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 = encode_json $perl_hash_or_arrayref; |
13 | $perl_hash_or_arrayref = from_json $utf8_encoded_json_text; |
16 | $perl_hash_or_arrayref = decode_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); |
23 | $perl_scalar = $coder->decode ($unicode_json_text); |
22 | $perl_scalar = $coder->decode ($unicode_json_text); |
24 | |
23 | |
|
|
24 | # Note that JSON version 2.0 and above will automatically use JSON::XS |
|
|
25 | # if available, at virtually no speed overhead either, so you should |
|
|
26 | # be able to just: |
|
|
27 | |
|
|
28 | use JSON; |
|
|
29 | |
|
|
30 | # and do the same things, except that you have a pure-perl fallback now. |
|
|
31 | |
25 | =head1 DESCRIPTION |
32 | =head1 DESCRIPTION |
26 | |
33 | |
27 | This module converts Perl data structures to JSON and vice versa. Its |
34 | This module converts Perl data structures to JSON and vice versa. Its |
28 | primary goal is to be I<correct> and its secondary goal is to be |
35 | primary goal is to be I<correct> and its secondary goal is to be |
29 | I<fast>. To reach the latter goal it was written in C. |
36 | I<fast>. To reach the latter goal it was written in C. |
|
|
37 | |
|
|
38 | Beginning with version 2.0 of the JSON module, when both JSON and |
|
|
39 | JSON::XS are installed, then JSON will fall back on JSON::XS (this can be |
|
|
40 | overriden) with no overhead due to emulation (by inheritign constructor |
|
|
41 | and methods). If JSON::XS is not available, it will fall back to the |
|
|
42 | compatible JSON::PP module as backend, so using JSON instead of JSON::XS |
|
|
43 | gives you a portable JSON API that can be fast when you need and doesn't |
|
|
44 | require a C compiler when that is a problem. |
30 | |
45 | |
31 | As this is the n-th-something JSON module on CPAN, what was the reason |
46 | As this is the n-th-something JSON module on CPAN, what was the reason |
32 | to write yet another JSON module? While it seems there are many JSON |
47 | to write yet another JSON module? While it seems there are many JSON |
33 | modules, none of them correctly handle all corner cases, and in most cases |
48 | modules, none of them correctly handle all corner cases, and in most cases |
34 | their maintainers are unresponsive, gone missing, or not listening to bug |
49 | their maintainers are unresponsive, gone missing, or not listening to bug |
… | |
… | |
41 | |
56 | |
42 | =head2 FEATURES |
57 | =head2 FEATURES |
43 | |
58 | |
44 | =over 4 |
59 | =over 4 |
45 | |
60 | |
46 | =item * correct unicode handling |
61 | =item * correct Unicode handling |
47 | |
62 | |
48 | This module knows how to handle Unicode, and even documents how and when |
63 | This module knows how to handle Unicode, and even documents how and when |
49 | it does so. |
64 | it does so. |
50 | |
65 | |
51 | =item * round-trip integrity |
66 | =item * round-trip integrity |
… | |
… | |
71 | This module has both a simple functional interface as well as an OO |
86 | This module has both a simple functional interface as well as an OO |
72 | interface. |
87 | interface. |
73 | |
88 | |
74 | =item * reasonably versatile output formats |
89 | =item * reasonably versatile output formats |
75 | |
90 | |
76 | You can choose between the most compact guarenteed single-line format |
91 | You can choose between the most compact guaranteed single-line format |
77 | possible (nice for simple line-based protocols), a pure-ascii format |
92 | 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 |
93 | (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 |
94 | 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. |
95 | stuff). Or you can combine those features in whatever way you like. |
81 | |
96 | |
82 | =back |
97 | =back |
83 | |
98 | |
84 | =cut |
99 | =cut |
85 | |
100 | |
86 | package JSON::XS; |
101 | package JSON::XS; |
87 | |
102 | |
88 | use strict; |
103 | use strict; |
89 | |
104 | |
90 | BEGIN { |
|
|
91 | our $VERSION = '1.22'; |
105 | our $VERSION = '2.01'; |
92 | our @ISA = qw(Exporter); |
106 | our @ISA = qw(Exporter); |
93 | |
107 | |
94 | our @EXPORT = qw(to_json from_json objToJson jsonToObj); |
108 | our @EXPORT = qw(encode_json decode_json to_json from_json); |
95 | require Exporter; |
|
|
96 | |
109 | |
|
|
110 | sub to_json($) { |
97 | require XSLoader; |
111 | require Carp; |
98 | XSLoader::load JSON::XS::, $VERSION; |
112 | Carp::croak ("JSON::XS::to_json has been renamed to encode_json, either downgrade to pre-2.0 versions of JSON::XS or rename the call"); |
99 | } |
113 | } |
100 | |
114 | |
|
|
115 | sub from_json($) { |
|
|
116 | require Carp; |
|
|
117 | Carp::croak ("JSON::XS::from_json has been renamed to decode_json, either downgrade to pre-2.0 versions of JSON::XS or rename the call"); |
|
|
118 | } |
|
|
119 | |
|
|
120 | use Exporter; |
|
|
121 | use XSLoader; |
|
|
122 | |
101 | =head1 FUNCTIONAL INTERFACE |
123 | =head1 FUNCTIONAL INTERFACE |
102 | |
124 | |
103 | The following convinience methods are provided by this module. They are |
125 | The following convenience methods are provided by this module. They are |
104 | exported by default: |
126 | exported by default: |
105 | |
127 | |
106 | =over 4 |
128 | =over 4 |
107 | |
129 | |
108 | =item $json_text = to_json $perl_scalar |
130 | =item $json_text = encode_json $perl_scalar |
109 | |
131 | |
110 | Converts the given Perl data structure (a simple scalar or a reference to |
132 | 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 |
133 | (that is, the string contains octets only). Croaks on error. |
112 | octets only). Croaks on error. |
|
|
113 | |
134 | |
114 | This function call is functionally identical to: |
135 | This function call is functionally identical to: |
115 | |
136 | |
116 | $json_text = JSON::XS->new->utf8->encode ($perl_scalar) |
137 | $json_text = JSON::XS->new->utf8->encode ($perl_scalar) |
117 | |
138 | |
118 | except being faster. |
139 | except being faster. |
119 | |
140 | |
120 | =item $perl_scalar = from_json $json_text |
141 | =item $perl_scalar = decode_json $json_text |
121 | |
142 | |
122 | The opposite of C<to_json>: expects an UTF-8 (binary) string and tries to |
143 | The opposite of C<encode_json>: expects an UTF-8 (binary) string and tries |
123 | parse that as an UTF-8 encoded JSON text, returning the resulting simple |
144 | to parse that as an UTF-8 encoded JSON text, returning the resulting |
124 | scalar or reference. Croaks on error. |
145 | reference. Croaks on error. |
125 | |
146 | |
126 | This function call is functionally identical to: |
147 | This function call is functionally identical to: |
127 | |
148 | |
128 | $perl_scalar = JSON::XS->new->utf8->decode ($json_text) |
149 | $perl_scalar = JSON::XS->new->utf8->decode ($json_text) |
129 | |
150 | |
130 | except being faster. |
151 | except being faster. |
131 | |
152 | |
|
|
153 | =item $is_boolean = JSON::XS::is_bool $scalar |
|
|
154 | |
|
|
155 | Returns true if the passed scalar represents either JSON::XS::true or |
|
|
156 | JSON::XS::false, two constants that act like C<1> and C<0>, respectively |
|
|
157 | and are used to represent JSON C<true> and C<false> values in Perl. |
|
|
158 | |
|
|
159 | See MAPPING, below, for more information on how JSON values are mapped to |
|
|
160 | Perl. |
|
|
161 | |
132 | =back |
162 | =back |
|
|
163 | |
|
|
164 | |
|
|
165 | =head1 A FEW NOTES ON UNICODE AND PERL |
|
|
166 | |
|
|
167 | Since this often leads to confusion, here are a few very clear words on |
|
|
168 | how Unicode works in Perl, modulo bugs. |
|
|
169 | |
|
|
170 | =over 4 |
|
|
171 | |
|
|
172 | =item 1. Perl strings can store characters with ordinal values > 255. |
|
|
173 | |
|
|
174 | This enables you to store Unicode characters as single characters in a |
|
|
175 | Perl string - very natural. |
|
|
176 | |
|
|
177 | =item 2. Perl does I<not> associate an encoding with your strings. |
