… | |
… | |
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 | The primary goal of this module is to be I<correct> and the secondary goal |
|
|
44 | is to be I<fast>. To reach the latter goal it was written in C. |
50 | |
45 | |
51 | To give you a general idea about speed, with texts in the megabyte range, |
46 | 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 |
47 | 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 |
48 | L<JSON::XS> and decodes about 15%-30% faster than those. The shorter the |
54 | data, the worse L<Storable> performs in comparison. |
49 | data, the worse L<Storable> performs in comparison. |
55 | |
50 | |
56 | As for compactness, C<CBOR::XS> encoded data structures are usually about |
51 | Regarding compactness, C<CBOR::XS>-encoded data structures are usually |
57 | 20% smaller than the same data encoded as (compact) JSON or L<Storable>. |
52 | about 20% smaller than the same data encoded as (compact) JSON or |
|
|
53 | L<Storable>. |
58 | |
54 | |
59 | The primary goal of this module is to be I<correct> and the secondary goal |
55 | In addition to the core CBOR data format, this module implements a |
60 | is to be I<fast>. To reach the latter goal it was written in C. |
56 | number of extensions, to support cyclic and shared data structures |
|
|
57 | (see C<allow_sharing> and C<allow_cycles>), string deduplication (see |
|
|
58 | C<pack_strings>) and scalar references (always enabled). |
61 | |
59 | |
62 | 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 |
63 | vice versa. |
61 | vice versa. |
64 | |
62 | |
65 | =cut |
63 | =cut |
66 | |
64 | |
67 | package CBOR::XS; |
65 | package CBOR::XS; |
68 | |
66 | |
69 | use common::sense; |
67 | use common::sense; |
70 | |
68 | |
71 | our $VERSION = 0.06; |
69 | our $VERSION = 1.83; |
72 | our @ISA = qw(Exporter); |
70 | our @ISA = qw(Exporter); |
73 | |
71 | |
74 | our @EXPORT = qw(encode_cbor decode_cbor); |
72 | our @EXPORT = qw(encode_cbor decode_cbor); |
75 | |
73 | |
76 | use Exporter; |
74 | use Exporter; |
… | |
… | |
113 | strings. All boolean flags described below are by default I<disabled>. |
111 | strings. All boolean flags described below are by default I<disabled>. |
114 | |
112 | |
115 | 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 |
116 | be chained: |
114 | be chained: |
117 | |
115 | |
118 | #TODO |
|
|
119 | my $cbor = CBOR::XS->new->encode ({a => [1,2]}); |
116 | my $cbor = CBOR::XS->new->encode ({a => [1,2]}); |
|
|
117 | |
|
|
118 | =item $cbor = new_safe CBOR::XS |
|
|
119 | |
|
|
120 | Create a new, safe/secure CBOR::XS object. This is similar to C<new>, |
|
|
121 | but configures the coder object to be safe to use with untrusted |
|
|
122 | data. Currently, this is equivalent to: |
|
|
123 | |
|
|
124 | my $cbor = CBOR::XS |
|
|
125 | ->new |
|
|
126 | ->forbid_objects |
|
|
127 | ->filter (\&CBOR::XS::safe_filter) |
|
|
128 | ->max_size (1e8); |
|
|
129 | |
|
|
130 | But is more future proof (it is better to crash because of a change than |
|
|
131 | to be exploited in other ways). |
|
|
132 | |
|
|
133 | =cut |
|
|
134 | |
|
|
135 | sub new_safe { |
|
|
136 | CBOR::XS |
|
|
137 | ->new |
|
|
138 | ->forbid_objects |
|
|
139 | ->filter (\&CBOR::XS::safe_filter) |
|
|
140 | ->max_size (1e8) |
|
|
141 | } |
120 | |
142 | |
121 | =item $cbor = $cbor->max_depth ([$maximum_nesting_depth]) |
143 | =item $cbor = $cbor->max_depth ([$maximum_nesting_depth]) |
122 | |
144 | |
123 | =item $max_depth = $cbor->get_max_depth |
145 | =item $max_depth = $cbor->get_max_depth |
124 | |
146 | |
… | |
… | |
140 | |
162 | |
141 | Note that nesting is implemented by recursion in C. The default value has |
163 | Note that nesting is implemented by recursion in C. The default value has |
142 | been chosen to be as large as typical operating systems allow without |
164 | been chosen to be as large as typical operating systems allow without |
143 | crashing. |
165 | crashing. |
144 | |
166 | |
145 | See SECURITY CONSIDERATIONS, below, for more info on why this is useful. |
167 | See L<SECURITY CONSIDERATIONS>, below, for more info on why this is useful. |
146 | |
168 | |
147 | =item $cbor = $cbor->max_size ([$maximum_string_size]) |
169 | =item $cbor = $cbor->max_size ([$maximum_string_size]) |
148 | |
170 | |
149 | =item $max_size = $cbor->get_max_size |
171 | =item $max_size = $cbor->get_max_size |
150 | |
172 | |
… | |
… | |
155 | effect on C<encode> (yet). |
177 | effect on C<encode> (yet). |
156 | |
178 | |
157 | If no argument is given, the limit check will be deactivated (same as when |
179 | If no argument is given, the limit check will be deactivated (same as when |
158 | C<0> is specified). |
180 | C<0> is specified). |
159 | |
181 | |
160 | See SECURITY CONSIDERATIONS, below, for more info on why this is useful. |
182 | See L<SECURITY CONSIDERATIONS>, below, for more info on why this is useful. |
|
|
183 | |
|
|
184 | =item $cbor = $cbor->allow_unknown ([$enable]) |
|
|
185 | |
|
|
186 | =item $enabled = $cbor->get_allow_unknown |
|
|
187 | |
|
|
188 | If C<$enable> is true (or missing), then C<encode> will I<not> throw an |
|
|
189 | exception when it encounters values it cannot represent in CBOR (for |
|
|
190 | example, filehandles) but instead will encode a CBOR C<error> value. |
|
|
191 | |
|
|
192 | If C<$enable> is false (the default), then C<encode> will throw an |
|
|
193 | exception when it encounters anything it cannot encode as CBOR. |
|
|
194 | |
|
|
195 | This option does not affect C<decode> in any way, and it is recommended to |
|
|
196 | leave it off unless you know your communications partner. |
|
|
197 | |
|
|
198 | =item $cbor = $cbor->allow_sharing ([$enable]) |
|
|
199 | |
|
|
200 | =item $enabled = $cbor->get_allow_sharing |
|
|
201 | |
|
|
202 | If C<$enable> is true (or missing), then C<encode> will not double-encode |
|
|
203 | values that have been referenced before (e.g. when the same object, such |
|
|
204 | as an array, is referenced multiple times), but instead will emit a |
|
|
205 | reference to the earlier value. |
|
|
206 | |
|
|
207 | This means that such values will only be encoded once, and will not result |
|
|
208 | in a deep cloning of the value on decode, in decoders supporting the value |
|
|
209 | sharing extension. This also makes it possible to encode cyclic data |
|
|
210 | structures (which need C<allow_cycles> to be enabled to be decoded by this |
|
|
211 | module). |
|
|
212 | |
|
|
213 | It is recommended to leave it off unless you know your |
|
|
214 | communication partner supports the value sharing extensions to CBOR |
|
|
215 | (L<http://cbor.schmorp.de/value-sharing>), as without decoder support, the |
|
|
216 | resulting data structure might be unusable. |
|
|
217 | |
|
|
218 | Detecting shared values incurs a runtime overhead when values are encoded |
|
|
219 | that have a reference counter large than one, and might unnecessarily |
|
|
220 | increase the encoded size, as potentially shared values are encoded as |
|
|
221 | shareable whether or not they are actually shared. |
|
|
222 | |
|
|
223 | At the moment, only targets of references can be shared (e.g. scalars, |
|
|
224 | arrays or hashes pointed to by a reference). Weirder constructs, such as |
|
|
225 | an array with multiple "copies" of the I<same> string, which are hard but |
|
|
226 | not impossible to create in Perl, are not supported (this is the same as |
|
|
227 | with L<Storable>). |
|
|
228 | |
|
|
229 | If C<$enable> is false (the default), then C<encode> will encode shared |
|
|
230 | data structures repeatedly, unsharing them in the process. Cyclic data |
|
|
231 | structures cannot be encoded in this mode. |
|
|
232 | |
|
|
233 | This option does not affect C<decode> in any way - shared values and |
|
|
234 | references will always be decoded properly if present. |
|
|
235 | |
|
|
236 | =item $cbor = $cbor->allow_cycles ([$enable]) |
|
|
237 | |
|
|
238 | =item $enabled = $cbor->get_allow_cycles |
|
|
239 | |
|
|
240 | If C<$enable> is true (or missing), then C<decode> will happily decode |
|
|
241 | self-referential (cyclic) data structures. By default these will not be |
|
|
242 | decoded, as they need manual cleanup to avoid memory leaks, so code that |
|
|
243 | isn't prepared for this will not leak memory. |
|
|
244 | |
|
|
245 | If C<$enable> is false (the default), then C<decode> will throw an error |
|
|
246 | when it encounters a self-referential/cyclic data structure. |
|
|
247 | |
|
|
248 | FUTURE DIRECTION: the motivation behind this option is to avoid I<real> |
|
|
249 | cycles - future versions of this module might chose to decode cyclic data |
|
|
250 | structures using weak references when this option is off, instead of |
