… | |
… | |
71 | |
71 | |
72 | package CBOR::XS; |
72 | package CBOR::XS; |
73 | |
73 | |
74 | use common::sense; |
74 | use common::sense; |
75 | |
75 | |
76 | our $VERSION = 0.08; |
76 | our $VERSION = 0.09; |
77 | our @ISA = qw(Exporter); |
77 | our @ISA = qw(Exporter); |
78 | |
78 | |
79 | our @EXPORT = qw(encode_cbor decode_cbor); |
79 | our @EXPORT = qw(encode_cbor decode_cbor); |
80 | |
80 | |
81 | use Exporter; |
81 | use Exporter; |
… | |
… | |
118 | strings. All boolean flags described below are by default I<disabled>. |
118 | strings. All boolean flags described below are by default I<disabled>. |
119 | |
119 | |
120 | 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 |
121 | be chained: |
121 | be chained: |
122 | |
122 | |
123 | #TODO |
|
|
124 | my $cbor = CBOR::XS->new->encode ({a => [1,2]}); |
123 | my $cbor = CBOR::XS->new->encode ({a => [1,2]}); |
125 | |
124 | |
126 | =item $cbor = $cbor->max_depth ([$maximum_nesting_depth]) |
125 | =item $cbor = $cbor->max_depth ([$maximum_nesting_depth]) |
127 | |
126 | |
128 | =item $max_depth = $cbor->get_max_depth |
127 | =item $max_depth = $cbor->get_max_depth |
… | |
… | |
230 | exception when it encounters anything it cannot encode as CBOR. |
229 | exception when it encounters anything it cannot encode as CBOR. |
231 | |
230 | |
232 | This option does not affect C<decode> in any way - string references will |
231 | This option does not affect C<decode> in any way - string references will |
233 | always be decoded properly if present. |
232 | always be decoded properly if present. |
234 | |
233 | |
|
|
234 | =item $cbor = $cbor->filter ([$cb->($tag, $value)]) |
|
|
235 | |
|
|
236 | =item $cb_or_undef = $cbor->get_filter |
|
|
237 | |
|
|
238 | Sets or replaces the tagged value decoding filter (when C<$cb> is |
|
|
239 | specified) or clears the filter (if no argument or C<undef> is provided). |
|
|
240 | |
|
|
241 | The filter callback is called only during decoding, when a non-enforced |
|
|
242 | tagged value has been decoded (see L<TAG HANDLING AND EXTENSIONS> for a |
|
|
243 | list of enforced tags). For specific tags, it's often better to provide a |
|
|
244 | default converter using the C<%CBOR::XS::FILTER> hash (see below). |
|
|
245 | |
|
|
246 | The first argument is the numerical tag, the second is the (decoded) value |
|
|
247 | that has been tagged. |
|
|
248 | |
|
|
249 | The filter function should return either exactly one value, which will |
|
|
250 | replace the tagged value in the decoded data structure, or no values, |
|
|
251 | which will result in default handling, which currently means the decoder |
|
|
252 | creates a C<CBOR::XS::Tagged> object to hold the tag and the value. |
|
|
253 | |
|
|
254 | When the filter is cleared (the default state), the default filter |
|
|
255 | function, C<CBOR::XS::default_filter>, is used. This function simply looks |
|
|
256 | up the tag in the C<%CBOR::XS::FILTER> hash. If an entry exists it must be |
|
|
257 | a code reference that is called with tag and value, and is responsible for |
|
|
258 | decoding the value. If no entry exists, it returns no values. |
|
|
259 | |
|
|
260 | Example: decode all tags not handled internally into CBOR::XS::Tagged |
|
|
261 | objects, with no other special handling (useful when working with |
|
|
262 | potentially "unsafe" CBOR data). |
|
|
263 | |
|
|
264 | CBOR::XS->new->filter (sub { })->decode ($cbor_data); |
|
|
265 | |
|
|
266 | Example: provide a global filter for tag 1347375694, converting the value |
|
|
267 | into some string form. |
|
|
268 | |
|
|
269 | $CBOR::XS::FILTER{1347375694} = sub { |
|
|
270 | my ($tag, $value); |
|
|
271 | |
|
|
272 | "tag 1347375694 value $value" |
|
|
273 | }; |
|
|
274 | |
