… | |
… | |
4 | |
4 | |
5 | =head1 SYNOPSIS |
5 | =head1 SYNOPSIS |
6 | |
6 | |
7 | use JSON::XS; |
7 | use JSON::XS; |
8 | |
8 | |
9 | # exported functions, croak on error |
9 | # exported functions, they croak on error |
|
|
10 | # and expect/generate UTF-8 |
10 | |
11 | |
11 | $utf8_encoded_json_text = to_json $perl_hash_or_arrayref; |
12 | $utf8_encoded_json_text = to_json $perl_hash_or_arrayref; |
12 | $perl_hash_or_arrayref = from_json $utf8_encoded_json_text; |
13 | $perl_hash_or_arrayref = from_json $utf8_encoded_json_text; |
13 | |
14 | |
14 | # oo-interface |
15 | # OO-interface |
15 | |
16 | |
16 | $coder = JSON::XS->new->ascii->pretty->allow_nonref; |
17 | $coder = JSON::XS->new->ascii->pretty->allow_nonref; |
17 | $pretty_printed_unencoded = $coder->encode ($perl_scalar); |
18 | $pretty_printed_unencoded = $coder->encode ($perl_scalar); |
18 | $perl_scalar = $coder->decode ($unicode_json_text); |
19 | $perl_scalar = $coder->decode ($unicode_json_text); |
19 | |
20 | |
… | |
… | |
36 | |
37 | |
37 | =head2 FEATURES |
38 | =head2 FEATURES |
38 | |
39 | |
39 | =over 4 |
40 | =over 4 |
40 | |
41 | |
41 | =item * correct handling of unicode issues |
42 | =item * correct unicode handling |
42 | |
43 | |
43 | This module knows how to handle Unicode, and even documents how and when |
44 | This module knows how to handle Unicode, and even documents how and when |
44 | it does so. |
45 | it does so. |
45 | |
46 | |
46 | =item * round-trip integrity |
47 | =item * round-trip integrity |
47 | |
48 | |
48 | When you serialise a perl data structure using only datatypes supported |
49 | When you serialise a perl data structure using only datatypes supported |
49 | by JSON, the deserialised data structure is identical on the Perl level. |
50 | by JSON, the deserialised data structure is identical on the Perl level. |
50 | (e.g. the string "2.0" doesn't suddenly become "2"). |
51 | (e.g. the string "2.0" doesn't suddenly become "2" just because it looks |
|
|
52 | like a number). |
51 | |
53 | |
52 | =item * strict checking of JSON correctness |
54 | =item * strict checking of JSON correctness |
53 | |
55 | |
54 | There is no guessing, no generating of illegal JSON texts by default, |
56 | There is no guessing, no generating of illegal JSON texts by default, |
55 | and only JSON is accepted as input by default (the latter is a security |
57 | and only JSON is accepted as input by default (the latter is a security |
… | |
… | |
66 | interface. |
68 | interface. |
67 | |
69 | |
68 | =item * reasonably versatile output formats |
70 | =item * reasonably versatile output formats |
69 | |
71 | |
70 | You can choose between the most compact guarenteed single-line format |
72 | You can choose between the most compact guarenteed single-line format |
71 | possible (nice for simple line-based protocols), a pure-ascii format (for |
73 | possible (nice for simple line-based protocols), a pure-ascii format |
72 | when your transport is not 8-bit clean), or a pretty-printed format (for |
74 | (for when your transport is not 8-bit clean, still supports the whole |
73 | when you want to read that stuff). Or you can combine those features in |
75 | unicode range), or a pretty-printed format (for when you want to read that |
74 | whatever way you like. |
76 | stuff). Or you can combine those features in whatever way you like. |
75 | |
77 | |
76 | =back |
78 | =back |
77 | |
79 | |
78 | =cut |
80 | =cut |
79 | |
81 | |
80 | package JSON::XS; |
82 | package JSON::XS; |
81 | |
83 | |
82 | BEGIN { |
84 | use strict; |
|
|
85 | |
83 | $VERSION = '0.5'; |
86 | our $VERSION = '1.5'; |
84 | @ISA = qw(Exporter); |
87 | our @ISA = qw(Exporter); |
85 | |
88 | |
86 | @EXPORT = qw(to_json from_json); |
89 | our @EXPORT = qw(to_json from_json); |
87 | require Exporter; |
|
|
88 | |
90 | |
89 | require XSLoader; |
91 | use Exporter; |
90 | XSLoader::load JSON::XS::, $VERSION; |
92 | use XSLoader; |
91 | } |
|
|
92 | |
93 | |
93 | =head1 FUNCTIONAL INTERFACE |
94 | =head1 FUNCTIONAL INTERFACE |
94 | |
95 | |
95 | The following convinience methods are provided by this module. They are |
96 | The following convinience methods are provided by this module. They are |
96 | exported by default: |
97 | exported by default: |
… | |
… | |
119 | |
120 | |
120 | $perl_scalar = JSON::XS->new->utf8->decode ($json_text) |
121 | $perl_scalar = JSON::XS->new->utf8->decode ($json_text) |
121 | |
122 | |
122 | except being faster. |
123 | except being faster. |
123 | |
124 | |
|
|
125 | =item $is_boolean = JSON::XS::is_bool $scalar |
|
|
126 | |
|
|
127 | Returns true if the passed scalar represents either JSON::XS::true or |
|
|
128 | JSON::XS::false, two constants that act like C<1> and C<0>, respectively |
|
|
129 | and are used to represent JSON C<true> and C<false> values in Perl. |
|
|
130 | |
|
|
131 | See MAPPING, below, for more information on how JSON values are mapped to |
|
|
132 | Perl. |
|
|
133 | |
124 | =back |
