… | |
… | |
26 | substr $many_cbor_strings, 0, $length, ""; # remove decoded cbor string |
26 | substr $many_cbor_strings, 0, $length, ""; # remove decoded cbor string |
27 | } |
27 | } |
28 | |
28 | |
29 | =head1 DESCRIPTION |
29 | =head1 DESCRIPTION |
30 | |
30 | |
31 | WARNING! THIS IS A PRE-ALPHA RELEASE! IT WILL CRASH, CORRUPT YOUR DATA |
|
|
32 | AND EAT YOUR CHILDREN! (Actually, apart from being untested and a bit |
|
|
33 | feature-limited, it might already be useful). |
|
|
34 | |
|
|
35 | This module converts Perl data structures to the Concise Binary Object |
31 | This module converts Perl data structures to the Concise Binary Object |
36 | Representation (CBOR) and vice versa. CBOR is a fast binary serialisation |
32 | Representation (CBOR) and vice versa. CBOR is a fast binary serialisation |
37 | format that aims to use a superset of the JSON data model, i.e. when you |
33 | format that aims to use an (almost) superset of the JSON data model, i.e. |
38 | can represent something in JSON, you should be able to represent it in |
34 | when you can represent something useful in JSON, you should be able to |
39 | CBOR. |
35 | represent it in CBOR. |
40 | |
36 | |
41 | This makes it a faster and more compact binary alternative to JSON, with |
37 | In short, CBOR is a faster and quite compact binary alternative to JSON, |
42 | the added ability of supporting serialising of perl objects. |
38 | with the added ability of supporting serialisation of Perl objects. (JSON |
|
|
39 | often compresses better than CBOR though, so if you plan to compress the |
|
|
40 | data later and speed is less important you might want to compare both |
|
|
41 | formats first). |
|
|
42 | |
|
|
43 | To give you a general idea about speed, with texts in the megabyte range, |
|
|
44 | C<CBOR::XS> usually encodes roughly twice as fast as L<Storable> or |
|
|
45 | L<JSON::XS> and decodes about 15%-30% faster than those. The shorter the |
|
|
46 | data, the worse L<Storable> performs in comparison. |
|
|
47 | |
|
|
48 | Regarding compactness, C<CBOR::XS>-encoded data structures are usually |
|
|
49 | about 20% smaller than the same data encoded as (compact) JSON or |
|
|
50 | L<Storable>. |
|
|
51 | |
|
|
52 | In addition to the core CBOR data format, this module implements a |
|
|
53 | number of extensions, to support cyclic and shared data structures |
|
|
54 | (see C<allow_sharing> and C<allow_cycles>), string deduplication (see |
|
|
55 | C<pack_strings>) and scalar references (always enabled). |
43 | |
56 | |
44 | The primary goal of this module is to be I<correct> and the secondary goal |
57 | The primary goal of this module is to be I<correct> and the secondary goal |
45 | is to be I<fast>. To reach the latter goal it was written in C. |
58 | is to be I<fast>. To reach the latter goal it was written in C. |
46 | |
59 | |
47 | See MAPPING, below, on how CBOR::XS maps perl values to CBOR values and |
60 | See MAPPING, below, on how CBOR::XS maps perl values to CBOR values and |
… | |
… | |
51 | |
64 | |
52 | package CBOR::XS; |
65 | package CBOR::XS; |
53 | |
66 | |
54 | use common::sense; |
67 | use common::sense; |
55 | |
68 | |
56 | our $VERSION = 0.03; |
69 | our $VERSION = 1.41; |
57 | our @ISA = qw(Exporter); |
70 | our @ISA = qw(Exporter); |
58 | |
71 | |
59 | our @EXPORT = qw(encode_cbor decode_cbor); |
72 | our @EXPORT = qw(encode_cbor decode_cbor); |
60 | |
73 | |
61 | use Exporter; |
74 | use Exporter; |
… | |
… | |
98 | strings. All boolean flags described below are by default I<disabled>. |
111 | strings. All boolean flags described below are by default I<disabled>. |
99 | |
112 | |
100 | The mutators for flags all return the CBOR object again and thus calls can |
113 | The mutators for flags all return the CBOR object again and thus calls can |
101 | be chained: |
114 | be chained: |
102 | |
115 | |
103 | #TODO |
|
|
104 | my $cbor = CBOR::XS->new->encode ({a => [1,2]}); |
116 | my $cbor = CBOR::XS->new->encode ({a => [1,2]}); |
105 | |
117 | |
106 | =item $cbor = $cbor->max_depth ([$maximum_nesting_depth]) |
118 | =item $cbor = $cbor->max_depth ([$maximum_nesting_depth]) |
107 | |
119 | |
108 | =item $max_depth = $cbor->get_max_depth |
120 | =item $max_depth = $cbor->get_max_depth |
… | |
… | |
142 | If no argument is given, the limit check will be deactivated (same as when |
154 | If no argument is given, the limit check will be deactivated (same as when |
143 | C<0> is specified). |
155 | C<0> is specified). |
144 | |
156 | |
145 | See SECURITY CONSIDERATIONS, below, for more info on why this is useful. |
157 | See SECURITY CONSIDERATIONS, below, for more info on why this is useful. |
146 | |
158 | |
|
|
159 | =item $cbor = $cbor->allow_unknown ([$enable]) |
|
|
160 | |
|
|
161 | =item $enabled = $cbor->get_allow_unknown |
|
|
162 | |
|
|
163 | If C<$enable> is true (or missing), then C<encode> will I<not> throw an |
|
|
164 | exception when it encounters values it cannot represent in CBOR (for |
|
|
165 | example, filehandles) but instead will encode a CBOR C<error> value. |
|
|
166 | |
|
|
167 | If C<$enable> is false (the default), then C<encode> will throw an |
|
|
168 | exception when it encounters anything it cannot encode as CBOR. |
|
|
169 | |
|
|
170 | This option does not affect C<decode> in any way, and it is recommended to |
|
|
171 | leave it off unless you know your communications partner. |
|
|
172 | |
|
|
173 | =item $cbor = $cbor->allow_sharing ([$enable]) |
|
|
174 | |
|
|
175 | =item $enabled = $cbor->get_allow_sharing |
|
|
176 | |
|
|
177 | If C<$enable> is true (or missing), then C<encode> will not double-encode |
|
|
178 | values that have been referenced before (e.g. when the same object, such |
|
|
179 | as an array, is referenced multiple times), but instead will emit a |
|
|
180 | reference to the earlier value. |
|
|
181 | |
|
|
182 | This means that such values will only be encoded once, and will not result |
|
|
183 | in a deep cloning of the value on decode, in decoders supporting the value |
|
|
184 | sharing extension. This also makes it possible to encode cyclic data |
|
|
185 | structures (which need C<allow_cycles> to ne enabled to be decoded by this |
|
|
186 | module). |
