1 | =head1 NAME |
1 | =head1 NAME |
2 | |
2 | |
3 | JSON::XS - JSON serialising/deserialising, done correctly and fast |
3 | JSON::XS - JSON serialising/deserialising, done correctly and fast |
|
|
4 | |
|
|
5 | JSON::XS - 正しくて高速な JSON シリアライザ/デシリアライザ |
|
|
6 | (http://fleur.hio.jp/perldoc/mix/lib/JSON/XS.html) |
4 | |
7 | |
5 | =head1 SYNOPSIS |
8 | =head1 SYNOPSIS |
6 | |
9 | |
7 | use JSON::XS; |
10 | use JSON::XS; |
8 | |
11 | |
9 | # exported functions, they croak on error |
12 | # exported functions, they croak on error |
10 | # and expect/generate UTF-8 |
13 | # and expect/generate UTF-8 |
11 | |
14 | |
12 | $utf8_encoded_json_text = to_json $perl_hash_or_arrayref; |
15 | $utf8_encoded_json_text = to_json $perl_hash_or_arrayref; |
13 | $perl_hash_or_arrayref = from_json $utf8_encoded_json_text; |
16 | $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 | |
17 | |
19 | # OO-interface |
18 | # OO-interface |
20 | |
19 | |
21 | $coder = JSON::XS->new->ascii->pretty->allow_nonref; |
20 | $coder = JSON::XS->new->ascii->pretty->allow_nonref; |
22 | $pretty_printed_unencoded = $coder->encode ($perl_scalar); |
21 | $pretty_printed_unencoded = $coder->encode ($perl_scalar); |
… | |
… | |
41 | |
40 | |
42 | =head2 FEATURES |
41 | =head2 FEATURES |
43 | |
42 | |
44 | =over 4 |
43 | =over 4 |
45 | |
44 | |
46 | =item * correct unicode handling |
45 | =item * correct Unicode handling |
47 | |
46 | |
48 | This module knows how to handle Unicode, and even documents how and when |
47 | This module knows how to handle Unicode, and even documents how and when |
49 | it does so. |
48 | it does so. |
50 | |
49 | |
51 | =item * round-trip integrity |
50 | =item * round-trip integrity |
… | |
… | |
71 | This module has both a simple functional interface as well as an OO |
70 | This module has both a simple functional interface as well as an OO |
72 | interface. |
71 | interface. |
73 | |
72 | |
74 | =item * reasonably versatile output formats |
73 | =item * reasonably versatile output formats |
75 | |
74 | |
76 | You can choose between the most compact guarenteed single-line format |
75 | You can choose between the most compact guaranteed single-line format |
77 | possible (nice for simple line-based protocols), a pure-ascii format |
76 | possible (nice for simple line-based protocols), a pure-ascii format |
78 | (for when your transport is not 8-bit clean, still supports the whole |
77 | (for when your transport is not 8-bit clean, still supports the whole |
79 | unicode range), or a pretty-printed format (for when you want to read that |
78 | Unicode range), or a pretty-printed format (for when you want to read that |
80 | stuff). Or you can combine those features in whatever way you like. |
79 | stuff). Or you can combine those features in whatever way you like. |
81 | |
80 | |
82 | =back |
81 | =back |
83 | |
82 | |
84 | =cut |
83 | =cut |
85 | |
84 | |
86 | package JSON::XS; |
85 | package JSON::XS; |
87 | |
86 | |
88 | use strict; |
87 | use strict; |
89 | |
88 | |
90 | BEGIN { |
|
|
91 | our $VERSION = '0.8'; |
89 | our $VERSION = '2.0'; |
92 | our @ISA = qw(Exporter); |
90 | our @ISA = qw(Exporter); |
93 | |
91 | |
94 | our @EXPORT = qw(to_json from_json objToJson jsonToObj); |
92 | our @EXPORT = qw(to_json from_json); |
95 | require Exporter; |
|
|
96 | |
93 | |
97 | require XSLoader; |
94 | use Exporter; |
98 | XSLoader::load JSON::XS::, $VERSION; |
95 | use XSLoader; |
99 | } |
|
|
100 | |
96 | |
101 | =head1 FUNCTIONAL INTERFACE |
97 | =head1 FUNCTIONAL INTERFACE |
102 | |
98 | |
103 | The following convinience methods are provided by this module. They are |
99 | The following convenience methods are provided by this module. They are |
104 | exported by default: |
100 | exported by default: |
105 | |
101 | |
106 | =over 4 |
102 | =over 4 |
107 | |
103 | |
108 | =item $json_text = to_json $perl_scalar |
104 | =item $json_text = to_json $perl_scalar |
109 | |
105 | |
110 | Converts the given Perl data structure (a simple scalar or a reference to |
106 | Converts the given Perl data structure to a UTF-8 encoded, binary string |
111 | a hash or array) to a UTF-8 encoded, binary string (that is, the string contains |
107 | (that is, the string contains octets only). Croaks on error. |
112 | octets only). Croaks on error. |
|
|
113 | |
108 | |
114 | This function call is functionally identical to: |
109 | This function call is functionally identical to: |
115 | |
110 | |
116 | $json_text = JSON::XS->new->utf8->encode ($perl_scalar) |
111 | $json_text = JSON::XS->new->utf8->encode ($perl_scalar) |
117 | |
112 | |
118 | except being faster. |
113 | except being faster. |
119 | |
114 | |
120 | =item $perl_scalar = from_json $json_text |
115 | =item $perl_scalar = from_json $json_text |
121 | |
116 | |
122 | The opposite of C<to_json>: expects an UTF-8 (binary) string and tries to |
117 | The opposite of C<to_json>: expects an UTF-8 (binary) string and tries |
123 | parse that as an UTF-8 encoded JSON text, returning the resulting simple |
118 | to parse that as an UTF-8 encoded JSON text, returning the resulting |
124 | scalar or reference. Croaks on error. |
119 | reference. Croaks on error. |
125 | |
120 | |
126 | This function call is functionally identical to: |
121 | This function call is functionally identical to: |
127 | |
122 | |
128 | $perl_scalar = JSON::XS->new->utf8->decode ($json_text) |
123 | $perl_scalar = JSON::XS->new->utf8->decode ($json_text) |
129 | |
124 | |
130 | except being faster. |
125 | except being faster. |
131 | |
126 | |
|
|
127 | =item $is_boolean = JSON::XS::is_bool $scalar |
|
|
128 | |
|
|
129 | Returns true if the passed scalar represents either JSON::XS::true or |
|
|
130 | JSON::XS::false, two constants that act like C<1> and C<0>, respectively |
|
|
131 | and are used to represent JSON C<true> and C<false> values in Perl. |
|
|
132 | |
|
|
133 | See MAPPING, below, for more information on how JSON values are mapped to |
|
|
134 | Perl. |
|
|
135 | |
132 | =back |
136 | =back |
|
|
137 | |
|
|
138 | |
|
|
139 | =head1 A FEW NOTES ON UNICODE AND PERL |
|
|
140 | |
|
|
141 | Since this often leads to confusion, here are a few very clear words on |
|
|
142 | how Unicode works in Perl, modulo bugs. |
|
|
143 | |
|
|
144 | =over 4 |
|
|
145 | |
|
|
146 | =item 1. Perl strings can store characters with ordinal values > 255. |
|
|
147 | |
|
|
148 | This enables you to store Unicode characters as single characters in a |
|
|
149 | Perl string - very natural. |
|
|
150 | |
|
|
151 | =item 2. Perl does I<not> associate an encoding with your strings. |
|
|
152 | |
|
|
153 | Unless you force it to, e.g. when matching it against a regex, or printing |
|
|
154 | the scalar to a file, in which case Perl either interprets your string as |
|
|
155 | locale-encoded text, octets/binary, or as Unicode, depending on various |
|
|
156 | settings. In no case is an encoding stored together with your data, it is |
|
|
157 | I<use> that decides encoding, not any magical metadata. |
|
|
158 | |
|
|
159 | =item 3. The internal utf-8 flag has no meaning with regards to the |
|
|
160 | encoding of your string. |
|
|
161 | |
|
|
162 | Just ignore that flag unless you debug a Perl bug, a module written in |
|
|
163 | XS or want to dive into the internals of perl. Otherwise it will only |
|
|
164 | confuse you, as, despite the name, it says nothing about how your string |
|
|
165 | is encoded. You can have Unicode strings with that flag set, with that |
|
|
166 | flag clear, and you can have binary data with that flag set and that flag |
|
|
167 | clear. Other possibilities exist, too. |
|
|
168 | |
|
|
169 | If you didn't know about that flag, just the better, pretend it doesn't |
|
|
170 | exist. |
|
|
171 | |