235 | =item $cbor_data = $cbor->encode ($perl_scalar) |
275 | =item $cbor_data = $cbor->encode ($perl_scalar) |
236 | |
276 | |
237 | Converts the given Perl data structure (a scalar value) to its CBOR |
277 | Converts the given Perl data structure (a scalar value) to its CBOR |
238 | representation. |
278 | representation. |
239 | |
279 | |
… | |
… | |
307 | C<Types:Serialiser::false> and C<Types::Serialiser::error>, |
347 | C<Types:Serialiser::false> and C<Types::Serialiser::error>, |
308 | respectively. They are overloaded to act almost exactly like the numbers |
348 | respectively. They are overloaded to act almost exactly like the numbers |
309 | C<1> and C<0> (for true and false) or to throw an exception on access (for |
349 | C<1> and C<0> (for true and false) or to throw an exception on access (for |
310 | error). See the L<Types::Serialiser> manpage for details. |
350 | error). See the L<Types::Serialiser> manpage for details. |
311 | |
351 | |
312 | =item CBOR tag 256 (perl object) |
352 | =item tagged values |
313 | |
353 | |
314 | The tag value C<256> (TODO: pending iana registration) will be used |
|
|
315 | to deserialise a Perl object serialised with C<FREEZE>. See L<OBJECT |
|
|
316 | SERIALISATION>, below, for details. |
|
|
317 | |
|
|
318 | =item CBOR tag 55799 (magic header) |
|
|
319 | |
|
|
320 | The tag 55799 is ignored (this tag implements the magic header). |
|
|
321 | |
|
|
322 | =item other CBOR tags |
|
|
323 | |
|
|
324 | Tagged items consists of a numeric tag and another CBOR value. Tags not |
354 | Tagged items consists of a numeric tag and another CBOR value. |
325 | handled internally are currently converted into a L<CBOR::XS::Tagged> |
|
|
326 | object, which is simply a blessed array reference consisting of the |
|
|
327 | numeric tag value followed by the (decoded) CBOR value. |
|
|
328 | |
355 | |
329 | In the future, support for user-supplied conversions might get added. |
356 | See L<TAG HANDLING AND EXTENSIONS> and the description of C<< ->filter >> |
|
|
357 | for details. |
330 | |
358 | |
331 | =item anything else |
359 | =item anything else |
332 | |
360 | |
333 | Anything else (e.g. unsupported simple values) will raise a decoding |
361 | Anything else (e.g. unsupported simple values) will raise a decoding |
334 | error. |
362 | error. |
… | |
… | |
377 | if you want. |
405 | if you want. |
378 | |
406 | |
379 | =item other blessed objects |
407 | =item other blessed objects |
380 | |
408 | |
381 | Other blessed objects are serialised via C<TO_CBOR> or C<FREEZE>. See |
409 | Other blessed objects are serialised via C<TO_CBOR> or C<FREEZE>. See |
382 | L<OBJECT SERIALISATION>, below, for details. |
410 | L<TAG HANDLING AND EXTENSIONS> for specific classes handled by this |
|
|
411 | module, and L<OBJECT SERIALISATION> for generic object serialisation. |
383 | |
412 | |
384 | =item simple scalars |
413 | =item simple scalars |
385 | |
414 | |
386 | TODO |
|
|
387 | Simple Perl scalars (any scalar that is not a reference) are the most |
415 | Simple Perl scalars (any scalar that is not a reference) are the most |
388 | difficult objects to encode: CBOR::XS will encode undefined scalars as |
416 | difficult objects to encode: CBOR::XS will encode undefined scalars as |
389 | CBOR null values, scalars that have last been used in a string context |
417 | CBOR null values, scalars that have last been used in a string context |
390 | before encoding as CBOR strings, and anything else as number value: |
418 | before encoding as CBOR strings, and anything else as number value: |
391 | |
419 | |
… | |
… | |
627 | CBOR::XS::tag 24, |
655 | CBOR::XS::tag 24, |
628 | encode_cbor [1, 2, 3]; |
656 | encode_cbor [1, 2, 3]; |
629 | |
657 | |
