--- JSON-XS/XS.pm 2007/03/29 01:27:36 1.24 +++ JSON-XS/XS.pm 2007/10/15 01:22:34 1.67 @@ -2,6 +2,9 @@ JSON::XS - JSON serialising/deserialising, done correctly and fast +JSON::XS - 正しくて高速な JSON シリアライザ/デシリアライザ + (http://fleur.hio.jp/perldoc/mix/lib/JSON/XS.html) + =head1 SYNOPSIS use JSON::XS; @@ -12,10 +15,6 @@ $utf8_encoded_json_text = to_json $perl_hash_or_arrayref; $perl_hash_or_arrayref = from_json $utf8_encoded_json_text; - # objToJson and jsonToObj aliases to to_json and from_json - # are exported for compatibility to the JSON module, - # but should not be used in new code. - # OO-interface $coder = JSON::XS->new->ascii->pretty->allow_nonref; @@ -87,16 +86,13 @@ use strict; -BEGIN { - our $VERSION = '0.8'; - our @ISA = qw(Exporter); +our $VERSION = '1.52'; +our @ISA = qw(Exporter); - our @EXPORT = qw(to_json from_json objToJson jsonToObj); - require Exporter; +our @EXPORT = qw(to_json from_json); - require XSLoader; - XSLoader::load JSON::XS::, $VERSION; -} +use Exporter; +use XSLoader; =head1 FUNCTIONAL INTERFACE @@ -107,9 +103,8 @@ =item $json_text = to_json $perl_scalar -Converts the given Perl data structure (a simple scalar or a reference to -a hash or array) to a UTF-8 encoded, binary string (that is, the string contains -octets only). Croaks on error. +Converts the given Perl data structure to a UTF-8 encoded, binary string +(that is, the string contains octets only). Croaks on error. This function call is functionally identical to: @@ -119,9 +114,9 @@ =item $perl_scalar = from_json $json_text -The opposite of C: expects an UTF-8 (binary) string and tries to -parse that as an UTF-8 encoded JSON text, returning the resulting simple -scalar or reference. Croaks on error. +The opposite of C: expects an UTF-8 (binary) string and tries +to parse that as an UTF-8 encoded JSON text, returning the resulting +reference. Croaks on error. This function call is functionally identical to: @@ -129,9 +124,66 @@ except being faster. +=item $is_boolean = JSON::XS::is_bool $scalar + +Returns true if the passed scalar represents either JSON::XS::true or +JSON::XS::false, two constants that act like C<1> and C<0>, respectively +and are used to represent JSON C and C values in Perl. + +See MAPPING, below, for more information on how JSON values are mapped to +Perl. + =back +=head1 A FEW NOTES ON UNICODE AND PERL + +Since this often leads to confusion, here are a few very clear words on +how Unicode works in Perl, modulo bugs. + +=over 4 + +=item 1. Perl strings can store characters with ordinal values > 255. + +This enables you to store unicode characters as single characters in a +Perl string - very natural. + +=item 2. Perl does I associate an encoding with your strings. + +Unless you force it to, e.g. when matching it against a regex, or printing +the scalar to a file, in which case Perl either interprets your string as +locale-encoded text, octets/binary, or as Unicode, depending on various +settings. In no case is an encoding stored together with your data, it is +I that decides encoding, not any magical metadata. + +=item 3. The internal utf-8 flag has no meaning with regards to the +encoding of your string. + +Just ignore that flag unless you debug a Perl bug, a module written in +XS or want to dive into the internals of perl. Otherwise it will only +confuse you, as, despite the name, it says nothing about how your string +is encoded. You can have unicode strings with that flag set, with that +flag clear, and you can have binary data with that flag set and that flag +clear. Other possibilities exist, too. + +If you didn't know about that flag, just the better, pretend it doesn't +exist. + +=item 4. A "Unicode String" is simply a string where each character can be +validly interpreted as a Unicode codepoint. + +If you have UTF-8 encoded data, it is no longer a Unicode string, but a +Unicode string encoded in UTF-8, giving you a binary string. + +=item 5. A string containing "high" (> 255) character values is I a UTF-8 string. + +Its a fact. Learn to live with it. + +=back + +I hope this helps :) + + =head1 OBJECT-ORIENTED INTERFACE The object oriented interface lets you configure your own encoding or @@ -156,15 +208,44 @@ generate characters outside the code range C<0..127> (which is ASCII). Any unicode characters outside that range will be escaped using