|
|
172 | =item 4. A "Unicode String" is simply a string where each character can be |
|
|
173 | validly interpreted as a Unicode codepoint. |
|
|
174 | |
|
|
175 | If you have UTF-8 encoded data, it is no longer a Unicode string, but a |
|
|
176 | Unicode string encoded in UTF-8, giving you a binary string. |
|
|
177 | |
|
|
178 | =item 5. A string containing "high" (> 255) character values is I<not> a UTF-8 string. |
|
|
179 | |
|
|
180 | It's a fact. Learn to live with it. |
|
|
181 | |
|
|
182 | =back |
|
|
183 | |
|
|
184 | I hope this helps :) |
133 | |
185 | |
134 | |
186 | |
135 | =head1 OBJECT-ORIENTED INTERFACE |
187 | =head1 OBJECT-ORIENTED INTERFACE |
136 | |
188 | |
137 | The object oriented interface lets you configure your own encoding or |
189 | The object oriented interface lets you configure your own encoding or |
… | |
… | |
150 | my $json = JSON::XS->new->utf8->space_after->encode ({a => [1,2]}) |
202 | my $json = JSON::XS->new->utf8->space_after->encode ({a => [1,2]}) |
151 | => {"a": [1, 2]} |
203 | => {"a": [1, 2]} |
152 | |
204 | |
153 | =item $json = $json->ascii ([$enable]) |
205 | =item $json = $json->ascii ([$enable]) |
154 | |
206 | |
|
|
207 | =item $enabled = $json->get_ascii |
|
|
208 | |
155 | If C<$enable> is true (or missing), then the C<encode> method will not |
209 | If C<$enable> is true (or missing), then the C<encode> method will not |
156 | generate characters outside the code range C<0..127> (which is ASCII). Any |
210 | generate characters outside the code range C<0..127> (which is ASCII). Any |
157 | unicode characters outside that range will be escaped using either a |
211 | Unicode characters outside that range will be escaped using either a |
158 | single \uXXXX (BMP characters) or a double \uHHHH\uLLLLL escape sequence, |
212 | single \uXXXX (BMP characters) or a double \uHHHH\uLLLLL escape sequence, |
159 | as per RFC4627. |
213 | as per RFC4627. The resulting encoded JSON text can be treated as a native |
|
|
214 | Unicode string, an ascii-encoded, latin1-encoded or UTF-8 encoded string, |
|
|
215 | or any other superset of ASCII. |
160 | |
216 | |
161 | If C<$enable> is false, then the C<encode> method will not escape Unicode |
217 | 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 |
218 | characters unless required by the JSON syntax or other flags. This results |
163 | and more compact format. |
219 | in a faster and more compact format. |
|
|
220 | |
|
|
221 | The main use for this flag is to produce JSON texts that can be |
|
|
222 | transmitted over a 7-bit channel, as the encoded JSON texts will not |
|
|
223 | contain any 8 bit characters. |
164 | |
224 | |
165 | JSON::XS->new->ascii (1)->encode ([chr 0x10401]) |
225 | JSON::XS->new->ascii (1)->encode ([chr 0x10401]) |
166 | => ["\ud801\udc01"] |
226 | => ["\ud801\udc01"] |
167 | |
227 | |
|
|
228 | =item $json = $json->latin1 ([$enable]) |
|
|
229 | |
|
|
230 | =item $enabled = $json->get_latin1 |
|
|
231 | |
|
|
232 | If C<$enable> is true (or missing), then the C<encode> method will encode |
|
|
233 | the resulting JSON text as latin1 (or iso-8859-1), escaping any characters |
|
|
234 | outside the code range C<0..255>. The resulting string can be treated as a |
|
|
235 | latin1-encoded JSON text or a native Unicode string. The C<decode> method |
|
|
236 | will not be affected in any way by this flag, as C<decode> by default |
|
|
237 | expects Unicode, which is a strict superset of latin1. |
|
|
238 | |
|
|
239 | If C<$enable> is false, then the C<encode> method will not escape Unicode |
|
|
240 | characters unless required by the JSON syntax or other flags. |
|
|
241 | |
|
|
242 | The main use for this flag is efficiently encoding binary data as JSON |
|
|
243 | text, as most octets will not be escaped, resulting in a smaller encoded |
|
|
244 | size. The disadvantage is that the resulting JSON text is encoded |
|
|
245 | in latin1 (and must correctly be treated as such when storing and |
|
|
246 | transferring), a rare encoding for JSON. It is therefore most useful when |
|
|
247 | you want to store data structures known to contain binary data efficiently |
|
|
248 | in files or databases, not when talking to other JSON encoders/decoders. |
|
|
249 | |
|
|
250 | JSON::XS->new->latin1->encode (["\x{89}\x{abc}"] |
|
|
251 | => ["\x{89}\\u0abc"] # (perl syntax, U+abc escaped, U+89 not) |
|
|
252 | |
168 | =item $json = $json->utf8 ([$enable]) |
253 | =item $json = $json->utf8 ([$enable]) |
|
|
254 | |
|
|
255 | =item $enabled = $json->get_utf8 |
169 | |
256 | |
170 | If C<$enable> is true (or missing), then the C<encode> method will encode |
257 | If C<$enable> is true (or missing), then the C<encode> method will encode |
171 | the JSON result into UTF-8, as required by many protocols, while the |
258 | the JSON result into UTF-8, as required by many protocols, while the |
172 | C<decode> method expects to be handled an UTF-8-encoded string. Please |
259 | C<decode> method expects to be handled an UTF-8-encoded string. Please |
173 | note that UTF-8-encoded strings do not contain any characters outside the |
260 | note that UTF-8-encoded strings do not contain any characters outside the |
174 | range C<0..255>, they are thus useful for bytewise/binary I/O. In future |
261 | range C<0..255>, they are thus useful for bytewise/binary I/O. In future |
175 | versions, enabling this option might enable autodetection of the UTF-16 |
262 | versions, enabling this option might enable autodetection of the UTF-16 |
176 | and UTF-32 encoding families, as described in RFC4627. |
263 | and UTF-32 encoding families, as described in RFC4627. |
177 | |
264 | |
178 | If C<$enable> is false, then the C<encode> method will return the JSON |
265 | If C<$enable> is false, then the C<encode> method will return the JSON |
179 | string as a (non-encoded) unicode string, while C<decode> expects thus a |
266 | string as a (non-encoded) Unicode string, while C<decode> expects thus a |
180 | unicode string. Any decoding or encoding (e.g. to UTF-8 or UTF-16) needs |
267 | Unicode string. Any decoding or encoding (e.g. to UTF-8 or UTF-16) needs |
181 | to be done yourself, e.g. using the Encode module. |
268 | to be done yourself, e.g. using the Encode module. |
182 | |
269 | |
183 | Example, output UTF-16BE-encoded JSON: |
270 | Example, output UTF-16BE-encoded JSON: |
184 | |
271 | |
185 | use Encode; |
272 | use Encode; |
… | |
… | |
207 | ] |
294 | ] |
208 | } |
295 | } |
209 | |
296 | |
210 | =item $json = $json->indent ([$enable]) |
297 | =item $json = $json->indent ([$enable]) |
211 | |
298 | |
|
|
299 | =item $enabled = $json->get_indent |
|
|
300 | |
212 | If C<$enable> is true (or missing), then the C<encode> method will use a multiline |
301 | If C<$enable> is true (or missing), then the C<encode> method will use a multiline |
213 | format as output, putting every array member or object/hash key-value pair |
302 | format as output, putting every array member or object/hash key-value pair |
214 | into its own line, identing them properly. |
303 | into its own line, indenting them properly. |
215 | |
304 | |
216 | If C<$enable> is false, no newlines or indenting will be produced, and the |
305 | If C<$enable> is false, no newlines or indenting will be produced, and the |
217 | resulting JSON text is guarenteed not to contain any C<newlines>. |
306 | resulting JSON text is guaranteed not to contain any C<newlines>. |
218 | |
307 | |
219 | This setting has no effect when decoding JSON texts. |
308 | This setting has no effect when decoding JSON texts. |
220 | |
309 | |
221 | =item $json = $json->space_before ([$enable]) |
310 | =item $json = $json->space_before ([$enable]) |
|
|
311 | |
|
|