|
|
187 | |
|
|
188 | It is recommended to leave it off unless you know your |
|
|
189 | communication partner supports the value sharing extensions to CBOR |
|
|
190 | (L<http://cbor.schmorp.de/value-sharing>), as without decoder support, the |
|
|
191 | resulting data structure might be unusable. |
|
|
192 | |
|
|
193 | Detecting shared values incurs a runtime overhead when values are encoded |
|
|
194 | that have a reference counter large than one, and might unnecessarily |
|
|
195 | increase the encoded size, as potentially shared values are encode as |
|
|
196 | shareable whether or not they are actually shared. |
|
|
197 | |
|
|
198 | At the moment, only targets of references can be shared (e.g. scalars, |
|
|
199 | arrays or hashes pointed to by a reference). Weirder constructs, such as |
|
|
200 | an array with multiple "copies" of the I<same> string, which are hard but |
|
|
201 | not impossible to create in Perl, are not supported (this is the same as |
|
|
202 | with L<Storable>). |
|
|
203 | |
|
|
204 | If C<$enable> is false (the default), then C<encode> will encode shared |
|
|
205 | data structures repeatedly, unsharing them in the process. Cyclic data |
|
|
206 | structures cannot be encoded in this mode. |
|
|
207 | |
|
|
208 | This option does not affect C<decode> in any way - shared values and |
|
|
209 | references will always be decoded properly if present. |
|
|
210 | |
|
|
211 | =item $cbor = $cbor->allow_cycles ([$enable]) |
|
|
212 | |
|
|
213 | =item $enabled = $cbor->get_allow_cycles |
|
|
214 | |
|
|
215 | If C<$enable> is true (or missing), then C<decode> will happily decode |
|
|
216 | self-referential (cyclic) data structures. By default these will not be |
|
|
217 | decoded, as they need manual cleanup to avoid memory leaks, so code that |
|
|
218 | isn't prepared for this will not leak memory. |
|
|
219 | |
|
|
220 | If C<$enable> is false (the default), then C<decode> will throw an error |
|
|
221 | when it encounters a self-referential/cyclic data structure. |
|
|
222 | |
|
|
223 | FUTURE DIRECTION: the motivation behind this option is to avoid I<real> |
|
|
224 | cycles - future versions of this module might chose to decode cyclic data |
|
|
225 | structures using weak references when this option is off, instead of |
|
|
226 | throwing an error. |
|
|
227 | |
|
|
228 | This option does not affect C<encode> in any way - shared values and |
|
|
229 | references will always be encoded properly if present. |
|
|
230 | |
|
|
231 | =item $cbor = $cbor->pack_strings ([$enable]) |
|
|
232 | |
|
|
233 | =item $enabled = $cbor->get_pack_strings |
|
|
234 | |
|
|
235 | If C<$enable> is true (or missing), then C<encode> will try not to encode |
|
|
236 | the same string twice, but will instead encode a reference to the string |
|
|
237 | instead. Depending on your data format, this can save a lot of space, but |
|
|
238 | also results in a very large runtime overhead (expect encoding times to be |
|
|
239 | 2-4 times as high as without). |
|
|
240 | |
|
|
241 | It is recommended to leave it off unless you know your |
|
|
242 | communications partner supports the stringref extension to CBOR |
|
|
243 | (L<http://cbor.schmorp.de/stringref>), as without decoder support, the |
|
|
244 | resulting data structure might not be usable. |
|
|
245 | |
|
|
246 | If C<$enable> is false (the default), then C<encode> will encode strings |
|
|
247 | the standard CBOR way. |
|
|
248 | |
|
|
249 | This option does not affect C<decode> in any way - string references will |
|
|
250 | always be decoded properly if present. |
|
|
251 | |
|
|
252 | =item $cbor = $cbor->validate_utf8 ([$enable]) |
|
|
253 | |
|
|
254 | =item $enabled = $cbor->get_validate_utf8 |
|
|
255 | |
|
|
256 | If C<$enable> is true (or missing), then C<decode> will validate that |
|
|
257 | elements (text strings) containing UTF-8 data in fact contain valid UTF-8 |
|
|
258 | data (instead of blindly accepting it). This validation obviously takes |
|
|
259 | extra time during decoding. |
|
|
260 | |
|
|
261 | The concept of "valid UTF-8" used is perl's concept, which is a superset |
|
|
262 | of the official UTF-8. |
|
|
263 | |
|
|
264 | If C<$enable> is false (the default), then C<decode> will blindly accept |
|
|
265 | UTF-8 data, marking them as valid UTF-8 in the resulting data structure |
|
|
266 | regardless of whether thats true or not. |
|
|
267 | |
|
|
268 | Perl isn't too happy about corrupted UTF-8 in strings, but should |
|
|
269 | generally not crash or do similarly evil things. Extensions might be not |
|
|
270 | so forgiving, so it's recommended to turn on this setting if you receive |
|
|
271 | untrusted CBOR. |
|
|
272 | |
|
|
273 | This option does not affect C<encode> in any way - strings that are |
|
|
274 | supposedly valid UTF-8 will simply be dumped into the resulting CBOR |
|
|
275 | string without checking whether that is, in fact, true or not. |
|
|
276 | |
|
|
277 | =item $cbor = $cbor->filter ([$cb->($tag, $value)]) |
|
|
278 | |
|
|
279 | =item $cb_or_undef = $cbor->get_filter |
|
|
280 | |
|
|
281 | Sets or replaces the tagged value decoding filter (when C<$cb> is |
|
|
282 | specified) or clears the filter (if no argument or C<undef> is provided). |
|
|
283 | |
|
|
284 | The filter callback is called only during decoding, when a non-enforced |
|
|
285 | tagged value has been decoded (see L<TAG HANDLING AND EXTENSIONS> for a |
|
|
286 | list of enforced tags). For specific tags, it's often better to provide a |
|
|
287 | default converter using the C<%CBOR::XS::FILTER> hash (see below). |
|
|
288 | |
|
|
289 | The first argument is the numerical tag, the second is the (decoded) value |
|
|
290 | that has been tagged. |
|
|
291 | |
|
|
292 | The filter function should return either exactly one value, which will |
|
|
293 | replace the tagged value in the decoded data structure, or no values, |
|
|
294 | which will result in default handling, which currently means the decoder |
|
|
295 | creates a C<CBOR::XS::Tagged> object to hold the tag and the value. |
|
|
296 | |
|
|
297 | When the filter is cleared (the default state), the default filter |
|
|
298 | function, C<CBOR::XS::default_filter>, is used. This function simply looks |