630 | =head1 TAG HANDLING AND EXTENSIONS |
658 | =head1 TAG HANDLING AND EXTENSIONS |
631 | |
659 | |
632 | This section describes how this module handles specific tagged values and |
660 | This section describes how this module handles specific tagged values |
633 | extensions. If a tag is not mentioned here, then the default handling |
661 | and extensions. If a tag is not mentioned here and no additional filters |
|
|
662 | are provided for it, then the default handling applies (creating a |
634 | applies (creating a CBOR::XS::Tagged object on decoding, and only encoding |
663 | CBOR::XS::Tagged object on decoding, and only encoding the tag when |
635 | the tag when explicitly requested). |
664 | explicitly requested). |
|
|
665 | |
|
|
666 | Tags not handled specifically are currently converted into a |
|
|
667 | L<CBOR::XS::Tagged> object, which is simply a blessed array reference |
|
|
668 | consisting of the numeric tag value followed by the (decoded) CBOR value. |
636 | |
669 | |
637 | Future versions of this module reserve the right to special case |
670 | Future versions of this module reserve the right to special case |
638 | additional tags (such as bigfloat or base64url). |
671 | additional tags (such as base64url). |
|
|
672 | |
|
|
673 | =head2 ENFORCED TAGS |
|
|
674 | |
|
|
675 | These tags are always handled when decoding, and their handling cannot be |
|
|
676 | overriden by the user. |
639 | |
677 | |
640 | =over 4 |
678 | =over 4 |
641 | |
679 | |
642 | =item <unassigned> (perl-object, L<http://cbor.schmorp.de/perl-object>) |
680 | =item <unassigned> (perl-object, L<http://cbor.schmorp.de/perl-object>) |
643 | |
681 | |
644 | These tags are automatically created for serialisable objects using the |
682 | These tags are automatically created (and decoded) for serialisable |
645 | C<FREEZE/THAW> methods (the L<Types::Serialier> object serialisation |
683 | objects using the C<FREEZE/THAW> methods (the L<Types::Serialier> object |
646 | protocol). |
684 | serialisation protocol). See L<OBJECT SERIALISATION> for details. |
647 | |
685 | |
648 | =item <unassigned>, <unassigned> (sharable, sharedref, L <http://cbor.schmorp.de/value-sharing>) |
686 | =item <unassigned>, <unassigned> (sharable, sharedref, L <http://cbor.schmorp.de/value-sharing>) |
649 | |
687 | |
650 | These tags are automatically decoded when encountered, resulting in |
688 | These tags are automatically decoded when encountered, resulting in |
651 | shared values in the decoded object. They are only encoded, however, when |
689 | shared values in the decoded object. They are only encoded, however, when |
… | |
… | |
666 | |
704 | |
667 | This value is not generated on encoding (unless explicitly requested by |
705 | This value is not generated on encoding (unless explicitly requested by |
668 | the user), and is simply ignored when decoding. |
706 | the user), and is simply ignored when decoding. |
669 | |
707 | |
670 | =back |
708 | =back |
|
|
709 | |
|
|
710 | =head2 NON-ENFORCED TAGS |
|
|
711 | |
|
|
712 | These tags have default filters provided when decoding. Their handling can |
|
|
713 | be overriden by changing the C<%CBOR::XS::FILTER> entry for the tag, or by |
|
|
714 | providing a custom C<filter> callback when decoding. |
|
|
715 | |
|
|
716 | When they result in decoding into a specific Perl class, the module |
|
|
717 | usually provides a corresponding C<TO_CBOR> method as well. |
|
|
718 | |
|
|
719 | When any of these need to load additional modules that are not part of the |
|
|
720 | perl core distribution (e.g. L<URI>), it is (currently) up to the user to |
|
|
721 | provide these modules. The decoding usually fails with an exception if the |
|
|
722 | required module cannot be loaded. |
