… | |
… | |
26 | substr $many_cbor_strings, 0, $length, ""; # remove decoded cbor string |
26 | substr $many_cbor_strings, 0, $length, ""; # remove decoded cbor string |
27 | } |
27 | } |
28 | |
28 | |
29 | =head1 DESCRIPTION |
29 | =head1 DESCRIPTION |
30 | |
30 | |
31 | WARNING! This module is very new, and not very well tested (that's up to |
31 | WARNING! This module is very new, and not very well tested (that's up |
32 | you to do). Furthermore, details of the implementation might change freely |
32 | to you to do). Furthermore, details of the implementation might change |
33 | before version 1.0. And lastly, the object serialisation protocol depends |
33 | freely before version 1.0. And lastly, most extensions depend on an IANA |
34 | on a pending IANA assignment, and until that assignment is official, this |
34 | assignment, and until that assignment is official, this implementation is |
35 | implementation is not interoperable with other implementations (even |
35 | not interoperable with other implementations (even future versions of this |
36 | future versions of this module) until the assignment is done. |
36 | module) until the assignment is done. |
37 | |
37 | |
38 | You are still invited to try out CBOR, and this module. |
38 | You are still invited to try out CBOR, and this module. |
39 | |
39 | |
40 | This module converts Perl data structures to the Concise Binary Object |
40 | This module converts Perl data structures to the Concise Binary Object |
41 | Representation (CBOR) and vice versa. CBOR is a fast binary serialisation |
41 | Representation (CBOR) and vice versa. CBOR is a fast binary serialisation |
… | |
… | |
54 | data, the worse L<Storable> performs in comparison. |
54 | data, the worse L<Storable> performs in comparison. |
55 | |
55 | |
56 | As for compactness, C<CBOR::XS> encoded data structures are usually about |
56 | As for compactness, C<CBOR::XS> encoded data structures are usually about |
57 | 20% smaller than the same data encoded as (compact) JSON or L<Storable>. |
57 | 20% smaller than the same data encoded as (compact) JSON or L<Storable>. |
58 | |
58 | |
|
|
59 | In addition to the core CBOR data format, this module implements a number |
|
|
60 | of extensions, to support cyclic and self-referencing data structures |
|
|
61 | (see C<allow_sharing>), string deduplication (see C<pack_strings>) and |
|
|
62 | scalar references (always enabled). |
|
|
63 | |
59 | The primary goal of this module is to be I<correct> and the secondary goal |
64 | The primary goal of this module is to be I<correct> and the secondary goal |
60 | is to be I<fast>. To reach the latter goal it was written in C. |
65 | is to be I<fast>. To reach the latter goal it was written in C. |
61 | |
66 | |
62 | See MAPPING, below, on how CBOR::XS maps perl values to CBOR values and |
67 | See MAPPING, below, on how CBOR::XS maps perl values to CBOR values and |
63 | vice versa. |
68 | vice versa. |
… | |
… | |
66 | |
71 | |
67 | package CBOR::XS; |
72 | package CBOR::XS; |
68 | |
73 | |
69 | use common::sense; |
74 | use common::sense; |
70 | |
75 | |
71 | our $VERSION = 0.08; |
76 | our $VERSION = 0.09; |
72 | our @ISA = qw(Exporter); |
77 | our @ISA = qw(Exporter); |
73 | |
78 | |
74 | our @EXPORT = qw(encode_cbor decode_cbor); |
79 | our @EXPORT = qw(encode_cbor decode_cbor); |
75 | |
80 | |
76 | use Exporter; |
81 | use Exporter; |
… | |
… | |
113 | strings. All boolean flags described below are by default I<disabled>. |
118 | strings. All boolean flags described below are by default I<disabled>. |
114 | |
119 | |
115 | The mutators for flags all return the CBOR object again and thus calls can |
120 | The mutators for flags all return the CBOR object again and thus calls can |
116 | be chained: |
121 | be chained: |
117 | |
122 | |
118 | #TODO |
