… | |
… | |
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 module is very new, and not very well tested (that's up to |
|
|
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. |
|
|
37 | |
|
|
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 |
31 | This module converts Perl data structures to the Concise Binary Object |
41 | Representation (CBOR) and vice versa. CBOR is a fast binary serialisation |
32 | 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 |
33 | format that aims to use an (almost) superset of the JSON data model, i.e. |
43 | 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 |
44 | CBOR. |
35 | represent it in CBOR. |
45 | |
36 | |
46 | In short, CBOR is a faster and very compact binary alternative to JSON, |
37 | In short, CBOR is a faster and quite compact binary alternative to JSON, |
47 | with the added ability of supporting serialisation of Perl objects. (JSON |
38 | 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 |
39 | often compresses better than CBOR though, so if you plan to compress the |
49 | data later you might want to compare both formats first). |
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). |
50 | |
56 | |
51 | 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 |
52 | 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. |
53 | |
59 | |
54 | 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 |
… | |
… | |
58 | |
64 | |
59 | package CBOR::XS; |
65 | package CBOR::XS; |
60 | |
66 | |
61 | use common::sense; |
67 | use common::sense; |
62 | |
68 | |
63 | our $VERSION = 0.05; |
69 | our $VERSION = 1.11; |
64 | our @ISA = qw(Exporter); |
70 | our @ISA = qw(Exporter); |
65 | |
71 | |
66 | our @EXPORT = qw(encode_cbor decode_cbor); |
72 | our @EXPORT = qw(encode_cbor decode_cbor); |
67 | |
73 | |
68 | use Exporter; |
74 | use Exporter; |
… | |
… | |
105 | strings. All boolean flags described below are by default I<disabled>. |
111 | strings. All boolean flags described below are by default I<disabled>. |
106 | |
112 | |
107 | 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 |
108 | be chained: |
114 | be chained: |
109 | |
115 | |
110 | #TODO |
|
|
111 | my $cbor = CBOR::XS->new->encode ({a => [1,2]}); |
116 | my $cbor = CBOR::XS->new->encode ({a => [1,2]}); |
112 | |
117 | |
113 | =item $cbor = $cbor->max_depth ([$maximum_nesting_depth]) |
118 | =item $cbor = $cbor->max_depth ([$maximum_nesting_depth]) |
114 | |
119 | |
115 | =item $max_depth = $cbor->get_max_depth |
120 | =item $max_depth = $cbor->get_max_depth |
… | |
… | |
149 | 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 |
150 | C<0> is specified). |
155 | C<0> is specified). |
151 | |
156 | |
152 | 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. |
153 | |
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 | This option does not affect C<encode> in any way - shared values and |
|
|
224 | references will always be decoded properly if present. |
|
|
225 | |
|
|
226 | =item $cbor = $cbor->pack_strings ([$enable]) |
|
|
227 | |
|
|
228 | =item $enabled = $cbor->get_pack_strings |
|
|
229 | |
|
|
230 | If C<$enable> is true (or missing), then C<encode> will try not to encode |
|
|
231 | the same string twice, but will instead encode a reference to the string |
|
|
232 | instead. Depending on your data format, this can save a lot of space, but |
|
|
233 | also results in a very large runtime overhead (expect encoding times to be |
|
|
234 | 2-4 times as high as without). |
|
|
235 | |
|
|
236 | It is recommended to leave it off unless you know your |
|
|
237 | communications partner supports the stringref extension to CBOR |
|
|
238 | (L<http://cbor.schmorp.de/stringref>), as without decoder support, the |
|
|
239 | resulting data structure might not be usable. |
|
|
240 | |
|
|
241 | If C<$enable> is false (the default), then C<encode> will encode strings |
|
|
242 | the standard CBOR way. |
|
|
243 | |
|
|
244 | This option does not affect C<decode> in any way - string references will |
|
|
245 | always be decoded properly if present. |
|
|
246 | |
|
|
247 | =item $cbor = $cbor->validate_utf8 ([$enable]) |
|
|
248 | |
|
|
249 | =item $enabled = $cbor->get_validate_utf8 |
|
|
250 | |
|
|
251 | If C<$enable> is true (or missing), then C<decode> will validate that |
|
|
252 | elements (text strings) containing UTF-8 data in fact contain valid UTF-8 |
|
|
253 | data (instead of blindly accepting it). This validation obviously takes |
|
|
254 | extra time during decoding. |
|
|
255 | |
|
|
256 | The concept of "valid UTF-8" used is perl's concept, which is a superset |
|
|
257 | of the official UTF-8. |
