… | |
… | |
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 | our $VERSION = '1.3'; |
86 | our $VERSION = '1.5'; |
91 | our @ISA = qw(Exporter); |
87 | our @ISA = qw(Exporter); |
92 | |
88 | |
93 | our @EXPORT = qw(to_json from_json objToJson jsonToObj); |
89 | our @EXPORT = qw(to_json from_json); |
94 | |
90 | |
95 | use Exporter; |
91 | use Exporter; |
96 | use XSLoader; |
92 | use XSLoader; |
97 | |
93 | |
98 | =head1 FUNCTIONAL INTERFACE |
94 | =head1 FUNCTIONAL INTERFACE |
… | |
… | |
282 | |
278 | |
283 | Example, space_before and indent disabled, space_after enabled: |
279 | Example, space_before and indent disabled, space_after enabled: |
284 | |
280 | |
285 | {"key": "value"} |
281 | {"key": "value"} |
286 | |
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 | |
287 | =item $json = $json->canonical ([$enable]) |
317 | =item $json = $json->canonical ([$enable]) |
288 | |
318 | |
289 | 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 |
290 | by sorting their keys. This is adding a comparatively high overhead. |
320 | by sorting their keys. This is adding a comparatively high overhead. |
291 | |
321 | |
… | |
… | |
315 | 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>, |
316 | resulting in an invalid JSON text: |
346 | resulting in an invalid JSON text: |
317 | |
347 | |
318 | JSON::XS->new->allow_nonref->encode ("Hello, World!") |
348 | JSON::XS->new->allow_nonref->encode ("Hello, World!") |
319 | => "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 | } |
320 | |
462 | |
321 | =item $json = $json->shrink ([$enable]) |
463 | =item $json = $json->shrink ([$enable]) |
322 | |
464 | |
323 | Perl usually over-allocates memory a bit when allocating space for |
465 | Perl usually over-allocates memory a bit when allocating space for |
324 | strings. This flag optionally resizes strings generated by either |
466 | strings. This flag optionally resizes strings generated by either |
… | |
… | |
357 | given character in a string. |
499 | given character in a string. |
358 | |
500 | |
359 | 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 |
360 | that the object is only a single hash/object or array. |
502 | that the object is only a single hash/object or array. |
361 | |
503 | |
362 | 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 |
363 | 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). |
364 | |
521 | |
365 | 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. |
366 | |
523 | |
367 | =item $json_text = $json->encode ($perl_scalar) |
524 | =item $json_text = $json->encode ($perl_scalar) |
368 | |
525 | |
… | |
… | |
430 | 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 |
431 | decoding is necessary. |
588 | decoding is necessary. |
432 | |
589 | |
433 | =item number |
590 | =item number |
434 | |
591 | |
435 | A JSON number becomes either an integer or numeric (floating point) |
592 | A JSON number becomes either an integer, numeric (floating point) or |
436 | 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 |
437 | 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 |
438 | 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 |
439 | 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. |
440 | |
609 | |
441 | =item true, false |
610 | =item true, false |
442 | |
611 | |
443 | These JSON atoms become C<JSON::XS::true> and C<JSON::XS::false>, |
612 | These JSON atoms become C<JSON::XS::true> and C<JSON::XS::false>, |
444 | respectively. They are overloaded to act almost exactly like the numbers |
613 | respectively. They are overloaded to act almost exactly like the numbers |
… | |
… | |
660 | It shows the number of encodes/decodes per second (JSON::XS uses |
829 | It shows the number of encodes/decodes per second (JSON::XS uses |
661 | the functional interface, while JSON::XS/2 uses the OO interface |
830 | the functional interface, while JSON::XS/2 uses the OO interface |
662 | with pretty-printing and hashkey sorting enabled, JSON::XS/3 enables |
831 | with pretty-printing and hashkey sorting enabled, JSON::XS/3 enables |
663 | shrink). Higher is better: |
832 | shrink). Higher is better: |
664 | |
833 | |
|
|
834 | Storable | 15779.925 | 14169.946 | |
|
|
835 | -----------+------------+------------+ |