|
|
178 | |
|
|
179 | Unless you force it to, e.g. when matching it against a regex, or printing |
|
|
180 | the scalar to a file, in which case Perl either interprets your string as |
|
|
181 | locale-encoded text, octets/binary, or as Unicode, depending on various |
|
|
182 | settings. In no case is an encoding stored together with your data, it is |
|
|
183 | I<use> that decides encoding, not any magical metadata. |
|
|
184 | |
|
|
185 | =item 3. The internal utf-8 flag has no meaning with regards to the |
|
|
186 | encoding of your string. |
|
|
187 | |
|
|
188 | Just ignore that flag unless you debug a Perl bug, a module written in |
|
|
189 | XS or want to dive into the internals of perl. Otherwise it will only |
|
|
190 | confuse you, as, despite the name, it says nothing about how your string |
|
|
191 | is encoded. You can have Unicode strings with that flag set, with that |
|
|
192 | flag clear, and you can have binary data with that flag set and that flag |
|
|
193 | clear. Other possibilities exist, too. |
|
|
194 | |
|
|
195 | If you didn't know about that flag, just the better, pretend it doesn't |
|
|
196 | exist. |
|
|
197 | |
|
|
198 | =item 4. A "Unicode String" is simply a string where each character can be |
|
|
199 | validly interpreted as a Unicode codepoint. |
|
|
200 | |
|
|
201 | If you have UTF-8 encoded data, it is no longer a Unicode string, but a |
|
|
202 | Unicode string encoded in UTF-8, giving you a binary string. |
|
|
203 | |
|
|
204 | =item 5. A string containing "high" (> 255) character values is I<not> a UTF-8 string. |
|
|
205 | |
|
|
206 | It's a fact. Learn to live with it. |
|
|
207 | |
|
|
208 | =back |
|
|
209 | |
|
|
210 | I hope this helps :) |
133 | |
211 | |
134 | |
212 | |
135 | =head1 OBJECT-ORIENTED INTERFACE |
213 | =head1 OBJECT-ORIENTED INTERFACE |
136 | |
214 | |
137 | The object oriented interface lets you configure your own encoding or |
215 | The object oriented interface lets you configure your own encoding or |
… | |
… | |
150 | my $json = JSON::XS->new->utf8->space_after->encode ({a => [1,2]}) |
228 | my $json = JSON::XS->new->utf8->space_after->encode ({a => [1,2]}) |
151 | => {"a": [1, 2]} |
229 | => {"a": [1, 2]} |
152 | |
230 | |
153 | =item $json = $json->ascii ([$enable]) |
231 | =item $json = $json->ascii ([$enable]) |
154 | |
232 | |
|
|
233 | =item $enabled = $json->get_ascii |
|
|
234 | |
155 | If C<$enable> is true (or missing), then the C<encode> method will not |
235 | If C<$enable> is true (or missing), then the C<encode> method will not |
156 | generate characters outside the code range C<0..127> (which is ASCII). Any |
236 | generate characters outside the code range C<0..127> (which is ASCII). Any |
157 | unicode characters outside that range will be escaped using either a |
237 | Unicode characters outside that range will be escaped using either a |
158 | single \uXXXX (BMP characters) or a double \uHHHH\uLLLLL escape sequence, |
238 | single \uXXXX (BMP characters) or a double \uHHHH\uLLLLL escape sequence, |
159 | as per RFC4627. The resulting encoded JSON text can be treated as a native |
239 | as per RFC4627. The resulting encoded JSON text can be treated as a native |
160 | unicode string, an ascii-encoded, latin1-encoded or UTF-8 encoded string, |
240 | Unicode string, an ascii-encoded, latin1-encoded or UTF-8 encoded string, |
161 | or any other superset of ASCII. |
241 | or any other superset of ASCII. |
162 | |
242 | |
163 | If C<$enable> is false, then the C<encode> method will not escape Unicode |
243 | If C<$enable> is false, then the C<encode> method will not escape Unicode |
164 | characters unless required by the JSON syntax or other flags. This results |
244 | characters unless required by the JSON syntax or other flags. This results |
165 | in a faster and more compact format. |
245 | in a faster and more compact format. |
… | |
… | |
171 | JSON::XS->new->ascii (1)->encode ([chr 0x10401]) |
251 | JSON::XS->new->ascii (1)->encode ([chr 0x10401]) |
172 | => ["\ud801\udc01"] |
252 | => ["\ud801\udc01"] |
173 | |
253 | |
174 | =item $json = $json->latin1 ([$enable]) |
254 | =item $json = $json->latin1 ([$enable]) |
175 | |
255 | |
|
|
256 | =item $enabled = $json->get_latin1 |
|
|
257 | |
176 | If C<$enable> is true (or missing), then the C<encode> method will encode |
258 | If C<$enable> is true (or missing), then the C<encode> method will encode |
177 | the resulting JSON text as latin1 (or iso-8859-1), escaping any characters |
259 | the resulting JSON text as latin1 (or iso-8859-1), escaping any characters |
178 | outside the code range C<0..255>. The resulting string can be treated as a |
260 | outside the code range C<0..255>. The resulting string can be treated as a |
179 | latin1-encoded JSON text or a native unicode string. The C<decode> method |
261 | latin1-encoded JSON text or a native Unicode string. The C<decode> method |
180 | will not be affected in any way by this flag, as C<decode> by default |
262 | will not be affected in any way by this flag, as C<decode> by default |
181 | expects unicode, which is a strict superset of latin1. |
263 | expects Unicode, which is a strict superset of latin1. |
182 | |
264 | |
183 | If C<$enable> is false, then the C<encode> method will not escape Unicode |
265 | If C<$enable> is false, then the C<encode> method will not escape Unicode |
184 | characters unless required by the JSON syntax or other flags. |
266 | characters unless required by the JSON syntax or other flags. |
185 | |
267 | |
186 | The main use for this flag is efficiently encoding binary data as JSON |
268 | The main use for this flag is efficiently encoding binary data as JSON |
187 | text, as most octets will not be escaped, resulting in a smaller encoded |
269 | text, as most octets will not be escaped, resulting in a smaller encoded |
188 | size. The disadvantage is that the resulting JSON text is encoded |
270 | size. The disadvantage is that the resulting JSON text is encoded |
189 | in latin1 (and must correctly be treated as such when storing and |
271 | in latin1 (and must correctly be treated as such when storing and |
190 | transfering), a rare encoding for JSON. It is therefore most useful when |
272 | transferring), a rare encoding for JSON. It is therefore most useful when |
191 | you want to store data structures known to contain binary data efficiently |
273 | you want to store data structures known to contain binary data efficiently |
192 | in files or databases, not when talking to other JSON encoders/decoders. |
274 | in files or databases, not when talking to other JSON encoders/decoders. |
193 | |
275 | |
194 | JSON::XS->new->latin1->encode (["\x{89}\x{abc}"] |
276 | JSON::XS->new->latin1->encode (["\x{89}\x{abc}"] |
195 | => ["\x{89}\\u0abc"] # (perl syntax, U+abc escaped, U+89 not) |
277 | => ["\x{89}\\u0abc"] # (perl syntax, U+abc escaped, U+89 not) |
196 | |
278 | |
197 | =item $json = $json->utf8 ([$enable]) |
279 | =item $json = $json->utf8 ([$enable]) |
|
|
280 | |
|
|
281 | =item $enabled = $json->get_utf8 |
198 | |
282 | |
199 | If C<$enable> is true (or missing), then the C<encode> method will encode |
283 | If C<$enable> is true (or missing), then the C<encode> method will encode |
200 | the JSON result into UTF-8, as required by many protocols, while the |
284 | the JSON result into UTF-8, as required by many protocols, while the |
201 | C<decode> method expects to be handled an UTF-8-encoded string. Please |
285 | C<decode> method expects to be handled an UTF-8-encoded string. Please |
202 | note that UTF-8-encoded strings do not contain any characters outside the |
286 | note that UTF-8-encoded strings do not contain any characters outside the |
203 | range C<0..255>, they are thus useful for bytewise/binary I/O. In future |
287 | range C<0..255>, they are thus useful for bytewise/binary I/O. In future |