312 | =item $enabled = $json->get_space_before |
222 | |
313 | |
223 | If C<$enable> is true (or missing), then the C<encode> method will add an extra |
314 | If C<$enable> is true (or missing), then the C<encode> method will add an extra |
224 | optional space before the C<:> separating keys from values in JSON objects. |
315 | optional space before the C<:> separating keys from values in JSON objects. |
225 | |
316 | |
226 | If C<$enable> is false, then the C<encode> method will not add any extra |
317 | If C<$enable> is false, then the C<encode> method will not add any extra |
… | |
… | |
232 | Example, space_before enabled, space_after and indent disabled: |
323 | Example, space_before enabled, space_after and indent disabled: |
233 | |
324 | |
234 | {"key" :"value"} |
325 | {"key" :"value"} |
235 | |
326 | |
236 | =item $json = $json->space_after ([$enable]) |
327 | =item $json = $json->space_after ([$enable]) |
|
|
328 | |
|
|
329 | =item $enabled = $json->get_space_after |
237 | |
330 | |
238 | If C<$enable> is true (or missing), then the C<encode> method will add an extra |
331 | If C<$enable> is true (or missing), then the C<encode> method will add an extra |
239 | optional space after the C<:> separating keys from values in JSON objects |
332 | optional space after the C<:> separating keys from values in JSON objects |
240 | and extra whitespace after the C<,> separating key-value pairs and array |
333 | and extra whitespace after the C<,> separating key-value pairs and array |
241 | members. |
334 | members. |
… | |
… | |
247 | |
340 | |
248 | Example, space_before and indent disabled, space_after enabled: |
341 | Example, space_before and indent disabled, space_after enabled: |
249 | |
342 | |
250 | {"key": "value"} |
343 | {"key": "value"} |
251 | |
344 | |
|
|
345 | =item $json = $json->relaxed ([$enable]) |
|
|
346 | |
|
|
347 | =item $enabled = $json->get_relaxed |
|
|
348 | |
|
|
349 | If C<$enable> is true (or missing), then C<decode> will accept some |
|
|
350 | extensions to normal JSON syntax (see below). C<encode> will not be |
|
|
351 | affected in anyway. I<Be aware that this option makes you accept invalid |
|
|
352 | JSON texts as if they were valid!>. I suggest only to use this option to |
|
|
353 | parse application-specific files written by humans (configuration files, |
|
|
354 | resource files etc.) |
|
|
355 | |
|
|
356 | If C<$enable> is false (the default), then C<decode> will only accept |
|
|
357 | valid JSON texts. |
|
|
358 | |
|
|
359 | Currently accepted extensions are: |
|
|
360 | |
|
|
361 | =over 4 |
|
|
362 | |
|
|
363 | =item * list items can have an end-comma |
|
|
364 | |
|
|
365 | JSON I<separates> array elements and key-value pairs with commas. This |
|
|
366 | can be annoying if you write JSON texts manually and want to be able to |
|
|
367 | quickly append elements, so this extension accepts comma at the end of |
|
|
368 | such items not just between them: |
|
|
369 | |
|
|
370 | [ |
|
|
371 | 1, |
|
|
372 | 2, <- this comma not normally allowed |
|
|
373 | ] |
|
|
374 | { |
|
|
375 | "k1": "v1", |
|
|
376 | "k2": "v2", <- this comma not normally allowed |
|
|
377 | } |
|
|
378 | |
|
|
379 | =item * shell-style '#'-comments |
|
|
380 | |
|
|
381 | Whenever JSON allows whitespace, shell-style comments are additionally |
|
|
382 | allowed. They are terminated by the first carriage-return or line-feed |
|
|
383 | character, after which more white-space and comments are allowed. |
|
|
384 | |
|
|
385 | [ |
|
|
386 | 1, # this comment not allowed in JSON |
|
|
387 | # neither this one... |
|
|
388 | ] |
|
|
389 | |
|
|
390 | =back |
|
|
391 | |
252 | =item $json = $json->canonical ([$enable]) |
392 | =item $json = $json->canonical ([$enable]) |
|
|
393 | |
|
|
394 | =item $enabled = $json->get_canonical |
253 | |
395 | |
254 | If C<$enable> is true (or missing), then the C<encode> method will output JSON objects |
396 | If C<$enable> is true (or missing), then the C<encode> method will output JSON objects |
255 | by sorting their keys. This is adding a comparatively high overhead. |
397 | by sorting their keys. This is adding a comparatively high overhead. |
256 | |
398 | |
257 | If C<$enable> is false, then the C<encode> method will output key-value |
399 | If C<$enable> is false, then the C<encode> method will output key-value |
258 | pairs in the order Perl stores them (which will likely change between runs |
400 | pairs in the order Perl stores them (which will likely change between runs |
259 | of the same script). |
401 | of the same script). |
260 | |
402 | |
261 | This option is useful if you want the same data structure to be encoded as |
403 | This option is useful if you want the same data structure to be encoded as |
262 | the same JSON text (given the same overall settings). If it is disabled, |
404 | the same JSON text (given the same overall settings). If it is disabled, |
263 | the same hash migh be encoded differently even if contains the same data, |
405 | the same hash might be encoded differently even if contains the same data, |
264 | as key-value pairs have no inherent ordering in Perl. |
406 | as key-value pairs have no inherent ordering in Perl. |
265 | |
407 | |
266 | This setting has no effect when decoding JSON texts. |
408 | This setting has no effect when decoding JSON texts. |
267 | |
409 | |
268 | =item $json = $json->allow_nonref ([$enable]) |
410 | =item $json = $json->allow_nonref ([$enable]) |
|
|
411 | |
|
|
412 | =item $enabled = $json->get_allow_nonref |
269 | |
413 | |
270 | If C<$enable> is true (or missing), then the C<encode> method can convert a |
414 | If C<$enable> is true (or missing), then the C<encode> method can convert a |
271 | non-reference into its corresponding string, number or null JSON value, |
415 | non-reference into its corresponding string, number or null JSON value, |
272 | which is an extension to RFC4627. Likewise, C<decode> will accept those JSON |
416 | which is an extension to RFC4627. Likewise, C<decode> will accept those JSON |
273 | values instead of croaking. |
417 | values instead of croaking. |
… | |
… | |
281 | resulting in an invalid JSON text: |
425 | resulting in an invalid JSON text: |
282 | |
426 | |
283 | JSON::XS->new->allow_nonref->encode ("Hello, World!") |
427 | JSON::XS->new->allow_nonref->encode ("Hello, World!") |
284 | => "Hello, World!" |
428 | => "Hello, World!" |
285 | |
429 | |
|
|
430 | =item $json = $json->allow_blessed ([$enable]) |
|
|
431 | |
|
|
432 | =item $enabled = $json->get_allow_blessed |
|
|
433 | |
|
|
434 | If C<$enable> is true (or missing), then the C<encode> method will not |
|
|
435 | barf when it encounters a blessed reference. Instead, the value of the |
|
|
436 | B<convert_blessed> option will decide whether C<null> (C<convert_blessed> |
|
|
437 | disabled or no C<to_json> method found) or a representation of the |
|
|
438 | object (C<convert_blessed> enabled and C<to_json> method found) is being |
|
|
439 | encoded. Has no effect on C<decode>. |
|
|
440 | |
|
|
441 | If C<$enable> is false (the default), then C<encode> will throw an |
|
|
442 | exception when it encounters a blessed object. |
|
|
443 | |
|
|
444 | =item $json = $json->convert_blessed ([$enable]) |
|
|
445 | |
|
|
446 | =item $enabled = $json->get_convert_blessed |
|
|
447 | |
|
|
448 | If C<$enable> is true (or missing), then C<encode>, upon encountering a |
|
|
449 | blessed object, will check for the availability of the C<TO_JSON> method |
|
|
450 | on the object's class. If found, it will be called in scalar context |
|
|
451 | and the resulting scalar will be encoded instead of the object. If no |
|
|
452 | C<TO_JSON> method is found, the value of C<allow_blessed> will decide what |
|
|
