… | |
… | |
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 |
|
|
32 | to you to do). Furthermore, details of the implementation might change |
|
|
33 | freely before version 1.0. And lastly, most extensions depend on an IANA |
|
|
34 | assignment, and until that assignment is official, this implementation is |
|
|
35 | not interoperable with other implementations (even future versions of this |
|
|
36 | 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). |
50 | |
42 | |
51 | To give you a general idea about speed, with texts in the megabyte range, |
43 | 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 |
44 | 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 |
45 | L<JSON::XS> and decodes about 15%-30% faster than those. The shorter the |
54 | data, the worse L<Storable> performs in comparison. |
46 | data, the worse L<Storable> performs in comparison. |
55 | |
47 | |
56 | As for compactness, C<CBOR::XS> encoded data structures are usually about |
48 | Regarding compactness, C<CBOR::XS>-encoded data structures are usually |
57 | 20% smaller than the same data encoded as (compact) JSON or L<Storable>. |
49 | about 20% smaller than the same data encoded as (compact) JSON or |
|
|
50 | L<Storable>. |
58 | |
51 | |
59 | In addition to the core CBOR data format, this module implements a number |
52 | In addition to the core CBOR data format, this module implements a |
60 | of extensions, to support cyclic and self-referencing data structures |
53 | number of extensions, to support cyclic and shared data structures |
61 | (see C<allow_sharing>), string deduplication (see C<pack_strings>) and |
54 | (see C<allow_sharing> and C<allow_cycles>), string deduplication (see |
62 | scalar references (always enabled). |
55 | C<pack_strings>) and scalar references (always enabled). |
63 | |
56 | |
64 | 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 |
65 | 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. |
66 | |
59 | |
67 | 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 |
… | |
… | |
71 | |
64 | |
72 | package CBOR::XS; |
65 | package CBOR::XS; |
73 | |
66 | |
74 | use common::sense; |
67 | use common::sense; |
75 | |
68 | |
76 | our $VERSION = 0.09; |
69 | our $VERSION = 1.5; |
77 | our @ISA = qw(Exporter); |
70 | our @ISA = qw(Exporter); |
78 | |
71 | |
79 | our @EXPORT = qw(encode_cbor decode_cbor); |
72 | our @EXPORT = qw(encode_cbor decode_cbor); |
80 | |
73 | |
81 | use Exporter; |
74 | use Exporter; |
… | |
… | |
187 | reference to the earlier value. |
180 | reference to the earlier value. |
188 | |
181 | |
189 | This means that such values will only be encoded once, and will not result |
182 | This means that such values will only be encoded once, and will not result |
190 | in a deep cloning of the value on decode, in decoders supporting the value |
183 | in a deep cloning of the value on decode, in decoders supporting the value |
191 | sharing extension. This also makes it possible to encode cyclic data |
184 | sharing extension. This also makes it possible to encode cyclic data |
192 | structures. |
185 | structures (which need C<allow_cycles> to ne enabled to be decoded by this |
|
|
186 | module). |
193 | |
187 | |
194 | It is recommended to leave it off unless you know your |
188 | It is recommended to leave it off unless you know your |
195 | communication partner supports the value sharing extensions to CBOR |
189 | communication partner supports the value sharing extensions to CBOR |
196 | (L<http://cbor.schmorp.de/value-sharing>), as without decoder support, the |
190 | (L<http://cbor.schmorp.de/value-sharing>), as without decoder support, the |
197 | resulting data structure might be unusable. |
191 | resulting data structure might be unusable. |
198 | |
192 | |
199 | Detecting shared values incurs a runtime overhead when values are encoded |
193 | Detecting shared values incurs a runtime overhead when values are encoded |
200 | that have a reference counter large than one, and might unnecessarily |
194 | that have a reference counter large than one, and might unnecessarily |
201 | increase the encoded size, as potentially shared values are encode as |
195 | increase the encoded size, as potentially shared values are encode as |
202 | sharable whether or not they are actually shared. |
196 | shareable whether or not they are actually shared. |
203 | |
197 | |
204 | At the moment, only targets of references can be shared (e.g. scalars, |
198 | At the moment, only targets of references can be shared (e.g. scalars, |
205 | arrays or hashes pointed to by a reference). Weirder constructs, such as |
199 | arrays or hashes pointed to by a reference). Weirder constructs, such as |
206 | an array with multiple "copies" of the I<same> string, which are hard but |
200 | an array with multiple "copies" of the I<same> string, which are hard but |
207 | not impossible to create in Perl, are not supported (this is the same as |
201 | not impossible to create in Perl, are not supported (this is the same as |
… | |
… | |
212 | structures cannot be encoded in this mode. |
206 | structures cannot be encoded in this mode. |
213 | |
207 | |
214 | This option does not affect C<decode> in any way - shared values and |
208 | This option does not affect C<decode> in any way - shared values and |
215 | references will always be decoded properly if present. |
209 | references will always be decoded properly if present. |
216 | |
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 | FUTURE DIRECTION: the motivation behind this option is to avoid I<real> |
|
|
224 | cycles - future versions of this module might chose to decode cyclic data |
|
|
225 | structures using weak references when this option is off, instead of |
|
|
226 | throwing an error. |
|
|
227 | |
|
|
228 | This option does not affect C<encode> in any way - shared values and |