|
|
251 | throwing an error. |
|
|
252 | |
|
|
253 | This option does not affect C<encode> in any way - shared values and |
|
|
254 | references will always be encoded properly if present. |
|
|
255 | |
|
|
256 | =item $cbor = $cbor->forbid_objects ([$enable]) |
|
|
257 | |
|
|
258 | =item $enabled = $cbor->get_forbid_objects |
|
|
259 | |
|
|
260 | Disables the use of the object serialiser protocol. |
|
|
261 | |
|
|
262 | If C<$enable> is true (or missing), then C<encode> will will throw an |
|
|
263 | exception when it encounters perl objects that would be encoded using the |
|
|
264 | perl-object tag (26). When C<decode> encounters such tags, it will fall |
|
|
265 | back to the general filter/tagged logic as if this were an unknown tag (by |
|
|
266 | default resulting in a C<CBOR::XC::Tagged> object). |
|
|
267 | |
|
|
268 | If C<$enable> is false (the default), then C<encode> will use the |
|
|
269 | L<Types::Serialiser> object serialisation protocol to serialise objects |
|
|
270 | into perl-object tags, and C<decode> will do the same to decode such tags. |
|
|
271 | |
|
|
272 | See L<SECURITY CONSIDERATIONS>, below, for more info on why forbidding this |
|
|
273 | protocol can be useful. |
|
|
274 | |
|
|
275 | =item $cbor = $cbor->pack_strings ([$enable]) |
|
|
276 | |
|
|
277 | =item $enabled = $cbor->get_pack_strings |
|
|
278 | |
|
|
279 | If C<$enable> is true (or missing), then C<encode> will try not to encode |
|
|
280 | the same string twice, but will instead encode a reference to the string |
|
|
281 | instead. Depending on your data format, this can save a lot of space, but |
|
|
282 | also results in a very large runtime overhead (expect encoding times to be |
|
|
283 | 2-4 times as high as without). |
|
|
284 | |
|
|
285 | It is recommended to leave it off unless you know your |
|
|
286 | communications partner supports the stringref extension to CBOR |
|
|
287 | (L<http://cbor.schmorp.de/stringref>), as without decoder support, the |
|
|
288 | resulting data structure might not be usable. |
|
|
289 | |
|
|
290 | If C<$enable> is false (the default), then C<encode> will encode strings |
|
|
291 | the standard CBOR way. |
|
|
292 | |
|
|
293 | This option does not affect C<decode> in any way - string references will |
|
|
294 | always be decoded properly if present. |
|
|
295 | |
|
|
296 | =item $cbor = $cbor->text_keys ([$enable]) |
|
|
297 | |
|
|
298 | =item $enabled = $cbor->get_text_keys |
|
|
299 | |
|
|
300 | If C<$enabled> is true (or missing), then C<encode> will encode all |
|
|
301 | perl hash keys as CBOR text strings/UTF-8 string, upgrading them as needed. |
|
|
302 | |
|
|
303 | If C<$enable> is false (the default), then C<encode> will encode hash keys |
|
|
304 | normally - upgraded perl strings (strings internally encoded as UTF-8) as |
|
|
305 | CBOR text strings, and downgraded perl strings as CBOR byte strings. |
|
|
306 | |
|
|
307 | This option does not affect C<decode> in any way. |
|
|
308 | |
|
|
309 | This option is useful for interoperability with CBOR decoders that don't |
|
|
310 | treat byte strings as a form of text. It is especially useful as Perl |
|
|
311 | gives very little control over hash keys. |
|
|
312 | |
|
|
313 | Enabling this option can be slow, as all downgraded hash keys that are |
|
|
314 | encoded need to be scanned and converted to UTF-8. |
|
|
315 | |
|
|
316 | =item $cbor = $cbor->text_strings ([$enable]) |
|
|
317 | |
|
|
318 | =item $enabled = $cbor->get_text_strings |
|
|
319 | |
|
|
320 | This option works similar to C<text_keys>, above, but works on all strings |
|
|
321 | (including hash keys), so C<text_keys> has no further effect after |
|
|
322 | enabling C<text_strings>. |
|
|
323 | |
|
|
324 | If C<$enabled> is true (or missing), then C<encode> will encode all perl |
|
|
325 | strings as CBOR text strings/UTF-8 strings, upgrading them as needed. |
|
|
326 | |
|
|
327 | If C<$enable> is false (the default), then C<encode> will encode strings |
|
|
328 | normally (but see C<text_keys>) - upgraded perl strings (strings |
|
|
329 | internally encoded as UTF-8) as CBOR text strings, and downgraded perl |
|
|
330 | strings as CBOR byte strings. |
|
|
331 | |
|
|
332 | This option does not affect C<decode> in any way. |
|
|
333 | |
|
|
334 | This option has similar advantages and disadvantages as C<text_keys>. In |
|
|
335 | addition, this option effectively removes the ability to automatically |
|
|
336 | encode byte strings, which might break some C<FREEZE> and C<TO_CBOR> |
|
|
337 | methods that rely on this. |
|
|
338 | |
|
|
339 | A workaround is to use explicit type casts, which are unaffected by this option. |
|
|
340 | |
|
|
341 | =item $cbor = $cbor->validate_utf8 ([$enable]) |
|
|
342 | |
|
|
343 | =item $enabled = $cbor->get_validate_utf8 |
|
|
344 | |
|
|
345 | If C<$enable> is true (or missing), then C<decode> will validate that |
|
|
346 | elements (text strings) containing UTF-8 data in fact contain valid UTF-8 |
|
|
347 | data (instead of blindly accepting it). This validation obviously takes |
|
|
348 | extra time during decoding. |
|
|
349 | |
|
|
350 | The concept of "valid UTF-8" used is perl's concept, which is a superset |
|
|
351 | of the official UTF-8. |
|
|
352 | |
|
|
353 | If C<$enable> is false (the default), then C<decode> will blindly accept |
|
|
354 | UTF-8 data, marking them as valid UTF-8 in the resulting data structure |
|
|
355 | regardless of whether that's true or not. |
|
|
356 | |
|
|
357 | Perl isn't too happy about corrupted UTF-8 in strings, but should |
|
|
358 | generally not crash or do similarly evil things. Extensions might be not |
|
|
359 | so forgiving, so it's recommended to turn on this setting if you receive |
|
|
360 | untrusted CBOR. |
|
|
361 | |
|
|
362 | This option does not affect C<encode> in any way - strings that are |
|
|
363 | supposedly valid UTF-8 will simply be dumped into the resulting CBOR |
|
|
364 | string without checking whether that is, in fact, true or not. |
|
|
365 | |
|
|
366 | =item $cbor = $cbor->filter ([$cb->($tag, $value)]) |
|
|
367 | |
|
|
368 | =item $cb_or_undef = $cbor->get_filter |
|
|
369 | |
|
|
370 | Sets or replaces the tagged value decoding filter (when C<$cb> is |
|
|
371 | specified) or clears the filter (if no argument or C<undef> is provided). |
|
|
372 | |
|
|
373 | The filter callback is called only during decoding, when a non-enforced |
|
|
374 | tagged value has been decoded (see L<TAG HANDLING AND EXTENSIONS> for a |
|
|
375 | list of enforced tags). For specific tags, it's often better to provide a |
|
|
376 | default converter using the C<%CBOR::XS::FILTER> hash (see below). |
|
|
377 | |
|
|
378 | The first argument is the numerical tag, the second is the (decoded) value |
|
|
379 | that has been tagged. |
|
|
380 | |
|
|
381 | The filter function should return either exactly one value, which will |
|
|
382 | replace the tagged value in the decoded data structure, or no values, |
|
|
383 | which will result in default handling, which currently means the decoder |
|
|
384 | creates a C<CBOR::XS::Tagged> object to hold the tag and the value. |
|
|
385 | |
|
|
386 | When the filter is cleared (the default state), the default filter |
|
|
387 | function, C<CBOR::XS::default_filter>, is used. This function simply |
|
|
388 | looks up the tag in the C<%CBOR::XS::FILTER> hash. If an entry exists |
|
|
389 | it must be a code reference that is called with tag and value, and is |
|
|
390 | responsible for decoding the value. If no entry exists, it returns no |
|
|
391 | values. C<CBOR::XS> provides a number of default filter functions already, |
|
|
392 | the the C<%CBOR::XS::FILTER> hash can be freely extended with more. |
|
|
393 | |
|
|
394 | C<CBOR::XS> additionally provides an alternative filter function that is |
|
|
395 | supposed to be safe to use with untrusted data (which the default filter |
|
|
396 | might not), called C<CBOR::XS::safe_filter>, which works the same as |
|
|
397 | the C<default_filter> but uses the C<%CBOR::XS::SAFE_FILTER> variable |
|
|
398 | instead. It is prepopulated with the tag decoding functions that are |
|
|
399 | deemed safe (basically the same as C<%CBOR::XS::FILTER> without all |
|
|
400 | the bignum tags), and can be extended by user code as wlel, although, |
|
|
401 | obviously, one should be very careful about adding decoding functions |
|
|
402 | here, since the expectation is that they are safe to use on untrusted |
|
|
403 | data, after all. |
|
|
404 | |
|
|
405 | Example: decode all tags not handled internally into C<CBOR::XS::Tagged> |
|
|
406 | objects, with no other special handling (useful when working with |
|
|
