… | |
… | |
9 | # exported functions, they croak on error |
9 | # exported functions, they croak on error |
10 | # and expect/generate UTF-8 |
10 | # and expect/generate UTF-8 |
11 | |
11 | |
12 | $utf8_encoded_json_text = to_json $perl_hash_or_arrayref; |
12 | $utf8_encoded_json_text = to_json $perl_hash_or_arrayref; |
13 | $perl_hash_or_arrayref = from_json $utf8_encoded_json_text; |
13 | $perl_hash_or_arrayref = from_json $utf8_encoded_json_text; |
14 | |
|
|
15 | # objToJson and jsonToObj aliases to to_json and from_json |
|
|
16 | # are exported for compatibility to the JSON module, |
|
|
17 | # but should not be used in new code. |
|
|
18 | |
14 | |
19 | # OO-interface |
15 | # OO-interface |
20 | |
16 | |
21 | $coder = JSON::XS->new->ascii->pretty->allow_nonref; |
17 | $coder = JSON::XS->new->ascii->pretty->allow_nonref; |
22 | $pretty_printed_unencoded = $coder->encode ($perl_scalar); |
18 | $pretty_printed_unencoded = $coder->encode ($perl_scalar); |
… | |
… | |
85 | |
81 | |
86 | package JSON::XS; |
82 | package JSON::XS; |
87 | |
83 | |
88 | use strict; |
84 | use strict; |
89 | |
85 | |
90 | BEGIN { |
|
|
91 | our $VERSION = '1.11'; |
86 | our $VERSION = '1.5'; |
92 | our @ISA = qw(Exporter); |
87 | our @ISA = qw(Exporter); |
93 | |
88 | |
94 | our @EXPORT = qw(to_json from_json objToJson jsonToObj); |
89 | our @EXPORT = qw(to_json from_json); |
95 | require Exporter; |
|
|
96 | |
90 | |
97 | require XSLoader; |
91 | use Exporter; |
98 | XSLoader::load JSON::XS::, $VERSION; |
92 | use XSLoader; |
99 | } |
|
|
100 | |
93 | |
101 | =head1 FUNCTIONAL INTERFACE |
94 | =head1 FUNCTIONAL INTERFACE |
102 | |
95 | |
103 | The following convinience methods are provided by this module. They are |
96 | The following convinience methods are provided by this module. They are |
104 | exported by default: |
97 | exported by default: |
… | |
… | |
126 | This function call is functionally identical to: |
119 | This function call is functionally identical to: |
127 | |
120 | |
128 | $perl_scalar = JSON::XS->new->utf8->decode ($json_text) |
121 | $perl_scalar = JSON::XS->new->utf8->decode ($json_text) |
129 | |
122 | |
130 | except being faster. |
123 | except being faster. |
|
|
124 | |
|
|
125 | =item $is_boolean = JSON::XS::is_bool $scalar |
|
|
126 | |
|
|
127 | Returns true if the passed scalar represents either JSON::XS::true or |
|
|
128 | JSON::XS::false, two constants that act like C<1> and C<0>, respectively |
|
|
129 | and are used to represent JSON C<true> and C<false> values in Perl. |
|
|
130 | |
|
|
131 | See MAPPING, below, for more information on how JSON values are mapped to |
|
|
132 | Perl. |
131 | |
133 | |
132 | =back |
134 | =back |
133 | |
135 | |
134 | |
136 | |
135 | =head1 OBJECT-ORIENTED INTERFACE |
137 | =head1 OBJECT-ORIENTED INTERFACE |
… | |
… | |
154 | |
156 | |
155 | If C<$enable> is true (or missing), then the C<encode> method will not |
157 | If C<$enable> is true (or missing), then the C<encode> method will not |
156 | generate characters outside the code range C<0..127> (which is ASCII). Any |
158 | generate characters outside the code range C<0..127> (which is ASCII). Any |
157 | unicode characters outside that range will be escaped using either a |
159 | unicode characters outside that range will be escaped using either a |
158 | single \uXXXX (BMP characters) or a double \uHHHH\uLLLLL escape sequence, |
160 | single \uXXXX (BMP characters) or a double \uHHHH\uLLLLL escape sequence, |
159 | as per RFC4627. |
161 | as per RFC4627. The resulting encoded JSON text can be treated as a native |
|
|
162 | unicode string, an ascii-encoded, latin1-encoded or UTF-8 encoded string, |
|
|
163 | or any other superset of ASCII. |
160 | |
164 | |
161 | If C<$enable> is false, then the C<encode> method will not escape Unicode |
165 | If C<$enable> is false, then the C<encode> method will not escape Unicode |
162 | characters unless required by the JSON syntax. This results in a faster |
166 | characters unless required by the JSON syntax or other flags. This results |