|
|
258 | |
|
|
259 | If C<$enable> is false (the default), then C<decode> will blindly accept |
|
|
260 | UTF-8 data, marking them as valid UTF-8 in the resulting data structure |
|
|
261 | regardless of whether thats true or not. |
|
|
262 | |
|
|
263 | Perl isn't too happy about corrupted UTF-8 in strings, but should |
|
|
264 | generally not crash or do similarly evil things. Extensions might be not |
|
|
265 | so forgiving, so it's recommended to turn on this setting if you receive |
|
|
266 | untrusted CBOR. |
|
|
267 | |
|
|
268 | This option does not affect C<encode> in any way - strings that are |
|
|
269 | supposedly valid UTF-8 will simply be dumped into the resulting CBOR |
|
|
270 | string without checking whether that is, in fact, true or not. |
|
|
271 | |
|
|
272 | =item $cbor = $cbor->filter ([$cb->($tag, $value)]) |
|
|
273 | |
|
|
274 | =item $cb_or_undef = $cbor->get_filter |
|
|
275 | |
|
|
276 | Sets or replaces the tagged value decoding filter (when C<$cb> is |
|
|
277 | specified) or clears the filter (if no argument or C<undef> is provided). |
|
|
278 | |
|
|
279 | The filter callback is called only during decoding, when a non-enforced |
|
|
280 | tagged value has been decoded (see L<TAG HANDLING AND EXTENSIONS> for a |
|
|
281 | list of enforced tags). For specific tags, it's often better to provide a |
|
|
282 | default converter using the C<%CBOR::XS::FILTER> hash (see below). |
|
|
283 | |
|
|
284 | The first argument is the numerical tag, the second is the (decoded) value |
|
|
285 | that has been tagged. |
|
|
286 | |
|
|
287 | The filter function should return either exactly one value, which will |
|
|
288 | replace the tagged value in the decoded data structure, or no values, |
|
|
289 | which will result in default handling, which currently means the decoder |
|
|
290 | creates a C<CBOR::XS::Tagged> object to hold the tag and the value. |
|
|
291 | |
|
|
292 | When the filter is cleared (the default state), the default filter |
|
|
293 | function, C<CBOR::XS::default_filter>, is used. This function simply looks |
|
|
294 | up the tag in the C<%CBOR::XS::FILTER> hash. If an entry exists it must be |
|
|
295 | a code reference that is called with tag and value, and is responsible for |
|
|
296 | decoding the value. If no entry exists, it returns no values. |
|
|
297 | |
|
|
298 | Example: decode all tags not handled internally into C<CBOR::XS::Tagged> |
|
|
299 | objects, with no other special handling (useful when working with |
|
|
300 | potentially "unsafe" CBOR data). |
|
|
301 | |
|
|
302 | CBOR::XS->new->filter (sub { })->decode ($cbor_data); |
|
|
303 | |
|
|
304 | Example: provide a global filter for tag 1347375694, converting the value |
|
|
305 | into some string form. |
|
|
306 | |
|
|
307 | $CBOR::XS::FILTER{1347375694} = sub { |
|
|
308 | my ($tag, $value); |
|
|
309 | |
|
|
310 | "tag 1347375694 value $value" |
|
|
311 | }; |
|
|
312 | |
154 | =item $cbor_data = $cbor->encode ($perl_scalar) |
313 | =item $cbor_data = $cbor->encode ($perl_scalar) |
155 | |
314 | |
156 | Converts the given Perl data structure (a scalar value) to its CBOR |
315 | Converts the given Perl data structure (a scalar value) to its CBOR |
157 | representation. |
316 | representation. |
158 | |
317 | |
… | |
… | |
198 | CBOR integers become (numeric) perl scalars. On perls without 64 bit |
357 | CBOR integers become (numeric) perl scalars. On perls without 64 bit |
199 | support, 64 bit integers will be truncated or otherwise corrupted. |
358 | support, 64 bit integers will be truncated or otherwise corrupted. |
200 | |
359 | |
201 | =item byte strings |
360 | =item byte strings |
202 | |
361 | |
203 | Byte strings will become octet strings in Perl (the byte values 0..255 |
362 | Byte strings will become octet strings in Perl (the Byte values 0..255 |
204 | will simply become characters of the same value in Perl). |
363 | will simply become characters of the same value in Perl). |
205 | |
364 | |
206 | =item UTF-8 strings |
365 | =item UTF-8 strings |
207 | |
366 | |
208 | UTF-8 strings in CBOR will be decoded, i.e. the UTF-8 octets will be |
367 | UTF-8 strings in CBOR will be decoded, i.e. the UTF-8 octets will be |
… | |
… | |
226 | C<Types:Serialiser::false> and C<Types::Serialiser::error>, |
385 | C<Types:Serialiser::false> and C<Types::Serialiser::error>, |
227 | respectively. They are overloaded to act almost exactly like the numbers |
386 | respectively. They are overloaded to act almost exactly like the numbers |
228 | C<1> and C<0> (for true and false) or to throw an exception on access (for |