134 | =back |
|
|
135 | |
125 | |
136 | |
126 | =head1 OBJECT-ORIENTED INTERFACE |
137 | =head1 OBJECT-ORIENTED INTERFACE |
127 | |
138 | |
128 | The object oriented interface lets you configure your own encoding or |
139 | The object oriented interface lets you configure your own encoding or |
129 | decoding style, within the limits of supported formats. |
140 | decoding style, within the limits of supported formats. |
… | |
… | |
145 | |
156 | |
146 | If C<$enable> is true (or missing), then the C<encode> method will not |
157 | If C<$enable> is true (or missing), then the C<encode> method will not |
147 | generate characters outside the code range C<0..127> (which is ASCII). Any |
158 | generate characters outside the code range C<0..127> (which is ASCII). Any |
148 | unicode characters outside that range will be escaped using either a |
159 | unicode characters outside that range will be escaped using either a |
149 | single \uXXXX (BMP characters) or a double \uHHHH\uLLLLL escape sequence, |
160 | single \uXXXX (BMP characters) or a double \uHHHH\uLLLLL escape sequence, |
150 | as per RFC4627. |
161 | as per RFC4627. The resulting encoded JSON text can be treated as a native |
|
|
162 | unicode string, an ascii-encoded, latin1-encoded or UTF-8 encoded string, |
|
|
163 | or any other superset of ASCII. |
151 | |
164 | |
152 | If C<$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 |
153 | 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 |
154 | 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. |
155 | |
172 | |
156 | JSON::XS->new->ascii (1)->encode ([chr 0x10401]) |
173 | JSON::XS->new->ascii (1)->encode ([chr 0x10401]) |
157 | => ["\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) |
158 | |
198 | |
159 | =item $json = $json->utf8 ([$enable]) |
199 | =item $json = $json->utf8 ([$enable]) |
160 | |
200 | |
161 | 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 |
162 | 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 |
… | |
… | |
238 | |
278 | |
239 | Example, space_before and indent disabled, space_after enabled: |
279 | Example, space_before and indent disabled, space_after enabled: |
240 | |
280 | |
241 | {"key": "value"} |
281 | {"key": "value"} |
242 | |
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 | =item * shell-style '#'-comments |
|
|
316 | |
|
|
317 | Whenever JSON allows whitespace, shell-style comments are additionally |
|
|
318 | allowed. They are terminated by the first carriage-return or line-feed |
|
|
319 | character, after which more white-space and comments are allowed. |
|
|
320 | |
|
|
321 | [ |
|
|
322 | 1, # this comment not allowed in JSON |
|
|
323 | # neither this one... |
|
|
324 | ] |
|
|
325 | |
|
|
326 | =back |
|
|
327 | |
243 | =item $json = $json->canonical ([$enable]) |
328 | =item $json = $json->canonical ([$enable]) |
244 | |
329 | |
245 | If C<$enable> is true (or missing), then the C<encode> method will output JSON objects |
330 | If C<$enable> is true (or missing), then the C<encode> method will output JSON objects |
246 | by sorting their keys. This is adding a comparatively high overhead. |
331 | by sorting their keys. This is adding a comparatively high overhead. |
247 | |
332 | |
… | |
… | |
272 | resulting in an invalid JSON text: |
357 | resulting in an invalid JSON text: |
273 | |
358 | |
274 | JSON::XS->new->allow_nonref->encode ("Hello, World!") |
359 | JSON::XS->new->allow_nonref->encode ("Hello, World!") |
275 | => "Hello, World!" |
360 | => "Hello, World!" |
276 | |
361 | |
|
|
362 | =item $json = $json->allow_blessed ([$enable]) |
|
|
363 | |
|
|
364 | If C<$enable> is true (or missing), then the C<encode> method will not |
|
|
365 | barf when it encounters a blessed reference. Instead, the value of the |
|
|
366 | B<convert_blessed> option will decide wether C<null> (C<convert_blessed> |
|
|
367 | disabled or no C<to_json> method found) or a representation of the |
|
|
368 | object (C<convert_blessed> enabled and C<to_json> method found) is being |
|
|
369 | encoded. Has no effect on C<decode>. |
|
|
370 | |
|
|
371 | If C<$enable> is false (the default), then C<encode> will throw an |
|
|
372 | exception when it encounters a blessed object. |
|
|
373 | |
|
|
374 | =item $json = $json->convert_blessed ([$enable]) |
|
|
375 | |
|
|
376 | If C<$enable> is true (or missing), then C<encode>, upon encountering a |
|
|
377 | blessed object, will check for the availability of the C<TO_JSON> method |
|
|
378 | on the object's class. If found, it will be called in scalar context |
|
|
379 | and the resulting scalar will be encoded instead of the object. If no |
|
|
380 | C<TO_JSON> method is found, the value of C<allow_blessed> will decide what |
|
|
381 | to do. |
|
|
382 | |
|
|
383 | The C<TO_JSON> method may safely call die if it wants. If C<TO_JSON> |
|
|
384 | returns other blessed objects, those will be handled in the same |
|
|