407 | potentially "unsafe" CBOR data). |
|
|
408 | |
|
|
409 | CBOR::XS->new->filter (sub { })->decode ($cbor_data); |
|
|
410 | |
|
|
411 | Example: provide a global filter for tag 1347375694, converting the value |
|
|
412 | into some string form. |
|
|
413 | |
|
|
414 | $CBOR::XS::FILTER{1347375694} = sub { |
|
|
415 | my ($tag, $value); |
|
|
416 | |
|
|
417 | "tag 1347375694 value $value" |
|
|
418 | }; |
|
|
419 | |
|
|
420 | Example: provide your own filter function that looks up tags in your own |
|
|
421 | hash: |
|
|
422 | |
|
|
423 | my %my_filter = ( |
|
|
424 | 998347484 => sub { |
|
|
425 | my ($tag, $value); |
|
|
426 | |
|
|
427 | "tag 998347484 value $value" |
|
|
428 | }; |
|
|
429 | ); |
|
|
430 | |
|
|
431 | my $coder = CBOR::XS->new->filter (sub { |
|
|
432 | &{ $my_filter{$_[0]} or return } |
|
|
433 | }); |
|
|
434 | |
|
|
435 | |
|
|
436 | Example: use the safe filter function (see L<SECURITY CONSIDERATIONS> for |
|
|
437 | more considerations on security). |
|
|
438 | |
|
|
439 | CBOR::XS->new->filter (\&CBOR::XS::safe_filter)->decode ($cbor_data); |
161 | |
440 | |
162 | =item $cbor_data = $cbor->encode ($perl_scalar) |
441 | =item $cbor_data = $cbor->encode ($perl_scalar) |
163 | |
442 | |
164 | Converts the given Perl data structure (a scalar value) to its CBOR |
443 | Converts the given Perl data structure (a scalar value) to its CBOR |
165 | representation. |
444 | representation. |
… | |
… | |
175 | when there is trailing garbage after the CBOR string, it will silently |
454 | when there is trailing garbage after the CBOR string, it will silently |
176 | stop parsing there and return the number of characters consumed so far. |
455 | stop parsing there and return the number of characters consumed so far. |
177 | |
456 | |
178 | This is useful if your CBOR texts are not delimited by an outer protocol |
457 | This is useful if your CBOR texts are not delimited by an outer protocol |
179 | and you need to know where the first CBOR string ends amd the next one |
458 | and you need to know where the first CBOR string ends amd the next one |
180 | starts. |
459 | starts - CBOR strings are self-delimited, so it is possible to concatenate |
|
|
460 | CBOR strings without any delimiters or size fields and recover their data. |
181 | |
461 | |
182 | CBOR::XS->new->decode_prefix ("......") |
462 | CBOR::XS->new->decode_prefix ("......") |
183 | => ("...", 3) |
463 | => ("...", 3) |
|
|
464 | |
|
|
465 | =back |
|
|
466 | |
|
|
467 | =head2 INCREMENTAL PARSING |
|
|
468 | |
|
|
469 | In some cases, there is the need for incremental parsing of JSON |
|
|
470 | texts. While this module always has to keep both CBOR text and resulting |
|
|
471 | Perl data structure in memory at one time, it does allow you to parse a |
|
|
472 | CBOR stream incrementally, using a similar to using "decode_prefix" to see |
|
|
473 | if a full CBOR object is available, but is much more efficient. |
|
|
474 | |
|
|
475 | It basically works by parsing as much of a CBOR string as possible - if |
|
|
476 | the CBOR data is not complete yet, the pasrer will remember where it was, |
|
|
477 | to be able to restart when more data has been accumulated. Once enough |
|
|
478 | data is available to either decode a complete CBOR value or raise an |
|
|
479 | error, a real decode will be attempted. |
|
|
480 | |
|
|
481 | A typical use case would be a network protocol that consists of sending |
|
|
482 | and receiving CBOR-encoded messages. The solution that works with CBOR and |
|
|
483 | about anything else is by prepending a length to every CBOR value, so the |
|
|
484 | receiver knows how many octets to read. More compact (and slightly slower) |
|
|
485 | would be to just send CBOR values back-to-back, as C<CBOR::XS> knows where |
|
|
486 | a CBOR value ends, and doesn't need an explicit length. |
|
|
487 | |
|
|
488 | The following methods help with this: |
|
|
489 | |
|
|
490 | =over 4 |
|
|
491 | |
|
|
492 | =item @decoded = $cbor->incr_parse ($buffer) |
|
|
493 | |
|
|
494 | This method attempts to decode exactly one CBOR value from the beginning |
|
|
495 | of the given C<$buffer>. The value is removed from the C<$buffer> on |
|
|
496 | success. When C<$buffer> doesn't contain a complete value yet, it returns |
|
|
497 | nothing. Finally, when the C<$buffer> doesn't start with something |
|
|
498 | that could ever be a valid CBOR value, it raises an exception, just as |
|
|
499 | C<decode> would. In the latter case the decoder state is undefined and |
|
|
500 | must be reset before being able to parse further. |
|
|
501 | |
|
|
502 | This method modifies the C<$buffer> in place. When no CBOR value can be |
|
|
503 | decoded, the decoder stores the current string offset. On the next call, |
|
|
504 | continues decoding at the place where it stopped before. For this to make |
|
|
505 | sense, the C<$buffer> must begin with the same octets as on previous |
|
|
506 | unsuccessful calls. |
|
|
507 | |
|
|
508 | You can call this method in scalar context, in which case it either |
|
|
509 | returns a decoded value or C<undef>. This makes it impossible to |
|
|
510 | distinguish between CBOR null values (which decode to C<undef>) and an |
|
|
511 | unsuccessful decode, which is often acceptable. |
|
|
512 | |
|
|
513 | =item @decoded = $cbor->incr_parse_multiple ($buffer) |
|
|
514 | |
|
|
515 | Same as C<incr_parse>, but attempts to decode as many CBOR values as |
|
|
516 | possible in one go, instead of at most one. Calls to C<incr_parse> and |
|
|
517 | C<incr_parse_multiple> can be interleaved. |
|
|
518 | |
|
|
519 | =item $cbor->incr_reset |
|
|
520 | |
|
|
521 | Resets the incremental decoder. This throws away any saved state, so that |
|
|
522 | subsequent calls to C<incr_parse> or C<incr_parse_multiple> start to parse |
|
|
523 | a new CBOR value from the beginning of the C<$buffer> again. |
|
|
524 | |
|
|
525 | This method can be called at any time, but it I<must> be called if you want |
|
|
526 | to change your C<$buffer> or there was a decoding error and you want to |
|
|
527 | reuse the C<$cbor> object for future incremental parsings. |
184 | |
528 | |
185 | =back |
529 | =back |
186 | |
530 | |
187 | |
531 | |
188 | =head1 MAPPING |
532 | =head1 MAPPING |
… | |
… | |
206 | CBOR integers become (numeric) perl scalars. On perls without 64 bit |
550 | CBOR integers become (numeric) perl scalars. On perls without 64 bit |
207 | support, 64 bit integers will be truncated or otherwise corrupted. |
551 | support, 64 bit integers will be truncated or otherwise corrupted. |
208 | |
552 | |
209 | =item byte strings |
553 | =item byte strings |
210 | |
554 | |
211 | Byte strings will become octet strings in Perl (the byte values 0..255 |
555 | Byte strings will become octet strings in Perl (the Byte values 0..255 |
212 | will simply become characters of the same value in Perl). |
556 | will simply become characters of the same value in Perl). |
213 | |
557 | |
214 | =item UTF-8 strings |
558 | =item UTF-8 strings |
215 | |
559 | |
216 | UTF-8 strings in CBOR will be decoded, i.e. the UTF-8 octets will be |
560 | UTF-8 strings in CBOR will be decoded, i.e. the UTF-8 octets will be |
… | |
… | |
234 | C<Types:Serialiser::false> and C<Types::Serialiser::error>, |
578 | C<Types:Serialiser::false> and C<Types::Serialiser::error>, |
235 | respectively. They are overloaded to act almost exactly like the numbers |
579 | respectively. They are overloaded to act almost exactly like the numbers |
236 | C<1> and C<0> (for true and false) or to throw an exception on access (for |
580 | C<1> and C<0> (for true and false) or to throw an exception on access (for |
237 | error). See the L<Types::Serialiser> manpage for details. |
581 | error). See the L<Types::Serialiser> manpage for details. |
238 | |
582 | |
239 | =item CBOR tag 256 (perl object) |
583 | =item tagged values |
240 | |
584 | |
241 | The tag value C<256> (TODO: pending iana registration) will be used |
|
|
242 | to deserialise a Perl object serialised with C<FREEZE>. See L<OBJECT |
|
|
243 | SERIALISATION>, below, for details. |
|
|
244 | |
|
|
245 | =item CBOR tag 55799 (magic header) |
|
|
246 | |
|
|
247 | The tag 55799 is ignored (this tag implements the magic header). |
|
|
248 | |
|
|
249 | =item other CBOR tags |
|
|
250 | |
|
|
251 | Tagged items consists of a numeric tag and another CBOR value. Tags not |
585 | Tagged items consists of a numeric tag and another CBOR value. |
252 | handled internally are currently converted into a L<CBOR::XS::Tagged> |
|
|
253 | object, which is simply a blessed array reference consisting of the |
|
|
254 | numeric tag value followed by the (decoded) CBOR value. |
|
|
255 | |
586 | |