204 | versions, enabling this option might enable autodetection of the UTF-16 |
288 | versions, enabling this option might enable autodetection of the UTF-16 |
205 | and UTF-32 encoding families, as described in RFC4627. |
289 | and UTF-32 encoding families, as described in RFC4627. |
206 | |
290 | |
207 | If C<$enable> is false, then the C<encode> method will return the JSON |
291 | If C<$enable> is false, then the C<encode> method will return the JSON |
208 | string as a (non-encoded) unicode string, while C<decode> expects thus a |
292 | string as a (non-encoded) Unicode string, while C<decode> expects thus a |
209 | unicode string. Any decoding or encoding (e.g. to UTF-8 or UTF-16) needs |
293 | Unicode string. Any decoding or encoding (e.g. to UTF-8 or UTF-16) needs |
210 | to be done yourself, e.g. using the Encode module. |
294 | to be done yourself, e.g. using the Encode module. |
211 | |
295 | |
212 | Example, output UTF-16BE-encoded JSON: |
296 | Example, output UTF-16BE-encoded JSON: |
213 | |
297 | |
214 | use Encode; |
298 | use Encode; |
… | |
… | |
236 | ] |
320 | ] |
237 | } |
321 | } |
238 | |
322 | |
239 | =item $json = $json->indent ([$enable]) |
323 | =item $json = $json->indent ([$enable]) |
240 | |
324 | |
|
|
325 | =item $enabled = $json->get_indent |
|
|
326 | |
241 | If C<$enable> is true (or missing), then the C<encode> method will use a multiline |
327 | If C<$enable> is true (or missing), then the C<encode> method will use a multiline |
242 | format as output, putting every array member or object/hash key-value pair |
328 | format as output, putting every array member or object/hash key-value pair |
243 | into its own line, identing them properly. |
329 | into its own line, indenting them properly. |
244 | |
330 | |
245 | If C<$enable> is false, no newlines or indenting will be produced, and the |
331 | If C<$enable> is false, no newlines or indenting will be produced, and the |
246 | resulting JSON text is guarenteed not to contain any C<newlines>. |
332 | resulting JSON text is guaranteed not to contain any C<newlines>. |
247 | |
333 | |
248 | This setting has no effect when decoding JSON texts. |
334 | This setting has no effect when decoding JSON texts. |
249 | |
335 | |
250 | =item $json = $json->space_before ([$enable]) |
336 | =item $json = $json->space_before ([$enable]) |
|
|
337 | |
|
|
338 | =item $enabled = $json->get_space_before |
251 | |
339 | |
252 | If C<$enable> is true (or missing), then the C<encode> method will add an extra |
340 | If C<$enable> is true (or missing), then the C<encode> method will add an extra |
253 | optional space before the C<:> separating keys from values in JSON objects. |
341 | optional space before the C<:> separating keys from values in JSON objects. |
254 | |
342 | |
255 | If C<$enable> is false, then the C<encode> method will not add any extra |
343 | If C<$enable> is false, then the C<encode> method will not add any extra |
… | |
… | |
261 | Example, space_before enabled, space_after and indent disabled: |
349 | Example, space_before enabled, space_after and indent disabled: |
262 | |
350 | |
263 | {"key" :"value"} |
351 | {"key" :"value"} |
264 | |
352 | |
265 | =item $json = $json->space_after ([$enable]) |
353 | =item $json = $json->space_after ([$enable]) |
|
|
354 | |
|
|
355 | =item $enabled = $json->get_space_after |
266 | |
356 | |
267 | If C<$enable> is true (or missing), then the C<encode> method will add an extra |
357 | If C<$enable> is true (or missing), then the C<encode> method will add an extra |
268 | optional space after the C<:> separating keys from values in JSON objects |
358 | optional space after the C<:> separating keys from values in JSON objects |
269 | and extra whitespace after the C<,> separating key-value pairs and array |
359 | and extra whitespace after the C<,> separating key-value pairs and array |
270 | members. |
360 | members. |
… | |
… | |
276 | |
366 | |
277 | Example, space_before and indent disabled, space_after enabled: |
367 | Example, space_before and indent disabled, space_after enabled: |
278 | |
368 | |
279 | {"key": "value"} |
369 | {"key": "value"} |
280 | |
370 | |
|
|
371 | =item $json = $json->relaxed ([$enable]) |
|
|
372 | |
|
|
373 | =item $enabled = $json->get_relaxed |
|
|
374 | |
|
|
375 | If C<$enable> is true (or missing), then C<decode> will accept some |
|
|
376 | extensions to normal JSON syntax (see below). C<encode> will not be |
|
|
377 | affected in anyway. I<Be aware that this option makes you accept invalid |
|
|
378 | JSON texts as if they were valid!>. I suggest only to use this option to |
|
|
379 | parse application-specific files written by humans (configuration files, |
|
|
380 | resource files etc.) |
|
|
381 | |
|
|
382 | If C<$enable> is false (the default), then C<decode> will only accept |
|
|
383 | valid JSON texts. |
|
|
384 | |
|
|
385 | Currently accepted extensions are: |
|
|
386 | |
|
|
387 | =over 4 |
|
|
388 | |
|
|
389 | =item * list items can have an end-comma |
|
|
390 | |
|
|
391 | JSON I<separates> array elements and key-value pairs with commas. This |
|
|
392 | can be annoying if you write JSON texts manually and want to be able to |
|
|
393 | quickly append elements, so this extension accepts comma at the end of |
|
|
394 | such items not just between them: |
|
|
395 | |
|
|
396 | [ |
|
|
397 | 1, |
|
|
398 | 2, <- this comma not normally allowed |
|
|
399 | ] |
|
|
400 | { |
|
|
401 | "k1": "v1", |
|
|
402 | "k2": "v2", <- this comma not normally allowed |
|
|
403 | } |
|
|
404 | |
|
|
405 | =item * shell-style '#'-comments |
|
|
406 | |
|
|
407 | Whenever JSON allows whitespace, shell-style comments are additionally |
|
|
408 | allowed. They are terminated by the first carriage-return or line-feed |
|
|
409 | character, after which more white-space and comments are allowed. |
|
|
410 | |
|
|
411 | [ |
|
|
412 | 1, # this comment not allowed in JSON |
|
|
413 | # neither this one... |
|
|
414 | ] |
|
|
415 | |
|
|
416 | =back |
|
|
417 | |
281 | =item $json = $json->canonical ([$enable]) |
418 | =item $json = $json->canonical ([$enable]) |
|
|
419 | |
|
|
420 | =item $enabled = $json->get_canonical |
282 | |
421 | |
283 | If C<$enable> is true (or missing), then the C<encode> method will output JSON objects |
422 | If C<$enable> is true (or missing), then the C<encode> method will output JSON objects |
284 | by sorting their keys. This is adding a comparatively high overhead. |
423 | by sorting their keys. This is adding a comparatively high overhead. |
285 | |
424 | |
286 | If C<$enable> is false, then the C<encode> method will output key-value |
425 | If C<$enable> is false, then the C<encode> method will output key-value |
287 | pairs in the order Perl stores them (which will likely change between runs |
426 | pairs in the order Perl stores them (which will likely change between runs |
288 | of the same script). |
427 | of the same script). |
289 | |
428 | |
290 | This option is useful if you want the same data structure to be encoded as |
429 | This option is useful if you want the same data structure to be encoded as |
291 | the same JSON text (given the same overall settings). If it is disabled, |
430 | the same JSON text (given the same overall settings). If it is disabled, |
292 | the same hash migh be encoded differently even if contains the same data, |
431 | the same hash might be encoded differently even if contains the same data, |
293 | as key-value pairs have no inherent ordering in Perl. |
432 | as key-value pairs have no inherent ordering in Perl. |
294 | |
433 | |
295 | This setting has no effect when decoding JSON texts. |
434 | This setting has no effect when decoding JSON texts. |
296 | |
435 | |
297 | =item $json = $json->allow_nonref ([$enable]) |
436 | =item $json = $json->allow_nonref ([$enable]) |
|
|
437 | |
|
|
438 | =item $enabled = $json->get_allow_nonref |
298 | |
439 | |