|
|
299 | up the tag in the C<%CBOR::XS::FILTER> hash. If an entry exists it must be |
|
|
300 | a code reference that is called with tag and value, and is responsible for |
|
|
301 | decoding the value. If no entry exists, it returns no values. |
|
|
302 | |
|
|
303 | Example: decode all tags not handled internally into C<CBOR::XS::Tagged> |
|
|
304 | objects, with no other special handling (useful when working with |
|
|
305 | potentially "unsafe" CBOR data). |
|
|
306 | |
|
|
307 | CBOR::XS->new->filter (sub { })->decode ($cbor_data); |
|
|
308 | |
|
|
309 | Example: provide a global filter for tag 1347375694, converting the value |
|
|
310 | into some string form. |
|
|
311 | |
|
|
312 | $CBOR::XS::FILTER{1347375694} = sub { |
|
|
313 | my ($tag, $value); |
|
|
314 | |
|
|
315 | "tag 1347375694 value $value" |
|
|
316 | }; |
|
|
317 | |
147 | =item $cbor_data = $cbor->encode ($perl_scalar) |
318 | =item $cbor_data = $cbor->encode ($perl_scalar) |
148 | |
319 | |
149 | Converts the given Perl data structure (a scalar value) to its CBOR |
320 | Converts the given Perl data structure (a scalar value) to its CBOR |
150 | representation. |
321 | representation. |
151 | |
322 | |
… | |
… | |
164 | and you need to know where the first CBOR string ends amd the next one |
335 | and you need to know where the first CBOR string ends amd the next one |
165 | starts. |
336 | starts. |
166 | |
337 | |
167 | CBOR::XS->new->decode_prefix ("......") |
338 | CBOR::XS->new->decode_prefix ("......") |
168 | => ("...", 3) |
339 | => ("...", 3) |
|
|
340 | |
|
|
341 | =back |
|
|
342 | |
|
|
343 | =head2 INCREMENTAL PARSING |
|
|
344 | |
|
|
345 | In some cases, there is the need for incremental parsing of JSON |
|
|
346 | texts. While this module always has to keep both CBOR text and resulting |
|
|
347 | Perl data structure in memory at one time, it does allow you to parse a |
|
|
348 | CBOR stream incrementally, using a similar to using "decode_prefix" to see |
|
|
349 | if a full CBOR object is available, but is much more efficient. |
|
|
350 | |
|
|
351 | It basically works by parsing as much of a CBOR string as possible - if |
|
|
352 | the CBOR data is not complete yet, the pasrer will remember where it was, |
|
|
353 | to be able to restart when more data has been accumulated. Once enough |
|
|
354 | data is available to either decode a complete CBOR value or raise an |
|
|
355 | error, a real decode will be attempted. |
|
|
356 | |
|
|
357 | A typical use case would be a network protocol that consists of sending |
|
|
358 | and receiving CBOR-encoded messages. The solution that works with CBOR and |
|
|
359 | about anything else is by prepending a length to every CBOR value, so the |
|
|
360 | receiver knows how many octets to read. More compact (and slightly slower) |
|
|
361 | would be to just send CBOR values back-to-back, as C<CBOR::XS> knows where |
|
|
362 | a CBOR value ends, and doesn't need an explicit length. |
|
|
363 | |
|
|
364 | The following methods help with this: |
|
|
365 | |
|
|
366 | =over 4 |
|
|
367 | |
|
|
368 | =item @decoded = $cbor->incr_parse ($buffer) |
|
|
369 | |
|
|
370 | This method attempts to decode exactly one CBOR value from the beginning |
|
|
371 | of the given C<$buffer>. The value is removed from the C<$buffer> on |
|
|
372 | success. When C<$buffer> doesn't contain a complete value yet, it returns |
|
|
373 | nothing. Finally, when the C<$buffer> doesn't start with something |
|
|
374 | that could ever be a valid CBOR value, it raises an exception, just as |
|
|
375 | C<decode> would. In the latter case the decoder state is undefined and |
|
|
376 | must be reset before being able to parse further. |
|
|
377 | |
|
|
378 | This method modifies the C<$buffer> in place. When no CBOR value can be |
|
|
379 | decoded, the decoder stores the current string offset. On the next call, |
|
|
380 | continues decoding at the place where it stopped before. For this to make |
|
|
381 | sense, the C<$buffer> must begin with the same octets as on previous |
|
|
382 | unsuccessful calls. |
|
|
383 | |
|
|
384 | You can call this method in scalar context, in which case it either |
|
|
385 | returns a decoded value or C<undef>. This makes it impossible to |
|
|
386 | distinguish between CBOR null values (which decode to C<undef>) and an |
|
|
387 | unsuccessful decode, which is often acceptable. |
|
|
388 | |
|
|
389 | =item @decoded = $cbor->incr_parse_multiple ($buffer) |
|
|
390 | |
|
|
391 | Same as C<incr_parse>, but attempts to decode as many CBOR values as |
|
|
392 | possible in one go, instead of at most one. Calls to C<incr_parse> and |
|
|
393 | C<incr_parse_multiple> can be interleaved. |
|
|
394 | |
|
|
395 | =item $cbor->incr_reset |
|
|
396 | |
|
|
397 | Resets the incremental decoder. This throws away any saved state, so that |
|
|
398 | subsequent calls to C<incr_parse> or C<incr_parse_multiple> start to parse |
|
|
399 | a new CBOR value from the beginning of the C<$buffer> again. |
|
|
400 | |
|
|
401 | This method can be caled at any time, but it I<must> be called if you want |
|
|
402 | to change your C<$buffer> or there was a decoding error and you want to |
|
|
403 | reuse the C<$cbor> object for future incremental parsings. |
169 | |
404 | |
170 | =back |
405 | =back |
171 | |
406 | |
172 | |
407 | |
173 | =head1 MAPPING |
408 | =head1 MAPPING |
… | |
… | |
191 | CBOR integers become (numeric) perl scalars. On perls without 64 bit |
426 | CBOR integers become (numeric) perl scalars. On perls without 64 bit |
192 | support, 64 bit integers will be truncated or otherwise corrupted. |
427 | support, 64 bit integers will be truncated or otherwise corrupted. |
193 | |
428 | |
194 | =item byte strings |
429 | =item byte strings |
195 | |
430 | |
196 | Byte strings will become octet strings in Perl (the byte values 0..255 |
431 | Byte strings will become octet strings in Perl (the Byte values 0..255 |
197 | will simply become characters of the same value in Perl). |
432 | will simply become characters of the same value in Perl). |
198 | |
433 | |
199 | =item UTF-8 strings |
434 | =item UTF-8 strings |
200 | |
435 | |