either a single \uXXXX (BMP characters) or a double \uHHHH\uLLLLL escape sequence, -as per RFC4627. +as per RFC4627. The resulting encoded JSON text can be treated as a native +unicode string, an ascii-encoded, latin1-encoded or UTF-8 encoded string, +or any other superset of ASCII. If C<$enable> is false, then the C method will not escape Unicode -characters unless required by the JSON syntax. This results in a faster -and more compact format. +characters unless required by the JSON syntax or other flags. This results +in a faster and more compact format. + +The main use for this flag is to produce JSON texts that can be +transmitted over a 7-bit channel, as the encoded JSON texts will not +contain any 8 bit characters. JSON::XS->new->ascii (1)->encode ([chr 0x10401]) => ["\ud801\udc01"] +=item $json = $json->latin1 ([$enable]) + +If C<$enable> is true (or missing), then the C method will encode +the resulting JSON text as latin1 (or iso-8859-1), escaping any characters +outside the code range C<0..255>. The resulting string can be treated as a +latin1-encoded JSON text or a native unicode string. The C method +will not be affected in any way by this flag, as C by default +expects unicode, which is a strict superset of latin1. + +If C<$enable> is false, then the C method will not escape Unicode +characters unless required by the JSON syntax or other flags. + +The main use for this flag is efficiently encoding binary data as JSON +text, as most octets will not be escaped, resulting in a smaller encoded +size. The disadvantage is that the resulting JSON text is encoded +in latin1 (and must correctly be treated as such when storing and +transfering), a rare encoding for JSON. It is therefore most useful when +you want to store data structures known to contain binary data efficiently +in files or databases, not when talking to other JSON encoders/decoders. + + JSON::XS->new->latin1->encode (["\x{89}\x{abc}"] + => ["\x{89}\\u0abc"] # (perl syntax, U+abc escaped, U+89 not) + =item $json = $json->utf8 ([$enable]) If C<$enable> is true (or missing), then the C method will encode @@ -249,6 +330,51 @@ {"key": "value"} +=item $json = $json->relaxed ([$enable]) + +If C<$enable> is true (or missing), then C will accept some +extensions to normal JSON syntax (see below). C will not be +affected in anyway. I. I suggest only to use this option to +parse application-specific files written by humans (configuration files, +resource files etc.) + +If C<$enable> is false (the default), then C will only accept +valid JSON texts. + +Currently accepted extensions are: + +=over 4 + +=item * list items can have an end-comma + +JSON I array elements and key-value pairs with commas. This +can be annoying if you write JSON texts manually and want to be able to +quickly append elements, so this extension accepts comma at the end of +such items not just between them: + + [ + 1, + 2, <- this comma not normally allowed + ] + { + "k1": "v1", + "k2": "v2", <- this comma not normally allowed + } + +=item * shell-style '#'-comments + +Whenever JSON allows whitespace, shell-style comments are additionally +allowed. They are terminated by the first carriage-return or line-feed +character, after which more white-space and comments are allowed. + + [ + 1, # this comment not allowed in JSON + # neither this one... + ] + +=back + =item $json = $json->canonical ([$enable]) If C<$enable> is true (or missing), then the C method will output JSON objects @@ -283,6 +409,118 @@ JSON::XS->new->allow_nonref->encode ("Hello, World!") => "Hello, World!" +=item $json = $json->allow_blessed ([$enable]) + +If C<$enable> is true (or missing), then the C method will not +barf when it encounters a blessed reference. Instead, the value of the +B option will decide wether C (C +disabled or no C method found) or a representation of the +object (C enabled and C method found) is being +encoded. Has no effect on C. + +If C<$enable> is false (the default), then C will throw an +exception when it encounters a blessed object. + +=item $json = $json->convert_blessed ([$enable]) + +If C<$enable> is true (or missing), then C, upon encountering a +blessed object, will check for the availability of the C method +on the object's class. If found, it will be called in scalar context +and the resulting scalar will be encoded