… | |
… | |
38 | with the added ability of supporting serialisation of Perl objects. (JSON |
38 | with the added ability of supporting serialisation of Perl objects. (JSON |
39 | 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 |
40 | data later and speed is less important you might want to compare both |
40 | data later and speed is less important you might want to compare both |
41 | formats first). |
41 | formats first). |
42 | |
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. |
|
|
45 | |
43 | 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, |
44 | 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 |
45 | 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 |
46 | data, the worse L<Storable> performs in comparison. |
49 | data, the worse L<Storable> performs in comparison. |
47 | |
50 | |
… | |
… | |
52 | In addition to the core CBOR data format, this module implements a |
55 | In addition to the core CBOR data format, this module implements a |
53 | number of extensions, to support cyclic and shared data structures |
56 | number of extensions, to support cyclic and shared data structures |
54 | (see C<allow_sharing> and C<allow_cycles>), string deduplication (see |
57 | (see C<allow_sharing> and C<allow_cycles>), string deduplication (see |
55 | C<pack_strings>) and scalar references (always enabled). |
58 | C<pack_strings>) and scalar references (always enabled). |
56 | |
59 | |
57 | The primary goal of this module is to be I<correct> and the secondary goal |
|
|
58 | is to be I<fast>. To reach the latter goal it was written in C. |
|
|
59 | |
|
|
60 | 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 |
61 | vice versa. |
61 | vice versa. |
62 | |
62 | |
63 | =cut |
63 | =cut |
64 | |
64 | |
65 | package CBOR::XS; |
65 | package CBOR::XS; |
66 | |
66 | |
67 | use common::sense; |
67 | use common::sense; |
68 | |
68 | |
69 | our $VERSION = 1.41; |
69 | our $VERSION = 1.83; |
70 | our @ISA = qw(Exporter); |
70 | our @ISA = qw(Exporter); |
71 | |
71 | |
72 | our @EXPORT = qw(encode_cbor decode_cbor); |
72 | our @EXPORT = qw(encode_cbor decode_cbor); |
73 | |
73 | |
74 | use Exporter; |
74 | use Exporter; |
… | |
… | |
112 | |
112 | |
113 | 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 |
114 | be chained: |
114 | be chained: |
115 | |
115 | |
116 | 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 | } |
117 | |
142 | |
118 | =item $cbor = $cbor->max_depth ([$maximum_nesting_depth]) |
143 | =item $cbor = $cbor->max_depth ([$maximum_nesting_depth]) |
119 | |
144 | |
120 | =item $max_depth = $cbor->get_max_depth |
145 | =item $max_depth = $cbor->get_max_depth |
121 | |
146 | |
… | |
… | |
137 | |
162 | |
138 | 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 |
139 | 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 |
140 | crashing. |
165 | crashing. |
141 | |
166 | |
142 | 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. |
143 | |
168 | |
144 | =item $cbor = $cbor->max_size ([$maximum_string_size]) |
169 | =item $cbor = $cbor->max_size ([$maximum_string_size]) |
145 | |
170 | |
146 | =item $max_size = $cbor->get_max_size |
171 | =item $max_size = $cbor->get_max_size |
147 | |
172 | |
… | |
… | |
152 | effect on C<encode> (yet). |
177 | effect on C<encode> (yet). |
153 | |
178 | |
154 | 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 |
155 | C<0> is specified). |
180 | C<0> is specified). |
156 | |
181 | |
157 | 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. |
158 | |
183 | |
159 | =item $cbor = $cbor->allow_unknown ([$enable]) |
184 | =item $cbor = $cbor->allow_unknown ([$enable]) |
160 | |
185 | |
161 | =item $enabled = $cbor->get_allow_unknown |
186 | =item $enabled = $cbor->get_allow_unknown |
162 | |
187 | |
… | |
… | |
180 | reference to the earlier value. |
205 | reference to the earlier value. |
181 | |
206 | |
182 | This means that such values will only be encoded once, and will not result |
207 | This means that such values will only be encoded once, and will not result |
183 | in a deep cloning of the value on decode, in decoders supporting the value |
208 | in a deep cloning of the value on decode, in decoders supporting the value |
184 | sharing extension. This also makes it possible to encode cyclic data |
209 | sharing extension. This also makes it possible to encode cyclic data |
185 | structures (which need C<allow_cycles> to ne enabled to be decoded by this |
210 | structures (which need C<allow_cycles> to be enabled to be decoded by this |
186 | module). |
211 | module). |
187 | |
212 | |
188 | It is recommended to leave it off unless you know your |
213 | It is recommended to leave it off unless you know your |
189 | communication partner supports the value sharing extensions to CBOR |
214 | communication partner supports the value sharing extensions to CBOR |
190 | (L<http://cbor.schmorp.de/value-sharing>), as without decoder support, the |
215 | (L<http://cbor.schmorp.de/value-sharing>), as without decoder support, the |
191 | resulting data structure might be unusable. |
216 | resulting data structure might be unusable. |
192 | |
217 | |
193 | Detecting shared values incurs a runtime overhead when values are encoded |
218 | Detecting shared values incurs a runtime overhead when values are encoded |
194 | that have a reference counter large than one, and might unnecessarily |