299 | If C<$enable> is true (or missing), then the C<encode> method can convert a |
440 | If C<$enable> is true (or missing), then the C<encode> method can convert a |
300 | non-reference into its corresponding string, number or null JSON value, |
441 | non-reference into its corresponding string, number or null JSON value, |
301 | which is an extension to RFC4627. Likewise, C<decode> will accept those JSON |
442 | which is an extension to RFC4627. Likewise, C<decode> will accept those JSON |
302 | values instead of croaking. |
443 | values instead of croaking. |
… | |
… | |
310 | resulting in an invalid JSON text: |
451 | resulting in an invalid JSON text: |
311 | |
452 | |
312 | JSON::XS->new->allow_nonref->encode ("Hello, World!") |
453 | JSON::XS->new->allow_nonref->encode ("Hello, World!") |
313 | => "Hello, World!" |
454 | => "Hello, World!" |
314 | |
455 | |
|
|
456 | =item $json = $json->allow_blessed ([$enable]) |
|
|
457 | |
|
|
458 | =item $enabled = $json->get_allow_blessed |
|
|
459 | |
|
|
460 | If C<$enable> is true (or missing), then the C<encode> method will not |
|
|
461 | barf when it encounters a blessed reference. Instead, the value of the |
|
|
462 | B<convert_blessed> option will decide whether C<null> (C<convert_blessed> |
|
|
463 | disabled or no C<TO_JSON> method found) or a representation of the |
|
|
464 | object (C<convert_blessed> enabled and C<TO_JSON> method found) is being |
|
|
465 | encoded. Has no effect on C<decode>. |
|
|
466 | |
|
|
467 | If C<$enable> is false (the default), then C<encode> will throw an |
|
|
468 | exception when it encounters a blessed object. |
|
|
469 | |
|
|
470 | =item $json = $json->convert_blessed ([$enable]) |
|
|
471 | |
|
|
472 | =item $enabled = $json->get_convert_blessed |
|
|
473 | |
|
|
474 | If C<$enable> is true (or missing), then C<encode>, upon encountering a |
|
|
475 | blessed object, will check for the availability of the C<TO_JSON> method |
|
|
476 | on the object's class. If found, it will be called in scalar context |
|
|
477 | and the resulting scalar will be encoded instead of the object. If no |
|
|
478 | C<TO_JSON> method is found, the value of C<allow_blessed> will decide what |
|
|
479 | to do. |
|
|
480 | |
|
|
481 | The C<TO_JSON> method may safely call die if it wants. If C<TO_JSON> |
|
|
482 | returns other blessed objects, those will be handled in the same |
|
|
483 | way. C<TO_JSON> must take care of not causing an endless recursion cycle |
|
|
484 | (== crash) in this case. The name of C<TO_JSON> was chosen because other |
|
|
485 | methods called by the Perl core (== not by the user of the object) are |
|
|
486 | usually in upper case letters and to avoid collisions with any C<to_json> |
|
|
487 | function or method. |
|
|
488 | |
|
|
489 | This setting does not yet influence C<decode> in any way, but in the |
|
|
490 | future, global hooks might get installed that influence C<decode> and are |
|
|
491 | enabled by this setting. |
|
|
492 | |
|
|
493 | If C<$enable> is false, then the C<allow_blessed> setting will decide what |
|
|
494 | to do when a blessed object is found. |
|
|
495 | |
|
|
496 | =item $json = $json->filter_json_object ([$coderef->($hashref)]) |
|
|
497 | |
|
|
498 | When C<$coderef> is specified, it will be called from C<decode> each |
|
|
499 | time it decodes a JSON object. The only argument is a reference to the |
|
|
500 | newly-created hash. If the code references returns a single scalar (which |
|
|
501 | need not be a reference), this value (i.e. a copy of that scalar to avoid |
|
|
502 | aliasing) is inserted into the deserialised data structure. If it returns |
|
|
503 | an empty list (NOTE: I<not> C<undef>, which is a valid scalar), the |
|
|
504 | original deserialised hash will be inserted. This setting can slow down |
|
|
505 | decoding considerably. |
|
|
506 | |
|
|
507 | When C<$coderef> is omitted or undefined, any existing callback will |
|
|
508 | be removed and C<decode> will not change the deserialised hash in any |
|
|
509 | way. |
|
|
510 | |
|
|
511 | Example, convert all JSON objects into the integer 5: |
|
|
512 | |
|
|
513 | my $js = JSON::XS->new->filter_json_object (sub { 5 }); |
|
|
514 | # returns [5] |
|
|
515 | $js->decode ('[{}]') |
|
|
516 | # throw an exception because allow_nonref is not enabled |
|
|
517 | # so a lone 5 is not allowed. |
|
|
518 | $js->decode ('{"a":1, "b":2}'); |
|
|
519 | |
|
|
520 | =item $json = $json->filter_json_single_key_object ($key [=> $coderef->($value)]) |
|
|
521 | |
|
|
522 | Works remotely similar to C<filter_json_object>, but is only called for |
|
|
523 | JSON objects having a single key named C<$key>. |
|
|
524 | |
|
|
525 | This C<$coderef> is called before the one specified via |
|
|
526 | C<filter_json_object>, if any. It gets passed the single value in the JSON |
|
|
527 | object. If it returns a single value, it will be inserted into the data |
|
|
528 | structure. If it returns nothing (not even C<undef> but the empty list), |
|
|
529 | the callback from C<filter_json_object> will be called next, as if no |
|
|
530 | single-key callback were specified. |
|
|
531 | |
|
|
532 | If C<$coderef> is omitted or undefined, the corresponding callback will be |
|
|
533 | disabled. There can only ever be one callback for a given key. |
|
|
534 | |
|
|
535 | As this callback gets called less often then the C<filter_json_object> |
|
|
536 | one, decoding speed will not usually suffer as much. Therefore, single-key |
|
|
537 | objects make excellent targets to serialise Perl objects into, especially |
|
|
538 | as single-key JSON objects are as close to the type-tagged value concept |
|
|
539 | as JSON gets (it's basically an ID/VALUE tuple). Of course, JSON does not |
|
|
540 | support this in any way, so you need to make sure your data never looks |
|
|
541 | like a serialised Perl hash. |
|
|
542 | |
|
|
543 | Typical names for the single object key are C<__class_whatever__>, or |
|
|
544 | C<$__dollars_are_rarely_used__$> or C<}ugly_brace_placement>, or even |
|
|
545 | things like C<__class_md5sum(classname)__>, to reduce the risk of clashing |
|
|
546 | with real hashes. |
|
|
547 | |
|
|
548 | Example, decode JSON objects of the form C<< { "__widget__" => <id> } >> |
|
|
549 | into the corresponding C<< $WIDGET{<id>} >> object: |
|
|
550 | |
|
|
551 | # return whatever is in $WIDGET{5}: |
|
|
552 | JSON::XS |
|
|
553 | ->new |
|
|
554 | ->filter_json_single_key_object (__widget__ => sub { |
|
|
555 | $WIDGET{ $_[0] } |
|
|
556 | }) |
|
|
557 | ->decode ('{"__widget__": 5') |
|
|
558 | |
|
|
559 | # this can be used with a TO_JSON method in some "widget" class |
|
|
560 | # for serialisation to json: |
|
|
561 | sub WidgetBase::TO_JSON { |
|
|
562 | my ($self) = @_; |
|
|
563 | |
|
|
564 | unless ($self->{id}) { |
|
|
565 | $self->{id} = ..get..some..id..; |
|
|
566 | $WIDGET{$self->{id}} = $self; |
|
|
567 | } |
|
|
568 | |
|
|
569 | { __widget__ => $self->{id} } |
|
|
570 | } |
|
|
571 | |
315 | =item $json = $json->shrink ([$enable]) |
572 | =item $json = $json->shrink ([$enable]) |
|
|
573 | |
|
|
574 | =item $enabled = $json->get_shrink |
316 | |
575 | |
317 | Perl usually over-allocates memory a bit when allocating space for |
576 | Perl usually over-allocates memory a bit when allocating space for |
318 | strings. This flag optionally resizes strings generated by either |
577 | strings. This flag optionally resizes strings generated by either |
319 | C<encode> or C<decode> to their minimum size possible. This can save |
578 | C<encode> or C<decode> to their minimum size possible. This can save |
320 | memory when your JSON texts are either very very long or you have many |
579 | memory when your JSON texts are either very very long or you have many |
… | |
… | |
338 | strings that look like integers or floats into integers or floats |
597 | strings that look like integers or floats into integers or floats |