201 | UTF-8 strings in CBOR will be decoded, i.e. the UTF-8 octets will be |
436 | UTF-8 strings in CBOR will be decoded, i.e. the UTF-8 octets will be |
… | |
… | |
219 | C<Types:Serialiser::false> and C<Types::Serialiser::error>, |
454 | C<Types:Serialiser::false> and C<Types::Serialiser::error>, |
220 | respectively. They are overloaded to act almost exactly like the numbers |
455 | respectively. They are overloaded to act almost exactly like the numbers |
221 | C<1> and C<0> (for true and false) or to throw an exception on access (for |
456 | C<1> and C<0> (for true and false) or to throw an exception on access (for |
222 | error). See the L<Types::Serialiser> manpage for details. |
457 | error). See the L<Types::Serialiser> manpage for details. |
223 | |
458 | |
224 | =item CBOR tag 256 (perl object) |
459 | =item tagged values |
225 | |
460 | |
226 | The tag value C<256> (TODO: pending iana registration) will be used |
|
|
227 | to deserialise a Perl object serialised with C<FREEZE>. See "OBJECT |
|
|
228 | SERIALISATION", below, for details. |
|
|
229 | |
|
|
230 | =item CBOR tag 55799 (magic header) |
|
|
231 | |
|
|
232 | The tag 55799 is ignored (this tag implements the magic header). |
|
|
233 | |
|
|
234 | =item other CBOR tags |
|
|
235 | |
|
|
236 | Tagged items consists of a numeric tag and another CBOR value. Tags not |
461 | Tagged items consists of a numeric tag and another CBOR value. |
237 | handled internally are currently converted into a L<CBOR::XS::Tagged> |
|
|
238 | object, which is simply a blessed array reference consisting of the |
|
|
239 | numeric tag value followed by the (decoded) CBOR value. |
|
|
240 | |
462 | |
241 | In the future, support for user-supplied conversions might get added. |
463 | See L<TAG HANDLING AND EXTENSIONS> and the description of C<< ->filter >> |
|
|
464 | for details on which tags are handled how. |
242 | |
465 | |
243 | =item anything else |
466 | =item anything else |
244 | |
467 | |
245 | Anything else (e.g. unsupported simple values) will raise a decoding |
468 | Anything else (e.g. unsupported simple values) will raise a decoding |
246 | error. |
469 | error. |
… | |
… | |
249 | |
472 | |
250 | |
473 | |
251 | =head2 PERL -> CBOR |
474 | =head2 PERL -> CBOR |
252 | |
475 | |
253 | The mapping from Perl to CBOR is slightly more difficult, as Perl is a |
476 | The mapping from Perl to CBOR is slightly more difficult, as Perl is a |
254 | truly typeless language, so we can only guess which CBOR type is meant by |
477 | typeless language. That means this module can only guess which CBOR type |
255 | a Perl value. |
478 | is meant by a perl value. |
256 | |
479 | |
257 | =over 4 |
480 | =over 4 |
258 | |
481 | |
259 | =item hash references |
482 | =item hash references |
260 | |
483 | |
261 | Perl hash references become CBOR maps. As there is no inherent ordering in |
484 | Perl hash references become CBOR maps. As there is no inherent ordering in |
262 | hash keys (or CBOR maps), they will usually be encoded in a pseudo-random |
485 | hash keys (or CBOR maps), they will usually be encoded in a pseudo-random |
263 | order. |
486 | order. This order can be different each time a hahs is encoded. |
264 | |
487 | |
265 | Currently, tied hashes will use the indefinite-length format, while normal |
488 | Currently, tied hashes will use the indefinite-length format, while normal |
266 | hashes will use the fixed-length format. |
489 | hashes will use the fixed-length format. |
267 | |
490 | |
268 | =item array references |
491 | =item array references |
269 | |
492 | |
270 | Perl array references become fixed-length CBOR arrays. |
493 | Perl array references become fixed-length CBOR arrays. |
271 | |
494 | |
272 | =item other references |
495 | =item other references |
273 | |
496 | |
274 | Other unblessed references are generally not allowed and will cause an |
497 | Other unblessed references will be represented using |
275 | exception to be thrown, except for references to the integers C<0> and |
498 | the indirection tag extension (tag value C<22098>, |
276 | C<1>, which get turned into false and true in CBOR. |
499 | L<http://cbor.schmorp.de/indirection>). CBOR decoders are guaranteed |
|
|
500 | to be able to decode these values somehow, by either "doing the right |
|
|
501 | thing", decoding into a generic tagged object, simply ignoring the tag, or |
|
|
502 | something else. |
277 | |
503 | |
278 | =item CBOR::XS::Tagged objects |
504 | =item CBOR::XS::Tagged objects |
279 | |
505 | |
280 | Objects of this type must be arrays consisting of a single C<[tag, value]> |
506 | Objects of this type must be arrays consisting of a single C<[tag, value]> |
281 | pair. The (numerical) tag will be encoded as a CBOR tag, the value will be |
507 | pair. The (numerical) tag will be encoded as a CBOR tag, the value will |
282 | encoded as appropriate for the value. |
508 | be encoded as appropriate for the value. You must use C<CBOR::XS::tag> to |
|
|
509 | create such objects. |
283 | |
510 | |
284 | =item Types::Serialiser::true, Types::Serialiser::false, Types::Serialiser::error |
511 | =item Types::Serialiser::true, Types::Serialiser::false, Types::Serialiser::error |
285 | |
512 | |
286 | These special values become CBOR true, CBOR false and CBOR undefined |
513 | These special values become CBOR true, CBOR false and CBOR undefined |
287 | values, respectively. You can also use C<\1>, C<\0> and C<\undef> directly |
514 | values, respectively. You can also use C<\1>, C<\0> and C<\undef> directly |
288 | if you want. |
515 | if you want. |
289 | |
516 | |
290 | =item other blessed objects |
517 | =item other blessed objects |
291 | |
518 | |
292 | Other blessed objects are serialised via C<TO_CBOR> or C<FREEZE>. See |
519 | Other blessed objects are serialised via C<TO_CBOR> or C<FREEZE>. See |
293 | "OBJECT SERIALISATION", below, for details. |
520 | L<TAG HANDLING AND EXTENSIONS> for specific classes handled by this |
|
|
521 | module, and L<OBJECT SERIALISATION> for generic object serialisation. |
294 | |
522 | |
295 | =item simple scalars |
523 | =item simple scalars |
296 | |
524 | |
297 | TODO |
|
|
298 | Simple Perl scalars (any scalar that is not a reference) are the most |
