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 | |
4 | |
|
|
5 | =encoding utf-8 |
|
|
6 | |
|
|
7 | JSON::XS - 正しくて高速な JSON シリアライザ/デシリアライザ |
|
|
8 | (http://fleur.hio.jp/perldoc/mix/lib/JSON/XS.html) |
|
|
9 | |
5 | =head1 SYNOPSIS |
10 | =head1 SYNOPSIS |
6 | |
11 | |
7 | use JSON::XS; |
12 | use JSON::XS; |
8 | |
13 | |
|
|
14 | # exported functions, they croak on error |
|
|
15 | # and expect/generate UTF-8 |
|
|
16 | |
|
|
17 | $utf8_encoded_json_text = encode_json $perl_hash_or_arrayref; |
|
|
18 | $perl_hash_or_arrayref = decode_json $utf8_encoded_json_text; |
|
|
19 | |
|
|
20 | # OO-interface |
|
|
21 | |
|
|
22 | $coder = JSON::XS->new->ascii->pretty->allow_nonref; |
|
|
23 | $pretty_printed_unencoded = $coder->encode ($perl_scalar); |
|
|
24 | $perl_scalar = $coder->decode ($unicode_json_text); |
|
|
25 | |
|
|
26 | # Note that JSON version 2.0 and above will automatically use JSON::XS |
|
|
27 | # if available, at virtually no speed overhead either, so you should |
|
|
28 | # be able to just: |
|
|
29 | |
|
|
30 | use JSON; |
|
|
31 | |
|
|
32 | # and do the same things, except that you have a pure-perl fallback now. |
|
|
33 | |
9 | =head1 DESCRIPTION |
34 | =head1 DESCRIPTION |
10 | |
35 | |
|
|
36 | This module converts Perl data structures to JSON and vice versa. Its |
|
|
37 | primary goal is to be I<correct> and its secondary goal is to be |
|
|
38 | I<fast>. To reach the latter goal it was written in C. |
|
|
39 | |
|
|
40 | Beginning with version 2.0 of the JSON module, when both JSON and |
|
|
41 | JSON::XS are installed, then JSON will fall back on JSON::XS (this can be |
|
|
42 | overridden) with no overhead due to emulation (by inheriting constructor |
|
|
43 | and methods). If JSON::XS is not available, it will fall back to the |
|
|
44 | compatible JSON::PP module as backend, so using JSON instead of JSON::XS |
|
|
45 | gives you a portable JSON API that can be fast when you need and doesn't |
|
|
46 | require a C compiler when that is a problem. |
|
|
47 | |
|
|
48 | As this is the n-th-something JSON module on CPAN, what was the reason |
|
|
49 | to write yet another JSON module? While it seems there are many JSON |
|
|
50 | modules, none of them correctly handle all corner cases, and in most cases |
|
|
51 | their maintainers are unresponsive, gone missing, or not listening to bug |
|
|
52 | reports for other reasons. |
|
|
53 | |
|
|
54 | See MAPPING, below, on how JSON::XS maps perl values to JSON values and |
|
|
55 | vice versa. |
|
|
56 | |
|
|
57 | =head2 FEATURES |
|
|
58 | |
11 | =over 4 |
59 | =over 4 |
12 | |
60 | |
|
|
61 | =item * correct Unicode handling |
|
|
62 | |
|
|
63 | This module knows how to handle Unicode, documents how and when it does |
|
|
64 | so, and even documents what "correct" means. |
|
|
65 | |
|
|
66 | =item * round-trip integrity |
|
|
67 | |
|
|
68 | When you serialise a perl data structure using only data types supported |
|
|
69 | by JSON and Perl, the deserialised data structure is identical on the Perl |
|
|
70 | level. (e.g. the string "2.0" doesn't suddenly become "2" just because |
|
|
71 | it looks like a number). There I<are> minor exceptions to this, read the |
|
|
72 | MAPPING section below to learn about those. |
|
|
73 | |
|
|
74 | =item * strict checking of JSON correctness |
|
|
75 | |
|
|
76 | There is no guessing, no generating of illegal JSON texts by default, |
|
|
77 | and only JSON is accepted as input by default (the latter is a security |
|
|
78 | feature). |
|
|
79 | |
|
|
80 | =item * fast |
|
|
81 | |
|
|
82 | Compared to other JSON modules and other serialisers such as Storable, |
|
|
83 | this module usually compares favourably in terms of speed, too. |
|
|
84 | |
|
|
85 | =item * simple to use |
|
|
86 | |
|
|
87 | This module has both a simple functional interface as well as an object |
|
|
88 | oriented interface. |
|
|
89 | |
|
|
90 | =item * reasonably versatile output formats |
|
|
91 | |
|
|
92 | You can choose between the most compact guaranteed-single-line format |
|
|
93 | possible (nice for simple line-based protocols), a pure-ASCII format |
|
|
94 | (for when your transport is not 8-bit clean, still supports the whole |
|
|
95 | Unicode range), or a pretty-printed format (for when you want to read that |
|
|
96 | stuff). Or you can combine those features in whatever way you like. |
|
|
97 | |
|
|
98 | =back |
|
|
99 | |
13 | =cut |
100 | =cut |
14 | |
101 | |
15 | package JSON::XS; |
102 | package JSON::XS; |
16 | |
103 | |
|
|
104 | use common::sense; |
|
|
105 | |
|
|
106 | our $VERSION = 3.01; |
|
|
107 | our @ISA = qw(Exporter); |
|
|
108 | |
|
|
109 | our @EXPORT = qw(encode_json decode_json); |
|
|
110 | |
|
|
111 | use Exporter; |
|
|
112 | use XSLoader; |
|
|
113 | |
|
|
114 | use Types::Serialiser (); |
|
|
115 | |
|
|
116 | =head1 FUNCTIONAL INTERFACE |
|
|
117 | |
|
|
118 | The following convenience methods are provided by this module. They are |
|
|
119 | exported by default: |
|
|
120 | |
|
|
121 | =over 4 |
|
|
122 | |
|
|
123 | =item $json_text = encode_json $perl_scalar |
|
|
124 | |
|
|
125 | Converts the given Perl data structure to a UTF-8 encoded, binary string |
|
|
126 | (that is, the string contains octets only). Croaks on error. |
|
|
127 | |
|
|
128 | This function call is functionally identical to: |
|
|
129 | |
|
|
130 | $json_text = JSON::XS->new->utf8->encode ($perl_scalar) |
|
|
131 | |
|
|
132 | Except being faster. |
|
|
133 | |
|
|
134 | =item $perl_scalar = decode_json $json_text |
|
|
135 | |
|
|
136 | The opposite of C<encode_json>: expects an UTF-8 (binary) string and tries |
|
|
137 | to parse that as an UTF-8 encoded JSON text, returning the resulting |
|
|
138 | reference. Croaks on error. |
|
|
139 | |
|
|
140 | This function call is functionally identical to: |
|
|
141 | |
|
|
142 | $perl_scalar = JSON::XS->new->utf8->decode ($json_text) |
|
|
143 | |
|
|
144 | Except being faster. |
|
|
145 | |
|
|
146 | =back |
|
|
147 | |
|
|
148 | |
|
|
149 | =head1 A FEW NOTES ON UNICODE AND PERL |
|
|
150 | |
|
|
151 | Since this often leads to confusion, here are a few very clear words on |
|
|
152 | how Unicode works in Perl, modulo bugs. |
|
|
153 | |
|
|
154 | =over 4 |
|
|
155 | |
|
|
156 | =item 1. Perl strings can store characters with ordinal values > 255. |
|
|
157 | |
|
|
158 | This enables you to store Unicode characters as single characters in a |
|
|
159 | Perl string - very natural. |
|
|
160 | |
|
|
161 | =item 2. Perl does I<not> associate an encoding with your strings. |
|
|
162 | |
|
|
163 | ... until you force it to, e.g. when matching it against a regex, or |
|
|
164 | printing the scalar to a file, in which case Perl either interprets your |
|
|
165 | string as locale-encoded text, octets/binary, or as Unicode, depending |
|
|
166 | on various settings. In no case is an encoding stored together with your |
|
|
167 | data, it is I<use> that decides encoding, not any magical meta data. |
|
|
168 | |
|
|
169 | =item 3. The internal utf-8 flag has no meaning with regards to the |
|
|
170 | encoding of your string. |
|
|
171 | |
|
|
172 | Just ignore that flag unless you debug a Perl bug, a module written in |
|
|
173 | XS or want to dive into the internals of perl. Otherwise it will only |
|
|
174 | confuse you, as, despite the name, it says nothing about how your string |
|
|
175 | is encoded. You can have Unicode strings with that flag set, with that |
|
|
176 | flag clear, and you can have binary data with that flag set and that flag |
|
|
177 | clear. Other possibilities exist, too. |
|
|
178 | |
|
|
179 | If you didn't know about that flag, just the better, pretend it doesn't |
|
|
180 | exist. |
|
|
181 | |
|
|
182 | =item 4. A "Unicode String" is simply a string where each character can be |
|
|
183 | validly interpreted as a Unicode code point. |
|
|
184 | |
|
|
185 | If you have UTF-8 encoded data, it is no longer a Unicode string, but a |
|
|
186 | Unicode string encoded in UTF-8, giving you a binary string. |
|
|
187 | |
|
|
188 | =item 5. A string containing "high" (> 255) character values is I<not> a UTF-8 string. |
|
|
189 | |
|
|
190 | It's a fact. Learn to live with it. |
|
|
191 | |
|
|
192 | =back |
|
|
193 | |
|
|
194 | I hope this helps :) |
|
|
195 | |
|
|
196 | |
|
|
197 | =head1 OBJECT-ORIENTED INTERFACE |
|
|
198 | |
|
|
199 | The object oriented interface lets you configure your own encoding or |
|
|
200 | decoding style, within the limits of supported formats. |
|
|
201 | |
|
|
202 | =over 4 |
|
|
203 | |
|
|
204 | =item $json = new JSON::XS |
|
|
205 | |
|
|
206 | Creates a new JSON::XS object that can be used to de/encode JSON |
|
|
207 | strings. All boolean flags described below are by default I<disabled>. |
|
|
208 | |
|
|
209 | The mutators for flags all return the JSON object again and thus calls can |
|
|
210 | be chained: |
|
|
211 | |
|
|
212 | my $json = JSON::XS->new->utf8->space_after->encode ({a => [1,2]}) |
|
|
213 | => {"a": [1, 2]} |
|
|
214 | |
|
|
215 | =item $json = $json->ascii ([$enable]) |
|
|
216 | |
|
|
217 | =item $enabled = $json->get_ascii |
|
|
218 | |
|
|
219 | If C<$enable> is true (or missing), then the C<encode> method will not |
|
|
220 | generate characters outside the code range C<0..127> (which is ASCII). Any |
|
|
221 | Unicode characters outside that range will be escaped using either a |
|
|
222 | single \uXXXX (BMP characters) or a double \uHHHH\uLLLLL escape sequence, |
|
|
223 | as per RFC4627. The resulting encoded JSON text can be treated as a native |
|
|
224 | Unicode string, an ascii-encoded, latin1-encoded or UTF-8 encoded string, |
|
|
225 | or any other superset of ASCII. |
|
|
226 | |
|
|
227 | If C<$enable> is false, then the C<encode> method will not escape Unicode |
|
|
228 | characters unless required by the JSON syntax or other flags. This results |
|
|
229 | in a faster and more compact format. |
|
|
230 | |
|
|
231 | See also the section I<ENCODING/CODESET FLAG NOTES> later in this |
|
|
232 | document. |
|
|
233 | |
|
|
234 | The main use for this flag is to produce JSON texts that can be |
|
|
235 | transmitted over a 7-bit channel, as the encoded JSON texts will not |
|
|
236 | contain any 8 bit characters. |
|
|
237 | |
|
|
238 | JSON::XS->new->ascii (1)->encode ([chr 0x10401]) |
|
|
239 | => ["\ud801\udc01"] |
|
|
240 | |
|
|
241 | =item $json = $json->latin1 ([$enable]) |
|
|
242 | |
|
|
243 | =item $enabled = $json->get_latin1 |
|
|
244 | |
|
|
245 | If C<$enable> is true (or missing), then the C<encode> method will encode |
|
|
246 | the resulting JSON text as latin1 (or iso-8859-1), escaping any characters |
|
|
247 | outside the code range C<0..255>. The resulting string can be treated as a |
|
|