|
|
119 | my $cbor = CBOR::XS->new->encode ({a => [1,2]}); |
123 | my $cbor = CBOR::XS->new->encode ({a => [1,2]}); |
120 | |
124 | |
121 | =item $cbor = $cbor->max_depth ([$maximum_nesting_depth]) |
125 | =item $cbor = $cbor->max_depth ([$maximum_nesting_depth]) |
122 | |
126 | |
123 | =item $max_depth = $cbor->get_max_depth |
127 | =item $max_depth = $cbor->get_max_depth |
… | |
… | |
157 | If no argument is given, the limit check will be deactivated (same as when |
161 | If no argument is given, the limit check will be deactivated (same as when |
158 | C<0> is specified). |
162 | C<0> is specified). |
159 | |
163 | |
160 | See SECURITY CONSIDERATIONS, below, for more info on why this is useful. |
164 | See SECURITY CONSIDERATIONS, below, for more info on why this is useful. |
161 | |
165 | |
|
|
166 | =item $cbor = $cbor->allow_unknown ([$enable]) |
|
|
167 | |
|
|
168 | =item $enabled = $cbor->get_allow_unknown |
|
|
169 | |
|
|
170 | If C<$enable> is true (or missing), then C<encode> will I<not> throw an |
|
|
171 | exception when it encounters values it cannot represent in CBOR (for |
|
|
172 | example, filehandles) but instead will encode a CBOR C<error> value. |
|
|
173 | |
|
|
174 | If C<$enable> is false (the default), then C<encode> will throw an |
|
|
175 | exception when it encounters anything it cannot encode as CBOR. |
|
|
176 | |
|
|
177 | This option does not affect C<decode> in any way, and it is recommended to |
|
|
178 | leave it off unless you know your communications partner. |
|
|
179 | |
|
|
180 | =item $cbor = $cbor->allow_sharing ([$enable]) |
|
|
181 | |
|
|
182 | =item $enabled = $cbor->get_allow_sharing |
|
|
183 | |
|
|
184 | If C<$enable> is true (or missing), then C<encode> will not double-encode |
|
|
185 | values that have been referenced before (e.g. when the same object, such |
|
|
186 | as an array, is referenced multiple times), but instead will emit a |
|
|
187 | reference to the earlier value. |
|
|
188 | |
|
|
189 | 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 |
|
|
191 | sharing extension. This also makes it possible to encode cyclic data |
|
|
192 | structures. |
|
|
193 | |
|
|
194 | It is recommended to leave it off unless you know your |
|
|
195 | communication partner supports the value sharing extensions to CBOR |
|
|
196 | (L<http://cbor.schmorp.de/value-sharing>), as without decoder support, the |
|
|
197 | resulting data structure might be unusable. |
|
|
198 | |
|
|
199 | Detecting shared values incurs a runtime overhead when values are encoded |
|
|
200 | that have a reference counter large than one, and might unnecessarily |
|
|
201 | increase the encoded size, as potentially shared values are encode as |
|
|
202 | sharable whether or not they are actually shared. |
|
|
203 | |
|
|
204 | 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 |
|
|
206 | 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 |
|
|
208 | with L<Storable>). |
|
|
209 | |
|
|
210 | If C<$enable> is false (the default), then C<encode> will encode shared |
|
|
211 | data structures repeatedly, unsharing them in the process. Cyclic data |
|
|
212 | structures cannot be encoded in this mode. |
|
|
213 | |
|
|
214 | This option does not affect C<decode> in any way - shared values and |
|
|
215 | references will always be decoded properly if present. |
|
|
216 | |
|
|
217 | =item $cbor = $cbor->pack_strings ([$enable]) |
|
|
218 | |
|
|
219 | =item $enabled = $cbor->get_pack_strings |
|
|
220 | |
|
|
221 | If C<$enable> is true (or missing), then C<encode> will try not to encode |
|
|
222 | the same string twice, but will instead encode a reference to the string |
|
|
223 | instead. Depending on your data format, this can save a lot of space, but |
|
|
224 | also results in a very large runtime overhead (expect encoding times to be |