453 | to do. |
|
|
454 | |
|
|
455 | The C<TO_JSON> method may safely call die if it wants. If C<TO_JSON> |
|
|
456 | returns other blessed objects, those will be handled in the same |
|
|
457 | way. C<TO_JSON> must take care of not causing an endless recursion cycle |
|
|
458 | (== crash) in this case. The name of C<TO_JSON> was chosen because other |
|
|
459 | methods called by the Perl core (== not by the user of the object) are |
|
|
460 | usually in upper case letters and to avoid collisions with the C<to_json> |
|
|
461 | function. |
|
|
462 | |
|
|
463 | This setting does not yet influence C<decode> in any way, but in the |
|
|
464 | future, global hooks might get installed that influence C<decode> and are |
|
|
465 | enabled by this setting. |
|
|
466 | |
|
|
467 | If C<$enable> is false, then the C<allow_blessed> setting will decide what |
|
|
468 | to do when a blessed object is found. |
|
|
469 | |
|
|
470 | =item $json = $json->filter_json_object ([$coderef->($hashref)]) |
|
|
471 | |
|
|
472 | When C<$coderef> is specified, it will be called from C<decode> each |
|
|
473 | time it decodes a JSON object. The only argument is a reference to the |
|
|
474 | newly-created hash. If the code references returns a single scalar (which |
|
|
475 | need not be a reference), this value (i.e. a copy of that scalar to avoid |
|
|
476 | aliasing) is inserted into the deserialised data structure. If it returns |
|
|
477 | an empty list (NOTE: I<not> C<undef>, which is a valid scalar), the |
|
|
478 | original deserialised hash will be inserted. This setting can slow down |
|
|
479 | decoding considerably. |
|
|
480 | |
|
|
481 | When C<$coderef> is omitted or undefined, any existing callback will |
|
|
482 | be removed and C<decode> will not change the deserialised hash in any |
|
|
483 | way. |
|
|
484 | |
|
|
485 | Example, convert all JSON objects into the integer 5: |
|
|
486 | |
|
|
487 | my $js = JSON::XS->new->filter_json_object (sub { 5 }); |
|
|
488 | # returns [5] |
|
|
489 | $js->decode ('[{}]') |
|
|
490 | # throw an exception because allow_nonref is not enabled |
|
|
491 | # so a lone 5 is not allowed. |
|
|
492 | $js->decode ('{"a":1, "b":2}'); |
|
|
493 | |
|
|
494 | =item $json = $json->filter_json_single_key_object ($key [=> $coderef->($value)]) |
|
|
495 | |
|
|
496 | Works remotely similar to C<filter_json_object>, but is only called for |
|
|
497 | JSON objects having a single key named C<$key>. |
|
|
498 | |
|
|
499 | This C<$coderef> is called before the one specified via |
|
|
500 | C<filter_json_object>, if any. It gets passed the single value in the JSON |
|
|
501 | object. If it returns a single value, it will be inserted into the data |
|
|
502 | structure. If it returns nothing (not even C<undef> but the empty list), |
|
|
503 | the callback from C<filter_json_object> will be called next, as if no |
|
|
504 | single-key callback were specified. |
|
|
505 | |
|
|
506 | If C<$coderef> is omitted or undefined, the corresponding callback will be |
|
|
507 | disabled. There can only ever be one callback for a given key. |
|
|
508 | |
|
|
509 | As this callback gets called less often then the C<filter_json_object> |
|
|
510 | one, decoding speed will not usually suffer as much. Therefore, single-key |
|
|
511 | objects make excellent targets to serialise Perl objects into, especially |
|
|
512 | as single-key JSON objects are as close to the type-tagged value concept |
|
|
513 | as JSON gets (it's basically an ID/VALUE tuple). Of course, JSON does not |
|
|
514 | support this in any way, so you need to make sure your data never looks |
|
|
515 | like a serialised Perl hash. |
|
|
516 | |
|
|
517 | Typical names for the single object key are C<__class_whatever__>, or |
|
|
518 | C<$__dollars_are_rarely_used__$> or C<}ugly_brace_placement>, or even |
|
|
519 | things like C<__class_md5sum(classname)__>, to reduce the risk of clashing |
|
|
520 | with real hashes. |
|
|
521 | |
|
|
522 | Example, decode JSON objects of the form C<< { "__widget__" => <id> } >> |
|
|
523 | into the corresponding C<< $WIDGET{<id>} >> object: |
|
|
524 | |
|
|
525 | # return whatever is in $WIDGET{5}: |
|
|
526 | JSON::XS |
|
|
527 | ->new |
|
|
528 | ->filter_json_single_key_object (__widget__ => sub { |
|
|
529 | $WIDGET{ $_[0] } |
|
|
530 | }) |
|
|
531 | ->decode ('{"__widget__": 5') |
|
|
532 | |
|
|
533 | # this can be used with a TO_JSON method in some "widget" class |
|
|
534 | # for serialisation to json: |
|
|
535 | sub WidgetBase::TO_JSON { |
|
|
536 | my ($self) = @_; |
|
|
537 | |
|
|
538 | unless ($self->{id}) { |
|
|
539 | $self->{id} = ..get..some..id..; |
|
|
540 | $WIDGET{$self->{id}} = $self; |
|
|
541 | } |
|
|
542 | |
|
|
543 | { __widget__ => $self->{id} } |
|
|
544 | } |
|
|
545 | |
286 | =item $json = $json->shrink ([$enable]) |
546 | =item $json = $json->shrink ([$enable]) |
287 | |
547 | |
|
|
548 | =item $enabled = $json->get_shrink |
|
|
549 | |
288 | Perl usually over-allocates memory a bit when allocating space for |
550 | Perl usually over-allocates memory a bit when allocating space for |
289 | strings. This flag optionally resizes strings generated by either |
551 | strings. This flag optionally resizes strings generated by either |
290 | C<encode> or C<decode> to their minimum size possible. This can save |
552 | C<encode> or C<decode> to their minimum size possible. This can save |
291 | memory when your JSON texts are either very very long or you have many |
553 | memory when your JSON texts are either very very long or you have many |
292 | short strings. It will also try to downgrade any strings to octet-form |
554 | short strings. It will also try to downgrade any strings to octet-form |
293 | if possible: perl stores strings internally either in an encoding called |
555 | if possible: perl stores strings internally either in an encoding called |
294 | UTF-X or in octet-form. The latter cannot store everything but uses less |
556 | UTF-X or in octet-form. The latter cannot store everything but uses less |
295 | space in general. |
557 | space in general (and some buggy Perl or C code might even rely on that |
|
|
558 | internal representation being used). |
296 | |
559 | |
|
|
560 | The actual definition of what shrink does might change in future versions, |
|
|
561 | but it will always try to save space at the expense of time. |
|
|
562 | |
297 | If C<$enable> is true (or missing), the string returned by C<encode> will be shrunk-to-fit, |
563 | If C<$enable> is true (or missing), the string returned by C<encode> will |
298 | while all strings generated by C<decode> will also be shrunk-to-fit. |
564 | be shrunk-to-fit, while all strings generated by C<decode> will also be |
|
|
565 | shrunk-to-fit. |
299 | |
566 | |
300 | If C<$enable> is false, then the normal perl allocation algorithms are used. |
567 | If C<$enable> is false, then the normal perl allocation algorithms are used. |
301 | If you work with your data, then this is likely to be faster. |
568 | If you work with your data, then this is likely to be faster. |
302 | |
569 | |
303 | In the future, this setting might control other things, such as converting |
570 | In the future, this setting might control other things, such as converting |
304 | strings that look like integers or floats into integers or floats |
571 | strings that look like integers or floats into integers or floats |
305 | internally (there is no difference on the Perl level), saving space. |
572 | internally (there is no difference on the Perl level), saving space. |
306 | |
573 | |
307 | =item $json = $json->max_depth ([$maximum_nesting_depth]) |
574 | =item $json = $json->max_depth ([$maximum_nesting_depth]) |
308 | |
575 | |
|
|