525 | Simple Perl scalars (any scalar that is not a reference) are the most |
299 | difficult objects to encode: CBOR::XS will encode undefined scalars as |
526 | difficult objects to encode: CBOR::XS will encode undefined scalars as |
300 | CBOR null values, scalars that have last been used in a string context |
527 | CBOR null values, scalars that have last been used in a string context |
301 | before encoding as CBOR strings, and anything else as number value: |
528 | before encoding as CBOR strings, and anything else as number value: |
302 | |
529 | |
303 | # dump as number |
530 | # dump as number |
304 | encode_cbor [2] # yields [2] |
531 | encode_cbor [2] # yields [2] |
305 | encode_cbor [-3.0e17] # yields [-3e+17] |
532 | encode_cbor [-3.0e17] # yields [-3e+17] |
306 | my $value = 5; encode_cbor [$value] # yields [5] |
533 | my $value = 5; encode_cbor [$value] # yields [5] |
307 | |
534 | |
308 | # used as string, so dump as string |
535 | # used as string, so dump as string (either byte or text) |
309 | print $value; |
536 | print $value; |
310 | encode_cbor [$value] # yields ["5"] |
537 | encode_cbor [$value] # yields ["5"] |
311 | |
538 | |
312 | # undef becomes null |
539 | # undef becomes null |
313 | encode_cbor [undef] # yields [null] |
540 | encode_cbor [undef] # yields [null] |
… | |
… | |
316 | |
543 | |
317 | my $x = 3.1; # some variable containing a number |
544 | my $x = 3.1; # some variable containing a number |
318 | "$x"; # stringified |
545 | "$x"; # stringified |
319 | $x .= ""; # another, more awkward way to stringify |
546 | $x .= ""; # another, more awkward way to stringify |
320 | print $x; # perl does it for you, too, quite often |
547 | print $x; # perl does it for you, too, quite often |
|
|
548 | |
|
|
549 | You can force whether a string ie encoded as byte or text string by using |
|
|
550 | C<utf8::upgrade> and C<utf8::downgrade>): |
|
|
551 | |
|
|
552 | utf8::upgrade $x; # encode $x as text string |
|
|
553 | utf8::downgrade $x; # encode $x as byte string |
|
|
554 | |
|
|
555 | Perl doesn't define what operations up- and downgrade strings, so if the |
|
|
556 | difference between byte and text is important, you should up- or downgrade |
|
|
557 | your string as late as possible before encoding. |
321 | |
558 | |
322 | You can force the type to be a CBOR number by numifying it: |
559 | You can force the type to be a CBOR number by numifying it: |
323 | |
560 | |
324 | my $x = "3"; # some variable containing a string |
561 | my $x = "3"; # some variable containing a string |
325 | $x += 0; # numify it, ensuring it will be dumped as a number |
562 | $x += 0; # numify it, ensuring it will be dumped as a number |
… | |
… | |
338 | |
575 | |
339 | =back |
576 | =back |
340 | |
577 | |
341 | =head2 OBJECT SERIALISATION |
578 | =head2 OBJECT SERIALISATION |
342 | |
579 | |
|
|
580 | This module implements both a CBOR-specific and the generic |
|
|
581 | L<Types::Serialier> object serialisation protocol. The following |
|
|
582 | subsections explain both methods. |
|
|
583 | |
|
|
584 | =head3 ENCODING |
|
|
585 | |
343 | This module knows two way to serialise a Perl object: The CBOR-specific |
586 | This module knows two way to serialise a Perl object: The CBOR-specific |
344 | way, and the generic way. |
587 | way, and the generic way. |
345 | |
588 | |
346 | Whenever the encoder encounters a Perl object that it cnanot serialise |
589 | Whenever the encoder encounters a Perl object that it cannot serialise |
347 | directly (most of them), it will first look up the C<TO_CBOR> method on |
590 | directly (most of them), it will first look up the C<TO_CBOR> method on |
348 | it. |
591 | it. |
349 | |
592 | |
350 | If it has a C<TO_CBOR> method, it will call it with the object as only |
593 | If it has a C<TO_CBOR> method, it will call it with the object as only |
351 | argument, and expects exactly one return value, which it will then |
594 | argument, and expects exactly one return value, which it will then |
… | |
… | |
357 | |
600 | |
358 | The C<FREEZE> method can return any number of values (i.e. zero or |
601 | The C<FREEZE> method can return any number of values (i.e. zero or |
359 | more). These will be encoded as CBOR perl object, together with the |
602 | more). These will be encoded as CBOR perl object, together with the |
360 | classname. |
603 | classname. |
361 | |
604 | |
|
|
605 | These methods I<MUST NOT> change the data structure that is being |
|
|
606 | serialised. Failure to comply to this can result in memory corruption - |
|
|
607 | and worse. |
|
|
608 | |
362 | If an object supports neither C<TO_CBOR> nor C<FREEZE>, encoding will fail |
609 | If an object supports neither C<TO_CBOR> nor C<FREEZE>, encoding will fail |
363 | with an error. |
610 | with an error. |
364 | |
611 | |
|
|
612 | =head3 DECODING |
|
|
613 | |
365 | Objects encoded via C<TO_CBOR> cannot be automatically decoded, but |
614 | Objects encoded via C<TO_CBOR> cannot (normally) be automatically decoded, |
366 | objects encoded via C<FREEZE> can be decoded using the following protocol: |
615 | but objects encoded via C<FREEZE> can be decoded using the following |
|
|
616 | protocol: |
367 | |
617 | |
368 | When an encoded CBOR perl object is encountered by the decoder, it will |
618 | When an encoded CBOR perl object is encountered by the decoder, it will |
369 | look up the C<THAW> method, by using the stored classname, and will fail |
619 | look up the C<THAW> method, by using the stored classname, and will fail |
370 | if the method cannot be found. |
620 | if the method cannot be found. |
371 | |
621 | |
372 | After the lookup it will call the C<THAW> method with the stored classname |
622 | After the lookup it will call the C<THAW> method with the stored classname |
373 | as first argument, the constant string C<CBOR> as second argument, and all |
623 | as first argument, the constant string C<CBOR> as second argument, and all |
374 | values returned by C<FREEZE> as remaining arguments. |
624 | values returned by C<FREEZE> as remaining arguments. |
375 | |
625 | |
376 | =head4 EXAMPLES |
626 | =head3 EXAMPLES |
377 | |
627 | |
378 | Here is an example C<TO_CBOR> method: |
