… | |
… | |
12 | $perl_value = decode_cbor $binary_cbor_data; |
12 | $perl_value = decode_cbor $binary_cbor_data; |
13 | |
13 | |
14 | # OO-interface |
14 | # OO-interface |
15 | |
15 | |
16 | $coder = CBOR::XS->new; |
16 | $coder = CBOR::XS->new; |
17 | #TODO |
17 | $binary_cbor_data = $coder->encode ($perl_value); |
|
|
18 | $perl_value = $coder->decode ($binary_cbor_data); |
|
|
19 | |
|
|
20 | # prefix decoding |
|
|
21 | |
|
|
22 | my $many_cbor_strings = ...; |
|
|
23 | while (length $many_cbor_strings) { |
|
|
24 | my ($data, $length) = $cbor->decode_prefix ($many_cbor_strings); |
|
|
25 | # data was decoded |
|
|
26 | substr $many_cbor_strings, 0, $length, ""; # remove decoded cbor string |
|
|
27 | } |
18 | |
28 | |
19 | =head1 DESCRIPTION |
29 | =head1 DESCRIPTION |
20 | |
30 | |
21 | WARNING! THIS IS A PRE-ALPHA RELEASE! IT WILL CRASH, CORRUPT YOUR DATA AND |
31 | WARNING! This module is very new, and not very well tested (that's up |
22 | EAT YOUR CHILDREN! |
32 | to you to do). Furthermore, details of the implementation might change |
|
|
33 | freely before version 1.0. And lastly, most extensions depend on an IANA |
|
|
34 | assignment, and until that assignment is official, this implementation is |
|
|
35 | not interoperable with other implementations (even future versions of this |
|
|
36 | module) until the assignment is done. |
23 | |
37 | |
24 | This module converts Perl data structures to CBOR and vice versa. Its |
38 | You are still invited to try out CBOR, and this module. |
|
|
39 | |
|
|
40 | This module converts Perl data structures to the Concise Binary Object |
|
|
41 | Representation (CBOR) and vice versa. CBOR is a fast binary serialisation |
|
|
42 | format that aims to use a superset of the JSON data model, i.e. when you |
|
|
43 | can represent something in JSON, you should be able to represent it in |
|
|
44 | CBOR. |
|
|
45 | |
|
|
46 | In short, CBOR is a faster and very compact binary alternative to JSON, |
|
|
47 | with the added ability of supporting serialisation of Perl objects. (JSON |
|
|
48 | often compresses better than CBOR though, so if you plan to compress the |
|
|
49 | data later you might want to compare both formats first). |
|
|
50 | |
|
|
51 | To give you a general idea about speed, with texts in the megabyte range, |
|
|
52 | C<CBOR::XS> usually encodes roughly twice as fast as L<Storable> or |
|
|
53 | L<JSON::XS> and decodes about 15%-30% faster than those. The shorter the |
|
|
54 | data, the worse L<Storable> performs in comparison. |
|
|
55 | |
|
|
56 | As for compactness, C<CBOR::XS> encoded data structures are usually about |
|
|
57 | 20% smaller than the same data encoded as (compact) JSON or L<Storable>. |
|
|
58 | |
|
|
59 | In addition to the core CBOR data format, this module implements a number |
|
|
60 | of extensions, to support cyclic and self-referencing data structures |
|
|
61 | (see C<allow_sharing>), string deduplication (see C<allow_stringref>) and |
|
|
62 | scalar references (always enabled). |
|
|
63 | |
25 | primary goal is to be I<correct> and its secondary goal is to be |
64 | The primary goal of this module is to be I<correct> and the secondary goal |
26 | I<fast>. To reach the latter goal it was written in C. |
65 | is to be I<fast>. To reach the latter goal it was written in C. |
27 | |
66 | |
28 | See MAPPING, below, on how CBOR::XS maps perl values to CBOR values and |
67 | See MAPPING, below, on how CBOR::XS maps perl values to CBOR values and |
29 | vice versa. |
68 | vice versa. |
30 | |
69 | |
31 | =cut |
70 | =cut |
32 | |
71 | |
33 | package CBOR::XS; |
72 | package CBOR::XS; |
34 | |
73 | |
35 | use common::sense; |
74 | use common::sense; |
36 | |
75 | |
37 | our $VERSION = 0.02; |
76 | our $VERSION = 0.08; |
38 | our @ISA = qw(Exporter); |
77 | our @ISA = qw(Exporter); |
39 | |
78 | |
40 | our @EXPORT = qw(encode_cbor decode_cbor); |
79 | our @EXPORT = qw(encode_cbor decode_cbor); |
41 | |
80 | |
42 | use Exporter; |
81 | use Exporter; |
43 | use XSLoader; |
82 | use XSLoader; |
44 | |
83 | |
|
|
84 | use Types::Serialiser; |
|
|
85 | |
45 | our $MAGIC = "\xd9\xd9\xf7"; |
86 | our $MAGIC = "\xd9\xd9\xf7"; |
46 | |
87 | |
47 | =head1 FUNCTIONAL INTERFACE |
88 | =head1 FUNCTIONAL INTERFACE |
48 | |
89 | |
49 | The following convenience methods are provided by this module. They are |
90 | The following convenience methods are provided by this module. They are |
… | |
… | |
77 | strings. All boolean flags described below are by default I<disabled>. |
118 | strings. All boolean flags described below are by default I<disabled>. |
78 | |
119 | |
79 | The mutators for flags all return the CBOR object again and thus calls can |
