… | |
… | |
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 |
… | |
… | |
247 | |
278 | |
248 | Example, space_before and indent disabled, space_after enabled: |
279 | Example, space_before and indent disabled, space_after enabled: |
249 | |
280 | |
250 | {"key": "value"} |
281 | {"key": "value"} |
251 | |
282 | |
|
|
283 | =item $json = $json->relaxed ([$enable]) |
|
|
284 | |
|
|
285 | If C<$enable> is true (or missing), then C<decode> will accept some |
|
|
286 | extensions to normal JSON syntax (see below). C<encode> will not be |
|
|
287 | affected in anyway. I<Be aware that this option makes you accept invalid |
|
|
288 | JSON texts as if they were valid!>. I suggest only to use this option to |
|
|
289 | parse application-specific files written by humans (configuration files, |
|
|
290 | resource files etc.) |
|
|
291 | |
|
|
292 | If C<$enable> is false (the default), then C<decode> will only accept |
|
|
293 | valid JSON texts. |
|
|
294 | |
|
|
295 | Currently accepted extensions are: |
|
|
296 | |
|
|
297 | =over 4 |
|
|
298 | |
|
|
299 | =item * list items can have an end-comma |
|
|
300 | |
|
|
301 | JSON I<separates> array elements and key-value pairs with commas. This |
|
|
302 | can be annoying if you write JSON texts manually and want to be able to |
|
|
303 | quickly append elements, so this extension accepts comma at the end of |
|
|
304 | such items not just between them: |
|
|
305 | |
|
|
306 | [ |
|
|
307 | 1, |
|
|
308 | 2, <- this comma not normally allowed |
|
|
309 | ] |
|
|
310 | { |
|
|
311 | "k1": "v1", |
|
|
312 | "k2": "v2", <- this comma not normally allowed |
|
|
313 | } |
|
|
314 | |
|
|
315 | =back |
|
|
316 | |
252 | =item $json = $json->canonical ([$enable]) |
317 | =item $json = $json->canonical ([$enable]) |
253 | |
318 | |
254 | If C<$enable> is true (or missing), then the C<encode> method will output JSON objects |
319 | If C<$enable> is true (or missing), then the C<encode> method will output JSON objects |
255 | by sorting their keys. This is adding a comparatively high overhead. |
320 | by sorting their keys. This is adding a comparatively high overhead. |
256 | |
321 | |
… | |
… | |
280 | Example, encode a Perl scalar as JSON value with enabled C<allow_nonref>, |
345 | Example, encode a Perl scalar as JSON value with enabled C<allow_nonref>, |
281 | resulting in an invalid JSON text: |
346 | resulting in an invalid JSON text: |
282 | |
347 | |
283 | JSON::XS->new->allow_nonref->encode ("Hello, World!") |
348 | JSON::XS->new->allow_nonref->encode ("Hello, World!") |
284 | => "Hello, World!" |
349 | => "Hello, World!" |
|
|
350 | |
|
|
351 | =item $json = $json->allow_blessed ([$enable]) |
|
|
352 | |
|
|
353 | If C<$enable> is true (or missing), then the C<encode> method will not |
|
|
354 | barf when it encounters a blessed reference. Instead, the value of the |
|
|
355 | B<convert_blessed> option will decide wether C<null> (C<convert_blessed> |
|
|
356 | disabled or no C<to_json> method found) or a representation of the |
|
|
357 | object (C<convert_blessed> enabled and C<to_json> method found) is being |
|
|
358 | encoded. Has no effect on C<decode>. |
|
|
359 | |
|
|
360 | If C<$enable> is false (the default), then C<encode> will throw an |
|
|
361 | exception when it encounters a blessed object. |
|
|
362 | |
|
|
363 | =item $json = $json->convert_blessed ([$enable]) |
|
|
364 | |
|
|
365 | If C<$enable> is true (or missing), then C<encode>, upon encountering a |
|
|
366 | blessed object, will check for the availability of the C<TO_JSON> method |
|
|
367 | on the object's class. If found, it will be called in scalar context |
|
|
368 | and the resulting scalar will be encoded instead of the object. If no |