628 | Here is an example C<TO_CBOR> method: |
379 | |
629 | |
380 | sub My::Object::TO_CBOR { |
630 | sub My::Object::TO_CBOR { |
381 | my ($obj) = @_; |
631 | my ($obj) = @_; |
… | |
… | |
392 | |
642 | |
393 | sub URI::TO_CBOR { |
643 | sub URI::TO_CBOR { |
394 | my ($self) = @_; |
644 | my ($self) = @_; |
395 | my $uri = "$self"; # stringify uri |
645 | my $uri = "$self"; # stringify uri |
396 | utf8::upgrade $uri; # make sure it will be encoded as UTF-8 string |
646 | utf8::upgrade $uri; # make sure it will be encoded as UTF-8 string |
397 | CBOR::XS::tagged 32, "$_[0]" |
647 | CBOR::XS::tag 32, "$_[0]" |
398 | } |
648 | } |
399 | |
649 | |
400 | This will encode URIs as a UTF-8 string with tag 32, which indicates an |
650 | This will encode URIs as a UTF-8 string with tag 32, which indicates an |
401 | URI. |
651 | URI. |
402 | |
652 | |
… | |
… | |
439 | =head1 MAGIC HEADER |
689 | =head1 MAGIC HEADER |
440 | |
690 | |
441 | There is no way to distinguish CBOR from other formats |
691 | There is no way to distinguish CBOR from other formats |
442 | programmatically. To make it easier to distinguish CBOR from other |
692 | programmatically. To make it easier to distinguish CBOR from other |
443 | formats, the CBOR specification has a special "magic string" that can be |
693 | formats, the CBOR specification has a special "magic string" that can be |
444 | prepended to any CBOR string without changing it's meaning. |
694 | prepended to any CBOR string without changing its meaning. |
445 | |
695 | |
446 | This string is available as C<$CBOR::XS::MAGIC>. This module does not |
696 | This string is available as C<$CBOR::XS::MAGIC>. This module does not |
447 | prepend this string tot he CBOR data it generates, but it will ignroe it |
697 | prepend this string to the CBOR data it generates, but it will ignore it |
448 | if present, so users can prepend this string as a "file type" indicator as |
698 | if present, so users can prepend this string as a "file type" indicator as |
449 | required. |
699 | required. |
|
|
700 | |
|
|
701 | |
|
|
702 | =head1 THE CBOR::XS::Tagged CLASS |
|
|
703 | |
|
|
704 | CBOR has the concept of tagged values - any CBOR value can be tagged with |
|
|
705 | a numeric 64 bit number, which are centrally administered. |
|
|
706 | |
|
|
707 | C<CBOR::XS> handles a few tags internally when en- or decoding. You can |
|
|
708 | also create tags yourself by encoding C<CBOR::XS::Tagged> objects, and the |
|
|
709 | decoder will create C<CBOR::XS::Tagged> objects itself when it hits an |
|
|
710 | unknown tag. |
|
|
711 | |
|
|
712 | These objects are simply blessed array references - the first member of |
|
|
713 | the array being the numerical tag, the second being the value. |
|
|
714 | |
|
|
715 | You can interact with C<CBOR::XS::Tagged> objects in the following ways: |
|
|
716 | |
|
|
717 | =over 4 |
|
|
718 | |
|
|
719 | =item $tagged = CBOR::XS::tag $tag, $value |
|
|
720 | |
|
|
721 | This function(!) creates a new C<CBOR::XS::Tagged> object using the given |
|
|
722 | C<$tag> (0..2**64-1) to tag the given C<$value> (which can be any Perl |
|
|
723 | value that can be encoded in CBOR, including serialisable Perl objects and |
|
|
724 | C<CBOR::XS::Tagged> objects). |
|
|
725 | |
|
|
726 | =item $tagged->[0] |
|
|
727 | |
|
|
728 | =item $tagged->[0] = $new_tag |
|
|
729 | |
|
|
730 | =item $tag = $tagged->tag |
|
|
731 | |
|
|
732 | =item $new_tag = $tagged->tag ($new_tag) |
|
|
733 | |
|
|
734 | Access/mutate the tag. |
|
|
735 | |
|
|
736 | =item $tagged->[1] |
|
|
737 | |
|
|
738 | =item $tagged->[1] = $new_value |
|
|
739 | |
|
|
740 | =item $value = $tagged->value |
|
|
741 | |
|
|
742 | =item $new_value = $tagged->value ($new_value) |
|
|
743 | |
|
|
744 | Access/mutate the tagged value. |
|
|
745 | |
|
|
746 | =back |
|
|
747 | |
|
|
748 | =cut |
|
|
749 | |
|
|
750 | sub tag($$) { |
|
|
751 | bless [@_], CBOR::XS::Tagged::; |
|
|
752 | } |
|
|
753 | |
|
|
754 | sub CBOR::XS::Tagged::tag { |
|
|
755 | $_[0][0] = $_[1] if $#_; |
|
|
756 | $_[0][0] |
|
|
757 | } |
|
|
758 | |
|
|
759 | sub CBOR::XS::Tagged::value { |
|
|
760 | $_[0][1] = $_[1] if $#_; |
|
|
761 | $_[0][1] |
|
|
762 | } |
|
|
763 | |
|
|
764 | =head2 EXAMPLES |
|
|
765 | |
|
|
766 | Here are some examples of C<CBOR::XS::Tagged> uses to tag objects. |
|
|
767 | |
|
|
768 | You can look up CBOR tag value and emanings in the IANA registry at |
|
|
769 | L<http://www.iana.org/assignments/cbor-tags/cbor-tags.xhtml>. |
|
|
770 | |
|
|
771 | Prepend a magic header (C<$CBOR::XS::MAGIC>): |
|
|
772 | |
|
|
773 | my $cbor = encode_cbor CBOR::XS::tag 55799, $value; |
|
|
774 | # same as: |
|
|
775 | my $cbor = $CBOR::XS::MAGIC . encode_cbor $value; |
|
|
776 | |
|
|
777 | Serialise some URIs and a regex in an array: |
|
|
778 | |
|
|
779 | my $cbor = encode_cbor [ |
|
|
780 | (CBOR::XS::tag 32, "http://www.nethype.de/"), |
|
|
781 | (CBOR::XS::tag 32, "http://software.schmorp.de/"), |
|
|
782 | (CBOR::XS::tag 35, "^[Pp][Ee][Rr][lL]\$"), |
|
|
783 | ]; |
|
|
784 | |
|
|
785 | Wrap CBOR data in CBOR: |
|
|
786 | |
|
|
787 | my $cbor_cbor = encode_cbor |
|
|
788 | CBOR::XS::tag 24, |
|
|
789 | encode_cbor [1, 2, 3]; |
|
|
790 | |
|
|
791 | =head1 TAG HANDLING AND EXTENSIONS |
|
|
792 | |
|
|
793 | This section describes how this module handles specific tagged values |
|
|
794 | and extensions. If a tag is not mentioned here and no additional filters |
|
|
795 | are provided for it, then the default handling applies (creating a |
|
|
796 | CBOR::XS::Tagged object on decoding, and only encoding the tag when |
|
|
797 | explicitly requested). |
|
|
798 | |
|
|
799 | Tags not handled specifically are currently converted into a |
|
|
800 | L<CBOR::XS::Tagged> object, which is simply a blessed array reference |
|
|
801 | consisting of the numeric tag value followed by the (decoded) CBOR value. |
|
|
802 | |
|
|
803 | Future versions of this module reserve the right to special case |
|
|
804 | additional tags (such as base64url). |
|
|
805 | |
|
|
806 | =head2 ENFORCED TAGS |
|
|
807 | |
|
|
808 | These tags are always handled when decoding, and their handling cannot be |
|
|
809 | overriden by the user. |
|
|