576 | =item $max_depth = $json->get_max_depth |
|
|
577 | |
309 | Sets the maximum nesting level (default C<8192>) accepted while encoding |
578 | Sets the maximum nesting level (default C<512>) accepted while encoding |
310 | or decoding. If the JSON text or Perl data structure has an equal or |
579 | or decoding. If the JSON text or Perl data structure has an equal or |
311 | higher nesting level then this limit, then the encoder and decoder will |
580 | higher nesting level then this limit, then the encoder and decoder will |
312 | stop and croak at that point. |
581 | stop and croak at that point. |
313 | |
582 | |
314 | Nesting level is defined by number of hash- or arrayrefs that the encoder |
583 | Nesting level is defined by number of hash- or arrayrefs that the encoder |
… | |
… | |
317 | given character in a string. |
586 | given character in a string. |
318 | |
587 | |
319 | Setting the maximum depth to one disallows any nesting, so that ensures |
588 | Setting the maximum depth to one disallows any nesting, so that ensures |
320 | that the object is only a single hash/object or array. |
589 | that the object is only a single hash/object or array. |
321 | |
590 | |
322 | The argument to C<max_depth> will be rounded up to the next nearest power |
591 | The argument to C<max_depth> will be rounded up to the next highest power |
323 | of two. |
592 | of two. If no argument is given, the highest possible setting will be |
|
|
593 | used, which is rarely useful. |
|
|
594 | |
|
|
595 | See SECURITY CONSIDERATIONS, below, for more info on why this is useful. |
|
|
596 | |
|
|
597 | =item $json = $json->max_size ([$maximum_string_size]) |
|
|
598 | |
|
|
599 | =item $max_size = $json->get_max_size |
|
|
600 | |
|
|
601 | Set the maximum length a JSON text may have (in bytes) where decoding is |
|
|
602 | being attempted. The default is C<0>, meaning no limit. When C<decode> |
|
|
603 | is called on a string longer then this number of characters it will not |
|
|
604 | attempt to decode the string but throw an exception. This setting has no |
|
|
605 | effect on C<encode> (yet). |
|
|
606 | |
|
|
607 | The argument to C<max_size> will be rounded up to the next B<highest> |
|
|
608 | power of two (so may be more than requested). If no argument is given, the |
|
|
609 | limit check will be deactivated (same as when C<0> is specified). |
324 | |
610 | |
325 | See SECURITY CONSIDERATIONS, below, for more info on why this is useful. |
611 | See SECURITY CONSIDERATIONS, below, for more info on why this is useful. |
326 | |
612 | |
327 | =item $json_text = $json->encode ($perl_scalar) |
613 | =item $json_text = $json->encode ($perl_scalar) |
328 | |
614 | |
… | |
… | |
340 | |
626 | |
341 | JSON numbers and strings become simple Perl scalars. JSON arrays become |
627 | JSON numbers and strings become simple Perl scalars. JSON arrays become |
342 | Perl arrayrefs and JSON objects become Perl hashrefs. C<true> becomes |
628 | Perl arrayrefs and JSON objects become Perl hashrefs. C<true> becomes |
343 | C<1>, C<false> becomes C<0> and C<null> becomes C<undef>. |
629 | C<1>, C<false> becomes C<0> and C<null> becomes C<undef>. |
344 | |
630 | |
|
|
631 | =item ($perl_scalar, $characters) = $json->decode_prefix ($json_text) |
|
|
632 | |
|
|
633 | This works like the C<decode> method, but instead of raising an exception |
|
|
634 | when there is trailing garbage after the first JSON object, it will |
|
|
635 | silently stop parsing there and return the number of characters consumed |
|
|
636 | so far. |
|
|
637 | |
|
|
638 | This is useful if your JSON texts are not delimited by an outer protocol |
|
|
639 | (which is not the brightest thing to do in the first place) and you need |
|
|
640 | to know where the JSON text ends. |
|
|
641 | |
|
|
642 | JSON::XS->new->decode_prefix ("[1] the tail") |
|
|
643 | => ([], 3) |
|
|
644 | |
345 | =back |
645 | =back |
346 | |
646 | |
347 | |
647 | |
348 | =head1 MAPPING |
648 | =head1 MAPPING |
349 | |
649 | |
… | |
… | |
351 | vice versa. These mappings are designed to "do the right thing" in most |
651 | vice versa. These mappings are designed to "do the right thing" in most |
352 | circumstances automatically, preserving round-tripping characteristics |
652 | circumstances automatically, preserving round-tripping characteristics |
353 | (what you put in comes out as something equivalent). |
653 | (what you put in comes out as something equivalent). |
354 | |
654 | |
355 | For the more enlightened: note that in the following descriptions, |
655 | For the more enlightened: note that in the following descriptions, |
356 | lowercase I<perl> refers to the Perl interpreter, while uppcercase I<Perl> |
656 | lowercase I<perl> refers to the Perl interpreter, while uppercase I<Perl> |
357 | refers to the abstract Perl language itself. |
657 | refers to the abstract Perl language itself. |
358 | |
658 | |
|
|
659 | |
359 | =head2 JSON -> PERL |
660 | =head2 JSON -> PERL |
360 | |
661 | |
361 | =over 4 |
662 | =over 4 |
362 | |
663 | |
363 | =item object |
664 | =item object |
364 | |
665 | |
365 | A JSON object becomes a reference to a hash in Perl. No ordering of object |
666 | A JSON object becomes a reference to a hash in Perl. No ordering of object |
366 | keys is preserved (JSON does not preserver object key ordering itself). |
667 | keys is preserved (JSON does not preserve object key ordering itself). |
367 | |
668 | |
368 | =item array |
669 | =item array |
369 | |
670 | |
370 | A JSON array becomes a reference to an array in Perl. |
671 | A JSON array becomes a reference to an array in Perl. |
371 | |
672 | |
… | |
… | |
375 | are represented by the same codepoints in the Perl string, so no manual |
676 | are represented by the same codepoints in the Perl string, so no manual |
376 | decoding is necessary. |
677 | decoding is necessary. |
377 | |
678 | |
378 | =item number |
679 | =item number |
379 | |
680 | |
380 | A JSON number becomes either an integer or numeric (floating point) |
681 | A JSON number becomes either an integer, numeric (floating point) or |
381 | scalar in perl, depending on its range and any fractional parts. On the |
682 | string scalar in perl, depending on its range and any fractional parts. On |
382 | Perl level, there is no difference between those as Perl handles all the |
683 | the Perl level, there is no difference between those as Perl handles all |
383 | conversion details, but an integer may take slightly less memory and might |
684 | the conversion details, but an integer may take slightly less memory and |
384 | represent more values exactly than (floating point) numbers. |
685 | might represent more values exactly than (floating point) numbers. |
|
|
686 | |
|
|
687 | If the number consists of digits only, JSON::XS will try to represent |
|
|
688 | it as an integer value. If that fails, it will try to represent it as |
|
|
689 | a numeric (floating point) value if that is possible without loss of |
|
|
690 | precision. Otherwise it will preserve the number as a string value. |
|
|
691 | |
|
|
692 | Numbers containing a fractional or exponential part will always be |
|
|
693 | represented as numeric (floating point) values, possibly at a loss of |
|
|
694 | precision. |
|
|
695 | |
|
|
696 | This might create round-tripping problems as numbers might become strings, |
|
|
697 | but as Perl is typeless there is no other way to do it. |
385 | |
698 | |
386 | =item true, false |
699 | =item true, false |
387 | |
700 | |
388 | These JSON atoms become C<0>, C<1>, respectively. Information is lost in |
701 | These JSON atoms become C<JSON::XS::true> and C<JSON::XS::false>, |
389 | this process. Future versions might represent those values differently, |