|
|
229 | references will always be encoded properly if present. |
|
|
230 | |
217 | =item $cbor = $cbor->pack_strings ([$enable]) |
231 | =item $cbor = $cbor->pack_strings ([$enable]) |
218 | |
232 | |
219 | =item $enabled = $cbor->get_pack_strings |
233 | =item $enabled = $cbor->get_pack_strings |
220 | |
234 | |
221 | If C<$enable> is true (or missing), then C<encode> will try not to encode |
235 | If C<$enable> is true (or missing), then C<encode> will try not to encode |
… | |
… | |
233 | the standard CBOR way. |
247 | the standard CBOR way. |
234 | |
248 | |
235 | This option does not affect C<decode> in any way - string references will |
249 | This option does not affect C<decode> in any way - string references will |
236 | always be decoded properly if present. |
250 | always be decoded properly if present. |
237 | |
251 | |
|
|
252 | =item $cbor = $cbor->text_keys ([$enable]) |
|
|
253 | |
|
|
254 | =item $enabled = $cbor->get_text_keys |
|
|
255 | |
|
|
256 | If C<$enabled> is true (or missing), then C<encode> will encode all |
|
|
257 | perl hash keys as CBOR text strings/UTF-8 string, upgrading them as needed. |
|
|
258 | |
|
|
259 | If C<$enable> is false (the default), then C<encode> will encode hash keys |
|
|
260 | normally - upgraded perl strings (strings internally encoded as UTF-8) as |
|
|
261 | CBOR text strings, and downgraded perl strings as CBOR byte strings. |
|
|
262 | |
|
|
263 | This option does not affect C<decode> in any way. |
|
|
264 | |
|
|
265 | This option is useful for interoperability with CBOR decoders that don't |
|
|
266 | treat byte strings as a form of text. It is especially useful as Perl |
|
|
267 | gives very little control over hash keys. |
|
|
268 | |
|
|
269 | Enabling this option can be slow, as all downgraded hash keys that are |
|
|
270 | encoded need to be scanned and converted to UTF-8. |
|
|
271 | |
|
|
272 | =item $cbor = $cbor->text_strings ([$enable]) |
|
|
273 | |
|
|
274 | =item $enabled = $cbor->get_text_strings |
|
|
275 | |
|
|
276 | This option works similar to C<text_keys>, above, but works on all strings |
|
|
277 | (including hash keys), so C<text_keys> has no further effect after |
|
|
278 | enabling C<text_strings>. |
|
|
279 | |
|
|
280 | If C<$enabled> is true (or missing), then C<encode> will encode all perl |
|
|
281 | strings as CBOR text strings/UTF-8 strings, upgrading them as needed. |
|
|
282 | |
|
|
283 | If C<$enable> is false (the default), then C<encode> will encode strings |
|
|
284 | normally (but see C<text_keys>) - upgraded perl strings (strings |
|
|
285 | internally encoded as UTF-8) as CBOR text strings, and downgraded perl |
|
|
286 | strings as CBOR byte strings. |
|
|
287 | |
|
|
288 | This option does not affect C<decode> in any way. |
|
|
289 | |
|
|
290 | This option has similar advantages and disadvantages as C<text_keys>. In |
|
|
291 | addition, this option effectively removes the ability to encode byte |
|
|
292 | strings, which might break some C<FREEZE> and C<TO_CBOR> methods that rely |
|
|
293 | on this, such as bignum encoding, so this option is mainly useful for very |
|
|
294 | simple data. |
|
|
295 | |
|
|
296 | =item $cbor = $cbor->validate_utf8 ([$enable]) |
|
|
297 | |
|
|
298 | =item $enabled = $cbor->get_validate_utf8 |
|
|
299 | |
|
|
300 | If C<$enable> is true (or missing), then C<decode> will validate that |
|
|
301 | elements (text strings) containing UTF-8 data in fact contain valid UTF-8 |
|
|
302 | data (instead of blindly accepting it). This validation obviously takes |
|
|
303 | extra time during decoding. |
|
|
304 | |
|
|
305 | The concept of "valid UTF-8" used is perl's concept, which is a superset |
|
|
306 | of the official UTF-8. |
|
|
307 | |
|
|
308 | If C<$enable> is false (the default), then C<decode> will blindly accept |
|
|
309 | UTF-8 data, marking them as valid UTF-8 in the resulting data structure |
|
|
310 | regardless of whether that's true or not. |
|
|
311 | |
|
|
312 | Perl isn't too happy about corrupted UTF-8 in strings, but should |
|
|
313 | generally not crash or do similarly evil things. Extensions might be not |
|
|
314 | so forgiving, so it's recommended to turn on this setting if you receive |
|
|
315 | untrusted CBOR. |
|
|
316 | |
|
|
317 | This option does not affect C<encode> in any way - strings that are |
|
|
318 | supposedly valid UTF-8 will simply be dumped into the resulting CBOR |
|
|
319 | string without checking whether that is, in fact, true or not. |
|
|
320 | |
238 | =item $cbor = $cbor->filter ([$cb->($tag, $value)]) |
321 | =item $cbor = $cbor->filter ([$cb->($tag, $value)]) |
239 | |
322 | |
240 | =item $cb_or_undef = $cbor->get_filter |
323 | =item $cb_or_undef = $cbor->get_filter |
241 | |
324 | |
242 | Sets or replaces the tagged value decoding filter (when C<$cb> is |
325 | Sets or replaces the tagged value decoding filter (when C<$cb> is |
… | |
… | |
259 | function, C<CBOR::XS::default_filter>, is used. This function simply looks |
342 | function, C<CBOR::XS::default_filter>, is used. This function simply looks |
260 | up the tag in the C<%CBOR::XS::FILTER> hash. If an entry exists it must be |
343 | up the tag in the C<%CBOR::XS::FILTER> hash. If an entry exists it must be |
261 | a code reference that is called with tag and value, and is responsible for |
344 | a code reference that is called with tag and value, and is responsible for |
262 | decoding the value. If no entry exists, it returns no values. |
345 | decoding the value. If no entry exists, it returns no values. |
263 | |
346 | |
264 | Example: decode all tags not handled internally into CBOR::XS::Tagged |
347 | Example: decode all tags not handled internally into C<CBOR::XS::Tagged> |
265 | objects, with no other special handling (useful when working with |