|
|
225 | 2-4 times as high as without). |
|
|
226 | |
|
|
227 | It is recommended to leave it off unless you know your |
|
|
228 | communications partner supports the stringref extension to CBOR |
|
|
229 | (L<http://cbor.schmorp.de/stringref>), as without decoder support, the |
|
|
230 | resulting data structure might not be usable. |
|
|
231 | |
|
|
232 | If C<$enable> is false (the default), then C<encode> will encode strings |
|
|
233 | the standard CBOR way. |
|
|
234 | |
|
|
235 | This option does not affect C<decode> in any way - string references will |
|
|
236 | always be decoded properly if present. |
|
|
237 | |
|
|
238 | =item $cbor = $cbor->filter ([$cb->($tag, $value)]) |
|
|
239 | |
|
|
240 | =item $cb_or_undef = $cbor->get_filter |
|
|
241 | |
|
|
242 | Sets or replaces the tagged value decoding filter (when C<$cb> is |
|
|
243 | specified) or clears the filter (if no argument or C<undef> is provided). |
|
|
244 | |
|
|
245 | The filter callback is called only during decoding, when a non-enforced |
|
|
246 | tagged value has been decoded (see L<TAG HANDLING AND EXTENSIONS> for a |
|
|
247 | list of enforced tags). For specific tags, it's often better to provide a |
|
|
248 | default converter using the C<%CBOR::XS::FILTER> hash (see below). |
|
|
249 | |
|
|
250 | The first argument is the numerical tag, the second is the (decoded) value |
|
|
251 | that has been tagged. |
|
|
252 | |
|
|
253 | The filter function should return either exactly one value, which will |
|
|
254 | replace the tagged value in the decoded data structure, or no values, |
|
|
255 | which will result in default handling, which currently means the decoder |
|
|
256 | creates a C<CBOR::XS::Tagged> object to hold the tag and the value. |
|
|
257 | |
|
|
258 | When the filter is cleared (the default state), the default filter |
|
|
259 | 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 |
|
|
261 | 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. |
|
|
263 | |
|
|
264 | Example: decode all tags not handled internally into CBOR::XS::Tagged |
|
|
265 | objects, with no other special handling (useful when working with |
|
|
266 | potentially "unsafe" CBOR data). |
|
|
267 | |
|
|
268 | CBOR::XS->new->filter (sub { })->decode ($cbor_data); |
|
|
269 | |
|
|
270 | Example: provide a global filter for tag 1347375694, converting the value |
|
|
271 | into some string form. |
|
|
272 | |
|
|
273 | $CBOR::XS::FILTER{1347375694} = sub { |
|
|
274 | my ($tag, $value); |
|
|
275 | |
|
|
276 | "tag 1347375694 value $value" |
|
|
277 | }; |
|
|
278 | |
162 | =item $cbor_data = $cbor->encode ($perl_scalar) |
279 | =item $cbor_data = $cbor->encode ($perl_scalar) |
163 | |
280 | |
164 | Converts the given Perl data structure (a scalar value) to its CBOR |
281 | Converts the given Perl data structure (a scalar value) to its CBOR |
165 | representation. |
282 | representation. |
166 | |
283 | |
… | |
… | |
206 | CBOR integers become (numeric) perl scalars. On perls without 64 bit |
323 | CBOR integers become (numeric) perl scalars. On perls without 64 bit |
207 | support, 64 bit integers will be truncated or otherwise corrupted. |
324 | support, 64 bit integers will be truncated or otherwise corrupted. |
208 | |
325 | |
209 | =item byte strings |
326 | =item byte strings |
210 | |
327 | |
211 | Byte strings will become octet strings in Perl (the byte values 0..255 |
328 | Byte strings will become octet strings in Perl (the Byte values 0..255 |
212 | will simply become characters of the same value in Perl). |
329 | will simply become characters of the same value in Perl). |
213 | |
330 | |
214 | =item UTF-8 strings |
331 | =item UTF-8 strings |
215 | |
332 | |
216 | UTF-8 strings in CBOR will be decoded, i.e. the UTF-8 octets will be |