702 | respectively. They are overloaded to act almost exactly like the numbers |
390 | but they will be guarenteed to act like these integers would normally in |
703 | C<1> and C<0>. You can check whether a scalar is a JSON boolean by using |
391 | Perl. |
704 | the C<JSON::XS::is_bool> function. |
392 | |
705 | |
393 | =item null |
706 | =item null |
394 | |
707 | |
395 | A JSON null atom becomes C<undef> in Perl. |
708 | A JSON null atom becomes C<undef> in Perl. |
396 | |
709 | |
397 | =back |
710 | =back |
|
|
711 | |
398 | |
712 | |
399 | =head2 PERL -> JSON |
713 | =head2 PERL -> JSON |
400 | |
714 | |
401 | The mapping from Perl to JSON is slightly more difficult, as Perl is a |
715 | The mapping from Perl to JSON is slightly more difficult, as Perl is a |
402 | truly typeless language, so we can only guess which JSON type is meant by |
716 | truly typeless language, so we can only guess which JSON type is meant by |
… | |
… | |
405 | =over 4 |
719 | =over 4 |
406 | |
720 | |
407 | =item hash references |
721 | =item hash references |
408 | |
722 | |
409 | Perl hash references become JSON objects. As there is no inherent ordering |
723 | Perl hash references become JSON objects. As there is no inherent ordering |
410 | in hash keys, they will usually be encoded in a pseudo-random order that |
724 | in hash keys (or JSON objects), they will usually be encoded in a |
411 | can change between runs of the same program but stays generally the same |
725 | pseudo-random order that can change between runs of the same program but |
412 | within a single run of a program. JSON::XS can optionally sort the hash |
726 | stays generally the same within a single run of a program. JSON::XS can |
413 | keys (determined by the I<canonical> flag), so the same datastructure |
727 | optionally sort the hash keys (determined by the I<canonical> flag), so |
414 | will serialise to the same JSON text (given same settings and version of |
728 | the same datastructure will serialise to the same JSON text (given same |
415 | JSON::XS), but this incurs a runtime overhead. |
729 | settings and version of JSON::XS), but this incurs a runtime overhead |
|
|
730 | and is only rarely useful, e.g. when you want to compare some JSON text |
|
|
731 | against another for equality. |
416 | |
732 | |
417 | =item array references |
733 | =item array references |
418 | |
734 | |
419 | Perl array references become JSON arrays. |
735 | Perl array references become JSON arrays. |
|
|
736 | |
|
|
737 | =item other references |
|
|
738 | |
|
|
739 | Other unblessed references are generally not allowed and will cause an |
|
|
740 | exception to be thrown, except for references to the integers C<0> and |
|
|
741 | C<1>, which get turned into C<false> and C<true> atoms in JSON. You can |
|
|
742 | also use C<JSON::XS::false> and C<JSON::XS::true> to improve readability. |
|
|
743 | |
|
|
744 | to_json [\0,JSON::XS::true] # yields [false,true] |
|
|
745 | |
|
|
746 | =item JSON::XS::true, JSON::XS::false |
|
|
747 | |
|
|
748 | These special values become JSON true and JSON false values, |
|
|
749 | respectively. You can also use C<\1> and C<\0> directly if you want. |
420 | |
750 | |
421 | =item blessed objects |
751 | =item blessed objects |
422 | |
752 | |
423 | Blessed objects are not allowed. JSON::XS currently tries to encode their |
753 | Blessed objects are not allowed. JSON::XS currently tries to encode their |
424 | underlying representation (hash- or arrayref), but this behaviour might |
754 | underlying representation (hash- or arrayref), but this behaviour might |
… | |
… | |
441 | to_json [$value] # yields ["5"] |
771 | to_json [$value] # yields ["5"] |
442 | |
772 | |
443 | # undef becomes null |
773 | # undef becomes null |
444 | to_json [undef] # yields [null] |
774 | to_json [undef] # yields [null] |
445 | |
775 | |
446 | You can force the type to be a string by stringifying it: |
776 | You can force the type to be a JSON string by stringifying it: |
447 | |
777 | |
448 | my $x = 3.1; # some variable containing a number |
778 | my $x = 3.1; # some variable containing a number |
449 | "$x"; # stringified |
779 | "$x"; # stringified |
450 | $x .= ""; # another, more awkward way to stringify |
780 | $x .= ""; # another, more awkward way to stringify |
451 | print $x; # perl does it for you, too, quite often |
781 | print $x; # perl does it for you, too, quite often |
452 | |
782 | |
453 | You can force the type to be a number by numifying it: |
783 | You can force the type to be a JSON number by numifying it: |
454 | |
784 | |
455 | my $x = "3"; # some variable containing a string |
785 | my $x = "3"; # some variable containing a string |
456 | $x += 0; # numify it, ensuring it will be dumped as a number |
786 | $x += 0; # numify it, ensuring it will be dumped as a number |
457 | $x *= 1; # same thing, the choise is yours. |
787 | $x *= 1; # same thing, the choice is yours. |
458 | |
788 | |
459 | You can not currently output JSON booleans or force the type in other, |
789 | You can not currently force the type in other, less obscure, ways. Tell me |
460 | less obscure, ways. Tell me if you need this capability. |
790 | if you need this capability. |
461 | |
|
|
462 | =item circular data structures |
|
|
463 | |
|
|
464 | Those will be encoded until memory or stackspace runs out. |
|
|
465 | |
791 | |
466 | =back |
792 | =back |
467 | |
793 | |
468 | |
794 | |
469 | =head1 COMPARISON |
795 | =head1 COMPARISON |
… | |
… | |
478 | |
804 | |
479 | =item JSON 1.07 |
805 | =item JSON 1.07 |
480 | |
806 | |
481 | Slow (but very portable, as it is written in pure Perl). |
807 | Slow (but very portable, as it is written in pure Perl). |
482 | |
808 | |
483 | Undocumented/buggy Unicode handling (how JSON handles unicode values is |
809 | Undocumented/buggy Unicode handling (how JSON handles Unicode values is |
484 | undocumented. One can get far by feeding it unicode strings and doing |
810 | undocumented. One can get far by feeding it Unicode strings and doing |
485 | en-/decoding oneself, but unicode escapes are not working properly). |
811 | en-/decoding oneself, but Unicode escapes are not working properly). |
486 | |
812 | |
487 | No roundtripping (strings get clobbered if they look like numbers, e.g. |
813 | No round-tripping (strings get clobbered if they look like numbers, e.g. |
488 | the string C<2.0> will encode to C<2.0> instead of C<"2.0">, and that will |
814 | the string C<2.0> will encode to C<2.0> instead of C<"2.0">, and that will |
489 | decode into the number 2. |
815 | decode into the number 2. |
490 | |
816 | |
491 | =item JSON::PC 0.01 |
817 | =item JSON::PC 0.01 |
492 | |
818 | |
493 | Very fast. |
819 | Very fast. |
494 | |
820 | |
495 | Undocumented/buggy Unicode handling. |
821 | Undocumented/buggy Unicode handling. |
496 | |
822 | |
497 | No roundtripping. |
823 | No round-tripping. |
498 | |
824 | |
499 | Has problems handling many Perl values (e.g. regex results and other magic |
825 | Has problems handling many Perl values (e.g. regex results and other magic |
500 | values will make it croak). |
826 | values will make it croak). |
501 | |
827 | |
502 | Does not even generate valid JSON (C<{1,2}> gets converted to C<{1:2}> |
828 | Does not even generate valid JSON (C<{1,2}> gets converted to C<{1:2}> |
… | |
… | |
512 | Very inflexible (no human-readable format supported, format pretty much |
838 | Very inflexible (no human-readable format supported, format pretty much |
513 | undocumented. I need at least a format for easy reading by humans and a |
839 | undocumented. I need at least a format for easy reading by humans and a |
514 | single-line compact format for use in a protocol, and preferably a way to |