219 | that have a reference counter large than one, and might unnecessarily |
195 | increase the encoded size, as potentially shared values are encode as |
220 | increase the encoded size, as potentially shared values are encoded as |
196 | shareable whether or not they are actually shared. |
221 | shareable whether or not they are actually shared. |
197 | |
222 | |
198 | At the moment, only targets of references can be shared (e.g. scalars, |
223 | At the moment, only targets of references can be shared (e.g. scalars, |
199 | arrays or hashes pointed to by a reference). Weirder constructs, such as |
224 | arrays or hashes pointed to by a reference). Weirder constructs, such as |
200 | an array with multiple "copies" of the I<same> string, which are hard but |
225 | an array with multiple "copies" of the I<same> string, which are hard but |
… | |
… | |
226 | throwing an error. |
251 | throwing an error. |
227 | |
252 | |
228 | This option does not affect C<encode> in any way - shared values and |
253 | This option does not affect C<encode> in any way - shared values and |
229 | references will always be encoded properly if present. |
254 | references will always be encoded properly if present. |
230 | |
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 | |
231 | =item $cbor = $cbor->pack_strings ([$enable]) |
275 | =item $cbor = $cbor->pack_strings ([$enable]) |
232 | |
276 | |
233 | =item $enabled = $cbor->get_pack_strings |
277 | =item $enabled = $cbor->get_pack_strings |
234 | |
278 | |
235 | If C<$enable> is true (or missing), then C<encode> will try not to encode |
279 | If C<$enable> is true (or missing), then C<encode> will try not to encode |
… | |
… | |
247 | the standard CBOR way. |
291 | the standard CBOR way. |
248 | |
292 | |
249 | This option does not affect C<decode> in any way - string references will |
293 | This option does not affect C<decode> in any way - string references will |
250 | always be decoded properly if present. |
294 | always be decoded properly if present. |
251 | |
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 | |
252 | =item $cbor = $cbor->validate_utf8 ([$enable]) |
341 | =item $cbor = $cbor->validate_utf8 ([$enable]) |
253 | |
342 | |
254 | =item $enabled = $cbor->get_validate_utf8 |
343 | =item $enabled = $cbor->get_validate_utf8 |
255 | |
344 | |
256 | If C<$enable> is true (or missing), then C<decode> will validate that |
345 | If C<$enable> is true (or missing), then C<decode> will validate that |
… | |
… | |
261 | The concept of "valid UTF-8" used is perl's concept, which is a superset |
350 | The concept of "valid UTF-8" used is perl's concept, which is a superset |
262 | of the official UTF-8. |
351 | of the official UTF-8. |
263 | |
352 | |
264 | If C<$enable> is false (the default), then C<decode> will blindly accept |
353 | If C<$enable> is false (the default), then C<decode> will blindly accept |
265 | UTF-8 data, marking them as valid UTF-8 in the resulting data structure |
354 | UTF-8 data, marking them as valid UTF-8 in the resulting data structure |
266 | regardless of whether thats true or not. |
355 | regardless of whether that's true or not. |
267 | |
356 | |
268 | Perl isn't too happy about corrupted UTF-8 in strings, but should |
357 | Perl isn't too happy about corrupted UTF-8 in strings, but should |
269 | generally not crash or do similarly evil things. Extensions might be not |
358 | generally not crash or do similarly evil things. Extensions might be not |
270 | so forgiving, so it's recommended to turn on this setting if you receive |
359 | so forgiving, so it's recommended to turn on this setting if you receive |
271 | untrusted CBOR. |
360 | untrusted CBOR. |
… | |
… | |
293 | replace the tagged value in the decoded data structure, or no values, |
382 | replace the tagged value in the decoded data structure, or no values, |
294 | which will result in default handling, which currently means the decoder |
383 | which will result in default handling, which currently means the decoder |
295 | creates a C<CBOR::XS::Tagged> object to hold the tag and the value. |
384 | creates a C<CBOR::XS::Tagged> object to hold the tag and the value. |
296 | |
385 | |
297 | When the filter is cleared (the default state), the default filter |
386 | When the filter is cleared (the default state), the default filter |
298 | function, C<CBOR::XS::default_filter>, is used. This function simply looks |
387 | function, C<CBOR::XS::default_filter>, is used. This function simply |
299 | up the tag in the C<%CBOR::XS::FILTER> hash. If an entry exists it must be |
388 | looks up the tag in the C<%CBOR::XS::FILTER> hash. If an entry exists |
300 | a code reference that is called with tag and value, and is responsible for |
389 | it must be a code reference that is called with tag and value, and is |
301 | decoding the value. If no entry exists, it returns no values. |
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. |
302 | |
404 | |
303 | Example: decode all tags not handled internally into C<CBOR::XS::Tagged> |
405 | Example: decode all tags not handled internally into C<CBOR::XS::Tagged> |
304 | objects, with no other special handling (useful when working with |
406 | objects, with no other special handling (useful when working with |
305 | potentially "unsafe" CBOR data). |
407 | potentially "unsafe" CBOR data). |
306 | |
408 | |
… | |
… | |