333 | UTF-8 strings in CBOR will be decoded, i.e. the UTF-8 octets will be |
… | |
… | |
234 | C<Types:Serialiser::false> and C<Types::Serialiser::error>, |
351 | C<Types:Serialiser::false> and C<Types::Serialiser::error>, |
235 | respectively. They are overloaded to act almost exactly like the numbers |
352 | respectively. They are overloaded to act almost exactly like the numbers |
236 | C<1> and C<0> (for true and false) or to throw an exception on access (for |
353 | C<1> and C<0> (for true and false) or to throw an exception on access (for |
237 | error). See the L<Types::Serialiser> manpage for details. |
354 | error). See the L<Types::Serialiser> manpage for details. |
238 | |
355 | |
239 | =item CBOR tag 256 (perl object) |
356 | =item tagged values |
240 | |
357 | |
241 | The tag value C<256> (TODO: pending iana registration) will be used |
|
|
242 | to deserialise a Perl object serialised with C<FREEZE>. See L<OBJECT |
|
|
243 | SERIALISATION>, below, for details. |
|
|
244 | |
|
|
245 | =item CBOR tag 55799 (magic header) |
|
|
246 | |
|
|
247 | The tag 55799 is ignored (this tag implements the magic header). |
|
|
248 | |
|
|
249 | =item other CBOR tags |
|
|
250 | |
|
|
251 | Tagged items consists of a numeric tag and another CBOR value. Tags not |
358 | Tagged items consists of a numeric tag and another CBOR value. |
252 | handled internally are currently converted into a L<CBOR::XS::Tagged> |
|
|
253 | object, which is simply a blessed array reference consisting of the |
|
|
254 | numeric tag value followed by the (decoded) CBOR value. |
|
|
255 | |
359 | |
256 | In the future, support for user-supplied conversions might get added. |
360 | See L<TAG HANDLING AND EXTENSIONS> and the description of C<< ->filter >> |
|
|
361 | for details. |
257 | |
362 | |
258 | =item anything else |
363 | =item anything else |
259 | |
364 | |
260 | Anything else (e.g. unsupported simple values) will raise a decoding |
365 | Anything else (e.g. unsupported simple values) will raise a decoding |
261 | error. |
366 | error. |
… | |
… | |
304 | if you want. |
409 | if you want. |
305 | |
410 | |
306 | =item other blessed objects |
411 | =item other blessed objects |
307 | |
412 | |
308 | Other blessed objects are serialised via C<TO_CBOR> or C<FREEZE>. See |
413 | Other blessed objects are serialised via C<TO_CBOR> or C<FREEZE>. See |
309 | L<OBJECT SERIALISATION>, below, for details. |
414 | L<TAG HANDLING AND EXTENSIONS> for specific classes handled by this |
|
|
415 | module, and L<OBJECT SERIALISATION> for generic object serialisation. |
310 | |
416 | |
311 | =item simple scalars |
417 | =item simple scalars |
312 | |
418 | |
313 | TODO |
|
|
314 | Simple Perl scalars (any scalar that is not a reference) are the most |
419 | Simple Perl scalars (any scalar that is not a reference) are the most |
315 | difficult objects to encode: CBOR::XS will encode undefined scalars as |
420 | difficult objects to encode: CBOR::XS will encode undefined scalars as |
316 | CBOR null values, scalars that have last been used in a string context |
421 | CBOR null values, scalars that have last been used in a string context |
317 | before encoding as CBOR strings, and anything else as number value: |
422 | before encoding as CBOR strings, and anything else as number value: |
318 | |
423 | |
319 | # dump as number |
424 | # dump as number |
320 | encode_cbor [2] # yields [2] |
425 | encode_cbor [2] # yields [2] |
321 | encode_cbor [-3.0e17] # yields [-3e+17] |
426 | encode_cbor [-3.0e17] # yields [-3e+17] |
322 | my $value = 5; encode_cbor [$value] # yields [5] |
427 | my $value = 5; encode_cbor [$value] # yields [5] |
323 | |
428 | |
324 | # used as string, so dump as string |
429 | # used as string, so dump as string (either byte or text) |
325 | print $value; |
430 | print $value; |