348 | objects, with no other special handling (useful when working with |
266 | potentially "unsafe" CBOR data). |
349 | potentially "unsafe" CBOR data). |
267 | |
350 | |
268 | CBOR::XS->new->filter (sub { })->decode ($cbor_data); |
351 | CBOR::XS->new->filter (sub { })->decode ($cbor_data); |
269 | |
352 | |
… | |
… | |
296 | and you need to know where the first CBOR string ends amd the next one |
379 | and you need to know where the first CBOR string ends amd the next one |
297 | starts. |
380 | starts. |
298 | |
381 | |
299 | CBOR::XS->new->decode_prefix ("......") |
382 | CBOR::XS->new->decode_prefix ("......") |
300 | => ("...", 3) |
383 | => ("...", 3) |
|
|
384 | |
|
|
385 | =back |
|
|
386 | |
|
|
387 | =head2 INCREMENTAL PARSING |
|
|
388 | |
|
|
389 | In some cases, there is the need for incremental parsing of JSON |
|
|
390 | texts. While this module always has to keep both CBOR text and resulting |
|
|
391 | Perl data structure in memory at one time, it does allow you to parse a |
|
|
392 | CBOR stream incrementally, using a similar to using "decode_prefix" to see |
|
|
393 | if a full CBOR object is available, but is much more efficient. |
|
|
394 | |
|
|
395 | It basically works by parsing as much of a CBOR string as possible - if |
|
|
396 | the CBOR data is not complete yet, the pasrer will remember where it was, |
|
|
397 | to be able to restart when more data has been accumulated. Once enough |
|
|
398 | data is available to either decode a complete CBOR value or raise an |
|
|
399 | error, a real decode will be attempted. |
|
|
400 | |
|
|
401 | A typical use case would be a network protocol that consists of sending |
|
|
402 | and receiving CBOR-encoded messages. The solution that works with CBOR and |
|
|
403 | about anything else is by prepending a length to every CBOR value, so the |
|
|
404 | receiver knows how many octets to read. More compact (and slightly slower) |
|
|
405 | would be to just send CBOR values back-to-back, as C<CBOR::XS> knows where |
|
|
406 | a CBOR value ends, and doesn't need an explicit length. |
|
|
407 | |
|
|
408 | The following methods help with this: |
|
|
409 | |
|
|
410 | =over 4 |
|
|
411 | |
|
|
412 | =item @decoded = $cbor->incr_parse ($buffer) |
|
|
413 | |
|
|
414 | This method attempts to decode exactly one CBOR value from the beginning |
|
|
415 | of the given C<$buffer>. The value is removed from the C<$buffer> on |
|
|
416 | success. When C<$buffer> doesn't contain a complete value yet, it returns |
|
|
417 | nothing. Finally, when the C<$buffer> doesn't start with something |
|
|
418 | that could ever be a valid CBOR value, it raises an exception, just as |
|
|
419 | C<decode> would. In the latter case the decoder state is undefined and |
|
|
420 | must be reset before being able to parse further. |
|
|
421 | |
|
|
422 | This method modifies the C<$buffer> in place. When no CBOR value can be |
|
|
423 | decoded, the decoder stores the current string offset. On the next call, |
|
|
424 | continues decoding at the place where it stopped before. For this to make |
|
|
425 | sense, the C<$buffer> must begin with the same octets as on previous |
|
|
426 | unsuccessful calls. |
|
|
427 | |
|
|
428 | You can call this method in scalar context, in which case it either |
|
|
429 | returns a decoded value or C<undef>. This makes it impossible to |
|
|
430 | distinguish between CBOR null values (which decode to C<undef>) and an |
|
|
431 | unsuccessful decode, which is often acceptable. |
|
|
432 | |
|
|
433 | =item @decoded = $cbor->incr_parse_multiple ($buffer) |
|
|
434 | |
|
|
435 | Same as C<incr_parse>, but attempts to decode as many CBOR values as |
|
|
436 | possible in one go, instead of at most one. Calls to C<incr_parse> and |
|
|
437 | C<incr_parse_multiple> can be interleaved. |
|
|
438 | |
|
|
439 | =item $cbor->incr_reset |
|
|
440 | |
|
|
441 | Resets the incremental decoder. This throws away any saved state, so that |
|
|
442 | subsequent calls to C<incr_parse> or C<incr_parse_multiple> start to parse |
|
|
443 | a new CBOR value from the beginning of the C<$buffer> again. |
|
|
444 | |
|
|
445 | This method can be caled at any time, but it I<must> be called if you want |
|
|
446 | to change your C<$buffer> or there was a decoding error and you want to |
|
|
447 | reuse the C<$cbor> object for future incremental parsings. |
301 | |
448 | |
302 | =back |
449 | =back |
303 | |
450 | |
304 | |
451 | |
305 | =head1 MAPPING |
452 | =head1 MAPPING |
… | |
… | |
356 | =item tagged values |
503 | =item tagged values |
357 | |
504 | |
358 | Tagged items consists of a numeric tag and another CBOR value. |
505 | Tagged items consists of a numeric tag and another CBOR value. |
359 | |
506 | |
360 | See L<TAG HANDLING AND EXTENSIONS> and the description of C<< ->filter >> |
507 | See L<TAG HANDLING AND EXTENSIONS> and the description of C<< ->filter >> |
361 | for details. |
508 | for details on which tags are handled how. |
362 | |
509 | |
363 | =item anything else |
510 | =item anything else |
364 | |
511 | |
365 | Anything else (e.g. unsupported simple values) will raise a decoding |
512 | Anything else (e.g. unsupported simple values) will raise a decoding |
366 | error. |
513 | error. |
… | |
… | |
369 | |
516 | |
370 | |
517 | |
371 | =head2 PERL -> CBOR |
518 | =head2 PERL -> CBOR |
372 | |
519 | |
373 | The mapping from Perl to CBOR is slightly more difficult, as Perl is a |
520 | The mapping from Perl to CBOR is slightly more difficult, as Perl is a |
374 | truly typeless language, so we can only guess which CBOR type is meant by |
521 | typeless language. That means this module can only guess which CBOR type |
375 | a Perl value. |
522 | is meant by a perl value. |
376 | |
523 | |
377 | =over 4 |
524 | =over 4 |
378 | |
525 | |
379 | =item hash references |
526 | =item hash references |