|
|
369 | C<TO_JSON> method is found, the value of C<allow_blessed> will decide what |
|
|
370 | to do. |
|
|
371 | |
|
|
372 | The C<TO_JSON> method may safely call die if it wants. If C<TO_JSON> |
|
|
373 | returns other blessed objects, those will be handled in the same |
|
|
374 | way. C<TO_JSON> must take care of not causing an endless recursion cycle |
|
|
375 | (== crash) in this case. The name of C<TO_JSON> was chosen because other |
|
|
376 | methods called by the Perl core (== not by the user of the object) are |
|
|
377 | usually in upper case letters and to avoid collisions with the C<to_json> |
|
|
378 | function. |
|
|
379 | |
|
|
380 | This setting does not yet influence C<decode> in any way, but in the |
|
|
381 | future, global hooks might get installed that influence C<decode> and are |
|
|
382 | enabled by this setting. |
|
|
383 | |
|
|
384 | If C<$enable> is false, then the C<allow_blessed> setting will decide what |
|
|
385 | to do when a blessed object is found. |
|
|
386 | |
|
|
387 | =item $json = $json->filter_json_object ([$coderef->($hashref)]) |
|
|
388 | |
|
|
389 | When C<$coderef> is specified, it will be called from C<decode> each |
|
|
390 | time it decodes a JSON object. The only argument is a reference to the |
|
|
391 | newly-created hash. If the code references returns a single scalar (which |
|
|
392 | need not be a reference), this value (i.e. a copy of that scalar to avoid |
|
|
393 | aliasing) is inserted into the deserialised data structure. If it returns |
|
|
394 | an empty list (NOTE: I<not> C<undef>, which is a valid scalar), the |
|
|
395 | original deserialised hash will be inserted. This setting can slow down |
|
|
396 | decoding considerably. |
|
|
397 | |
|
|
398 | When C<$coderef> is omitted or undefined, any existing callback will |
|
|
399 | be removed and C<decode> will not change the deserialised hash in any |
|
|
400 | way. |
|
|
401 | |
|
|
402 | Example, convert all JSON objects into the integer 5: |
|
|
403 | |
|
|
404 | my $js = JSON::XS->new->filter_json_object (sub { 5 }); |
|
|
405 | # returns [5] |
|
|
406 | $js->decode ('[{}]') |
|
|
407 | # throw an exception because allow_nonref is not enabled |
|
|
408 | # so a lone 5 is not allowed. |
|
|
409 | $js->decode ('{"a":1, "b":2}'); |
|
|
410 | |
|
|
411 | =item $json = $json->filter_json_single_key_object ($key [=> $coderef->($value)]) |
|
|
412 | |
|
|
413 | Works remotely similar to C<filter_json_object>, but is only called for |
|
|
414 | JSON objects having a single key named C<$key>. |
|
|
415 | |
|
|
416 | This C<$coderef> is called before the one specified via |
|
|
417 | C<filter_json_object>, if any. It gets passed the single value in the JSON |
|
|
418 | object. If it returns a single value, it will be inserted into the data |
|
|
419 | structure. If it returns nothing (not even C<undef> but the empty list), |
|
|
420 | the callback from C<filter_json_object> will be called next, as if no |
|
|
421 | single-key callback were specified. |
|
|
422 | |
|
|
423 | If C<$coderef> is omitted or undefined, the corresponding callback will be |
|
|
424 | disabled. There can only ever be one callback for a given key. |
|
|
425 | |
|
|
426 | As this callback gets called less often then the C<filter_json_object> |
|
|
427 | one, decoding speed will not usually suffer as much. Therefore, single-key |
|
|
428 | objects make excellent targets to serialise Perl objects into, especially |
|
|
429 | as single-key JSON objects are as close to the type-tagged value concept |
|
|
430 | as JSON gets (its basically an ID/VALUE tuple). Of course, JSON does not |
|
|