326 | encode_cbor [$value] # yields ["5"] |
431 | encode_cbor [$value] # yields ["5"] |
327 | |
432 | |
328 | # undef becomes null |
433 | # undef becomes null |
329 | encode_cbor [undef] # yields [null] |
434 | encode_cbor [undef] # yields [null] |
… | |
… | |
332 | |
437 | |
333 | my $x = 3.1; # some variable containing a number |
438 | my $x = 3.1; # some variable containing a number |
334 | "$x"; # stringified |
439 | "$x"; # stringified |
335 | $x .= ""; # another, more awkward way to stringify |
440 | $x .= ""; # another, more awkward way to stringify |
336 | print $x; # perl does it for you, too, quite often |
441 | print $x; # perl does it for you, too, quite often |
|
|
442 | |
|
|
443 | You can force whether a string ie encoded as byte or text string by using |
|
|
444 | C<utf8::upgrade> and C<utf8::downgrade>): |
|
|
445 | |
|
|
446 | utf8::upgrade $x; # encode $x as text string |
|
|
447 | utf8::downgrade $x; # encode $x as byte string |
|
|
448 | |
|
|
449 | 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 |
|
|
451 | your string as late as possible before encoding. |
337 | |
452 | |
338 | You can force the type to be a CBOR number by numifying it: |
453 | You can force the type to be a CBOR number by numifying it: |
339 | |
454 | |
340 | my $x = "3"; # some variable containing a string |
455 | my $x = "3"; # some variable containing a string |
341 | $x += 0; # numify it, ensuring it will be dumped as a number |
456 | $x += 0; # numify it, ensuring it will be dumped as a number |
… | |
… | |
455 | =head1 MAGIC HEADER |
570 | =head1 MAGIC HEADER |
456 | |
571 | |
457 | There is no way to distinguish CBOR from other formats |
572 | There is no way to distinguish CBOR from other formats |
458 | programmatically. To make it easier to distinguish CBOR from other |
573 | programmatically. To make it easier to distinguish CBOR from other |
459 | formats, the CBOR specification has a special "magic string" that can be |
574 | formats, the CBOR specification has a special "magic string" that can be |
460 | prepended to any CBOR string without changing it's meaning. |
575 | prepended to any CBOR string without changing its meaning. |
461 | |
576 | |
462 | This string is available as C<$CBOR::XS::MAGIC>. This module does not |
577 | This string is available as C<$CBOR::XS::MAGIC>. This module does not |
463 | prepend this string tot he CBOR data it generates, but it will ignroe it |
578 | prepend this string to the CBOR data it generates, but it will ignore it |
464 | if present, so users can prepend this string as a "file type" indicator as |
579 | if present, so users can prepend this string as a "file type" indicator as |
465 | required. |
580 | required. |
466 | |
581 | |
467 | |
582 | |
468 | =head1 THE CBOR::XS::Tagged CLASS |
583 | =head1 THE CBOR::XS::Tagged CLASS |
… | |
… | |
551 | Wrap CBOR data in CBOR: |
666 | Wrap CBOR data in CBOR: |
552 | |
667 | |
553 | my $cbor_cbor = encode_cbor |
668 | my $cbor_cbor = encode_cbor |
554 | CBOR::XS::tag 24, |
669 | CBOR::XS::tag 24, |
555 | encode_cbor [1, 2, 3]; |
670 | encode_cbor [1, 2, 3]; |
|
|
671 | |
|
|
672 | =head1 TAG HANDLING AND EXTENSIONS |
|
|
673 | |
|
|
674 | This section describes how this module handles specific tagged values |
|
|
675 | and extensions. If a tag is not mentioned here and no additional filters |
|
|
676 | are provided for it, then the default handling applies (creating a |
|
|
677 | CBOR::XS::Tagged object on decoding, and only encoding the tag when |
|
|
678 | explicitly requested). |
|
|
679 | |
|
|
680 | Tags not handled specifically are currently converted into a |
|
|
681 | L<CBOR::XS::Tagged> object, which is simply a blessed array reference |
|
|
682 | consisting of the numeric tag value followed by the (decoded) CBOR value. |
|
|
683 | |