313 | my ($tag, $value); |
415 | my ($tag, $value); |
314 | |
416 | |
315 | "tag 1347375694 value $value" |
417 | "tag 1347375694 value $value" |
316 | }; |
418 | }; |
317 | |
419 | |
|
|
420 | Example: provide your own filter function that looks up tags in your own |
|
|
421 | hash: |
|
|
422 | |
|
|
423 | my %my_filter = ( |
|
|
424 | 998347484 => sub { |
|
|
425 | my ($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); |
|
|
440 | |
318 | =item $cbor_data = $cbor->encode ($perl_scalar) |
441 | =item $cbor_data = $cbor->encode ($perl_scalar) |
319 | |
442 | |
320 | 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 |
321 | representation. |
444 | representation. |
322 | |
445 | |
… | |
… | |
331 | 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 |
332 | 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. |
333 | |
456 | |
334 | 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 |
335 | 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 |
336 | 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. |
337 | |
461 | |
338 | CBOR::XS->new->decode_prefix ("......") |
462 | CBOR::XS->new->decode_prefix ("......") |
339 | => ("...", 3) |
463 | => ("...", 3) |
340 | |
464 | |
341 | =back |
465 | =back |
… | |
… | |
396 | |
520 | |
397 | Resets the incremental decoder. This throws away any saved state, so that |
521 | Resets the incremental decoder. This throws away any saved state, so that |
398 | subsequent calls to C<incr_parse> or C<incr_parse_multiple> start to parse |
522 | subsequent calls to C<incr_parse> or C<incr_parse_multiple> start to parse |
399 | a new CBOR value from the beginning of the C<$buffer> again. |
523 | a new CBOR value from the beginning of the C<$buffer> again. |
400 | |
524 | |
401 | This method can be caled at any time, but it I<must> be called if you want |
525 | This method can be called at any time, but it I<must> be called if you want |
402 | to change your C<$buffer> or there was a decoding error and you want to |
526 | to change your C<$buffer> or there was a decoding error and you want to |
403 | reuse the C<$cbor> object for future incremental parsings. |
527 | reuse the C<$cbor> object for future incremental parsings. |
404 | |
528 | |
405 | =back |
529 | =back |
406 | |
530 | |
… | |
… | |
544 | my $x = 3.1; # some variable containing a number |
668 | my $x = 3.1; # some variable containing a number |
545 | "$x"; # stringified |
669 | "$x"; # stringified |
546 | $x .= ""; # another, more awkward way to stringify |
670 | $x .= ""; # another, more awkward way to stringify |
547 | print $x; # perl does it for you, too, quite often |
671 | print $x; # perl does it for you, too, quite often |
548 | |
672 | |
549 | You can force whether a string ie encoded as byte or text string by using |
673 | You can force whether a string is encoded as byte or text string by using |
550 | C<utf8::upgrade> and C<utf8::downgrade>): |
674 | C<utf8::upgrade> and C<utf8::downgrade> (if C<text_strings> is disabled). |
551 | |
675 | |
552 | utf8::upgrade $x; # encode $x as text string |
676 | utf8::upgrade $x; # encode $x as text string |
553 | utf8::downgrade $x; # encode $x as byte string |
677 | utf8::downgrade $x; # encode $x as byte string |
554 | |
678 | |
|
|
679 | More options are available, see L<TYPE CASTS>, below, and the C<text_keys> |
|
|
680 | and C<text_strings> options. |
|
|
681 | |
555 | Perl doesn't define what operations up- and downgrade strings, so if the |
682 | Perl doesn't define what operations up- and downgrade strings, so if the |
556 | difference between byte and text is important, you should up- or downgrade |
683 | difference between byte and text is important, you should up- or downgrade |
557 | your string as late as possible before encoding. |
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>. |
558 | |
686 | |
559 | 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: |
560 | |
688 | |
561 | my $x = "3"; # some variable containing a string |
689 | my $x = "3"; # some variable containing a string |
562 | $x += 0; # numify it, ensuring it will be dumped as a number |
690 | $x += 0; # numify it, ensuring it will be dumped as a number |
… | |
… | |
573 | represent numerical values are supported, but might suffer loss of |
701 | represent numerical values are supported, but might suffer loss of |
574 | precision. |
702 | precision. |
575 | |
703 | |
576 | =back |
704 | =back |
577 | |
705 | |
|
|
706 | =head2 TYPE CASTS |
|
|
707 | |
|
|
708 | B<EXPERIMENTAL>: As an experimental extension, C<CBOR::XS> allows you to |
|
|
709 | force specific CBOR types to be used when encoding. That allows you to |
|
|
710 | encode types not normally accessible (e.g. half floats) as well as force |
|
|
711 | string types even when C<text_strings> is in effect. |
|
|
712 | |
|
|
713 | Type forcing is done by calling a special "cast" function which keeps a |
|
|
714 | copy of the value and returns a new value that can be handed over to any |
|
|
715 | CBOR encoder function. |
|
|
716 | |
|
|
717 | The following casts are currently available (all of which are unary |
|
|
718 | operators, that is, have a prototype of C<$>): |
|
|
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 $cbor_text |
|
|
760 | |
|
|
761 | Not a type cast per-se, this type cast forces the argument to be encoded |
|
|
762 | as-is. This can be used to embed pre-encoded CBOR data. |