431 | support this in any way, so you need to make sure your data never looks |
|
|
432 | like a serialised Perl hash. |
|
|
433 | |
|
|
434 | Typical names for the single object key are C<__class_whatever__>, or |
|
|
435 | C<$__dollars_are_rarely_used__$> or C<}ugly_brace_placement>, or even |
|
|
436 | things like C<__class_md5sum(classname)__>, to reduce the risk of clashing |
|
|
437 | with real hashes. |
|
|
438 | |
|
|
439 | Example, decode JSON objects of the form C<< { "__widget__" => <id> } >> |
|
|
440 | into the corresponding C<< $WIDGET{<id>} >> object: |
|
|
441 | |
|
|
442 | # return whatever is in $WIDGET{5}: |
|
|
443 | JSON::XS |
|
|
444 | ->new |
|
|
445 | ->filter_json_single_key_object (__widget__ => sub { |
|
|
446 | $WIDGET{ $_[0] } |
|
|
447 | }) |
|
|
448 | ->decode ('{"__widget__": 5') |
|
|
449 | |
|
|
450 | # this can be used with a TO_JSON method in some "widget" class |
|
|
451 | # for serialisation to json: |
|
|
452 | sub WidgetBase::TO_JSON { |
|
|
453 | my ($self) = @_; |
|
|
454 | |
|
|
455 | unless ($self->{id}) { |
|
|
456 | $self->{id} = ..get..some..id..; |
|
|
457 | $WIDGET{$self->{id}} = $self; |
|
|
458 | } |
|
|
459 | |
|
|
460 | { __widget__ => $self->{id} } |
|
|
461 | } |
285 | |
462 | |
286 | =item $json = $json->shrink ([$enable]) |
463 | =item $json = $json->shrink ([$enable]) |
287 | |
464 | |
288 | Perl usually over-allocates memory a bit when allocating space for |
465 | Perl usually over-allocates memory a bit when allocating space for |
289 | strings. This flag optionally resizes strings generated by either |
466 | strings. This flag optionally resizes strings generated by either |
… | |
… | |
322 | given character in a string. |
499 | given character in a string. |
323 | |
500 | |
324 | Setting the maximum depth to one disallows any nesting, so that ensures |
501 | Setting the maximum depth to one disallows any nesting, so that ensures |
325 | that the object is only a single hash/object or array. |
502 | that the object is only a single hash/object or array. |
326 | |
503 | |
327 | The argument to C<max_depth> will be rounded up to the next nearest power |
504 | The argument to C<max_depth> will be rounded up to the next highest power |
328 | of two. |
505 | of two. If no argument is given, the highest possible setting will be |
|
|
506 | used, which is rarely useful. |
|
|
507 | |
|
|
508 | See SECURITY CONSIDERATIONS, below, for more info on why this is useful. |
|
|
509 | |
|
|
510 | =item $json = $json->max_size ([$maximum_string_size]) |
|
|
511 | |
|
|
512 | Set the maximum length a JSON text may have (in bytes) where decoding is |
|
|
513 | being attempted. The default is C<0>, meaning no limit. When C<decode> |
|
|
514 | is called on a string longer then this number of characters it will not |
|
|
515 | attempt to decode the string but throw an exception. This setting has no |
|
|
516 | effect on C<encode> (yet). |
|
|
517 | |
|
|
518 | The argument to C<max_size> will be rounded up to the next B<highest> |
|
|
519 | power of two (so may be more than requested). If no argument is given, the |
|
|
520 | limit check will be deactivated (same as when C<0> is specified). |
329 | |
521 | |
330 | See SECURITY CONSIDERATIONS, below, for more info on why this is useful. |
522 | See SECURITY CONSIDERATIONS, below, for more info on why this is useful. |
331 | |
523 | |
332 | =item $json_text = $json->encode ($perl_scalar) |
524 | =item $json_text = $json->encode ($perl_scalar) |
333 | |
525 | |
… | |
… | |
345 | |
537 | |
346 | JSON numbers and strings become simple Perl scalars. JSON arrays become |
538 | JSON numbers and strings become simple Perl scalars. JSON arrays become |
