e60ae9ce6499b;hb=7e19fb92789b07f9ae6ba1ee1b4f5fbb72612161;hp=0bf6a2489ff841df4a1bd4f51990657c50bb2bf9;hpb=6d1c0808b641926567cd16e07679f427c5fedc61;p=p5sagit%2Fp5-mst-13.2.git diff --git a/ext/Encode/Encode.pm b/ext/Encode/Encode.pm index 0bf6a24..b502e8f 100644 --- a/ext/Encode/Encode.pm +++ b/ext/Encode/Encode.pm @@ -1,12 +1,12 @@ package Encode; use strict; -our $VERSION = do { my @r = (q$Revision: 1.52 $ =~ /\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 Exporter; -our @ISA = qw(Exporter); +use base qw/Exporter/; # Public, encouraged API is exported by default @@ -15,8 +15,10 @@ our @EXPORT = qw( 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 @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 = ( @@ -65,10 +67,9 @@ sub encodings } 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"); + my $obj = ref($_[0]) ? $_[0] : find_encoding($_[0]); + $obj->can("perlio_ok") and return $obj->perlio_ok(); + return 0; # safety net } sub define_encoding @@ -195,6 +196,11 @@ sub predefine_encodings{ 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 = ''; @@ -222,6 +228,11 @@ sub predefine_encodings{ 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); @@ -238,6 +249,11 @@ sub predefine_encodings{ 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); @@ -258,17 +274,6 @@ sub predefine_encodings{ } } -require Encode::Encoding; - -eval { - require PerlIO::encoding; - unless (PerlIO::encoding->VERSION >= 0.02){ - delete $INC{"PerlIO/encoding.pm"}; - } -}; -# warn $@ if $@; -@Encode::XS::ISA = qw(Encode::Encoding); - 1; __END__ @@ -281,13 +286,12 @@ 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; +see the PODs below: Name Description -------------------------------------------------------- @@ -313,21 +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 * @@ -342,7 +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 @@ -352,74 +356,89 @@ and such details may change in future releases. =head1 PERL ENCODING API -=over 4 +=over 2 =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 +For example, to convert (internally UTF-8 encoded) Unicode string to iso-8859-1 (also known as Latin1), - $octets = encode("iso-8859-1", $unicode); + $octets = encode("iso-8859-1", $utf8); + +B: When you C<$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, $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", $latin1); -=item [$length =] 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 $octets entirely conststs of +ASCII data (or EBCDIC on EBCDIC machines). See L +below. + +=item [$length =] from_to($string, FROM_ENC, TO_ENC [, CHECK]) -Convert B the data between two encodings. -For example to convert ISO-8859-1 data to UTF-8: +Converts B data between two encodings. For example, to +convert ISO-8859-1 data to UTF-8: - from_to($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($data, "utf8", "iso-8859-1"); Note that because the conversion happens in place, the data to be -converted cannot be a string constant, it must be a scalar variable. +converted cannot be a string constant; it must be a scalar variable. -from_to() return the length of the converted string on success, undef +from_to() returns the length of the converted string on success, undef otherwise. -=back +B: The following operations look the same but not quite so; + + from_to($data, "iso-8859-1", "utf8"); #1 + $data = decode("iso-8859-1", $data); #2 -=head2 UTF-8 / utf8 +Both #1 and #2 makes $data consists of completely valid UTF-8 string +but only #2 turns utf8 flag on. #1 is equivalent to -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). + $data = encode("utf8", decode("iso-8859-1", $data)); -=over 4 +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 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]); -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", $octets [, CHECK])>. +decode_utf8($octets [, CHECK]); The sequence of octets represented by +$octets is decoded from UTF-8 into a sequence of logical +characters. Not all sequences of octets form valid UTF-8 encodings, so +it is possible for this call to fail. For CHECK, see +L. =back @@ -434,7 +453,7 @@ ones that are not loaded yet, say @all_encodings = Encode->encodings(":all"); -Or you can give the name of specific module. +Or you can give the name of a specific module. @with_jp = Encode->encodings("Encode::JP"); @@ -442,12 +461,12 @@ When "::" is not in the name, "Encode::" is assumed. @ebcdic = Encode->encodings("EBCDIC"); -To find which encodings are supported by this package in details, +To find out in detail which encodings are supported by this package, see L. =head2 Defining Aliases -To add new alias to a given encoding, Use; +To add a new alias to a given encoding, use: use Encode; use Encode::Alias; @@ -465,16 +484,16 @@ i.e. Encode::resolve_alias("iso-8859-12") # false; nonexistent Encode::resolve_alias($name) eq $name # true if $name is canonical -This resolve_alias() does not need C and is -exported via C. +resolve_alias() does not need C; it can be +exported via C. -See L on details. +See L for details. =head1 Encoding via PerlIO -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. +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. # via