instead of the object. If no +C method is found, the value of C will decide what +to do. + +The C method may safely call die if it wants. If C +returns other blessed objects, those will be handled in the same +way. C must take care of not causing an endless recursion cycle +(== crash) in this case. The name of C was chosen because other +methods called by the Perl core (== not by the user of the object) are +usually in upper case letters and to avoid collisions with the C +function. + +This setting does not yet influence C in any way, but in the +future, global hooks might get installed that influence C and are +enabled by this setting. + +If C<$enable> is false, then the C setting will decide what +to do when a blessed object is found. + +=item $json = $json->filter_json_object ([$coderef->($hashref)]) + +When C<$coderef> is specified, it will be called from C each +time it decodes a JSON object. The only argument is a reference to the +newly-created hash. If the code references returns a single scalar (which +need not be a reference), this value (i.e. a copy of that scalar to avoid +aliasing) is inserted into the deserialised data structure. If it returns +an empty list (NOTE: I C, which is a valid scalar), the +original deserialised hash will be inserted. This setting can slow down +decoding considerably. + +When C<$coderef> is omitted or undefined, any existing callback will +be removed and C will not change the deserialised hash in any +way. + +Example, convert all JSON objects into the integer 5: + + my $js = JSON::XS->new->filter_json_object (sub { 5 }); + # returns [5] + $js->decode ('[{}]') + # throw an exception because allow_nonref is not enabled + # so a lone 5 is not allowed. + $js->decode ('{"a":1, "b":2}'); + +=item $json = $json->filter_json_single_key_object ($key [=> $coderef->($value)]) + +Works remotely similar to C, but is only called for +JSON objects having a single key named C<$key>. + +This C<$coderef> is called before the one specified via +C, if any. It gets passed the single value in the JSON +object. If it returns a single value, it will be inserted into the data +structure. If it returns nothing (not even C but the empty list), +the callback from C will be called next, as if no +single-key callback were specified. + +If C<$coderef> is omitted or undefined, the corresponding callback will be +disabled. There can only ever be one callback for a given key. + +As this callback gets called less often then the C +one, decoding speed will not usually suffer as much. Therefore, single-key +objects make excellent targets to serialise Perl objects into, especially +as single-key JSON objects are as close to the type-tagged value concept +as JSON gets (its basically an ID/VALUE tuple). Of course, JSON does not +support this in any way, so you need to make sure your data never looks +like a serialised Perl hash. + +Typical names for the single object key are C<__class_whatever__>, or +C<$__dollars_are_rarely_used__$> or C<}ugly_brace_placement>, or even +things like C<__class_md5sum(classname)__>, to reduce the risk of clashing +with real hashes. + +Example, decode JSON objects of the form C<< { "__widget__" => } >> +into the corresponding C<< $WIDGET{} >> object: + + # return whatever is in $WIDGET{5}: + JSON::XS + ->new + ->filter_json_single_key_object (__widget__ => sub { + $WIDGET{ $_[0] } + }) + ->decode ('{"__widget__": 5') + + # this can be used with a TO_JSON method in some "widget" class + # for serialisation to json: + sub WidgetBase::TO_JSON { + my ($self) = @_; + + unless ($self->{id}) { + $self->{id} = ..get..some..id..; + $WIDGET{$self->{id}} = $self; + } + + { __widget__ => $self->{id} } + } + =item $json = $json->shrink ([$enable]) Perl usually over-allocates memory a bit when allocating space for @@ -311,7 +549,7 @@ =item $json = $json->max_depth ([$maximum_nesting_depth]) -Sets the maximum nesting level (default C<8192>) accepted while encoding +Sets the maximum nesting level (default C<512>) accepted while encoding or decoding. If the JSON text or Perl data structure has an equal or higher nesting level then this limit, then the encoder and decoder will stop and croak at that point. @@ -324,8 +562,23 @@ Setting the maximum depth to one disallows any nesting, so that ensures that the object is only a single hash/object