347 | Perl arrayrefs and JSON objects become Perl hashrefs. C<true> becomes |
539 | 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>. |
540 | C<1>, C<false> becomes C<0> and C<null> becomes C<undef>. |
349 | |
541 | |
|
|
542 | =item ($perl_scalar, $characters) = $json->decode_prefix ($json_text) |
|
|
543 | |
|
|
544 | This works like the C<decode> method, but instead of raising an exception |
|
|
545 | when there is trailing garbage after the first JSON object, it will |
|
|
546 | silently stop parsing there and return the number of characters consumed |
|
|
547 | so far. |
|
|
548 | |
|
|
549 | This is useful if your JSON texts are not delimited by an outer protocol |
|
|
550 | (which is not the brightest thing to do in the first place) and you need |
|
|
551 | to know where the JSON text ends. |
|
|
552 | |
|
|
553 | JSON::XS->new->decode_prefix ("[1] the tail") |
|
|
554 | => ([], 3) |
|
|
555 | |
350 | =back |
556 | =back |
351 | |
557 | |
352 | |
558 | |
353 | =head1 MAPPING |
559 | =head1 MAPPING |
354 | |
560 | |
… | |
… | |
359 | |
565 | |
360 | For the more enlightened: note that in the following descriptions, |
566 | For the more enlightened: note that in the following descriptions, |
361 | lowercase I<perl> refers to the Perl interpreter, while uppcercase I<Perl> |
567 | lowercase I<perl> refers to the Perl interpreter, while uppcercase I<Perl> |
362 | refers to the abstract Perl language itself. |
568 | refers to the abstract Perl language itself. |
363 | |
569 | |
|
|
570 | |
364 | =head2 JSON -> PERL |
571 | =head2 JSON -> PERL |
365 | |
572 | |
366 | =over 4 |
573 | =over 4 |
367 | |
574 | |
368 | =item object |
575 | =item object |
… | |
… | |
380 | are represented by the same codepoints in the Perl string, so no manual |
587 | are represented by the same codepoints in the Perl string, so no manual |
381 | decoding is necessary. |
588 | decoding is necessary. |
382 | |
589 | |
383 | =item number |
590 | =item number |
384 | |
591 | |
385 | A JSON number becomes either an integer or numeric (floating point) |
592 | 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 |
593 | 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 |
594 | 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 |
595 | the conversion details, but an integer may take slightly less memory and |
389 | represent more values exactly than (floating point) numbers. |
596 | might represent more values exactly than (floating point) numbers. |
|
|
597 | |
|
|
598 | If the number consists of digits only, JSON::XS will try to represent |
|
|
599 | it as an integer value. If that fails, it will try to represent it as |
|
|
600 | a numeric (floating point) value if that is possible without loss of |
|
|
601 | precision. Otherwise it will preserve the number as a string value. |
|
|
602 | |
|
|
603 | Numbers containing a fractional or exponential part will always be |
|
|
604 | represented as numeric (floating point) values, possibly at a loss of |
|
|
605 | precision. |
|
|
606 | |
|
|
607 | This might create round-tripping problems as numbers might become strings, |
|
|
608 | but as Perl is typeless there is no other way to do it. |
390 | |
609 | |
391 | =item true, false |
610 | =item true, false |
392 | |
611 | |
393 | These JSON atoms become C<0>, C<1>, respectively. Information is lost in |
612 | These JSON atoms become C<JSON::XS::true> and C<JSON::XS::false>, |
394 | this process. Future versions might represent those values differently, |
613 | 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 |
614 | C<1> and C<0>. You can check wether a scalar is a JSON boolean by using |
396 | Perl. |
615 | the C<JSON::XS::is_bool> function. |
397 | |
616 | |