248 | latin1-encoded JSON text or a native Unicode string. The C<decode> method |
|
|
249 | will not be affected in any way by this flag, as C<decode> by default |
|
|
250 | expects Unicode, which is a strict superset of latin1. |
|
|
251 | |
|
|
252 | If C<$enable> is false, then the C<encode> method will not escape Unicode |
|
|
253 | characters unless required by the JSON syntax or other flags. |
|
|
254 | |
|
|
255 | See also the section I<ENCODING/CODESET FLAG NOTES> later in this |
|
|
256 | document. |
|
|
257 | |
|
|
258 | The main use for this flag is efficiently encoding binary data as JSON |
|
|
259 | text, as most octets will not be escaped, resulting in a smaller encoded |
|
|
260 | size. The disadvantage is that the resulting JSON text is encoded |
|
|
261 | in latin1 (and must correctly be treated as such when storing and |
|
|
262 | transferring), a rare encoding for JSON. It is therefore most useful when |
|
|
263 | you want to store data structures known to contain binary data efficiently |
|
|
264 | in files or databases, not when talking to other JSON encoders/decoders. |
|
|
265 | |
|
|
266 | JSON::XS->new->latin1->encode (["\x{89}\x{abc}"] |
|
|
267 | => ["\x{89}\\u0abc"] # (perl syntax, U+abc escaped, U+89 not) |
|
|
268 | |
|
|
269 | =item $json = $json->utf8 ([$enable]) |
|
|
270 | |
|
|
271 | =item $enabled = $json->get_utf8 |
|
|
272 | |
|
|
273 | If C<$enable> is true (or missing), then the C<encode> method will encode |
|
|
274 | the JSON result into UTF-8, as required by many protocols, while the |
|
|
275 | C<decode> method expects to be handled an UTF-8-encoded string. Please |
|
|
276 | note that UTF-8-encoded strings do not contain any characters outside the |
|
|
277 | range C<0..255>, they are thus useful for bytewise/binary I/O. In future |
|
|
278 | versions, enabling this option might enable autodetection of the UTF-16 |
|
|
279 | and UTF-32 encoding families, as described in RFC4627. |
|
|
280 | |
|
|
281 | If C<$enable> is false, then the C<encode> method will return the JSON |
|
|
282 | string as a (non-encoded) Unicode string, while C<decode> expects thus a |
|
|
283 | Unicode string. Any decoding or encoding (e.g. to UTF-8 or UTF-16) needs |
|
|
284 | to be done yourself, e.g. using the Encode module. |
|
|
285 | |
|
|
286 | See also the section I<ENCODING/CODESET FLAG NOTES> later in this |
|
|
287 | document. |
|
|
288 | |
|
|
289 | Example, output UTF-16BE-encoded JSON: |
|
|
290 | |
|
|
291 | use Encode; |
|
|
292 | $jsontext = encode "UTF-16BE", JSON::XS->new->encode ($object); |
|
|
293 | |
|
|
294 | Example, decode UTF-32LE-encoded JSON: |
|
|
295 | |
|
|
296 | use Encode; |
|
|
297 | $object = JSON::XS->new->decode (decode "UTF-32LE", $jsontext); |
|
|
298 | |
|
|
299 | =item $json = $json->pretty ([$enable]) |
|
|
300 | |
|
|
301 | This enables (or disables) all of the C<indent>, C<space_before> and |
|
|
302 | C<space_after> (and in the future possibly more) flags in one call to |
|
|
303 | generate the most readable (or most compact) form possible. |
|
|
304 | |
|
|
305 | Example, pretty-print some simple structure: |
|
|
306 | |
|
|
307 | my $json = JSON::XS->new->pretty(1)->encode ({a => [1,2]}) |
|
|
308 | => |
|
|
309 | { |
|
|
310 | "a" : [ |
|
|
311 | 1, |
|
|
312 | 2 |
|
|
313 | ] |
|
|
314 | } |
|
|
315 | |
|
|
316 | =item $json = $json->indent ([$enable]) |
|
|
317 | |
|
|
318 | =item $enabled = $json->get_indent |
|
|
319 | |
|
|
320 | If C<$enable> is true (or missing), then the C<encode> method will use a multiline |
|
|
321 | format as output, putting every array member or object/hash key-value pair |
|
|
322 | into its own line, indenting them properly. |
|
|
323 | |
|
|
324 | If C<$enable> is false, no newlines or indenting will be produced, and the |
|
|
325 | resulting JSON text is guaranteed not to contain any C<newlines>. |
|
|
326 | |
|
|
327 | This setting has no effect when decoding JSON texts. |
|
|
328 | |
|
|
329 | =item $json = $json->space_before ([$enable]) |
|
|
330 | |
|
|
331 | =item $enabled = $json->get_space_before |
|
|
332 | |
|
|
333 | If C<$enable> is true (or missing), then the C<encode> method will add an extra |
|
|
334 | optional space before the C<:> separating keys from values in JSON objects. |
|
|
335 | |
|
|
336 | If C<$enable> is false, then the C<encode> method will not add any extra |
|
|
337 | space at those places. |
|
|
338 | |
|
|
339 | This setting has no effect when decoding JSON texts. You will also |
|
|
340 | most likely combine this setting with C<space_after>. |
|
|
341 | |
|
|
342 | Example, space_before enabled, space_after and indent disabled: |
|
|
343 | |
|
|
344 | {"key" :"value"} |
|
|
345 | |
|
|
346 | =item $json = $json->space_after ([$enable]) |
|
|
347 | |
|
|
348 | =item $enabled = $json->get_space_after |
|
|
349 | |
|
|
350 | If C<$enable> is true (or missing), then the C<encode> method will add an extra |
|
|
351 | optional space after the C<:> separating keys from values in JSON objects |
|
|
352 | and extra whitespace after the C<,> separating key-value pairs and array |
|
|
353 | members. |
|
|
354 | |
|
|
355 | If C<$enable> is false, then the C<encode> method will not add any extra |
|
|
356 | space at those places. |
|
|
357 | |
|
|
358 | This setting has no effect when decoding JSON texts. |
|
|
359 | |
|
|
360 | Example, space_before and indent disabled, space_after enabled: |
|
|
361 | |
|
|
362 | {"key": "value"} |
|
|
363 | |
|
|
364 | =item $json = $json->relaxed ([$enable]) |
|
|
365 | |
|
|
366 | =item $enabled = $json->get_relaxed |
|
|
367 | |
|
|
368 | If C<$enable> is true (or missing), then C<decode> will accept some |
|
|
369 | extensions to normal JSON syntax (see below). C<encode> will not be |
|
|
370 | affected in anyway. I<Be aware that this option makes you accept invalid |
|
|
371 | JSON texts as if they were valid!>. I suggest only to use this option to |
|
|
372 | parse application-specific files written by humans (configuration files, |
|
|
373 | resource files etc.) |
|
|
374 | |
|
|
375 | If C<$enable> is false (the default), then C<decode> will only accept |
|
|
376 | valid JSON texts. |
|
|
377 | |
|
|
378 | Currently accepted extensions are: |
|
|
379 | |
|
|
380 | =over 4 |
|
|
381 | |
|
|
382 | =item * list items can have an end-comma |
|
|
383 | |
|
|
384 | JSON I<separates> array elements and key-value pairs with commas. This |
|
|
385 | can be annoying if you write JSON texts manually and want to be able to |
|
|
386 | quickly append elements, so this extension accepts comma at the end of |
|
|
387 | such items not just between them: |
|
|
388 | |
|
|
389 | [ |
|
|
390 | 1, |
|
|
391 | 2, <- this comma not normally allowed |
|
|
392 | ] |
|
|
393 | { |
|
|
394 | "k1": "v1", |
|
|
395 | "k2": "v2", <- this comma not normally allowed |
|
|
396 | } |
|
|
397 | |
|
|
398 | =item * shell-style '#'-comments |
|
|
399 | |
|
|
400 | Whenever JSON allows whitespace, shell-style comments are additionally |
|
|
401 | allowed. They are terminated by the first carriage-return or line-feed |
|
|
402 | character, after which more white-space and comments are allowed. |
|
|
403 | |
|
|
404 | [ |
|
|
405 | 1, # this comment not allowed in JSON |
|
|
406 | # neither this one... |
|
|
407 | ] |
|
|
408 | |
|
|
409 | =item * literal ASCII TAB characters in strings |
|
|
410 | |
|
|
411 | Literal ASCII TAB characters are now allowed in strings (and treated as |
|
|
412 | C<\t>). |
|
|
413 | |
|
|
414 | [ |
|
|
415 | "Hello\tWorld", |
|
|
416 | "Hello<TAB>World", # literal <TAB> would not normally be allowed |
|
|
417 | ] |
|
|
418 | |
|
|
419 | =back |
|
|
420 | |
|
|
421 | =item $json = $json->canonical ([$enable]) |
|
|
422 | |
|
|
423 | =item $enabled = $json->get_canonical |
|
|
424 | |
|
|
425 | If C<$enable> is true (or missing), then the C<encode> method will output JSON objects |
|
|
426 | by sorting their keys. This is adding a comparatively high overhead. |
|
|
427 | |
|
|
428 | If C<$enable> is false, then the C<encode> method will output key-value |
|
|
429 | pairs in the order Perl stores them (which will likely change between runs |
|
|
430 | of the same script, and can change even within the same run from 5.18 |
|
|
431 | onwards). |
|
|
432 | |
|
|
433 | This option is useful if you want the same data structure to be encoded as |
|
|
434 | the same JSON text (given the same overall settings). If it is disabled, |
|
|
435 | the same hash might be encoded differently even if contains the same data, |
|
|
436 | as key-value pairs have no inherent ordering in Perl. |
|
|
437 | |
|
|
438 | This setting has no effect when decoding JSON texts. |
|
|
439 | |
|
|
440 | This setting has currently no effect on tied hashes. |
|
|
441 | |
|
|
442 | =item $json = $json->allow_nonref ([$enable]) |
|
|
443 | |
|
|
444 | =item $enabled = $json->get_allow_nonref |
|
|
445 | |
|
|
446 | If C<$enable> is true (or missing), then the C<encode> method can convert a |
|
|
447 | non-reference into its corresponding string, number or null JSON value, |
|
|
448 | which is an extension to RFC4627. Likewise, C<decode> will accept those JSON |
|
|
449 | values instead of croaking. |
|
|
450 | |
|
|
451 | If C<$enable> is false, then the C<encode> method will croak if it isn't |
|
|
452 | passed an arrayref or hashref, as JSON texts must either be an object |
|
|
453 | or array. Likewise, C<decode> will croak if given something that is not a |
|
|
454 | JSON object or array. |
|
|
455 | |
|
|
456 | Example, encode a Perl scalar as JSON value with enabled C<allow_nonref>, |
|
|
457 | resulting in an invalid JSON text: |
|
|
458 | |
|
|
459 | JSON::XS->new->allow_nonref->encode ("Hello, World!") |
|
|
460 | => "Hello, World!" |
|
|
461 | |
|
|
462 | =item $json = $json->allow_unknown ([$enable]) |
|
|
463 | |
|
|
464 | =item $enabled = $json->get_allow_unknown |
|
|
465 | |
|
|
466 | If C<$enable> is true (or missing), then C<encode> will I<not> throw an |
|
|
467 | exception when it encounters values it cannot represent in JSON (for |
|
|
468 | example, filehandles) but instead will encode a JSON C<null> value. Note |
|
|
469 | that blessed objects are not included here and are handled separately by |
|
|
470 | c<allow_nonref>. |
|
|
471 | |
|
|
472 | If C<$enable> is false (the default), then C<encode> will throw an |
|
|
473 | exception when it encounters anything it cannot encode as JSON. |
|
|
474 | |
|
|
475 | This option does not affect C<decode> in any way, and it is recommended to |
|
|
476 | leave it off unless you know your communications partner. |
|
|
477 | |
|
|
478 | =item $json = $json->allow_blessed ([$enable]) |
|
|
479 | |
|
|
480 | =item $enabled = $json->get_allow_blessed |
|
|
481 | |
|
|