380 | |
527 | |
381 | Perl hash references become CBOR maps. As there is no inherent ordering in |
528 | Perl hash references become CBOR maps. As there is no inherent ordering in |
382 | hash keys (or CBOR maps), they will usually be encoded in a pseudo-random |
529 | hash keys (or CBOR maps), they will usually be encoded in a pseudo-random |
383 | order. |
530 | order. This order can be different each time a hash is encoded. |
384 | |
531 | |
385 | Currently, tied hashes will use the indefinite-length format, while normal |
532 | Currently, tied hashes will use the indefinite-length format, while normal |
386 | hashes will use the fixed-length format. |
533 | hashes will use the fixed-length format. |
387 | |
534 | |
388 | =item array references |
535 | =item array references |
389 | |
536 | |
390 | Perl array references become fixed-length CBOR arrays. |
537 | Perl array references become fixed-length CBOR arrays. |
391 | |
538 | |
392 | =item other references |
539 | =item other references |
393 | |
540 | |
394 | Other unblessed references are generally not allowed and will cause an |
541 | Other unblessed references will be represented using |
395 | exception to be thrown, except for references to the integers C<0> and |
542 | the indirection tag extension (tag value C<22098>, |
396 | C<1>, which get turned into false and true in CBOR. |
543 | L<http://cbor.schmorp.de/indirection>). CBOR decoders are guaranteed |
|
|
544 | to be able to decode these values somehow, by either "doing the right |
|
|
545 | thing", decoding into a generic tagged object, simply ignoring the tag, or |
|
|
546 | something else. |
397 | |
547 | |
398 | =item CBOR::XS::Tagged objects |
548 | =item CBOR::XS::Tagged objects |
399 | |
549 | |
400 | Objects of this type must be arrays consisting of a single C<[tag, value]> |
550 | Objects of this type must be arrays consisting of a single C<[tag, value]> |
401 | pair. The (numerical) tag will be encoded as a CBOR tag, the value will |
551 | pair. The (numerical) tag will be encoded as a CBOR tag, the value will |
402 | be encoded as appropriate for the value. You cna use C<CBOR::XS::tag> to |
552 | be encoded as appropriate for the value. You must use C<CBOR::XS::tag> to |
403 | create such objects. |
553 | create such objects. |
404 | |
554 | |
405 | =item Types::Serialiser::true, Types::Serialiser::false, Types::Serialiser::error |
555 | =item Types::Serialiser::true, Types::Serialiser::false, Types::Serialiser::error |
406 | |
556 | |
407 | These special values become CBOR true, CBOR false and CBOR undefined |
557 | These special values become CBOR true, CBOR false and CBOR undefined |
… | |
… | |
438 | my $x = 3.1; # some variable containing a number |
588 | my $x = 3.1; # some variable containing a number |
439 | "$x"; # stringified |
589 | "$x"; # stringified |
440 | $x .= ""; # another, more awkward way to stringify |
590 | $x .= ""; # another, more awkward way to stringify |
441 | print $x; # perl does it for you, too, quite often |
591 | print $x; # perl does it for you, too, quite often |
442 | |
592 | |
443 | You can force whether a string ie encoded as byte or text string by using |
593 | You can force whether a string is encoded as byte or text string by using |
444 | C<utf8::upgrade> and C<utf8::downgrade>): |
594 | C<utf8::upgrade> and C<utf8::downgrade> (if C<text_strings> is disabled): |
445 | |
595 | |
446 | utf8::upgrade $x; # encode $x as text string |
596 | utf8::upgrade $x; # encode $x as text string |
447 | utf8::downgrade $x; # encode $x as byte string |
597 | utf8::downgrade $x; # encode $x as byte string |
448 | |
598 | |
449 | Perl doesn't define what operations up- and downgrade strings, so if the |
599 | Perl doesn't define what operations up- and downgrade strings, so if the |
450 | difference between byte and text is important, you should up- or downgrade |
600 | difference between byte and text is important, you should up- or downgrade |
451 | your string as late as possible before encoding. |
601 | your string as late as possible before encoding. You can also force the |
|
|
602 | use of CBOR text strings by using C<text_keys> or C<text_strings>. |
452 | |
603 | |
453 | You can force the type to be a CBOR number by numifying it: |
604 | You can force the type to be a CBOR number by numifying it: |
454 | |
605 | |
455 | my $x = "3"; # some variable containing a string |
606 | my $x = "3"; # some variable containing a string |
456 | $x += 0; # numify it, ensuring it will be dumped as a number |
607 | $x += 0; # numify it, ensuring it will be dumped as a number |
… | |
… | |
469 | |
620 | |
470 | =back |
621 | =back |
471 | |
622 | |
472 | =head2 OBJECT SERIALISATION |
623 | =head2 OBJECT SERIALISATION |
473 | |
624 | |
|
|
625 | This module implements both a CBOR-specific and the generic |
|
|
626 | L<Types::Serialier> object serialisation protocol. The following |
|
|
627 | subsections explain both methods. |
|
|
628 | |
|
|
629 | =head3 ENCODING |
|
|
630 | |
474 | This module knows two way to serialise a Perl object: The CBOR-specific |
631 | This module knows two way to serialise a Perl object: The CBOR-specific |
475 | way, and the generic way. |
632 | way, and the generic way. |
476 | |
633 | |
477 | Whenever the encoder encounters a Perl object that it cnanot serialise |
634 | Whenever the encoder encounters a Perl object that it cannot serialise |
478 | directly (most of them), it will first look up the C<TO_CBOR> method on |
635 | directly (most of them), it will first look up the C<TO_CBOR> method on |
479 | it. |
636 | it. |
480 | |
637 | |
481 | If it has a C<TO_CBOR> method, it will call it with the object as only |
638 | If it has a C<TO_CBOR> method, it will call it with the object as only |
482 | argument, and expects exactly one return value, which it will then |