120 | The mutators for flags all return the CBOR object again and thus calls can |
80 | be chained: |
121 | be chained: |
81 | |
122 | |
82 | #TODO |
|
|
83 | my $cbor = CBOR::XS->new->encode ({a => [1,2]}); |
123 | my $cbor = CBOR::XS->new->encode ({a => [1,2]}); |
84 | |
124 | |
85 | =item $cbor = $cbor->max_depth ([$maximum_nesting_depth]) |
125 | =item $cbor = $cbor->max_depth ([$maximum_nesting_depth]) |
86 | |
126 | |
87 | =item $max_depth = $cbor->get_max_depth |
127 | =item $max_depth = $cbor->get_max_depth |
… | |
… | |
121 | If no argument is given, the limit check will be deactivated (same as when |
161 | If no argument is given, the limit check will be deactivated (same as when |
122 | C<0> is specified). |
162 | C<0> is specified). |
123 | |
163 | |
124 | See SECURITY CONSIDERATIONS, below, for more info on why this is useful. |
164 | See SECURITY CONSIDERATIONS, below, for more info on why this is useful. |
125 | |
165 | |
|
|
166 | =item $cbor = $cbor->allow_unknown ([$enable]) |
|
|
167 | |
|
|
168 | =item $enabled = $cbor->get_allow_unknown |
|
|
169 | |
|
|
170 | If C<$enable> is true (or missing), then C<encode> will I<not> throw an |
|
|
171 | exception when it encounters values it cannot represent in CBOR (for |
|
|
172 | example, filehandles) but instead will encode a CBOR C<error> value. |
|
|
173 | |
|
|
174 | If C<$enable> is false (the default), then C<encode> will throw an |
|
|
175 | exception when it encounters anything it cannot encode as CBOR. |
|
|
176 | |
|
|
177 | This option does not affect C<decode> in any way, and it is recommended to |
|
|
178 | leave it off unless you know your communications partner. |
|
|
179 | |
|
|
180 | =item $cbor = $cbor->allow_sharing ([$enable]) |
|
|
181 | |
|
|
182 | =item $enabled = $cbor->get_allow_sharing |
|
|
183 | |
|
|
184 | If C<$enable> is true (or missing), then C<encode> will not double-encode |
|
|
185 | values that have been referenced before (e.g. when the same object, such |
|
|
186 | as an array, is referenced multiple times), but instead will emit a |
|
|
187 | reference to the earlier value. |
|
|
188 | |
|
|
189 | This means that such values will only be encoded once, and will not result |
|
|
190 | in a deep cloning of the value on decode, in decoders supporting the value |
|
|
191 | sharing extension. |
|
|
192 | |
|
|
193 | It is recommended to leave it off unless you know your |
|
|
194 | communication partner supports the value sharing extensions to CBOR |
|
|
195 | (http://cbor.schmorp.de/value-sharing). |
|
|
196 | |
|
|
197 | Detecting shared values incurs a runtime overhead when values are encoded |
|
|
198 | that have a reference counter large than one, and might unnecessarily |
|
|
199 | increase the encoded size, as potentially shared values are encode as |
|
|
200 | sharable whether or not they are actually shared. |
|
|
201 | |
|
|
202 | At the moment, only targets of references can be shared (e.g. scalars, |
|
|
203 | arrays or hashes pointed to by a reference). Weirder constructs, such as |
|
|
204 | an array with multiple "copies" of the I<same> string, which are hard but |
|
|
205 | not impossible to create in Perl, are not supported (this is the same as |
|
|
206 | for L<Storable>). |
|
|
207 | |
|
|
208 | If C<$enable> is false (the default), then C<encode> will encode |
|
|
209 | exception when it encounters anything it cannot encode as CBOR. |
|
|
210 | |
|
|
211 | This option does not affect C<decode> in any way - shared values and |
|
|
212 | references will always be decoded properly if present. |
|
|
213 | |
|
|
214 | =item $cbor = $cbor->allow_stringref ([$enable]) |
|
|
215 | |
|
|
216 | =item $enabled = $cbor->get_allow_stringref |
|
|
217 | |
|
|
218 | If C<$enable> is true (or missing), then C<encode> will try not to encode |
|
|
219 | the same string twice, but will instead encode a reference to the string |
|
|
220 | instead. Depending on your data format. this can save a lot of space, but |
|
|
221 | also results in a very large runtime overhead (expect encoding times to be |
|
|
222 | 2-4 times as high as without). |
|
|
223 | |
|
|
224 | It is recommended to leave it off unless you know your |
|
|
225 | communications partner supports the stringref extension to CBOR |
|
|
226 | (http://cbor.schmorp.de/stringref). |
|
|
227 | |
|
|
228 | If C<$enable> is false (the default), then C<encode> will encode |
|
|
229 | exception when it encounters anything it cannot encode as CBOR. |
|
|
230 | |
|
|
231 | This option does not affect C<decode> in any way - string references will |
|
|
232 | always be decoded properly if present. |
|
|
233 | |
|
|
234 | =item $cbor = $cbor->filter ([$cb->($tag, $value)]) |