256 | In the future, support for user-supplied conversions might get added. |
587 | See L<TAG HANDLING AND EXTENSIONS> and the description of C<< ->filter >> |
|
|
588 | for details on which tags are handled how. |
257 | |
589 | |
258 | =item anything else |
590 | =item anything else |
259 | |
591 | |
260 | Anything else (e.g. unsupported simple values) will raise a decoding |
592 | Anything else (e.g. unsupported simple values) will raise a decoding |
261 | error. |
593 | error. |
… | |
… | |
264 | |
596 | |
265 | |
597 | |
266 | =head2 PERL -> CBOR |
598 | =head2 PERL -> CBOR |
267 | |
599 | |
268 | The mapping from Perl to CBOR is slightly more difficult, as Perl is a |
600 | The mapping from Perl to CBOR is slightly more difficult, as Perl is a |
269 | truly typeless language, so we can only guess which CBOR type is meant by |
601 | typeless language. That means this module can only guess which CBOR type |
270 | a Perl value. |
602 | is meant by a perl value. |
271 | |
603 | |
272 | =over 4 |
604 | =over 4 |
273 | |
605 | |
274 | =item hash references |
606 | =item hash references |
275 | |
607 | |
276 | Perl hash references become CBOR maps. As there is no inherent ordering in |
608 | Perl hash references become CBOR maps. As there is no inherent ordering in |
277 | hash keys (or CBOR maps), they will usually be encoded in a pseudo-random |
609 | hash keys (or CBOR maps), they will usually be encoded in a pseudo-random |
278 | order. |
610 | order. This order can be different each time a hash is encoded. |
279 | |
611 | |
280 | Currently, tied hashes will use the indefinite-length format, while normal |
612 | Currently, tied hashes will use the indefinite-length format, while normal |
281 | hashes will use the fixed-length format. |
613 | hashes will use the fixed-length format. |
282 | |
614 | |
283 | =item array references |
615 | =item array references |
284 | |
616 | |
285 | Perl array references become fixed-length CBOR arrays. |
617 | Perl array references become fixed-length CBOR arrays. |
286 | |
618 | |
287 | =item other references |
619 | =item other references |
288 | |
620 | |
289 | Other unblessed references are generally not allowed and will cause an |
621 | Other unblessed references will be represented using |
290 | exception to be thrown, except for references to the integers C<0> and |
622 | the indirection tag extension (tag value C<22098>, |
291 | C<1>, which get turned into false and true in CBOR. |
623 | L<http://cbor.schmorp.de/indirection>). CBOR decoders are guaranteed |
|
|
624 | to be able to decode these values somehow, by either "doing the right |
|
|
625 | thing", decoding into a generic tagged object, simply ignoring the tag, or |
|
|
626 | something else. |
292 | |
627 | |
293 | =item CBOR::XS::Tagged objects |
628 | =item CBOR::XS::Tagged objects |
294 | |
629 | |
295 | Objects of this type must be arrays consisting of a single C<[tag, value]> |
630 | Objects of this type must be arrays consisting of a single C<[tag, value]> |
296 | pair. The (numerical) tag will be encoded as a CBOR tag, the value will |
631 | pair. The (numerical) tag will be encoded as a CBOR tag, the value will |
297 | be encoded as appropriate for the value. You cna use C<CBOR::XS::tag> to |
632 | be encoded as appropriate for the value. You must use C<CBOR::XS::tag> to |
298 | create such objects. |
633 | create such objects. |
299 | |
634 | |
300 | =item Types::Serialiser::true, Types::Serialiser::false, Types::Serialiser::error |
635 | =item Types::Serialiser::true, Types::Serialiser::false, Types::Serialiser::error |
301 | |
636 | |
302 | These special values become CBOR true, CBOR false and CBOR undefined |
637 | These special values become CBOR true, CBOR false and CBOR undefined |
… | |
… | |
304 | if you want. |
639 | if you want. |
305 | |
640 | |
306 | =item other blessed objects |
641 | =item other blessed objects |
307 | |
642 | |
308 | Other blessed objects are serialised via C<TO_CBOR> or C<FREEZE>. See |
643 | Other blessed objects are serialised via C<TO_CBOR> or C<FREEZE>. See |
309 | L<OBJECT SERIALISATION>, below, for details. |
644 | L<TAG HANDLING AND EXTENSIONS> for specific classes handled by this |
|
|
645 | module, and L<OBJECT SERIALISATION> for generic object serialisation. |
310 | |
646 | |
311 | =item simple scalars |
647 | =item simple scalars |
312 | |
648 | |
313 | TODO |
|
|
314 | Simple Perl scalars (any scalar that is not a reference) are the most |
649 | Simple Perl scalars (any scalar that is not a reference) are the most |
315 | difficult objects to encode: CBOR::XS will encode undefined scalars as |
650 | difficult objects to encode: CBOR::XS will encode undefined scalars as |
316 | CBOR null values, scalars that have last been used in a string context |
651 | CBOR null values, scalars that have last been used in a string context |
317 | before encoding as CBOR strings, and anything else as number value: |
652 | before encoding as CBOR strings, and anything else as number value: |
318 | |
653 | |
319 | # dump as number |
654 | # dump as number |
320 | encode_cbor [2] # yields [2] |
655 | encode_cbor [2] # yields [2] |
321 | encode_cbor [-3.0e17] # yields [-3e+17] |
656 | encode_cbor [-3.0e17] # yields [-3e+17] |
322 | my $value = 5; encode_cbor [$value] # yields [5] |
657 | my $value = 5; encode_cbor [$value] # yields [5] |
323 | |
658 | |
324 | # used as string, so dump as string |
659 | # used as string, so dump as string (either byte or text) |
325 | print $value; |
660 | print $value; |
326 | encode_cbor [$value] # yields ["5"] |
661 | encode_cbor [$value] # yields ["5"] |
327 | |
662 | |
328 | # undef becomes null |
663 | # undef becomes null |
329 | encode_cbor [undef] # yields [null] |
664 | encode_cbor [undef] # yields [null] |
… | |
… | |
332 | |
667 | |
333 | my $x = 3.1; # some variable containing a number |
668 | my $x = 3.1; # some variable containing a number |
334 | "$x"; # stringified |
669 | "$x"; # stringified |
335 | $x .= ""; # another, more awkward way to stringify |
670 | $x .= ""; # another, more awkward way to stringify |
336 | print $x; # perl does it for you, too, quite often |
671 | print $x; # perl does it for you, too, quite often |
|
|
672 | |
|
|
673 | You can force whether a string is encoded as byte or text string by using |
|
|
674 | C<utf8::upgrade> and C<utf8::downgrade> (if C<text_strings> is disabled). |
|
|
675 | |
|
|
676 | utf8::upgrade $x; # encode $x as text string |
|
|
677 | utf8::downgrade $x; # encode $x as byte string |
|
|
678 | |
|
|
679 | More options are available, see L<TYPE CASTS>, below, and the C<text_keys> |
|
|
680 | and C<text_strings> options. |
|
|
681 | |
|
|
682 | Perl doesn't define what operations up- and downgrade strings, so if the |
|
|
683 | difference between byte and text is important, you should up- or downgrade |
|
|
684 | your string as late as possible before encoding. You can also force the |
|
|
685 | use of CBOR text strings by using C<text_keys> or C<text_strings>. |
337 | |
686 | |
338 | You can force the type to be a CBOR number by numifying it: |
687 | You can force the type to be a CBOR number by numifying it: |
339 | |
688 | |
340 | my $x = "3"; # some variable containing a string |
689 | my $x = "3"; # some variable containing a string |
341 | $x += 0; # numify it, ensuring it will be dumped as a number |
690 | $x += 0; # numify it, ensuring it will be dumped as a number |
… | |
… | |
352 | represent numerical values are supported, but might suffer loss of |
701 | represent numerical values are supported, but might suffer loss of |
353 | precision. |
702 | precision. |
354 | |
703 | |
355 | =back |
704 | =back |
356 | |
705 | |
|
|
706 | =head2 TYPE CASTS |
|
|
707 | |
|
|
708 | B<EXPERIMENTAL>: As an experimental extension, C<CBOR::XS> allows you to |
|
|
709 | force specific cbor types to be used when encoding. That allows you to |
|
|
710 | encode types not normally accessible (e.g. half floats) as well as force |
|
|
711 | string types even when C<text_strings> is in effect. |
|
|
712 | |
|
|
713 | Type forcing is done by calling a special "cast" function which keeps a |
|
|
714 | copy of the value and returns a new value that can be handed over to any |
|
|
715 | CBOR encoder function. |
|
|
716 | |
|
|
717 | The following casts are currently available (all of which are unary |
|
|
718 | operators, that is, have a prototype of C<$>): |
|
|
719 | |
|
|
720 | =over |
|
|
721 | |
|
|
722 | =item CBOR::XS::as_int $value |
|
|
723 | |
|
|
724 | Forces the value to be encoded as some form of (basic, not bignum) integer |
|
|
725 | type. |
|
|
726 | |
|
|
727 | =item CBOR::XS::as_text $value |
|
|
728 | |
|
|