|
|
763 | |
|
|
764 | Note that no checking on the validity of the C<$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 pairs 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 | Note that only the reference to the array is copied, the array itself is |
|
|
778 | not. Modifications done to the array before calling an encoding function |
|
|
779 | will be reflected in the encoded output. |
|
|
780 | |
|
|
781 | Example: encode a CBOR map with a string and an integer as keys. |
|
|
782 | |
|
|
783 | encode_cbor CBOR::XS::as_map [string => "value", 5 => "value"] |
|
|
784 | |
|
|
785 | =back |
|
|
786 | |
|
|
787 | =cut |
|
|
788 | |
|
|
789 | sub CBOR::XS::as_cbor ($) { bless [$_[0], 0, undef], CBOR::XS::Tagged:: } |
|
|
790 | sub CBOR::XS::as_int ($) { bless [$_[0], 1, undef], CBOR::XS::Tagged:: } |
|
|
791 | sub CBOR::XS::as_bytes ($) { bless [$_[0], 2, undef], CBOR::XS::Tagged:: } |
|
|
792 | sub CBOR::XS::as_text ($) { bless [$_[0], 3, undef], CBOR::XS::Tagged:: } |
|
|
793 | sub CBOR::XS::as_float16 ($) { bless [$_[0], 4, undef], CBOR::XS::Tagged:: } |
|
|
794 | sub CBOR::XS::as_float32 ($) { bless [$_[0], 5, undef], CBOR::XS::Tagged:: } |
|
|
795 | sub CBOR::XS::as_float64 ($) { bless [$_[0], 6, undef], CBOR::XS::Tagged:: } |
|
|
796 | |
|
|
797 | sub CBOR::XS::as_bool ($) { $_[0] ? $Types::Serialiser::true : $Types::Serialiser::false } |
|
|
798 | |
|
|
799 | sub CBOR::XS::as_map ($) { |
|
|
800 | ARRAY:: eq ref $_[0] |
|
|
801 | and $#{ $_[0] } & 1 |
|
|
802 | or do { require Carp; Carp::croak ("CBOR::XS::as_map only acepts array references with an even number of elements, caught") }; |
|
|
803 | |
|
|
804 | bless [$_[0], 7, undef], CBOR::XS::Tagged:: |
|
|
805 | } |
|
|
806 | |
578 | =head2 OBJECT SERIALISATION |
807 | =head2 OBJECT SERIALISATION |
579 | |
808 | |
580 | This module implements both a CBOR-specific and the generic |
809 | This module implements both a CBOR-specific and the generic |
581 | L<Types::Serialier> object serialisation protocol. The following |
810 | L<Types::Serialier> object serialisation protocol. The following |
582 | subsections explain both methods. |
811 | subsections explain both methods. |
… | |
… | |
663 | "$self" # encode url string |
892 | "$self" # encode url string |
664 | } |
893 | } |
665 | |
894 | |
666 | sub URI::THAW { |
895 | sub URI::THAW { |
667 | my ($class, $serialiser, $uri) = @_; |
896 | my ($class, $serialiser, $uri) = @_; |
668 | |
|
|
669 | $class->new ($uri) |
897 | $class->new ($uri) |
670 | } |
898 | } |
671 | |
899 | |
672 | Unlike C<TO_CBOR>, multiple values can be returned by C<FREEZE>. For |
900 | Unlike C<TO_CBOR>, multiple values can be returned by C<FREEZE>. For |
673 | example, a C<FREEZE> method that returns "type", "id" and "variant" values |
901 | example, a C<FREEZE> method that returns "type", "id" and "variant" values |
… | |
… | |
804 | additional tags (such as base64url). |
1032 | additional tags (such as base64url). |
805 | |
1033 | |
806 | =head2 ENFORCED TAGS |
1034 | =head2 ENFORCED TAGS |
807 | |
1035 | |
808 | These tags are always handled when decoding, and their handling cannot be |
1036 | These tags are always handled when decoding, and their handling cannot be |
809 | overriden by the user. |
1037 | overridden by the user. |
810 | |
1038 | |
811 | =over 4 |
1039 | =over 4 |
812 | |
1040 | |
813 | =item 26 (perl-object, L<http://cbor.schmorp.de/perl-object>) |
1041 | =item 26 (perl-object, L<http://cbor.schmorp.de/perl-object>) |
814 | |
1042 | |
… | |
… | |
842 | encoded, however, when C<pack_strings> is enabled. |
1070 | encoded, however, when C<pack_strings> is enabled. |
843 | |
1071 | |
844 | =item 22098 (indirection, L<http://cbor.schmorp.de/indirection>) |
1072 | =item 22098 (indirection, L<http://cbor.schmorp.de/indirection>) |
845 | |
1073 | |
846 | This tag is automatically generated when a reference are encountered (with |
1074 | This tag is automatically generated when a reference are encountered (with |
847 | the exception of hash and array refernces). It is converted to a reference |
1075 | the exception of hash and array references). It is converted to a reference |
848 | when decoding. |
1076 | when decoding. |
849 | |
1077 | |
850 | =item 55799 (self-describe CBOR, RFC 7049) |
1078 | =item 55799 (self-describe CBOR, RFC 7049) |
851 | |
1079 | |
852 | This value is not generated on encoding (unless explicitly requested by |
1080 | This value is not generated on encoding (unless explicitly requested by |
… | |
… | |
855 | =back |
1083 | =back |
856 | |
1084 | |
857 | =head2 NON-ENFORCED TAGS |
1085 | =head2 NON-ENFORCED TAGS |
858 | |
1086 | |
859 | These tags have default filters provided when decoding. Their handling can |
1087 | These tags have default filters provided when decoding. Their handling can |
860 | be overriden by changing the C<%CBOR::XS::FILTER> entry for the tag, or by |
1088 | be overridden by changing the C<%CBOR::XS::FILTER> entry for the tag, or by |
861 | providing a custom C<filter> callback when decoding. |
1089 | providing a custom C<filter> callback when decoding. |
862 | |
1090 | |
863 | When they result in decoding into a specific Perl class, the module |
1091 | When they result in decoding into a specific Perl class, the module |
864 | usually provides a corresponding C<TO_CBOR> method as well. |
