… | |
… | |
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 to |
22 | EAT YOUR CHILDREN! |
32 | you to do). Furthermore, details of the implementation might change freely |
|
|
33 | before version 1.0. And lastly, the object serialisation protocol depends |
|
|
34 | on a pending IANA assignment, and until that assignment is official, this |
|
|
35 | implementation is not interoperable with other implementations (even |
|
|
36 | future versions of this 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 | |
25 | primary goal is to be I<correct> and its secondary goal is to be |
51 | 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. |
52 | is to be I<fast>. To reach the latter goal it was written in C. |
27 | |
53 | |
28 | See MAPPING, below, on how CBOR::XS maps perl values to CBOR values and |
54 | See MAPPING, below, on how CBOR::XS maps perl values to CBOR values and |
29 | vice versa. |
55 | vice versa. |
30 | |
56 | |
31 | =cut |
57 | =cut |
32 | |
58 | |
33 | package CBOR::XS; |
59 | package CBOR::XS; |
34 | |
60 | |
35 | use common::sense; |
61 | use common::sense; |
36 | |
62 | |
37 | our $VERSION = 0.02; |
63 | our $VERSION = 0.06; |
38 | our @ISA = qw(Exporter); |
64 | our @ISA = qw(Exporter); |
39 | |
65 | |
40 | our @EXPORT = qw(encode_cbor decode_cbor); |
66 | our @EXPORT = qw(encode_cbor decode_cbor); |
41 | |
67 | |
42 | use Exporter; |
68 | use Exporter; |
43 | use XSLoader; |
69 | use XSLoader; |
|
|
70 | |
|
|
71 | use Types::Serialiser; |
44 | |
72 | |
45 | our $MAGIC = "\xd9\xd9\xf7"; |
73 | our $MAGIC = "\xd9\xd9\xf7"; |
46 | |
74 | |
47 | =head1 FUNCTIONAL INTERFACE |
75 | =head1 FUNCTIONAL INTERFACE |
48 | |
76 | |
… | |
… | |
186 | |
214 | |
187 | CBOR arrays and CBOR maps will be converted into references to a Perl |
215 | CBOR arrays and CBOR maps will be converted into references to a Perl |
188 | array or hash, respectively. The keys of the map will be stringified |
216 | array or hash, respectively. The keys of the map will be stringified |
189 | during this process. |
217 | during this process. |
190 | |
218 | |
|
|
219 | =item null |
|
|
220 | |
|
|
221 | CBOR null becomes C<undef> in Perl. |
|
|
222 | |
191 | =item true, false |
223 | =item true, false, undefined |
192 | |
224 | |
193 | These CBOR values become C<CBOR::XS::true> and C<CBOR::XS::false>, |
225 | These CBOR values become C<Types:Serialiser::true>, |
|
|
226 | C<Types:Serialiser::false> and C<Types::Serialiser::error>, |
194 | respectively. They are overloaded to act almost exactly like the numbers |
227 | respectively. They are overloaded to act almost exactly like the numbers |
195 | C<1> and C<0>. You can check whether a scalar is a CBOR boolean by using |
228 | C<1> and C<0> (for true and false) or to throw an exception on access (for |
196 | the C<CBOR::XS::is_bool> function. |
229 | error). See the L<Types::Serialiser> manpage for details. |
197 | |
230 | |
198 | =item null, undefined |
231 | =item CBOR tag 256 (perl object) |
199 | |
232 | |
200 | CBOR null and undefined values becomes C<undef> in Perl (in the future, |
233 | The tag value C<256> (TODO: pending iana registration) will be used |
201 | Undefined may raise an exception or something else). |
234 | to deserialise a Perl object serialised with C<FREEZE>. See L<OBJECT |
|
|
235 | SERIALISATION>, below, for details. |
202 | |
236 | |
203 | =item tags |
237 | =item CBOR tag 55799 (magic header) |
204 | |
238 | |
|
|
239 | The tag 55799 is ignored (this tag implements the magic header). |
|
|
240 | |
|
|