729 | Forces the value to be encoded as (UTF-8) text values. |
|
|
730 | |
|
|
731 | =item CBOR::XS::as_bytes $value |
|
|
732 | |
|
|
733 | Forces the value to be encoded as a (binary) string value. |
|
|
734 | |
|
|
735 | Example: encode a perl string as binary even though C<text_strings> is in |
|
|
736 | effect. |
|
|
737 | |
|
|
738 | CBOR::XS->new->text_strings->encode ([4, "text", CBOR::XS::bytes "bytevalue"]); |
|
|
739 | |
|
|
740 | =item CBOR::XS::as_bool $value |
|
|
741 | |
|
|
742 | Converts a Perl boolean (which can be any kind of scalar) into a CBOR |
|
|
743 | boolean. Strictly the same, but shorter to write, than: |
|
|
744 | |
|
|
745 | $value ? Types::Serialiser::true : Types::Serialiser::false |
|
|
746 | |
|
|
747 | =item CBOR::XS::as_float16 $value |
|
|
748 | |
|
|
749 | Forces half-float (IEEE 754 binary16) encoding of the given value. |
|
|
750 | |
|
|
751 | =item CBOR::XS::as_float32 $value |
|
|
752 | |
|
|
753 | Forces single-float (IEEE 754 binary32) encoding of the given value. |
|
|
754 | |
|
|
755 | =item CBOR::XS::as_float64 $value |
|
|
756 | |
|
|
757 | Forces double-float (IEEE 754 binary64) encoding of the given value. |
|
|
758 | |
|
|
759 | =item CBOR::XS::as_cbor $cbor_text |
|
|
760 | |
|
|
761 | Not a type cast per-se, this type cast forces the argument to eb encoded |
|
|
762 | as-is. This can be used to embed pre-encoded CBOR data. |
|
|
763 | |
|
|
764 | Note that no checking on the validity of the C<$cbor_text> is done - it's |
|
|
765 | the callers responsibility to correctly encode values. |
|
|
766 | |
|
|
767 | =item CBOR::XS::as_map [key => value...] |
|
|
768 | |
|
|
769 | Treat the array reference as key value pairs and output a CBOR map. This |
|
|
770 | allows you to generate CBOR maps with arbitrary key types (or, if you |
|
|
771 | don't care about semantics, duplicate keys or prairs in a custom order), |
|
|
772 | which is otherwise hard to do with Perl. |
|
|
773 | |
|
|
774 | The single argument must be an array reference with an even number of |
|
|
775 | elements. |
|
|
776 | |
|
|
777 | Example: encode a CBOR map with a string and an integer as keys. |
|
|
778 | |
|
|
779 | encode_cbor CBOR::XS::as_map [string => "value", 5 => "value"] |
|
|
780 | |
|
|
781 | =back |
|
|
782 | |
|
|
783 | =cut |
|
|
784 | |
|
|
785 | sub CBOR::XS::as_cbor ($) { bless [$_[0], 0, undef], CBOR::XS::Tagged:: } |
|
|
786 | sub CBOR::XS::as_int ($) { bless [$_[0], 1, undef], CBOR::XS::Tagged:: } |
|
|
787 | sub CBOR::XS::as_bytes ($) { bless [$_[0], 2, undef], CBOR::XS::Tagged:: } |
|
|
788 | sub CBOR::XS::as_text ($) { bless [$_[0], 3, undef], CBOR::XS::Tagged:: } |
|
|
789 | sub CBOR::XS::as_float16 ($) { bless [$_[0], 4, undef], CBOR::XS::Tagged:: } |
|
|
790 | sub CBOR::XS::as_float32 ($) { bless [$_[0], 5, undef], CBOR::XS::Tagged:: } |
|
|
791 | sub CBOR::XS::as_float64 ($) { bless [$_[0], 6, undef], CBOR::XS::Tagged:: } |
|
|
792 | |
|
|
793 | sub CBOR::XS::as_bool ($) { $_[0] ? $Types::Serialiser::true : $Types::Serialiser::false } |
|
|
794 | |
|
|
795 | sub CBOR::XS::as_map ($) { |
|
|
796 | ARRAY:: eq ref $_[0] |
|
|
797 | and $#{ $_[0] } & 1 |
|
|
798 | or do { require Carp; Carp::croak ("CBOR::XS::as_map only acepts array references with an even number of elements, caught") }; |
|
|
799 | |
|
|
800 | bless [$_[0], 7, undef], CBOR::XS::Tagged:: |
|
|
801 | } |
|
|
802 | |
357 | =head2 OBJECT SERIALISATION |
803 | =head2 OBJECT SERIALISATION |
|
|
804 | |
|
|
805 | This module implements both a CBOR-specific and the generic |
|
|
806 | L<Types::Serialier> object serialisation protocol. The following |
|
|
807 | subsections explain both methods. |
|
|
808 | |
|
|
809 | =head3 ENCODING |
358 | |
810 | |
359 | This module knows two way to serialise a Perl object: The CBOR-specific |
811 | This module knows two way to serialise a Perl object: The CBOR-specific |
360 | way, and the generic way. |
812 | way, and the generic way. |
361 | |
813 | |
362 | Whenever the encoder encounters a Perl object that it cnanot serialise |
814 | Whenever the encoder encounters a Perl object that it cannot serialise |
363 | directly (most of them), it will first look up the C<TO_CBOR> method on |
815 | directly (most of them), it will first look up the C<TO_CBOR> method on |
364 | it. |
816 | it. |
365 | |
817 | |
366 | If it has a C<TO_CBOR> method, it will call it with the object as only |
818 | If it has a C<TO_CBOR> method, it will call it with the object as only |
367 | argument, and expects exactly one return value, which it will then |
819 | argument, and expects exactly one return value, which it will then |
… | |
… | |
373 | |
825 | |
374 | The C<FREEZE> method can return any number of values (i.e. zero or |
826 | The C<FREEZE> method can return any number of values (i.e. zero or |
375 | more). These will be encoded as CBOR perl object, together with the |
827 | more). These will be encoded as CBOR perl object, together with the |
376 | classname. |
828 | classname. |
377 | |
829 | |
|
|
830 | These methods I<MUST NOT> change the data structure that is being |
|
|
831 | serialised. Failure to comply to this can result in memory corruption - |
|
|
832 | and worse. |
|
|
833 | |
378 | If an object supports neither C<TO_CBOR> nor C<FREEZE>, encoding will fail |
834 | If an object supports neither C<TO_CBOR> nor C<FREEZE>, encoding will fail |
379 | with an error. |
835 | with an error. |
380 | |
836 | |
|
|
837 | =head3 DECODING |
|
|
838 | |
381 | Objects encoded via C<TO_CBOR> cannot be automatically decoded, but |
839 | Objects encoded via C<TO_CBOR> cannot (normally) be automatically decoded, |
382 | objects encoded via C<FREEZE> can be decoded using the following protocol: |
840 | but objects encoded via C<FREEZE> can be decoded using the following |
|
|
841 | protocol: |
383 | |
842 | |
384 | When an encoded CBOR perl object is encountered by the decoder, it will |
843 | When an encoded CBOR perl object is encountered by the decoder, it will |
385 | look up the C<THAW> method, by using the stored classname, and will fail |
844 | look up the C<THAW> method, by using the stored classname, and will fail |
386 | if the method cannot be found. |
845 | if the method cannot be found. |
387 | |
846 | |
388 | After the lookup it will call the C<THAW> method with the stored classname |
847 | After the lookup it will call the C<THAW> method with the stored classname |
389 | as first argument, the constant string C<CBOR> as second argument, and all |
848 | as first argument, the constant string C<CBOR> as second argument, and all |
390 | values returned by C<FREEZE> as remaining arguments. |
849 | values returned by C<FREEZE> as remaining arguments. |
391 | |
850 | |
392 | =head4 EXAMPLES |
851 | =head3 EXAMPLES |
393 | |
852 | |
394 | Here is an example C<TO_CBOR> method: |
853 | Here is an example C<TO_CBOR> method: |
395 | |
854 | |
396 | sub My::Object::TO_CBOR { |
855 | sub My::Object::TO_CBOR { |
397 | my ($obj) = @_; |
856 | my ($obj) = @_; |
… | |
… | |
408 | |
867 | |
409 | sub URI::TO_CBOR { |
868 | sub URI::TO_CBOR { |
410 | my ($self) = @_; |
869 | my ($self) = @_; |
411 | my $uri = "$self"; # stringify uri |
870 | my $uri = "$self"; # stringify uri |
412 | utf8::upgrade $uri; # make sure it will be encoded as UTF-8 string |
871 | utf8::upgrade $uri; # make sure it will be encoded as UTF-8 string |
413 | CBOR::XS::tagged 32, "$_[0]" |
872 | CBOR::XS::tag 32, "$_[0]" |
414 | } |
873 | } |
415 | |
874 | |
416 | This will encode URIs as a UTF-8 string with tag 32, which indicates an |
875 | This will encode URIs as a UTF-8 string with tag 32, which indicates an |
417 | URI. |
876 | URI. |
418 | |
877 | |
… | |
… | |
429 | "$self" # encode url string |
888 | "$self" # encode url string |
430 | } |
889 | } |
431 | |
890 | |
432 | sub URI::THAW { |
891 | sub URI::THAW { |
433 | my ($class, $serialiser, $uri) = @_; |
892 | my ($class, $serialiser, $uri) = @_; |
434 | |
|
|
435 | $class->new ($uri) |
893 | $class->new ($uri) |
436 | } |
894 | } |
437 | |
895 | |
438 | Unlike C<TO_CBOR>, multiple values can be returned by C<FREEZE>. For |
896 | Unlike C<TO_CBOR>, multiple values can be returned by C<FREEZE>. For |
439 | example, a C<FREEZE> method that returns "type", "id" and "variant" values |
897 | example, a C<FREEZE> method that returns "type", "id" and "variant" values |
… | |
… | |
455 | =head1 MAGIC HEADER |
913 | =head1 MAGIC HEADER |
456 | |
914 | |
457 | There is no way to distinguish CBOR from other formats |
915 | There is no way to distinguish CBOR from other formats |
458 | programmatically. To make it easier to distinguish CBOR from other |
916 | programmatically. To make it easier to distinguish CBOR from other |