or array. -The argument to C will be rounded up to the next nearest power -of two. +The argument to C will be rounded up to the next highest power +of two. If no argument is given, the highest possible setting will be +used, which is rarely useful. + +See SECURITY CONSIDERATIONS, below, for more info on why this is useful. + +=item $json = $json->max_size ([$maximum_string_size]) + +Set the maximum length a JSON text may have (in bytes) where decoding is +being attempted. The default is C<0>, meaning no limit. When C +is called on a string longer then this number of characters it will not +attempt to decode the string but throw an exception. This setting has no +effect on C (yet). + +The argument to C will be rounded up to the next B +power of two (so may be more than requested). If no argument is given, the +limit check will be deactivated (same as when C<0> is specified). See SECURITY CONSIDERATIONS, below, for more info on why this is useful. @@ -347,6 +600,20 @@ Perl arrayrefs and JSON objects become Perl hashrefs. C becomes C<1>, C becomes C<0> and C becomes C. +=item ($perl_scalar, $characters) = $json->decode_prefix ($json_text) + +This works like the C method, but instead of raising an exception +when there is trailing garbage after the first JSON object, it will +silently stop parsing there and return the number of characters consumed +so far. + +This is useful if your JSON texts are not delimited by an outer protocol +(which is not the brightest thing to do in the first place) and you need +to know where the JSON text ends. + + JSON::XS->new->decode_prefix ("[1] the tail") + => ([], 3) + =back @@ -361,6 +628,7 @@ lowercase I refers to the Perl interpreter, while uppcercase I refers to the abstract Perl language itself. + =head2 JSON -> PERL =over 4 @@ -382,18 +650,30 @@ =item number -A JSON number becomes either an integer or numeric (floating point) -scalar in perl, depending on its range and any fractional parts. On the -Perl level, there is no difference between those as Perl handles all the -conversion details, but an integer may take slightly less memory and might -represent more values exactly than (floating point) numbers. +A JSON number becomes either an integer, numeric (floating point) or +string scalar in perl, depending on its range and any fractional parts. On +the Perl level, there is no difference between those as Perl handles all +the conversion details, but an integer may take slightly less memory and +might represent more values exactly than (floating point) numbers. + +If the number consists of digits only, JSON::XS will try to represent +it as an integer value. If that fails, it will try to represent it as +a numeric (floating point) value if that is possible without loss of +precision. Otherwise it will preserve the number as a string value. + +Numbers containing a fractional or exponential part will always be +represented as numeric (floating point) values, possibly at a loss of +precision. + +This might create round-tripping problems as numbers might become strings, +but as Perl is typeless there is no other way to do it. =item true, false -These JSON atoms become C<0>, C<1>, respectively. Information is lost in -this process. Future versions might represent those values differently, -but they will be guarenteed to act like these integers would normally in -Perl. +These JSON atoms become C and C, +respectively. They are overloaded to act almost exactly like the numbers +C<1> and C<0>. You can check wether a scalar is a JSON boolean by using +the C function. =item null @@ -401,6 +681,7 @@ =back + =head2 PERL -> JSON The mapping from Perl to JSON is slightly more difficult, as Perl is a @@ -412,17 +693,33 @@ =item hash references Perl hash references become JSON objects. As there is no inherent ordering -in hash keys, they will usually be encoded in a pseudo-random order that -can change between runs of the same program but stays generally the same -within a single run of a program. JSON::XS can optionally sort the hash -keys (determined by the I flag), so the same datastructure -will serialise to the same JSON text (given same settings and version of -JSON::XS), but this incurs a runtime overhead. +in hash keys (or JSON objects), they will usually be encoded in a +pseudo-random order that can change between runs of the