385 | way. C<TO_JSON> must take care of not causing an endless recursion cycle |
|
|
386 | (== crash) in this case. The name of C<TO_JSON> was chosen because other |
|
|
387 | methods called by the Perl core (== not by the user of the object) are |
|
|
388 | usually in upper case letters and to avoid collisions with the C<to_json> |
|
|
389 | function. |
|
|
390 | |
|
|
391 | This setting does not yet influence C<decode> in any way, but in the |
|
|
392 | future, global hooks might get installed that influence C<decode> and are |
|
|
393 | enabled by this setting. |
|
|
394 | |
|
|
395 | If C<$enable> is false, then the C<allow_blessed> setting will decide what |
|
|
396 | to do when a blessed object is found. |
|
|
397 | |
|
|
398 | =item $json = $json->filter_json_object ([$coderef->($hashref)]) |
|
|
399 | |
|
|
400 | When C<$coderef> is specified, it will be called from C<decode> each |
|
|
401 | time it decodes a JSON object. The only argument is a reference to the |
|
|
402 | newly-created hash. If the code references returns a single scalar (which |
|
|
403 | need not be a reference), this value (i.e. a copy of that scalar to avoid |
|
|
404 | aliasing) is inserted into the deserialised data structure. If it returns |
|
|
405 | an empty list (NOTE: I<not> C<undef>, which is a valid scalar), the |
|
|
406 | original deserialised hash will be inserted. This setting can slow down |
|
|
407 | decoding considerably. |
|
|
408 | |
|
|
409 | When C<$coderef> is omitted or undefined, any existing callback will |
|
|
410 | be removed and C<decode> will not change the deserialised hash in any |
|
|
411 | way. |
|
|
412 | |
|
|
413 | Example, convert all JSON objects into the integer 5: |
|
|
414 | |
|
|
415 | my $js = JSON::XS->new->filter_json_object (sub { 5 }); |
|
|
416 | # returns [5] |
|
|
417 | $js->decode ('[{}]') |
|
|
418 | # throw an exception because allow_nonref is not enabled |
|
|
419 | # so a lone 5 is not allowed. |
|
|
420 | $js->decode ('{"a":1, "b":2}'); |
|
|
421 | |
|
|
422 | =item $json = $json->filter_json_single_key_object ($key [=> $coderef->($value)]) |
|
|
423 | |
|
|
424 | Works remotely similar to C<filter_json_object>, but is only called for |
|
|
425 | JSON objects having a single key named C<$key>. |
|
|
426 | |
|
|
427 | This C<$coderef> is called before the one specified via |
|
|
428 | C<filter_json_object>, if any. It gets passed the single value in the JSON |
|
|
429 | object. If it returns a single value, it will be inserted into the data |
|
|
430 | structure. If it returns nothing (not even C<undef> but the empty list), |
|
|
431 | the callback from C<filter_json_object> will be called next, as if no |
|
|
432 | single-key callback were specified. |
|
|
433 | |
|
|
434 | If C<$coderef> is omitted or undefined, the corresponding callback will be |
|
|
435 | disabled. There can only ever be one callback for a given key. |
|
|
436 | |
|
|
437 | As this callback gets called less often then the C<filter_json_object> |
|
|
438 | one, decoding speed will not usually suffer as much. Therefore, single-key |
|
|
439 | objects make excellent targets to serialise Perl objects into, especially |
|
|
440 | as single-key JSON objects are as close to the type-tagged value concept |
|
|
441 | as JSON gets (its basically an ID/VALUE tuple). Of course, JSON does not |
|
|
442 | support this in any way, so you need to make sure your data never looks |
|
|
443 | like a serialised Perl hash. |
|
|
444 | |
|
|
445 | Typical names for the single object key are C<__class_whatever__>, or |
|
|
446 | C<$__dollars_are_rarely_used__$> or C<}ugly_brace_placement>, or even |
|
|
447 | things like C<__class_md5sum(classname)__>, to reduce the risk of clashing |
|
|
448 | with real hashes. |
|
|
449 | |
|
|
450 | Example, decode JSON objects of the form C<< { "__widget__" => <id> } >> |
|
|
451 | into the corresponding C<< $WIDGET{<id>} >> object: |
|
|
452 | |
|
|
453 | # return whatever is in $WIDGET{5}: |
|
|
454 | JSON::XS |
|
|
455 | ->new |
|
|
456 | ->filter_json_single_key_object (__widget__ => sub { |
|
|
457 | $WIDGET{ $_[0] } |
|
|
458 | }) |
|
|
459 | ->decode ('{"__widget__": 5') |
|
|
460 | |
|
|
461 | # this can be used with a TO_JSON method in some "widget" class |
|
|
462 | # for serialisation to json: |
|
|
463 | sub WidgetBase::TO_JSON { |
|
|
464 | my ($self) = @_; |
|
|
465 | |
|
|
466 | unless ($self->{id}) { |
|
|
467 | $self->{id} = ..get..some..id..; |
|
|
468 | $WIDGET{$self->{id}} = $self; |
|
|
469 | } |
|
|
470 | |
|
|
471 | { __widget__ => $self->{id} } |
|
|
472 | } |
|
|
473 | |
277 | =item $json = $json->shrink ([$enable]) |
474 | =item $json = $json->shrink ([$enable]) |
278 | |
475 | |
279 | Perl usually over-allocates memory a bit when allocating space for |
476 | Perl usually over-allocates memory a bit when allocating space for |
280 | strings. This flag optionally resizes strings generated by either |
477 | strings. This flag optionally resizes strings generated by either |
