… | |
… | |
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 |
31 | WARNING! This module is very new, and not very well tested (that's up to |
32 | AND EAT YOUR CHILDREN! (Actually, apart from being untested and a bit |
32 | you to do). Furthermore, details of the implementation might change freely |
33 | feature-limited, it might already be useful). |
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. |
|
|
37 | |
|
|
38 | You are still invited to try out CBOR, and this module. |
34 | |
39 | |
35 | This module converts Perl data structures to the Concise Binary Object |
40 | This module converts Perl data structures to the Concise Binary Object |
36 | Representation (CBOR) and vice versa. CBOR is a fast binary serialisation |
41 | 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 |
42 | format that aims to use a superset of the JSON data model, i.e. when you |
38 | can represent something in JSON, you should be able to represent it in |
43 | can represent something in JSON, you should be able to represent it in |
39 | CBOR. |
44 | CBOR. |
40 | |
45 | |
41 | This makes it a faster and more compact binary alternative to JSON, with |
46 | In short, CBOR is a faster and very compact binary alternative to JSON, |
42 | the added ability of supporting serialising of perl objects. |
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). |
43 | |
50 | |
44 | The primary goal of this module is to be I<correct> and the secondary goal |
51 | 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. |
52 | is to be I<fast>. To reach the latter goal it was written in C. |
46 | |
53 | |
47 | 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 |
… | |
… | |
51 | |
58 | |
52 | package CBOR::XS; |
59 | package CBOR::XS; |
53 | |
60 | |
54 | use common::sense; |
61 | use common::sense; |
55 | |
62 | |
56 | our $VERSION = 0.03; |
63 | our $VERSION = 0.05; |
57 | our @ISA = qw(Exporter); |
64 | our @ISA = qw(Exporter); |
58 | |
65 | |
59 | our @EXPORT = qw(encode_cbor decode_cbor); |
66 | our @EXPORT = qw(encode_cbor decode_cbor); |
60 | |
67 | |
61 | use Exporter; |
68 | use Exporter; |
… | |
… | |
221 | C<1> and C<0> (for true and false) or to throw an exception on access (for |
228 | 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. |
229 | error). See the L<Types::Serialiser> manpage for details. |
223 | |
230 | |
224 | =item CBOR tag 256 (perl object) |
231 | =item CBOR tag 256 (perl object) |
225 | |
232 | |
226 | The tag value C<256> (TODO: pending iana registration) will be used to |
233 | The tag value C<256> (TODO: pending iana registration) will be used |
227 | deserialise a Perl object. |
234 | to deserialise a Perl object serialised with C<FREEZE>. See L<OBJECT |
228 | |
235 | SERIALISATION>, below, for details. |
229 | TODO For this to work, the class must be loaded and must have a |
|
|
230 | C<FROM_CBOR> method. The decoder will then call the C<FROM_CBOR> method |
|
|
231 | with the constructor arguments provided by the C<TO_CBOR> method (see |
|
|
232 | below). |
|
|
233 | |
|
|
234 | The C<FROM_CBOR> method must return a single value that will then be used |
|
|
235 | as the deserialised value. |
|
|
236 | |
236 | |
237 | =item CBOR tag 55799 (magic header) |
237 | =item CBOR tag 55799 (magic header) |
238 | |
238 | |
239 | The tag 55799 is ignored (this tag implements the magic header). |
239 | The tag 55799 is ignored (this tag implements the magic header). |
240 | |
240 | |
… | |
… | |
292 | |
292 | |
293 | These special values become CBOR true, CBOR false and CBOR undefined |