482 | See L<OBJECT SERIALISATION> for details. |
|
|
483 | |
|
|
484 | If C<$enable> is true (or missing), then the C<encode> method will not |
|
|
485 | barf when it encounters a blessed reference that it cannot convert |
|
|
486 | otherwise. Instead, a JSON C<null> value is encoded instead of the object. |
|
|
487 | |
|
|
488 | If C<$enable> is false (the default), then C<encode> will throw an |
|
|
489 | exception when it encounters a blessed object that it cannot convert |
|
|
490 | otherwise. |
|
|
491 | |
|
|
492 | This setting has no effect on C<decode>. |
|
|
493 | |
|
|
494 | =item $json = $json->convert_blessed ([$enable]) |
|
|
495 | |
|
|
496 | =item $enabled = $json->get_convert_blessed |
|
|
497 | |
|
|
498 | See L<OBJECT SERIALISATION> for details. |
|
|
499 | |
|
|
500 | If C<$enable> is true (or missing), then C<encode>, upon encountering a |
|
|
501 | blessed object, will check for the availability of the C<TO_JSON> method |
|
|
502 | on the object's class. If found, it will be called in scalar context and |
|
|
503 | the resulting scalar will be encoded instead of the object. |
|
|
504 | |
|
|
505 | The C<TO_JSON> method may safely call die if it wants. If C<TO_JSON> |
|
|
506 | returns other blessed objects, those will be handled in the same |
|
|
507 | way. C<TO_JSON> must take care of not causing an endless recursion cycle |
|
|
508 | (== crash) in this case. The name of C<TO_JSON> was chosen because other |
|
|
509 | methods called by the Perl core (== not by the user of the object) are |
|
|
510 | usually in upper case letters and to avoid collisions with any C<to_json> |
|
|
511 | function or method. |
|
|
512 | |
|
|
513 | If C<$enable> is false (the default), then C<encode> will not consider |
|
|
514 | this type of conversion. |
|
|
515 | |
|
|
516 | This setting has no effect on C<decode>. |
|
|
517 | |
|
|
518 | =item $json = $json->allow_tags ([$enable]) |
|
|
519 | |
|
|
520 | =item $enabled = $json->allow_tags |
|
|
521 | |
|
|
522 | See L<OBJECT SERIALISATION> for details. |
|
|
523 | |
|
|
524 | If C<$enable> is true (or missing), then C<encode>, upon encountering a |
|
|
525 | blessed object, will check for the availability of the C<FREEZE> method on |
|
|
526 | the object's class. If found, it will be used to serialise the object into |
|
|
527 | a nonstandard tagged JSON value (that JSON decoders cannot decode). |
|
|
528 | |
|
|
529 | It also causes C<decode> to parse such tagged JSON values and deserialise |
|
|
530 | them via a call to the C<THAW> method. |
|
|
531 | |
|
|
532 | If C<$enable> is false (the default), then C<encode> will not consider |
|
|
533 | this type of conversion, and tagged JSON values will cause a parse error |
|
|
534 | in C<decode>, as if tags were not part of the grammar. |
|
|
535 | |
|
|
536 | =item $json = $json->filter_json_object ([$coderef->($hashref)]) |
|
|
537 | |
|
|
538 | When C<$coderef> is specified, it will be called from C<decode> each |
|
|
539 | time it decodes a JSON object. The only argument is a reference to the |
|
|
540 | newly-created hash. If the code references returns a single scalar (which |
|
|
541 | need not be a reference), this value (i.e. a copy of that scalar to avoid |
|
|
542 | aliasing) is inserted into the deserialised data structure. If it returns |
|
|
543 | an empty list (NOTE: I<not> C<undef>, which is a valid scalar), the |
|
|
544 | original deserialised hash will be inserted. This setting can slow down |
|
|
545 | decoding considerably. |
|
|
546 | |
|
|
547 | When C<$coderef> is omitted or undefined, any existing callback will |
|
|
548 | be removed and C<decode> will not change the deserialised hash in any |
|
|
549 | way. |
|
|
550 | |
|
|
551 | Example, convert all JSON objects into the integer 5: |
|
|
552 | |
|
|
553 | my $js = JSON::XS->new->filter_json_object (sub { 5 }); |
|
|
554 | # returns [5] |
|
|
555 | $js->decode ('[{}]') |
|
|
556 | # throw an exception because allow_nonref is not enabled |
|
|
557 | # so a lone 5 is not allowed. |
|
|
558 | $js->decode ('{"a":1, "b":2}'); |
|
|
559 | |
|
|
560 | =item $json = $json->filter_json_single_key_object ($key [=> $coderef->($value)]) |
|
|
561 | |
|
|
562 | Works remotely similar to C<filter_json_object>, but is only called for |
|
|
563 | JSON objects having a single key named C<$key>. |
|
|
564 | |
|
|
565 | This C<$coderef> is called before the one specified via |
|
|
566 | C<filter_json_object>, if any. It gets passed the single value in the JSON |
|
|
567 | object. If it returns a single value, it will be inserted into the data |
|
|
568 | structure. If it returns nothing (not even C<undef> but the empty list), |
|
|
569 | the callback from C<filter_json_object> will be called next, as if no |
|
|
570 | single-key callback were specified. |
|
|
571 | |
|
|
572 | If C<$coderef> is omitted or undefined, the corresponding callback will be |
|
|
573 | disabled. There can only ever be one callback for a given key. |
|
|
574 | |
|
|
575 | As this callback gets called less often then the C<filter_json_object> |
|
|
576 | one, decoding speed will not usually suffer as much. Therefore, single-key |
|
|
577 | objects make excellent targets to serialise Perl objects into, especially |
|
|
578 | as single-key JSON objects are as close to the type-tagged value concept |
|
|
579 | as JSON gets (it's basically an ID/VALUE tuple). Of course, JSON does not |
|
|
580 | support this in any way, so you need to make sure your data never looks |
|
|
581 | like a serialised Perl hash. |
|
|
582 | |
|
|
583 | Typical names for the single object key are C<__class_whatever__>, or |
|
|
584 | C<$__dollars_are_rarely_used__$> or C<}ugly_brace_placement>, or even |
|
|
585 | things like C<__class_md5sum(classname)__>, to reduce the risk of clashing |
|
|
586 | with real hashes. |
|
|
587 | |
|
|
588 | Example, decode JSON objects of the form C<< { "__widget__" => <id> } >> |
|
|
589 | into the corresponding C<< $WIDGET{<id>} >> object: |
|
|
590 | |
|
|
591 | # return whatever is in $WIDGET{5}: |
|
|
592 | JSON::XS |
|
|
593 | ->new |
|
|
594 | ->filter_json_single_key_object (__widget__ => sub { |
|
|
595 | $WIDGET{ $_[0] } |
|
|
596 | }) |
|
|
597 | ->decode ('{"__widget__": 5') |
|
|
598 | |
|
|
599 | # this can be used with a TO_JSON method in some "widget" class |
|
|
600 | # for serialisation to json: |
|
|
601 | sub WidgetBase::TO_JSON { |
|
|
602 | my ($self) = @_; |
|
|
603 | |
|
|
604 | unless ($self->{id}) { |
|
|
605 | $self->{id} = ..get..some..id..; |
|
|
606 | $WIDGET{$self->{id}} = $self; |
|
|
607 | } |
|
|
608 | |
|
|
609 | { __widget__ => $self->{id} } |
|
|
610 | } |
|
|
611 | |
|
|
612 | =item $json = $json->shrink ([$enable]) |
|
|
613 | |
|
|
614 | =item $enabled = $json->get_shrink |
|
|
615 | |
|
|
616 | Perl usually over-allocates memory a bit when allocating space for |
|
|
617 | strings. This flag optionally resizes strings generated by either |
|
|
618 | C<encode> or C<decode> to their minimum size possible. This can save |
|
|
619 | memory when your JSON texts are either very very long or you have many |
|
|
620 | short strings. It will also try to downgrade any strings to octet-form |
|
|
621 | if possible: perl stores strings internally either in an encoding called |
|
|
622 | UTF-X or in octet-form. The latter cannot store everything but uses less |
|
|
623 | space in general (and some buggy Perl or C code might even rely on that |
|
|
624 | internal representation being used). |
|
|
625 | |
|
|
626 | The actual definition of what shrink does might change in future versions, |
|
|
627 | but it will always try to save space at the expense of time. |
|
|
628 | |
|
|
629 | If C<$enable> is true (or missing), the string returned by C<encode> will |
|
|
630 | be shrunk-to-fit, while all strings generated by C<decode> will also be |
|
|
631 | shrunk-to-fit. |
|
|
632 | |
|
|
633 | If C<$enable> is false, then the normal perl allocation algorithms are used. |
|
|
634 | If you work with your data, then this is likely to be faster. |
|
|
635 | |
|
|
636 | In the future, this setting might control other things, such as converting |
|
|
637 | strings that look like integers or floats into integers or floats |
|
|
638 | internally (there is no difference on the Perl level), saving space. |
|
|
639 | |
|
|
640 | =item $json = $json->max_depth ([$maximum_nesting_depth]) |
|
|
641 | |
|
|
642 | =item $max_depth = $json->get_max_depth |
|
|
643 | |
|
|
644 | Sets the maximum nesting level (default C<512>) accepted while encoding |
|
|
645 | or decoding. If a higher nesting level is detected in JSON text or a Perl |
|
|
646 | data structure, then the encoder and decoder will stop and croak at that |
|
|
647 | point. |
|
|
648 | |
|
|
649 | Nesting level is defined by number of hash- or arrayrefs that the encoder |
|
|
650 | needs to traverse to reach a given point or the number of C<{> or C<[> |
|
|
651 | characters without their matching closing parenthesis crossed to reach a |
|
|
652 | given character in a string. |
|
|
653 | |
|
|
654 | Setting the maximum depth to one disallows any nesting, so that ensures |
|
|
655 | that the object is only a single hash/object or array. |
|
|
656 | |
|
|
657 | If no argument is given, the highest possible setting will be used, which |
|
|
658 | is rarely useful. |
|
|
659 | |
|
|
660 | Note that nesting is implemented by recursion in C. The default value has |
|
|
661 | been chosen to be as large as typical operating systems allow without |
|
|
662 | crashing. |
|
|
663 | |
|
|
664 | See SECURITY CONSIDERATIONS, below, for more info on why this is useful. |
|
|
665 | |
|
|
666 | =item $json = $json->max_size ([$maximum_string_size]) |
|
|
667 | |
|
|
668 | =item $max_size = $json->get_max_size |
|
|
669 | |
|
|
670 | Set the maximum length a JSON text may have (in bytes) where decoding is |
|
|
671 | being attempted. The default is C<0>, meaning no limit. When C<decode> |
|
|
672 | is called on a string that is longer then this many bytes, it will not |
|
|
673 | attempt to decode the string but throw an exception. This setting has no |
|
|
674 | effect on C<encode> (yet). |
|
|
675 | |
|
|
676 | If no argument is given, the limit check will be deactivated (same as when |
|
|
677 | C<0> is specified). |
|
|
678 | |
|
|
679 | See SECURITY CONSIDERATIONS, below, for more info on why this is useful. |
|
|
680 | |
|
|
681 | =item $json_text = $json->encode ($perl_scalar) |
|
|
682 | |
|
|
683 | Converts the given Perl value or data structure to its JSON |
|
|
684 | representation. Croaks on error. |
|
|
685 | |
|
|
686 | =item $perl_scalar = $json->decode ($json_text) |
|
|
687 | |
|
|
688 | The opposite of C<encode>: expects a JSON text and tries to parse it, |