639 | argument, and expects exactly one return value, which it will then |
… | |
… | |
488 | |
645 | |
489 | The C<FREEZE> method can return any number of values (i.e. zero or |
646 | The C<FREEZE> method can return any number of values (i.e. zero or |
490 | more). These will be encoded as CBOR perl object, together with the |
647 | more). These will be encoded as CBOR perl object, together with the |
491 | classname. |
648 | classname. |
492 | |
649 | |
|
|
650 | These methods I<MUST NOT> change the data structure that is being |
|
|
651 | serialised. Failure to comply to this can result in memory corruption - |
|
|
652 | and worse. |
|
|
653 | |
493 | If an object supports neither C<TO_CBOR> nor C<FREEZE>, encoding will fail |
654 | If an object supports neither C<TO_CBOR> nor C<FREEZE>, encoding will fail |
494 | with an error. |
655 | with an error. |
495 | |
656 | |
|
|
657 | =head3 DECODING |
|
|
658 | |
496 | Objects encoded via C<TO_CBOR> cannot be automatically decoded, but |
659 | Objects encoded via C<TO_CBOR> cannot (normally) be automatically decoded, |
497 | objects encoded via C<FREEZE> can be decoded using the following protocol: |
660 | but objects encoded via C<FREEZE> can be decoded using the following |
|
|
661 | protocol: |
498 | |
662 | |
499 | When an encoded CBOR perl object is encountered by the decoder, it will |
663 | When an encoded CBOR perl object is encountered by the decoder, it will |
500 | look up the C<THAW> method, by using the stored classname, and will fail |
664 | look up the C<THAW> method, by using the stored classname, and will fail |
501 | if the method cannot be found. |
665 | if the method cannot be found. |
502 | |
666 | |
503 | After the lookup it will call the C<THAW> method with the stored classname |
667 | After the lookup it will call the C<THAW> method with the stored classname |
504 | as first argument, the constant string C<CBOR> as second argument, and all |
668 | as first argument, the constant string C<CBOR> as second argument, and all |
505 | values returned by C<FREEZE> as remaining arguments. |
669 | values returned by C<FREEZE> as remaining arguments. |
506 | |
670 | |
507 | =head4 EXAMPLES |
671 | =head3 EXAMPLES |
508 | |
672 | |
509 | Here is an example C<TO_CBOR> method: |
673 | Here is an example C<TO_CBOR> method: |
510 | |
674 | |
511 | sub My::Object::TO_CBOR { |
675 | sub My::Object::TO_CBOR { |
512 | my ($obj) = @_; |
676 | my ($obj) = @_; |
… | |
… | |
523 | |
687 | |
524 | sub URI::TO_CBOR { |
688 | sub URI::TO_CBOR { |
525 | my ($self) = @_; |
689 | my ($self) = @_; |
526 | my $uri = "$self"; # stringify uri |
690 | my $uri = "$self"; # stringify uri |
527 | utf8::upgrade $uri; # make sure it will be encoded as UTF-8 string |
691 | utf8::upgrade $uri; # make sure it will be encoded as UTF-8 string |
528 | CBOR::XS::tagged 32, "$_[0]" |
692 | CBOR::XS::tag 32, "$_[0]" |
529 | } |
693 | } |
530 | |
694 | |
531 | This will encode URIs as a UTF-8 string with tag 32, which indicates an |
695 | This will encode URIs as a UTF-8 string with tag 32, which indicates an |
532 | URI. |
696 | URI. |
533 | |
697 | |
… | |
… | |
544 | "$self" # encode url string |
708 | "$self" # encode url string |
545 | } |
709 | } |
546 | |
710 | |
547 | sub URI::THAW { |
711 | sub URI::THAW { |
548 | my ($class, $serialiser, $uri) = @_; |
712 | my ($class, $serialiser, $uri) = @_; |
549 | |
|
|
550 | $class->new ($uri) |
713 | $class->new ($uri) |
551 | } |
714 | } |
552 | |
715 | |
553 | Unlike C<TO_CBOR>, multiple values can be returned by C<FREEZE>. For |
716 | Unlike C<TO_CBOR>, multiple values can be returned by C<FREEZE>. For |
554 | example, a C<FREEZE> method that returns "type", "id" and "variant" values |
717 | example, a C<FREEZE> method that returns "type", "id" and "variant" values |
… | |
… | |
685 | additional tags (such as base64url). |
848 | additional tags (such as base64url). |
686 | |
849 | |
687 | =head2 ENFORCED TAGS |
850 | =head2 ENFORCED TAGS |
688 | |
851 | |
689 | These tags are always handled when decoding, and their handling cannot be |
852 | These tags are always handled when decoding, and their handling cannot be |
690 | overriden by the user. |
853 | overridden by the user. |
691 | |
854 | |
692 | =over 4 |
855 | =over 4 |
693 | |
856 | |
694 | =item 26 (perl-object, L<http://cbor.schmorp.de/perl-object>) |
857 | =item 26 (perl-object, L<http://cbor.schmorp.de/perl-object>) |
695 | |
858 | |
696 | These tags are automatically created (and decoded) for serialisable |
859 | These tags are automatically created (and decoded) for serialisable |
697 | objects using the C<FREEZE/THAW> methods (the L<Types::Serialier> object |
860 | objects using the C<FREEZE/THAW> methods (the L<Types::Serialier> object |
698 | serialisation protocol). See L<OBJECT SERIALISATION> for details. |
861 | serialisation protocol). See L<OBJECT SERIALISATION> for details. |
699 | |
862 | |
700 | =item 28, 29 (sharable, sharedref, L <http://cbor.schmorp.de/value-sharing>) |
863 | =item 28, 29 (shareable, sharedref, L<http://cbor.schmorp.de/value-sharing>) |
701 | |
864 | |
702 | These tags are automatically decoded when encountered, resulting in |
865 | These tags are automatically decoded when encountered (and they do not |
|
|
866 | result in a cyclic data structure, see C<allow_cycles>), resulting in |
703 | shared values in the decoded object. They are only encoded, however, when |
867 | shared values in the decoded object. They are only encoded, however, when |
704 | C<allow_sharable> is enabled. |
868 | C<allow_sharing> is enabled. |
705 | |
869 | |
|
|
870 | Not all shared values can be successfully decoded: values that reference |
|
|
871 | themselves will I<currently> decode as C<undef> (this is not the same |
|
|
872 | as a reference pointing to itself, which will be represented as a value |