|
|
684 | Future versions of this module reserve the right to special case |
|
|
685 | additional tags (such as base64url). |
|
|
686 | |
|
|
687 | =head2 ENFORCED TAGS |
|
|
688 | |
|
|
689 | These tags are always handled when decoding, and their handling cannot be |
|
|
690 | overriden by the user. |
|
|
691 | |
|
|
692 | =over 4 |
|
|
693 | |
|
|
694 | =item 26 (perl-object, L<http://cbor.schmorp.de/perl-object>) |
|
|
695 | |
|
|
696 | These tags are automatically created (and decoded) for serialisable |
|
|
697 | objects using the C<FREEZE/THAW> methods (the L<Types::Serialier> object |
|
|
698 | serialisation protocol). See L<OBJECT SERIALISATION> for details. |
|
|
699 | |
|
|
700 | =item 28, 29 (sharable, sharedref, L <http://cbor.schmorp.de/value-sharing>) |
|
|
701 | |
|
|
702 | These tags are automatically decoded when encountered, resulting in |
|
|
703 | shared values in the decoded object. They are only encoded, however, when |
|
|
704 | C<allow_sharable> is enabled. |
|
|
705 | |
|
|
706 | =item 256, 25 (stringref-namespace, stringref, L <http://cbor.schmorp.de/stringref>) |
|
|
707 | |
|
|
708 | These tags are automatically decoded when encountered. They are only |
|
|
709 | encoded, however, when C<pack_strings> is enabled. |
|
|
710 | |
|
|
711 | =item 22098 (indirection, L<http://cbor.schmorp.de/indirection>) |
|
|
712 | |
|
|
713 | 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 |
|
|
715 | when decoding. |
|
|
716 | |
|
|
717 | =item 55799 (self-describe CBOR, RFC 7049) |
|
|
718 | |
|
|
719 | This value is not generated on encoding (unless explicitly requested by |
|
|
720 | the user), and is simply ignored when decoding. |
|
|
721 | |
|
|
722 | =back |
|
|
723 | |
|
|
724 | =head2 NON-ENFORCED TAGS |
|
|
725 | |
|
|
726 | 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 |
|
|
728 | providing a custom C<filter> callback when decoding. |
|
|
729 | |
|
|
730 | When they result in decoding into a specific Perl class, the module |
|
|
731 | usually provides a corresponding C<TO_CBOR> method as well. |
|
|
732 | |
|
|
733 | When any of these need to load additional modules that are not part of the |
|
|
734 | perl core distribution (e.g. L<URI>), it is (currently) up to the user to |
|
|
735 | provide these modules. The decoding usually fails with an exception if the |
|
|
736 | required module cannot be loaded. |
|
|
737 | |
|
|
738 | =over 4 |
|
|
739 | |
|
|
740 | =item 2, 3 (positive/negative bignum) |
|
|
741 | |
|
|
742 | These tags are decoded into L<Math::BigInt> objects. The corresponding |
|
|
743 | C<Math::BigInt::TO_CBOR> method encodes "small" bigints into normal CBOR |
|
|
744 | integers, and others into positive/negative CBOR bignums. |
|
|
745 | |
|
|
746 | =item 4, 5 (decimal fraction/bigfloat) |
|
|
747 | |
|
|
748 | Both decimal fractions and bigfloats are decoded into L<Math::BigFloat> |
|
|
749 | objects. The corresponding C<Math::BigFloat::TO_CBOR> method I<always> |
|
|
750 | encodes into a decimal fraction. |
|
|
751 | |
|
|
752 | CBOR cannot represent bigfloats with I<very> large exponents - conversion |
|
|
753 | of such big float objects is undefined. |
|
|
754 | |
|
|
755 | Also, NaN and infinities are not encoded properly. |
|
|
756 | |
|
|
757 | =item 21, 22, 23 (expected later JSON conversion) |
|
|
758 | |
|
|
759 | CBOR::XS is not a CBOR-to-JSON converter, and will simply ignore these |
|
|
760 | tags. |
|
|
761 | |
|
|
762 | =item 32 (URI) |
|
|
763 | |
|
|
764 | These objects decode into L<URI> objects. The corresponding |
|
|
765 | C<URI::TO_CBOR> method again results in a CBOR URI value. |
|
|
766 | |
|
|
767 | =back |
|
|
768 | |
|
|
769 | =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 ($_[1][0], 2) |
|
|
793 | }, |
|
|
794 | |
|
|
795 | 21 => sub { pop }, # expected conversion to base64url encoding |