665 | module | encode | decode | |
836 | module | encode | decode | |
666 | -----------|------------|------------| |
837 | -----------|------------|------------| |
667 | JSON | 7645.468 | 4208.613 | |
838 | JSON | 4990.842 | 4088.813 | |
668 | JSON::DWIW | 40721.398 | 77101.176 | |
839 | JSON::DWIW | 51653.990 | 71575.154 | |
669 | JSON::PC | 65948.176 | 78251.940 | |
840 | JSON::PC | 65948.176 | 74631.744 | |
670 | JSON::Syck | 22844.793 | 26479.192 | |
841 | JSON::PP | 8931.652 | 3817.168 | |
|
|
842 | JSON::Syck | 24877.248 | 27776.848 | |
671 | JSON::XS | 388361.481 | 199728.762 | |
843 | JSON::XS | 388361.481 | 227951.304 | |
672 | JSON::XS/2 | 218453.333 | 192399.266 | |
844 | JSON::XS/2 | 227951.304 | 218453.333 | |
673 | JSON::XS/3 | 338250.323 | 192399.266 | |
845 | JSON::XS/3 | 338250.323 | 218453.333 | |
674 | Storable | 15779.925 | 14169.946 | |
846 | Storable | 16500.016 | 135300.129 | |
675 | -----------+------------+------------+ |
847 | -----------+------------+------------+ |
676 | |
848 | |
677 | That is, JSON::XS is about five times faster than JSON::DWIW on encoding, |
849 | That is, JSON::XS is about five times faster than JSON::DWIW on encoding, |
678 | about three times faster on decoding, and over fourty times faster |
850 | about three times faster on decoding, and over fourty times faster |
679 | than JSON, even with pretty-printing and key sorting. It also compares |
851 | than JSON, even with pretty-printing and key sorting. It also compares |
… | |
… | |
682 | Using a longer test string (roughly 18KB, generated from Yahoo! Locals |
854 | Using a longer test string (roughly 18KB, generated from Yahoo! Locals |
683 | search API (http://nanoref.com/yahooapis/mgPdGg): |
855 | search API (http://nanoref.com/yahooapis/mgPdGg): |
684 | |
856 | |
685 | module | encode | decode | |
857 | module | encode | decode | |
686 | -----------|------------|------------| |
858 | -----------|------------|------------| |
687 | JSON | 254.685 | 37.665 | |
859 | JSON | 55.260 | 34.971 | |
688 | JSON::DWIW | 843.343 | 1049.731 | |
860 | JSON::DWIW | 825.228 | 1082.513 | |
689 | JSON::PC | 3602.116 | 2307.352 | |
861 | JSON::PC | 3571.444 | 2394.829 | |
|
|
862 | JSON::PP | 210.987 | 32.574 | |
690 | JSON::Syck | 505.107 | 787.899 | |
863 | JSON::Syck | 552.551 | 787.544 | |
691 | JSON::XS | 5747.196 | 3690.220 | |
864 | JSON::XS | 5780.463 | 4854.519 | |
692 | JSON::XS/2 | 3968.121 | 3676.634 | |
865 | JSON::XS/2 | 3869.998 | 4798.975 | |
693 | JSON::XS/3 | 6105.246 | 3662.508 | |
866 | JSON::XS/3 | 5862.880 | 4798.975 | |
694 | Storable | 4417.337 | 5285.161 | |
867 | Storable | 4445.002 | 5235.027 | |
695 | -----------+------------+------------+ |
868 | -----------+------------+------------+ |
696 | |
869 | |
697 | Again, JSON::XS leads by far (except for Storable which non-surprisingly |
870 | Again, JSON::XS leads by far (except for Storable which non-surprisingly |
698 | decodes faster). |
871 | decodes faster). |
699 | |
872 | |
… | |
… | |
716 | 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 |
717 | 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 |
718 | 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 |
719 | 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 |
720 | 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 |
721 | 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. |
722 | |
897 | |
723 | 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 |
724 | 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 |
725 | 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 |
726 | 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 |
… | |
… | |
757 | sub true() { $true } |
932 | sub true() { $true } |
758 | sub false() { $false } |
933 | sub false() { $false } |
759 | |
934 | |
760 | sub is_bool($) { |
935 | sub is_bool($) { |
761 | UNIVERSAL::isa $_[0], "JSON::XS::Boolean" |
936 | UNIVERSAL::isa $_[0], "JSON::XS::Boolean" |
762 | or UNIVERSAL::isa $_[0], "JSON::Literal" |
937 | # or UNIVERSAL::isa $_[0], "JSON::Literal" |
763 | } |
938 | } |
764 | |
939 | |
765 | XSLoader::load "JSON::XS", $VERSION; |
940 | XSLoader::load "JSON::XS", $VERSION; |
766 | |
941 | |
767 | package JSON::XS::Boolean; |
942 | package JSON::XS::Boolean; |