… | |
… | |
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 IS A PRE-ALPHA RELEASE! IT WILL CRASH, CORRUPT YOUR DATA |
22 | EAT YOUR CHILDREN! |
32 | AND EAT YOUR CHILDREN! (Actually, apart from being untested and a bit |
|
|
33 | feature-limited, it might already be useful). |
23 | |
34 | |
24 | This module converts Perl data structures to CBOR and vice versa. Its |
35 | This module converts Perl data structures to the Concise Binary Object |
|
|
36 | 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 |
|
|
38 | can represent something in JSON, you should be able to represent it in |
|
|
39 | CBOR. |
|
|
40 | |
|
|
41 | This makes it a faster and more compact binary alternative to JSON, with |
|
|
42 | the added ability of supporting serialising of perl objects. |
|
|
43 | |
25 | primary goal is to be I<correct> and its secondary goal is to be |
44 | 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. |
45 | is to be I<fast>. To reach the latter goal it was written in C. |
27 | |
46 | |
28 | See MAPPING, below, on how CBOR::XS maps perl values to CBOR values and |
47 | See MAPPING, below, on how CBOR::XS maps perl values to CBOR values and |
29 | vice versa. |
48 | vice versa. |
30 | |
49 | |
31 | =cut |
50 | =cut |
32 | |
51 | |
33 | package CBOR::XS; |
52 | package CBOR::XS; |
34 | |
53 | |
35 | use common::sense; |
54 | use common::sense; |
36 | |
55 | |
37 | our $VERSION = 0.02; |
56 | our $VERSION = 0.03; |
38 | our @ISA = qw(Exporter); |
57 | our @ISA = qw(Exporter); |
39 | |
58 | |
40 | our @EXPORT = qw(encode_cbor decode_cbor); |
59 | our @EXPORT = qw(encode_cbor decode_cbor); |
41 | |
60 | |
42 | use Exporter; |
61 | use Exporter; |
43 | use XSLoader; |
62 | use XSLoader; |
|
|
63 | |
|
|
64 | use Types::Serialiser; |
44 | |
65 | |
45 | our $MAGIC = "\xd9\xd9\xf7"; |
66 | our $MAGIC = "\xd9\xd9\xf7"; |
46 | |
67 | |
47 | =head1 FUNCTIONAL INTERFACE |
68 | =head1 FUNCTIONAL INTERFACE |
48 | |
69 | |
… | |
… | |
163 | |
184 | |
164 | =head2 CBOR -> PERL |
185 | =head2 CBOR -> PERL |
165 | |
186 | |
166 | =over 4 |
187 | =over 4 |
167 | |
188 | |
168 | =item True, False |
189 | =item integers |
169 | |
190 | |
170 | These CBOR values become C<CBOR::XS::true> and C<CBOR::XS::false>, |
191 | CBOR integers become (numeric) perl scalars. On perls without 64 bit |
|
|
192 | support, 64 bit integers will be truncated or otherwise corrupted. |
|
|
193 | |
|
|
194 | =item byte strings |
|
|
195 | |
|
|
196 | Byte strings will become octet strings in Perl (the byte values 0..255 |
|
|
197 | will simply become characters of the same value in Perl). |
|
|
198 | |
|
|
199 | =item UTF-8 strings |
|
|
200 | |
|
|
201 | UTF-8 strings in CBOR will be decoded, i.e. the UTF-8 octets will be |
|
|
202 | decoded into proper Unicode code points. At the moment, the validity of |
|
|
203 | the UTF-8 octets will not be validated - corrupt input will result in |
|
|
204 | corrupted Perl strings. |
|
|
205 | |
|
|
206 | =item arrays, maps |
|
|
207 | |
|
|
208 | CBOR arrays and CBOR maps will be converted into references to a Perl |
|
|
209 | array or hash, respectively. The keys of the map will be stringified |
|
|
210 | during this process. |
|
|
211 | |
|
|
212 | =item null |
|
|
213 | |
|
|
214 | CBOR null becomes C<undef> in Perl. |
|
|
215 | |
|
|
216 | =item true, false, undefined |
|
|
217 | |
|
|
218 | These CBOR values become C<Types:Serialiser::true>, |
|
|
219 | C<Types:Serialiser::false> and C<Types::Serialiser::error>, |
171 | respectively. They are overloaded to act almost exactly like the numbers |
220 | 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 |
221 | 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. |
222 | error). See the L<Types::Serialiser> manpage for details. |
174 | |
223 | |
175 | =item Null, Undefined |
224 | =item CBOR tag 256 (perl object) |
176 | |
225 | |