163 | and more compact format. |
167 | in a faster and more compact format. |
|
|
168 | |
|
|
169 | The main use for this flag is to produce JSON texts that can be |
|
|
170 | transmitted over a 7-bit channel, as the encoded JSON texts will not |
|
|
171 | contain any 8 bit characters. |
164 | |
172 | |
165 | JSON::XS->new->ascii (1)->encode ([chr 0x10401]) |
173 | JSON::XS->new->ascii (1)->encode ([chr 0x10401]) |
166 | => ["\ud801\udc01"] |
174 | => ["\ud801\udc01"] |
|
|
175 | |
|
|
176 | =item $json = $json->latin1 ([$enable]) |
|
|
177 | |
|
|
178 | If C<$enable> is true (or missing), then the C<encode> method will encode |
|
|
179 | the resulting JSON text as latin1 (or iso-8859-1), escaping any characters |
|
|
180 | outside the code range C<0..255>. The resulting string can be treated as a |
|
|
181 | latin1-encoded JSON text or a native unicode string. The C<decode> method |
|
|
182 | will not be affected in any way by this flag, as C<decode> by default |
|
|
183 | expects unicode, which is a strict superset of latin1. |
|
|
184 | |
|
|
185 | If C<$enable> is false, then the C<encode> method will not escape Unicode |
|
|
186 | characters unless required by the JSON syntax or other flags. |
|
|
187 | |
|
|
188 | The main use for this flag is efficiently encoding binary data as JSON |
|
|
189 | text, as most octets will not be escaped, resulting in a smaller encoded |
|
|
190 | size. The disadvantage is that the resulting JSON text is encoded |
|
|
191 | in latin1 (and must correctly be treated as such when storing and |
|
|
192 | transfering), a rare encoding for JSON. It is therefore most useful when |
|
|
193 | you want to store data structures known to contain binary data efficiently |
|
|
194 | in files or databases, not when talking to other JSON encoders/decoders. |
|
|
195 | |
|
|
196 | JSON::XS->new->latin1->encode (["\x{89}\x{abc}"] |
|
|
197 | => ["\x{89}\\u0abc"] # (perl syntax, U+abc escaped, U+89 not) |
167 | |
198 | |
168 | =item $json = $json->utf8 ([$enable]) |
199 | =item $json = $json->utf8 ([$enable]) |
169 | |
200 | |
170 | If C<$enable> is true (or missing), then the C<encode> method will encode |
201 | If C<$enable> is true (or missing), then the C<encode> method will encode |
171 | the JSON result into UTF-8, as required by many protocols, while the |
202 | the JSON result into UTF-8, as required by many protocols, while the |
… | |
… | |
280 | Example, encode a Perl scalar as JSON value with enabled C<allow_nonref>, |
311 | Example, encode a Perl scalar as JSON value with enabled C<allow_nonref>, |
281 | resulting in an invalid JSON text: |
312 | resulting in an invalid JSON text: |
282 | |
313 | |
283 | JSON::XS->new->allow_nonref->encode ("Hello, World!") |
314 | JSON::XS->new->allow_nonref->encode ("Hello, World!") |
284 | => "Hello, World!" |
315 | => "Hello, World!" |
|
|
316 | |
|
|
317 | =item $json = $json->allow_blessed ([$enable]) |
|
|
318 | |
|
|
319 | If C<$enable> is true (or missing), then the C<encode> method will not |
|
|
320 | barf when it encounters a blessed reference. Instead, the value of the |
|
|
321 | B<convert_blessed> option will decide wether C<null> (C<convert_blessed> |
|
|
322 | disabled or no C<to_json> method found) or a representation of the |
|
|
323 | object (C<convert_blessed> enabled and C<to_json> method found) is being |
|
|
324 | encoded. Has no effect on C<decode>. |
|
|
325 | |
|
|
326 | If C<$enable> is false (the default), then C<encode> will throw an |
|
|
327 | exception when it encounters a blessed object. |
|
|
328 | |
|
|
329 | =item $json = $json->convert_blessed ([$enable]) |
|
|
330 | |
|
|
331 | If C<$enable> is true (or missing), then C<encode>, upon encountering a |
|
|
332 | blessed object, will check for the availability of the C<TO_JSON> method |
|
|
333 | on the object's class. If found, it will be called in scalar context |
|
|
334 | and the resulting scalar will be encoded instead of the object. If no |
|
|