387 | C<1> and C<0> (for true and false) or to throw an exception on access (for |
229 | error). See the L<Types::Serialiser> manpage for details. |
388 | error). See the L<Types::Serialiser> manpage for details. |
230 | |
389 | |
231 | =item CBOR tag 256 (perl object) |
390 | =item tagged values |
232 | |
391 | |
233 | The tag value C<256> (TODO: pending iana registration) will be used |
|
|
234 | to deserialise a Perl object serialised with C<FREEZE>. See L<OBJECT |
|
|
235 | SERIALISATION>, below, for details. |
|
|
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 |
392 | Tagged items consists of a numeric tag and another CBOR value. |
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 | |
393 | |
248 | In the future, support for user-supplied conversions might get added. |
394 | See L<TAG HANDLING AND EXTENSIONS> and the description of C<< ->filter >> |
|
|
395 | for details on which tags are handled how. |
249 | |
396 | |
250 | =item anything else |
397 | =item anything else |
251 | |
398 | |
252 | Anything else (e.g. unsupported simple values) will raise a decoding |
399 | Anything else (e.g. unsupported simple values) will raise a decoding |
253 | error. |
400 | error. |
… | |
… | |
256 | |
403 | |
257 | |
404 | |
258 | =head2 PERL -> CBOR |
405 | =head2 PERL -> CBOR |
259 | |
406 | |
260 | The mapping from Perl to CBOR is slightly more difficult, as Perl is a |
407 | The mapping from Perl to CBOR is slightly more difficult, as Perl is a |
261 | truly typeless language, so we can only guess which CBOR type is meant by |
408 | typeless language. That means this module can only guess which CBOR type |
262 | a Perl value. |
409 | is meant by a perl value. |
263 | |
410 | |
264 | =over 4 |
411 | =over 4 |
265 | |
412 | |
266 | =item hash references |
413 | =item hash references |
267 | |
414 | |
268 | Perl hash references become CBOR maps. As there is no inherent ordering in |
415 | Perl hash references become CBOR maps. As there is no inherent ordering in |
269 | hash keys (or CBOR maps), they will usually be encoded in a pseudo-random |
416 | hash keys (or CBOR maps), they will usually be encoded in a pseudo-random |
270 | order. |
417 | order. This order can be different each time a hahs is encoded. |
271 | |
418 | |
272 | Currently, tied hashes will use the indefinite-length format, while normal |
419 | Currently, tied hashes will use the indefinite-length format, while normal |
273 | hashes will use the fixed-length format. |
420 | hashes will use the fixed-length format. |
274 | |
421 | |
275 | =item array references |
422 | =item array references |
276 | |
423 | |
277 | Perl array references become fixed-length CBOR arrays. |
424 | Perl array references become fixed-length CBOR arrays. |
278 | |
425 | |
279 | =item other references |
426 | =item other references |
280 | |
427 | |
281 | Other unblessed references are generally not allowed and will cause an |
428 | Other unblessed references will be represented using |
282 | exception to be thrown, except for references to the integers C<0> and |
429 | the indirection tag extension (tag value C<22098>, |
283 | C<1>, which get turned into false and true in CBOR. |
430 | L<http://cbor.schmorp.de/indirection>). CBOR decoders are guaranteed |
|
|
431 | to be able to decode these values somehow, by either "doing the right |
|
|
432 | thing", decoding into a generic tagged object, simply ignoring the tag, or |
|
|
433 | something else. |
284 | |
434 | |
285 | =item CBOR::XS::Tagged objects |
435 | =item CBOR::XS::Tagged objects |
286 | |
436 | |
287 | Objects of this type must be arrays consisting of a single C<[tag, value]> |
437 | 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 |
438 | pair. The (numerical) tag will be encoded as a CBOR tag, the value will |
289 | encoded as appropriate for the value. |
439 | be encoded as appropriate for the value. You must use C<CBOR::XS::tag> to |
|
|
440 | create such objects. |
290 | |
441 | |
291 | =item Types::Serialiser::true, Types::Serialiser::false, Types::Serialiser::error |
442 | =item Types::Serialiser::true, Types::Serialiser::false, Types::Serialiser::error |
292 | |
443 | |
293 | These special values become CBOR true, CBOR false and CBOR undefined |
444 | 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 |
445 | values, respectively. You can also use C<\1>, C<\0> and C<\undef> directly |
295 | if you want. |
446 | if you want. |
296 | |
447 | |
297 | =item other blessed objects |
448 | =item other blessed objects |
298 | |
449 | |
299 | Other blessed objects are serialised via C<TO_CBOR> or C<FREEZE>. See |