1092 | usually provides a corresponding C<TO_CBOR> method as well. |
865 | |
1093 | |
… | |
… | |
883 | |
1111 | |
884 | These tags are decoded into L<Math::BigInt> objects. The corresponding |
1112 | These tags are decoded into L<Math::BigInt> objects. The corresponding |
885 | C<Math::BigInt::TO_CBOR> method encodes "small" bigints into normal CBOR |
1113 | C<Math::BigInt::TO_CBOR> method encodes "small" bigints into normal CBOR |
886 | integers, and others into positive/negative CBOR bignums. |
1114 | integers, and others into positive/negative CBOR bignums. |
887 | |
1115 | |
888 | =item 4, 5 (decimal fraction/bigfloat) |
1116 | =item 4, 5, 264, 265 (decimal fraction/bigfloat) |
889 | |
1117 | |
890 | Both decimal fractions and bigfloats are decoded into L<Math::BigFloat> |
1118 | Both decimal fractions and bigfloats are decoded into L<Math::BigFloat> |
891 | objects. The corresponding C<Math::BigFloat::TO_CBOR> method I<always> |
1119 | objects. The corresponding C<Math::BigFloat::TO_CBOR> method I<always> |
892 | encodes into a decimal fraction. |
1120 | encodes into a decimal fraction (either tag 4 or 264). |
893 | |
1121 | |
894 | CBOR cannot represent bigfloats with I<very> large exponents - conversion |
1122 | NaN and infinities are not encoded properly, as they cannot be represented |
895 | of such big float objects is undefined. |
1123 | in CBOR. |
896 | |
1124 | |
897 | Also, NaN and infinities are not encoded properly. |
1125 | See L<BIGNUM SECURITY CONSIDERATIONS> for more info. |
|
|
1126 | |
|
|
1127 | =item 30 (rational numbers) |
|
|
1128 | |
|
|
1129 | These tags are decoded into L<Math::BigRat> objects. The corresponding |
|
|
1130 | C<Math::BigRat::TO_CBOR> method encodes rational numbers with denominator |
|
|
1131 | C<1> via their numerator only, i.e., they become normal integers or |
|
|
1132 | C<bignums>. |
|
|
1133 | |
|
|
1134 | See L<BIGNUM SECURITY CONSIDERATIONS> for more info. |
898 | |
1135 | |
899 | =item 21, 22, 23 (expected later JSON conversion) |
1136 | =item 21, 22, 23 (expected later JSON conversion) |
900 | |
1137 | |
901 | CBOR::XS is not a CBOR-to-JSON converter, and will simply ignore these |
1138 | CBOR::XS is not a CBOR-to-JSON converter, and will simply ignore these |
902 | tags. |
1139 | tags. |
… | |
… | |
907 | C<URI::TO_CBOR> method again results in a CBOR URI value. |
1144 | C<URI::TO_CBOR> method again results in a CBOR URI value. |
908 | |
1145 | |
909 | =back |
1146 | =back |
910 | |
1147 | |
911 | =cut |
1148 | =cut |
912 | |
|
|
913 | our %FILTER = ( |
|
|
914 | # 0 # rfc4287 datetime, utf-8 |
|
|
915 | # 1 # unix timestamp, any |
|
|
916 | |
|
|
917 | 2 => sub { # pos bigint |
|
|
918 | require Math::BigInt; |
|
|
919 | Math::BigInt->new ("0x" . unpack "H*", pop) |
|
|
920 | }, |
|
|
921 | |
|
|
922 | 3 => sub { # neg bigint |
|
|
923 | require Math::BigInt; |
|
|
924 | -Math::BigInt->new ("0x" . unpack "H*", pop) |
|
|
925 | }, |
|
|
926 | |
|
|
927 | 4 => sub { # decimal fraction, array |
|
|
928 | require Math::BigFloat; |
|
|
929 | Math::BigFloat->new ($_[1][1] . "E" . $_[1][0]) |
|
|
930 | }, |
|
|
931 | |
|
|
932 | 5 => sub { # bigfloat, array |
|
|
933 | require Math::BigFloat; |
|
|
934 | scalar Math::BigFloat->new ($_[1][1])->blsft ($_[1][0], 2) |
|
|
935 | }, |
|
|
936 | |
|
|
937 | 21 => sub { pop }, # expected conversion to base64url encoding |
|
|
938 | 22 => sub { pop }, # expected conversion to base64 encoding |
|
|
939 | 23 => sub { pop }, # expected conversion to base16 encoding |
|
|
940 | |
|
|
941 | # 24 # embedded cbor, byte string |
|
|
942 | |
|
|
943 | 32 => sub { |
|
|
944 | require URI; |
|
|
945 | URI->new (pop) |
|
|
946 | }, |
|
|
947 | |
|
|
948 | # 33 # base64url rfc4648, utf-8 |
|
|
949 | # 34 # base64 rfc46484, utf-8 |
|
|
950 | # 35 # regex pcre/ecma262, utf-8 |
|
|
951 | # 36 # mime message rfc2045, utf-8 |
|
|
952 | ); |
|
|
953 | |
|
|
954 | |
1149 | |
955 | =head1 CBOR and JSON |
1150 | =head1 CBOR and JSON |
956 | |
1151 | |
957 | CBOR is supposed to implement a superset of the JSON data model, and is, |
1152 | CBOR is supposed to implement a superset of the JSON data model, and is, |
958 | with some coercion, able to represent all JSON texts (something that other |
1153 | with some coercion, able to represent all JSON texts (something that other |
… | |
… | |
967 | CBOR intact. |
1162 | CBOR intact. |
968 | |
1163 | |
969 | |
1164 | |
970 | =head1 SECURITY CONSIDERATIONS |
1165 | =head1 SECURITY CONSIDERATIONS |
971 | |
1166 | |
972 | When you are using CBOR in a protocol, talking to untrusted potentially |
1167 | Tl;dr... if you want to decode or encode CBOR from untrusted sources, you |
973 | hostile creatures requires relatively few measures. |
1168 | should start with a coder object created via C<new_safe> (which implements |
|
|
1169 | the mitigations explained below): |
974 | |
1170 | |
|
|
1171 | my $coder = CBOR::XS->new_safe; |
|
|
1172 | |
|
|
1173 | my $data = $coder->decode ($cbor_text); |
|
|
1174 | my $cbor = $coder->encode ($data); |
|
|
1175 | |
|
|
1176 | Longer version: When you are using CBOR in a protocol, talking to |
|
|
1177 | untrusted potentially hostile creatures requires some thought: |
|
|
1178 | |
|
|
1179 | =over 4 |
|
|
1180 | |
|
|
1181 | =item Security of the CBOR decoder itself |
|
|
1182 | |
975 | First of all, your CBOR decoder should be secure, that is, should not have |