|
|
235 | |
|
|
236 | =item $cb_or_undef = $cbor->get_filter |
|
|
237 | |
|
|
238 | TODO |
|
|
239 | |
126 | =item $cbor_data = $cbor->encode ($perl_scalar) |
240 | =item $cbor_data = $cbor->encode ($perl_scalar) |
127 | |
241 | |
128 | Converts the given Perl data structure (a scalar value) to its CBOR |
242 | Converts the given Perl data structure (a scalar value) to its CBOR |
129 | representation. |
243 | representation. |
130 | |
244 | |
… | |
… | |
163 | |
277 | |
164 | =head2 CBOR -> PERL |
278 | =head2 CBOR -> PERL |
165 | |
279 | |
166 | =over 4 |
280 | =over 4 |
167 | |
281 | |
168 | =item True, False |
282 | =item integers |
169 | |
283 | |
170 | These CBOR values become C<CBOR::XS::true> and C<CBOR::XS::false>, |
284 | CBOR integers become (numeric) perl scalars. On perls without 64 bit |
|
|
285 | support, 64 bit integers will be truncated or otherwise corrupted. |
|
|
286 | |
|
|
287 | =item byte strings |
|
|
288 | |
|
|
289 | Byte strings will become octet strings in Perl (the byte values 0..255 |
|
|
290 | will simply become characters of the same value in Perl). |
|
|
291 | |
|
|
292 | =item UTF-8 strings |
|
|
293 | |
|
|
294 | UTF-8 strings in CBOR will be decoded, i.e. the UTF-8 octets will be |
|
|
295 | decoded into proper Unicode code points. At the moment, the validity of |
|
|
296 | the UTF-8 octets will not be validated - corrupt input will result in |
|
|
297 | corrupted Perl strings. |
|
|
298 | |
|
|
299 | =item arrays, maps |
|
|
300 | |
|
|
301 | CBOR arrays and CBOR maps will be converted into references to a Perl |
|
|
302 | array or hash, respectively. The keys of the map will be stringified |
|
|
303 | during this process. |
|
|
304 | |
|
|
305 | =item null |
|
|
306 | |
|
|
307 | CBOR null becomes C<undef> in Perl. |
|
|
308 | |
|
|
309 | =item true, false, undefined |
|
|
310 | |
|
|
311 | These CBOR values become C<Types:Serialiser::true>, |
|
|
312 | C<Types:Serialiser::false> and C<Types::Serialiser::error>, |
171 | respectively. They are overloaded to act almost exactly like the numbers |
313 | respectively. They are overloaded to act almost exactly like the numbers |
172 | C<1> and C<0>. You can check whether a scalar is a CBOR boolean by using |
314 | C<1> and C<0> (for true and false) or to throw an exception on access (for |
173 | the C<CBOR::XS::is_bool> function. |
315 | error). See the L<Types::Serialiser> manpage for details. |
174 | |
316 | |
175 | =item Null, Undefined |
317 | =item tagged values |
176 | |
318 | |
177 | CBOR Null and Undefined values becomes C<undef> in Perl (in the future, |
319 | Tagged items consists of a numeric tag and another CBOR value. |
178 | Undefined may raise an exception). |
320 | |
|
|
321 | See L<TAG HANDLING AND EXTENSIONS> and the description of C<< ->filter >> |
|
|
322 | for details. |
|
|
323 | |
|
|
324 | =item anything else |
|
|
325 | |
|
|
326 | Anything else (e.g. unsupported simple values) will raise a decoding |
|
|
327 | error. |
179 | |
328 | |
180 | =back |
329 | =back |
181 | |
330 | |
182 | |
331 | |
183 | =head2 PERL -> CBOR |
332 | =head2 PERL -> CBOR |
… | |
… | |
188 | |
337 | |
189 | =over 4 |
338 | =over 4 |
190 | |
339 | |
191 | =item hash references |
340 | =item hash references |
192 | |
341 | |
193 | Perl hash references become CBOR maps. As there is no inherent ordering |
342 | Perl hash references become CBOR maps. As there is no inherent ordering in |
194 | in hash keys (or CBOR maps), they will usually be encoded in a |
343 | hash keys (or CBOR maps), they will usually be encoded in a pseudo-random |
195 | pseudo-random order. |
344 | order. |
|
|
345 | |
|
|
346 | Currently, tied hashes will use the indefinite-length format, while normal |
|
|
347 | hashes will use the fixed-length format. |
196 | |
348 | |
197 | =item array references |
349 | =item array references |
198 | |
350 | |
199 | Perl array references become CBOR arrays. |
351 | Perl array references become fixed-length CBOR arrays. |
200 | |
352 | |
201 | =item other references |
353 | =item other references |
202 | |
354 | |
203 | Other unblessed references are generally not allowed and will cause an |
355 | Other unblessed references are generally not allowed and will cause an |
204 | exception to be thrown, except for references to the integers C<0> and |
356 | exception to be thrown, except for references to the integers C<0> and |
205 | C<1>, which get turned into C<False> and C<True> in CBOR. |
357 | C<1>, which get turned into false and true in CBOR. |
206 | |
358 | |
207 | =item CBOR::XS::true, CBOR::XS::false |
359 | =item CBOR::XS::Tagged objects |
208 | |
360 | |
|
|