450 | Other blessed objects are serialised via C<TO_CBOR> or C<FREEZE>. See |
300 | L<OBJECT SERIALISATION>, below, for details. |
451 | L<TAG HANDLING AND EXTENSIONS> for specific classes handled by this |
|
|
452 | module, and L<OBJECT SERIALISATION> for generic object serialisation. |
301 | |
453 | |
302 | =item simple scalars |
454 | =item simple scalars |
303 | |
455 | |
304 | TODO |
|
|
305 | Simple Perl scalars (any scalar that is not a reference) are the most |
456 | Simple Perl scalars (any scalar that is not a reference) are the most |
306 | difficult objects to encode: CBOR::XS will encode undefined scalars as |
457 | difficult objects to encode: CBOR::XS will encode undefined scalars as |
307 | CBOR null values, scalars that have last been used in a string context |
458 | CBOR null values, scalars that have last been used in a string context |
308 | before encoding as CBOR strings, and anything else as number value: |
459 | before encoding as CBOR strings, and anything else as number value: |
309 | |
460 | |
310 | # dump as number |
461 | # dump as number |
311 | encode_cbor [2] # yields [2] |
462 | encode_cbor [2] # yields [2] |
312 | encode_cbor [-3.0e17] # yields [-3e+17] |
463 | encode_cbor [-3.0e17] # yields [-3e+17] |
313 | my $value = 5; encode_cbor [$value] # yields [5] |
464 | my $value = 5; encode_cbor [$value] # yields [5] |
314 | |
465 | |
315 | # used as string, so dump as string |
466 | # used as string, so dump as string (either byte or text) |
316 | print $value; |
467 | print $value; |
317 | encode_cbor [$value] # yields ["5"] |
468 | encode_cbor [$value] # yields ["5"] |
318 | |
469 | |
319 | # undef becomes null |
470 | # undef becomes null |
320 | encode_cbor [undef] # yields [null] |
471 | encode_cbor [undef] # yields [null] |
… | |
… | |
323 | |
474 | |
324 | my $x = 3.1; # some variable containing a number |
475 | my $x = 3.1; # some variable containing a number |
325 | "$x"; # stringified |
476 | "$x"; # stringified |
326 | $x .= ""; # another, more awkward way to stringify |
477 | $x .= ""; # another, more awkward way to stringify |
327 | print $x; # perl does it for you, too, quite often |
478 | print $x; # perl does it for you, too, quite often |
|
|
479 | |
|
|
480 | You can force whether a string ie encoded as byte or text string by using |
|
|
481 | C<utf8::upgrade> and C<utf8::downgrade>): |
|
|
482 | |
|
|
483 | utf8::upgrade $x; # encode $x as text string |
|
|
484 | utf8::downgrade $x; # encode $x as byte string |
|
|
485 | |
|
|
486 | Perl doesn't define what operations up- and downgrade strings, so if the |
|
|
487 | difference between byte and text is important, you should up- or downgrade |
|
|
488 | your string as late as possible before encoding. |
328 | |
489 | |
329 | You can force the type to be a CBOR number by numifying it: |
490 | You can force the type to be a CBOR number by numifying it: |
330 | |
491 | |
331 | my $x = "3"; # some variable containing a string |
492 | my $x = "3"; # some variable containing a string |
332 | $x += 0; # numify it, ensuring it will be dumped as a number |
493 | $x += 0; # numify it, ensuring it will be dumped as a number |
… | |
… | |
345 | |
506 | |
346 | =back |
507 | =back |
347 | |
508 | |
348 | =head2 OBJECT SERIALISATION |
509 | =head2 OBJECT SERIALISATION |
349 | |
510 | |
|
|
511 | This module implements both a CBOR-specific and the generic |
|
|
512 | L<Types::Serialier> object serialisation protocol. The following |
|
|
513 | subsections explain both methods. |
|
|
514 | |
|
|
515 | =head3 ENCODING |
|
|
516 | |
350 | This module knows two way to serialise a Perl object: The CBOR-specific |
517 | This module knows two way to serialise a Perl object: The CBOR-specific |
351 | way, and the generic way. |
518 | way, and the generic way. |
352 | |
519 | |
353 | Whenever the encoder encounters a Perl object that it cnanot serialise |
520 | Whenever the encoder encounters a Perl object that it cannot serialise |
354 | directly (most of them), it will first look up the C<TO_CBOR> method on |
521 | directly (most of them), it will first look up the C<TO_CBOR> method on |
355 | it. |
522 | it. |
356 | |
523 | |
357 | If it has a C<TO_CBOR> method, it will call it with the object as only |
524 | 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 |
525 | argument, and expects exactly one return value, which it will then |
… | |
… | |
364 | |
531 | |
365 | The C<FREEZE> method can return any number of values (i.e. zero or |
532 | 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 |
533 | more). These will be encoded as CBOR perl object, together with the |
367 | classname. |