281 | C<encode> or C<decode> to their minimum size possible. This can save |
478 | C<encode> or C<decode> to their minimum size possible. This can save |
282 | memory when your JSON texts are either very very long or you have many |
479 | memory when your JSON texts are either very very long or you have many |
283 | short strings. It will also try to downgrade any strings to octet-form |
480 | short strings. It will also try to downgrade any strings to octet-form |
284 | if possible: perl stores strings internally either in an encoding called |
481 | if possible: perl stores strings internally either in an encoding called |
285 | UTF-X or in octet-form. The latter cannot store everything but uses less |
482 | UTF-X or in octet-form. The latter cannot store everything but uses less |
286 | space in general. |
483 | space in general (and some buggy Perl or C code might even rely on that |
|
|
484 | internal representation being used). |
287 | |
485 | |
|
|
486 | The actual definition of what shrink does might change in future versions, |
|
|
487 | but it will always try to save space at the expense of time. |
|
|
488 | |
288 | If C<$enable> is true (or missing), the string returned by C<encode> will be shrunk-to-fit, |
489 | If C<$enable> is true (or missing), the string returned by C<encode> will |
289 | while all strings generated by C<decode> will also be shrunk-to-fit. |
490 | be shrunk-to-fit, while all strings generated by C<decode> will also be |
|
|
491 | shrunk-to-fit. |
290 | |
492 | |
291 | If C<$enable> is false, then the normal perl allocation algorithms are used. |
493 | If C<$enable> is false, then the normal perl allocation algorithms are used. |
292 | If you work with your data, then this is likely to be faster. |
494 | If you work with your data, then this is likely to be faster. |
293 | |
495 | |
294 | In the future, this setting might control other things, such as converting |
496 | In the future, this setting might control other things, such as converting |
295 | strings that look like integers or floats into integers or floats |
497 | strings that look like integers or floats into integers or floats |
296 | internally (there is no difference on the Perl level), saving space. |
498 | internally (there is no difference on the Perl level), saving space. |
|
|
499 | |
|
|
500 | =item $json = $json->max_depth ([$maximum_nesting_depth]) |
|
|
501 | |
|
|
502 | Sets the maximum nesting level (default C<512>) accepted while encoding |
|
|
503 | or decoding. If the JSON text or Perl data structure has an equal or |
|
|
504 | higher nesting level then this limit, then the encoder and decoder will |
|
|
505 | stop and croak at that point. |
|
|
506 | |
|
|
507 | Nesting level is defined by number of hash- or arrayrefs that the encoder |
|
|
508 | needs to traverse to reach a given point or the number of C<{> or C<[> |
|
|
509 | characters without their matching closing parenthesis crossed to reach a |
|
|
510 | given character in a string. |
|
|
511 | |
|
|
512 | Setting the maximum depth to one disallows any nesting, so that ensures |
|
|
513 | that the object is only a single hash/object or array. |
|
|
514 | |
|
|
515 | The argument to C<max_depth> will be rounded up to the next highest power |
|
|
516 | of two. If no argument is given, the highest possible setting will be |
|
|
517 | used, which is rarely useful. |
|
|
518 | |
|
|
519 | See SECURITY CONSIDERATIONS, below, for more info on why this is useful. |
|
|
520 | |
|
|
521 | =item $json = $json->max_size ([$maximum_string_size]) |
|
|
522 | |
|
|
523 | Set the maximum length a JSON text may have (in bytes) where decoding is |
|
|
524 | being attempted. The default is C<0>, meaning no limit. When C<decode> |
|
|
525 | is called on a string longer then this number of characters it will not |
|
|
526 | attempt to decode the string but throw an exception. This setting has no |
|
|
527 | effect on C<encode> (yet). |
|
|
528 | |
|
|
529 | The argument to C<max_size> will be rounded up to the next B<highest> |
|
|
530 | power of two (so may be more than requested). If no argument is given, the |
|
|
531 | limit check will be deactivated (same as when C<0> is specified). |
|
|
532 | |
|
|
533 | See SECURITY CONSIDERATIONS, below, for more info on why this is useful. |
297 | |
534 | |
298 | =item $json_text = $json->encode ($perl_scalar) |
535 | =item $json_text = $json->encode ($perl_scalar) |
299 | |
536 | |
300 | Converts the given Perl data structure (a simple scalar or a reference |
537 | Converts the given Perl data structure (a simple scalar or a reference |
301 | to a hash or array) to its JSON representation. Simple scalars will be |
538 | to a hash or array) to its JSON representation. Simple scalars will be |
… | |
… | |
311 | |
548 | |
312 | JSON numbers and strings become simple Perl scalars. JSON arrays become |
549 | JSON numbers and strings become simple Perl scalars. JSON arrays become |