361 | Objects of this type must be arrays consisting of a single C<[tag, value]> |
|
|
362 | pair. The (numerical) tag will be encoded as a CBOR tag, the value will |
|
|
363 | be encoded as appropriate for the value. You cna use C<CBOR::XS::tag> to |
|
|
364 | create such objects. |
|
|
365 | |
|
|
366 | =item Types::Serialiser::true, Types::Serialiser::false, Types::Serialiser::error |
|
|
367 | |
209 | These special values become CBOR True and CBOR False values, |
368 | These special values become CBOR true, CBOR false and CBOR undefined |
210 | respectively. You can also use C<\1> and C<\0> directly if you want. |
369 | values, respectively. You can also use C<\1>, C<\0> and C<\undef> directly |
|
|
370 | if you want. |
211 | |
371 | |
212 | =item blessed objects |
372 | =item other blessed objects |
213 | |
373 | |
214 | Blessed objects are not directly representable in CBOR. TODO |
374 | Other blessed objects are serialised via C<TO_CBOR> or C<FREEZE>. See |
215 | See the |
375 | L<TAG HANDLING AND EXTENSIONS> for specific classes handled by this |
216 | C<allow_blessed> and C<convert_blessed> methods on various options on |
376 | module, and L<OBJECT SERIALISATION> for generic object serialisation. |
217 | how to deal with this: basically, you can choose between throwing an |
|
|
218 | exception, encoding the reference as if it weren't blessed, or provide |
|
|
219 | your own serialiser method. |
|
|
220 | |
377 | |
221 | =item simple scalars |
378 | =item simple scalars |
222 | |
379 | |
223 | TODO |
|
|
224 | Simple Perl scalars (any scalar that is not a reference) are the most |
380 | Simple Perl scalars (any scalar that is not a reference) are the most |
225 | difficult objects to encode: CBOR::XS will encode undefined scalars as |
381 | difficult objects to encode: CBOR::XS will encode undefined scalars as |
226 | CBOR C<Null> values, scalars that have last been used in a string context |
382 | CBOR null values, scalars that have last been used in a string context |
227 | before encoding as CBOR strings, and anything else as number value: |
383 | before encoding as CBOR strings, and anything else as number value: |
228 | |
384 | |
229 | # dump as number |
385 | # dump as number |
230 | encode_cbor [2] # yields [2] |
386 | encode_cbor [2] # yields [2] |
231 | encode_cbor [-3.0e17] # yields [-3e+17] |
387 | encode_cbor [-3.0e17] # yields [-3e+17] |
… | |
… | |
253 | |
409 | |
254 | You can not currently force the type in other, less obscure, ways. Tell me |
410 | You can not currently force the type in other, less obscure, ways. Tell me |
255 | if you need this capability (but don't forget to explain why it's needed |
411 | if you need this capability (but don't forget to explain why it's needed |
256 | :). |
412 | :). |
257 | |
413 | |
258 | Note that numerical precision has the same meaning as under Perl (so |
414 | Perl values that seem to be integers generally use the shortest possible |
259 | binary to decimal conversion follows the same rules as in Perl, which |
415 | representation. Floating-point values will use either the IEEE single |
260 | can differ to other languages). Also, your perl interpreter might expose |
416 | format if possible without loss of precision, otherwise the IEEE double |
261 | extensions to the floating point numbers of your platform, such as |
417 | format will be used. Perls that use formats other than IEEE double to |
262 | infinities or NaN's - these cannot be represented in CBOR, and it is an |
418 | represent numerical values are supported, but might suffer loss of |
263 | error to pass those in. |
419 | precision. |
264 | |
420 | |
265 | =back |
421 | =back |
266 | |
422 | |
|
|
423 | =head2 OBJECT SERIALISATION |
267 | |
424 | |
|
|
425 | This module knows two way to serialise a Perl object: The CBOR-specific |
|
|
426 | way, and the generic way. |
|
|
427 | |
|
|
428 | Whenever the encoder encounters a Perl object that it cnanot serialise |
|
|
429 | directly (most of them), it will first look up the C<TO_CBOR> method on |
|
|
430 | it. |
|
|
431 | |
|
|
432 | If it has a C<TO_CBOR> method, it will call it with the object as only |
|
|
433 | argument, and expects exactly one return value, which it will then |
|
|
434 | substitute and encode it in the place of the object. |
|
|
435 | |
|
|
436 | Otherwise, it will look up the C<FREEZE> method. If it exists, it will |
|
|
437 | call it with the object as first argument, and the constant string C<CBOR> |
|
|
438 | as the second argument, to distinguish it from other serialisers. |
|
|
439 | |
|
|
440 | The C<FREEZE> method can return any number of values (i.e. zero or |
|
|
441 | more). These will be encoded as CBOR perl object, together with the |