1183 | First and foremost, your CBOR decoder should be secure, that is, should |
|
|
1184 | not have any buffer overflows or similar bugs that could potentially be |
976 | any buffer overflows. Obviously, this module should ensure that and I am |
1185 | exploited. Obviously, this module should ensure that and I am trying hard |
977 | trying hard on making that true, but you never know. |
1186 | on making that true, but you never know. |
978 | |
1187 | |
|
|
1188 | =item CBOR::XS can invoke almost arbitrary callbacks during decoding |
|
|
1189 | |
|
|
1190 | CBOR::XS supports object serialisation - decoding CBOR can cause calls |
|
|
1191 | to I<any> C<THAW> method in I<any> package that exists in your process |
|
|
1192 | (that is, CBOR::XS will not try to load modules, but any existing C<THAW> |
|
|
1193 | method or function can be called, so they all have to be secure). |
|
|
1194 | |
|
|
1195 | Less obviously, it will also invoke C<TO_CBOR> and C<FREEZE> methods - |
|
|
1196 | even if all your C<THAW> methods are secure, encoding data structures from |
|
|
1197 | untrusted sources can invoke those and trigger bugs in those. |
|
|
1198 | |
|
|
1199 | So, if you are not sure about the security of all the modules you |
|
|
1200 | have loaded (you shouldn't), you should disable this part using |
|
|
1201 | C<forbid_objects> or using C<new_safe>. |
|
|
1202 | |
|
|
1203 | =item CBOR can be extended with tags that call library code |
|
|
1204 | |
|
|
1205 | CBOR can be extended with tags, and C<CBOR::XS> has a registry of |
|
|
1206 | conversion functions for many existing tags that can be extended via |
|
|
1207 | third-party modules (see the C<filter> method). |
|
|
1208 | |
|
|
1209 | If you don't trust these, you should configure the "safe" filter function, |
|
|
1210 | C<CBOR::XS::safe_filter> (C<new_safe> does this), which by default only |
|
|
1211 | includes conversion functions that are considered "safe" by the author |
|
|
1212 | (but again, they can be extended by third party modules). |
|
|
1213 | |
|
|
1214 | Depending on your level of paranoia, you can use the "safe" filter: |
|
|
1215 | |
|
|
1216 | $cbor->filter (\&CBOR::XS::safe_filter); |
|
|
1217 | |
|
|
1218 | ... your own filter... |
|
|
1219 | |
|
|
1220 | $cbor->filter (sub { ... do your stuffs here ... }); |
|
|
1221 | |
|
|
1222 | ... or even no filter at all, disabling all tag decoding: |
|
|
1223 | |
|
|
1224 | $cbor->filter (sub { }); |
|
|
1225 | |
|
|
1226 | This is never a problem for encoding, as the tag mechanism only exists in |
|
|
1227 | CBOR texts. |
|
|
1228 | |
|
|
1229 | =item Resource-starving attacks: object memory usage |
|
|
1230 | |
979 | Second, you need to avoid resource-starving attacks. That means you should |
1231 | You need to avoid resource-starving attacks. That means you should limit |
980 | limit the size of CBOR data you accept, or make sure then when your |
1232 | the size of CBOR data you accept, or make sure then when your resources |
981 | resources run out, that's just fine (e.g. by using a separate process that |
1233 | run out, that's just fine (e.g. by using a separate process that can |
982 | can crash safely). The size of a CBOR string in octets is usually a good |
1234 | crash safely). The size of a CBOR string in octets is usually a good |
983 | indication of the size of the resources required to decode it into a Perl |
1235 | indication of the size of the resources required to decode it into a Perl |
984 | structure. While CBOR::XS can check the size of the CBOR text, it might be |
1236 | structure. While CBOR::XS can check the size of the CBOR text (using |
985 | too late when you already have it in memory, so you might want to check |
1237 | C<max_size> - done by C<new_safe>), it might be too late when you already |
986 | the size before you accept the string. |
1238 | have it in memory, so you might want to check the size before you accept |
|
|
1239 | the string. |
987 | |
1240 | |
|
|
1241 | As for encoding, it is possible to construct data structures that are |
|
|
1242 | relatively small but result in large CBOR texts (for example by having an |
|
|
1243 | array full of references to the same big data structure, which will all be |
|
|
1244 | deep-cloned during encoding by default). This is rarely an actual issue |
|
|
1245 | (and the worst case is still just running out of memory), but you can |
|
|
1246 | reduce this risk by using C<allow_sharing>. |
|
|
1247 | |
|
|
1248 | =item Resource-starving attacks: stack overflows |
|
|
1249 | |
988 | Third, CBOR::XS recurses using the C stack when decoding objects and |
1250 | CBOR::XS recurses using the C stack when decoding objects and arrays. The |
989 | arrays. The C stack is a limited resource: for instance, on my amd64 |
1251 | C stack is a limited resource: for instance, on my amd64 machine with 8MB |
990 | machine with 8MB of stack size I can decode around 180k nested arrays but |
1252 | of stack size I can decode around 180k nested arrays but only 14k nested |
991 | only 14k nested CBOR objects (due to perl itself recursing deeply on croak |
1253 | CBOR objects (due to perl itself recursing deeply on croak to free the |
992 | to free the temporary). If that is exceeded, the program crashes. To be |
1254 | temporary). If that is exceeded, the program crashes. To be conservative, |