534 | classname. |
368 | |
535 | |
|
|
536 | These methods I<MUST NOT> change the data structure that is being |
|
|
537 | serialised. Failure to comply to this can result in memory corruption - |
|
|
538 | and worse. |
|
|
539 | |
369 | If an object supports neither C<TO_CBOR> nor C<FREEZE>, encoding will fail |
540 | If an object supports neither C<TO_CBOR> nor C<FREEZE>, encoding will fail |
370 | with an error. |
541 | with an error. |
371 | |
542 | |
|
|
543 | =head3 DECODING |
|
|
544 | |
372 | Objects encoded via C<TO_CBOR> cannot be automatically decoded, but |
545 | Objects encoded via C<TO_CBOR> cannot (normally) be automatically decoded, |
373 | objects encoded via C<FREEZE> can be decoded using the following protocol: |
546 | but objects encoded via C<FREEZE> can be decoded using the following |
|
|
547 | protocol: |
374 | |
548 | |
375 | When an encoded CBOR perl object is encountered by the decoder, it will |
549 | 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 |
550 | look up the C<THAW> method, by using the stored classname, and will fail |
377 | if the method cannot be found. |
551 | if the method cannot be found. |
378 | |
552 | |
379 | After the lookup it will call the C<THAW> method with the stored classname |
553 | 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 |
554 | as first argument, the constant string C<CBOR> as second argument, and all |
381 | values returned by C<FREEZE> as remaining arguments. |
555 | values returned by C<FREEZE> as remaining arguments. |
382 | |
556 | |
383 | =head4 EXAMPLES |
557 | =head3 EXAMPLES |
384 | |
558 | |
385 | Here is an example C<TO_CBOR> method: |
559 | Here is an example C<TO_CBOR> method: |
386 | |
560 | |
387 | sub My::Object::TO_CBOR { |
561 | sub My::Object::TO_CBOR { |
388 | my ($obj) = @_; |
562 | my ($obj) = @_; |
… | |
… | |
399 | |
573 | |
400 | sub URI::TO_CBOR { |
574 | sub URI::TO_CBOR { |
401 | my ($self) = @_; |
575 | my ($self) = @_; |
402 | my $uri = "$self"; # stringify uri |
576 | my $uri = "$self"; # stringify uri |
403 | utf8::upgrade $uri; # make sure it will be encoded as UTF-8 string |
577 | utf8::upgrade $uri; # make sure it will be encoded as UTF-8 string |
404 | CBOR::XS::tagged 32, "$_[0]" |
578 | CBOR::XS::tag 32, "$_[0]" |
405 | } |
579 | } |
406 | |
580 | |
407 | This will encode URIs as a UTF-8 string with tag 32, which indicates an |
581 | This will encode URIs as a UTF-8 string with tag 32, which indicates an |
408 | URI. |
582 | URI. |
409 | |
583 | |
… | |
… | |
446 | =head1 MAGIC HEADER |
620 | =head1 MAGIC HEADER |
447 | |
621 | |
448 | There is no way to distinguish CBOR from other formats |
622 | There is no way to distinguish CBOR from other formats |
449 | programmatically. To make it easier to distinguish CBOR from other |
623 | programmatically. To make it easier to distinguish CBOR from other |
450 | formats, the CBOR specification has a special "magic string" that can be |
624 | formats, the CBOR specification has a special "magic string" that can be |
451 | prepended to any CBOR string without changing it's meaning. |
625 | prepended to any CBOR string without changing its meaning. |
452 | |
626 | |
453 | This string is available as C<$CBOR::XS::MAGIC>. This module does not |
627 | This string is available as C<$CBOR::XS::MAGIC>. This module does not |
454 | prepend this string tot he CBOR data it generates, but it will ignroe it |
628 | prepend this string to the CBOR data it generates, but it will ignore it |
455 | if present, so users can prepend this string as a "file type" indicator as |
629 | if present, so users can prepend this string as a "file type" indicator as |
456 | required. |
630 | required. |
457 | |
631 | |
458 | |
632 | |
459 | =head1 THE CBOR::XS::Tagged CLASS |
633 | =head1 THE CBOR::XS::Tagged CLASS |
… | |
… | |
515 | |
689 | |
516 | sub CBOR::XS::Tagged::value { |
690 | sub CBOR::XS::Tagged::value { |
517 | $_[0][1] = $_[1] if $#_; |
691 | $_[0][1] = $_[1] if $#_; |
518 | $_[0][1] |
692 | $_[0][1] |
519 | } |
693 | } |
|
|
694 | |
|
|
695 | =head2 EXAMPLES |
|
|
696 | |
|
|
697 | Here are some examples of C<CBOR::XS::Tagged> uses to tag objects. |
|
|
698 | |
|
|
699 | You can look up CBOR tag value and emanings in the IANA registry at |
|
|
700 | L<http://www.iana.org/assignments/cbor-tags/cbor-tags.xhtml>. |
|
|
701 | |
|
|
702 | Prepend a magic header (C<$CBOR::XS::MAGIC>): |
|
|
703 | |
|
|
704 | my $cbor = encode_cbor CBOR::XS::tag 55799, $value; |
|
|
705 | # same as: |
|
|
706 | my $cbor = $CBOR::XS::MAGIC . encode_cbor $value; |
|
|
707 | |
|
|
708 | Serialise some URIs and a regex in an array: |