335 | C<TO_JSON> method is found, the value of C<allow_blessed> will decide what |
|
|
336 | to do. |
|
|
337 | |
|
|
338 | The C<TO_JSON> method may safely call die if it wants. If C<TO_JSON> |
|
|
339 | returns other blessed objects, those will be handled in the same |
|
|
340 | way. C<TO_JSON> must take care of not causing an endless recursion cycle |
|
|
341 | (== crash) in this case. The name of C<TO_JSON> was chosen because other |
|
|
342 | methods called by the Perl core (== not by the user of the object) are |
|
|
343 | usually in upper case letters and to avoid collisions with the C<to_json> |
|
|
344 | function. |
|
|
345 | |
|
|
346 | This setting does not yet influence C<decode> in any way, but in the |
|
|
347 | future, global hooks might get installed that influence C<decode> and are |
|
|
348 | enabled by this setting. |
|
|
349 | |
|
|
350 | If C<$enable> is false, then the C<allow_blessed> setting will decide what |
|
|
351 | to do when a blessed object is found. |
|
|
352 | |
|
|
353 | =item $json = $json->filter_json_object ([$coderef->($hashref)]) |
|
|
354 | |
|
|
355 | When C<$coderef> is specified, it will be called from C<decode> each |
|
|
356 | time it decodes a JSON object. The only argument is a reference to the |
|
|
357 | newly-created hash. If the code references returns a single scalar (which |
|
|
358 | need not be a reference), this value (i.e. a copy of that scalar to avoid |
|
|
359 | aliasing) is inserted into the deserialised data structure. If it returns |
|
|
360 | an empty list (NOTE: I<not> C<undef>, which is a valid scalar), the |
|
|
361 | original deserialised hash will be inserted. This setting can slow down |
|
|
362 | decoding considerably. |
|
|
363 | |
|
|
364 | When C<$coderef> is omitted or undefined, any existing callback will |
|
|
365 | be removed and C<decode> will not change the deserialised hash in any |
|
|
366 | way. |
|
|
367 | |
|
|
368 | Example, convert all JSON objects into the integer 5: |
|
|
369 | |
|
|
370 | my $js = JSON::XS->new->filter_json_object (sub { 5 }); |
|
|
371 | # returns [5] |
|
|
372 | $js->decode ('[{}]') |
|
|
373 | # throw an exception because allow_nonref is not enabled |
|
|
374 | # so a lone 5 is not allowed. |
|
|
375 | $js->decode ('{"a":1, "b":2}'); |
|
|
376 | |
|
|
377 | =item $json = $json->filter_json_single_key_object ($key [=> $coderef->($value)]) |
|
|
378 | |
|
|
379 | Works remotely similar to C<filter_json_object>, but is only called for |
|
|
380 | JSON objects having a single key named C<$key>. |
|
|
381 | |
|
|
382 | This C<$coderef> is called before the one specified via |
|
|
383 | C<filter_json_object>, if any. It gets passed the single value in the JSON |
|
|
384 | object. If it returns a single value, it will be inserted into the data |
|
|
385 | structure. If it returns nothing (not even C<undef> but the empty list), |
|
|
386 | the callback from C<filter_json_object> will be called next, as if no |
|
|
387 | single-key callback were specified. |
|
|
388 | |
|
|
389 | If C<$coderef> is omitted or undefined, the corresponding callback will be |
|
|
390 | disabled. There can only ever be one callback for a given key. |
|
|
391 | |
|
|
392 | As this callback gets called less often then the C<filter_json_object> |
|
|
393 | one, decoding speed will not usually suffer as much. Therefore, single-key |
|
|
394 | objects make excellent targets to serialise Perl objects into, especially |
|
|
395 | as single-key JSON objects are as close to the type-tagged value concept |
|
|
396 | as JSON gets (its basically an ID/VALUE tuple). Of course, JSON does not |
|
|
397 | support this in any way, so you need to make sure your data never looks |
|
|
398 | like a serialised Perl hash. |
|
|
399 | |
|
|
400 | Typical names for the single object key are C<__class_whatever__>, or |
|
|
401 | C<$__dollars_are_rarely_used__$> or C<}ugly_brace_placement>, or even |
|
|
402 | things like C<__class_md5sum(classname)__>, to reduce the risk of clashing |
|
|
403 | with real hashes. |