339 | internally (there is no difference on the Perl level), saving space. |
598 | internally (there is no difference on the Perl level), saving space. |
340 | |
599 | |
341 | =item $json = $json->max_depth ([$maximum_nesting_depth]) |
600 | =item $json = $json->max_depth ([$maximum_nesting_depth]) |
342 | |
601 | |
|
|
602 | =item $max_depth = $json->get_max_depth |
|
|
603 | |
343 | Sets the maximum nesting level (default C<512>) accepted while encoding |
604 | Sets the maximum nesting level (default C<512>) accepted while encoding |
344 | or decoding. If the JSON text or Perl data structure has an equal or |
605 | or decoding. If the JSON text or Perl data structure has an equal or |
345 | higher nesting level then this limit, then the encoder and decoder will |
606 | higher nesting level then this limit, then the encoder and decoder will |
346 | stop and croak at that point. |
607 | stop and croak at that point. |
347 | |
608 | |
… | |
… | |
351 | given character in a string. |
612 | given character in a string. |
352 | |
613 | |
353 | Setting the maximum depth to one disallows any nesting, so that ensures |
614 | Setting the maximum depth to one disallows any nesting, so that ensures |
354 | that the object is only a single hash/object or array. |
615 | that the object is only a single hash/object or array. |
355 | |
616 | |
356 | The argument to C<max_depth> will be rounded up to the next nearest power |
617 | The argument to C<max_depth> will be rounded up to the next highest power |
357 | of two. |
618 | of two. If no argument is given, the highest possible setting will be |
|
|
619 | used, which is rarely useful. |
|
|
620 | |
|
|
621 | See SECURITY CONSIDERATIONS, below, for more info on why this is useful. |
|
|
622 | |
|
|
623 | =item $json = $json->max_size ([$maximum_string_size]) |
|
|
624 | |
|
|
625 | =item $max_size = $json->get_max_size |
|
|
626 | |
|
|
627 | Set the maximum length a JSON text may have (in bytes) where decoding is |
|
|
628 | being attempted. The default is C<0>, meaning no limit. When C<decode> |
|
|
629 | is called on a string longer then this number of characters it will not |
|
|
630 | attempt to decode the string but throw an exception. This setting has no |
|
|
631 | effect on C<encode> (yet). |
|
|
632 | |
|
|
633 | The argument to C<max_size> will be rounded up to the next B<highest> |
|
|
634 | power of two (so may be more than requested). If no argument is given, the |
|
|
635 | limit check will be deactivated (same as when C<0> is specified). |
358 | |
636 | |
359 | See SECURITY CONSIDERATIONS, below, for more info on why this is useful. |
637 | See SECURITY CONSIDERATIONS, below, for more info on why this is useful. |
360 | |
638 | |
361 | =item $json_text = $json->encode ($perl_scalar) |
639 | =item $json_text = $json->encode ($perl_scalar) |
362 | |
640 | |
… | |
… | |
399 | vice versa. These mappings are designed to "do the right thing" in most |
677 | vice versa. These mappings are designed to "do the right thing" in most |
400 | circumstances automatically, preserving round-tripping characteristics |
678 | circumstances automatically, preserving round-tripping characteristics |
401 | (what you put in comes out as something equivalent). |
679 | (what you put in comes out as something equivalent). |
402 | |
680 | |
403 | For the more enlightened: note that in the following descriptions, |
681 | For the more enlightened: note that in the following descriptions, |
404 | lowercase I<perl> refers to the Perl interpreter, while uppcercase I<Perl> |
682 | lowercase I<perl> refers to the Perl interpreter, while uppercase I<Perl> |
405 | refers to the abstract Perl language itself. |
683 | refers to the abstract Perl language itself. |
406 | |
684 | |
|
|
685 | |
407 | =head2 JSON -> PERL |
686 | =head2 JSON -> PERL |
408 | |
687 | |
409 | =over 4 |
688 | =over 4 |
410 | |
689 | |
411 | =item object |
690 | =item object |
412 | |
691 | |
413 | A JSON object becomes a reference to a hash in Perl. No ordering of object |
692 | A JSON object becomes a reference to a hash in Perl. No ordering of object |
414 | keys is preserved (JSON does not preserver object key ordering itself). |
693 | keys is preserved (JSON does not preserve object key ordering itself). |
415 | |
694 | |
416 | =item array |
695 | =item array |
417 | |
696 | |
418 | A JSON array becomes a reference to an array in Perl. |
697 | A JSON array becomes a reference to an array in Perl. |
419 | |
698 | |
… | |
… | |
423 | are represented by the same codepoints in the Perl string, so no manual |
702 | are represented by the same codepoints in the Perl string, so no manual |
424 | decoding is necessary. |
703 | decoding is necessary. |
425 | |
704 | |
426 | =item number |
705 | =item number |
427 | |
706 | |
428 | A JSON number becomes either an integer or numeric (floating point) |
707 | A JSON number becomes either an integer, numeric (floating point) or |
429 | scalar in perl, depending on its range and any fractional parts. On the |
708 | string scalar in perl, depending on its range and any fractional parts. On |
430 | Perl level, there is no difference between those as Perl handles all the |
709 | the Perl level, there is no difference between those as Perl handles all |
431 | conversion details, but an integer may take slightly less memory and might |
710 | the conversion details, but an integer may take slightly less memory and |
432 | represent more values exactly than (floating point) numbers. |
711 | might represent more values exactly than (floating point) numbers. |
|
|
712 | |
|
|
713 | If the number consists of digits only, JSON::XS will try to represent |
|
|
714 | it as an integer value. If that fails, it will try to represent it as |
|
|
715 | a numeric (floating point) value if that is possible without loss of |
|
|
716 | precision. Otherwise it will preserve the number as a string value. |
|
|
717 | |
|
|
718 | Numbers containing a fractional or exponential part will always be |
|
|
719 | represented as numeric (floating point) values, possibly at a loss of |
|
|
720 | precision. |
|
|
721 | |
|
|
722 | This might create round-tripping problems as numbers might become strings, |
|
|
723 | but as Perl is typeless there is no other way to do it. |
433 | |
724 | |
434 | =item true, false |
725 | =item true, false |
435 | |
726 | |
436 | These JSON atoms become C<0>, C<1>, respectively. Information is lost in |
727 | These JSON atoms become C<JSON::XS::true> and C<JSON::XS::false>, |
437 | this process. Future versions might represent those values differently, |
728 | respectively. They are overloaded to act almost exactly like the numbers |
438 | but they will be guarenteed to act like these integers would normally in |
729 | C<1> and C<0>. You can check whether a scalar is a JSON boolean by using |
439 | Perl. |
730 | the C<JSON::XS::is_bool> function. |
440 | |
731 | |
441 | =item null |
732 | =item null |
442 | |
733 | |
443 | A JSON null atom becomes C<undef> in Perl. |
734 | A JSON null atom becomes C<undef> in Perl. |
444 | |
735 | |
445 | =back |
736 | =back |
|
|
737 | |
446 | |
738 | |
447 | =head2 PERL -> JSON |
739 | =head2 PERL -> JSON |
448 | |
740 | |
449 | The mapping from Perl to JSON is slightly more difficult, as Perl is a |
741 | The mapping from Perl to JSON is slightly more difficult, as Perl is a |
450 | truly typeless language, so we can only guess which JSON type is meant by |
742 | truly typeless language, so we can only guess which JSON type is meant by |
… | |
… | |
473 | Other unblessed references are generally not allowed and will cause an |
765 | Other unblessed references are generally not allowed and will cause an |
474 | exception to be thrown, except for references to the integers C<0> and |
766 | exception to be thrown, except for references to the integers C<0> and |
475 | C<1>, which get turned into C<false> and C<true> atoms in JSON. You can |