241 | =item other CBOR tags |
|
|
242 | |
205 | Tagged items consists of a numeric tag and another CBOR value. The tag |
243 | Tagged items consists of a numeric tag and another CBOR value. Tags not |
206 | 55799 is ignored (this tag implements the magic header). |
244 | handled internally are currently converted into a L<CBOR::XS::Tagged> |
207 | |
|
|
208 | All other tags are currently converted into a L<CBOR::XS::Tagged> object, |
|
|
209 | which is simply a blessed array reference consistsing of the numeric tag |
245 | object, which is simply a blessed array reference consisting of the |
210 | value followed by the (decoded) BOR value. |
246 | numeric tag value followed by the (decoded) CBOR value. |
|
|
247 | |
|
|
248 | In the future, support for user-supplied conversions might get added. |
211 | |
249 | |
212 | =item anything else |
250 | =item anything else |
213 | |
251 | |
214 | Anything else (e.g. unsupported simple values) will raise a decoding |
252 | Anything else (e.g. unsupported simple values) will raise a decoding |
215 | error. |
253 | error. |
… | |
… | |
245 | C<1>, which get turned into false and true in CBOR. |
283 | C<1>, which get turned into false and true in CBOR. |
246 | |
284 | |
247 | =item CBOR::XS::Tagged objects |
285 | =item CBOR::XS::Tagged objects |
248 | |
286 | |
249 | Objects of this type must be arrays consisting of a single C<[tag, value]> |
287 | Objects of this type must be arrays consisting of a single C<[tag, value]> |
250 | pair. The (numerical) tag will be encoded as a CBOR tag, the value will be |
288 | pair. The (numerical) tag will be encoded as a CBOR tag, the value will |
251 | encoded as appropriate for the value. |
289 | be encoded as appropriate for the value. You cna use C<CBOR::XS::tag> to |
|
|
290 | create such objects. |
252 | |
291 | |
253 | =item CBOR::XS::true, CBOR::XS::false |
292 | =item Types::Serialiser::true, Types::Serialiser::false, Types::Serialiser::error |
254 | |
293 | |
255 | These special values become CBOR true and CBOR false values, |
294 | These special values become CBOR true, CBOR false and CBOR undefined |
256 | respectively. You can also use C<\1> and C<\0> directly if you want. |
295 | values, respectively. You can also use C<\1>, C<\0> and C<\undef> directly |
|
|
296 | if you want. |
257 | |
297 | |
258 | =item blessed objects |
298 | =item other blessed objects |
259 | |
299 | |
260 | Other blessed objects currently need to have a C<TO_CBOR> method. It |
300 | Other blessed objects are serialised via C<TO_CBOR> or C<FREEZE>. See |
261 | will be called on every object that is being serialised, and must return |
301 | L<OBJECT SERIALISATION>, below, for details. |
262 | something that can be encoded in CBOR. |
|
|
263 | |
302 | |
264 | =item simple scalars |
303 | =item simple scalars |
265 | |
304 | |
266 | TODO |
305 | TODO |
267 | Simple Perl scalars (any scalar that is not a reference) are the most |
306 | Simple Perl scalars (any scalar that is not a reference) are the most |
… | |
… | |
305 | represent numerical values are supported, but might suffer loss of |
344 | represent numerical values are supported, but might suffer loss of |
306 | precision. |
345 | precision. |
307 | |
346 | |
308 | =back |
347 | =back |
309 | |
348 | |
|
|
349 | =head2 OBJECT SERIALISATION |
310 | |
350 | |
|
|
351 | This module knows two way to serialise a Perl object: The CBOR-specific |
|
|
352 | way, and the generic way. |
|
|
353 | |
|
|
354 | Whenever the encoder encounters a Perl object that it cnanot serialise |
|
|