840 | single-line compact format for use in a protocol, and preferably a way to |
515 | generate ASCII-only JSON texts). |
841 | generate ASCII-only JSON texts). |
516 | |
842 | |
517 | Completely broken (and confusingly documented) Unicode handling (unicode |
843 | Completely broken (and confusingly documented) Unicode handling (Unicode |
518 | escapes are not working properly, you need to set ImplicitUnicode to |
844 | escapes are not working properly, you need to set ImplicitUnicode to |
519 | I<different> values on en- and decoding to get symmetric behaviour). |
845 | I<different> values on en- and decoding to get symmetric behaviour). |
520 | |
846 | |
521 | No roundtripping (simple cases work, but this depends on wether the scalar |
847 | No round-tripping (simple cases work, but this depends on whether the scalar |
522 | value was used in a numeric context or not). |
848 | value was used in a numeric context or not). |
523 | |
849 | |
524 | Dumping hashes may skip hash values depending on iterator state. |
850 | Dumping hashes may skip hash values depending on iterator state. |
525 | |
851 | |
526 | Unmaintained (maintainer unresponsive for many months, bugs are not |
852 | Unmaintained (maintainer unresponsive for many months, bugs are not |
527 | getting fixed). |
853 | getting fixed). |
528 | |
854 | |
529 | Does not check input for validity (i.e. will accept non-JSON input and |
855 | Does not check input for validity (i.e. will accept non-JSON input and |
530 | return "something" instead of raising an exception. This is a security |
856 | return "something" instead of raising an exception. This is a security |
531 | issue: imagine two banks transfering money between each other using |
857 | issue: imagine two banks transferring money between each other using |
532 | JSON. One bank might parse a given non-JSON request and deduct money, |
858 | JSON. One bank might parse a given non-JSON request and deduct money, |
533 | while the other might reject the transaction with a syntax error. While a |
859 | while the other might reject the transaction with a syntax error. While a |
534 | good protocol will at least recover, that is extra unnecessary work and |
860 | good protocol will at least recover, that is extra unnecessary work and |
535 | the transaction will still not succeed). |
861 | the transaction will still not succeed). |
536 | |
862 | |
537 | =item JSON::DWIW 0.04 |
863 | =item JSON::DWIW 0.04 |
538 | |
864 | |
539 | Very fast. Very natural. Very nice. |
865 | Very fast. Very natural. Very nice. |
540 | |
866 | |
541 | Undocumented unicode handling (but the best of the pack. Unicode escapes |
867 | Undocumented Unicode handling (but the best of the pack. Unicode escapes |
542 | still don't get parsed properly). |
868 | still don't get parsed properly). |
543 | |
869 | |
544 | Very inflexible. |
870 | Very inflexible. |
545 | |
871 | |
546 | No roundtripping. |
872 | No round-tripping. |
547 | |
873 | |
548 | Does not generate valid JSON texts (key strings are often unquoted, empty keys |
874 | Does not generate valid JSON texts (key strings are often unquoted, empty keys |
549 | result in nothing being output) |
875 | result in nothing being output) |
550 | |
876 | |
551 | Does not check input for validity. |
877 | Does not check input for validity. |
552 | |
878 | |
553 | =back |
879 | =back |
|
|
880 | |
|
|
881 | |
|
|
882 | =head2 JSON and YAML |
|
|
883 | |
|
|
884 | You often hear that JSON is a subset (or a close subset) of YAML. This is, |
|
|
885 | however, a mass hysteria and very far from the truth. In general, there is |
|
|
886 | no way to configure JSON::XS to output a data structure as valid YAML. |
|
|
887 | |
|
|
888 | If you really must use JSON::XS to generate YAML, you should use this |
|
|
889 | algorithm (subject to change in future versions): |
|
|
890 | |
|
|
891 | my $to_yaml = JSON::XS->new->utf8->space_after (1); |
|
|
892 | my $yaml = $to_yaml->encode ($ref) . "\n"; |
|
|
893 | |
|
|
894 | This will usually generate JSON texts that also parse as valid |
|
|
895 | YAML. Please note that YAML has hardcoded limits on (simple) object key |
|
|
896 | lengths that JSON doesn't have, so you should make sure that your hash |
|
|
897 | keys are noticeably shorter than the 1024 characters YAML allows. |
|
|
898 | |
|
|
899 | There might be other incompatibilities that I am not aware of. In general |
|
|
900 | you should not try to generate YAML with a JSON generator or vice versa, |
|
|
901 | or try to parse JSON with a YAML parser or vice versa: chances are high |
|
|
902 | that you will run into severe interoperability problems. |
|
|
903 | |
554 | |
904 | |
555 | =head2 SPEED |
905 | =head2 SPEED |
556 | |
906 | |
557 | It seems that JSON::XS is surprisingly fast, as shown in the following |
907 | It seems that JSON::XS is surprisingly fast, as shown in the following |
558 | tables. They have been generated with the help of the C<eg/bench> program |
908 | tables. They have been generated with the help of the C<eg/bench> program |
559 | in the JSON::XS distribution, to make it easy to compare on your own |
909 | in the JSON::XS distribution, to make it easy to compare on your own |
560 | system. |
910 | system. |
561 | |
911 | |
562 | First comes a comparison between various modules using a very short JSON |
912 | First comes a comparison between various modules using a very short |
563 | string: |
913 | single-line JSON string: |
564 | |
914 | |
565 | {"method": "handleMessage", "params": ["user1", "we were just talking"], "id": null} |
915 | {"method": "handleMessage", "params": ["user1", "we were just talking"], \ |
|
|
916 | "id": null, "array":[1,11,234,-5,1e5,1e7, true, false]} |
566 | |
917 | |
567 | It shows the number of encodes/decodes per second (JSON::XS uses the |
918 | It shows the number of encodes/decodes per second (JSON::XS uses |
568 | functional interface, while JSON::XS/2 uses the OO interface with |
919 | the functional interface, while JSON::XS/2 uses the OO interface |
569 | pretty-printing and hashkey sorting enabled). Higher is better: |
920 | with pretty-printing and hashkey sorting enabled, JSON::XS/3 enables |
|
|
921 | shrink). Higher is better: |
570 | |
922 | |
571 | module | encode | decode | |
923 | module | encode | decode | |
572 | -----------|------------|------------| |
924 | -----------|------------|------------| |
573 | JSON | 11488.516 | 7823.035 | |
925 | JSON 1.x | 4990.842 | 4088.813 | |
574 | JSON::DWIW | 94708.054 | 129094.260 | |
926 | JSON::DWIW | 51653.990 | 71575.154 | |
575 | JSON::PC | 63884.157 | 128528.212 | |
927 | JSON::PC | 65948.176 | 74631.744 | |
576 | JSON::Syck | 34898.677 | 42096.911 | |
928 | JSON::PP | 8931.652 | 3817.168 | |
577 | JSON::XS | 654027.064 | 396423.669 | |
929 | JSON::Syck | 24877.248 | 27776.848 | |
578 | JSON::XS/2 | 371564.190 | 371725.613 | |
930 | JSON::XS | 388361.481 | 227951.304 | |
|
|
931 | JSON::XS/2 | 227951.304 | 218453.333 | |
|
|
932 | JSON::XS/3 | 338250.323 | 218453.333 | |
|
|
933 | Storable | 16500.016 | 135300.129 | |
579 | -----------+------------+------------+ |
934 | -----------+------------+------------+ |
580 | |
935 | |
581 | That is, JSON::XS is more than six times faster than JSON::DWIW on |
936 | That is, JSON::XS is about five times faster than JSON::DWIW on encoding, |
582 | encoding, more than three times faster on decoding, and about thirty times |
937 | about three times faster on decoding, and over forty times faster |
583 | faster than JSON, even with pretty-printing and key sorting. |
938 | than JSON, even with pretty-printing and key sorting. It also compares |
|
|
939 | favourably to Storable for small amounts of data. |
584 | |
940 | |