767 | C<1>, which get turned into C<false> and C<true> atoms in JSON. You can |
476 | also use C<JSON::XS::false> and C<JSON::XS::true> to improve readability. |
768 | also use C<JSON::XS::false> and C<JSON::XS::true> to improve readability. |
477 | |
769 | |
478 | to_json [\0,JSON::XS::true] # yields [false,true] |
770 | encode_json [\0,JSON::XS::true] # yields [false,true] |
|
|
771 | |
|
|
772 | =item JSON::XS::true, JSON::XS::false |
|
|
773 | |
|
|
774 | These special values become JSON true and JSON false values, |
|
|
775 | respectively. You can also use C<\1> and C<\0> directly if you want. |
479 | |
776 | |
480 | =item blessed objects |
777 | =item blessed objects |
481 | |
778 | |
482 | Blessed objects are not allowed. JSON::XS currently tries to encode their |
779 | Blessed objects are not allowed. JSON::XS currently tries to encode their |
483 | underlying representation (hash- or arrayref), but this behaviour might |
780 | underlying representation (hash- or arrayref), but this behaviour might |
… | |
… | |
489 | difficult objects to encode: JSON::XS will encode undefined scalars as |
786 | difficult objects to encode: JSON::XS will encode undefined scalars as |
490 | JSON null value, scalars that have last been used in a string context |
787 | JSON null value, scalars that have last been used in a string context |
491 | before encoding as JSON strings and anything else as number value: |
788 | before encoding as JSON strings and anything else as number value: |
492 | |
789 | |
493 | # dump as number |
790 | # dump as number |
494 | to_json [2] # yields [2] |
791 | encode_json [2] # yields [2] |
495 | to_json [-3.0e17] # yields [-3e+17] |
792 | encode_json [-3.0e17] # yields [-3e+17] |
496 | my $value = 5; to_json [$value] # yields [5] |
793 | my $value = 5; encode_json [$value] # yields [5] |
497 | |
794 | |
498 | # used as string, so dump as string |
795 | # used as string, so dump as string |
499 | print $value; |
796 | print $value; |
500 | to_json [$value] # yields ["5"] |
797 | encode_json [$value] # yields ["5"] |
501 | |
798 | |
502 | # undef becomes null |
799 | # undef becomes null |
503 | to_json [undef] # yields [null] |
800 | encode_json [undef] # yields [null] |
504 | |
801 | |
505 | You can force the type to be a string by stringifying it: |
802 | You can force the type to be a JSON string by stringifying it: |
506 | |
803 | |
507 | my $x = 3.1; # some variable containing a number |
804 | my $x = 3.1; # some variable containing a number |
508 | "$x"; # stringified |
805 | "$x"; # stringified |
509 | $x .= ""; # another, more awkward way to stringify |
806 | $x .= ""; # another, more awkward way to stringify |
510 | print $x; # perl does it for you, too, quite often |
807 | print $x; # perl does it for you, too, quite often |
511 | |
808 | |
512 | You can force the type to be a number by numifying it: |
809 | You can force the type to be a JSON number by numifying it: |
513 | |
810 | |
514 | my $x = "3"; # some variable containing a string |
811 | my $x = "3"; # some variable containing a string |
515 | $x += 0; # numify it, ensuring it will be dumped as a number |
812 | $x += 0; # numify it, ensuring it will be dumped as a number |
516 | $x *= 1; # same thing, the choise is yours. |
813 | $x *= 1; # same thing, the choice is yours. |
517 | |
814 | |
518 | You can not currently output JSON booleans or force the type in other, |
815 | You can not currently force the type in other, less obscure, ways. Tell me |
519 | less obscure, ways. Tell me if you need this capability. |
816 | if you need this capability. |
520 | |
817 | |
521 | =back |
818 | =back |
522 | |
819 | |
523 | |
820 | |
524 | =head1 COMPARISON |
821 | =head1 COMPARISON |
… | |
… | |
533 | |
830 | |
534 | =item JSON 1.07 |
831 | =item JSON 1.07 |
535 | |
832 | |
536 | Slow (but very portable, as it is written in pure Perl). |
833 | Slow (but very portable, as it is written in pure Perl). |
537 | |
834 | |
538 | Undocumented/buggy Unicode handling (how JSON handles unicode values is |
835 | Undocumented/buggy Unicode handling (how JSON handles Unicode values is |
539 | undocumented. One can get far by feeding it unicode strings and doing |
836 | undocumented. One can get far by feeding it Unicode strings and doing |
540 | en-/decoding oneself, but unicode escapes are not working properly). |
837 | en-/decoding oneself, but Unicode escapes are not working properly). |
541 | |
838 | |
542 | No roundtripping (strings get clobbered if they look like numbers, e.g. |
839 | No round-tripping (strings get clobbered if they look like numbers, e.g. |
543 | the string C<2.0> will encode to C<2.0> instead of C<"2.0">, and that will |
840 | the string C<2.0> will encode to C<2.0> instead of C<"2.0">, and that will |
544 | decode into the number 2. |
841 | decode into the number 2. |
545 | |
842 | |
546 | =item JSON::PC 0.01 |
843 | =item JSON::PC 0.01 |
547 | |
844 | |
548 | Very fast. |
845 | Very fast. |
549 | |
846 | |
550 | Undocumented/buggy Unicode handling. |
847 | Undocumented/buggy Unicode handling. |
551 | |
848 | |
552 | No roundtripping. |
849 | No round-tripping. |
553 | |
850 | |
554 | Has problems handling many Perl values (e.g. regex results and other magic |
851 | Has problems handling many Perl values (e.g. regex results and other magic |
555 | values will make it croak). |
852 | values will make it croak). |
556 | |
853 | |
557 | Does not even generate valid JSON (C<{1,2}> gets converted to C<{1:2}> |
854 | Does not even generate valid JSON (C<{1,2}> gets converted to C<{1:2}> |
… | |
… | |
567 | Very inflexible (no human-readable format supported, format pretty much |
864 | Very inflexible (no human-readable format supported, format pretty much |
568 | undocumented. I need at least a format for easy reading by humans and a |
865 | undocumented. I need at least a format for easy reading by humans and a |
569 | single-line compact format for use in a protocol, and preferably a way to |
866 | single-line compact format for use in a protocol, and preferably a way to |
570 | generate ASCII-only JSON texts). |
867 | generate ASCII-only JSON texts). |
571 | |
868 | |
572 | Completely broken (and confusingly documented) Unicode handling (unicode |
869 | Completely broken (and confusingly documented) Unicode handling (Unicode |
573 | escapes are not working properly, you need to set ImplicitUnicode to |
870 | escapes are not working properly, you need to set ImplicitUnicode to |
574 | I<different> values on en- and decoding to get symmetric behaviour). |
871 | I<different> values on en- and decoding to get symmetric behaviour). |
575 | |
872 | |
576 | No roundtripping (simple cases work, but this depends on wether the scalar |
873 | No round-tripping (simple cases work, but this depends on whether the scalar |
577 | value was used in a numeric context or not). |
874 | value was used in a numeric context or not). |
578 | |
875 | |
579 | Dumping hashes may skip hash values depending on iterator state. |
876 | Dumping hashes may skip hash values depending on iterator state. |
580 | |
877 | |
581 | Unmaintained (maintainer unresponsive for many months, bugs are not |
878 | Unmaintained (maintainer unresponsive for many months, bugs are not |
582 | getting fixed). |
879 | getting fixed). |
583 | |
880 | |
584 | Does not check input for validity (i.e. will accept non-JSON input and |
881 | Does not check input for validity (i.e. will accept non-JSON input and |
585 | return "something" instead of raising an exception. This is a security |
882 | return "something" instead of raising an exception. This is a security |
586 | issue: imagine two banks transfering money between each other using |
883 | issue: imagine two banks transferring money between each other using |
587 | JSON. One bank might parse a given non-JSON request and deduct money, |