|
|
442 | classname. |
|
|
443 | |
|
|
444 | If an object supports neither C<TO_CBOR> nor C<FREEZE>, encoding will fail |
|
|
445 | with an error. |
|
|
446 | |
|
|
447 | Objects encoded via C<TO_CBOR> cannot be automatically decoded, but |
|
|
448 | objects encoded via C<FREEZE> can be decoded using the following protocol: |
|
|
449 | |
|
|
450 | When an encoded CBOR perl object is encountered by the decoder, it will |
|
|
451 | look up the C<THAW> method, by using the stored classname, and will fail |
|
|
452 | if the method cannot be found. |
|
|
453 | |
|
|
454 | After the lookup it will call the C<THAW> method with the stored classname |
|
|
455 | as first argument, the constant string C<CBOR> as second argument, and all |
|
|
456 | values returned by C<FREEZE> as remaining arguments. |
|
|
457 | |
|
|
458 | =head4 EXAMPLES |
|
|
459 | |
|
|
460 | Here is an example C<TO_CBOR> method: |
|
|
461 | |
|
|
462 | sub My::Object::TO_CBOR { |
|
|
463 | my ($obj) = @_; |
|
|
464 | |
|
|
465 | ["this is a serialised My::Object object", $obj->{id}] |
|
|
466 | } |
|
|
467 | |
|
|
468 | When a C<My::Object> is encoded to CBOR, it will instead encode a simple |
|
|
469 | array with two members: a string, and the "object id". Decoding this CBOR |
|
|
470 | string will yield a normal perl array reference in place of the object. |
|
|
471 | |
|
|
472 | A more useful and practical example would be a serialisation method for |
|
|
473 | the URI module. CBOR has a custom tag value for URIs, namely 32: |
|
|
474 | |
|
|
475 | sub URI::TO_CBOR { |
|
|
476 | my ($self) = @_; |
|
|
477 | my $uri = "$self"; # stringify uri |
|
|
478 | utf8::upgrade $uri; # make sure it will be encoded as UTF-8 string |
|
|
479 | CBOR::XS::tagged 32, "$_[0]" |
|
|
480 | } |
|
|
481 | |
|
|
482 | This will encode URIs as a UTF-8 string with tag 32, which indicates an |
|
|
483 | URI. |
|
|
484 | |
|
|
485 | Decoding such an URI will not (currently) give you an URI object, but |
|
|
486 | instead a CBOR::XS::Tagged object with tag number 32 and the string - |
|
|
487 | exactly what was returned by C<TO_CBOR>. |
|
|
488 | |
|
|
489 | To serialise an object so it can automatically be deserialised, you need |
|
|
490 | to use C<FREEZE> and C<THAW>. To take the URI module as example, this |
|
|
491 | would be a possible implementation: |
|
|
492 | |
|
|
493 | sub URI::FREEZE { |
|
|
494 | my ($self, $serialiser) = @_; |
|
|
495 | "$self" # encode url string |
|
|
496 | } |
|
|
497 | |
|
|
498 | sub URI::THAW { |
|
|
499 | my ($class, $serialiser, $uri) = @_; |
|
|
500 | |
|
|
501 | $class->new ($uri) |
|
|
502 | } |
|
|
503 | |
|
|
504 | Unlike C<TO_CBOR>, multiple values can be returned by C<FREEZE>. For |
|
|
505 | example, a C<FREEZE> method that returns "type", "id" and "variant" values |
|
|
506 | would cause an invocation of C<THAW> with 5 arguments: |
|
|
507 | |
|
|
508 | sub My::Object::FREEZE { |
|
|
509 | my ($self, $serialiser) = @_; |
|
|
510 | |
|
|
511 | ($self->{type}, $self->{id}, $self->{variant}) |
|
|
512 | } |
|
|
513 | |
|
|
514 | sub My::Object::THAW { |
|
|
515 | my ($class, $serialiser, $type, $id, $variant) = @_; |
|
|
516 | |
|
|
517 | $class-<new (type => $type, id => $id, variant => $variant) |
|
|
518 | } |
|
|
519 | |
|
|
520 | |
268 | =head2 MAGIC HEADER |
521 | =head1 MAGIC HEADER |
269 | |
522 | |
270 | There is no way to distinguish CBOR from other formats |
523 | There is no way to distinguish CBOR from other formats |
271 | programmatically. To make it easier to distinguish CBOR from other |
524 | programmatically. To make it easier to distinguish CBOR from other |
272 | formats, the CBOR specification has a special "magic string" that can be |
525 | formats, the CBOR specification has a special "magic string" that can be |
273 | prepended to any CBOR string without changing it's meaning. |
526 | prepended to any CBOR string without changing its meaning. |
274 | |
527 | |
275 | This string is available as C<$CBOR::XS::MAGIC>. This module does not |
528 | This string is available as C<$CBOR::XS::MAGIC>. This module does not |
276 | prepend this string tot he CBOR data it generates, but it will ignroe it |
529 | prepend this string to the CBOR data it generates, but it will ignore it |
277 | if present, so users can prepend this string as a "file type" indicator as |
530 | if present, so users can prepend this string as a "file type" indicator as |
278 | required. |
531 | required. |
279 | |
532 | |
280 | |
533 | |
|
|
534 | =head1 THE CBOR::XS::Tagged CLASS |
|
|
535 | |
|
|
536 | CBOR has the concept of tagged values - any CBOR value can be tagged with |
|
|