|
|
404 | |
|
|
405 | Example, decode JSON objects of the form C<< { "__widget__" => <id> } >> |
|
|
406 | into the corresponding C<< $WIDGET{<id>} >> object: |
|
|
407 | |
|
|
408 | # return whatever is in $WIDGET{5}: |
|
|
409 | JSON::XS |
|
|
410 | ->new |
|
|
411 | ->filter_json_single_key_object (__widget__ => sub { |
|
|
412 | $WIDGET{ $_[0] } |
|
|
413 | }) |
|
|
414 | ->decode ('{"__widget__": 5') |
|
|
415 | |
|
|
416 | # this can be used with a TO_JSON method in some "widget" class |
|
|
417 | # for serialisation to json: |
|
|
418 | sub WidgetBase::TO_JSON { |
|
|
419 | my ($self) = @_; |
|
|
420 | |
|
|
421 | unless ($self->{id}) { |
|
|
422 | $self->{id} = ..get..some..id..; |
|
|
423 | $WIDGET{$self->{id}} = $self; |
|
|
424 | } |
|
|
425 | |
|
|
426 | { __widget__ => $self->{id} } |
|
|
427 | } |
285 | |
428 | |
286 | =item $json = $json->shrink ([$enable]) |
429 | =item $json = $json->shrink ([$enable]) |
287 | |
430 | |
288 | Perl usually over-allocates memory a bit when allocating space for |
431 | Perl usually over-allocates memory a bit when allocating space for |
289 | strings. This flag optionally resizes strings generated by either |
432 | strings. This flag optionally resizes strings generated by either |
… | |
… | |
322 | given character in a string. |
465 | given character in a string. |
323 | |
466 | |
324 | Setting the maximum depth to one disallows any nesting, so that ensures |
467 | Setting the maximum depth to one disallows any nesting, so that ensures |
325 | that the object is only a single hash/object or array. |
468 | that the object is only a single hash/object or array. |
326 | |
469 | |
327 | The argument to C<max_depth> will be rounded up to the next nearest power |
470 | The argument to C<max_depth> will be rounded up to the next highest power |
328 | of two. |
471 | of two. If no argument is given, the highest possible setting will be |
|
|
472 | used, which is rarely useful. |
|
|
473 | |
|
|
474 | See SECURITY CONSIDERATIONS, below, for more info on why this is useful. |
|
|
475 | |
|
|
476 | =item $json = $json->max_size ([$maximum_string_size]) |
|
|
477 | |
|
|
478 | Set the maximum length a JSON text may have (in bytes) where decoding is |
|
|
479 | being attempted. The default is C<0>, meaning no limit. When C<decode> |
|
|
480 | is called on a string longer then this number of characters it will not |
|
|
481 | attempt to decode the string but throw an exception. This setting has no |
|
|
482 | effect on C<encode> (yet). |
|
|
483 | |
|
|
484 | The argument to C<max_size> will be rounded up to the next B<highest> |
|
|
485 | power of two (so may be more than requested). If no argument is given, the |
|
|
486 | limit check will be deactivated (same as when C<0> is specified). |
329 | |
487 | |
330 | See SECURITY CONSIDERATIONS, below, for more info on why this is useful. |
488 | See SECURITY CONSIDERATIONS, below, for more info on why this is useful. |
331 | |
489 | |
332 | =item $json_text = $json->encode ($perl_scalar) |
490 | =item $json_text = $json->encode ($perl_scalar) |
333 | |
491 | |
… | |
… | |
345 | |
503 | |
346 | JSON numbers and strings become simple Perl scalars. JSON arrays become |
504 | JSON numbers and strings become simple Perl scalars. JSON arrays become |
347 | Perl arrayrefs and JSON objects become Perl hashrefs. C<true> becomes |
505 | Perl arrayrefs and JSON objects become Perl hashrefs. C<true> becomes |
348 | C<1>, C<false> becomes C<0> and C<null> becomes C<undef>. |
506 | C<1>, C<false> becomes C<0> and C<null> becomes C<undef>. |
349 | |
507 | |
|
|
508 | =item ($perl_scalar, $characters) = $json->decode_prefix ($json_text) |
|
|
509 | |
|
|
510 | This works like the C<decode> method, but instead of raising an exception |
|
|
511 | when there is trailing garbage after the first JSON object, it will |
|
|
512 | silently stop parsing there and return the number of characters consumed |
|
|
513 | so far. |
|
|
514 | |
|
|