313 | Perl arrayrefs and JSON objects become Perl hashrefs. C<true> becomes |
550 | Perl arrayrefs and JSON objects become Perl hashrefs. C<true> becomes |
314 | C<1>, C<false> becomes C<0> and C<null> becomes C<undef>. |
551 | C<1>, C<false> becomes C<0> and C<null> becomes C<undef>. |
315 | |
552 | |
|
|
553 | =item ($perl_scalar, $characters) = $json->decode_prefix ($json_text) |
|
|
554 | |
|
|
555 | This works like the C<decode> method, but instead of raising an exception |
|
|
556 | when there is trailing garbage after the first JSON object, it will |
|
|
557 | silently stop parsing there and return the number of characters consumed |
|
|
558 | so far. |
|
|
559 | |
|
|
560 | This is useful if your JSON texts are not delimited by an outer protocol |
|
|
561 | (which is not the brightest thing to do in the first place) and you need |
|
|
562 | to know where the JSON text ends. |
|
|
563 | |
|
|
564 | JSON::XS->new->decode_prefix ("[1] the tail") |
|
|
565 | => ([], 3) |
|
|
566 | |
316 | =back |
567 | =back |
|
|
568 | |
317 | |
569 | |
318 | =head1 MAPPING |
570 | =head1 MAPPING |
319 | |
571 | |
320 | This section describes how JSON::XS maps Perl values to JSON values and |
572 | This section describes how JSON::XS maps Perl values to JSON values and |
321 | vice versa. These mappings are designed to "do the right thing" in most |
573 | vice versa. These mappings are designed to "do the right thing" in most |
… | |
… | |
324 | |
576 | |
325 | For the more enlightened: note that in the following descriptions, |
577 | For the more enlightened: note that in the following descriptions, |
326 | lowercase I<perl> refers to the Perl interpreter, while uppcercase I<Perl> |
578 | lowercase I<perl> refers to the Perl interpreter, while uppcercase I<Perl> |
327 | refers to the abstract Perl language itself. |
579 | refers to the abstract Perl language itself. |
328 | |
580 | |
|
|
581 | |
329 | =head2 JSON -> PERL |
582 | =head2 JSON -> PERL |
330 | |
583 | |
331 | =over 4 |
584 | =over 4 |
332 | |
585 | |
333 | =item object |
586 | =item object |
… | |
… | |
345 | are represented by the same codepoints in the Perl string, so no manual |
598 | are represented by the same codepoints in the Perl string, so no manual |
346 | decoding is necessary. |
599 | decoding is necessary. |
347 | |
600 | |
348 | =item number |
601 | =item number |
349 | |
602 | |
350 | A JSON number becomes either an integer or numeric (floating point) |
603 | A JSON number becomes either an integer, numeric (floating point) or |
351 | scalar in perl, depending on its range and any fractional parts. On the |
604 | string scalar in perl, depending on its range and any fractional parts. On |
352 | Perl level, there is no difference between those as Perl handles all the |
605 | the Perl level, there is no difference between those as Perl handles all |
353 | conversion details, but an integer may take slightly less memory and might |
606 | the conversion details, but an integer may take slightly less memory and |
354 | represent more values exactly than (floating point) numbers. |
607 | might represent more values exactly than (floating point) numbers. |
|
|
608 | |
|
|
609 | If the number consists of digits only, JSON::XS will try to represent |
|
|
610 | it as an integer value. If that fails, it will try to represent it as |
|
|
611 | a numeric (floating point) value if that is possible without loss of |
|
|
612 | precision. Otherwise it will preserve the number as a string value. |
|
|
613 | |
|
|
614 | Numbers containing a fractional or exponential part will always be |
|
|
615 | represented as numeric (floating point) values, possibly at a loss of |
|
|
616 | precision. |
|
|
617 | |
|
|
618 | This might create round-tripping problems as numbers might become strings, |
|
|
619 | but as Perl is typeless there is no other way to do it. |
355 | |
620 | |
356 | =item true, false |
621 | =item true, false |
357 | |
622 | |
358 | These JSON atoms become C<0>, C<1>, respectively. Information is lost in |
623 | These JSON atoms become C<JSON::XS::true> and C<JSON::XS::false>, |
359 | this process. Future versions might represent those values differently, |
624 | respectively. They are overloaded to act almost exactly like the numbers |
360 | but they will be guarenteed to act like these integers would normally in |
625 | C<1> and C<0>. You can check wether a scalar is a JSON boolean by using |
361 | Perl. |
626 | the C<JSON::XS::is_bool> function. |
362 | |
627 | |
363 | =item null |
628 | =item null |
364 | |
629 | |
365 | A JSON null atom becomes C<undef> in Perl. |
630 | A JSON null atom becomes C<undef> in Perl. |
366 | |
631 | |
367 | =back |
632 | =back |
|
|
633 | |
368 | |
634 | |
369 | =head2 PERL -> JSON |
635 | =head2 PERL -> JSON |
370 | |
636 | |
371 | The mapping from Perl to JSON is slightly more difficult, as Perl is a |
637 | The mapping from Perl to JSON is slightly more difficult, as Perl is a |