537 | a numeric 64 bit number, which are centrally administered. |
|
|
538 | |
|
|
539 | C<CBOR::XS> handles a few tags internally when en- or decoding. You can |
|
|
540 | also create tags yourself by encoding C<CBOR::XS::Tagged> objects, and the |
|
|
541 | decoder will create C<CBOR::XS::Tagged> objects itself when it hits an |
|
|
542 | unknown tag. |
|
|
543 | |
|
|
544 | These objects are simply blessed array references - the first member of |
|
|
545 | the array being the numerical tag, the second being the value. |
|
|
546 | |
|
|
547 | You can interact with C<CBOR::XS::Tagged> objects in the following ways: |
|
|
548 | |
|
|
549 | =over 4 |
|
|
550 | |
|
|
551 | =item $tagged = CBOR::XS::tag $tag, $value |
|
|
552 | |
|
|
553 | This function(!) creates a new C<CBOR::XS::Tagged> object using the given |
|
|
554 | C<$tag> (0..2**64-1) to tag the given C<$value> (which can be any Perl |
|
|
555 | value that can be encoded in CBOR, including serialisable Perl objects and |
|
|
556 | C<CBOR::XS::Tagged> objects). |
|
|
557 | |
|
|
558 | =item $tagged->[0] |
|
|
559 | |
|
|
560 | =item $tagged->[0] = $new_tag |
|
|
561 | |
|
|
562 | =item $tag = $tagged->tag |
|
|
563 | |
|
|
564 | =item $new_tag = $tagged->tag ($new_tag) |
|
|
565 | |
|
|
566 | Access/mutate the tag. |
|
|
567 | |
|
|
568 | =item $tagged->[1] |
|
|
569 | |
|
|
570 | =item $tagged->[1] = $new_value |
|
|
571 | |
|
|
572 | =item $value = $tagged->value |
|
|
573 | |
|
|
574 | =item $new_value = $tagged->value ($new_value) |
|
|
575 | |
|
|
576 | Access/mutate the tagged value. |
|
|
577 | |
|
|
578 | =back |
|
|
579 | |
|
|
580 | =cut |
|
|
581 | |
|
|
582 | sub tag($$) { |
|
|
583 | bless [@_], CBOR::XS::Tagged::; |
|
|
584 | } |
|
|
585 | |
|
|
586 | sub CBOR::XS::Tagged::tag { |
|
|
587 | $_[0][0] = $_[1] if $#_; |
|
|
588 | $_[0][0] |
|
|
589 | } |
|
|
590 | |
|
|
591 | sub CBOR::XS::Tagged::value { |
|
|
592 | $_[0][1] = $_[1] if $#_; |
|
|
593 | $_[0][1] |
|
|
594 | } |
|
|
595 | |
|
|
596 | =head2 EXAMPLES |
|
|
597 | |
|
|
598 | Here are some examples of C<CBOR::XS::Tagged> uses to tag objects. |
|
|
599 | |
|
|
600 | You can look up CBOR tag value and emanings in the IANA registry at |
|
|
601 | L<http://www.iana.org/assignments/cbor-tags/cbor-tags.xhtml>. |
|
|
602 | |
|
|
603 | Prepend a magic header (C<$CBOR::XS::MAGIC>): |
|
|
604 | |
|
|
605 | my $cbor = encode_cbor CBOR::XS::tag 55799, $value; |
|
|
606 | # same as: |
|
|
607 | my $cbor = $CBOR::XS::MAGIC . encode_cbor $value; |
|
|
608 | |
|
|
609 | Serialise some URIs and a regex in an array: |
|
|
610 | |
|
|
611 | my $cbor = encode_cbor [ |
|
|
612 | (CBOR::XS::tag 32, "http://www.nethype.de/"), |
|
|
613 | (CBOR::XS::tag 32, "http://software.schmorp.de/"), |
|
|
614 | (CBOR::XS::tag 35, "^[Pp][Ee][Rr][lL]\$"), |
|
|
615 | ]; |
|
|
616 | |
|
|
617 | Wrap CBOR data in CBOR: |
|
|
618 | |
|
|
619 | my $cbor_cbor = encode_cbor |
|
|
620 | CBOR::XS::tag 24, |
|
|
621 | encode_cbor [1, 2, 3]; |
|
|
622 | |
|
|
623 | =head1 TAG HANDLING AND EXTENSIONS |
|
|
624 | |
|
|
625 | This section describes how this module handles specific tagged values |
|
|
626 | and extensions. If a tag is not mentioned here and no additional filters |
|
|
627 | are provided for it, then the default handling applies (creating a |
|
|
628 | CBOR::XS::Tagged object on decoding, and only encoding the tag when |
|
|
629 | explicitly requested). |
|
|
630 | |
|
|
631 | Tags not handled specifically are currently converted into a |
|
|
632 | L<CBOR::XS::Tagged> object, which is simply a blessed array reference |
|
|
633 | consisting of the numeric tag value followed by the (decoded) CBOR value. |
|
|
634 | |
|
|
635 | Future versions of this module reserve the right to special case |
|
|
636 | additional tags (such as base64url). |
|
|
637 | |
|
|
638 | =head2 ENFORCED TAGS |
|
|
639 | |
|
|
640 | These tags are always handled when decoding, and their handling cannot be |
|
|
641 | overriden by the user. |
|
|
642 | |
|
|
643 | =over 4 |
|
|
644 | |
|
|
645 | =item <unassigned> (perl-object, L<http://cbor.schmorp.de/perl-object>) |
|
|
646 | |
|
|
647 | These tags are automatically created (and decoded) for serialisable |
|
|
648 | objects using the C<FREEZE/THAW> methods (the L<Types::Serialier> object |
|
|
649 | serialisation protocol). See L<OBJECT SERIALISATION> for details. |
|
|
650 | |
|
|
651 | =item <unassigned>, <unassigned> (sharable, sharedref, L <http://cbor.schmorp.de/value-sharing>) |
|
|
652 | |
|
|
653 | These tags are automatically decoded when encountered, resulting in |
|
|
654 | shared values in the decoded object. They are only encoded, however, when |
|
|
655 | C<allow_sharable> is enabled. |
|
|