|
|
689 | returning the resulting simple scalar or reference. Croaks on error. |
|
|
690 | |
|
|
691 | =item ($perl_scalar, $characters) = $json->decode_prefix ($json_text) |
|
|
692 | |
|
|
693 | This works like the C<decode> method, but instead of raising an exception |
|
|
694 | when there is trailing garbage after the first JSON object, it will |
|
|
695 | silently stop parsing there and return the number of characters consumed |
|
|
696 | so far. |
|
|
697 | |
|
|
698 | This is useful if your JSON texts are not delimited by an outer protocol |
|
|
699 | and you need to know where the JSON text ends. |
|
|
700 | |
|
|
701 | JSON::XS->new->decode_prefix ("[1] the tail") |
|
|
702 | => ([], 3) |
|
|
703 | |
|
|
704 | =back |
|
|
705 | |
|
|
706 | |
|
|
707 | =head1 INCREMENTAL PARSING |
|
|
708 | |
|
|
709 | In some cases, there is the need for incremental parsing of JSON |
|
|
710 | texts. While this module always has to keep both JSON text and resulting |
|
|
711 | Perl data structure in memory at one time, it does allow you to parse a |
|
|
712 | JSON stream incrementally. It does so by accumulating text until it has |
|
|
713 | a full JSON object, which it then can decode. This process is similar to |
|
|
714 | using C<decode_prefix> to see if a full JSON object is available, but |
|
|
715 | is much more efficient (and can be implemented with a minimum of method |
|
|
716 | calls). |
|
|
717 | |
|
|
718 | JSON::XS will only attempt to parse the JSON text once it is sure it |
|
|
719 | has enough text to get a decisive result, using a very simple but |
|
|
720 | truly incremental parser. This means that it sometimes won't stop as |
|
|
721 | early as the full parser, for example, it doesn't detect mismatched |
|
|
722 | parentheses. The only thing it guarantees is that it starts decoding as |
|
|
723 | soon as a syntactically valid JSON text has been seen. This means you need |
|
|
724 | to set resource limits (e.g. C<max_size>) to ensure the parser will stop |
|
|
725 | parsing in the presence if syntax errors. |
|
|
726 | |
|
|
727 | The following methods implement this incremental parser. |
|
|
728 | |
|
|
729 | =over 4 |
|
|
730 | |
|
|
731 | =item [void, scalar or list context] = $json->incr_parse ([$string]) |
|
|
732 | |
|
|
733 | This is the central parsing function. It can both append new text and |
|
|
734 | extract objects from the stream accumulated so far (both of these |
|
|
735 | functions are optional). |
|
|
736 | |
|
|
737 | If C<$string> is given, then this string is appended to the already |
|
|
738 | existing JSON fragment stored in the C<$json> object. |
|
|
739 | |
|
|
740 | After that, if the function is called in void context, it will simply |
|
|
741 | return without doing anything further. This can be used to add more text |
|
|
742 | in as many chunks as you want. |
|
|
743 | |
|
|
744 | If the method is called in scalar context, then it will try to extract |
|
|
745 | exactly I<one> JSON object. If that is successful, it will return this |
|
|
746 | object, otherwise it will return C<undef>. If there is a parse error, |
|
|
747 | this method will croak just as C<decode> would do (one can then use |
|
|
748 | C<incr_skip> to skip the erroneous part). This is the most common way of |
|
|
749 | using the method. |
|
|
750 | |
|
|
751 | And finally, in list context, it will try to extract as many objects |
|
|
752 | from the stream as it can find and return them, or the empty list |
|
|
753 | otherwise. For this to work, there must be no separators between the JSON |
|
|
754 | objects or arrays, instead they must be concatenated back-to-back. If |
|
|
755 | an error occurs, an exception will be raised as in the scalar context |
|
|
756 | case. Note that in this case, any previously-parsed JSON texts will be |
|
|
757 | lost. |
|
|
758 | |
|
|
759 | Example: Parse some JSON arrays/objects in a given string and return |
|
|
760 | them. |
|
|
761 | |
|
|
762 | my @objs = JSON::XS->new->incr_parse ("[5][7][1,2]"); |
|
|
763 | |
|
|
764 | =item $lvalue_string = $json->incr_text |
|
|
765 | |
|
|
766 | This method returns the currently stored JSON fragment as an lvalue, that |
|
|
767 | is, you can manipulate it. This I<only> works when a preceding call to |
|
|
768 | C<incr_parse> in I<scalar context> successfully returned an object. Under |
|
|
769 | all other circumstances you must not call this function (I mean it. |
|
|
770 | although in simple tests it might actually work, it I<will> fail under |
|
|
771 | real world conditions). As a special exception, you can also call this |
|
|
772 | method before having parsed anything. |
|
|
773 | |
|
|
774 | This function is useful in two cases: a) finding the trailing text after a |
|
|
775 | JSON object or b) parsing multiple JSON objects separated by non-JSON text |
|
|
776 | (such as commas). |
|
|
777 | |
|
|
778 | =item $json->incr_skip |
|
|
779 | |
|
|
780 | This will reset the state of the incremental parser and will remove |
|
|
781 | the parsed text from the input buffer so far. This is useful after |
|
|
782 | C<incr_parse> died, in which case the input buffer and incremental parser |
|
|
783 | state is left unchanged, to skip the text parsed so far and to reset the |
|
|
784 | parse state. |
|
|
785 | |
|
|
786 | The difference to C<incr_reset> is that only text until the parse error |
|
|
787 | occurred is removed. |
|
|
788 | |
|
|
789 | =item $json->incr_reset |
|
|
790 | |
|
|
791 | This completely resets the incremental parser, that is, after this call, |
|
|
792 | it will be as if the parser had never parsed anything. |
|
|
793 | |
|
|
794 | This is useful if you want to repeatedly parse JSON objects and want to |
|
|
795 | ignore any trailing data, which means you have to reset the parser after |
|
|
796 | each successful decode. |
|
|
797 | |
|
|
798 | =back |
|
|
799 | |
|
|
800 | =head2 LIMITATIONS |
|
|
801 | |
|
|
802 | All options that affect decoding are supported, except |
|
|
803 | C<allow_nonref>. The reason for this is that it cannot be made to work |
|
|
804 | sensibly: JSON objects and arrays are self-delimited, i.e. you can |
|
|
805 | concatenate them back to back and still decode them perfectly. This does |
|
|
806 | not hold true for JSON numbers, however. |
|
|
807 | |
|
|
808 | For example, is the string C<1> a single JSON number, or is it simply the |
|
|
809 | start of C<12>? Or is C<12> a single JSON number, or the concatenation |
|
|
810 | of C<1> and C<2>? In neither case you can tell, and this is why JSON::XS |
|
|
811 | takes the conservative route and disallows this case. |
|
|
812 | |
|
|
813 | =head2 EXAMPLES |
|
|
814 | |
|
|
815 | Some examples will make all this clearer. First, a simple example that |
|
|
816 | works similarly to C<decode_prefix>: We want to decode the JSON object at |
|
|
817 | the start of a string and identify the portion after the JSON object: |
|
|
818 | |
|
|
819 | my $text = "[1,2,3] hello"; |
|
|
820 | |
|
|
821 | my $json = new JSON::XS; |
|
|
822 | |
|
|
823 | my $obj = $json->incr_parse ($text) |
|
|
824 | or die "expected JSON object or array at beginning of string"; |
|
|
825 | |
|
|
826 | my $tail = $json->incr_text; |
|
|
827 | # $tail now contains " hello" |
|
|
828 | |
|
|
829 | Easy, isn't it? |
|
|
830 | |
|
|
831 | Now for a more complicated example: Imagine a hypothetical protocol where |
|
|
832 | you read some requests from a TCP stream, and each request is a JSON |
|
|
833 | array, without any separation between them (in fact, it is often useful to |
|
|
834 | use newlines as "separators", as these get interpreted as whitespace at |
|
|
835 | the start of the JSON text, which makes it possible to test said protocol |
|
|
836 | with C<telnet>...). |
|
|
837 | |
|
|
838 | Here is how you'd do it (it is trivial to write this in an event-based |
|
|
839 | manner): |
|
|
840 | |
|
|
841 | my $json = new JSON::XS; |
|
|
842 | |
|
|
843 | # read some data from the socket |
|
|
844 | while (sysread $socket, my $buf, 4096) { |
|
|
845 | |
|
|
846 | # split and decode as many requests as possible |
|
|
847 | for my $request ($json->incr_parse ($buf)) { |
|
|
848 | # act on the $request |
|
|
849 | } |
|
|
850 | } |
|
|
851 | |
|
|
852 | Another complicated example: Assume you have a string with JSON objects |
|
|
853 | or arrays, all separated by (optional) comma characters (e.g. C<[1],[2], |
|
|
854 | [3]>). To parse them, we have to skip the commas between the JSON texts, |
|
|
855 | and here is where the lvalue-ness of C<incr_text> comes in useful: |
|
|
856 | |
|
|
857 | my $text = "[1],[2], [3]"; |
|
|
858 | my $json = new JSON::XS; |
|
|
859 | |
|
|
860 | # void context, so no parsing done |
|
|
861 | $json->incr_parse ($text); |
|
|
862 | |
|
|
863 | # now extract as many objects as possible. note the |
|
|
864 | # use of scalar context so incr_text can be called. |
|
|
865 | while (my $obj = $json->incr_parse) { |
|
|
866 | # do something with $obj |
|
|
867 | |
|
|
868 | # now skip the optional comma |
|
|
869 | $json->incr_text =~ s/^ \s* , //x; |
|
|
870 | } |
|
|
871 | |
|
|
872 | Now lets go for a very complex example: Assume that you have a gigantic |
|
|
873 | JSON array-of-objects, many gigabytes in size, and you want to parse it, |
|
|
874 | but you cannot load it into memory fully (this has actually happened in |
|
|
875 | the real world :). |
|
|
876 | |
|
|
877 | Well, you lost, you have to implement your own JSON parser. But JSON::XS |
|
|
878 | can still help you: You implement a (very simple) array parser and let |
|
|
879 | JSON decode the array elements, which are all full JSON objects on their |
|
|
880 | own (this wouldn't work if the array elements could be JSON numbers, for |
|
|
881 | example): |
|
|
882 | |
|
|
883 | my $json = new JSON::XS; |
|
|
884 | |
|
|
885 | # open the monster |
|
|
886 | open my $fh, "<bigfile.json" |
|
|
887 | or die "bigfile: $!"; |
|
|
888 | |
|
|
889 | # first parse the initial "[" |
|
|
890 | for (;;) { |
|
|
891 | sysread $fh, my $buf, 65536 |
|
|
892 | or die "read error: $!"; |
|
|
893 | $json->incr_parse ($buf); # void context, so no parsing |
|
|
894 | |
|
|
895 | # Exit the loop once we found and removed(!) the initial "[". |
|
|
896 | # In essence, we are (ab-)using the $json object as a simple scalar |
|
|
897 | # we append data to. |
|
|
898 | last if $json->incr_text =~ s/^ \s* \[ //x; |
|
|
899 | } |
|
|
900 | |
|
|
901 | # now we have the skipped the initial "[", so continue |
|
|
902 | # parsing all the elements. |
|
|
903 | for (;;) { |
|
|
904 | # in this loop we read data until we got a single JSON object |
|
|
905 | for (;;) { |
|
|
906 | if (my $obj = $json->incr_parse) { |
|
|
907 | # do something with $obj |
|
|