810 | |
|
|
811 | =over 4 |
|
|
812 | |
|
|
813 | =item 26 (perl-object, L<http://cbor.schmorp.de/perl-object>) |
|
|
814 | |
|
|
815 | These tags are automatically created (and decoded) for serialisable |
|
|
816 | objects using the C<FREEZE/THAW> methods (the L<Types::Serialier> object |
|
|
817 | serialisation protocol). See L<OBJECT SERIALISATION> for details. |
|
|
818 | |
|
|
819 | =item 28, 29 (shareable, sharedref, L<http://cbor.schmorp.de/value-sharing>) |
|
|
820 | |
|
|
821 | These tags are automatically decoded when encountered (and they do not |
|
|
822 | result in a cyclic data structure, see C<allow_cycles>), resulting in |
|
|
823 | shared values in the decoded object. They are only encoded, however, when |
|
|
824 | C<allow_sharing> is enabled. |
|
|
825 | |
|
|
826 | Not all shared values can be successfully decoded: values that reference |
|
|
827 | themselves will I<currently> decode as C<undef> (this is not the same |
|
|
828 | as a reference pointing to itself, which will be represented as a value |
|
|
829 | that contains an indirect reference to itself - these will be decoded |
|
|
830 | properly). |
|
|
831 | |
|
|
832 | Note that considerably more shared value data structures can be decoded |
|
|
833 | than will be encoded - currently, only values pointed to by references |
|
|
834 | will be shared, others will not. While non-reference shared values can be |
|
|
835 | generated in Perl with some effort, they were considered too unimportant |
|
|
836 | to be supported in the encoder. The decoder, however, will decode these |
|
|
837 | values as shared values. |
|
|
838 | |
|
|
839 | =item 256, 25 (stringref-namespace, stringref, L<http://cbor.schmorp.de/stringref>) |
|
|
840 | |
|
|
841 | These tags are automatically decoded when encountered. They are only |
|
|
842 | encoded, however, when C<pack_strings> is enabled. |
|
|
843 | |
|
|
844 | =item 22098 (indirection, L<http://cbor.schmorp.de/indirection>) |
|
|
845 | |
|
|
846 | This tag is automatically generated when a reference are encountered (with |
|
|
847 | the exception of hash and array refernces). It is converted to a reference |
|
|
848 | when decoding. |
|
|
849 | |
|
|
850 | =item 55799 (self-describe CBOR, RFC 7049) |
|
|
851 | |
|
|
852 | This value is not generated on encoding (unless explicitly requested by |
|
|
853 | the user), and is simply ignored when decoding. |
|
|
854 | |
|
|
855 | =back |
|
|
856 | |
|
|
857 | =head2 NON-ENFORCED TAGS |
|
|
858 | |
|
|
859 | These tags have default filters provided when decoding. Their handling can |
|
|
860 | be overriden by changing the C<%CBOR::XS::FILTER> entry for the tag, or by |
|
|
861 | providing a custom C<filter> callback when decoding. |
|
|
862 | |
|
|
863 | When they result in decoding into a specific Perl class, the module |
|
|
864 | usually provides a corresponding C<TO_CBOR> method as well. |
|
|
865 | |
|
|
866 | When any of these need to load additional modules that are not part of the |
|
|
867 | perl core distribution (e.g. L<URI>), it is (currently) up to the user to |
|
|
868 | provide these modules. The decoding usually fails with an exception if the |
|
|
869 | required module cannot be loaded. |
|
|
870 | |
|
|
871 | =over 4 |
|
|
872 | |
|
|
873 | =item 0, 1 (date/time string, seconds since the epoch) |
|
|
874 | |
|
|
875 | These tags are decoded into L<Time::Piece> objects. The corresponding |
|
|
876 | C<Time::Piece::TO_CBOR> method always encodes into tag 1 values currently. |
|
|
877 | |
|
|
878 | The L<Time::Piece> API is generally surprisingly bad, and fractional |
|
|
879 | seconds are only accidentally kept intact, so watch out. On the plus side, |
|
|
880 | the module comes with perl since 5.10, which has to count for something. |
|
|
881 | |
|
|
882 | =item 2, 3 (positive/negative bignum) |
|
|
883 | |
|
|
884 | These tags are decoded into L<Math::BigInt> objects. The corresponding |
|
|
885 | C<Math::BigInt::TO_CBOR> method encodes "small" bigints into normal CBOR |
|
|
886 | integers, and others into positive/negative CBOR bignums. |
|
|
887 | |
|
|
888 | =item 4, 5 (decimal fraction/bigfloat) |
|
|
889 | |
|
|
890 | Both decimal fractions and bigfloats are decoded into L<Math::BigFloat> |
|
|
891 | objects. The corresponding C<Math::BigFloat::TO_CBOR> method I<always> |
|
|
892 | encodes into a decimal fraction. |
|
|
893 | |
|
|
894 | CBOR cannot represent bigfloats with I<very> large exponents - conversion |
|
|
895 | of such big float objects is undefined. |
|
|
896 | |
|
|
897 | Also, NaN and infinities are not encoded properly. |
|
|
898 | |
|
|
899 | =item 21, 22, 23 (expected later JSON conversion) |
|
|
900 | |
|
|
901 | CBOR::XS is not a CBOR-to-JSON converter, and will simply ignore these |
|
|
902 | tags. |
|
|
903 | |
|
|
904 | =item 32 (URI) |
|
|
905 | |
|
|
906 | These objects decode into L<URI> objects. The corresponding |
|
|
907 | C<URI::TO_CBOR> method again results in a CBOR URI value. |
|
|
908 | |
|
|
909 | =back |
|
|
910 | |
|
|
911 | =cut |
|
|
912 | |
|
|
913 | our %FILTER = ( |
|
|
914 | # 0 # rfc4287 datetime, utf-8 |
|
|
915 | # 1 # unix timestamp, any |
|
|
916 | |
|
|
917 | 2 => sub { # pos bigint |
|
|
918 | require Math::BigInt; |
|
|
919 | Math::BigInt->new ("0x" . unpack "H*", pop) |
|
|
920 | }, |
|
|
921 | |
|
|
922 | 3 => sub { # neg bigint |
|
|
923 | require Math::BigInt; |
|
|
924 | -Math::BigInt->new ("0x" . unpack "H*", pop) |
|
|
925 | }, |
|
|
926 | |
|
|
927 | 4 => sub { # decimal fraction, array |
|
|
928 | require Math::BigFloat; |
|
|
929 | Math::BigFloat->new ($_[1][1] . "E" . $_[1][0]) |
|
|
930 | }, |
|
|
931 | |
|
|
932 | 5 => sub { # bigfloat, array |
|
|
933 | require Math::BigFloat; |
|
|
934 | scalar Math::BigFloat->new ($_[1][1])->blsft ($_[1][0], 2) |
|
|
935 | }, |
|
|
936 | |
|
|
937 | 21 => sub { pop }, # expected conversion to base64url encoding |
|
|
938 | 22 => sub { pop }, # expected conversion to base64 encoding |
|
|
939 | 23 => sub { pop }, # expected conversion to base16 encoding |
|
|
940 | |
|
|
941 | # 24 # embedded cbor, byte string |
|
|
942 | |
|
|
943 | 32 => sub { |
|
|
944 | require URI; |
|
|
945 | URI->new (pop) |
|
|
946 | }, |
|
|
947 | |
|
|