|
|
873 | that contains an indirect reference to itself - these will be decoded |
|
|
874 | properly). |
|
|
875 | |
|
|
876 | Note that considerably more shared value data structures can be decoded |
|
|
877 | than will be encoded - currently, only values pointed to by references |
|
|
878 | will be shared, others will not. While non-reference shared values can be |
|
|
879 | generated in Perl with some effort, they were considered too unimportant |
|
|
880 | to be supported in the encoder. The decoder, however, will decode these |
|
|
881 | values as shared values. |
|
|
882 | |
706 | =item 256, 25 (stringref-namespace, stringref, L <http://cbor.schmorp.de/stringref>) |
883 | =item 256, 25 (stringref-namespace, stringref, L<http://cbor.schmorp.de/stringref>) |
707 | |
884 | |
708 | These tags are automatically decoded when encountered. They are only |
885 | These tags are automatically decoded when encountered. They are only |
709 | encoded, however, when C<pack_strings> is enabled. |
886 | encoded, however, when C<pack_strings> is enabled. |
710 | |
887 | |
711 | =item 22098 (indirection, L<http://cbor.schmorp.de/indirection>) |
888 | =item 22098 (indirection, L<http://cbor.schmorp.de/indirection>) |
712 | |
889 | |
713 | This tag is automatically generated when a reference are encountered (with |
890 | This tag is automatically generated when a reference are encountered (with |
714 | the exception of hash and array refernces). It is converted to a reference |
891 | the exception of hash and array references). It is converted to a reference |
715 | when decoding. |
892 | when decoding. |
716 | |
893 | |
717 | =item 55799 (self-describe CBOR, RFC 7049) |
894 | =item 55799 (self-describe CBOR, RFC 7049) |
718 | |
895 | |
719 | This value is not generated on encoding (unless explicitly requested by |
896 | This value is not generated on encoding (unless explicitly requested by |
… | |
… | |
722 | =back |
899 | =back |
723 | |
900 | |
724 | =head2 NON-ENFORCED TAGS |
901 | =head2 NON-ENFORCED TAGS |
725 | |
902 | |
726 | These tags have default filters provided when decoding. Their handling can |
903 | These tags have default filters provided when decoding. Their handling can |
727 | be overriden by changing the C<%CBOR::XS::FILTER> entry for the tag, or by |
904 | be overridden by changing the C<%CBOR::XS::FILTER> entry for the tag, or by |
728 | providing a custom C<filter> callback when decoding. |
905 | providing a custom C<filter> callback when decoding. |
729 | |
906 | |
730 | When they result in decoding into a specific Perl class, the module |
907 | When they result in decoding into a specific Perl class, the module |
731 | usually provides a corresponding C<TO_CBOR> method as well. |
908 | usually provides a corresponding C<TO_CBOR> method as well. |
732 | |
909 | |
… | |
… | |
735 | provide these modules. The decoding usually fails with an exception if the |
912 | provide these modules. The decoding usually fails with an exception if the |
736 | required module cannot be loaded. |
913 | required module cannot be loaded. |
737 | |
914 | |
738 | =over 4 |
915 | =over 4 |
739 | |
916 | |
|
|
917 | =item 0, 1 (date/time string, seconds since the epoch) |
|
|
918 | |
|
|
919 | These tags are decoded into L<Time::Piece> objects. The corresponding |
|
|
920 | C<Time::Piece::TO_CBOR> method always encodes into tag 1 values currently. |
|
|
921 | |
|
|
922 | The L<Time::Piece> API is generally surprisingly bad, and fractional |
|
|
923 | seconds are only accidentally kept intact, so watch out. On the plus side, |
|
|
924 | the module comes with perl since 5.10, which has to count for something. |
|
|
925 | |
740 | =item 2, 3 (positive/negative bignum) |
926 | =item 2, 3 (positive/negative bignum) |
741 | |
927 | |
742 | These tags are decoded into L<Math::BigInt> objects. The corresponding |
928 | These tags are decoded into L<Math::BigInt> objects. The corresponding |
743 | C<Math::BigInt::TO_CBOR> method encodes "small" bigints into normal CBOR |
929 | C<Math::BigInt::TO_CBOR> method encodes "small" bigints into normal CBOR |
744 | integers, and others into positive/negative CBOR bignums. |
930 | integers, and others into positive/negative CBOR bignums. |
745 | |
931 | |
746 | =item 4, 5 (decimal fraction/bigfloat) |
932 | =item 4, 5, 264, 265 (decimal fraction/bigfloat) |
747 | |
933 | |
748 | Both decimal fractions and bigfloats are decoded into L<Math::BigFloat> |
934 | Both decimal fractions and bigfloats are decoded into L<Math::BigFloat> |
749 | objects. The corresponding C<Math::BigFloat::TO_CBOR> method I<always> |
935 | objects. The corresponding C<Math::BigFloat::TO_CBOR> method I<always> |
750 | encodes into a decimal fraction. |
936 | encodes into a decimal fraction (either tag 4 or 264). |
751 | |
937 | |
752 | CBOR cannot represent bigfloats with I<very> large exponents - conversion |
938 | NaN and infinities are not encoded properly, as they cannot be represented |
753 | of such big float objects is undefined. |
939 | in CBOR. |
754 | |
940 | |
755 | Also, NaN and infinities are not encoded properly. |
941 | See L<BIGNUM SECURITY CONSIDERATIONS> for more info. |
756 | |
942 | |
757 | =item 21, 22, 23 (expected later JSON conversion) |
943 | =item 21, 22, 23 (expected later JSON conversion) |
758 | |
944 | |
759 | CBOR::XS is not a CBOR-to-JSON converter, and will simply ignore these |
945 | CBOR::XS is not a CBOR-to-JSON converter, and will simply ignore these |
760 | tags. |
946 | tags. |
… | |
… | |
765 | C<URI::TO_CBOR> method again results in a CBOR URI value. |
951 | C<URI::TO_CBOR> method again results in a CBOR URI value. |
766 | |
952 | |
767 | =back |
953 | =back |
768 | |
954 | |
769 | =cut |
955 | =cut |
770 | |
|
|
771 | our %FILTER = ( |
|
|
772 | # 0 # rfc4287 datetime, utf-8 |
|
|