908 | last; |
|
|
909 | } |
|
|
910 | |
|
|
911 | # add more data |
|
|
912 | sysread $fh, my $buf, 65536 |
|
|
913 | or die "read error: $!"; |
|
|
914 | $json->incr_parse ($buf); # void context, so no parsing |
|
|
915 | } |
|
|
916 | |
|
|
917 | # in this loop we read data until we either found and parsed the |
|
|
918 | # separating "," between elements, or the final "]" |
|
|
919 | for (;;) { |
|
|
920 | # first skip whitespace |
|
|
921 | $json->incr_text =~ s/^\s*//; |
|
|
922 | |
|
|
923 | # if we find "]", we are done |
|
|
924 | if ($json->incr_text =~ s/^\]//) { |
|
|
925 | print "finished.\n"; |
|
|
926 | exit; |
|
|
927 | } |
|
|
928 | |
|
|
929 | # if we find ",", we can continue with the next element |
|
|
930 | if ($json->incr_text =~ s/^,//) { |
|
|
931 | last; |
|
|
932 | } |
|
|
933 | |
|
|
934 | # if we find anything else, we have a parse error! |
|
|
935 | if (length $json->incr_text) { |
|
|
936 | die "parse error near ", $json->incr_text; |
|
|
937 | } |
|
|
938 | |
|
|
939 | # else add more data |
|
|
940 | sysread $fh, my $buf, 65536 |
|
|
941 | or die "read error: $!"; |
|
|
942 | $json->incr_parse ($buf); # void context, so no parsing |
|
|
943 | } |
|
|
944 | |
|
|
945 | This is a complex example, but most of the complexity comes from the fact |
|
|
946 | that we are trying to be correct (bear with me if I am wrong, I never ran |
|
|
947 | the above example :). |
|
|
948 | |
|
|
949 | |
|
|
950 | |
|
|
951 | =head1 MAPPING |
|
|
952 | |
|
|
953 | This section describes how JSON::XS maps Perl values to JSON values and |
|
|
954 | vice versa. These mappings are designed to "do the right thing" in most |
|
|
955 | circumstances automatically, preserving round-tripping characteristics |
|
|
956 | (what you put in comes out as something equivalent). |
|
|
957 | |
|
|
958 | For the more enlightened: note that in the following descriptions, |
|
|
959 | lowercase I<perl> refers to the Perl interpreter, while uppercase I<Perl> |
|
|
960 | refers to the abstract Perl language itself. |
|
|
961 | |
|
|
962 | |
|
|
963 | =head2 JSON -> PERL |
|
|
964 | |
|
|
965 | =over 4 |
|
|
966 | |
|
|
967 | =item object |
|
|
968 | |
|
|
969 | A JSON object becomes a reference to a hash in Perl. No ordering of object |
|
|
970 | keys is preserved (JSON does not preserve object key ordering itself). |
|
|
971 | |
|
|
972 | =item array |
|
|
973 | |
|
|
974 | A JSON array becomes a reference to an array in Perl. |
|
|
975 | |
|
|
976 | =item string |
|
|
977 | |
|
|
978 | A JSON string becomes a string scalar in Perl - Unicode codepoints in JSON |
|
|
979 | are represented by the same codepoints in the Perl string, so no manual |
|
|
980 | decoding is necessary. |
|
|
981 | |
|
|
982 | =item number |
|
|
983 | |
|
|
984 | A JSON number becomes either an integer, numeric (floating point) or |
|
|
985 | string scalar in perl, depending on its range and any fractional parts. On |
|
|
986 | the Perl level, there is no difference between those as Perl handles all |
|
|
987 | the conversion details, but an integer may take slightly less memory and |
|
|
988 | might represent more values exactly than floating point numbers. |
|
|
989 | |
|
|
990 | If the number consists of digits only, JSON::XS will try to represent |
|
|
991 | it as an integer value. If that fails, it will try to represent it as |
|
|
992 | a numeric (floating point) value if that is possible without loss of |
|
|
993 | precision. Otherwise it will preserve the number as a string value (in |
|
|
994 | which case you lose roundtripping ability, as the JSON number will be |
|
|
995 | re-encoded to a JSON string). |
|
|
996 | |
|
|
997 | Numbers containing a fractional or exponential part will always be |
|
|
998 | represented as numeric (floating point) values, possibly at a loss of |
|
|
999 | precision (in which case you might lose perfect roundtripping ability, but |
|
|
1000 | the JSON number will still be re-encoded as a JSON number). |
|
|
1001 | |
|
|
1002 | Note that precision is not accuracy - binary floating point values cannot |
|
|
1003 | represent most decimal fractions exactly, and when converting from and to |
|
|
1004 | floating point, JSON::XS only guarantees precision up to but not including |
|
|
1005 | the least significant bit. |
|
|
1006 | |
|
|
1007 | =item true, false |
|
|
1008 | |
|
|
1009 | These JSON atoms become C<Types::Serialiser::true> and |
|
|
1010 | C<Types::Serialiser::false>, respectively. They are overloaded to act |
|
|
1011 | almost exactly like the numbers C<1> and C<0>. You can check whether |
|
|
1012 | a scalar is a JSON boolean by using the C<Types::Serialiser::is_bool> |
|
|
1013 | function (after C<use Types::Serialier>, of course). |
|
|
1014 | |
|
|
1015 | =item null |
|
|
1016 | |
|
|
1017 | A JSON null atom becomes C<undef> in Perl. |
|
|
1018 | |
|
|
1019 | =item shell-style comments (C<< # I<text> >>) |
|
|
1020 | |
|
|
1021 | As a nonstandard extension to the JSON syntax that is enabled by the |
|
|
1022 | C<relaxed> setting, shell-style comments are allowed. They can start |
|
|
1023 | anywhere outside strings and go till the end of the line. |
|
|
1024 | |
|
|
1025 | =item tagged values (C<< (I<tag>)I<value> >>). |
|
|
1026 | |
|
|
1027 | Another nonstandard extension to the JSON syntax, enabled with the |
|
|
1028 | C<allow_tags> setting, are tagged values. In this implementation, the |
|
|
1029 | I<tag> must be a perl package/class name encoded as a JSON string, and the |
|
|
1030 | I<value> must be a JSON array encoding optional constructor arguments. |
|
|
1031 | |
|
|
1032 | See L<OBJECT SERIALISATION>, below, for details. |
|
|
1033 | |
|
|
1034 | =back |
|
|
1035 | |
|
|
1036 | |
|
|
1037 | =head2 PERL -> JSON |
|
|
1038 | |
|
|
1039 | The mapping from Perl to JSON is slightly more difficult, as Perl is a |
|
|
1040 | truly typeless language, so we can only guess which JSON type is meant by |
|
|
1041 | a Perl value. |
|
|
1042 | |
|
|
1043 | =over 4 |
|
|
1044 | |
|
|
1045 | =item hash references |
|
|
1046 | |
|
|
1047 | Perl hash references become JSON objects. As there is no inherent |
|
|
1048 | ordering in hash keys (or JSON objects), they will usually be encoded |
|
|
1049 | in a pseudo-random order. JSON::XS can optionally sort the hash keys |
|
|
1050 | (determined by the I<canonical> flag), so the same datastructure will |
|
|
1051 | serialise to the same JSON text (given same settings and version of |
|
|
1052 | JSON::XS), but this incurs a runtime overhead and is only rarely useful, |
|
|
1053 | e.g. when you want to compare some JSON text against another for equality. |
|
|
1054 | |
|
|
1055 | =item array references |
|
|
1056 | |
|
|
1057 | Perl array references become JSON arrays. |
|
|
1058 | |
|
|
1059 | =item other references |
|
|
1060 | |
|
|
1061 | Other unblessed references are generally not allowed and will cause an |
|
|
1062 | exception to be thrown, except for references to the integers C<0> and |
|
|
1063 | C<1>, which get turned into C<false> and C<true> atoms in JSON. |
|
|
1064 | |
|
|
1065 | Since C<JSON::XS> uses the boolean model from L<Types::Serialiser>, you |
|
|
1066 | can also C<use Types::Serialiser> and then use C<Types::Serialiser::false> |
|
|
1067 | and C<Types::Serialiser::true> to improve readability. |
|
|
1068 | |
|
|
1069 | use Types::Serialiser; |
|
|
1070 | encode_json [\0, Types::Serialiser::true] # yields [false,true] |
|
|
1071 | |
|
|
1072 | =item Types::Serialiser::true, Types::Serialiser::false |
|
|
1073 | |
|
|
1074 | These special values from the L<Types::Serialiser> module become JSON true |
|
|
1075 | and JSON false values, respectively. You can also use C<\1> and C<\0> |
|
|
1076 | directly if you want. |
|
|
1077 | |
|
|
1078 | =item blessed objects |
|
|
1079 | |
|
|
1080 | Blessed objects are not directly representable in JSON, but C<JSON::XS> |
|
|
1081 | allows various ways of handling objects. See L<OBJECT SERIALISATION>, |
|
|
1082 | below, for details. |
|
|
1083 | |
|
|
1084 | =item simple scalars |
|
|
1085 | |
|
|
1086 | Simple Perl scalars (any scalar that is not a reference) are the most |
|
|
1087 | difficult objects to encode: JSON::XS will encode undefined scalars as |
|
|
1088 | JSON C<null> values, scalars that have last been used in a string context |
|
|
1089 | before encoding as JSON strings, and anything else as number value: |
|
|
1090 | |
|
|
1091 | # dump as number |
|
|
1092 | encode_json [2] # yields [2] |
|
|
1093 | encode_json [-3.0e17] # yields [-3e+17] |
|
|
1094 | my $value = 5; encode_json [$value] # yields [5] |
|
|
1095 | |
|
|
1096 | # used as string, so dump as string |
|
|
1097 | print $value; |
|
|
1098 | encode_json [$value] # yields ["5"] |
|
|
1099 | |
|
|
1100 | # undef becomes null |
|
|
1101 | encode_json [undef] # yields [null] |
|
|
1102 | |
|
|
1103 | You can force the type to be a JSON string by stringifying it: |
|
|
1104 | |
|
|
1105 | my $x = 3.1; # some variable containing a number |
|
|
1106 | "$x"; # stringified |
|
|
1107 | $x .= ""; # another, more awkward way to stringify |
|
|
1108 | print $x; # perl does it for you, too, quite often |
|
|
1109 | |
|
|
1110 | You can force the type to be a JSON number by numifying it: |
|
|
1111 | |
|
|
1112 | my $x = "3"; # some variable containing a string |
|
|
1113 | $x += 0; # numify it, ensuring it will be dumped as a number |
|
|
1114 | $x *= 1; # same thing, the choice is yours. |
|
|
1115 | |
|
|
1116 | You can not currently force the type in other, less obscure, ways. Tell me |
|
|
1117 | if you need this capability (but don't forget to explain why it's needed |
|
|
1118 | :). |
|
|
1119 | |
|
|
1120 | Note that numerical precision has the same meaning as under Perl (so |
|
|
1121 | binary to decimal conversion follows the same rules as in Perl, which |
|
|
1122 | can differ to other languages). Also, your perl interpreter might expose |
|
|
1123 | extensions to the floating point numbers of your platform, such as |
|
|
1124 | infinities or NaN's - these cannot be represented in JSON, and it is an |
|
|
1125 | error to pass those in. |
|
|
1126 | |
|
|
1127 | =back |
|
|
1128 | |
|
|
1129 | =head2 OBJECT SERIALISATION |
|
|
1130 | |
|
|
1131 | As JSON cannot directly represent Perl objects, you have to choose between |
|
|
1132 | a pure JSON representation (without the ability to deserialise the object |
|
|
1133 | automatically again), and a nonstandard extension to the JSON syntax, |
|
|
1134 | tagged values. |
|
|
1135 | |
|
|
1136 | =head3 SERIALISATION |
|
|
1137 | |
|
|
1138 | What happens when C<JSON::XS> encounters a Perl object depends on the |
|
|
1139 | C<allow_blessed>, C<convert_blessed> and C<allow_tags> settings, which are |
|
|
1140 | used in this order: |