459 | formats, the CBOR specification has a special "magic string" that can be |
917 | formats, the CBOR specification has a special "magic string" that can be |
460 | prepended to any CBOR string without changing it's meaning. |
918 | prepended to any CBOR string without changing its meaning. |
461 | |
919 | |
462 | This string is available as C<$CBOR::XS::MAGIC>. This module does not |
920 | This string is available as C<$CBOR::XS::MAGIC>. This module does not |
463 | prepend this string tot he CBOR data it generates, but it will ignroe it |
921 | prepend this string to the CBOR data it generates, but it will ignore it |
464 | if present, so users can prepend this string as a "file type" indicator as |
922 | if present, so users can prepend this string as a "file type" indicator as |
465 | required. |
923 | required. |
466 | |
924 | |
467 | |
925 | |
468 | =head1 THE CBOR::XS::Tagged CLASS |
926 | =head1 THE CBOR::XS::Tagged CLASS |
… | |
… | |
551 | Wrap CBOR data in CBOR: |
1009 | Wrap CBOR data in CBOR: |
552 | |
1010 | |
553 | my $cbor_cbor = encode_cbor |
1011 | my $cbor_cbor = encode_cbor |
554 | CBOR::XS::tag 24, |
1012 | CBOR::XS::tag 24, |
555 | encode_cbor [1, 2, 3]; |
1013 | encode_cbor [1, 2, 3]; |
|
|
1014 | |
|
|
1015 | =head1 TAG HANDLING AND EXTENSIONS |
|
|
1016 | |
|
|
1017 | This section describes how this module handles specific tagged values |
|
|
1018 | and extensions. If a tag is not mentioned here and no additional filters |
|
|
1019 | are provided for it, then the default handling applies (creating a |
|
|
1020 | CBOR::XS::Tagged object on decoding, and only encoding the tag when |
|
|
1021 | explicitly requested). |
|
|
1022 | |
|
|
1023 | Tags not handled specifically are currently converted into a |
|
|
1024 | L<CBOR::XS::Tagged> object, which is simply a blessed array reference |
|
|
1025 | consisting of the numeric tag value followed by the (decoded) CBOR value. |
|
|
1026 | |
|
|
1027 | Future versions of this module reserve the right to special case |
|
|
1028 | additional tags (such as base64url). |
|
|
1029 | |
|
|
1030 | =head2 ENFORCED TAGS |
|
|
1031 | |
|
|
1032 | These tags are always handled when decoding, and their handling cannot be |
|
|
1033 | overridden by the user. |
|
|
1034 | |
|
|
1035 | =over 4 |
|
|
1036 | |
|
|
1037 | =item 26 (perl-object, L<http://cbor.schmorp.de/perl-object>) |
|
|
1038 | |
|
|
1039 | These tags are automatically created (and decoded) for serialisable |
|
|
1040 | objects using the C<FREEZE/THAW> methods (the L<Types::Serialier> object |
|
|
1041 | serialisation protocol). See L<OBJECT SERIALISATION> for details. |
|
|
1042 | |
|
|
1043 | =item 28, 29 (shareable, sharedref, L<http://cbor.schmorp.de/value-sharing>) |
|
|
1044 | |
|
|
1045 | These tags are automatically decoded when encountered (and they do not |
|
|
1046 | result in a cyclic data structure, see C<allow_cycles>), resulting in |
|
|
1047 | shared values in the decoded object. They are only encoded, however, when |
|
|
1048 | C<allow_sharing> is enabled. |
|
|
1049 | |
|
|
1050 | Not all shared values can be successfully decoded: values that reference |
|
|
1051 | themselves will I<currently> decode as C<undef> (this is not the same |
|
|
1052 | as a reference pointing to itself, which will be represented as a value |
|
|
1053 | that contains an indirect reference to itself - these will be decoded |
|
|
1054 | properly). |
|
|
1055 | |
|
|
1056 | Note that considerably more shared value data structures can be decoded |
|
|
1057 | than will be encoded - currently, only values pointed to by references |
|
|
1058 | will be shared, others will not. While non-reference shared values can be |
|
|
1059 | generated in Perl with some effort, they were considered too unimportant |
|
|
1060 | to be supported in the encoder. The decoder, however, will decode these |
|
|
1061 | values as shared values. |
|
|
1062 | |
|
|
1063 | =item 256, 25 (stringref-namespace, stringref, L<http://cbor.schmorp.de/stringref>) |
|
|
1064 | |
|
|
1065 | These tags are automatically decoded when encountered. They are only |
|
|
1066 | encoded, however, when C<pack_strings> is enabled. |
|
|
1067 | |
|
|
1068 | =item 22098 (indirection, L<http://cbor.schmorp.de/indirection>) |
|
|
1069 | |
|
|
1070 | This tag is automatically generated when a reference are encountered (with |
|
|
1071 | the exception of hash and array references). It is converted to a reference |
|
|
1072 | when decoding. |
|
|
1073 | |
|
|
1074 | =item 55799 (self-describe CBOR, RFC 7049) |
|
|
1075 | |
|
|
1076 | This value is not generated on encoding (unless explicitly requested by |
|
|
1077 | the user), and is simply ignored when decoding. |
|
|
1078 | |
|
|
1079 | =back |
|
|
1080 | |
|
|
1081 | =head2 NON-ENFORCED TAGS |
|
|
1082 | |
|
|
1083 | These tags have default filters provided when decoding. Their handling can |
|
|
1084 | be overridden by changing the C<%CBOR::XS::FILTER> entry for the tag, or by |
|
|
1085 | providing a custom C<filter> callback when decoding. |
|
|
1086 | |
|
|
1087 | When they result in decoding into a specific Perl class, the module |
|
|
1088 | usually provides a corresponding C<TO_CBOR> method as well. |
|
|
1089 | |
|
|
1090 | When any of these need to load additional modules that are not part of the |
|
|
1091 | perl core distribution (e.g. L<URI>), it is (currently) up to the user to |
|
|
1092 | provide these modules. The decoding usually fails with an exception if the |
|
|
1093 | required module cannot be loaded. |
|
|
1094 | |
|
|
1095 | =over 4 |
|
|
1096 | |
|
|
1097 | =item 0, 1 (date/time string, seconds since the epoch) |
|
|
1098 | |
|
|
1099 | These tags are decoded into L<Time::Piece> objects. The corresponding |
|
|
1100 | C<Time::Piece::TO_CBOR> method always encodes into tag 1 values currently. |
|
|
1101 | |
|
|
1102 | The L<Time::Piece> API is generally surprisingly bad, and fractional |
|
|
1103 | seconds are only accidentally kept intact, so watch out. On the plus side, |
|
|
1104 | the module comes with perl since 5.10, which has to count for something. |
|
|
1105 | |
|
|
1106 | =item 2, 3 (positive/negative bignum) |
|
|
1107 | |
|
|
1108 | These tags are decoded into L<Math::BigInt> objects. The corresponding |
|
|
1109 | C<Math::BigInt::TO_CBOR> method encodes "small" bigints into normal CBOR |
|
|
1110 | integers, and others into positive/negative CBOR bignums. |
|
|
1111 | |
|
|
1112 | =item 4, 5, 264, 265 (decimal fraction/bigfloat) |
|
|
1113 | |
|
|
1114 | Both decimal fractions and bigfloats are decoded into L<Math::BigFloat> |
|
|
1115 | objects. The corresponding C<Math::BigFloat::TO_CBOR> method I<always> |
|
|
1116 | encodes into a decimal fraction (either tag 4 or 264). |
|
|
1117 | |
|
|
1118 | NaN and infinities are not encoded properly, as they cannot be represented |
|
|
1119 | in CBOR. |
|
|
1120 | |
|
|
1121 | See L<BIGNUM SECURITY CONSIDERATIONS> for more info. |
|
|
1122 | |
|
|
1123 | =item 30 (rational numbers) |
|
|
1124 | |
|
|
1125 | These tags are decoded into L<Math::BigRat> objects. The corresponding |
|
|
1126 | C<Math::BigRat::TO_CBOR> method encodes rational numbers with denominator |
|
|
1127 | C<1> via their numerator only, i.e., they become normal integers or |
|
|
1128 | C<bignums>. |
|
|
1129 | |
|
|
1130 | See L<BIGNUM SECURITY CONSIDERATIONS> for more info. |
|
|
1131 | |
|
|
1132 | =item 21, 22, 23 (expected later JSON conversion) |
|
|
1133 | |
|
|
1134 | CBOR::XS is not a CBOR-to-JSON converter, and will simply ignore these |
|
|
1135 | tags. |
|
|
1136 | |
|
|
1137 | =item 32 (URI) |
|
|
1138 | |
|
|
1139 | These objects decode into L<URI> objects. The corresponding |
|
|
1140 | C<URI::TO_CBOR> method again results in a CBOR URI value. |
|
|
1141 | |
|
|
1142 | =back |
|
|
1143 | |
|
|
1144 | =cut |
556 | |
1145 | |
557 | =head1 CBOR and JSON |
1146 | =head1 CBOR and JSON |
558 | |
1147 | |
559 | CBOR is supposed to implement a superset of the JSON data model, and is, |
1148 | CBOR is supposed to implement a superset of the JSON data model, and is, |
560 | with some coercion, able to represent all JSON texts (something that other |
1149 | with some coercion, able to represent all JSON texts (something that other |
… | |
… | |
569 | CBOR intact. |
1158 | CBOR intact. |
570 | |
1159 | |
571 | |
1160 | |
572 | =head1 SECURITY CONSIDERATIONS |
1161 | =head1 SECURITY CONSIDERATIONS |
573 | |
1162 | |
574 | When you are using CBOR in a protocol, talking to untrusted potentially |
1163 | Tl;dr... if you want to decode or encode CBOR from untrusted sources, you |
575 | hostile creatures requires relatively few measures. |
1164 | should start with a coder object created via C<new_safe> (which implements |
|
|