656 | |
|
|
657 | =item <unassigned>, <unassigned> (stringref-namespace, stringref, L <http://cbor.schmorp.de/stringref>) |
|
|
658 | |
|
|
659 | These tags are automatically decoded when encountered. They are only |
|
|
660 | encoded, however, when C<allow_stringref> is enabled. |
|
|
661 | |
|
|
662 | =item 22098 (indirection, L<http://cbor.schmorp.de/indirection>) |
|
|
663 | |
|
|
664 | This tag is automatically generated when a reference are encountered (with |
|
|
665 | the exception of hash and array refernces). It is converted to a reference |
|
|
666 | when decoding. |
|
|
667 | |
|
|
668 | =item 55799 (self-describe CBOR, RFC 7049) |
|
|
669 | |
|
|
670 | This value is not generated on encoding (unless explicitly requested by |
|
|
671 | the user), and is simply ignored when decoding. |
|
|
672 | |
|
|
673 | =back |
|
|
674 | |
|
|
675 | =head2 OPTIONAL TAGS |
|
|
676 | |
|
|
677 | These tags have default filters provided when decoding. Their handling can |
|
|
678 | be overriden by changing the C<%CBOR::XS::FILTER> entry for the tag, or by |
|
|
679 | providing a custom C<filter> function when decoding. |
|
|
680 | |
|
|
681 | When they result in decoding into a specific Perl class, the module |
|
|
682 | usually provides a corresponding C<TO_CBOR> method as well. |
|
|
683 | |
|
|
684 | When any of these need to load additional modules that are not part of the |
|
|
685 | perl core distribution (e.g. L<URI>), it is (currently) up to the user to |
|
|
686 | provide these modules. The decoding usually fails with an exception if the |
|
|
687 | required module cannot be loaded. |
|
|
688 | |
|
|
689 | =over 4 |
|
|
690 | |
|
|
691 | =item 2, 3 (positive/negative bignum) |
|
|
692 | |
|
|
693 | These tags are decoded into L<Math::BigInt> objects. The corresponding |
|
|
694 | C<Math::BigInt::TO_CBOR> method encodes "small" bigints into normal CBOR |
|
|
695 | integers, and others into positive/negative CBOR bignums. |
|
|
696 | |
|
|
697 | =item 4, 5 (decimal fraction/bigfloat) |
|
|
698 | |
|
|
699 | Both decimal fractions and bigfloats are decoded into L<Math::BigFloat> |
|
|
700 | objects. The corresponding C<Math::BigFloat::TO_CBOR> method I<always> |
|
|
701 | encodes into a decimal fraction. |
|
|
702 | |
|
|
703 | CBOR cannot represent bigfloats with I<very> large exponents - conversion |
|
|
704 | of such big float objects is undefined. |
|
|
705 | |
|
|
706 | Also, NaN and infinities are not encoded properly. |
|
|
707 | |
|
|
708 | =item 21, 22, 23 (expected later JSON conversion) |
|
|
709 | |
|
|
710 | CBOR::XS is not a CBOR-to-JSON converter, and will simply ignore these |
|
|
711 | tags. |
|
|
712 | |
|
|
713 | =item 32 (URI) |
|
|
714 | |
|
|
715 | These objects decode into L<URI> objects. The corresponding |
|
|
716 | C<URI::TO_CBOR> method again results in a CBOR URI value. |
|
|
717 | |
|
|
718 | =back |
|
|
719 | |
|
|
720 | =cut |
|
|
721 | |
|
|
722 | our %FILTER = ( |
|
|
723 | # 0 # rfc4287 datetime, utf-8 |
|
|
724 | # 1 # unix timestamp, any |
|
|
725 | |
|
|
726 | 2 => sub { # pos bigint |
|
|
727 | require Math::BigInt; |
|
|
728 | Math::BigInt->new ("0x" . unpack "H*", pop) |
|
|
729 | }, |
|
|
730 | |
|
|
731 | 3 => sub { # neg bigint |
|
|
732 | require Math::BigInt; |
|
|
733 | -Math::BigInt->new ("0x" . unpack "H*", pop) |
|
|
734 | }, |
|
|
735 | |
|
|
736 | 4 => sub { # decimal fraction, array |
|
|
737 | require Math::BigFloat; |
|
|
738 | Math::BigFloat->new ($_[1][1] . "E" . $_[1][0]) |
|
|
739 | }, |
|
|
740 | |
|
|
741 | 5 => sub { # bigfloat, array |
|
|
742 | require Math::BigFloat; |
|
|
743 | scalar Math::BigFloat->new ($_[1][1])->blsft ($_[1][0], 2) |
|
|
744 | }, |
|
|
745 | |
|
|
746 | 21 => sub { pop }, # expected conversion to base64url encoding |
|
|
747 | 22 => sub { pop }, # expected conversion to base64 encoding |
|
|
748 | 23 => sub { pop }, # expected conversion to base16 encoding |
|
|
749 | |
|
|
750 | # 24 # embedded cbor, byte string |
|
|
751 | |
|
|
752 | 32 => sub { |
|
|
753 | require URI; |
|
|
754 | URI->new (pop) |
|
|
755 | }, |
|
|
756 | |
|
|
757 | # 33 # base64url rfc4648, utf-8 |
|
|
758 | # 34 # base64 rfc46484, utf-8 |
|
|
759 | # 35 # regex pcre/ecma262, utf-8 |
|
|
760 | # 36 # mime message rfc2045, utf-8 |
|
|
761 | ); |
|
|
762 | |
|
|
763 | |
281 | =head2 CBOR and JSON |
764 | =head1 CBOR and JSON |
282 | |
765 | |
283 | TODO |
766 | CBOR is supposed to implement a superset of the JSON data model, and is, |
|
|
767 | with some coercion, able to represent all JSON texts (something that other |
|
|
768 | "binary JSON" formats such as BSON generally do not support). |
|
|
769 | |
|
|