585 | Using a longer test string (roughly 18KB, generated from Yahoo! Locals |
941 | Using a longer test string (roughly 18KB, generated from Yahoo! Locals |
586 | search API (http://nanoref.com/yahooapis/mgPdGg): |
942 | search API (http://nanoref.com/yahooapis/mgPdGg): |
587 | |
943 | |
588 | module | encode | decode | |
944 | module | encode | decode | |
589 | -----------|------------|------------| |
945 | -----------|------------|------------| |
590 | JSON | 273.023 | 44.674 | |
946 | JSON 1.x | 55.260 | 34.971 | |
591 | JSON::DWIW | 1089.383 | 1145.704 | |
947 | JSON::DWIW | 825.228 | 1082.513 | |
592 | JSON::PC | 3097.419 | 2393.921 | |
948 | JSON::PC | 3571.444 | 2394.829 | |
593 | JSON::Syck | 514.060 | 843.053 | |
949 | JSON::PP | 210.987 | 32.574 | |
594 | JSON::XS | 6479.668 | 3636.364 | |
950 | JSON::Syck | 552.551 | 787.544 | |
595 | JSON::XS/2 | 3774.221 | 3599.124 | |
951 | JSON::XS | 5780.463 | 4854.519 | |
|
|
952 | JSON::XS/2 | 3869.998 | 4798.975 | |
|
|
953 | JSON::XS/3 | 5862.880 | 4798.975 | |
|
|
954 | Storable | 4445.002 | 5235.027 | |
596 | -----------+------------+------------+ |
955 | -----------+------------+------------+ |
597 | |
956 | |
598 | Again, JSON::XS leads by far. |
957 | Again, JSON::XS leads by far (except for Storable which non-surprisingly |
|
|
958 | decodes faster). |
599 | |
959 | |
600 | On large strings containing lots of high unicode characters, some modules |
960 | On large strings containing lots of high Unicode characters, some modules |
601 | (such as JSON::PC) seem to decode faster than JSON::XS, but the result |
961 | (such as JSON::PC) seem to decode faster than JSON::XS, but the result |
602 | will be broken due to missing (or wrong) unicode handling. Others refuse |
962 | will be broken due to missing (or wrong) Unicode handling. Others refuse |
603 | to decode or encode properly, so it was impossible to prepare a fair |
963 | to decode or encode properly, so it was impossible to prepare a fair |
604 | comparison table for that case. |
964 | comparison table for that case. |
605 | |
965 | |
606 | |
966 | |
607 | =head1 SECURITY CONSIDERATIONS |
967 | =head1 SECURITY CONSIDERATIONS |
… | |
… | |
613 | any buffer overflows. Obviously, this module should ensure that and I am |
973 | any buffer overflows. Obviously, this module should ensure that and I am |
614 | trying hard on making that true, but you never know. |
974 | trying hard on making that true, but you never know. |
615 | |
975 | |
616 | Second, you need to avoid resource-starving attacks. That means you should |
976 | Second, you need to avoid resource-starving attacks. That means you should |
617 | limit the size of JSON texts you accept, or make sure then when your |
977 | limit the size of JSON texts you accept, or make sure then when your |
618 | resources run out, thats just fine (e.g. by using a separate process that |
978 | resources run out, that's just fine (e.g. by using a separate process that |
619 | can crash safely). The size of a JSON text in octets or characters is |
979 | can crash safely). The size of a JSON text in octets or characters is |
620 | usually a good indication of the size of the resources required to decode |
980 | usually a good indication of the size of the resources required to decode |
621 | it into a Perl structure. |
981 | it into a Perl structure. While JSON::XS can check the size of the JSON |
|
|
982 | text, it might be too late when you already have it in memory, so you |
|
|
983 | might want to check the size before you accept the string. |
622 | |
984 | |
623 | Third, JSON::XS recurses using the C stack when decoding objects and |
985 | Third, JSON::XS recurses using the C stack when decoding objects and |
624 | arrays. The C stack is a limited resource: for instance, on my amd64 |
986 | arrays. The C stack is a limited resource: for instance, on my amd64 |
625 | machine with 8MB of stack size I can decode around 180k nested arrays |
987 | machine with 8MB of stack size I can decode around 180k nested arrays but |
626 | but only 14k nested JSON objects. If that is exceeded, the program |
988 | only 14k nested JSON objects (due to perl itself recursing deeply on croak |
|
|
989 | to free the temporary). If that is exceeded, the program crashes. to be |
627 | crashes. Thats why the default nesting limit is set to 8192. If your |
990 | conservative, the default nesting limit is set to 512. If your process |
628 | process has a smaller stack, you should adjust this setting accordingly |
991 | has a smaller stack, you should adjust this setting accordingly with the |
629 | with the C<max_depth> method. |
992 | C<max_depth> method. |
630 | |
993 | |
631 | And last but least, something else could bomb you that I forgot to think |
994 | And last but least, something else could bomb you that I forgot to think |
632 | of. In that case, you get to keep the pieces. I am alway sopen for hints, |
995 | of. In that case, you get to keep the pieces. I am always open for hints, |
633 | though... |
996 | though... |
|
|
997 | |
|
|
998 | If you are using JSON::XS to return packets to consumption |
|
|
999 | by JavaScript scripts in a browser you should have a look at |
|
|
1000 | L<http://jpsykes.com/47/practical-csrf-and-json-security> to see whether |
|
|
1001 | you are vulnerable to some common attack vectors (which really are browser |
|
|
1002 | design bugs, but it is still you who will have to deal with it, as major |
|
|
1003 | browser developers care only for features, not about doing security |
|
|
1004 | right). |
|
|
1005 | |
|
|
1006 | |
|
|
1007 | =head1 THREADS |
|
|
1008 | |
|
|
1009 | This module is I<not> guaranteed to be thread safe and there are no |
|
|
1010 | plans to change this until Perl gets thread support (as opposed to the |
|
|
1011 | horribly slow so-called "threads" which are simply slow and bloated |
|
|
1012 | process simulations - use fork, its I<much> faster, cheaper, better). |
|
|
1013 | |
|
|
1014 | (It might actually work, but you have been warned). |
634 | |
1015 | |
635 | |
1016 | |
636 | =head1 BUGS |
1017 | =head1 BUGS |
637 | |
1018 | |
638 | While the goal of this module is to be correct, that unfortunately does |
1019 | While the goal of this module is to be correct, that unfortunately does |
639 | not mean its bug-free, only that I think its design is bug-free. It is |
1020 | not mean its bug-free, only that I think its design is bug-free. It is |
640 | still relatively early in its development. If you keep reporting bugs they |
1021 | still relatively early in its development. If you keep reporting bugs they |
641 | will be fixed swiftly, though. |
1022 | will be fixed swiftly, though. |
642 | |
1023 | |
|
|
1024 | Please refrain from using rt.cpan.org or any other bug reporting |
|
|
1025 | service. I put the contact address into my modules for a reason. |
|
|
1026 | |
643 | =cut |
1027 | =cut |
|
|
1028 | |
|
|
1029 | our $true = do { bless \(my $dummy = 1), "JSON::XS::Boolean" }; |
|
|
1030 | our $false = do { bless \(my $dummy = 0), "JSON::XS::Boolean" }; |
|
|
1031 | |
|
|
1032 | sub true() { $true } |
|
|
1033 | sub false() { $false } |
|
|
1034 | |
|
|
1035 | sub is_bool($) { |
|
|
1036 | UNIVERSAL::isa $_[0], "JSON::XS::Boolean" |
|
|
1037 | # or UNIVERSAL::isa $_[0], "JSON::Literal" |
|
|
1038 | } |
|
|
1039 | |
|
|
1040 | XSLoader::load "JSON::XS", $VERSION; |
|
|
1041 | |
|
|
1042 | package JSON::XS::Boolean; |
|
|
1043 | |
|
|
1044 | use overload |
|
|
1045 | "0+" => sub { ${$_[0]} }, |
|
|
1046 | "++" => sub { $_[0] = ${$_[0]} + 1 }, |
|
|
1047 | "--" => sub { $_[0] = ${$_[0]} - 1 }, |
|
|
1048 | fallback => 1; |
644 | |
1049 | |
645 | 1; |
1050 | 1; |
646 | |
1051 | |
647 | =head1 AUTHOR |
1052 | =head1 AUTHOR |
648 | |
1053 | |