PerlIO open my $in, "<:encoding(shiftjis)", $infile or die; @@ -482,82 +501,98 @@ totally identical by functionality. while(<>){ print; } # via from_to - open my $in, $infile or die; - open my $out, $outfile or die; + open my $in, "<", $infile or die; + open my $out, ">", $outfile or die; while(<>){ - from_to($_, "shiftjis", "euc", 1); + from_to($_, "shiftjis", "euc-jp", 1); } -Unfortunately, not all encodings are PerlIO-savvy. You can check if -your encoding is supported by PerlIO by C method. +Unfortunately, there may be encodings are PerlIO-savvy. You can check +if your encoding is supported by PerlIO by calling the C +method. + + Encode::perlio_ok("hz"); # False + find_encoding("euc-cn")->perlio_ok; # True where PerlIO is available + + use Encode qw(perlio_ok); # exported upon request + perlio_ok("euc-jp") - 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 +Fortunately, all encodings that come with Encode core are PerlIO-savvy +except for hz and ISO-2022-kr. See L for details. -For gory details, see L; +For gory details, see L. =head1 Handling Malformed Data -=over 4 +=over 2 -THE I argument is used as follows. When you omit it, it is -identical to I = 0. +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. =item I = Encode::FB_DEFAULT ( == 0) -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. +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. -=item I = Encode::DIE_ON_ERROR (== 1) +=item I = Encode::FB_CROAK ( == 1) -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. +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. =item I = Encode::FB_QUIET 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. +return the portion of the data that has been processed so far when +an error occurs. The data argument will be overwritten with +everything after that point (that is, the unprocessed part of data). +This is handy when you have to call decode repeatedly in the case +where your source data may contain partial multi-byte character +sequences, for example because you are reading with a fixed-width +buffer. Here is some sample code that does exactly this: my $data = ''; while(defined(read $fh, $buffer, 256)){ - # buffer may end in partial character so we append + # buffer may end in a partial character so we append $data .= $buffer; $utf8 .= decode($encoding, $data, ENCODE::FB_QUIET); - # $data now contains unprocessed partial character + # $data now contains the unprocessed partial character } =item I = Encode::FB_WARN -This is the same as above, except it warns on error. Handy when you -are debugging the mode above. +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, '\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. +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. + +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. =item The bitmask -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. +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 @@ -565,10 +600,12 @@ generic bitmask constants, you can import via RETURN_ON_ERR 0x0004 X X LEAVE_SRC 0x0008 PERLQQ 0x0100 X + HTMLCREF 0x0200 + XMLCREF 0x0400 -=head2 Unemplemented fallback schemes +=head2 Unimplemented fallback schemes -In future you will be able to use a code reference to a callback +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. =head1 Defining Encodings @@ -579,38 +616,110 @@ To define a new encoding, use: 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<$object>, as for C. See L for more details. -=head1 Messing with Perl's Internals +=head1 The UTF-8 flag + +Before the introduction of utf8 support in perl, The C operator +just compares internal data of the scalars. Now C means internal +data equality AND I. To explain why we made it so, I +will quote page 402 of C + +=over 2 + +=item Goal #1: + +Old byte-oriented programs should not spontaneously break on the old +byte-oriented data they used to work on. + +=item Goal #2: + +Old byte-oriented programs should magically start working on the new +character-oriented data when appropriate. + +=item Goal #3: + +Programs should run just as fast in the new character-oriented mode +as in the old byte-oriented mode. + +=item Goal #4: + +Perl should remain one language, rather than forking into a +byte-oriented Perl and a character-oriented Perl. + +=back + +Back when C was written, not even Perl 5.6.0 +was born and many features documented in the book remained +unimplemented. Perl 5.8 hopefully correct this and the introduction +of UTF-8 flag is one of them. You can think this perl notion of +byte-oriented mode (utf8 flag off) and character-oriented mode (utf8 +flag on). + +Here is how Encode takes care of the utf8 flag. + +=over2 + +=item * + +When you encode, the resulting utf8 flag is always off. + +=item + +When you decode, the resuting utf8 flag is on unless you can +unambiguously represent data. Here is the definition of +dis-ambiguity. + + After C<$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 @@ -630,8 +739,8 @@ 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. +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