|
|
709 | |
|
|
710 | my $cbor = encode_cbor [ |
|
|
711 | (CBOR::XS::tag 32, "http://www.nethype.de/"), |
|
|
712 | (CBOR::XS::tag 32, "http://software.schmorp.de/"), |
|
|
713 | (CBOR::XS::tag 35, "^[Pp][Ee][Rr][lL]\$"), |
|
|
714 | ]; |
|
|
715 | |
|
|
716 | Wrap CBOR data in CBOR: |
|
|
717 | |
|
|
718 | my $cbor_cbor = encode_cbor |
|
|
719 | CBOR::XS::tag 24, |
|
|
720 | encode_cbor [1, 2, 3]; |
|
|
721 | |
|
|
722 | =head1 TAG HANDLING AND EXTENSIONS |
|
|
723 | |
|
|
724 | This section describes how this module handles specific tagged values |
|
|
725 | and extensions. If a tag is not mentioned here and no additional filters |
|
|
726 | are provided for it, then the default handling applies (creating a |
|
|
727 | CBOR::XS::Tagged object on decoding, and only encoding the tag when |
|
|
728 | explicitly requested). |
|
|
729 | |
|
|
730 | Tags not handled specifically are currently converted into a |
|
|
731 | L<CBOR::XS::Tagged> object, which is simply a blessed array reference |
|
|
732 | consisting of the numeric tag value followed by the (decoded) CBOR value. |
|
|
733 | |
|
|
734 | Future versions of this module reserve the right to special case |
|
|
735 | additional tags (such as base64url). |
|
|
736 | |
|
|
737 | =head2 ENFORCED TAGS |
|
|
738 | |
|
|
739 | These tags are always handled when decoding, and their handling cannot be |
|
|
740 | overriden by the user. |
|
|
741 | |
|
|
742 | =over 4 |
|
|
743 | |
|
|
744 | =item 26 (perl-object, L<http://cbor.schmorp.de/perl-object>) |
|
|
745 | |
|
|
746 | These tags are automatically created (and decoded) for serialisable |
|
|
747 | objects using the C<FREEZE/THAW> methods (the L<Types::Serialier> object |
|
|
748 | serialisation protocol). See L<OBJECT SERIALISATION> for details. |
|
|
749 | |
|
|
750 | =item 28, 29 (shareable, sharedref, L <http://cbor.schmorp.de/value-sharing>) |
|
|
751 | |
|
|
752 | These tags are automatically decoded when encountered (and they do not |
|
|
753 | result in a cyclic data structure, see C<allow_cycles>), resulting in |
|
|
754 | shared values in the decoded object. They are only encoded, however, when |
|
|
755 | C<allow_sharing> is enabled. |
|
|
756 | |
|
|
757 | Not all shared values can be successfully decoded: values that reference |
|
|
758 | themselves will I<currently> decode as C<undef> (this is not the same |
|
|
759 | as a reference pointing to itself, which will be represented as a value |
|
|
760 | that contains an indirect reference to itself - these will be decoded |
|
|
761 | properly). |
|
|
762 | |
|
|
763 | Note that considerably more shared value data structures can be decoded |
|
|
764 | than will be encoded - currently, only values pointed to by references |
|
|
765 | will be shared, others will not. While non-reference shared values can be |
|
|
766 | generated in Perl with some effort, they were considered too unimportant |
|
|
767 | to be supported in the encoder. The decoder, however, will decode these |
|
|
768 | values as shared values. |
|
|
769 | |
|
|
770 | =item 256, 25 (stringref-namespace, stringref, L <http://cbor.schmorp.de/stringref>) |
|
|
771 | |
|
|
772 | These tags are automatically decoded when encountered. They are only |
|
|
773 | encoded, however, when C<pack_strings> is enabled. |
|
|
774 | |
|
|
775 | =item 22098 (indirection, L<http://cbor.schmorp.de/indirection>) |
|
|
776 | |
|
|
777 | This tag is automatically generated when a reference are encountered (with |
|
|
778 | the exception of hash and array refernces). It is converted to a reference |
|
|
779 | when decoding. |
|
|
780 | |
|
|
781 | =item 55799 (self-describe CBOR, RFC 7049) |
|
|
782 | |
|
|
783 | This value is not generated on encoding (unless explicitly requested by |
|
|
784 | the user), and is simply ignored when decoding. |
|
|
785 | |
|
|
786 | =back |
|
|
787 | |
|
|
788 | =head2 NON-ENFORCED TAGS |
|
|
789 | |
|
|
790 | These tags have default filters provided when decoding. Their handling can |
|
|
791 | be overriden by changing the C<%CBOR::XS::FILTER> entry for the tag, or by |
|
|
792 | providing a custom C<filter> callback when decoding. |
|
|
793 | |
|
|
794 | When they result in decoding into a specific Perl class, the module |
|
|
795 | usually provides a corresponding C<TO_CBOR> method as well. |
|
|
796 | |
|
|
797 | When any of these need to load additional modules that are not part of the |
|
|
798 | perl core distribution (e.g. L<URI>), it is (currently) up to the user to |
|
|
799 | provide these modules. The decoding usually fails with an exception if the |
|
|