993 | conservative, the default nesting limit is set to 512. If your process |
1255 | the default nesting limit is set to 512. If your process has a smaller |
994 | has a smaller stack, you should adjust this setting accordingly with the |
1256 | stack, you should adjust this setting accordingly with the C<max_depth> |
995 | C<max_depth> method. |
1257 | method. |
|
|
1258 | |
|
|
1259 | =item Resource-starving attacks: CPU en-/decoding complexity |
|
|
1260 | |
|
|
1261 | CBOR::XS will use the L<Math::BigInt>, L<Math::BigFloat> and |
|
|
1262 | L<Math::BigRat> libraries to represent encode/decode bignums. These can be |
|
|
1263 | very slow (as in, centuries of CPU time) and can even crash your program |
|
|
1264 | (and are generally not very trustworthy). See the next section on bignum |
|
|
1265 | security for details. |
|
|
1266 | |
|
|
1267 | =item Data breaches: leaking information in error messages |
|
|
1268 | |
|
|
1269 | CBOR::XS might leak contents of your Perl data structures in its error |
|
|
1270 | messages, so when you serialise sensitive information you might want to |
|
|
1271 | make sure that exceptions thrown by CBOR::XS will not end up in front of |
|
|
1272 | untrusted eyes. |
|
|
1273 | |
|
|
1274 | =item Something else... |
996 | |
1275 | |
997 | Something else could bomb you, too, that I forgot to think of. In that |
1276 | Something else could bomb you, too, that I forgot to think of. In that |
998 | case, you get to keep the pieces. I am always open for hints, though... |
1277 | case, you get to keep the pieces. I am always open for hints, though... |
999 | |
1278 | |
1000 | Also keep in mind that CBOR::XS might leak contents of your Perl data |
1279 | =back |
1001 | structures in its error messages, so when you serialise sensitive |
1280 | |
1002 | information you might want to make sure that exceptions thrown by CBOR::XS |
1281 | |
1003 | will not end up in front of untrusted eyes. |
1282 | =head1 BIGNUM SECURITY CONSIDERATIONS |
|
|
1283 | |
|
|
1284 | CBOR::XS provides a C<TO_CBOR> method for both L<Math::BigInt> and |
|
|
1285 | L<Math::BigFloat> that tries to encode the number in the simplest possible |
|
|
1286 | way, that is, either a CBOR integer, a CBOR bigint/decimal fraction (tag |
|
|
1287 | 4) or an arbitrary-exponent decimal fraction (tag 264). Rational numbers |
|
|
1288 | (L<Math::BigRat>, tag 30) can also contain bignums as members. |
|
|
1289 | |
|
|
1290 | CBOR::XS will also understand base-2 bigfloat or arbitrary-exponent |
|
|
1291 | bigfloats (tags 5 and 265), but it will never generate these on its own. |
|
|
1292 | |
|
|
1293 | Using the built-in L<Math::BigInt::Calc> support, encoding and decoding |
|
|
1294 | decimal fractions is generally fast. Decoding bigints can be slow for very |
|
|
1295 | big numbers (tens of thousands of digits, something that could potentially |
|
|
1296 | be caught by limiting the size of CBOR texts), and decoding bigfloats or |
|
|
1297 | arbitrary-exponent bigfloats can be I<extremely> slow (minutes, decades) |
|
|
1298 | for large exponents (roughly 40 bit and longer). |
|
|
1299 | |
|
|
1300 | Additionally, L<Math::BigInt> can take advantage of other bignum |
|
|
1301 | libraries, such as L<Math::GMP>, which cannot handle big floats with large |
|
|
1302 | exponents, and might simply abort or crash your program, due to their code |
|
|
1303 | quality. |
|
|
1304 | |
|
|
1305 | This can be a concern if you want to parse untrusted CBOR. If it is, you |
|
|
1306 | might want to disable decoding of tag 2 (bigint) and 3 (negative bigint) |
|
|
1307 | types. You should also disable types 5 and 265, as these can be slow even |
|
|
1308 | without bigints. |
|
|
1309 | |
|
|
1310 | Disabling bigints will also partially or fully disable types that rely on |
|
|
1311 | them, e.g. rational numbers that use bignums. |
|
|
1312 | |
1004 | |
1313 | |
1005 | =head1 CBOR IMPLEMENTATION NOTES |
1314 | =head1 CBOR IMPLEMENTATION NOTES |
1006 | |
1315 | |
1007 | This section contains some random implementation notes. They do not |
1316 | This section contains some random implementation notes. They do not |
1008 | describe guaranteed behaviour, but merely behaviour as-is implemented |
1317 | describe guaranteed behaviour, but merely behaviour as-is implemented |
… | |
… | |
1024 | =head1 LIMITATIONS ON PERLS WITHOUT 64-BIT INTEGER SUPPORT |
1333 | =head1 LIMITATIONS ON PERLS WITHOUT 64-BIT INTEGER SUPPORT |
1025 | |
1334 | |
1026 | On perls that were built without 64 bit integer support (these are rare |
1335 | On perls that were built without 64 bit integer support (these are rare |
1027 | nowadays, even on 32 bit architectures, as all major Perl distributions |
1336 | nowadays, even on 32 bit architectures, as all major Perl distributions |
1028 | are built with 64 bit integer support), support for any kind of 64 bit |
1337 | are built with 64 bit integer support), support for any kind of 64 bit |
1029 | integer in CBOR is very limited - most likely, these 64 bit values will |
1338 | value in CBOR is very limited - most likely, these 64 bit values will |
1030 | be truncated, corrupted, or otherwise not decoded correctly. This also |
1339 | be truncated, corrupted, or otherwise not decoded correctly. This also |
1031 | includes string, array and map sizes that are stored as 64 bit integers. |