355 | directly (most of them), it will first look up the C<TO_CBOR> method on |
|
|
356 | it. |
|
|
357 | |
|
|
358 | If it has a C<TO_CBOR> method, it will call it with the object as only |
|
|
359 | argument, and expects exactly one return value, which it will then |
|
|
360 | substitute and encode it in the place of the object. |
|
|
361 | |
|
|
362 | Otherwise, it will look up the C<FREEZE> method. If it exists, it will |
|
|
363 | call it with the object as first argument, and the constant string C<CBOR> |
|
|
364 | as the second argument, to distinguish it from other serialisers. |
|
|
365 | |
|
|
366 | The C<FREEZE> method can return any number of values (i.e. zero or |
|
|
367 | more). These will be encoded as CBOR perl object, together with the |
|
|
368 | classname. |
|
|
369 | |
|
|
370 | If an object supports neither C<TO_CBOR> nor C<FREEZE>, encoding will fail |
|
|
371 | with an error. |
|
|
372 | |
|
|
373 | Objects encoded via C<TO_CBOR> cannot be automatically decoded, but |
|
|
374 | objects encoded via C<FREEZE> can be decoded using the following protocol: |
|
|
375 | |
|
|
376 | When an encoded CBOR perl object is encountered by the decoder, it will |
|
|
377 | look up the C<THAW> method, by using the stored classname, and will fail |
|
|
378 | if the method cannot be found. |
|
|
379 | |
|
|
380 | After the lookup it will call the C<THAW> method with the stored classname |
|
|
381 | as first argument, the constant string C<CBOR> as second argument, and all |
|
|
382 | values returned by C<FREEZE> as remaining arguments. |
|
|
383 | |
|
|
384 | =head4 EXAMPLES |
|
|
385 | |
|
|
386 | Here is an example C<TO_CBOR> method: |
|
|
387 | |
|
|
388 | sub My::Object::TO_CBOR { |
|
|
389 | my ($obj) = @_; |
|
|
390 | |
|
|
391 | ["this is a serialised My::Object object", $obj->{id}] |
|
|
392 | } |
|
|
393 | |
|
|
394 | When a C<My::Object> is encoded to CBOR, it will instead encode a simple |
|
|
395 | array with two members: a string, and the "object id". Decoding this CBOR |
|
|
396 | string will yield a normal perl array reference in place of the object. |
|
|
397 | |
|
|
398 | A more useful and practical example would be a serialisation method for |
|
|
399 | the URI module. CBOR has a custom tag value for URIs, namely 32: |
|
|
400 | |
|
|
401 | sub URI::TO_CBOR { |
|
|
402 | my ($self) = @_; |
|
|
403 | my $uri = "$self"; # stringify uri |
|
|
404 | utf8::upgrade $uri; # make sure it will be encoded as UTF-8 string |
|
|
405 | CBOR::XS::tagged 32, "$_[0]" |
|
|
406 | } |
|
|
407 | |
|
|
408 | This will encode URIs as a UTF-8 string with tag 32, which indicates an |
|
|
409 | URI. |
|
|
410 | |
|
|
411 | Decoding such an URI will not (currently) give you an URI object, but |
|
|
412 | instead a CBOR::XS::Tagged object with tag number 32 and the string - |
|
|
413 | exactly what was returned by C<TO_CBOR>. |
|
|
414 | |
|
|
415 | To serialise an object so it can automatically be deserialised, you need |
|
|
416 | to use C<FREEZE> and C<THAW>. To take the URI module as example, this |
|
|
417 | would be a possible implementation: |
|
|
418 | |
|
|
419 | sub URI::FREEZE { |
|
|
420 | my ($self, $serialiser) = @_; |
|
|
421 | "$self" # encode url string |
|
|
422 | } |
|
|
423 | |
|
|
424 | sub URI::THAW { |
|
|
425 | my ($class, $serialiser, $uri) = @_; |
|
|
426 | |
|
|
427 | $class->new ($uri) |
|
|
428 | } |
|
|
429 | |
|
|
430 | Unlike C<TO_CBOR>, multiple values can be returned by C<FREEZE>. For |
|
|
431 | example, a C<FREEZE> method that returns "type", "id" and "variant" values |