same program but +stays generally the same within a single run of a program. JSON::XS can +optionally sort the hash keys (determined by the I flag), so +the same datastructure will serialise to the same JSON text (given same +settings and version of JSON::XS), but this incurs a runtime overhead +and is only rarely useful, e.g. when you want to compare some JSON text +against another for equality. =item array references Perl array references become JSON arrays. +=item other references + +Other unblessed references are generally not allowed and will cause an +exception to be thrown, except for references to the integers C<0> and +C<1>, which get turned into C and C atoms in JSON. You can +also use C and C to improve readability. + + to_json [\0,JSON::XS::true] # yields [false,true] + +=item JSON::XS::true, JSON::XS::false + +These special values become JSON true and JSON false values, +respectively. You can also use C<\1> and C<\0> directly if you want. + =item blessed objects Blessed objects are not allowed. JSON::XS currently tries to encode their @@ -464,10 +761,6 @@ You can not currently output JSON booleans or force the type in other, less obscure, ways. Tell me if you need this capability. -=item circular data structures - -Those will be encoded until memory or stackspace runs out. - =back @@ -557,6 +850,30 @@ =back + +=head2 JSON and YAML + +You often hear that JSON is a subset (or a close subset) of YAML. This is, +however, a mass hysteria and very far from the truth. In general, there is +no way to configure JSON::XS to output a data structure as valid YAML. + +If you really must use JSON::XS to generate YAML, you should use this +algorithm (subject to change in future versions): + + my $to_yaml = JSON::XS->new->utf8->space_after (1); + my $yaml = $to_yaml->encode ($ref) . "\n"; + +This will usually generate JSON texts that also parse as valid +YAML. Please note that YAML has hardcoded limits on (simple) object key +lengths that JSON doesn't have, so you should make sure that your hash +keys are noticably shorter than the 1024 characters YAML allows. + +There might be other incompatibilities that I am not aware of. In general +you should not try to generate YAML with a JSON generator or vice versa, +or try to parse JSON with a YAML parser or vice versa: chances are high +that you will run into severe interoperability problems. + + =head2 SPEED It seems that JSON::XS is surprisingly fast, as shown in the following @@ -564,43 +881,55 @@ in the JSON::XS distribution, to make it easy to compare on your own system. -First comes a comparison between various modules using a very short JSON -string: +First comes a comparison between various modules using a very short +single-line JSON string: - {"method": "handleMessage", "params": ["user1", "we were just talking"], "id": null} + {"method": "handleMessage", "params": ["user1", "we were just talking"], \ + "id": null, "array":[1,11,234,-5,1e5,1e7, true, false]} -It shows the number of encodes/decodes per second (JSON::XS uses the -functional interface, while JSON::XS/2 uses the OO interface with -pretty-printing and hashkey sorting enabled). Higher is better: +It shows the number of encodes/decodes per second (JSON::XS uses +the functional interface, while JSON::XS/2 uses the OO interface +with pretty-printing and hashkey sorting enabled, JSON::XS/3 enables +shrink). Higher is better: + Storable | 15779.925 | 14169.946 | + -----------+------------+------------+ module | encode | decode | -----------|------------|------------| - JSON | 11488.516 | 7823.035 | - JSON::DWIW | 94708.054 | 129094.260 | - JSON::PC | 63884.157 | 128528.212 | - JSON::Syck | 34898.677 | 42096.911 | - JSON::XS | 654027.064 | 396423.669 | - JSON::XS/2 | 371564.190 | 371725.613 | + JSON | 4990.842 | 4088.813 | + JSON::DWIW | 51653.990 | 71575.154 | + JSON::PC | 65948.176 | 74631.744 | + JSON::PP | 8931.652 | 3817.168 | + JSON::Syck | 24877.248 | 27776.848 | + JSON::XS | 388361.481 | 227951.304 | + JSON::XS/2 | 227951.304 | 218453.333 | + JSON::XS/3 | 338250.323 | 218453.333 | + Storable | 16500.016 | 135300.129 | -----------+------------+------------+ -That is, JSON::XS is more than six times faster than JSON::DWIW on -encoding, more than three times faster on decoding, and about thirty times -faster than JSON, even with pretty-printing