|
|
1141 | |
|
|
1142 | =over 4 |
|
|
1143 | |
|
|
1144 | =item 1. C<allow_tags> is enabled and the object has a C<FREEZE> method. |
|
|
1145 | |
|
|
1146 | In this case, C<JSON::XS> uses the L<Types::Serialiser> object |
|
|
1147 | serialisation protocol to create a tagged JSON value, using a nonstandard |
|
|
1148 | extension to the JSON syntax. |
|
|
1149 | |
|
|
1150 | This works by invoking the C<FREEZE> method on the object, with the first |
|
|
1151 | argument being the object to serialise, and the second argument being the |
|
|
1152 | constant string C<JSON> to distinguish it from other serialisers. |
|
|
1153 | |
|
|
1154 | The C<FREEZE> method can return any number of values (i.e. zero or |
|
|
1155 | more). These values and the paclkage/classname of the object will then be |
|
|
1156 | encoded as a tagged JSON value in the following format: |
|
|
1157 | |
|
|
1158 | ("classname")[FREEZE return values...] |
|
|
1159 | |
|
|
1160 | e.g.: |
|
|
1161 | |
|
|
1162 | ("URI")["http://www.google.com/"] |
|
|
1163 | ("MyDate")[2013,10,29] |
|
|
1164 | ("ImageData::JPEG")["Z3...VlCg=="] |
|
|
1165 | |
|
|
1166 | For example, the hypothetical C<My::Object> C<FREEZE> method might use the |
|
|
1167 | objects C<type> and C<id> members to encode the object: |
|
|
1168 | |
|
|
1169 | sub My::Object::FREEZE { |
|
|
1170 | my ($self, $serialiser) = @_; |
|
|
1171 | |
|
|
1172 | ($self->{type}, $self->{id}) |
|
|
1173 | } |
|
|
1174 | |
|
|
1175 | =item 2. C<convert_blessed> is enabled and the object has a C<TO_JSON> method. |
|
|
1176 | |
|
|
1177 | In this case, the C<TO_JSON> method of the object is invoked in scalar |
|
|
1178 | context. It must return a single scalar that can be directly encoded into |
|
|
1179 | JSON. This scalar replaces the object in the JSON text. |
|
|
1180 | |
|
|
1181 | For example, the following C<TO_JSON> method will convert all L<URI> |
|
|
1182 | objects to JSON strings when serialised. The fatc that these values |
|
|
1183 | originally were L<URI> objects is lost. |
|
|
1184 | |
|
|
1185 | sub URI::TO_JSON { |
|
|
1186 | my ($uri) = @_; |
|
|
1187 | $uri->as_string |
|
|
1188 | } |
|
|
1189 | |
|
|
1190 | =item 3. C<allow_blessed> is enabled. |
|
|
1191 | |
|
|
1192 | The object will be serialised as a JSON null value. |
|
|
1193 | |
|
|
1194 | =item 4. none of the above |
|
|
1195 | |
|
|
1196 | If none of the settings are enabled or the respective methods are missing, |
|
|
1197 | C<JSON::XS> throws an exception. |
|
|
1198 | |
|
|
1199 | =back |
|
|
1200 | |
|
|
1201 | =head3 DESERIALISATION |
|
|
1202 | |
|
|
1203 | For deserialisation there are only two cases to consider: either |
|
|
1204 | nonstandard tagging was used, in which case C<allow_tags> decides, |
|
|
1205 | or objects cannot be automatically be deserialised, in which |
|
|
1206 | case you can use postprocessing or the C<filter_json_object> or |
|
|
1207 | C<filter_json_single_key_object> callbacks to get some real objects our of |
|
|
1208 | your JSON. |
|
|
1209 | |
|
|
1210 | This section only considers the tagged value case: I a tagged JSON object |
|
|
1211 | is encountered during decoding and C<allow_tags> is disabled, a parse |
|
|
1212 | error will result (as if tagged values were not part of the grammar). |
|
|
1213 | |
|
|
1214 | If C<allow_tags> is enabled, C<JSON::XS> will look up the C<THAW> method |
|
|
1215 | of the package/classname used during serialisation (it will not attempt |
|
|
1216 | to load the package as a Perl module). If there is no such method, the |
|
|
1217 | decoding will fail with an error. |
|
|
1218 | |
|
|
1219 | Otherwise, the C<THAW> method is invoked with the classname as first |
|
|
1220 | argument, the constant string C<JSON> as second argument, and all the |
|
|
1221 | values from the JSON array (the values originally returned by the |
|
|
1222 | C<FREEZE> method) as remaining arguments. |
|
|
1223 | |
|
|
1224 | The method must then return the object. While technically you can return |
|
|
1225 | any Perl scalar, you might have to enable the C<enable_nonref> setting to |
|
|
1226 | make that work in all cases, so better return an actual blessed reference. |
|
|
1227 | |
|
|
1228 | As an example, let's implement a C<THAW> function that regenerates the |
|
|
1229 | C<My::Object> from the C<FREEZE> example earlier: |
|
|
1230 | |
|
|
1231 | sub My::Object::THAW { |
|
|
1232 | my ($class, $serialiser, $type, $id) = @_; |
|
|
1233 | |
|
|
1234 | $class->new (type => $type, id => $id) |
|
|
1235 | } |
|
|
1236 | |
|
|
1237 | |
|
|
1238 | =head1 ENCODING/CODESET FLAG NOTES |
|
|
1239 | |
|
|
1240 | The interested reader might have seen a number of flags that signify |
|
|
1241 | encodings or codesets - C<utf8>, C<latin1> and C<ascii>. There seems to be |
|
|
1242 | some confusion on what these do, so here is a short comparison: |
|
|
1243 | |
|
|
1244 | C<utf8> controls whether the JSON text created by C<encode> (and expected |
|
|
1245 | by C<decode>) is UTF-8 encoded or not, while C<latin1> and C<ascii> only |
|
|
1246 | control whether C<encode> escapes character values outside their respective |
|
|
1247 | codeset range. Neither of these flags conflict with each other, although |
|
|
1248 | some combinations make less sense than others. |
|
|
1249 | |
|
|
1250 | Care has been taken to make all flags symmetrical with respect to |
|
|
1251 | C<encode> and C<decode>, that is, texts encoded with any combination of |
|
|
1252 | these flag values will be correctly decoded when the same flags are used |
|
|
1253 | - in general, if you use different flag settings while encoding vs. when |
|
|
1254 | decoding you likely have a bug somewhere. |
|
|
1255 | |
|
|
1256 | Below comes a verbose discussion of these flags. Note that a "codeset" is |
|
|
1257 | simply an abstract set of character-codepoint pairs, while an encoding |
|
|
1258 | takes those codepoint numbers and I<encodes> them, in our case into |
|
|
1259 | octets. Unicode is (among other things) a codeset, UTF-8 is an encoding, |
|
|
1260 | and ISO-8859-1 (= latin 1) and ASCII are both codesets I<and> encodings at |
|
|
1261 | the same time, which can be confusing. |
|
|
1262 | |
|
|
1263 | =over 4 |
|
|
1264 | |
|
|
1265 | =item C<utf8> flag disabled |
|
|
1266 | |
|
|
1267 | When C<utf8> is disabled (the default), then C<encode>/C<decode> generate |
|
|
1268 | and expect Unicode strings, that is, characters with high ordinal Unicode |
|
|
1269 | values (> 255) will be encoded as such characters, and likewise such |
|
|
1270 | characters are decoded as-is, no changes to them will be done, except |
|
|
1271 | "(re-)interpreting" them as Unicode codepoints or Unicode characters, |
|
|
1272 | respectively (to Perl, these are the same thing in strings unless you do |
|
|
1273 | funny/weird/dumb stuff). |
|
|
1274 | |
|
|
1275 | This is useful when you want to do the encoding yourself (e.g. when you |
|
|
1276 | want to have UTF-16 encoded JSON texts) or when some other layer does |
|
|
1277 | the encoding for you (for example, when printing to a terminal using a |
|
|
1278 | filehandle that transparently encodes to UTF-8 you certainly do NOT want |
|
|
1279 | to UTF-8 encode your data first and have Perl encode it another time). |
|
|
1280 | |
|
|
1281 | =item C<utf8> flag enabled |
|
|
1282 | |
|
|
1283 | If the C<utf8>-flag is enabled, C<encode>/C<decode> will encode all |
|
|
1284 | characters using the corresponding UTF-8 multi-byte sequence, and will |
|
|
1285 | expect your input strings to be encoded as UTF-8, that is, no "character" |
|
|
1286 | of the input string must have any value > 255, as UTF-8 does not allow |
|
|
1287 | that. |
|
|
1288 | |
|
|
1289 | The C<utf8> flag therefore switches between two modes: disabled means you |
|
|
1290 | will get a Unicode string in Perl, enabled means you get an UTF-8 encoded |
|
|
1291 | octet/binary string in Perl. |
|
|
1292 | |
|
|
1293 | =item C<latin1> or C<ascii> flags enabled |
|
|
1294 | |
|
|
1295 | With C<latin1> (or C<ascii>) enabled, C<encode> will escape characters |
|
|
1296 | with ordinal values > 255 (> 127 with C<ascii>) and encode the remaining |
|
|
1297 | characters as specified by the C<utf8> flag. |
|
|
1298 | |
|
|
1299 | If C<utf8> is disabled, then the result is also correctly encoded in those |
|
|
1300 | character sets (as both are proper subsets of Unicode, meaning that a |
|
|
1301 | Unicode string with all character values < 256 is the same thing as a |
|
|
1302 | ISO-8859-1 string, and a Unicode string with all character values < 128 is |
|
|
1303 | the same thing as an ASCII string in Perl). |
|
|
1304 | |
|
|
1305 | If C<utf8> is enabled, you still get a correct UTF-8-encoded string, |
|
|
1306 | regardless of these flags, just some more characters will be escaped using |
|
|
1307 | C<\uXXXX> then before. |
|
|
1308 | |
|
|
1309 | Note that ISO-8859-1-I<encoded> strings are not compatible with UTF-8 |
|
|
1310 | encoding, while ASCII-encoded strings are. That is because the ISO-8859-1 |
|
|
1311 | encoding is NOT a subset of UTF-8 (despite the ISO-8859-1 I<codeset> being |
|
|
1312 | a subset of Unicode), while ASCII is. |
|
|
1313 | |
|
|
1314 | Surprisingly, C<decode> will ignore these flags and so treat all input |
|
|
1315 | values as governed by the C<utf8> flag. If it is disabled, this allows you |
|
|
1316 | to decode ISO-8859-1- and ASCII-encoded strings, as both strict subsets of |
|
|
1317 | Unicode. If it is enabled, you can correctly decode UTF-8 encoded strings. |
|
|
1318 | |
|
|
1319 | So neither C<latin1> nor C<ascii> are incompatible with the C<utf8> flag - |
|
|
1320 | they only govern when the JSON output engine escapes a character or not. |
|
|
1321 | |
|
|
1322 | The main use for C<latin1> is to relatively efficiently store binary data |
|
|
1323 | as JSON, at the expense of breaking compatibility with most JSON decoders. |
|
|
1324 | |
|
|
1325 | The main use for C<ascii> is to force the output to not contain characters |
|
|
1326 | with values > 127, which means you can interpret the resulting string |
|
|
1327 | as UTF-8, ISO-8859-1, ASCII, KOI8-R or most about any character set and |
|
|
1328 | 8-bit-encoding, and still get the same data structure back. This is useful |
|
|
1329 | when your channel for JSON transfer is not 8-bit clean or the encoding |
|
|
1330 | might be mangled in between (e.g. in mail), and works because ASCII is a |
|
|
1331 | proper subset of most 8-bit and multibyte encodings in use in the world. |
|
|
1332 | |
|
|
1333 | =back |
|
|
1334 | |
|
|
1335 | |
|
|
1336 | =head2 JSON and ECMAscript |
|
|
1337 | |
|
|
1338 | JSON syntax is based on how literals are represented in javascript (the |
|
|