1165 | the mitigations explained below): |
576 | |
1166 | |
|
|
1167 | my $coder = CBOR::XS->new_safe; |
|
|
1168 | |
|
|
1169 | my $data = $coder->decode ($cbor_text); |
|
|
1170 | my $cbor = $coder->encode ($data); |
|
|
1171 | |
|
|
1172 | Longer version: When you are using CBOR in a protocol, talking to |
|
|
1173 | untrusted potentially hostile creatures requires some thought: |
|
|
1174 | |
|
|
1175 | =over 4 |
|
|
1176 | |
|
|
1177 | =item Security of the CBOR decoder itself |
|
|
1178 | |
577 | First of all, your CBOR decoder should be secure, that is, should not have |
1179 | First and foremost, your CBOR decoder should be secure, that is, should |
|
|
1180 | not have any buffer overflows or similar bugs that could potentially be |
578 | any buffer overflows. Obviously, this module should ensure that and I am |
1181 | exploited. Obviously, this module should ensure that and I am trying hard |
579 | trying hard on making that true, but you never know. |
1182 | on making that true, but you never know. |
580 | |
1183 | |
|
|
1184 | =item CBOR::XS can invoke almost arbitrary callbacks during decoding |
|
|
1185 | |
|
|
1186 | CBOR::XS supports object serialisation - decoding CBOR can cause calls |
|
|
1187 | to I<any> C<THAW> method in I<any> package that exists in your process |
|
|
1188 | (that is, CBOR::XS will not try to load modules, but any existing C<THAW> |
|
|
1189 | method or function can be called, so they all have to be secure). |
|
|
1190 | |
|
|
1191 | Less obviously, it will also invoke C<TO_CBOR> and C<FREEZE> methods - |
|
|
1192 | even if all your C<THAW> methods are secure, encoding data structures from |
|
|
1193 | untrusted sources can invoke those and trigger bugs in those. |
|
|
1194 | |
|
|
1195 | So, if you are not sure about the security of all the modules you |
|
|
1196 | have loaded (you shouldn't), you should disable this part using |
|
|
1197 | C<forbid_objects> or using C<new_safe>. |
|
|
1198 | |
|
|
1199 | =item CBOR can be extended with tags that call library code |
|
|
1200 | |
|
|
1201 | CBOR can be extended with tags, and C<CBOR::XS> has a registry of |
|
|
1202 | conversion functions for many existing tags that can be extended via |
|
|
1203 | third-party modules (see the C<filter> method). |
|
|
1204 | |
|
|
1205 | If you don't trust these, you should configure the "safe" filter function, |
|
|
1206 | C<CBOR::XS::safe_filter> (C<new_safe> does this), which by default only |
|
|
1207 | includes conversion functions that are considered "safe" by the author |
|
|
1208 | (but again, they can be extended by third party modules). |
|
|
1209 | |
|
|
1210 | Depending on your level of paranoia, you can use the "safe" filter: |
|
|
1211 | |
|
|
1212 | $cbor->filter (\&CBOR::XS::safe_filter); |
|
|
1213 | |
|
|
1214 | ... your own filter... |
|
|
1215 | |
|
|
1216 | $cbor->filter (sub { ... do your stuffs here ... }); |
|
|
1217 | |
|
|
1218 | ... or even no filter at all, disabling all tag decoding: |
|
|
1219 | |
|
|
1220 | $cbor->filter (sub { }); |
|
|
1221 | |
|
|
1222 | This is never a problem for encoding, as the tag mechanism only exists in |
|
|
1223 | CBOR texts. |
|
|
1224 | |
|
|
1225 | =item Resource-starving attacks: object memory usage |
|
|
1226 | |
581 | Second, you need to avoid resource-starving attacks. That means you should |
1227 | You need to avoid resource-starving attacks. That means you should limit |
582 | limit the size of CBOR data you accept, or make sure then when your |
1228 | the size of CBOR data you accept, or make sure then when your resources |
583 | resources run out, that's just fine (e.g. by using a separate process that |
1229 | run out, that's just fine (e.g. by using a separate process that can |
584 | can crash safely). The size of a CBOR string in octets is usually a good |
1230 | crash safely). The size of a CBOR string in octets is usually a good |
585 | indication of the size of the resources required to decode it into a Perl |
1231 | indication of the size of the resources required to decode it into a Perl |
586 | structure. While CBOR::XS can check the size of the CBOR text, it might be |
1232 | structure. While CBOR::XS can check the size of the CBOR text (using |
587 | too late when you already have it in memory, so you might want to check |
1233 | C<max_size> - done by C<new_safe>), it might be too late when you already |
588 | the size before you accept the string. |
1234 | have it in memory, so you might want to check the size before you accept |
|
|
1235 | the string. |
589 | |
1236 | |
|
|
1237 | As for encoding, it is possible to construct data structures that are |
|
|
1238 | relatively small but result in large CBOR texts (for example by having an |
|
|
1239 | array full of references to the same big data structure, which will all be |
|
|
1240 | deep-cloned during encoding by default). This is rarely an actual issue |
|
|
1241 | (and the worst case is still just running out of memory), but you can |
|
|
1242 | reduce this risk by using C<allow_sharing>. |
|
|
1243 | |
|
|
1244 | =item Resource-starving attacks: stack overflows |
|
|
1245 | |
590 | Third, CBOR::XS recurses using the C stack when decoding objects and |
1246 | CBOR::XS recurses using the C stack when decoding objects and arrays. The |
591 | arrays. The C stack is a limited resource: for instance, on my amd64 |
1247 | C stack is a limited resource: for instance, on my amd64 machine with 8MB |
592 | machine with 8MB of stack size I can decode around 180k nested arrays but |
1248 | of stack size I can decode around 180k nested arrays but only 14k nested |
593 | only 14k nested CBOR objects (due to perl itself recursing deeply on croak |
1249 | CBOR objects (due to perl itself recursing deeply on croak to free the |
594 | to free the temporary). If that is exceeded, the program crashes. To be |
1250 | temporary). If that is exceeded, the program crashes. To be conservative, |
595 | conservative, the default nesting limit is set to 512. If your process |
1251 | the default nesting limit is set to 512. If your process has a smaller |
596 | has a smaller stack, you should adjust this setting accordingly with the |
1252 | stack, you should adjust this setting accordingly with the C<max_depth> |
597 | C<max_depth> method. |
1253 | method. |
|
|
1254 | |
|
|
1255 | =item Resource-starving attacks: CPU en-/decoding complexity |
|
|
1256 | |
|
|
1257 | CBOR::XS will use the L<Math::BigInt>, L<Math::BigFloat> and |
|
|
1258 | L<Math::BigRat> libraries to represent encode/decode bignums. These can be |
|
|
1259 | very slow (as in, centuries of CPU time) and can even crash your program |
|
|
1260 | (and are generally not very trustworthy). See the next section on bignum |
|
|
1261 | security for details. |
|
|
1262 | |
|
|
1263 | =item Data breaches: leaking information in error messages |
|
|
1264 | |
|
|
1265 | CBOR::XS might leak contents of your Perl data structures in its error |
|
|
1266 | messages, so when you serialise sensitive information you might want to |
|
|
1267 | make sure that exceptions thrown by CBOR::XS will not end up in front of |
|
|
1268 | untrusted eyes. |
|
|
1269 | |
|
|
1270 | =item Something else... |
598 | |
1271 | |
599 | Something else could bomb you, too, that I forgot to think of. In that |
1272 | Something else could bomb you, too, that I forgot to think of. In that |
600 | case, you get to keep the pieces. I am always open for hints, though... |
1273 | case, you get to keep the pieces. I am always open for hints, though... |
601 | |
1274 | |
602 | Also keep in mind that CBOR::XS might leak contents of your Perl data |
1275 | =back |
603 | structures in its error messages, so when you serialise sensitive |
1276 | |
604 | information you might want to make sure that exceptions thrown by CBOR::XS |
1277 | |
605 | will not end up in front of untrusted eyes. |
1278 | =head1 BIGNUM SECURITY CONSIDERATIONS |
|
|
1279 | |
|
|
1280 | CBOR::XS provides a C<TO_CBOR> method for both L<Math::BigInt> and |
|
|
1281 | L<Math::BigFloat> that tries to encode the number in the simplest possible |
|
|
1282 | way, that is, either a CBOR integer, a CBOR bigint/decimal fraction (tag |
|
|
1283 | 4) or an arbitrary-exponent decimal fraction (tag 264). Rational numbers |
|
|
1284 | (L<Math::BigRat>, tag 30) can also contain bignums as members. |
|
|
1285 | |
|
|
1286 | CBOR::XS will also understand base-2 bigfloat or arbitrary-exponent |
|
|
1287 | bigfloats (tags 5 and 265), but it will never generate these on its own. |
|
|
1288 | |
|
|
1289 | Using the built-in L<Math::BigInt::Calc> support, encoding and decoding |
|
|
1290 | decimal fractions is generally fast. Decoding bigints can be slow for very |