|
|
796 | 22 => sub { pop }, # expected conversion to base64 encoding |
|
|
797 | 23 => sub { pop }, # expected conversion to base16 encoding |
|
|
798 | |
|
|
799 | # 24 # embedded cbor, byte string |
|
|
800 | |
|
|
801 | 32 => sub { |
|
|
802 | require URI; |
|
|
803 | URI->new (pop) |
|
|
804 | }, |
|
|
805 | |
|
|
806 | # 33 # base64url rfc4648, utf-8 |
|
|
807 | # 34 # base64 rfc46484, utf-8 |
|
|
808 | # 35 # regex pcre/ecma262, utf-8 |
|
|
809 | # 36 # mime message rfc2045, utf-8 |
|
|
810 | ); |
|
|
811 | |
556 | |
812 | |
557 | =head1 CBOR and JSON |
813 | =head1 CBOR and JSON |
558 | |
814 | |
559 | CBOR is supposed to implement a superset of the JSON data model, and is, |
815 | CBOR is supposed to implement a superset of the JSON data model, and is, |
560 | with some coercion, able to represent all JSON texts (something that other |
816 | with some coercion, able to represent all JSON texts (something that other |
… | |
… | |
642 | Please refrain from using rt.cpan.org or any other bug reporting |
898 | Please refrain from using rt.cpan.org or any other bug reporting |
643 | service. I put the contact address into my modules for a reason. |
899 | service. I put the contact address into my modules for a reason. |
644 | |
900 | |
645 | =cut |
901 | =cut |
646 | |
902 | |
|
|
903 | our %FILTER = ( |
|
|
904 | # 0 # rfc4287 datetime, utf-8 |
|
|
905 | # 1 # unix timestamp, any |
|
|
906 | |
|
|
907 | 2 => sub { # pos bigint |
|
|
908 | require Math::BigInt; |
|
|
909 | Math::BigInt->new ("0x" . unpack "H*", pop) |
|
|
910 | }, |
|
|
911 | |
|
|
912 | 3 => sub { # neg bigint |
|
|
913 | require Math::BigInt; |
|
|
914 | -Math::BigInt->new ("0x" . unpack "H*", pop) |
|
|
915 | }, |
|
|
916 | |
|
|
917 | 4 => sub { # decimal fraction, array |
|
|
918 | require Math::BigFloat; |
|
|
919 | Math::BigFloat->new ($_[1][1] . "E" . $_[1][0]) |
|
|
920 | }, |
|
|
921 | |
|
|
922 | 5 => sub { # bigfloat, array |
|
|
923 | require Math::BigFloat; |
|
|
924 | scalar Math::BigFloat->new ($_[1][1])->blsft ($_[1][0], 2) |
|
|
925 | }, |
|
|
926 | |
|
|
927 | 21 => sub { pop }, # expected conversion to base64url encoding |
|
|
928 | 22 => sub { pop }, # expected conversion to base64 encoding |
|
|
929 | 23 => sub { pop }, # expected conversion to base16 encoding |
|
|
930 | |
|
|
931 | # 24 # embedded cbor, byte string |
|
|
932 | |
|
|
933 | 32 => sub { |
|
|
934 | require URI; |
|
|
935 | URI->new (pop) |
|
|
936 | }, |
|
|
937 | |
|
|
938 | # 33 # base64url rfc4648, utf-8 |
|
|
939 | # 34 # base64 rfc46484, utf-8 |
|
|
940 | # 35 # regex pcre/ecma262, utf-8 |
|
|
941 | # 36 # mime message rfc2045, utf-8 |
|
|
942 | ); |
|
|
943 | |
|
|
944 | sub CBOR::XS::default_filter { |
|
|
945 | &{ $FILTER{$_[0]} or return } |
|
|
946 | } |
|
|
947 | |
|
|
948 | sub URI::TO_CBOR { |
|
|
949 | my $uri = $_[0]->as_string; |
|
|
950 | utf8::upgrade $uri; |
|
|
951 | CBOR::XS::tag 32, $uri |
|
|
952 | } |
|
|
953 | |
|
|
954 | sub Math::BigInt::TO_CBOR { |
|
|
955 | if ($_[0] >= -2147483648 && $_[0] <= 2147483647) { |
|
|
956 | $_[0]->numify |
|
|
957 | } else { |
|
|
958 | my $hex = substr $_[0]->as_hex, 2; |
|
|
959 | $hex = "0$hex" if 1 & length $hex; # sigh |
|
|
960 | CBOR::XS::tag $_[0] >= 0 ? 2 : 3, pack "H*", $hex |
|
|
961 | } |
|
|
962 | } |
|
|
963 | |
|
|
964 | sub Math::BigFloat::TO_CBOR { |
|
|
965 | my ($m, $e) = $_[0]->parts; |
|
|
966 | CBOR::XS::tag 4, [$e->numify, $m] |
|
|
967 | } |
|
|
968 | |
647 | XSLoader::load "CBOR::XS", $VERSION; |
969 | XSLoader::load "CBOR::XS", $VERSION; |
648 | |
970 | |
649 | =head1 SEE ALSO |
971 | =head1 SEE ALSO |
650 | |
972 | |
651 | The L<JSON> and L<JSON::XS> modules that do similar, but human-readable, |
973 | The L<JSON> and L<JSON::XS> modules that do similar, but human-readable, |