398 | =item null |
617 | =item null |
399 | |
618 | |
400 | A JSON null atom becomes C<undef> in Perl. |
619 | A JSON null atom becomes C<undef> in Perl. |
401 | |
620 | |
402 | =back |
621 | =back |
|
|
622 | |
403 | |
623 | |
404 | =head2 PERL -> JSON |
624 | =head2 PERL -> JSON |
405 | |
625 | |
406 | The mapping from Perl to JSON is slightly more difficult, as Perl is a |
626 | 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 |
627 | 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 |
652 | 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. |
653 | also use C<JSON::XS::false> and C<JSON::XS::true> to improve readability. |
434 | |
654 | |
435 | to_json [\0,JSON::XS::true] # yields [false,true] |
655 | to_json [\0,JSON::XS::true] # yields [false,true] |
436 | |
656 | |
|
|
657 | =item JSON::XS::true, JSON::XS::false |
|
|
658 | |
|
|
659 | These special values become JSON true and JSON false values, |
|
|
660 | respectively. You cna alos use C<\1> and C<\0> directly if you want. |
|
|
661 | |
437 | =item blessed objects |
662 | =item blessed objects |
438 | |
663 | |
439 | Blessed objects are not allowed. JSON::XS currently tries to encode their |
664 | Blessed objects are not allowed. JSON::XS currently tries to encode their |
440 | underlying representation (hash- or arrayref), but this behaviour might |
665 | underlying representation (hash- or arrayref), but this behaviour might |
441 | change in future versions. |
666 | change in future versions. |
… | |
… | |
562 | |
787 | |
563 | Does not check input for validity. |
788 | Does not check input for validity. |
564 | |
789 | |
565 | =back |
790 | =back |
566 | |
791 | |
|
|
792 | |
|
|
793 | =head2 JSON and YAML |
|
|
794 | |
|
|
795 | You often hear that JSON is a subset (or a close subset) of YAML. This is, |
|
|
796 | however, a mass hysteria and very far from the truth. In general, there is |
|
|
797 | no way to configure JSON::XS to output a data structure as valid YAML. |
|
|
798 | |
|
|
799 | If you really must use JSON::XS to generate YAML, you should use this |
|
|
800 | algorithm (subject to change in future versions): |
|
|
801 | |
|
|
802 | my $to_yaml = JSON::XS->new->utf8->space_after (1); |
|
|
803 | my $yaml = $to_yaml->encode ($ref) . "\n"; |
|
|
804 | |
|
|
805 | This will usually generate JSON texts that also parse as valid |
|
|
806 | YAML. Please note that YAML has hardcoded limits on (simple) object key |
|
|
807 | lengths that JSON doesn't have, so you should make sure that your hash |
|
|
808 | keys are noticably shorter than the 1024 characters YAML allows. |
|
|
809 | |
|
|
810 | There might be other incompatibilities that I am not aware of. In general |
|
|
811 | you should not try to generate YAML with a JSON generator or vice versa, |
|
|
812 | or try to parse JSON with a YAML parser or vice versa: chances are high |
|
|
813 | that you will run into severe interoperability problems. |
|
|
814 | |
|
|
815 | |
567 | =head2 SPEED |
816 | =head2 SPEED |
568 | |
817 | |
569 | It seems that JSON::XS is surprisingly fast, as shown in the following |
818 | 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 |
819 | 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 |
820 | in the JSON::XS distribution, to make it easy to compare on your own |
572 | system. |
821 | system. |
573 | |
822 | |
574 | First comes a comparison between various modules using a very short JSON |
823 | First comes a comparison between various modules using a very short |
575 | string: |
824 | single-line JSON string: |
576 | |
825 | |
577 | {"method": "handleMessage", "params": ["user1", "we were just talking"], "id": null} |