|
|
1291 | big numbers (tens of thousands of digits, something that could potentially |
|
|
1292 | be caught by limiting the size of CBOR texts), and decoding bigfloats or |
|
|
1293 | arbitrary-exponent bigfloats can be I<extremely> slow (minutes, decades) |
|
|
1294 | for large exponents (roughly 40 bit and longer). |
|
|
1295 | |
|
|
1296 | Additionally, L<Math::BigInt> can take advantage of other bignum |
|
|
1297 | libraries, such as L<Math::GMP>, which cannot handle big floats with large |
|
|
1298 | exponents, and might simply abort or crash your program, due to their code |
|
|
1299 | quality. |
|
|
1300 | |
|
|
1301 | This can be a concern if you want to parse untrusted CBOR. If it is, you |
|
|
1302 | might want to disable decoding of tag 2 (bigint) and 3 (negative bigint) |
|
|
1303 | types. You should also disable types 5 and 265, as these can be slow even |
|
|
1304 | without bigints. |
|
|
1305 | |
|
|
1306 | Disabling bigints will also partially or fully disable types that rely on |
|
|
1307 | them, e.g. rational numbers that use bignums. |
|
|
1308 | |
606 | |
1309 | |
607 | =head1 CBOR IMPLEMENTATION NOTES |
1310 | =head1 CBOR IMPLEMENTATION NOTES |
608 | |
1311 | |
609 | This section contains some random implementation notes. They do not |
1312 | This section contains some random implementation notes. They do not |
610 | describe guaranteed behaviour, but merely behaviour as-is implemented |
1313 | describe guaranteed behaviour, but merely behaviour as-is implemented |
… | |
… | |
619 | Only the double data type is supported for NV data types - when Perl uses |
1322 | Only the double data type is supported for NV data types - when Perl uses |
620 | long double to represent floating point values, they might not be encoded |
1323 | long double to represent floating point values, they might not be encoded |
621 | properly. Half precision types are accepted, but not encoded. |
1324 | properly. Half precision types are accepted, but not encoded. |
622 | |
1325 | |
623 | Strict mode and canonical mode are not implemented. |
1326 | Strict mode and canonical mode are not implemented. |
|
|
1327 | |
|
|
1328 | |
|
|
1329 | =head1 LIMITATIONS ON PERLS WITHOUT 64-BIT INTEGER SUPPORT |
|
|
1330 | |
|
|
1331 | On perls that were built without 64 bit integer support (these are rare |
|
|
1332 | nowadays, even on 32 bit architectures, as all major Perl distributions |
|
|
1333 | are built with 64 bit integer support), support for any kind of 64 bit |
|
|
1334 | value in CBOR is very limited - most likely, these 64 bit values will |
|
|
1335 | be truncated, corrupted, or otherwise not decoded correctly. This also |
|
|
1336 | includes string, float, array and map sizes that are stored as 64 bit |
|
|
1337 | integers. |
624 | |
1338 | |
625 | |
1339 | |
626 | =head1 THREADS |
1340 | =head1 THREADS |
627 | |
1341 | |
628 | This module is I<not> guaranteed to be thread safe and there are no |
1342 | This module is I<not> guaranteed to be thread safe and there are no |
… | |
… | |
642 | Please refrain from using rt.cpan.org or any other bug reporting |
1356 | Please refrain from using rt.cpan.org or any other bug reporting |
643 | service. I put the contact address into my modules for a reason. |
1357 | service. I put the contact address into my modules for a reason. |
644 | |
1358 | |
645 | =cut |
1359 | =cut |
646 | |
1360 | |
|
|
1361 | # clumsy and slow hv_store-in-hash helper function |
|
|
1362 | sub _hv_store { |
|
|
1363 | $_[0]{$_[1]} = $_[2]; |
|
|
1364 | } |
|
|
1365 | |
|
|
1366 | our %FILTER = ( |
|
|
1367 | 0 => sub { # rfc4287 datetime, utf-8 |
|
|
1368 | require Time::Piece; |
|
|
1369 | # Time::Piece::Strptime uses the "incredibly flexible date parsing routine" |
|
|
1370 | # from FreeBSD, which can't parse ISO 8601, RFC3339, RFC4287 or much of anything |
|
|
1371 | # else either. Whats incredibe over standard strptime totally escapes me. |
|
|
1372 | # doesn't do fractional times, either. sigh. |
|
|
1373 | # In fact, it's all a lie, it uses whatever strptime it wants, and of course, |
|
|
1374 | # they are all incompatible. The openbsd one simply ignores %z (but according to the |
|
|
1375 | # docs, it would be much more incredibly flexible indeed. If it worked, that is.). |
|
|
1376 | scalar eval { |
|
|
1377 | my $s = $_[1]; |
|
|
1378 | |
|
|
1379 | $s =~ s/Z$/+00:00/; |
|
|
1380 | $s =~ s/(\.[0-9]+)?([+-][0-9][0-9]):([0-9][0-9])$// |
|
|
1381 | or die; |
|
|
1382 | |
|
|
1383 | my $b = $1 - ($2 * 60 + $3) * 60; # fractional part + offset. hopefully |
|
|
1384 | my $d = Time::Piece->strptime ($s, "%Y-%m-%dT%H:%M:%S"); |
|
|
1385 | |
|
|
1386 | Time::Piece::gmtime ($d->epoch + $b) |
|
|
1387 | } || die "corrupted CBOR date/time string ($_[0])"; |
|
|
1388 | }, |
|
|
1389 | |
|
|
1390 | 1 => sub { # seconds since the epoch, possibly fractional |
|
|
1391 | require Time::Piece; |
|
|
1392 | scalar Time::Piece::gmtime (pop) |
|
|
1393 | }, |
|
|
1394 | |
|
|
1395 | 2 => sub { # pos bigint |
|
|
1396 | require Math::BigInt; |
|
|
1397 | Math::BigInt->new ("0x" . unpack "H*", pop) |
|
|
1398 | }, |
|
|
1399 | |
|
|
1400 | 3 => sub { # neg bigint |
|
|
1401 | require Math::BigInt; |
|
|
1402 | -Math::BigInt->new ("0x" . unpack "H*", pop) |
|
|
1403 | }, |
|
|
1404 | |
|
|
1405 | 4 => sub { # decimal fraction, array |
|
|
1406 | require Math::BigFloat; |
|
|
1407 | Math::BigFloat->new ($_[1][1] . "E" . $_[1][0]) |
|
|
1408 | }, |
|
|
1409 | |
|
|
1410 | 264 => sub { # decimal fraction with arbitrary exponent |
|
|
1411 | require Math::BigFloat; |
|
|
1412 | Math::BigFloat->new ($_[1][1] . "E" . $_[1][0]) |
|
|
1413 | }, |
|
|
1414 | |
|
|
1415 | 5 => sub { # bigfloat, array |
|
|
1416 | require Math::BigFloat; |
|
|
1417 | scalar Math::BigFloat->new ($_[1][1]) * Math::BigFloat->new (2)->bpow ($_[1][0]) |
|
|
1418 | }, |
|
|
1419 | |
|
|
1420 | 265 => sub { # bigfloat with arbitrary exponent |
|
|
1421 | require Math::BigFloat; |
|
|
1422 | scalar Math::BigFloat->new ($_[1][1]) * Math::BigFloat->new (2)->bpow ($_[1][0]) |
|
|
1423 | }, |
|
|
1424 | |
|
|
1425 | 30 => sub { # rational number |
|
|
1426 | require Math::BigRat; |
|
|
1427 | Math::BigRat->new ("$_[1][0]/$_[1][1]") # separate parameters only work in recent versons |
|
|
1428 | }, |
|
|
1429 | |
|
|
1430 | 21 => sub { pop }, # expected conversion to base64url encoding |
|
|
1431 | 22 => sub { pop }, # expected conversion to base64 encoding |
|
|
1432 | 23 => sub { pop }, # expected conversion to base16 encoding |
|
|
1433 | |
|
|
1434 | # 24 # embedded cbor, byte string |
|
|
1435 | |
|
|
1436 | 32 => sub { |
|
|
1437 | require URI; |
|
|
1438 | URI->new (pop) |
|
|
1439 | }, |
|
|
1440 | |
|
|
1441 | # 33 # base64url rfc4648, utf-8 |
|
|
1442 | # 34 # base64 rfc46484, utf-8 |
|
|
1443 | # 35 # regex pcre/ecma262, utf-8 |
|
|
1444 | # 36 # mime message rfc2045, utf-8 |
|
|
1445 | ); |
|
|
1446 | |
|
|
1447 | sub default_filter { |
|
|
1448 | &{ $FILTER{$_[0]} or return } |
|
|
1449 | } |
|
|
1450 | |
|
|
1451 | our %SAFE_FILTER = map { $_ => $FILTER{$_} } 0, 1, 21, 22, 23, 32; |
|
|
1452 | |
|
|
1453 | sub safe_filter { |
|
|
1454 | &{ $SAFE_FILTER{$_[0]} or return } |
|
|
1455 | } |
|
|
1456 | |
|
|
1457 | sub URI::TO_CBOR { |
|
|
1458 | my $uri = $_[0]->as_string; |
|
|
1459 | utf8::upgrade $uri; |
|
|
1460 | tag 32, $uri |
|
|
1461 | } |
|
|
1462 | |
|
|
1463 | sub Math::BigInt::TO_CBOR { |
|
|
1464 | if (-2147483648 <= $_[0] && $_[0] <= 2147483647) { |
|
|
1465 | $_[0]->numify |
|
|
1466 | } else { |
|
|
1467 | my $hex = substr $_[0]->as_hex, 2; |
|
|
1468 | $hex = "0$hex" if 1 & length $hex; # sigh |
|
|
1469 | tag $_[0] >= 0 ? 2 : 3, pack "H*", $hex |
|
|
1470 | } |
|
|
1471 | } |
|
|
1472 | |
|
|
1473 | sub Math::BigFloat::TO_CBOR { |
|
|
1474 | my ($m, $e) = $_[0]->parts; |
|
|
1475 | |
|
|
1476 | -9223372036854775808 <= $e && $e <= 18446744073709551615 |
|
|
1477 | ? tag 4, [$e->numify, $m] |
|
|
1478 | : tag 264, [$e, $m] |
|
|
1479 | } |
|
|
1480 | |
|
|
1481 | sub Math::BigRat::TO_CBOR { |
|
|
1482 | my ($n, $d) = $_[0]->parts; |
|
|
1483 | |
|
|
1484 | # older versions of BigRat need *1, as they not always return numbers |
|
|
1485 | |
|
|
1486 | $d*1 == 1 |
|
|
1487 | ? $n*1 |
|
|
1488 | : tag 30, [$n*1, $d*1] |
|
|
1489 | } |
|
|
1490 | |
|
|
1491 | sub Time::Piece::TO_CBOR { |
|
|
1492 | tag 1, 0 + $_[0]->epoch |
|
|
1493 | } |
|
|
1494 | |
647 | XSLoader::load "CBOR::XS", $VERSION; |
1495 | XSLoader::load "CBOR::XS", $VERSION; |
648 | |
1496 | |
649 | =head1 SEE ALSO |
1497 | =head1 SEE ALSO |
650 | |
1498 | |
651 | The L<JSON> and L<JSON::XS> modules that do similar, but human-readable, |
1499 | The L<JSON> and L<JSON::XS> modules that do similar, but human-readable, |