1339 | not-standardised predecessor of ECMAscript) which is presumably why it is |
|
|
1340 | called "JavaScript Object Notation". |
|
|
1341 | |
|
|
1342 | However, JSON is not a subset (and also not a superset of course) of |
|
|
1343 | ECMAscript (the standard) or javascript (whatever browsers actually |
|
|
1344 | implement). |
|
|
1345 | |
|
|
1346 | If you want to use javascript's C<eval> function to "parse" JSON, you |
|
|
1347 | might run into parse errors for valid JSON texts, or the resulting data |
|
|
1348 | structure might not be queryable: |
|
|
1349 | |
|
|
1350 | One of the problems is that U+2028 and U+2029 are valid characters inside |
|
|
1351 | JSON strings, but are not allowed in ECMAscript string literals, so the |
|
|
1352 | following Perl fragment will not output something that can be guaranteed |
|
|
1353 | to be parsable by javascript's C<eval>: |
|
|
1354 | |
|
|
1355 | use JSON::XS; |
|
|
1356 | |
|
|
1357 | print encode_json [chr 0x2028]; |
|
|
1358 | |
|
|
1359 | The right fix for this is to use a proper JSON parser in your javascript |
|
|
1360 | programs, and not rely on C<eval> (see for example Douglas Crockford's |
|
|
1361 | F<json2.js> parser). |
|
|
1362 | |
|
|
1363 | If this is not an option, you can, as a stop-gap measure, simply encode to |
|
|
1364 | ASCII-only JSON: |
|
|
1365 | |
|
|
1366 | use JSON::XS; |
|
|
1367 | |
|
|
1368 | print JSON::XS->new->ascii->encode ([chr 0x2028]); |
|
|
1369 | |
|
|
1370 | Note that this will enlarge the resulting JSON text quite a bit if you |
|
|
1371 | have many non-ASCII characters. You might be tempted to run some regexes |
|
|
1372 | to only escape U+2028 and U+2029, e.g.: |
|
|
1373 | |
|
|
1374 | # DO NOT USE THIS! |
|
|
1375 | my $json = JSON::XS->new->utf8->encode ([chr 0x2028]); |
|
|
1376 | $json =~ s/\xe2\x80\xa8/\\u2028/g; # escape U+2028 |
|
|
1377 | $json =~ s/\xe2\x80\xa9/\\u2029/g; # escape U+2029 |
|
|
1378 | print $json; |
|
|
1379 | |
|
|
1380 | Note that I<this is a bad idea>: the above only works for U+2028 and |
|
|
1381 | U+2029 and thus only for fully ECMAscript-compliant parsers. Many existing |
|
|
1382 | javascript implementations, however, have issues with other characters as |
|
|
1383 | well - using C<eval> naively simply I<will> cause problems. |
|
|
1384 | |
|
|
1385 | Another problem is that some javascript implementations reserve |
|
|
1386 | some property names for their own purposes (which probably makes |
|
|
1387 | them non-ECMAscript-compliant). For example, Iceweasel reserves the |
|
|
1388 | C<__proto__> property name for its own purposes. |
|
|
1389 | |
|
|
1390 | If that is a problem, you could parse try to filter the resulting JSON |
|
|
1391 | output for these property strings, e.g.: |
|
|
1392 | |
|
|
1393 | $json =~ s/"__proto__"\s*:/"__proto__renamed":/g; |
|
|
1394 | |
|
|
1395 | This works because C<__proto__> is not valid outside of strings, so every |
|
|
1396 | occurrence of C<"__proto__"\s*:> must be a string used as property name. |
|
|
1397 | |
|
|
1398 | If you know of other incompatibilities, please let me know. |
|
|
1399 | |
|
|
1400 | |
|
|
1401 | =head2 JSON and YAML |
|
|
1402 | |
|
|
1403 | You often hear that JSON is a subset of YAML. This is, however, a mass |
|
|
1404 | hysteria(*) and very far from the truth (as of the time of this writing), |
|
|
1405 | so let me state it clearly: I<in general, there is no way to configure |
|
|
1406 | JSON::XS to output a data structure as valid YAML> that works in all |
|
|
1407 | cases. |
|
|
1408 | |
|
|
1409 | If you really must use JSON::XS to generate YAML, you should use this |
|
|
1410 | algorithm (subject to change in future versions): |
|
|
1411 | |
|
|
1412 | my $to_yaml = JSON::XS->new->utf8->space_after (1); |
|
|
1413 | my $yaml = $to_yaml->encode ($ref) . "\n"; |
|
|
1414 | |
|
|
1415 | This will I<usually> generate JSON texts that also parse as valid |
|
|
1416 | YAML. Please note that YAML has hardcoded limits on (simple) object key |
|
|
1417 | lengths that JSON doesn't have and also has different and incompatible |
|
|
1418 | unicode character escape syntax, so you should make sure that your hash |
|
|
1419 | keys are noticeably shorter than the 1024 "stream characters" YAML allows |
|
|
1420 | and that you do not have characters with codepoint values outside the |
|
|
1421 | Unicode BMP (basic multilingual page). YAML also does not allow C<\/> |
|
|
1422 | sequences in strings (which JSON::XS does not I<currently> generate, but |
|
|
1423 | other JSON generators might). |
|
|
1424 | |
|
|
1425 | There might be other incompatibilities that I am not aware of (or the YAML |
|
|
1426 | specification has been changed yet again - it does so quite often). In |
|
|
1427 | general you should not try to generate YAML with a JSON generator or vice |
|
|
1428 | versa, or try to parse JSON with a YAML parser or vice versa: chances are |
|
|
1429 | high that you will run into severe interoperability problems when you |
|
|
1430 | least expect it. |
|
|
1431 | |
|
|
1432 | =over 4 |
|
|
1433 | |
|
|
1434 | =item (*) |
|
|
1435 | |
|
|
1436 | I have been pressured multiple times by Brian Ingerson (one of the |
|
|
1437 | authors of the YAML specification) to remove this paragraph, despite him |
|
|
1438 | acknowledging that the actual incompatibilities exist. As I was personally |
|
|
1439 | bitten by this "JSON is YAML" lie, I refused and said I will continue to |
|
|
1440 | educate people about these issues, so others do not run into the same |
|
|
1441 | problem again and again. After this, Brian called me a (quote)I<complete |
|
|
1442 | and worthless idiot>(unquote). |
|
|
1443 | |
|
|
1444 | In my opinion, instead of pressuring and insulting people who actually |
|
|
1445 | clarify issues with YAML and the wrong statements of some of its |
|
|
1446 | proponents, I would kindly suggest reading the JSON spec (which is not |
|
|
1447 | that difficult or long) and finally make YAML compatible to it, and |
|
|
1448 | educating users about the changes, instead of spreading lies about the |
|
|
1449 | real compatibility for many I<years> and trying to silence people who |
|
|
1450 | point out that it isn't true. |
|
|
1451 | |
|
|
1452 | Addendum/2009: the YAML 1.2 spec is still incompatible with JSON, even |
|
|
1453 | though the incompatibilities have been documented (and are known to Brian) |
|
|
1454 | for many years and the spec makes explicit claims that YAML is a superset |
|
|
1455 | of JSON. It would be so easy to fix, but apparently, bullying people and |
|
|
1456 | corrupting userdata is so much easier. |
|
|
1457 | |
|
|
1458 | =back |
|
|
1459 | |
|
|
1460 | |
|
|
1461 | =head2 SPEED |
|
|
1462 | |
|
|
1463 | It seems that JSON::XS is surprisingly fast, as shown in the following |
|
|
1464 | tables. They have been generated with the help of the C<eg/bench> program |
|
|
1465 | in the JSON::XS distribution, to make it easy to compare on your own |
|
|
1466 | system. |
|
|
1467 | |
|
|
1468 | First comes a comparison between various modules using |
|
|
1469 | a very short single-line JSON string (also available at |
|
|
1470 | L<http://dist.schmorp.de/misc/json/short.json>). |
|
|
1471 | |
|
|
1472 | {"method": "handleMessage", "params": ["user1", |
|
|
1473 | "we were just talking"], "id": null, "array":[1,11,234,-5,1e5,1e7, |
|
|
1474 | 1, 0]} |
|
|
1475 | |
|
|
1476 | It shows the number of encodes/decodes per second (JSON::XS uses |
|
|
1477 | the functional interface, while JSON::XS/2 uses the OO interface |
|
|
1478 | with pretty-printing and hashkey sorting enabled, JSON::XS/3 enables |
|
|
1479 | shrink. JSON::DWIW/DS uses the deserialise function, while JSON::DWIW::FJ |
|
|
1480 | uses the from_json method). Higher is better: |
|
|
1481 | |
|
|
1482 | module | encode | decode | |
|
|
1483 | --------------|------------|------------| |
|
|
1484 | JSON::DWIW/DS | 86302.551 | 102300.098 | |
|
|
1485 | JSON::DWIW/FJ | 86302.551 | 75983.768 | |
|
|
1486 | JSON::PP | 15827.562 | 6638.658 | |
|
|
1487 | JSON::Syck | 63358.066 | 47662.545 | |
|
|
1488 | JSON::XS | 511500.488 | 511500.488 | |
|
|
1489 | JSON::XS/2 | 291271.111 | 388361.481 | |
|
|
1490 | JSON::XS/3 | 361577.931 | 361577.931 | |
|
|
1491 | Storable | 66788.280 | 265462.278 | |
|
|
1492 | --------------+------------+------------+ |
|
|
1493 | |
|
|
1494 | That is, JSON::XS is almost six times faster than JSON::DWIW on encoding, |
|
|
1495 | about five times faster on decoding, and over thirty to seventy times |
|
|
1496 | faster than JSON's pure perl implementation. It also compares favourably |
|
|
1497 | to Storable for small amounts of data. |
|
|
1498 | |
|
|
1499 | Using a longer test string (roughly 18KB, generated from Yahoo! Locals |
|
|
1500 | search API (L<http://dist.schmorp.de/misc/json/long.json>). |
|
|
1501 | |
|
|
1502 | module | encode | decode | |
|
|
1503 | --------------|------------|------------| |
|
|
1504 | JSON::DWIW/DS | 1647.927 | 2673.916 | |
|
|
1505 | JSON::DWIW/FJ | 1630.249 | 2596.128 | |
|
|
1506 | JSON::PP | 400.640 | 62.311 | |
|
|
1507 | JSON::Syck | 1481.040 | 1524.869 | |
|
|
1508 | JSON::XS | 20661.596 | 9541.183 | |
|
|
1509 | JSON::XS/2 | 10683.403 | 9416.938 | |
|
|
1510 | JSON::XS/3 | 20661.596 | 9400.054 | |
|
|
1511 | Storable | 19765.806 | 10000.725 | |
|
|
1512 | --------------+------------+------------+ |
|
|
1513 | |
|
|
1514 | Again, JSON::XS leads by far (except for Storable which non-surprisingly |
|
|
1515 | decodes a bit faster). |
|
|
1516 | |
|
|
1517 | On large strings containing lots of high Unicode characters, some modules |
|
|
1518 | (such as JSON::PC) seem to decode faster than JSON::XS, but the result |
|
|
1519 | will be broken due to missing (or wrong) Unicode handling. Others refuse |
|
|
1520 | to decode or encode properly, so it was impossible to prepare a fair |
|
|
1521 | comparison table for that case. |
|
|
1522 | |
|
|
1523 | |
|
|
1524 | =head1 SECURITY CONSIDERATIONS |
|
|
1525 | |
|
|
1526 | When you are using JSON in a protocol, talking to untrusted potentially |
|
|
1527 | hostile creatures requires relatively few measures. |
|
|
1528 | |
|
|
1529 | First of all, your JSON decoder should be secure, that is, should not have |
|
|
1530 | any buffer overflows. Obviously, this module should ensure that and I am |
|
|
1531 | trying hard on making that true, but you never know. |
|
|
1532 | |
|
|
1533 | Second, you need to avoid resource-starving attacks. That means you should |
|
|
1534 | limit the size of JSON texts you accept, or make sure then when your |
|
|
1535 | resources run out, that's just fine (e.g. by using a separate process that |
|
|
1536 | can crash safely). The size of a JSON text in octets or characters is |
|
|