800 | required module cannot be loaded. |
|
|
801 | |
|
|
802 | =over 4 |
|
|
803 | |
|
|
804 | =item 0, 1 (date/time string, seconds since the epoch) |
|
|
805 | |
|
|
806 | These tags are decoded into L<Time::Piece> objects. The corresponding |
|
|
807 | C<Time::Piece::TO_CBOR> method always encodes into tag 1 values currently. |
|
|
808 | |
|
|
809 | The L<Time::Piece> API is generally surprisingly bad, and fractional |
|
|
810 | seconds are only accidentally kept intact, so watch out. On the plus side, |
|
|
811 | the module comes with perl since 5.10, which has to count for something. |
|
|
812 | |
|
|
813 | =item 2, 3 (positive/negative bignum) |
|
|
814 | |
|
|
815 | These tags are decoded into L<Math::BigInt> objects. The corresponding |
|
|
816 | C<Math::BigInt::TO_CBOR> method encodes "small" bigints into normal CBOR |
|
|
817 | integers, and others into positive/negative CBOR bignums. |
|
|
818 | |
|
|
819 | =item 4, 5 (decimal fraction/bigfloat) |
|
|
820 | |
|
|
821 | Both decimal fractions and bigfloats are decoded into L<Math::BigFloat> |
|
|
822 | objects. The corresponding C<Math::BigFloat::TO_CBOR> method I<always> |
|
|
823 | encodes into a decimal fraction. |
|
|
824 | |
|
|
825 | CBOR cannot represent bigfloats with I<very> large exponents - conversion |
|
|
826 | of such big float objects is undefined. |
|
|
827 | |
|
|
828 | Also, NaN and infinities are not encoded properly. |
|
|
829 | |
|
|
830 | =item 21, 22, 23 (expected later JSON conversion) |
|
|
831 | |
|
|
832 | CBOR::XS is not a CBOR-to-JSON converter, and will simply ignore these |
|
|
833 | tags. |
|
|
834 | |
|
|
835 | =item 32 (URI) |
|
|
836 | |
|
|
837 | These objects decode into L<URI> objects. The corresponding |
|
|
838 | C<URI::TO_CBOR> method again results in a CBOR URI value. |
|
|
839 | |
|
|
840 | =back |
|
|
841 | |
|
|
842 | =cut |
|
|
843 | |
|
|
844 | our %FILTER = ( |
|
|
845 | # 0 # rfc4287 datetime, utf-8 |
|
|
846 | # 1 # unix timestamp, any |
|
|
847 | |
|
|
848 | 2 => sub { # pos bigint |
|
|
849 | require Math::BigInt; |
|
|
850 | Math::BigInt->new ("0x" . unpack "H*", pop) |
|
|
851 | }, |
|
|
852 | |
|
|
853 | 3 => sub { # neg bigint |
|
|
854 | require Math::BigInt; |
|
|
855 | -Math::BigInt->new ("0x" . unpack "H*", pop) |
|
|
856 | }, |
|
|
857 | |
|
|
858 | 4 => sub { # decimal fraction, array |
|
|
859 | require Math::BigFloat; |
|
|
860 | Math::BigFloat->new ($_[1][1] . "E" . $_[1][0]) |
|
|
861 | }, |
|
|
862 | |
|
|
863 | 5 => sub { # bigfloat, array |
|
|
864 | require Math::BigFloat; |
|
|
865 | scalar Math::BigFloat->new ($_[1][1])->blsft ($_[1][0], 2) |
|
|
866 | }, |
|
|
867 | |
|
|
868 | 21 => sub { pop }, # expected conversion to base64url encoding |
|
|
869 | 22 => sub { pop }, # expected conversion to base64 encoding |
|
|
870 | 23 => sub { pop }, # expected conversion to base16 encoding |
|
|
871 | |
|
|
872 | # 24 # embedded cbor, byte string |
|
|
873 | |
|
|
874 | 32 => sub { |
|
|
875 | require URI; |
|
|
876 | URI->new (pop) |
|
|
877 | }, |
|
|
878 | |
|
|
879 | # 33 # base64url rfc4648, utf-8 |
|
|
880 | # 34 # base64 rfc46484, utf-8 |
|
|
881 | # 35 # regex pcre/ecma262, utf-8 |
|
|
882 | # 36 # mime message rfc2045, utf-8 |
|
|
883 | ); |
|
|
884 | |
520 | |
885 | |
521 | =head1 CBOR and JSON |
886 | =head1 CBOR and JSON |
522 | |
887 | |
523 | CBOR is supposed to implement a superset of the JSON data model, and is, |
888 | CBOR is supposed to implement a superset of the JSON data model, and is, |
524 | with some coercion, able to represent all JSON texts (something that other |
889 | with some coercion, able to represent all JSON texts (something that other |
… | |
… | |
585 | properly. Half precision types are accepted, but not encoded. |
950 | properly. Half precision types are accepted, but not encoded. |
586 | |
951 | |
587 | Strict mode and canonical mode are not implemented. |
952 | Strict mode and canonical mode are not implemented. |
588 | |
953 | |
589 | |
954 | |
|
|
955 | =head1 LIMITATIONS ON PERLS WITHOUT 64-BIT INTEGER SUPPORT |
|
|
956 | |
|
|
957 | On perls that were built without 64 bit integer support (these are rare |
|
|
958 | nowadays, even on 32 bit architectures), support for any kind of 64 bit |
|
|
959 | integer in CBOR is very limited - most likely, these 64 bit values will |
|
|
960 | be truncated, corrupted, or otherwise not decoded correctly. This also |
|
|
961 | includes string, array and map sizes that are stored as 64 bit integers. |
|
|
962 | |
|
|
963 | |
590 | =head1 THREADS |
964 | =head1 THREADS |
591 | |
965 | |
592 | This module is I<not> guaranteed to be thread safe and there are no |