293 | These special values become CBOR true, CBOR false and CBOR undefined |
294 | values, respectively. You can also use C<\1>, C<\0> and C<\undef> directly |
294 | values, respectively. You can also use C<\1>, C<\0> and C<\undef> directly |
295 | if you want. |
295 | if you want. |
296 | |
296 | |
297 | =item blessed objects |
297 | =item other blessed objects |
298 | |
298 | |
299 | Other blessed objects currently need to have a C<TO_CBOR> method. It |
299 | Other blessed objects are serialised via C<TO_CBOR> or C<FREEZE>. See |
300 | will be called on every object that is being serialised, and must return |
300 | L<OBJECT SERIALISATION>, below, for details. |
301 | something that can be encoded in CBOR. |
|
|
302 | |
301 | |
303 | =item simple scalars |
302 | =item simple scalars |
304 | |
303 | |
305 | TODO |
304 | TODO |
306 | Simple Perl scalars (any scalar that is not a reference) are the most |
305 | Simple Perl scalars (any scalar that is not a reference) are the most |
… | |
… | |
344 | represent numerical values are supported, but might suffer loss of |
343 | represent numerical values are supported, but might suffer loss of |
345 | precision. |
344 | precision. |
346 | |
345 | |
347 | =back |
346 | =back |
348 | |
347 | |
|
|
348 | =head2 OBJECT SERIALISATION |
349 | |
349 | |
|
|
350 | This module knows two way to serialise a Perl object: The CBOR-specific |
|
|
351 | way, and the generic way. |
|
|
352 | |
|
|
353 | Whenever the encoder encounters a Perl object that it cnanot serialise |
|
|
354 | directly (most of them), it will first look up the C<TO_CBOR> method on |
|
|
355 | it. |
|
|
356 | |
|
|
357 | If it has a C<TO_CBOR> method, it will call it with the object as only |
|
|
358 | argument, and expects exactly one return value, which it will then |
|
|
359 | substitute and encode it in the place of the object. |
|
|
360 | |
|
|
361 | Otherwise, it will look up the C<FREEZE> method. If it exists, it will |
|
|
362 | call it with the object as first argument, and the constant string C<CBOR> |
|
|
363 | as the second argument, to distinguish it from other serialisers. |
|
|
364 | |
|
|
365 | The C<FREEZE> method can return any number of values (i.e. zero or |
|
|
366 | more). These will be encoded as CBOR perl object, together with the |
|
|
367 | classname. |
|
|
368 | |
|
|
369 | If an object supports neither C<TO_CBOR> nor C<FREEZE>, encoding will fail |
|
|
370 | with an error. |
|
|
371 | |
|
|
372 | Objects encoded via C<TO_CBOR> cannot be automatically decoded, but |
|
|
373 | objects encoded via C<FREEZE> can be decoded using the following protocol: |
|
|
374 | |
|
|
375 | When an encoded CBOR perl object is encountered by the decoder, it will |
|
|
376 | look up the C<THAW> method, by using the stored classname, and will fail |
|
|
377 | if the method cannot be found. |
|
|
378 | |
|
|
379 | After the lookup it will call the C<THAW> method with the stored classname |
|
|
380 | as first argument, the constant string C<CBOR> as second argument, and all |
|
|
381 | values returned by C<FREEZE> as remaining arguments. |
|
|
382 | |
|
|
383 | =head4 EXAMPLES |
|
|
384 | |
|
|
385 | Here is an example C<TO_CBOR> method: |
|
|
386 | |
|
|
387 | sub My::Object::TO_CBOR { |
|
|
388 | my ($obj) = @_; |
|
|
389 | |
|
|
390 | ["this is a serialised My::Object object", $obj->{id}] |
|
|
391 | } |
|
|
392 | |
|
|
393 | When a C<My::Object> is encoded to CBOR, it will instead encode a simple |
|
|
394 | array with two members: a string, and the "object id". Decoding this CBOR |
|
|
395 | string will yield a normal perl array reference in place of the object. |