515 | This is useful if your JSON texts are not delimited by an outer protocol |
|
|
516 | (which is not the brightest thing to do in the first place) and you need |
|
|
517 | to know where the JSON text ends. |
|
|
518 | |
|
|
519 | JSON::XS->new->decode_prefix ("[1] the tail") |
|
|
520 | => ([], 3) |
|
|
521 | |
350 | =back |
522 | =back |
351 | |
523 | |
352 | |
524 | |
353 | =head1 MAPPING |
525 | =head1 MAPPING |
354 | |
526 | |
… | |
… | |
359 | |
531 | |
360 | For the more enlightened: note that in the following descriptions, |
532 | For the more enlightened: note that in the following descriptions, |
361 | lowercase I<perl> refers to the Perl interpreter, while uppcercase I<Perl> |
533 | lowercase I<perl> refers to the Perl interpreter, while uppcercase I<Perl> |
362 | refers to the abstract Perl language itself. |
534 | refers to the abstract Perl language itself. |
363 | |
535 | |
|
|
536 | |
364 | =head2 JSON -> PERL |
537 | =head2 JSON -> PERL |
365 | |
538 | |
366 | =over 4 |
539 | =over 4 |
367 | |
540 | |
368 | =item object |
541 | =item object |
… | |
… | |
380 | are represented by the same codepoints in the Perl string, so no manual |
553 | are represented by the same codepoints in the Perl string, so no manual |
381 | decoding is necessary. |
554 | decoding is necessary. |
382 | |
555 | |
383 | =item number |
556 | =item number |
384 | |
557 | |
385 | A JSON number becomes either an integer or numeric (floating point) |
558 | A JSON number becomes either an integer, numeric (floating point) or |
386 | scalar in perl, depending on its range and any fractional parts. On the |
559 | string scalar in perl, depending on its range and any fractional parts. On |
387 | Perl level, there is no difference between those as Perl handles all the |
560 | the Perl level, there is no difference between those as Perl handles all |
388 | conversion details, but an integer may take slightly less memory and might |
561 | the conversion details, but an integer may take slightly less memory and |
389 | represent more values exactly than (floating point) numbers. |
562 | might represent more values exactly than (floating point) numbers. |
|
|
563 | |
|
|
564 | If the number consists of digits only, JSON::XS will try to represent |
|
|
565 | it as an integer value. If that fails, it will try to represent it as |
|
|
566 | a numeric (floating point) value if that is possible without loss of |
|
|
567 | precision. Otherwise it will preserve the number as a string value. |
|
|
568 | |
|
|
569 | Numbers containing a fractional or exponential part will always be |
|
|
570 | represented as numeric (floating point) values, possibly at a loss of |
|
|
571 | precision. |
|
|
572 | |
|
|
573 | This might create round-tripping problems as numbers might become strings, |
|
|
574 | but as Perl is typeless there is no other way to do it. |
390 | |
575 | |
391 | =item true, false |
576 | =item true, false |
392 | |
577 | |
393 | These JSON atoms become C<0>, C<1>, respectively. Information is lost in |
578 | These JSON atoms become C<JSON::XS::true> and C<JSON::XS::false>, |
394 | this process. Future versions might represent those values differently, |
579 | respectively. They are overloaded to act almost exactly like the numbers |
395 | but they will be guarenteed to act like these integers would normally in |
580 | C<1> and C<0>. You can check wether a scalar is a JSON boolean by using |
396 | Perl. |
581 | the C<JSON::XS::is_bool> function. |
397 | |
582 | |
398 | =item null |
583 | =item null |
399 | |
584 | |
400 | A JSON null atom becomes C<undef> in Perl. |
585 | A JSON null atom becomes C<undef> in Perl. |
401 | |
586 | |
402 | =back |
587 | =back |
|
|
588 | |
403 | |
589 | |
404 | =head2 PERL -> JSON |
590 | =head2 PERL -> JSON |
405 | |
591 | |
406 | The mapping from Perl to JSON is slightly more difficult, as Perl is a |
592 | The mapping from Perl to JSON is slightly more difficult, as Perl is a |
407 | truly typeless language, so we can only guess which JSON type is meant by |