773 | # 1 # unix timestamp, any |
|
|
774 | |
|
|
775 | 2 => sub { # pos bigint |
|
|
776 | require Math::BigInt; |
|
|
777 | Math::BigInt->new ("0x" . unpack "H*", pop) |
|
|
778 | }, |
|
|
779 | |
|
|
780 | 3 => sub { # neg bigint |
|
|
781 | require Math::BigInt; |
|
|
782 | -Math::BigInt->new ("0x" . unpack "H*", pop) |
|
|
783 | }, |
|
|
784 | |
|
|
785 | 4 => sub { # decimal fraction, array |
|
|
786 | require Math::BigFloat; |
|
|
787 | Math::BigFloat->new ($_[1][1] . "E" . $_[1][0]) |
|
|
788 | }, |
|
|
789 | |
|
|
790 | 5 => sub { # bigfloat, array |
|
|
791 | require Math::BigFloat; |
|
|
792 | scalar Math::BigFloat->new ($_[1][1])->blsft ($_[1][0], 2) |
|
|
793 | }, |
|
|
794 | |
|
|
795 | 21 => sub { pop }, # expected conversion to base64url encoding |
|
|
796 | 22 => sub { pop }, # expected conversion to base64 encoding |
|
|
797 | 23 => sub { pop }, # expected conversion to base16 encoding |
|
|
798 | |
|
|
799 | # 24 # embedded cbor, byte string |
|
|
800 | |
|
|
801 | 32 => sub { |
|
|
802 | require URI; |
|
|
803 | URI->new (pop) |
|
|
804 | }, |
|
|
805 | |
|
|
806 | # 33 # base64url rfc4648, utf-8 |
|
|
807 | # 34 # base64 rfc46484, utf-8 |
|
|
808 | # 35 # regex pcre/ecma262, utf-8 |
|
|
809 | # 36 # mime message rfc2045, utf-8 |
|
|
810 | ); |
|
|
811 | |
|
|
812 | |
956 | |
813 | =head1 CBOR and JSON |
957 | =head1 CBOR and JSON |
814 | |
958 | |
815 | CBOR is supposed to implement a superset of the JSON data model, and is, |
959 | CBOR is supposed to implement a superset of the JSON data model, and is, |
816 | with some coercion, able to represent all JSON texts (something that other |
960 | with some coercion, able to represent all JSON texts (something that other |
… | |
… | |
858 | Also keep in mind that CBOR::XS might leak contents of your Perl data |
1002 | Also keep in mind that CBOR::XS might leak contents of your Perl data |
859 | structures in its error messages, so when you serialise sensitive |
1003 | structures in its error messages, so when you serialise sensitive |
860 | information you might want to make sure that exceptions thrown by CBOR::XS |
1004 | information you might want to make sure that exceptions thrown by CBOR::XS |
861 | will not end up in front of untrusted eyes. |
1005 | will not end up in front of untrusted eyes. |
862 | |
1006 | |
|
|
1007 | |
|
|
1008 | =head1 BIGNUM SECURITY CONSIDERATIONS |
|
|
1009 | |
|
|
1010 | CBOR::XS provides a C<TO_CBOR> method for both L<Math::BigInt> and |
|
|
1011 | L<Math::BigFloat> that tries to encode the number in the simplest possible |
|
|
1012 | way, that is, either a CBOR integer, a CBOR bigint/decimal fraction (tag |
|
|
1013 | 4) or an arbitrary-exponent decimal fraction (tag 264). |
|
|
1014 | |
|
|
1015 | It will also understand base-2 bigfloat or arbitrary-exponent bigfloats |
|
|
1016 | (tags 5 and 265), but it will never generate these on its own. |
|
|
1017 | |
|
|
1018 | Using the built-in L<Math::BigInt::Calc> support, encoding and decoding |
|
|
1019 | decimal fractions is generally fast. Decoding bigints can be slow for very |
|
|
1020 | big numbers, and decoding bigfloats or arbitrary-exponent bigfloats can be |
|
|
1021 | extremely slow (minutes, decades) for large exponents. |
|
|
1022 | |
|
|
1023 | Additionally, L<Math::BigInt> can take advantage of other bignum |
|
|
1024 | libraries, such as L<Math::GMP>, which cannot handle big |
|
|
1025 | floats with large exponents, and might simply abort or crash your program, |
|
|
1026 | due to their code quality. |
|
|
1027 | |
|
|
1028 | This can be a concern if you want to parse untrusted CBOR. If it is, you |
|
|
1029 | need to disable decoding of tag 2 (bigint) and 3 (negative bigint) types, |
|
|
1030 | which will also disable bigfloat support (to be sure, you can also disable |
|
|
1031 | types 4, 5, 264 and 265). |
|
|
1032 | |
|
|
1033 | |
863 | =head1 CBOR IMPLEMENTATION NOTES |
1034 | =head1 CBOR IMPLEMENTATION NOTES |
864 | |
1035 | |
865 | This section contains some random implementation notes. They do not |
1036 | This section contains some random implementation notes. They do not |
866 | describe guaranteed behaviour, but merely behaviour as-is implemented |
1037 | describe guaranteed behaviour, but merely behaviour as-is implemented |
867 | right now. |
1038 | right now. |
… | |
… | |
875 | Only the double data type is supported for NV data types - when Perl uses |
1046 | Only the double data type is supported for NV data types - when Perl uses |
876 | long double to represent floating point values, they might not be encoded |
1047 | long double to represent floating point values, they might not be encoded |
877 | properly. Half precision types are accepted, but not encoded. |
1048 | properly. Half precision types are accepted, but not encoded. |
878 | |
1049 | |
879 | Strict mode and canonical mode are not implemented. |
1050 | Strict mode and canonical mode are not implemented. |
|
|
1051 | |
|
|
1052 | |
|
|
1053 | =head1 LIMITATIONS ON PERLS WITHOUT 64-BIT INTEGER SUPPORT |
|
|
1054 | |
|
|
1055 | On perls that were built without 64 bit integer support (these are rare |
|
|
1056 | nowadays, even on 32 bit architectures, as all major Perl distributions |
|
|
1057 | are built with 64 bit integer support), support for any kind of 64 bit |
|
|
1058 | integer in CBOR is very limited - most likely, these 64 bit values will |
|
|
1059 | be truncated, corrupted, or otherwise not decoded correctly. This also |
|
|
1060 | includes string, array and map sizes that are stored as 64 bit integers. |
880 | |
1061 | |
881 | |
1062 | |
882 | =head1 THREADS |
1063 | =head1 THREADS |
883 | |
1064 | |
884 | This module is I<not> guaranteed to be thread safe and there are no |
1065 | This module is I<not> guaranteed to be thread safe and there are no |
… | |
… | |
899 | service. I put the contact address into my modules for a reason. |