177 | CBOR Null and Undefined values becomes C<undef> in Perl (in the future, |
226 | The tag value C<256> (TODO: pending iana registration) will be used to |
178 | Undefined may raise an exception). |
227 | deserialise a Perl object. |
|
|
228 | |
|
|
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 | |
|
|
237 | =item CBOR tag 55799 (magic header) |
|
|
238 | |
|
|
239 | The tag 55799 is ignored (this tag implements the magic header). |
|
|
240 | |
|
|
241 | =item other CBOR tags |
|
|
242 | |
|
|
243 | Tagged items consists of a numeric tag and another CBOR value. Tags not |
|
|
244 | handled internally are currently converted into a L<CBOR::XS::Tagged> |
|
|
245 | object, which is simply a blessed array reference consisting of the |
|
|
246 | numeric tag value followed by the (decoded) CBOR value. |
|
|
247 | |
|
|
248 | In the future, support for user-supplied conversions might get added. |
|
|
249 | |
|
|
250 | =item anything else |
|
|
251 | |
|
|
252 | Anything else (e.g. unsupported simple values) will raise a decoding |
|
|
253 | error. |
179 | |
254 | |
180 | =back |
255 | =back |
181 | |
256 | |
182 | |
257 | |
183 | =head2 PERL -> CBOR |
258 | =head2 PERL -> CBOR |
… | |
… | |
188 | |
263 | |
189 | =over 4 |
264 | =over 4 |
190 | |
265 | |
191 | =item hash references |
266 | =item hash references |
192 | |
267 | |
193 | Perl hash references become CBOR maps. As there is no inherent ordering |
268 | 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 |
269 | hash keys (or CBOR maps), they will usually be encoded in a pseudo-random |
195 | pseudo-random order. |
270 | order. |
|
|
271 | |
|
|
272 | Currently, tied hashes will use the indefinite-length format, while normal |
|
|
273 | hashes will use the fixed-length format. |
196 | |
274 | |
197 | =item array references |
275 | =item array references |
198 | |
276 | |
199 | Perl array references become CBOR arrays. |
277 | Perl array references become fixed-length CBOR arrays. |
200 | |
278 | |
201 | =item other references |
279 | =item other references |
202 | |
280 | |
203 | Other unblessed references are generally not allowed and will cause an |
281 | 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 |
282 | 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. |
283 | C<1>, which get turned into false and true in CBOR. |
206 | |
284 | |
207 | =item CBOR::XS::true, CBOR::XS::false |
285 | =item CBOR::XS::Tagged objects |
208 | |
286 | |
|
|
287 | Objects of this type must be arrays consisting of a single C<[tag, value]> |
|
|
288 | pair. The (numerical) tag will be encoded as a CBOR tag, the value will be |
|
|
289 | encoded as appropriate for the value. |
|
|
290 | |
|
|
291 | =item Types::Serialiser::true, Types::Serialiser::false, Types::Serialiser::error |
|
|
292 | |
209 | These special values become CBOR True and CBOR False values, |
293 | 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. |
294 | values, respectively. You can also use C<\1>, C<\0> and C<\undef> directly |
|
|
295 | if you want. |
211 | |
296 | |
212 | =item blessed objects |
297 | =item blessed objects |
213 | |
298 | |
214 | Blessed objects are not directly representable in CBOR. TODO |
299 | Other blessed objects currently need to have a C<TO_CBOR> method. It |
215 | See the |
300 | will be called on every object that is being serialised, and must return |
216 | C<allow_blessed> and C<convert_blessed> methods on various options on |
301 | something that can be encoded in CBOR. |
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 | |
302 | |
221 | =item simple scalars |
303 | =item simple scalars |
222 | |
304 | |
223 | TODO |
305 | TODO |
224 | 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 |
225 | difficult objects to encode: CBOR::XS will encode undefined scalars as |
307 | 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 |
308 | 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: |