593 | truly typeless language, so we can only guess which JSON type is meant by |
… | |
… | |
432 | C<1>, which get turned into C<false> and C<true> atoms in JSON. You can |
618 | C<1>, which get turned into C<false> and C<true> atoms in JSON. You can |
433 | also use C<JSON::XS::false> and C<JSON::XS::true> to improve readability. |
619 | also use C<JSON::XS::false> and C<JSON::XS::true> to improve readability. |
434 | |
620 | |
435 | to_json [\0,JSON::XS::true] # yields [false,true] |
621 | to_json [\0,JSON::XS::true] # yields [false,true] |
436 | |
622 | |
|
|
623 | =item JSON::XS::true, JSON::XS::false |
|
|
624 | |
|
|
625 | These special values become JSON true and JSON false values, |
|
|
626 | respectively. You cna alos use C<\1> and C<\0> directly if you want. |
|
|
627 | |
437 | =item blessed objects |
628 | =item blessed objects |
438 | |
629 | |
439 | Blessed objects are not allowed. JSON::XS currently tries to encode their |
630 | Blessed objects are not allowed. JSON::XS currently tries to encode their |
440 | underlying representation (hash- or arrayref), but this behaviour might |
631 | underlying representation (hash- or arrayref), but this behaviour might |
441 | change in future versions. |
632 | change in future versions. |
… | |
… | |
562 | |
753 | |
563 | Does not check input for validity. |
754 | Does not check input for validity. |
564 | |
755 | |
565 | =back |
756 | =back |
566 | |
757 | |
|
|
758 | |
|
|
759 | =head2 JSON and YAML |
|
|
760 | |
|
|
761 | You often hear that JSON is a subset (or a close subset) of YAML. This is, |
|
|
762 | however, a mass hysteria and very far from the truth. In general, there is |
|
|
763 | no way to configure JSON::XS to output a data structure as valid YAML. |
|
|
764 | |
|
|
765 | If you really must use JSON::XS to generate YAML, you should use this |
|
|
766 | algorithm (subject to change in future versions): |
|
|
767 | |
|
|
768 | my $to_yaml = JSON::XS->new->utf8->space_after (1); |
|
|
769 | my $yaml = $to_yaml->encode ($ref) . "\n"; |
|
|
770 | |
|
|
771 | This will usually generate JSON texts that also parse as valid |
|
|
772 | YAML. Please note that YAML has hardcoded limits on (simple) object key |
|
|
773 | lengths that JSON doesn't have, so you should make sure that your hash |
|
|
774 | keys are noticably shorter than the 1024 characters YAML allows. |
|
|
775 | |
|
|
776 | There might be other incompatibilities that I am not aware of. In general |
|
|
777 | you should not try to generate YAML with a JSON generator or vice versa, |
|
|
778 | or try to parse JSON with a YAML parser or vice versa: chances are high |
|
|
779 | that you will run into severe interoperability problems. |
|
|
780 | |
|
|
781 | |
567 | =head2 SPEED |
782 | =head2 SPEED |
568 | |
783 | |
569 | It seems that JSON::XS is surprisingly fast, as shown in the following |
784 | It seems that JSON::XS is surprisingly fast, as shown in the following |
570 | tables. They have been generated with the help of the C<eg/bench> program |
785 | tables. They have been generated with the help of the C<eg/bench> program |
571 | in the JSON::XS distribution, to make it easy to compare on your own |
786 | in the JSON::XS distribution, to make it easy to compare on your own |
572 | system. |
787 | system. |
573 | |
788 | |
574 | First comes a comparison between various modules using a very short JSON |
789 | First comes a comparison between various modules using a very short |
575 | string: |
790 | single-line JSON string: |
576 | |
791 | |
577 | {"method": "handleMessage", "params": ["user1", "we were just talking"], "id": null} |
792 | {"method": "handleMessage", "params": ["user1", "we were just talking"], \ |
|
|
793 | "id": null, "array":[1,11,234,-5,1e5,1e7, true, false]} |
578 | |
794 | |
579 | It shows the number of encodes/decodes per second (JSON::XS uses the |
795 | It shows the number of encodes/decodes per second (JSON::XS uses |
580 | functional interface, while JSON::XS/2 uses the OO interface with |