1080 | service. I put the contact address into my modules for a reason. |
900 | |
1081 | |
901 | =cut |
1082 | =cut |
902 | |
1083 | |
903 | our %FILTER = ( |
1084 | our %FILTER = ( |
904 | # 0 # rfc4287 datetime, utf-8 |
1085 | 0 => sub { # rfc4287 datetime, utf-8 |
905 | # 1 # unix timestamp, any |
1086 | require Time::Piece; |
|
|
1087 | # Time::Piece::Strptime uses the "incredibly flexible date parsing routine" |
|
|
1088 | # from FreeBSD, which can't parse ISO 8601, RFC3339, RFC4287 or much of anything |
|
|
1089 | # else either. Whats incredibe over standard strptime totally escapes me. |
|
|
1090 | # doesn't do fractional times, either. sigh. |
|
|
1091 | # In fact, it's all a lie, it uses whatever strptime it wants, and of course, |
|
|
1092 | # they are all incompatible. The openbsd one simply ignores %z (but according to the |
|
|
1093 | # docs, it would be much more incredibly flexible indeed. If it worked, that is.). |
|
|
1094 | scalar eval { |
|
|
1095 | my $s = $_[1]; |
|
|
1096 | |
|
|
1097 | $s =~ s/Z$/+00:00/; |
|
|
1098 | $s =~ s/(\.[0-9]+)?([+-][0-9][0-9]):([0-9][0-9])$// |
|
|
1099 | or die; |
|
|
1100 | |
|
|
1101 | my $b = $1 - ($2 * 60 + $3) * 60; # fractional part + offset. hopefully |
|
|
1102 | my $d = Time::Piece->strptime ($s, "%Y-%m-%dT%H:%M:%S"); |
|
|
1103 | |
|
|
1104 | Time::Piece::gmtime ($d->epoch + $b) |
|
|
1105 | } || die "corrupted CBOR date/time string ($_[0])"; |
|
|
1106 | }, |
|
|
1107 | |
|
|
1108 | 1 => sub { # seconds since the epoch, possibly fractional |
|
|
1109 | require Time::Piece; |
|
|
1110 | scalar Time::Piece::gmtime (pop) |
|
|
1111 | }, |
906 | |
1112 | |
907 | 2 => sub { # pos bigint |
1113 | 2 => sub { # pos bigint |
908 | require Math::BigInt; |
1114 | require Math::BigInt; |
909 | Math::BigInt->new ("0x" . unpack "H*", pop) |
1115 | Math::BigInt->from_hex ("0x" . unpack "H*", pop) |
910 | }, |
1116 | }, |
911 | |
1117 | |
912 | 3 => sub { # neg bigint |
1118 | 3 => sub { # neg bigint |
913 | require Math::BigInt; |
1119 | require Math::BigInt; |
914 | -Math::BigInt->new ("0x" . unpack "H*", pop) |
1120 | -Math::BigInt->from_hex ("0x" . unpack "H*", pop) |
915 | }, |
1121 | }, |
916 | |
1122 | |
917 | 4 => sub { # decimal fraction, array |
1123 | 4 => sub { # decimal fraction, array |
918 | require Math::BigFloat; |
1124 | require Math::BigFloat; |
919 | Math::BigFloat->new ($_[1][1] . "E" . $_[1][0]) |
1125 | Math::BigFloat->new ($_[1][1] . "E" . $_[1][0]) |
920 | }, |
1126 | }, |
921 | |
1127 | |
922 | 5 => sub { # bigfloat, array |
1128 | 5 => sub { # bigfloat, array |
923 | require Math::BigFloat; |
1129 | require Math::BigFloat; |
924 | scalar Math::BigFloat->new ($_[1][1])->blsft ($_[1][0], 2) |
1130 | scalar Math::BigFloat->new ($_[1][1]) * Math::BigFloat->new (2)->bpow ($_[1][0]) |
925 | }, |
1131 | }, |
926 | |
1132 | |
927 | 21 => sub { pop }, # expected conversion to base64url encoding |
1133 | 21 => sub { pop }, # expected conversion to base64url encoding |
928 | 22 => sub { pop }, # expected conversion to base64 encoding |
1134 | 22 => sub { pop }, # expected conversion to base64 encoding |
929 | 23 => sub { pop }, # expected conversion to base16 encoding |
1135 | 23 => sub { pop }, # expected conversion to base16 encoding |
… | |
… | |
937 | |
1143 | |
938 | # 33 # base64url rfc4648, utf-8 |
1144 | # 33 # base64url rfc4648, utf-8 |
939 | # 34 # base64 rfc46484, utf-8 |
1145 | # 34 # base64 rfc46484, utf-8 |
940 | # 35 # regex pcre/ecma262, utf-8 |
1146 | # 35 # regex pcre/ecma262, utf-8 |
941 | # 36 # mime message rfc2045, utf-8 |
1147 | # 36 # mime message rfc2045, utf-8 |
|
|
1148 | |
|
|
1149 | 264 => sub { # decimal fraction with arbitrary exponent |
|
|
1150 | require Math::BigFloat; |
|
|
1151 | Math::BigFloat->new ($_[1][1] . "E" . $_[1][0]) |
|
|
1152 | }, |
|
|
1153 | |
|
|
1154 | 265 => sub { # bigfloat with arbitrary exponent |
|
|
1155 | require Math::BigFloat; |
|
|
1156 | scalar Math::BigFloat->new ($_[1][1]) * Math::BigFloat->new (2)->bpow ($_[1][0]) |
|
|
1157 | }, |
942 | ); |
1158 | ); |
943 | |
1159 | |
944 | sub CBOR::XS::default_filter { |
1160 | sub CBOR::XS::default_filter { |
945 | &{ $FILTER{$_[0]} or return } |
1161 | &{ $FILTER{$_[0]} or return } |
946 | } |
1162 | } |
947 | |
1163 | |
948 | sub URI::TO_CBOR { |
1164 | sub URI::TO_CBOR { |
949 | my $uri = $_[0]->as_string; |
1165 | my $uri = $_[0]->as_string; |
950 | utf8::upgrade $uri; |
1166 | utf8::upgrade $uri; |
951 | CBOR::XS::tag 32, $uri |
1167 | tag 32, $uri |
952 | } |
1168 | } |
953 | |
1169 | |
954 | sub Math::BigInt::TO_CBOR { |
1170 | sub Math::BigInt::TO_CBOR { |
955 | if ($_[0] >= -2147483648 && $_[0] <= 2147483647) { |
1171 | if (-2147483648 <= $_[0] && $_[0] <= 2147483647) { |
956 | $_[0]->numify |
1172 | $_[0]->numify |
957 | } else { |
1173 | } else { |
958 | my $hex = substr $_[0]->as_hex, 2; |
1174 | my $hex = substr $_[0]->as_hex, 2; |
959 | $hex = "0$hex" if 1 & length $hex; # sigh |
1175 | $hex = "0$hex" if 1 & length $hex; # sigh |
960 | CBOR::XS::tag $_[0] >= 0 ? 2 : 3, pack "H*", $hex |
1176 | tag $_[0] >= 0 ? 2 : 3, pack "H*", $hex |
961 | } |
1177 | } |
962 | } |
1178 | } |
963 | |
1179 | |
964 | sub Math::BigFloat::TO_CBOR { |
1180 | sub Math::BigFloat::TO_CBOR { |
965 | my ($m, $e) = $_[0]->parts; |
1181 | my ($m, $e) = $_[0]->parts; |
|
|
1182 | |
|
|
1183 | -9223372036854775808 <= $e && $e <= 18446744073709551615 |
966 | CBOR::XS::tag 4, [$e->numify, $m] |
1184 | ? tag 4, [$e->numify, $m] |
|
|
1185 | : tag 264, [$e, $m] |
|
|
1186 | } |
|
|
1187 | |
|
|
1188 | sub Time::Piece::TO_CBOR { |
|
|
1189 | tag 1, 0 + $_[0]->epoch |
967 | } |
1190 | } |
968 | |
1191 | |
969 | XSLoader::load "CBOR::XS", $VERSION; |
1192 | XSLoader::load "CBOR::XS", $VERSION; |
970 | |
1193 | |
971 | =head1 SEE ALSO |
1194 | =head1 SEE ALSO |