884 | JSON. One bank might parse a given non-JSON request and deduct money, |
588 | while the other might reject the transaction with a syntax error. While a |
885 | while the other might reject the transaction with a syntax error. While a |
589 | good protocol will at least recover, that is extra unnecessary work and |
886 | good protocol will at least recover, that is extra unnecessary work and |
590 | the transaction will still not succeed). |
887 | the transaction will still not succeed). |
591 | |
888 | |
592 | =item JSON::DWIW 0.04 |
889 | =item JSON::DWIW 0.04 |
593 | |
890 | |
594 | Very fast. Very natural. Very nice. |
891 | Very fast. Very natural. Very nice. |
595 | |
892 | |
596 | Undocumented unicode handling (but the best of the pack. Unicode escapes |
893 | Undocumented Unicode handling (but the best of the pack. Unicode escapes |
597 | still don't get parsed properly). |
894 | still don't get parsed properly). |
598 | |
895 | |
599 | Very inflexible. |
896 | Very inflexible. |
600 | |
897 | |
601 | No roundtripping. |
898 | No round-tripping. |
602 | |
899 | |
603 | Does not generate valid JSON texts (key strings are often unquoted, empty keys |
900 | Does not generate valid JSON texts (key strings are often unquoted, empty keys |
604 | result in nothing being output) |
901 | result in nothing being output) |
605 | |
902 | |
606 | Does not check input for validity. |
903 | Does not check input for validity. |
607 | |
904 | |
608 | =back |
905 | =back |
|
|
906 | |
|
|
907 | |
|
|
908 | =head2 JSON and YAML |
|
|
909 | |
|
|
910 | You often hear that JSON is a subset of YAML. This is, however, a mass |
|
|
911 | hysteria(*) and very far from the truth. In general, there is no way to |
|
|
912 | configure JSON::XS to output a data structure as valid YAML that works for |
|
|
913 | all cases. |
|
|
914 | |
|
|
915 | If you really must use JSON::XS to generate YAML, you should use this |
|
|
916 | algorithm (subject to change in future versions): |
|
|
917 | |
|
|
918 | my $to_yaml = JSON::XS->new->utf8->space_after (1); |
|
|
919 | my $yaml = $to_yaml->encode ($ref) . "\n"; |
|
|
920 | |
|
|
921 | This will usually generate JSON texts that also parse as valid |
|
|
922 | YAML. Please note that YAML has hardcoded limits on (simple) object key |
|
|
923 | lengths that JSON doesn't have and also has different and incompatible |
|
|
924 | unicode handling, so you should make sure that your hash keys are |
|
|
925 | noticeably shorter than the 1024 "stream characters" YAML allows and that |
|
|
926 | you do not have codepoints with values outside the Unicode BMP (basic |
|
|
927 | multilingual page). YAML also does not allow C<\/> sequences in strings |
|
|
928 | (which JSON::XS does not I<currently> generate). |
|
|
929 | |
|
|
930 | There might be other incompatibilities that I am not aware of. In general |
|
|
931 | you should not try to generate YAML with a JSON generator or vice versa, |
|
|
932 | or try to parse JSON with a YAML parser or vice versa: chances are high |
|
|
933 | that you will run into severe interoperability problems when you least |
|
|
934 | expect it. |
|
|
935 | |
|
|
936 | =over 4 |
|
|
937 | |
|
|
938 | =item (*) |
|
|
939 | |
|
|
940 | This is spread actively by the YAML team, however. For many years now they |
|
|
941 | claim YAML were a superset of JSON, even when proven otherwise. |
|
|
942 | |
|
|
943 | Even the author of this manpage was at some point accused of providing |
|
|
944 | "incorrect" information, despite the evidence presented (claims ranged |
|
|
945 | from "your documentation contains inaccurate and negative statements about |
|
|
946 | YAML" (the only negative comment is this footnote, and it didn't exist |
|
|
947 | back then; the question on which claims were inaccurate was never answered |
|
|
948 | etc.) to "the YAML spec is not up-to-date" (the *real* and suppsedly |
|
|
949 | JSON-compatible spec is apparently not currently publicly available) |
|
|
950 | to actual requests to replace this section by *incorrect* information, |
|
|
951 | suppressing information about the real problem). |
|
|
952 | |
|
|
953 | So whenever you are told that YAML was a superset of JSON, first check |
|
|
954 | wether it is really true (it might be when you check it, but it cetrainly |
|
|
955 | is not true when this was written). I would much prefer if the YAML team |
|
|
956 | would spent their time on actually making JSON compatibility a truth |
|
|
957 | (JSON, after all, has a very small and simple specification) instead of |
|
|
958 | trying to lobby/force people into reporting untruths. |
|
|
959 | |
|
|
960 | =back |
|
|
961 | |
609 | |
962 | |
610 | =head2 SPEED |
963 | =head2 SPEED |
611 | |
964 | |
612 | It seems that JSON::XS is surprisingly fast, as shown in the following |
965 | It seems that JSON::XS is surprisingly fast, as shown in the following |
613 | tables. They have been generated with the help of the C<eg/bench> program |
966 | tables. They have been generated with the help of the C<eg/bench> program |
… | |
… | |
616 | |
969 | |
617 | First comes a comparison between various modules using a very short |
970 | First comes a comparison between various modules using a very short |
618 | single-line JSON string: |
971 | single-line JSON string: |
619 | |
972 | |
620 | {"method": "handleMessage", "params": ["user1", "we were just talking"], \ |
973 | {"method": "handleMessage", "params": ["user1", "we were just talking"], \ |
621 | "id": null, [1,11,234,-5,1e5,1e7, true, false]} |
974 | "id": null, "array":[1,11,234,-5,1e5,1e7, true, false]} |
622 | |
975 | |
623 | It shows the number of encodes/decodes per second (JSON::XS uses the |
976 | It shows the number of encodes/decodes per second (JSON::XS uses |
624 | functional interface, while JSON::XS/2 uses the OO interface with |
977 | the functional interface, while JSON::XS/2 uses the OO interface |
625 | pretty-printing and hashkey sorting enabled). Higher is better: |
978 | with pretty-printing and hashkey sorting enabled, JSON::XS/3 enables |
|
|
979 | shrink). Higher is better: |
626 | |
980 | |
627 | -----------+------------+------------+ |
|
|
628 | module | encode | decode | |
981 | module | encode | decode | |
629 | -----------|------------|------------| |
982 | -----------|------------|------------| |
630 | JSON | 10597.029 | 5740.903 | |
983 | JSON 1.x | 4990.842 | 4088.813 | |
631 | JSON::DWIW | 78251.940 | 98457.840 | |
984 | JSON::DWIW | 51653.990 | 71575.154 | |
632 | JSON::PC | 70611.178 | 92794.336 | |
985 | JSON::PC | 65948.176 | 74631.744 | |
633 | JSON::Syck | 28767.517 | 38199.490 | |
986 | JSON::PP | 8931.652 | 3817.168 | |
634 | JSON::XS | 419430.400 | 265462.278 | |
987 | JSON::Syck | 24877.248 | 27776.848 | |
635 | JSON::XS/2 | 279620.267 | 265462.278 | |
|
|
636 | JSON::XS/3 | 388361.481 | 265462.278 | |
988 | JSON::XS | 388361.481 | 227951.304 | |
637 | Storable | 16294.887 | 16844.594 | |
989 | JSON::XS/2 | 227951.304 | 218453.333 | |
|
|
990 | JSON::XS/3 | 338250.323 | 218453.333 | |
|
|
991 | Storable | 16500.016 | 135300.129 | |
638 | -----------+------------+------------+ |
992 | -----------+------------+------------+ |
639 | |
993 | |
640 | That is, JSON::XS is about five times faster than JSON::DWIW on encoding, |
994 | That is, JSON::XS is about five times faster than JSON::DWIW on encoding, |
641 | about three times faster on decoding, and about fourty times faster |
995 | about three times faster on decoding, and over forty times faster |
642 | than JSON, even with pretty-printing and key sorting. It also compares |
996 | than JSON, even with pretty-printing and key sorting. It also compares |
643 | favourably to Storable for small amounts of data. |
997 | favourably to Storable for small amounts of data. |
644 | |
998 | |
645 | Using a longer test string (roughly 18KB, generated from Yahoo! Locals |