826 | {"method": "handleMessage", "params": ["user1", "we were just talking"], \ |
|
|
827 | "id": null, "array":[1,11,234,-5,1e5,1e7, true, false]} |
578 | |
828 | |
579 | It shows the number of encodes/decodes per second (JSON::XS uses the |
829 | It shows the number of encodes/decodes per second (JSON::XS uses |
580 | functional interface, while JSON::XS/2 uses the OO interface with |
830 | the functional interface, while JSON::XS/2 uses the OO interface |
581 | pretty-printing and hashkey sorting enabled). Higher is better: |
831 | with pretty-printing and hashkey sorting enabled, JSON::XS/3 enables |
|
|
832 | shrink). Higher is better: |
582 | |
833 | |
|
|
834 | Storable | 15779.925 | 14169.946 | |
|
|
835 | -----------+------------+------------+ |
583 | module | encode | decode | |
836 | module | encode | decode | |
584 | -----------|------------|------------| |
837 | -----------|------------|------------| |
585 | JSON | 11488.516 | 7823.035 | |
838 | JSON | 4990.842 | 4088.813 | |
586 | JSON::DWIW | 94708.054 | 129094.260 | |
839 | JSON::DWIW | 51653.990 | 71575.154 | |
587 | JSON::PC | 63884.157 | 128528.212 | |
840 | JSON::PC | 65948.176 | 74631.744 | |
588 | JSON::Syck | 34898.677 | 42096.911 | |
841 | JSON::PP | 8931.652 | 3817.168 | |
589 | JSON::XS | 654027.064 | 396423.669 | |
842 | JSON::Syck | 24877.248 | 27776.848 | |
590 | JSON::XS/2 | 371564.190 | 371725.613 | |
843 | JSON::XS | 388361.481 | 227951.304 | |
|
|
844 | JSON::XS/2 | 227951.304 | 218453.333 | |
|
|
845 | JSON::XS/3 | 338250.323 | 218453.333 | |
|
|
846 | Storable | 16500.016 | 135300.129 | |
591 | -----------+------------+------------+ |
847 | -----------+------------+------------+ |
592 | |
848 | |
593 | That is, JSON::XS is more than six times faster than JSON::DWIW on |
849 | 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 |
850 | about three times faster on decoding, and over fourty times faster |
595 | faster than JSON, even with pretty-printing and key sorting. |
851 | than JSON, even with pretty-printing and key sorting. It also compares |
|
|
852 | favourably to Storable for small amounts of data. |
596 | |
853 | |
597 | Using a longer test string (roughly 18KB, generated from Yahoo! Locals |
854 | Using a longer test string (roughly 18KB, generated from Yahoo! Locals |
598 | search API (http://nanoref.com/yahooapis/mgPdGg): |
855 | search API (http://nanoref.com/yahooapis/mgPdGg): |
599 | |
856 | |
600 | module | encode | decode | |
857 | module | encode | decode | |
601 | -----------|------------|------------| |
858 | -----------|------------|------------| |
602 | JSON | 273.023 | 44.674 | |
859 | JSON | 55.260 | 34.971 | |
603 | JSON::DWIW | 1089.383 | 1145.704 | |
860 | JSON::DWIW | 825.228 | 1082.513 | |
604 | JSON::PC | 3097.419 | 2393.921 | |
861 | JSON::PC | 3571.444 | 2394.829 | |
605 | JSON::Syck | 514.060 | 843.053 | |
862 | JSON::PP | 210.987 | 32.574 | |
606 | JSON::XS | 6479.668 | 3636.364 | |
863 | JSON::Syck | 552.551 | 787.544 | |
607 | JSON::XS/2 | 3774.221 | 3599.124 | |
864 | JSON::XS | 5780.463 | 4854.519 | |
|
|
865 | JSON::XS/2 | 3869.998 | 4798.975 | |
|
|
866 | JSON::XS/3 | 5862.880 | 4798.975 | |
|
|
867 | Storable | 4445.002 | 5235.027 | |
608 | -----------+------------+------------+ |
868 | -----------+------------+------------+ |
609 | |
869 | |
610 | Again, JSON::XS leads by far. |
870 | Again, JSON::XS leads by far (except for Storable which non-surprisingly |
|
|
871 | decodes faster). |
611 | |
872 | |
612 | On large strings containing lots of high unicode characters, some modules |
873 | 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 |
874 | (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 |