372 | truly typeless language, so we can only guess which JSON type is meant by |
638 | truly typeless language, so we can only guess which JSON type is meant by |
… | |
… | |
375 | =over 4 |
641 | =over 4 |
376 | |
642 | |
377 | =item hash references |
643 | =item hash references |
378 | |
644 | |
379 | Perl hash references become JSON objects. As there is no inherent ordering |
645 | Perl hash references become JSON objects. As there is no inherent ordering |
380 | in hash keys, they will usually be encoded in a pseudo-random order that |
646 | in hash keys (or JSON objects), they will usually be encoded in a |
381 | can change between runs of the same program but stays generally the same |
647 | pseudo-random order that can change between runs of the same program but |
382 | within a single run of a program. JSON::XS can optionally sort the hash |
648 | stays generally the same within a single run of a program. JSON::XS can |
383 | keys (determined by the I<canonical> flag), so the same datastructure |
649 | optionally sort the hash keys (determined by the I<canonical> flag), so |
384 | will serialise to the same JSON text (given same settings and version of |
650 | the same datastructure will serialise to the same JSON text (given same |
385 | JSON::XS), but this incurs a runtime overhead. |
651 | settings and version of JSON::XS), but this incurs a runtime overhead |
|
|
652 | and is only rarely useful, e.g. when you want to compare some JSON text |
|
|
653 | against another for equality. |
386 | |
654 | |
387 | =item array references |
655 | =item array references |
388 | |
656 | |
389 | Perl array references become JSON arrays. |
657 | Perl array references become JSON arrays. |
|
|
658 | |
|
|
659 | =item other references |
|
|
660 | |
|
|
661 | Other unblessed references are generally not allowed and will cause an |
|
|
662 | exception to be thrown, except for references to the integers C<0> and |
|
|
663 | C<1>, which get turned into C<false> and C<true> atoms in JSON. You can |
|
|
664 | also use C<JSON::XS::false> and C<JSON::XS::true> to improve readability. |
|
|
665 | |
|
|
666 | to_json [\0,JSON::XS::true] # yields [false,true] |
|
|
667 | |
|
|
668 | =item JSON::XS::true, JSON::XS::false |
|
|
669 | |
|
|
670 | These special values become JSON true and JSON false values, |
|
|
671 | respectively. You cna alos use C<\1> and C<\0> directly if you want. |
390 | |
672 | |
391 | =item blessed objects |
673 | =item blessed objects |
392 | |
674 | |
393 | Blessed objects are not allowed. JSON::XS currently tries to encode their |
675 | Blessed objects are not allowed. JSON::XS currently tries to encode their |
394 | underlying representation (hash- or arrayref), but this behaviour might |
676 | underlying representation (hash- or arrayref), but this behaviour might |
… | |
… | |
427 | $x *= 1; # same thing, the choise is yours. |
709 | $x *= 1; # same thing, the choise is yours. |
428 | |
710 | |
429 | You can not currently output JSON booleans or force the type in other, |
711 | You can not currently output JSON booleans or force the type in other, |
430 | less obscure, ways. Tell me if you need this capability. |
712 | less obscure, ways. Tell me if you need this capability. |
431 | |
713 | |
432 | =item circular data structures |
|
|
433 | |
|
|
434 | Those will be encoded until memory or stackspace runs out. |
|
|
435 | |
|
|
436 | =back |
714 | =back |
|
|
715 | |
437 | |
716 | |
438 | =head1 COMPARISON |
717 | =head1 COMPARISON |
439 | |
718 | |
440 | As already mentioned, this module was created because none of the existing |
719 | As already mentioned, this module was created because none of the existing |
441 | JSON modules could be made to work correctly. First I will describe the |
720 | JSON modules could be made to work correctly. First I will describe the |
… | |
… | |
519 | |
798 | |
520 | Does not check input for validity. |
799 | Does not check input for validity. |
521 | |
800 | |
522 | =back |
801 | =back |
523 | |
802 | |
|
|
803 | |
|
|
804 | =head2 JSON and YAML |
|
|
805 | |
|
|
806 | You often hear that JSON is a subset (or a close subset) of YAML. This is, |
|
|
807 | however, a mass hysteria and very far from the truth. In general, there is |
|
|
808 | no way to configure JSON::XS to output a data structure as valid YAML. |
|
|
809 | |
|
|
810 | If you really must use JSON::XS to generate YAML, you should use this |
|
|
811 | algorithm (subject to change in future versions): |
|
|
812 | |
|
|
813 | my $to_yaml = JSON::XS->new->utf8->space_after (1); |
|
|
814 | my $yaml = $to_yaml->encode ($ref) . "\n"; |
|
|
815 | |
|
|
816 | This will usually generate JSON texts that also parse as valid |
|
|
817 | YAML. Please note that YAML has hardcoded limits on (simple) object key |
|
|
818 | lengths that JSON doesn't have, so you should make sure that your hash |
|
|
819 | keys are noticably shorter than the 1024 characters YAML allows. |