999 | Using a longer test string (roughly 18KB, generated from Yahoo! Locals |
646 | search API (http://nanoref.com/yahooapis/mgPdGg): |
1000 | search API (http://nanoref.com/yahooapis/mgPdGg): |
647 | |
1001 | |
648 | module | encode | decode | |
1002 | module | encode | decode | |
649 | -----------|------------|------------| |
1003 | -----------|------------|------------| |
650 | JSON | 254.685 | 37.665 | |
1004 | JSON 1.x | 55.260 | 34.971 | |
651 | JSON::DWIW | 1014.244 | 1087.678 | |
1005 | JSON::DWIW | 825.228 | 1082.513 | |
652 | JSON::PC | 3602.116 | 2307.352 | |
1006 | JSON::PC | 3571.444 | 2394.829 | |
653 | JSON::Syck | 558.035 | 776.263 | |
1007 | JSON::PP | 210.987 | 32.574 | |
654 | JSON::XS | 5747.196 | 3543.684 | |
1008 | JSON::Syck | 552.551 | 787.544 | |
655 | JSON::XS/2 | 3968.121 | 3589.170 | |
1009 | JSON::XS | 5780.463 | 4854.519 | |
656 | JSON::XS/3 | 6105.246 | 3561.134 | |
1010 | JSON::XS/2 | 3869.998 | 4798.975 | |
657 | Storable | 4456.337 | 5320.020 | |
1011 | JSON::XS/3 | 5862.880 | 4798.975 | |
|
|
1012 | Storable | 4445.002 | 5235.027 | |
658 | -----------+------------+------------+ |
1013 | -----------+------------+------------+ |
659 | |
1014 | |
660 | Again, JSON::XS leads by far. |
1015 | Again, JSON::XS leads by far (except for Storable which non-surprisingly |
|
|
1016 | decodes faster). |
661 | |
1017 | |
662 | On large strings containing lots of high unicode characters, some modules |
1018 | On large strings containing lots of high Unicode characters, some modules |
663 | (such as JSON::PC) seem to decode faster than JSON::XS, but the result |
1019 | (such as JSON::PC) seem to decode faster than JSON::XS, but the result |
664 | will be broken due to missing (or wrong) unicode handling. Others refuse |
1020 | will be broken due to missing (or wrong) Unicode handling. Others refuse |
665 | to decode or encode properly, so it was impossible to prepare a fair |
1021 | to decode or encode properly, so it was impossible to prepare a fair |
666 | comparison table for that case. |
1022 | comparison table for that case. |
667 | |
1023 | |
668 | |
1024 | |
669 | =head1 SECURITY CONSIDERATIONS |
1025 | =head1 SECURITY CONSIDERATIONS |
… | |
… | |
675 | any buffer overflows. Obviously, this module should ensure that and I am |
1031 | any buffer overflows. Obviously, this module should ensure that and I am |
676 | trying hard on making that true, but you never know. |
1032 | trying hard on making that true, but you never know. |
677 | |
1033 | |
678 | Second, you need to avoid resource-starving attacks. That means you should |
1034 | Second, you need to avoid resource-starving attacks. That means you should |
679 | limit the size of JSON texts you accept, or make sure then when your |
1035 | limit the size of JSON texts you accept, or make sure then when your |
680 | resources run out, thats just fine (e.g. by using a separate process that |
1036 | resources run out, that's just fine (e.g. by using a separate process that |
681 | can crash safely). The size of a JSON text in octets or characters is |
1037 | can crash safely). The size of a JSON text in octets or characters is |
682 | usually a good indication of the size of the resources required to decode |
1038 | usually a good indication of the size of the resources required to decode |
683 | it into a Perl structure. |
1039 | it into a Perl structure. While JSON::XS can check the size of the JSON |
|
|
1040 | text, it might be too late when you already have it in memory, so you |
|
|
1041 | might want to check the size before you accept the string. |
684 | |
1042 | |
685 | Third, JSON::XS recurses using the C stack when decoding objects and |
1043 | Third, JSON::XS recurses using the C stack when decoding objects and |
686 | arrays. The C stack is a limited resource: for instance, on my amd64 |
1044 | arrays. The C stack is a limited resource: for instance, on my amd64 |
687 | machine with 8MB of stack size I can decode around 180k nested arrays but |
1045 | machine with 8MB of stack size I can decode around 180k nested arrays but |
688 | only 14k nested JSON objects (due to perl itself recursing deeply on croak |
1046 | only 14k nested JSON objects (due to perl itself recursing deeply on croak |
689 | to free the temporary). If that is exceeded, the program crashes. to be |
1047 | to free the temporary). If that is exceeded, the program crashes. To be |
690 | conservative, the default nesting limit is set to 512. If your process |
1048 | conservative, the default nesting limit is set to 512. If your process |
691 | has a smaller stack, you should adjust this setting accordingly with the |
1049 | has a smaller stack, you should adjust this setting accordingly with the |
692 | C<max_depth> method. |
1050 | C<max_depth> method. |
693 | |
1051 | |
694 | And last but least, something else could bomb you that I forgot to think |
1052 | And last but least, something else could bomb you that I forgot to think |
695 | of. In that case, you get to keep the pieces. I am always open for hints, |
1053 | of. In that case, you get to keep the pieces. I am always open for hints, |
696 | though... |
1054 | though... |
|
|
1055 | |
|
|
1056 | If you are using JSON::XS to return packets to consumption |
|
|
1057 | by JavaScript scripts in a browser you should have a look at |
|
|
1058 | L<http://jpsykes.com/47/practical-csrf-and-json-security> to see whether |
|
|
1059 | you are vulnerable to some common attack vectors (which really are browser |
|
|
1060 | design bugs, but it is still you who will have to deal with it, as major |
|
|
1061 | browser developers care only for features, not about getting security |
|
|
1062 | right). |
|
|
1063 | |
|
|
1064 | |
|
|
1065 | =head1 THREADS |
|
|
1066 | |
|
|
1067 | This module is I<not> guaranteed to be thread safe and there are no |
|
|
1068 | plans to change this until Perl gets thread support (as opposed to the |
|
|
1069 | horribly slow so-called "threads" which are simply slow and bloated |
|
|
1070 | process simulations - use fork, its I<much> faster, cheaper, better). |
|
|
1071 | |
|
|
1072 | (It might actually work, but you have been warned). |
697 | |
1073 | |
698 | |
1074 | |
699 | =head1 BUGS |
1075 | =head1 BUGS |
700 | |
1076 | |
701 | While the goal of this module is to be correct, that unfortunately does |
1077 | While the goal of this module is to be correct, that unfortunately does |
702 | not mean its bug-free, only that I think its design is bug-free. It is |
1078 | not mean its bug-free, only that I think its design is bug-free. It is |
703 | still relatively early in its development. If you keep reporting bugs they |
1079 | still relatively early in its development. If you keep reporting bugs they |
704 | will be fixed swiftly, though. |
1080 | will be fixed swiftly, though. |
705 | |
1081 | |
|
|
1082 | Please refrain from using rt.cpan.org or any other bug reporting |
|
|
1083 | service. I put the contact address into my modules for a reason. |
|
|
1084 | |
706 | =cut |
1085 | =cut |
707 | |
1086 | |
|
|
1087 | our $true = do { bless \(my $dummy = 1), "JSON::XS::Boolean" }; |
|
|
1088 | our $false = do { bless \(my $dummy = 0), "JSON::XS::Boolean" }; |
|
|
1089 | |
708 | sub true() { \1 } |
1090 | sub true() { $true } |
709 | sub false() { \0 } |
1091 | sub false() { $false } |
|
|
1092 | |
|
|
1093 | sub is_bool($) { |
|
|
1094 | UNIVERSAL::isa $_[0], "JSON::XS::Boolean" |
|
|
1095 | # or UNIVERSAL::isa $_[0], "JSON::Literal" |
|
|
1096 | } |
|
|
1097 | |
|
|
1098 | XSLoader::load "JSON::XS", $VERSION; |
|
|
1099 | |
|
|
1100 | package JSON::XS::Boolean; |
|
|
1101 | |
|
|
1102 | use overload |
|
|
1103 | "0+" => sub { ${$_[0]} }, |
|
|
1104 | "++" => sub { $_[0] = ${$_[0]} + 1 }, |
|
|
1105 | "--" => sub { $_[0] = ${$_[0]} - 1 }, |
|
|
1106 | fallback => 1; |
710 | |
1107 | |
711 | 1; |
1108 | 1; |
712 | |
1109 | |
713 | =head1 AUTHOR |
1110 | =head1 AUTHOR |
714 | |
1111 | |