1340 | includes string, float, array and map sizes that are stored as 64 bit |
|
|
1341 | integers. |
1032 | |
1342 | |
1033 | |
1343 | |
1034 | =head1 THREADS |
1344 | =head1 THREADS |
1035 | |
1345 | |
1036 | This module is I<not> guaranteed to be thread safe and there are no |
1346 | This module is I<not> guaranteed to be thread safe and there are no |
… | |
… | |
1049 | |
1359 | |
1050 | Please refrain from using rt.cpan.org or any other bug reporting |
1360 | Please refrain from using rt.cpan.org or any other bug reporting |
1051 | service. I put the contact address into my modules for a reason. |
1361 | service. I put the contact address into my modules for a reason. |
1052 | |
1362 | |
1053 | =cut |
1363 | =cut |
|
|
1364 | |
|
|
1365 | # clumsy and slow hv_store-in-hash helper function |
|
|
1366 | sub _hv_store { |
|
|
1367 | $_[0]{$_[1]} = $_[2]; |
|
|
1368 | } |
1054 | |
1369 | |
1055 | our %FILTER = ( |
1370 | our %FILTER = ( |
1056 | 0 => sub { # rfc4287 datetime, utf-8 |
1371 | 0 => sub { # rfc4287 datetime, utf-8 |
1057 | require Time::Piece; |
1372 | require Time::Piece; |
1058 | # Time::Piece::Strptime uses the "incredibly flexible date parsing routine" |
1373 | # Time::Piece::Strptime uses the "incredibly flexible date parsing routine" |
… | |
… | |
1094 | 4 => sub { # decimal fraction, array |
1409 | 4 => sub { # decimal fraction, array |
1095 | require Math::BigFloat; |
1410 | require Math::BigFloat; |
1096 | Math::BigFloat->new ($_[1][1] . "E" . $_[1][0]) |
1411 | Math::BigFloat->new ($_[1][1] . "E" . $_[1][0]) |
1097 | }, |
1412 | }, |
1098 | |
1413 | |
|
|
1414 | 264 => sub { # decimal fraction with arbitrary exponent |
|
|
1415 | require Math::BigFloat; |
|
|
1416 | Math::BigFloat->new ($_[1][1] . "E" . $_[1][0]) |
|
|
1417 | }, |
|
|
1418 | |
1099 | 5 => sub { # bigfloat, array |
1419 | 5 => sub { # bigfloat, array |
1100 | require Math::BigFloat; |
1420 | require Math::BigFloat; |
1101 | scalar Math::BigFloat->new ($_[1][1])->blsft ($_[1][0], 2) |
1421 | scalar Math::BigFloat->new ($_[1][1]) * Math::BigFloat->new (2)->bpow ($_[1][0]) |
|
|
1422 | }, |
|
|
1423 | |
|
|
1424 | 265 => sub { # bigfloat with arbitrary exponent |
|
|
1425 | require Math::BigFloat; |
|
|
1426 | scalar Math::BigFloat->new ($_[1][1]) * Math::BigFloat->new (2)->bpow ($_[1][0]) |
|
|
1427 | }, |
|
|
1428 | |
|
|
1429 | 30 => sub { # rational number |
|
|
1430 | require Math::BigRat; |
|
|
1431 | Math::BigRat->new ("$_[1][0]/$_[1][1]") # separate parameters only work in recent versons |
1102 | }, |
1432 | }, |
1103 | |
1433 | |
1104 | 21 => sub { pop }, # expected conversion to base64url encoding |
1434 | 21 => sub { pop }, # expected conversion to base64url encoding |
1105 | 22 => sub { pop }, # expected conversion to base64 encoding |
1435 | 22 => sub { pop }, # expected conversion to base64 encoding |
1106 | 23 => sub { pop }, # expected conversion to base16 encoding |
1436 | 23 => sub { pop }, # expected conversion to base16 encoding |
… | |
… | |
1116 | # 34 # base64 rfc46484, utf-8 |
1446 | # 34 # base64 rfc46484, utf-8 |
1117 | # 35 # regex pcre/ecma262, utf-8 |
1447 | # 35 # regex pcre/ecma262, utf-8 |
1118 | # 36 # mime message rfc2045, utf-8 |
1448 | # 36 # mime message rfc2045, utf-8 |
1119 | ); |
1449 | ); |
1120 | |
1450 | |
1121 | sub CBOR::XS::default_filter { |
1451 | sub default_filter { |
1122 | &{ $FILTER{$_[0]} or return } |
1452 | &{ $FILTER{$_[0]} or return } |
|
|
1453 | } |
|
|
1454 | |
|
|
1455 | our %SAFE_FILTER = map { $_ => $FILTER{$_} } 0, 1, 21, 22, 23, 32; |
|
|
1456 | |
|
|
1457 | sub safe_filter { |
|
|
1458 | &{ $SAFE_FILTER{$_[0]} or return } |
1123 | } |
1459 | } |
1124 | |
1460 | |
1125 | sub URI::TO_CBOR { |
1461 | sub URI::TO_CBOR { |
1126 | my $uri = $_[0]->as_string; |
1462 | my $uri = $_[0]->as_string; |
1127 | utf8::upgrade $uri; |
1463 | utf8::upgrade $uri; |
1128 | tag 32, $uri |
1464 | tag 32, $uri |
1129 | } |
1465 | } |
1130 | |
1466 | |
1131 | sub Math::BigInt::TO_CBOR { |
1467 | sub Math::BigInt::TO_CBOR { |
1132 | if ($_[0] >= -2147483648 && $_[0] <= 2147483647) { |
1468 | if (-2147483648 <= $_[0] && $_[0] <= 2147483647) { |
1133 | $_[0]->numify |
1469 | $_[0]->numify |
1134 | } else { |
1470 | } else { |
1135 | my $hex = substr $_[0]->as_hex, 2; |
1471 | my $hex = substr $_[0]->as_hex, 2; |
1136 | $hex = "0$hex" if 1 & length $hex; # sigh |
1472 | $hex = "0$hex" if 1 & length $hex; # sigh |
1137 | tag $_[0] >= 0 ? 2 : 3, pack "H*", $hex |
1473 | tag $_[0] >= 0 ? 2 : 3, pack "H*", $hex |
1138 | } |
1474 | } |
1139 | } |
1475 | } |
1140 | |
1476 | |
1141 | sub Math::BigFloat::TO_CBOR { |
1477 | sub Math::BigFloat::TO_CBOR { |
1142 | my ($m, $e) = $_[0]->parts; |
1478 | my ($m, $e) = $_[0]->parts; |
|
|
1479 | |
|
|
1480 | -9223372036854775808 <= $e && $e <= 18446744073709551615 |
1143 | tag 4, [$e->numify, $m] |
1481 | ? tag 4, [$e->numify, $m] |
|
|
1482 | : tag 264, [$e, $m] |
|
|
1483 | } |
|
|
1484 | |
|
|
1485 | sub Math::BigRat::TO_CBOR { |
|
|
1486 | my ($n, $d) = $_[0]->parts; |
|
|
1487 | |
|
|
1488 | # older versions of BigRat need *1, as they not always return numbers |
|
|
1489 | |
|
|
1490 | $d*1 == 1 |
|
|
1491 | ? $n*1 |
|
|
1492 | : tag 30, [$n*1, $d*1] |
1144 | } |
1493 | } |
1145 | |
1494 | |
1146 | sub Time::Piece::TO_CBOR { |
1495 | sub Time::Piece::TO_CBOR { |
1147 | tag 1, 0 + $_[0]->epoch |
1496 | tag 1, 0 + $_[0]->epoch |
1148 | } |
1497 | } |