|
|
396 | |
|
|
397 | A more useful and practical example would be a serialisation method for |
|
|
398 | the URI module. CBOR has a custom tag value for URIs, namely 32: |
|
|
399 | |
|
|
400 | sub URI::TO_CBOR { |
|
|
401 | my ($self) = @_; |
|
|
402 | my $uri = "$self"; # stringify uri |
|
|
403 | utf8::upgrade $uri; # make sure it will be encoded as UTF-8 string |
|
|
404 | CBOR::XS::tagged 32, "$_[0]" |
|
|
405 | } |
|
|
406 | |
|
|
407 | This will encode URIs as a UTF-8 string with tag 32, which indicates an |
|
|
408 | URI. |
|
|
409 | |
|
|
410 | Decoding such an URI will not (currently) give you an URI object, but |
|
|
411 | instead a CBOR::XS::Tagged object with tag number 32 and the string - |
|
|
412 | exactly what was returned by C<TO_CBOR>. |
|
|
413 | |
|
|
414 | To serialise an object so it can automatically be deserialised, you need |
|
|
415 | to use C<FREEZE> and C<THAW>. To take the URI module as example, this |
|
|
416 | would be a possible implementation: |
|
|
417 | |
|
|
418 | sub URI::FREEZE { |
|
|
419 | my ($self, $serialiser) = @_; |
|
|
420 | "$self" # encode url string |
|
|
421 | } |
|
|
422 | |
|
|
423 | sub URI::THAW { |
|
|
424 | my ($class, $serialiser, $uri) = @_; |
|
|
425 | |
|
|
426 | $class->new ($uri) |
|
|
427 | } |
|
|
428 | |
|
|
429 | Unlike C<TO_CBOR>, multiple values can be returned by C<FREEZE>. For |
|
|
430 | example, a C<FREEZE> method that returns "type", "id" and "variant" values |
|
|
431 | would cause an invocation of C<THAW> with 5 arguments: |
|
|
432 | |
|
|
433 | sub My::Object::FREEZE { |
|
|
434 | my ($self, $serialiser) = @_; |
|
|
435 | |
|
|
436 | ($self->{type}, $self->{id}, $self->{variant}) |
|
|
437 | } |
|
|
438 | |
|
|
439 | sub My::Object::THAW { |
|
|
440 | my ($class, $serialiser, $type, $id, $variant) = @_; |
|
|
441 | |
|
|
442 | $class-<new (type => $type, id => $id, variant => $variant) |
|
|
443 | } |
|
|
444 | |
|
|
445 | |
350 | =head2 MAGIC HEADER |
446 | =head1 MAGIC HEADER |
351 | |
447 | |
352 | There is no way to distinguish CBOR from other formats |
448 | There is no way to distinguish CBOR from other formats |
353 | programmatically. To make it easier to distinguish CBOR from other |
449 | programmatically. To make it easier to distinguish CBOR from other |
354 | formats, the CBOR specification has a special "magic string" that can be |
450 | formats, the CBOR specification has a special "magic string" that can be |
355 | prepended to any CBOR string without changing it's meaning. |
451 | prepended to any CBOR string without changing it's meaning. |
… | |
… | |
358 | prepend this string tot he CBOR data it generates, but it will ignroe it |
454 | prepend this string tot he CBOR data it generates, but it will ignroe it |
359 | if present, so users can prepend this string as a "file type" indicator as |
455 | if present, so users can prepend this string as a "file type" indicator as |
360 | required. |
456 | required. |
361 | |
457 | |
362 | |
458 | |
363 | =head2 CBOR and JSON |
459 | =head1 CBOR and JSON |
364 | |
460 | |
365 | CBOR is supposed to implement a superset of the JSON data model, and is, |
461 | CBOR is supposed to implement a superset of the JSON data model, and is, |
366 | with some coercion, able to represent all JSON texts (something that other |
462 | with some coercion, able to represent all JSON texts (something that other |
367 | "binary JSON" formats such as BSON generally do not support). |
463 | "binary JSON" formats such as BSON generally do not support). |
368 | |
464 | |