770 | CBOR implements some extra hints and support for JSON interoperability, |
|
|
771 | and the spec offers further guidance for conversion between CBOR and |
|
|
772 | JSON. None of this is currently implemented in CBOR, and the guidelines |
|
|
773 | in the spec do not result in correct round-tripping of data. If JSON |
|
|
774 | interoperability is improved in the future, then the goal will be to |
|
|
775 | ensure that decoded JSON data will round-trip encoding and decoding to |
|
|
776 | CBOR intact. |
284 | |
777 | |
285 | |
778 | |
286 | =head1 SECURITY CONSIDERATIONS |
779 | =head1 SECURITY CONSIDERATIONS |
287 | |
780 | |
288 | When you are using CBOR in a protocol, talking to untrusted potentially |
781 | When you are using CBOR in a protocol, talking to untrusted potentially |
… | |
… | |
356 | Please refrain from using rt.cpan.org or any other bug reporting |
849 | Please refrain from using rt.cpan.org or any other bug reporting |
357 | service. I put the contact address into my modules for a reason. |
850 | service. I put the contact address into my modules for a reason. |
358 | |
851 | |
359 | =cut |
852 | =cut |
360 | |
853 | |
361 | our $true = do { bless \(my $dummy = 1), "CBOR::XS::Boolean" }; |
854 | our %FILTER = ( |
362 | our $false = do { bless \(my $dummy = 0), "CBOR::XS::Boolean" }; |
855 | # 0 # rfc4287 datetime, utf-8 |
|
|
856 | # 1 # unix timestamp, any |
363 | |
857 | |
364 | sub true() { $true } |
858 | 2 => sub { # pos bigint |
365 | sub false() { $false } |
859 | require Math::BigInt; |
|
|
860 | Math::BigInt->new ("0x" . unpack "H*", pop) |
|
|
861 | }, |
366 | |
862 | |
367 | sub is_bool($) { |
863 | 3 => sub { # neg bigint |
368 | UNIVERSAL::isa $_[0], "CBOR::XS::Boolean" |
864 | require Math::BigInt; |
369 | # or UNIVERSAL::isa $_[0], "CBOR::Literal" |
865 | -Math::BigInt->new ("0x" . unpack "H*", pop) |
|
|
866 | }, |
|
|
867 | |
|
|
868 | 4 => sub { # decimal fraction, array |
|
|
869 | require Math::BigFloat; |
|
|
870 | Math::BigFloat->new ($_[1][1] . "E" . $_[1][0]) |
|
|
871 | }, |
|
|
872 | |
|
|
873 | 5 => sub { # bigfloat, array |
|
|
874 | require Math::BigFloat; |
|
|
875 | scalar Math::BigFloat->new ($_[1][1])->blsft ($_[1][0], 2) |
|
|
876 | }, |
|
|
877 | |
|
|
878 | 21 => sub { pop }, # expected conversion to base64url encoding |
|
|
879 | 22 => sub { pop }, # expected conversion to base64 encoding |
|
|
880 | 23 => sub { pop }, # expected conversion to base16 encoding |
|
|
881 | |
|
|
882 | # 24 # embedded cbor, byte string |
|
|
883 | |
|
|
884 | 32 => sub { |
|
|
885 | require URI; |
|
|
886 | URI->new (pop) |
|
|
887 | }, |
|
|
888 | |
|
|
889 | # 33 # base64url rfc4648, utf-8 |
|
|
890 | # 34 # base64 rfc46484, utf-8 |
|
|
891 | # 35 # regex pcre/ecma262, utf-8 |
|
|
892 | # 36 # mime message rfc2045, utf-8 |
|
|
893 | ); |
|
|
894 | |
|
|
895 | sub CBOR::XS::default_filter { |
|
|
896 | &{ $FILTER{$_[0]} or return } |
370 | } |
897 | } |
371 | |
898 | |
|
|
899 | sub URI::TO_CBOR { |
|
|
900 | my $uri = $_[0]->as_string; |
|
|
901 | utf8::upgrade $uri; |
|
|
902 | CBOR::XS::tag 32, $uri |
|
|
903 | } |
|
|
904 | |
|
|
905 | sub Math::BigInt::TO_CBOR { |
|
|
906 | if ($_[0] >= -2147483648 && $_[0] <= 2147483647) { |
|
|
907 | $_[0]->numify |
|
|
908 | } else { |
|
|
909 | my $hex = substr $_[0]->as_hex, 2; |
|
|
910 | $hex = "0$hex" if 1 & length $hex; # sigh |
|
|
911 | CBOR::XS::tag $_[0] >= 0 ? 2 : 3, pack "H*", $hex |
|
|
912 | } |
|
|
913 | } |
|
|
914 | |
|
|
915 | sub Math::BigFloat::TO_CBOR { |
|
|
916 | my ($m, $e) = $_[0]->parts; |
|
|
917 | CBOR::XS::tag 4, [$e->numify, $m] |
|
|
918 | } |
|
|
919 | |
372 | XSLoader::load "CBOR::XS", $VERSION; |
920 | XSLoader::load "CBOR::XS", $VERSION; |
373 | |
|
|
374 | package CBOR::XS::Boolean; |
|
|
375 | |
|
|
376 | use overload |
|
|
377 | "0+" => sub { ${$_[0]} }, |
|
|
378 | "++" => sub { $_[0] = ${$_[0]} + 1 }, |
|
|
379 | "--" => sub { $_[0] = ${$_[0]} - 1 }, |
|
|
380 | fallback => 1; |
|
|
381 | |
|
|
382 | 1; |
|
|
383 | |
921 | |
384 | =head1 SEE ALSO |
922 | =head1 SEE ALSO |
385 | |
923 | |
386 | The L<JSON> and L<JSON::XS> modules that do similar, but human-readable, |
924 | The L<JSON> and L<JSON::XS> modules that do similar, but human-readable, |
387 | serialisation. |
925 | serialisation. |
388 | |
926 | |
|
|
927 | The L<Types::Serialiser> module provides the data model for true, false |
|
|
928 | and error values. |
|
|
929 | |
389 | =head1 AUTHOR |
930 | =head1 AUTHOR |
390 | |
931 | |
391 | Marc Lehmann <schmorp@schmorp.de> |
932 | Marc Lehmann <schmorp@schmorp.de> |
392 | http://home.schmorp.de/ |
933 | http://home.schmorp.de/ |
393 | |
934 | |
394 | =cut |
935 | =cut |
395 | |
936 | |
|
|
937 | 1 |
|
|
938 | |