966 | This module is I<not> guaranteed to be thread safe and there are no |
593 | plans to change this until Perl gets thread support (as opposed to the |
967 | plans to change this until Perl gets thread support (as opposed to the |
594 | horribly slow so-called "threads" which are simply slow and bloated |
968 | horribly slow so-called "threads" which are simply slow and bloated |
… | |
… | |
606 | Please refrain from using rt.cpan.org or any other bug reporting |
980 | Please refrain from using rt.cpan.org or any other bug reporting |
607 | service. I put the contact address into my modules for a reason. |
981 | service. I put the contact address into my modules for a reason. |
608 | |
982 | |
609 | =cut |
983 | =cut |
610 | |
984 | |
|
|
985 | our %FILTER = ( |
|
|
986 | 0 => sub { # rfc4287 datetime, utf-8 |
|
|
987 | require Time::Piece; |
|
|
988 | # Time::Piece::Strptime uses the "incredibly flexible date parsing routine" |
|
|
989 | # from FreeBSD, which can't parse ISO 8601, RFC3339, RFC4287 or much of anything |
|
|
990 | # else either. Whats incredibe over standard strptime totally escapes me. |
|
|
991 | # doesn't do fractional times, either. sigh. |
|
|
992 | # In fact, it's all a lie, it uses whatever strptime it wants, and of course, |
|
|
993 | # they are all incomptible. The openbsd one simply ignores %z (but according to the |
|
|
994 | # docs, it would be much more incredibly flexible). |
|
|
995 | scalar eval { |
|
|
996 | my $s = $_[1]; |
|
|
997 | |
|
|
998 | $s =~ s/Z$/+00:00/; |
|
|
999 | $s =~ s/(\.[0-9]+)?([+-][0-9][0-9]):([0-9][0-9])$// |
|
|
1000 | or die; |
|
|
1001 | |
|
|
1002 | my $b = $1 - ($2 * 60 + $3) * 60; # fractional part + offset. hopefully |
|
|
1003 | my $d = Time::Piece->strptime ($s, "%Y-%m-%dT%H:%M:%S"); |
|
|
1004 | |
|
|
1005 | Time::Piece::gmtime ($d->epoch + $b) |
|
|
1006 | } || die "corrupted CBOR date/time string ($_[0])"; |
|
|
1007 | }, |
|
|
1008 | |
|
|
1009 | 1 => sub { # seconds since the epoch, possibly fractional |
|
|
1010 | require Time::Piece; |
|
|
1011 | scalar Time::Piece::gmtime (pop) |
|
|
1012 | }, |
|
|
1013 | |
|
|
1014 | 2 => sub { # pos bigint |
|
|
1015 | require Math::BigInt; |
|
|
1016 | Math::BigInt->new ("0x" . unpack "H*", pop) |
|
|
1017 | }, |
|
|
1018 | |
|
|
1019 | 3 => sub { # neg bigint |
|
|
1020 | require Math::BigInt; |
|
|
1021 | -Math::BigInt->new ("0x" . unpack "H*", pop) |
|
|
1022 | }, |
|
|
1023 | |
|
|
1024 | 4 => sub { # decimal fraction, array |
|
|
1025 | require Math::BigFloat; |
|
|
1026 | Math::BigFloat->new ($_[1][1] . "E" . $_[1][0]) |
|
|
1027 | }, |
|
|
1028 | |
|
|
1029 | 5 => sub { # bigfloat, array |
|
|
1030 | require Math::BigFloat; |
|
|
1031 | scalar Math::BigFloat->new ($_[1][1])->blsft ($_[1][0], 2) |
|
|
1032 | }, |
|
|
1033 | |
|
|
1034 | 21 => sub { pop }, # expected conversion to base64url encoding |
|
|
1035 | 22 => sub { pop }, # expected conversion to base64 encoding |
|
|
1036 | 23 => sub { pop }, # expected conversion to base16 encoding |
|
|
1037 | |
|
|
1038 | # 24 # embedded cbor, byte string |
|
|
1039 | |
|
|
1040 | 32 => sub { |
|
|
1041 | require URI; |
|
|
1042 | URI->new (pop) |
|
|
1043 | }, |
|
|
1044 | |
|
|
1045 | # 33 # base64url rfc4648, utf-8 |
|
|
1046 | # 34 # base64 rfc46484, utf-8 |
|
|
1047 | # 35 # regex pcre/ecma262, utf-8 |
|
|
1048 | # 36 # mime message rfc2045, utf-8 |
|
|
1049 | ); |
|
|
1050 | |
|
|
1051 | sub CBOR::XS::default_filter { |
|
|
1052 | &{ $FILTER{$_[0]} or return } |
|
|
1053 | } |
|
|
1054 | |
|
|
1055 | sub URI::TO_CBOR { |
|
|
1056 | my $uri = $_[0]->as_string; |
|
|
1057 | utf8::upgrade $uri; |
|
|
1058 | tag 32, $uri |
|
|
1059 | } |
|
|
1060 | |
|
|
1061 | sub Math::BigInt::TO_CBOR { |
|
|
1062 | if ($_[0] >= -2147483648 && $_[0] <= 2147483647) { |
|
|
1063 | $_[0]->numify |
|
|
1064 | } else { |
|
|
1065 | my $hex = substr $_[0]->as_hex, 2; |
|
|
1066 | $hex = "0$hex" if 1 & length $hex; # sigh |
|
|
1067 | tag $_[0] >= 0 ? 2 : 3, pack "H*", $hex |
|
|
1068 | } |
|
|
1069 | } |
|
|
1070 | |
|
|
1071 | sub Math::BigFloat::TO_CBOR { |
|
|
1072 | my ($m, $e) = $_[0]->parts; |
|
|
1073 | tag 4, [$e->numify, $m] |
|
|
1074 | } |
|
|
1075 | |
|
|
1076 | sub Time::Piece::TO_CBOR { |
|
|
1077 | tag 1, $_[0]->epoch |
|
|
1078 | } |
|
|
1079 | |
611 | XSLoader::load "CBOR::XS", $VERSION; |
1080 | XSLoader::load "CBOR::XS", $VERSION; |
612 | |
1081 | |
613 | =head1 SEE ALSO |
1082 | =head1 SEE ALSO |
614 | |
1083 | |
615 | The L<JSON> and L<JSON::XS> modules that do similar, but human-readable, |
1084 | The L<JSON> and L<JSON::XS> modules that do similar, but human-readable, |