|
|
820 | |
|
|
821 | There might be other incompatibilities that I am not aware of. In general |
|
|
822 | you should not try to generate YAML with a JSON generator or vice versa, |
|
|
823 | or try to parse JSON with a YAML parser or vice versa: chances are high |
|
|
824 | that you will run into severe interoperability problems. |
|
|
825 | |
|
|
826 | |
524 | =head2 SPEED |
827 | =head2 SPEED |
525 | |
828 | |
526 | It seems that JSON::XS is surprisingly fast, as shown in the following |
829 | It seems that JSON::XS is surprisingly fast, as shown in the following |
527 | tables. They have been generated with the help of the C<eg/bench> program |
830 | tables. They have been generated with the help of the C<eg/bench> program |
528 | in the JSON::XS distribution, to make it easy to compare on your own |
831 | in the JSON::XS distribution, to make it easy to compare on your own |
529 | system. |
832 | system. |
530 | |
833 | |
531 | First comes a comparison between various modules using a very short JSON |
834 | First comes a comparison between various modules using a very short |
532 | string: |
835 | single-line JSON string: |
533 | |
836 | |
534 | {"method": "handleMessage", "params": ["user1", "we were just talking"], "id": null} |
837 | {"method": "handleMessage", "params": ["user1", "we were just talking"], \ |
|
|
838 | "id": null, "array":[1,11,234,-5,1e5,1e7, true, false]} |
535 | |
839 | |
536 | It shows the number of encodes/decodes per second (JSON::XS uses the |
840 | It shows the number of encodes/decodes per second (JSON::XS uses |
537 | functional interface, while JSON::XS/2 uses the OO interface with |
841 | the functional interface, while JSON::XS/2 uses the OO interface |
538 | pretty-printing and hashkey sorting enabled). Higher is better: |
842 | with pretty-printing and hashkey sorting enabled, JSON::XS/3 enables |
|
|
843 | shrink). Higher is better: |
539 | |
844 | |
|
|
845 | Storable | 15779.925 | 14169.946 | |
|
|
846 | -----------+------------+------------+ |
540 | module | encode | decode | |
847 | module | encode | decode | |
541 | -----------|------------|------------| |
848 | -----------|------------|------------| |
542 | JSON | 11488.516 | 7823.035 | |
849 | JSON | 4990.842 | 4088.813 | |
543 | JSON::DWIW | 94708.054 | 129094.260 | |
850 | JSON::DWIW | 51653.990 | 71575.154 | |
544 | JSON::PC | 63884.157 | 128528.212 | |
851 | JSON::PC | 65948.176 | 74631.744 | |
545 | JSON::Syck | 34898.677 | 42096.911 | |
852 | JSON::PP | 8931.652 | 3817.168 | |
546 | JSON::XS | 654027.064 | 396423.669 | |
853 | JSON::Syck | 24877.248 | 27776.848 | |
547 | JSON::XS/2 | 371564.190 | 371725.613 | |
854 | JSON::XS | 388361.481 | 227951.304 | |
|
|
855 | JSON::XS/2 | 227951.304 | 218453.333 | |
|
|
856 | JSON::XS/3 | 338250.323 | 218453.333 | |
|
|
857 | Storable | 16500.016 | 135300.129 | |
548 | -----------+------------+------------+ |
858 | -----------+------------+------------+ |
549 | |
859 | |
550 | That is, JSON::XS is more than six times faster than JSON::DWIW on |
860 | That is, JSON::XS is about five times faster than JSON::DWIW on encoding, |
551 | encoding, more than three times faster on decoding, and about thirty times |
861 | about three times faster on decoding, and over fourty times faster |
552 | faster than JSON, even with pretty-printing and key sorting. |
862 | than JSON, even with pretty-printing and key sorting. It also compares |
|
|
863 | favourably to Storable for small amounts of data. |
553 | |
864 | |
554 | Using a longer test string (roughly 18KB, generated from Yahoo! Locals |
865 | Using a longer test string (roughly 18KB, generated from Yahoo! Locals |
555 | search API (http://nanoref.com/yahooapis/mgPdGg): |
866 | search API (http://nanoref.com/yahooapis/mgPdGg): |
556 | |
867 | |
557 | module | encode | decode | |
868 | module | encode | decode | |
558 | -----------|------------|------------| |
869 | -----------|------------|------------| |
559 | JSON | 273.023 | 44.674 | |
870 | JSON | 55.260 | 34.971 | |
560 | JSON::DWIW | 1089.383 | 1145.704 | |
871 | JSON::DWIW | 825.228 | 1082.513 | |
561 | JSON::PC | 3097.419 | 2393.921 | |
872 | JSON::PC | 3571.444 | 2394.829 | |
562 | JSON::Syck | 514.060 | 843.053 | |
873 | JSON::PP | 210.987 | 32.574 | |
563 | JSON::XS | 6479.668 | 3636.364 | |
874 | JSON::Syck | 552.551 | 787.544 | |
564 | JSON::XS/2 | 3774.221 | 3599.124 | |
875 | JSON::XS | 5780.463 | 4854.519 | |
|
|
876 | JSON::XS/2 | 3869.998 | 4798.975 | |
|
|
877 | JSON::XS/3 | 5862.880 | 4798.975 | |
|
|
878 | Storable | 4445.002 | 5235.027 | |
565 | -----------+------------+------------+ |
879 | -----------+------------+------------+ |
566 | |
880 | |
567 | Again, JSON::XS leads by far. |
881 | Again, JSON::XS leads by far (except for Storable which non-surprisingly |
|
|
882 | decodes faster). |
568 | |
883 | |
569 | On large strings containing lots of high unicode characters, some modules |