796 | the functional interface, while JSON::XS/2 uses the OO interface |
581 | pretty-printing and hashkey sorting enabled). Higher is better: |
797 | with pretty-printing and hashkey sorting enabled, JSON::XS/3 enables |
|
|
798 | shrink). Higher is better: |
582 | |
799 | |
|
|
800 | Storable | 15779.925 | 14169.946 | |
|
|
801 | -----------+------------+------------+ |
583 | module | encode | decode | |
802 | module | encode | decode | |
584 | -----------|------------|------------| |
803 | -----------|------------|------------| |
585 | JSON | 11488.516 | 7823.035 | |
804 | JSON | 4990.842 | 4088.813 | |
586 | JSON::DWIW | 94708.054 | 129094.260 | |
805 | JSON::DWIW | 51653.990 | 71575.154 | |
587 | JSON::PC | 63884.157 | 128528.212 | |
806 | JSON::PC | 65948.176 | 74631.744 | |
588 | JSON::Syck | 34898.677 | 42096.911 | |
807 | JSON::PP | 8931.652 | 3817.168 | |
589 | JSON::XS | 654027.064 | 396423.669 | |
808 | JSON::Syck | 24877.248 | 27776.848 | |
590 | JSON::XS/2 | 371564.190 | 371725.613 | |
809 | JSON::XS | 388361.481 | 227951.304 | |
|
|
810 | JSON::XS/2 | 227951.304 | 218453.333 | |
|
|
811 | JSON::XS/3 | 338250.323 | 218453.333 | |
|
|
812 | Storable | 16500.016 | 135300.129 | |
591 | -----------+------------+------------+ |
813 | -----------+------------+------------+ |
592 | |
814 | |
593 | That is, JSON::XS is more than six times faster than JSON::DWIW on |
815 | That is, JSON::XS is about five times faster than JSON::DWIW on encoding, |
594 | encoding, more than three times faster on decoding, and about thirty times |
816 | about three times faster on decoding, and over fourty times faster |
595 | faster than JSON, even with pretty-printing and key sorting. |
817 | than JSON, even with pretty-printing and key sorting. It also compares |
|
|
818 | favourably to Storable for small amounts of data. |
596 | |
819 | |
597 | Using a longer test string (roughly 18KB, generated from Yahoo! Locals |
820 | Using a longer test string (roughly 18KB, generated from Yahoo! Locals |
598 | search API (http://nanoref.com/yahooapis/mgPdGg): |
821 | search API (http://nanoref.com/yahooapis/mgPdGg): |
599 | |
822 | |
600 | module | encode | decode | |
823 | module | encode | decode | |
601 | -----------|------------|------------| |
824 | -----------|------------|------------| |
602 | JSON | 273.023 | 44.674 | |
825 | JSON | 55.260 | 34.971 | |
603 | JSON::DWIW | 1089.383 | 1145.704 | |
826 | JSON::DWIW | 825.228 | 1082.513 | |
604 | JSON::PC | 3097.419 | 2393.921 | |
827 | JSON::PC | 3571.444 | 2394.829 | |
605 | JSON::Syck | 514.060 | 843.053 | |
828 | JSON::PP | 210.987 | 32.574 | |
606 | JSON::XS | 6479.668 | 3636.364 | |
829 | JSON::Syck | 552.551 | 787.544 | |
607 | JSON::XS/2 | 3774.221 | 3599.124 | |
830 | JSON::XS | 5780.463 | 4854.519 | |
|
|
831 | JSON::XS/2 | 3869.998 | 4798.975 | |
|
|
832 | JSON::XS/3 | 5862.880 | 4798.975 | |
|
|
833 | Storable | 4445.002 | 5235.027 | |
608 | -----------+------------+------------+ |
834 | -----------+------------+------------+ |
609 | |
835 | |
610 | Again, JSON::XS leads by far. |
836 | Again, JSON::XS leads by far (except for Storable which non-surprisingly |
|
|
837 | decodes faster). |
611 | |
838 | |
612 | On large strings containing lots of high unicode characters, some modules |
839 | On large strings containing lots of high unicode characters, some modules |
613 | (such as JSON::PC) seem to decode faster than JSON::XS, but the result |
840 | (such as JSON::PC) seem to decode faster than JSON::XS, but the result |
614 | will be broken due to missing (or wrong) unicode handling. Others refuse |
841 | will be broken due to missing (or wrong) unicode handling. Others refuse |
615 | to decode or encode properly, so it was impossible to prepare a fair |
842 | to decode or encode properly, so it was impossible to prepare a fair |
… | |
… | |
628 | Second, you need to avoid resource-starving attacks. That means you should |
855 | Second, you need to avoid resource-starving attacks. That means you should |