and key sorting. +That is, JSON::XS is about five times faster than JSON::DWIW on encoding, +about three times faster on decoding, and over fourty times faster +than JSON, even with pretty-printing and key sorting. It also compares +favourably to Storable for small amounts of data. Using a longer test string (roughly 18KB, generated from Yahoo! Locals search API (http://nanoref.com/yahooapis/mgPdGg): module | encode | decode | -----------|------------|------------| - JSON | 273.023 | 44.674 | - JSON::DWIW | 1089.383 | 1145.704 | - JSON::PC | 3097.419 | 2393.921 | - JSON::Syck | 514.060 | 843.053 | - JSON::XS | 6479.668 | 3636.364 | - JSON::XS/2 | 3774.221 | 3599.124 | + JSON | 55.260 | 34.971 | + JSON::DWIW | 825.228 | 1082.513 | + JSON::PC | 3571.444 | 2394.829 | + JSON::PP | 210.987 | 32.574 | + JSON::Syck | 552.551 | 787.544 | + JSON::XS | 5780.463 | 4854.519 | + JSON::XS/2 | 3869.998 | 4798.975 | + JSON::XS/3 | 5862.880 | 4798.975 | + Storable | 4445.002 | 5235.027 | -----------+------------+------------+ -Again, JSON::XS leads by far. +Again, JSON::XS leads by far (except for Storable which non-surprisingly +decodes faster). On large strings containing lots of high unicode characters, some modules (such as JSON::PC) seem to decode faster than JSON::XS, but the result @@ -623,20 +952,41 @@ resources run out, thats just fine (e.g. by using a separate process that can crash safely). The size of a JSON text in octets or characters is usually a good indication of the size of the resources required to decode -it into a Perl structure. +it into a Perl structure. While JSON::XS can check the size of the JSON +text, it might be too late when you already have it in memory, so you +might want to check the size before you accept the string. Third, JSON::XS recurses using the C stack when decoding objects and arrays. The C stack is a limited resource: for instance, on my amd64 -machine with 8MB of stack size I can decode around 180k nested arrays -but only 14k nested JSON objects. If that is exceeded, the program -crashes. Thats why the default nesting limit is set to 8192. If your -process has a smaller stack, you should adjust this setting accordingly -with the C method. +machine with 8MB of stack size I can decode around 180k nested arrays but +only 14k nested JSON objects (due to perl itself recursing deeply on croak +to free the temporary). If that is exceeded, the program crashes. to be +conservative, the default nesting limit is set to 512. If your process +has a smaller stack, you should adjust this setting accordingly with the +C method. And last but least, something else could bomb you that I forgot to think -of. In that case, you get to keep the pieces. I am alway sopen for hints, +of. In that case, you get to keep the pieces. I am always open for hints, though... +If you are using JSON::XS to return packets to consumption +by javascript scripts in a browser you should have a look at +L to see wether +you are vulnerable to some common attack vectors (which really are browser +design bugs, but it is still you who will have to deal with it, as major +browser developers care only for features, not about doing security +right). + + +=head1 THREADS + +This module is I guarenteed to be thread safe and there are no +plans to change this until Perl gets thread support (as opposed to the +horribly slow so-called "threads" which are simply slow and bloated +process simulations - use fork, its I faster, cheaper, better). + +(It might actually work, but you ahve ben warned). + =head1 BUGS @@ -645,8 +995,32 @@ still relatively early in its development. If you keep reporting bugs they will be fixed swiftly, though. +Please refrain from using rt.cpan.org or any other bug reporting +service. I put the contact address into my modules for a reason. + =cut +our $true = do { bless \(my $dummy = 1), "JSON::XS::Boolean" }; +our $false = do { bless \(my $dummy = 0), "JSON::XS::Boolean" }; + +sub true() { $true } +sub false() { $false } + +sub is_bool($) { + UNIVERSAL::isa $_[0], "JSON::XS::Boolean" +# or UNIVERSAL::isa $_[0], "JSON::Literal" +} + +XSLoader::load "JSON::XS", $VERSION; + +package JSON::XS::Boolean; + +use overload + "0+" => sub { ${$_[0]} }, + "++" => sub { $_[0] = ${$_[0]} + 1 }, + "--" => sub { $_[0] = ${$_[0]} - 1 }, + fallback => 1; + 1; =head1 AUTHOR