309 | before encoding as CBOR strings, and anything else as number value: |
228 | |
310 | |
229 | # dump as number |
311 | # dump as number |
230 | encode_cbor [2] # yields [2] |
312 | encode_cbor [2] # yields [2] |
231 | encode_cbor [-3.0e17] # yields [-3e+17] |
313 | encode_cbor [-3.0e17] # yields [-3e+17] |
… | |
… | |
253 | |
335 | |
254 | You can not currently force the type in other, less obscure, ways. Tell me |
336 | 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 |
337 | if you need this capability (but don't forget to explain why it's needed |
256 | :). |
338 | :). |
257 | |
339 | |
258 | Note that numerical precision has the same meaning as under Perl (so |
340 | 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 |
341 | representation. Floating-point values will use either the IEEE single |
260 | can differ to other languages). Also, your perl interpreter might expose |
342 | format if possible without loss of precision, otherwise the IEEE double |
261 | extensions to the floating point numbers of your platform, such as |
343 | 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 |
344 | represent numerical values are supported, but might suffer loss of |
263 | error to pass those in. |
345 | precision. |
264 | |
346 | |
265 | =back |
347 | =back |
266 | |
348 | |
267 | |
349 | |
268 | =head2 MAGIC HEADER |
350 | =head2 MAGIC HEADER |
… | |
… | |
278 | required. |
360 | required. |
279 | |
361 | |
280 | |
362 | |
281 | =head2 CBOR and JSON |
363 | =head2 CBOR and JSON |
282 | |
364 | |
283 | TODO |
365 | 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 |
|
|
367 | "binary JSON" formats such as BSON generally do not support). |
|
|
368 | |
|
|
369 | CBOR implements some extra hints and support for JSON interoperability, |
|
|
370 | and the spec offers further guidance for conversion between CBOR and |
|
|
371 | JSON. None of this is currently implemented in CBOR, and the guidelines |
|
|
372 | in the spec do not result in correct round-tripping of data. If JSON |
|
|
373 | interoperability is improved in the future, then the goal will be to |
|
|
374 | ensure that decoded JSON data will round-trip encoding and decoding to |
|
|
375 | CBOR intact. |
284 | |
376 | |
285 | |
377 | |
286 | =head1 SECURITY CONSIDERATIONS |
378 | =head1 SECURITY CONSIDERATIONS |
287 | |
379 | |
288 | When you are using CBOR in a protocol, talking to untrusted potentially |
380 | 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 |
448 | 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. |
449 | service. I put the contact address into my modules for a reason. |
358 | |
450 | |
359 | =cut |
451 | =cut |
360 | |
452 | |
361 | our $true = do { bless \(my $dummy = 1), "CBOR::XS::Boolean" }; |
|
|
362 | our $false = do { bless \(my $dummy = 0), "CBOR::XS::Boolean" }; |
|
|
363 | |
|
|
364 | sub true() { $true } |
|
|
365 | sub false() { $false } |
|
|
366 | |
|
|
367 | sub is_bool($) { |
|
|
368 | UNIVERSAL::isa $_[0], "CBOR::XS::Boolean" |
|
|
369 | # or UNIVERSAL::isa $_[0], "CBOR::Literal" |
|
|
370 | } |
|
|
371 | |
|
|
372 | XSLoader::load "CBOR::XS", $VERSION; |
453 | 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 | |
454 | |
384 | =head1 SEE ALSO |
455 | =head1 SEE ALSO |
385 | |
456 | |
386 | The L<JSON> and L<JSON::XS> modules that do similar, but human-readable, |
457 | The L<JSON> and L<JSON::XS> modules that do similar, but human-readable, |
387 | serialisation. |
458 | serialisation. |
388 | |
459 | |
|
|
460 | The L<Types::Serialiser> module provides the data model for true, false |
|
|
461 | and error values. |
|
|
462 | |
389 | =head1 AUTHOR |
463 | =head1 AUTHOR |
390 | |
464 | |
391 | Marc Lehmann <schmorp@schmorp.de> |
465 | Marc Lehmann <schmorp@schmorp.de> |
392 | http://home.schmorp.de/ |
466 | http://home.schmorp.de/ |
393 | |
467 | |
394 | =cut |
468 | =cut |
395 | |
469 | |
|
|
470 | 1 |
|
|
471 | |