884 | On large strings containing lots of high unicode characters, some modules |
570 | (such as JSON::PC) seem to decode faster than JSON::XS, but the result |
885 | (such as JSON::PC) seem to decode faster than JSON::XS, but the result |
571 | will be broken due to missing (or wrong) unicode handling. Others refuse |
886 | will be broken due to missing (or wrong) unicode handling. Others refuse |
572 | to decode or encode properly, so it was impossible to prepare a fair |
887 | to decode or encode properly, so it was impossible to prepare a fair |
573 | comparison table for that case. |
888 | comparison table for that case. |
574 | |
889 | |
575 | =head1 RESOURCE LIMITS |
|
|
576 | |
890 | |
577 | JSON::XS does not impose any limits on the size of JSON texts or Perl |
891 | =head1 SECURITY CONSIDERATIONS |
578 | values they represent - if your machine can handle it, JSON::XS will |
892 | |
579 | encode or decode it. Future versions might optionally impose structure |
893 | When you are using JSON in a protocol, talking to untrusted potentially |
580 | depth and memory use resource limits. |
894 | hostile creatures requires relatively few measures. |
|
|
895 | |
|
|
896 | First of all, your JSON decoder should be secure, that is, should not have |
|
|
897 | any buffer overflows. Obviously, this module should ensure that and I am |
|
|
898 | trying hard on making that true, but you never know. |
|
|
899 | |
|
|
900 | Second, you need to avoid resource-starving attacks. That means you should |
|
|
901 | limit the size of JSON texts you accept, or make sure then when your |
|
|
902 | resources run out, thats just fine (e.g. by using a separate process that |
|
|
903 | can crash safely). The size of a JSON text in octets or characters is |
|
|
904 | usually a good indication of the size of the resources required to decode |
|
|
905 | it into a Perl structure. While JSON::XS can check the size of the JSON |
|
|
906 | text, it might be too late when you already have it in memory, so you |
|
|
907 | might want to check the size before you accept the string. |
|
|
908 | |
|
|
909 | Third, JSON::XS recurses using the C stack when decoding objects and |
|
|
910 | arrays. The C stack is a limited resource: for instance, on my amd64 |
|
|
911 | machine with 8MB of stack size I can decode around 180k nested arrays but |
|
|
912 | only 14k nested JSON objects (due to perl itself recursing deeply on croak |
|
|
913 | to free the temporary). If that is exceeded, the program crashes. to be |
|
|
914 | conservative, the default nesting limit is set to 512. If your process |
|
|
915 | has a smaller stack, you should adjust this setting accordingly with the |
|
|
916 | C<max_depth> method. |
|
|
917 | |
|
|
918 | And last but least, something else could bomb you that I forgot to think |
|
|
919 | of. In that case, you get to keep the pieces. I am always open for hints, |
|
|
920 | though... |
|
|
921 | |
|
|
922 | If you are using JSON::XS to return packets to consumption |
|
|
923 | by javascript scripts in a browser you should have a look at |
|
|
924 | L<http://jpsykes.com/47/practical-csrf-and-json-security> to see wether |
|
|
925 | you are vulnerable to some common attack vectors (which really are browser |
|
|
926 | design bugs, but it is still you who will have to deal with it, as major |
|
|
927 | browser developers care only for features, not about doing security |
|
|
928 | right). |
|
|
929 | |
581 | |
930 | |
582 | =head1 BUGS |
931 | =head1 BUGS |
583 | |
932 | |
584 | While the goal of this module is to be correct, that unfortunately does |
933 | While the goal of this module is to be correct, that unfortunately does |
585 | not mean its bug-free, only that I think its design is bug-free. It is |
934 | not mean its bug-free, only that I think its design is bug-free. It is |
586 | still very young and not well-tested. If you keep reporting bugs they will |
935 | still relatively early in its development. If you keep reporting bugs they |
587 | be fixed swiftly, though. |
936 | will be fixed swiftly, though. |
588 | |
937 | |
589 | =cut |
938 | =cut |
|
|
939 | |
|
|
940 | our $true = do { bless \(my $dummy = 1), "JSON::XS::Boolean" }; |
|
|
941 | our $false = do { bless \(my $dummy = 0), "JSON::XS::Boolean" }; |
|
|
942 | |
|
|
943 | sub true() { $true } |
|
|
944 | sub false() { $false } |
|
|
945 | |
|
|
946 | sub is_bool($) { |
|
|
947 | UNIVERSAL::isa $_[0], "JSON::XS::Boolean" |
|
|
948 | # or UNIVERSAL::isa $_[0], "JSON::Literal" |
|
|
949 | } |
|
|
950 | |
|
|
951 | XSLoader::load "JSON::XS", $VERSION; |
|
|
952 | |
|
|
953 | package JSON::XS::Boolean; |
|
|
954 | |
|
|
955 | use overload |
|
|
956 | "0+" => sub { ${$_[0]} }, |
|
|
957 | "++" => sub { $_[0] = ${$_[0]} + 1 }, |
|
|
958 | "--" => sub { $_[0] = ${$_[0]} - 1 }, |
|
|
959 | fallback => 1; |
590 | |
960 | |
591 | 1; |
961 | 1; |
592 | |
962 | |
593 | =head1 AUTHOR |
963 | =head1 AUTHOR |
594 | |
964 | |