948 | # 33 # base64url rfc4648, utf-8 |
|
|
949 | # 34 # base64 rfc46484, utf-8 |
|
|
950 | # 35 # regex pcre/ecma262, utf-8 |
|
|
951 | # 36 # mime message rfc2045, utf-8 |
|
|
952 | ); |
450 | |
953 | |
451 | |
954 | |
452 | =head1 CBOR and JSON |
955 | =head1 CBOR and JSON |
453 | |
956 | |
454 | CBOR is supposed to implement a superset of the JSON data model, and is, |
957 | CBOR is supposed to implement a superset of the JSON data model, and is, |
… | |
… | |
516 | properly. Half precision types are accepted, but not encoded. |
1019 | properly. Half precision types are accepted, but not encoded. |
517 | |
1020 | |
518 | Strict mode and canonical mode are not implemented. |
1021 | Strict mode and canonical mode are not implemented. |
519 | |
1022 | |
520 | |
1023 | |
|
|
1024 | =head1 LIMITATIONS ON PERLS WITHOUT 64-BIT INTEGER SUPPORT |
|
|
1025 | |
|
|
1026 | On perls that were built without 64 bit integer support (these are rare |
|
|
1027 | nowadays, even on 32 bit architectures, as all major Perl distributions |
|
|
1028 | are built with 64 bit integer support), support for any kind of 64 bit |
|
|
1029 | integer in CBOR is very limited - most likely, these 64 bit values will |
|
|
1030 | be truncated, corrupted, or otherwise not decoded correctly. This also |
|
|
1031 | includes string, array and map sizes that are stored as 64 bit integers. |
|
|
1032 | |
|
|
1033 | |
521 | =head1 THREADS |
1034 | =head1 THREADS |
522 | |
1035 | |
523 | This module is I<not> guaranteed to be thread safe and there are no |
1036 | This module is I<not> guaranteed to be thread safe and there are no |
524 | plans to change this until Perl gets thread support (as opposed to the |
1037 | plans to change this until Perl gets thread support (as opposed to the |
525 | horribly slow so-called "threads" which are simply slow and bloated |
1038 | horribly slow so-called "threads" which are simply slow and bloated |
… | |
… | |
537 | Please refrain from using rt.cpan.org or any other bug reporting |
1050 | Please refrain from using rt.cpan.org or any other bug reporting |
538 | service. I put the contact address into my modules for a reason. |
1051 | service. I put the contact address into my modules for a reason. |
539 | |
1052 | |
540 | =cut |
1053 | =cut |
541 | |
1054 | |
|
|
1055 | our %FILTER = ( |
|
|
1056 | 0 => sub { # rfc4287 datetime, utf-8 |
|
|
1057 | require Time::Piece; |
|
|
1058 | # Time::Piece::Strptime uses the "incredibly flexible date parsing routine" |
|
|
1059 | # from FreeBSD, which can't parse ISO 8601, RFC3339, RFC4287 or much of anything |
|
|
1060 | # else either. Whats incredibe over standard strptime totally escapes me. |
|
|
1061 | # doesn't do fractional times, either. sigh. |
|
|
1062 | # In fact, it's all a lie, it uses whatever strptime it wants, and of course, |
|
|
1063 | # they are all incompatible. The openbsd one simply ignores %z (but according to the |
|
|
1064 | # docs, it would be much more incredibly flexible indeed. If it worked, that is.). |
|
|
1065 | scalar eval { |
|
|
1066 | my $s = $_[1]; |
|
|
1067 | |
|
|
1068 | $s =~ s/Z$/+00:00/; |
|
|
1069 | $s =~ s/(\.[0-9]+)?([+-][0-9][0-9]):([0-9][0-9])$// |
|
|
1070 | or die; |
|
|
1071 | |
|
|
1072 | my $b = $1 - ($2 * 60 + $3) * 60; # fractional part + offset. hopefully |
|
|
1073 | my $d = Time::Piece->strptime ($s, "%Y-%m-%dT%H:%M:%S"); |
|
|
1074 | |
|
|
1075 | Time::Piece::gmtime ($d->epoch + $b) |
|
|
1076 | } || die "corrupted CBOR date/time string ($_[0])"; |
|
|
1077 | }, |
|
|
1078 | |
|
|
1079 | 1 => sub { # seconds since the epoch, possibly fractional |
|
|
1080 | require Time::Piece; |
|
|
1081 | scalar Time::Piece::gmtime (pop) |
|
|
1082 | }, |
|
|
1083 | |
|
|
1084 | 2 => sub { # pos bigint |
|
|
1085 | require Math::BigInt; |
|
|
1086 | Math::BigInt->new ("0x" . unpack "H*", pop) |
|
|
1087 | }, |
|
|
1088 | |
|
|
1089 | 3 => sub { # neg bigint |
|
|
1090 | require Math::BigInt; |
|
|
1091 | -Math::BigInt->new ("0x" . unpack "H*", pop) |
|
|
1092 | }, |
|
|
1093 | |
|
|
1094 | 4 => sub { # decimal fraction, array |
|
|
1095 | require Math::BigFloat; |
|
|
1096 | Math::BigFloat->new ($_[1][1] . "E" . $_[1][0]) |
|
|
1097 | }, |
|
|
1098 | |
|
|
1099 | 5 => sub { # bigfloat, array |
|
|
1100 | require Math::BigFloat; |
|
|
1101 | scalar Math::BigFloat->new ($_[1][1])->blsft ($_[1][0], 2) |
|
|
1102 | }, |
|
|
1103 | |
|
|
1104 | 21 => sub { pop }, # expected conversion to base64url encoding |
|
|
1105 | 22 => sub { pop }, # expected conversion to base64 encoding |
|
|
1106 | 23 => sub { pop }, # expected conversion to base16 encoding |
|
|
1107 | |
|
|
1108 | # 24 # embedded cbor, byte string |
|
|
1109 | |
|
|
1110 | 32 => sub { |
|
|
1111 | require URI; |
|
|
1112 | URI->new (pop) |
|
|
1113 | }, |
|
|
1114 | |
|
|
1115 | # 33 # base64url rfc4648, utf-8 |
|
|
1116 | # 34 # base64 rfc46484, utf-8 |
|
|
1117 | # 35 # regex pcre/ecma262, utf-8 |
|
|
1118 | # 36 # mime message rfc2045, utf-8 |
|
|
1119 | ); |
|
|
1120 | |
|
|
1121 | sub CBOR::XS::default_filter { |
|
|
1122 | &{ $FILTER{$_[0]} or return } |
|
|
1123 | } |
|
|
1124 | |
|
|
1125 | sub URI::TO_CBOR { |
|
|
1126 | my $uri = $_[0]->as_string; |
|
|
1127 | utf8::upgrade $uri; |
|
|
1128 | tag 32, $uri |
|
|
1129 | } |
|
|
1130 | |
|
|
1131 | sub Math::BigInt::TO_CBOR { |
|
|
1132 | if ($_[0] >= -2147483648 && $_[0] <= 2147483647) { |
|
|
1133 | $_[0]->numify |
|
|
1134 | } else { |
|
|
1135 | my $hex = substr $_[0]->as_hex, 2; |
|
|
1136 | $hex = "0$hex" if 1 & length $hex; # sigh |
|
|
1137 | tag $_[0] >= 0 ? 2 : 3, pack "H*", $hex |
|
|
1138 | } |
|
|
1139 | } |
|
|
1140 | |
|
|
1141 | sub Math::BigFloat::TO_CBOR { |
|
|
1142 | my ($m, $e) = $_[0]->parts; |
|
|
1143 | tag 4, [$e->numify, $m] |
|
|
1144 | } |
|
|
1145 | |
|
|
1146 | sub Time::Piece::TO_CBOR { |
|
|
1147 | tag 1, 0 + $_[0]->epoch |
|
|
1148 | } |
|
|
1149 | |
542 | XSLoader::load "CBOR::XS", $VERSION; |
1150 | XSLoader::load "CBOR::XS", $VERSION; |
543 | |
1151 | |
544 | =head1 SEE ALSO |
1152 | =head1 SEE ALSO |
545 | |
1153 | |
546 | The L<JSON> and L<JSON::XS> modules that do similar, but human-readable, |
1154 | The L<JSON> and L<JSON::XS> modules that do similar, but human-readable, |