|
|
432 | would cause an invocation of C<THAW> with 5 arguments: |
|
|
433 | |
|
|
434 | sub My::Object::FREEZE { |
|
|
435 | my ($self, $serialiser) = @_; |
|
|
436 | |
|
|
437 | ($self->{type}, $self->{id}, $self->{variant}) |
|
|
438 | } |
|
|
439 | |
|
|
440 | sub My::Object::THAW { |
|
|
441 | my ($class, $serialiser, $type, $id, $variant) = @_; |
|
|
442 | |
|
|
443 | $class-<new (type => $type, id => $id, variant => $variant) |
|
|
444 | } |
|
|
445 | |
|
|
446 | |
311 | =head2 MAGIC HEADER |
447 | =head1 MAGIC HEADER |
312 | |
448 | |
313 | There is no way to distinguish CBOR from other formats |
449 | There is no way to distinguish CBOR from other formats |
314 | programmatically. To make it easier to distinguish CBOR from other |
450 | programmatically. To make it easier to distinguish CBOR from other |
315 | formats, the CBOR specification has a special "magic string" that can be |
451 | formats, the CBOR specification has a special "magic string" that can be |
316 | prepended to any CBOR string without changing it's meaning. |
452 | prepended to any CBOR string without changing it's meaning. |
… | |
… | |
319 | prepend this string tot he CBOR data it generates, but it will ignroe it |
455 | prepend this string tot he CBOR data it generates, but it will ignroe it |
320 | if present, so users can prepend this string as a "file type" indicator as |
456 | if present, so users can prepend this string as a "file type" indicator as |
321 | required. |
457 | required. |
322 | |
458 | |
323 | |
459 | |
|
|
460 | =head1 THE CBOR::XS::Tagged CLASS |
|
|
461 | |
|
|
462 | CBOR has the concept of tagged values - any CBOR value can be tagged with |
|
|
463 | a numeric 64 bit number, which are centrally administered. |
|
|
464 | |
|
|
465 | C<CBOR::XS> handles a few tags internally when en- or decoding. You can |
|
|
466 | also create tags yourself by encoding C<CBOR::XS::Tagged> objects, and the |
|
|
467 | decoder will create C<CBOR::XS::Tagged> objects itself when it hits an |
|
|
468 | unknown tag. |
|
|
469 | |
|
|
470 | These objects are simply blessed array references - the first member of |
|
|
471 | the array being the numerical tag, the second being the value. |
|
|
472 | |
|
|
473 | You can interact with C<CBOR::XS::Tagged> objects in the following ways: |
|
|
474 | |
|
|
475 | =over 4 |
|
|
476 | |
|
|
477 | =item $tagged = CBOR::XS::tag $tag, $value |
|
|
478 | |
|
|
479 | This function(!) creates a new C<CBOR::XS::Tagged> object using the given |
|
|
480 | C<$tag> (0..2**64-1) to tag the given C<$value> (which can be any Perl |
|
|
481 | value that can be encoded in CBOR, including serialisable Perl objects and |
|
|
482 | C<CBOR::XS::Tagged> objects). |
|
|
483 | |
|
|
484 | =item $tagged->[0] |
|
|
485 | |
|
|
486 | =item $tagged->[0] = $new_tag |
|
|
487 | |
|
|
488 | =item $tag = $tagged->tag |
|
|
489 | |
|
|
490 | =item $new_tag = $tagged->tag ($new_tag) |
|
|
491 | |
|
|
492 | Access/mutate the tag. |
|
|
493 | |
|
|
494 | =item $tagged->[1] |
|
|
495 | |
|
|
496 | =item $tagged->[1] = $new_value |
|
|
497 | |
|
|
498 | =item $value = $tagged->value |
|
|
499 | |
|
|
500 | =item $new_value = $tagged->value ($new_value) |
|
|
501 | |
|
|
502 | Access/mutate the tagged value. |
|
|
503 | |
|
|
504 | =back |
|
|
505 | |
|
|
506 | =cut |
|
|
507 | |
|
|
508 | sub tag($$) { |
|
|
509 | bless [@_], CBOR::XS::Tagged::; |
|
|
510 | } |
|
|
511 | |
|
|
512 | sub CBOR::XS::Tagged::tag { |
|
|
513 | $_[0][0] = $_[1] if $#_; |
|
|
514 | $_[0][0] |
|
|
515 | } |
|
|
516 | |