629 | limit the size of JSON texts you accept, or make sure then when your |
856 | limit the size of JSON texts you accept, or make sure then when your |
630 | resources run out, thats just fine (e.g. by using a separate process that |
857 | resources run out, thats just fine (e.g. by using a separate process that |
631 | can crash safely). The size of a JSON text in octets or characters is |
858 | can crash safely). The size of a JSON text in octets or characters is |
632 | usually a good indication of the size of the resources required to decode |
859 | usually a good indication of the size of the resources required to decode |
633 | it into a Perl structure. |
860 | it into a Perl structure. While JSON::XS can check the size of the JSON |
|
|
861 | text, it might be too late when you already have it in memory, so you |
|
|
862 | might want to check the size before you accept the string. |
634 | |
863 | |
635 | Third, JSON::XS recurses using the C stack when decoding objects and |
864 | Third, JSON::XS recurses using the C stack when decoding objects and |
636 | arrays. The C stack is a limited resource: for instance, on my amd64 |
865 | arrays. The C stack is a limited resource: for instance, on my amd64 |
637 | machine with 8MB of stack size I can decode around 180k nested arrays but |
866 | machine with 8MB of stack size I can decode around 180k nested arrays but |
638 | only 14k nested JSON objects (due to perl itself recursing deeply on croak |
867 | only 14k nested JSON objects (due to perl itself recursing deeply on croak |
… | |
… | |
643 | |
872 | |
644 | And last but least, something else could bomb you that I forgot to think |
873 | And last but least, something else could bomb you that I forgot to think |
645 | of. In that case, you get to keep the pieces. I am always open for hints, |
874 | of. In that case, you get to keep the pieces. I am always open for hints, |
646 | though... |
875 | though... |
647 | |
876 | |
|
|
877 | If you are using JSON::XS to return packets to consumption |
|
|
878 | by javascript scripts in a browser you should have a look at |
|
|
879 | L<http://jpsykes.com/47/practical-csrf-and-json-security> to see wether |
|
|
880 | you are vulnerable to some common attack vectors (which really are browser |
|
|
881 | design bugs, but it is still you who will have to deal with it, as major |
|
|
882 | browser developers care only for features, not about doing security |
|
|
883 | right). |
|
|
884 | |
648 | |
885 | |
649 | =head1 BUGS |
886 | =head1 BUGS |
650 | |
887 | |
651 | While the goal of this module is to be correct, that unfortunately does |
888 | While the goal of this module is to be correct, that unfortunately does |
652 | not mean its bug-free, only that I think its design is bug-free. It is |
889 | not mean its bug-free, only that I think its design is bug-free. It is |
653 | still relatively early in its development. If you keep reporting bugs they |
890 | still relatively early in its development. If you keep reporting bugs they |
654 | will be fixed swiftly, though. |
891 | will be fixed swiftly, though. |
655 | |
892 | |
656 | =cut |
893 | =cut |
657 | |
894 | |
|
|
895 | our $true = do { bless \(my $dummy = 1), "JSON::XS::Boolean" }; |
|
|
896 | our $false = do { bless \(my $dummy = 0), "JSON::XS::Boolean" }; |
|
|
897 | |
658 | sub true() { \1 } |
898 | sub true() { $true } |
659 | sub false() { \0 } |
899 | sub false() { $false } |
|
|
900 | |
|
|
901 | sub is_bool($) { |
|
|
902 | UNIVERSAL::isa $_[0], "JSON::XS::Boolean" |
|
|
903 | # or UNIVERSAL::isa $_[0], "JSON::Literal" |
|
|
904 | } |
|
|
905 | |
|
|
906 | XSLoader::load "JSON::XS", $VERSION; |
|
|
907 | |
|
|
908 | package JSON::XS::Boolean; |
|
|
909 | |
|
|
910 | use overload |
|
|
911 | "0+" => sub { ${$_[0]} }, |
|
|
912 | "++" => sub { $_[0] = ${$_[0]} + 1 }, |
|
|
913 | "--" => sub { $_[0] = ${$_[0]} - 1 }, |
|
|
914 | fallback => 1; |
660 | |
915 | |
661 | 1; |
916 | 1; |
662 | |
917 | |
663 | =head1 AUTHOR |
918 | =head1 AUTHOR |
664 | |
919 | |