875 | 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 |
876 | 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 |
889 | 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 |
890 | 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 |
891 | 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 |
892 | 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 |
893 | usually a good indication of the size of the resources required to decode |
633 | it into a Perl structure. |
894 | it into a Perl structure. While JSON::XS can check the size of the JSON |
|
|
895 | text, it might be too late when you already have it in memory, so you |
|
|
896 | might want to check the size before you accept the string. |
634 | |
897 | |
635 | Third, JSON::XS recurses using the C stack when decoding objects and |
898 | 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 |
899 | 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 |
900 | 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 |
901 | only 14k nested JSON objects (due to perl itself recursing deeply on croak |
… | |
… | |
640 | conservative, the default nesting limit is set to 512. If your process |
903 | conservative, the default nesting limit is set to 512. If your process |
641 | has a smaller stack, you should adjust this setting accordingly with the |
904 | has a smaller stack, you should adjust this setting accordingly with the |
642 | C<max_depth> method. |
905 | C<max_depth> method. |
643 | |
906 | |
644 | And last but least, something else could bomb you that I forgot to think |
907 | 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 alway sopen for hints, |
908 | of. In that case, you get to keep the pieces. I am always open for hints, |
646 | though... |
909 | though... |
|
|
910 | |
|
|
911 | If you are using JSON::XS to return packets to consumption |
|
|
912 | by javascript scripts in a browser you should have a look at |
|
|
913 | L<http://jpsykes.com/47/practical-csrf-and-json-security> to see wether |
|
|
914 | you are vulnerable to some common attack vectors (which really are browser |
|
|
915 | design bugs, but it is still you who will have to deal with it, as major |
|
|
916 | browser developers care only for features, not about doing security |
|
|
917 | right). |
647 | |
918 | |
648 | |
919 | |
649 | =head1 BUGS |
920 | =head1 BUGS |
650 | |
921 | |
651 | While the goal of this module is to be correct, that unfortunately does |
922 | While the goal of this module is to be correct, that unfortunately does |
… | |
… | |
653 | still relatively early in its development. If you keep reporting bugs they |
924 | still relatively early in its development. If you keep reporting bugs they |
654 | will be fixed swiftly, though. |
925 | will be fixed swiftly, though. |
655 | |
926 | |
656 | =cut |
927 | =cut |
657 | |
928 | |
|
|
929 | our $true = do { bless \(my $dummy = 1), "JSON::XS::Boolean" }; |
|
|
930 | our $false = do { bless \(my $dummy = 0), "JSON::XS::Boolean" }; |
|
|
931 | |
658 | sub true() { \1 } |
932 | sub true() { $true } |
659 | sub false() { \0 } |
933 | sub false() { $false } |
|
|
934 | |
|
|
935 | sub is_bool($) { |
|
|
936 | UNIVERSAL::isa $_[0], "JSON::XS::Boolean" |
|
|
937 | # or UNIVERSAL::isa $_[0], "JSON::Literal" |
|
|
938 | } |
|
|
939 | |
|
|
940 | XSLoader::load "JSON::XS", $VERSION; |
|
|
941 | |
|
|
942 | package JSON::XS::Boolean; |
|
|
943 | |
|
|
944 | use overload |
|
|
945 | "0+" => sub { ${$_[0]} }, |
|
|
946 | "++" => sub { $_[0] = ${$_[0]} + 1 }, |
|
|
947 | "--" => sub { $_[0] = ${$_[0]} - 1 }, |
|
|
948 | fallback => 1; |
660 | |
949 | |
661 | 1; |
950 | 1; |
662 | |
951 | |
663 | =head1 AUTHOR |
952 | =head1 AUTHOR |
664 | |
953 | |