|
|
517 | sub CBOR::XS::Tagged::value { |
|
|
518 | $_[0][1] = $_[1] if $#_; |
|
|
519 | $_[0][1] |
|
|
520 | } |
|
|
521 | |
|
|
522 | =head2 EXAMPLES |
|
|
523 | |
|
|
524 | Here are some examples of C<CBOR::XS::Tagged> uses to tag objects. |
|
|
525 | |
|
|
526 | You can look up CBOR tag value and emanings in the IANA registry at |
|
|
527 | L<http://www.iana.org/assignments/cbor-tags/cbor-tags.xhtml>. |
|
|
528 | |
|
|
529 | Prepend a magic header (C<$CBOR::XS::MAGIC>): |
|
|
530 | |
|
|
531 | my $cbor = encode_cbor CBOR::XS::tag 55799, $value; |
|
|
532 | # same as: |
|
|
533 | my $cbor = $CBOR::XS::MAGIC . encode_cbor $value; |
|
|
534 | |
|
|
535 | Serialise some URIs and a regex in an array: |
|
|
536 | |
|
|
537 | my $cbor = encode_cbor [ |
|
|
538 | (CBOR::XS::tag 32, "http://www.nethype.de/"), |
|
|
539 | (CBOR::XS::tag 32, "http://software.schmorp.de/"), |
|
|
540 | (CBOR::XS::tag 35, "^[Pp][Ee][Rr][lL]\$"), |
|
|
541 | ]; |
|
|
542 | |
|
|
543 | Wrap CBOR data in CBOR: |
|
|
544 | |
|
|
545 | my $cbor_cbor = encode_cbor |
|
|
546 | CBOR::XS::tag 24, |
|
|
547 | encode_cbor [1, 2, 3]; |
|
|
548 | |
324 | =head2 CBOR and JSON |
549 | =head1 CBOR and JSON |
325 | |
550 | |
326 | CBOR is supposed to implement a superset of the JSON data model, and is, |
551 | CBOR is supposed to implement a superset of the JSON data model, and is, |
327 | with some coercion, able to represent all JSON texts (something that other |
552 | with some coercion, able to represent all JSON texts (something that other |
328 | "binary JSON" formats such as BSON generally do not support). |
553 | "binary JSON" formats such as BSON generally do not support). |
329 | |
554 | |
… | |
… | |
409 | Please refrain from using rt.cpan.org or any other bug reporting |
634 | Please refrain from using rt.cpan.org or any other bug reporting |
410 | service. I put the contact address into my modules for a reason. |
635 | service. I put the contact address into my modules for a reason. |
411 | |
636 | |
412 | =cut |
637 | =cut |
413 | |
638 | |
414 | our $true = do { bless \(my $dummy = 1), "CBOR::XS::Boolean" }; |
|
|
415 | our $false = do { bless \(my $dummy = 0), "CBOR::XS::Boolean" }; |
|
|
416 | |
|
|
417 | sub true() { $true } |
|
|
418 | sub false() { $false } |
|
|
419 | |
|
|
420 | sub is_bool($) { |
|
|
421 | UNIVERSAL::isa $_[0], "CBOR::XS::Boolean" |
|
|
422 | # or UNIVERSAL::isa $_[0], "CBOR::Literal" |
|
|
423 | } |
|
|
424 | |
|
|
425 | XSLoader::load "CBOR::XS", $VERSION; |
639 | XSLoader::load "CBOR::XS", $VERSION; |
426 | |
|
|
427 | package CBOR::XS::Boolean; |
|
|
428 | |
|
|
429 | use overload |
|
|
430 | "0+" => sub { ${$_[0]} }, |
|
|
431 | "++" => sub { $_[0] = ${$_[0]} + 1 }, |
|
|
432 | "--" => sub { $_[0] = ${$_[0]} - 1 }, |
|
|
433 | fallback => 1; |
|
|
434 | |
|
|
435 | 1; |
|
|
436 | |
640 | |
437 | =head1 SEE ALSO |
641 | =head1 SEE ALSO |
438 | |
642 | |
439 | The L<JSON> and L<JSON::XS> modules that do similar, but human-readable, |
643 | The L<JSON> and L<JSON::XS> modules that do similar, but human-readable, |
440 | serialisation. |
644 | serialisation. |
441 | |
645 | |
|
|
646 | The L<Types::Serialiser> module provides the data model for true, false |
|
|
647 | and error values. |
|
|
648 | |
442 | =head1 AUTHOR |
649 | =head1 AUTHOR |
443 | |
650 | |
444 | Marc Lehmann <schmorp@schmorp.de> |
651 | Marc Lehmann <schmorp@schmorp.de> |
445 | http://home.schmorp.de/ |
652 | http://home.schmorp.de/ |
446 | |
653 | |
447 | =cut |
654 | =cut |
448 | |
655 | |
|
|
656 | 1 |
|
|
657 | |