1537 | usually a good indication of the size of the resources required to decode |
|
|
1538 | it into a Perl structure. While JSON::XS can check the size of the JSON |
|
|
1539 | text, it might be too late when you already have it in memory, so you |
|
|
1540 | might want to check the size before you accept the string. |
|
|
1541 | |
|
|
1542 | Third, JSON::XS recurses using the C stack when decoding objects and |
|
|
1543 | arrays. The C stack is a limited resource: for instance, on my amd64 |
|
|
1544 | machine with 8MB of stack size I can decode around 180k nested arrays but |
|
|
1545 | only 14k nested JSON objects (due to perl itself recursing deeply on croak |
|
|
1546 | to free the temporary). If that is exceeded, the program crashes. To be |
|
|
1547 | conservative, the default nesting limit is set to 512. If your process |
|
|
1548 | has a smaller stack, you should adjust this setting accordingly with the |
|
|
1549 | C<max_depth> method. |
|
|
1550 | |
|
|
1551 | Something else could bomb you, too, that I forgot to think of. In that |
|
|
1552 | case, you get to keep the pieces. I am always open for hints, though... |
|
|
1553 | |
|
|
1554 | Also keep in mind that JSON::XS might leak contents of your Perl data |
|
|
1555 | structures in its error messages, so when you serialise sensitive |
|
|
1556 | information you might want to make sure that exceptions thrown by JSON::XS |
|
|
1557 | will not end up in front of untrusted eyes. |
|
|
1558 | |
|
|
1559 | If you are using JSON::XS to return packets to consumption |
|
|
1560 | by JavaScript scripts in a browser you should have a look at |
|
|
1561 | L<http://blog.archive.jpsykes.com/47/practical-csrf-and-json-security/> to |
|
|
1562 | see whether you are vulnerable to some common attack vectors (which really |
|
|
1563 | are browser design bugs, but it is still you who will have to deal with |
|
|
1564 | it, as major browser developers care only for features, not about getting |
|
|
1565 | security right). |
|
|
1566 | |
|
|
1567 | |
|
|
1568 | =head1 INTEROPERABILITY WITH OTHER MODULES |
|
|
1569 | |
|
|
1570 | C<JSON::XS> uses the L<Types::Serialiser> module to provide boolean |
|
|
1571 | constants. That means that the JSON true and false values will be |
|
|
1572 | comaptible to true and false values of iother modules that do the same, |
|
|
1573 | such as L<JSON::PP> and L<CBOR::XS>. |
|
|
1574 | |
|
|
1575 | |
|
|
1576 | =head1 INTEROPERABILITY WITH OTHER JSON DECODERS |
|
|
1577 | |
|
|
1578 | As long as you only serialise data that can be directly expressed in JSON, |
|
|
1579 | C<JSON::XS> is incapable of generating invalid JSON output (modulo bugs, |
|
|
1580 | but C<JSON::XS> has found more bugs in the official JSON testsuite (1) |
|
|
1581 | than the official JSON testsuite has found in C<JSON::XS> (0)). |
|
|
1582 | |
|
|
1583 | When you have trouble decoding JSON generated by this module using other |
|
|
1584 | decoders, then it is very likely that you have an encoding mismatch or the |
|
|
1585 | other decoder is broken. |
|
|
1586 | |
|
|
1587 | When decoding, C<JSON::XS> is strict by default and will likely catch all |
|
|
1588 | errors. There are currently two settings that change this: C<relaxed> |
|
|
1589 | makes C<JSON::XS> accept (but not generate) some non-standard extensions, |
|
|
1590 | and C<allow_tags> will allow you to encode and decode Perl objects, at the |
|
|
1591 | cost of not outputting valid JSON anymore. |
|
|
1592 | |
|
|
1593 | =head2 TAGGED VALUE SYNTAX AND STANDARD JSON EN/DECODERS |
|
|
1594 | |
|
|
1595 | When you use C<allow_tags> to use the extended (and also nonstandard and |
|
|
1596 | invalid) JSON syntax for serialised objects, and you still want to decode |
|
|
1597 | the generated When you want to serialise objects, you can run a regex |
|
|
1598 | to replace the tagged syntax by standard JSON arrays (it only works for |
|
|
1599 | "normal" packagesnames without comma, newlines or single colons). First, |
|
|
1600 | the readable Perl version: |
|
|
1601 | |
|
|
1602 | # if your FREEZE methods return no values, you need this replace first: |
|
|
1603 | $json =~ s/\( \s* (" (?: [^\\":,]+|\\.|::)* ") \s* \) \s* \[\s*\]/[$1]/gx; |
|
|
1604 | |
|
|
1605 | # this works for non-empty constructor arg lists: |
|
|
1606 | $json =~ s/\( \s* (" (?: [^\\":,]+|\\.|::)* ") \s* \) \s* \[/[$1,/gx; |
|
|
1607 | |
|
|
1608 | And here is a less readable version that is easy to adapt to other |
|
|
1609 | languages: |
|
|
1610 | |
|
|
1611 | $json =~ s/\(\s*("([^\\":,]+|\\.|::)*")\s*\)\s*\[/[$1,/g; |
|
|
1612 | |
|
|
1613 | Here is an ECMAScript version (same regex): |
|
|
1614 | |
|
|
1615 | json = json.replace (/\(\s*("([^\\":,]+|\\.|::)*")\s*\)\s*\[/g, "[$1,"); |
|
|
1616 | |
|
|
1617 | Since this syntax converts to standard JSON arrays, it might be hard to |
|
|
1618 | distinguish serialised objects from normal arrays. You can prepend a |
|
|
1619 | "magic number" as first array element to reduce chances of a collision: |
|
|
1620 | |
|
|
1621 | $json =~ s/\(\s*("([^\\":,]+|\\.|::)*")\s*\)\s*\[/["XU1peReLzT4ggEllLanBYq4G9VzliwKF",$1,/g; |
|
|
1622 | |
|
|
1623 | And after decoding the JSON text, you could walk the data |
|
|
1624 | structure looking for arrays with a first element of |
|
|
1625 | C<XU1peReLzT4ggEllLanBYq4G9VzliwKF>. |
|
|
1626 | |
|
|
1627 | The same approach can be used to create the tagged format with another |
|
|
1628 | encoder. First, you create an array with the magic string as first member, |
|
|
1629 | the classname as second, and constructor arguments last, encode it as part |
|
|
1630 | of your JSON structure, and then: |
|
|
1631 | |
|
|
1632 | $json =~ s/\[\s*"XU1peReLzT4ggEllLanBYq4G9VzliwKF"\s*,\s*("([^\\":,]+|\\.|::)*")\s*,/($1)[/g; |
|
|
1633 | |
|
|
1634 | Again, this has some limitations - the magic string must not be encoded |
|
|
1635 | with character escapes, and the constructor arguments must be non-empty. |
|
|
1636 | |
|
|
1637 | |
|
|
1638 | =head1 RFC7159 |
|
|
1639 | |
|
|
1640 | Since this module was written, Google has written a new JSON RFC, RFC 7159 |
|
|
1641 | (and RFC7158). Unfortunately, this RFC breaks compatibility with both the |
|
|
1642 | original JSON specification on www.json.org and RFC4627. |
|
|
1643 | |
|
|
1644 | As far as I can see, you can get partial compatibility when parsing by |
|
|
1645 | using C<< ->allow_nonref >>. However, consider thew security implications |
|
|
1646 | of doing so. |
|
|
1647 | |
|
|
1648 | I haven't decided yet when to break compatibility with RFC4627 by default |
|
|
1649 | (and potentially leave applications insecure) and change the default to |
|
|
1650 | follow RFC7159, but application authors are well advised to call C<< |
|
|
1651 | ->allow_nonref(0) >> even if this is the current default, if they cannot |
|
|
1652 | handle non-reference values, in preparation for the day when the4 default |
|
|
1653 | will change. |
|
|
1654 | |
|
|
1655 | |
|
|
1656 | =head1 THREADS |
|
|
1657 | |
|
|
1658 | This module is I<not> guaranteed to be thread safe and there are no |
|
|
1659 | plans to change this until Perl gets thread support (as opposed to the |
|
|
1660 | horribly slow so-called "threads" which are simply slow and bloated |
|
|
1661 | process simulations - use fork, it's I<much> faster, cheaper, better). |
|
|
1662 | |
|
|
1663 | (It might actually work, but you have been warned). |
|
|
1664 | |
|
|
1665 | |
|
|
1666 | =head1 THE PERILS OF SETLOCALE |
|
|
1667 | |
|
|
1668 | Sometimes people avoid the Perl locale support and directly call the |
|
|
1669 | system's setlocale function with C<LC_ALL>. |
|
|
1670 | |
|
|
1671 | This breaks both perl and modules such as JSON::XS, as stringification of |
|
|
1672 | numbers no longer works correctly (e.g. C<$x = 0.1; print "$x"+1> might |
|
|
1673 | print C<1>, and JSON::XS might output illegal JSON as JSON::XS relies on |
|
|
1674 | perl to stringify numbers). |
|
|
1675 | |
|
|
1676 | The solution is simple: don't call C<setlocale>, or use it for only those |
|
|
1677 | categories you need, such as C<LC_MESSAGES> or C<LC_CTYPE>. |
|
|
1678 | |
|
|
1679 | If you need C<LC_NUMERIC>, you should enable it only around the code that |
|
|
1680 | actually needs it (avoiding stringification of numbers), and restore it |
|
|
1681 | afterwards. |
|
|
1682 | |
|
|
1683 | |
|
|
1684 | =head1 BUGS |
|
|
1685 | |
|
|
1686 | While the goal of this module is to be correct, that unfortunately does |
|
|
1687 | not mean it's bug-free, only that I think its design is bug-free. If you |
|
|
1688 | keep reporting bugs they will be fixed swiftly, though. |
|
|
1689 | |
|
|
1690 | Please refrain from using rt.cpan.org or any other bug reporting |
|
|
1691 | service. I put the contact address into my modules for a reason. |
|
|
1692 | |
|
|
1693 | =cut |
|
|
1694 | |
17 | BEGIN { |
1695 | BEGIN { |
18 | $VERSION = '0.1'; |
1696 | *true = \$Types::Serialiser::true; |
19 | @ISA = qw(Exporter); |
1697 | *true = \&Types::Serialiser::true; |
|
|
1698 | *false = \$Types::Serialiser::false; |
|
|
1699 | *false = \&Types::Serialiser::false; |
|
|
1700 | *is_bool = \&Types::Serialiser::is_bool; |
20 | |
1701 | |
21 | require Exporter; |
1702 | *JSON::XS::Boolean:: = *Types::Serialiser::Boolean::; |
22 | |
|
|
23 | require XSLoader; |
|
|
24 | XSLoader::load JSON::XS::, $VERSION; |
|
|
25 | } |
1703 | } |
26 | |
1704 | |
27 | =item |
1705 | XSLoader::load "JSON::XS", $VERSION; |
28 | |
1706 | |
29 | =cut |
1707 | =head1 SEE ALSO |
30 | |
1708 | |
31 | use JSON::DWIW; |
1709 | The F<json_xs> command line utility for quick experiments. |
32 | use Benchmark; |
|
|
33 | |
|
|
34 | use utf8; |
|
|
35 | #my $json = '{"ü":1,"a":[1,{"3":4},2],"b":5,"üü":2}'; |
|
|
36 | my $json = '{"test":9555555555555555555,"hu" : -1e+5, "arr" : [ 1,2,3,4,5]}'; |
|
|
37 | |
|
|
38 | my $js = JSON::XS->new; |
|
|
39 | warn $js->indent (0); |
|
|
40 | warn $js->canonical (0); |
|
|
41 | warn $js->ascii (0); |
|
|
42 | warn $js->space_after (0); |
|
|
43 | use Data::Dumper; |
|
|
44 | warn Dumper $js->decode ($json); |
|
|
45 | warn Dumper $js->encode ($js->decode ($json)); |
|
|
46 | #my $x = {"üü" => 2, "ü" => 1, "a" => [1,{3,4},2], b => 5}; |
|
|
47 | |
|
|
48 | #my $js2 = JSON::DWIW->new; |
|
|
49 | # |
|
|
50 | #timethese 200000, { |
|
|
51 | # a => sub { $js->encode ($x) }, |
|
|
52 | # b => sub { $js2->to_json ($x) }, |
|
|
53 | #}; |
|
|
54 | |
|
|
55 | 1; |
|
|
56 | |
|
|
57 | =back |
|
|
58 | |
1710 | |
59 | =head1 AUTHOR |
1711 | =head1 AUTHOR |
60 | |
1712 | |
61 | Marc Lehmann <schmorp@schmorp.de> |
1713 | Marc Lehmann <schmorp@schmorp.de> |
62 | http://home.schmorp.de/ |
1714 | http://home.schmorp.de/ |
63 | |
1715 | |
64 | =cut |
1716 | =cut |
65 | |
1717 | |
|
|
1718 | 1 |
|
|
1719 | |