|
|
723 | |
|
|
724 | =over 4 |
|
|
725 | |
|
|
726 | =item 2, 3 (positive/negative bignum) |
|
|
727 | |
|
|
728 | These tags are decoded into L<Math::BigInt> objects. The corresponding |
|
|
729 | C<Math::BigInt::TO_CBOR> method encodes "small" bigints into normal CBOR |
|
|
730 | integers, and others into positive/negative CBOR bignums. |
|
|
731 | |
|
|
732 | =item 4, 5 (decimal fraction/bigfloat) |
|
|
733 | |
|
|
734 | Both decimal fractions and bigfloats are decoded into L<Math::BigFloat> |
|
|
735 | objects. The corresponding C<Math::BigFloat::TO_CBOR> method I<always> |
|
|
736 | encodes into a decimal fraction. |
|
|
737 | |
|
|
738 | CBOR cannot represent bigfloats with I<very> large exponents - conversion |
|
|
739 | of such big float objects is undefined. |
|
|
740 | |
|
|
741 | Also, NaN and infinities are not encoded properly. |
|
|
742 | |
|
|
743 | =item 21, 22, 23 (expected later JSON conversion) |
|
|
744 | |
|
|
745 | CBOR::XS is not a CBOR-to-JSON converter, and will simply ignore these |
|
|
746 | tags. |
|
|
747 | |
|
|
748 | =item 32 (URI) |
|
|
749 | |
|
|
750 | These objects decode into L<URI> objects. The corresponding |
|
|
751 | C<URI::TO_CBOR> method again results in a CBOR URI value. |
|
|
752 | |
|
|
753 | =back |
|
|
754 | |
|
|
755 | =cut |
|
|
756 | |
|
|
757 | our %FILTER = ( |
|
|
758 | # 0 # rfc4287 datetime, utf-8 |
|
|
759 | # 1 # unix timestamp, any |
|
|
760 | |
|
|
761 | 2 => sub { # pos bigint |
|
|
762 | require Math::BigInt; |
|
|
763 | Math::BigInt->new ("0x" . unpack "H*", pop) |
|
|
764 | }, |
|
|
765 | |
|
|
766 | 3 => sub { # neg bigint |
|
|
767 | require Math::BigInt; |
|
|
768 | -Math::BigInt->new ("0x" . unpack "H*", pop) |
|
|
769 | }, |
|
|
770 | |
|
|
771 | 4 => sub { # decimal fraction, array |
|
|
772 | require Math::BigFloat; |
|
|
773 | Math::BigFloat->new ($_[1][1] . "E" . $_[1][0]) |
|
|
774 | }, |
|
|
775 | |
|
|
776 | 5 => sub { # bigfloat, array |
|
|
777 | require Math::BigFloat; |
|
|
778 | scalar Math::BigFloat->new ($_[1][1])->blsft ($_[1][0], 2) |
|
|
779 | }, |
|
|
780 | |
|
|
781 | 21 => sub { pop }, # expected conversion to base64url encoding |
|
|
782 | 22 => sub { pop }, # expected conversion to base64 encoding |
|
|
783 | 23 => sub { pop }, # expected conversion to base16 encoding |
|
|
784 | |
|
|
785 | # 24 # embedded cbor, byte string |
|
|
786 | |
|
|
787 | 32 => sub { |
|
|
788 | require URI; |
|
|
789 | URI->new (pop) |
|
|
790 | }, |
|
|
791 | |
|
|
792 | # 33 # base64url rfc4648, utf-8 |
|
|
793 | # 34 # base64 rfc46484, utf-8 |
|
|
794 | # 35 # regex pcre/ecma262, utf-8 |
|
|
795 | # 36 # mime message rfc2045, utf-8 |
|
|
796 | ); |
671 | |
797 | |
672 | |
798 | |
673 | =head1 CBOR and JSON |
799 | =head1 CBOR and JSON |
674 | |
800 | |
675 | CBOR is supposed to implement a superset of the JSON data model, and is, |
801 | CBOR is supposed to implement a superset of the JSON data model, and is, |
… | |
… | |
758 | Please refrain from using rt.cpan.org or any other bug reporting |
884 | Please refrain from using rt.cpan.org or any other bug reporting |
759 | service. I put the contact address into my modules for a reason. |
885 | service. I put the contact address into my modules for a reason. |
760 | |
886 | |
761 | =cut |
887 | =cut |
762 | |
888 | |
|
|
889 | our %FILTER = ( |
|
|
890 | # 0 # rfc4287 datetime, utf-8 |
|
|
891 | # 1 # unix timestamp, any |
|
|
892 | |
|
|
893 | 2 => sub { # pos bigint |
|
|
894 | require Math::BigInt; |
|
|
895 | Math::BigInt->new ("0x" . unpack "H*", pop) |
|
|
896 | }, |
|
|
897 | |
|
|
898 | 3 => sub { # neg bigint |
|
|
899 | require Math::BigInt; |
|
|
900 | -Math::BigInt->new ("0x" . unpack "H*", pop) |
|
|
901 | }, |
|
|
902 | |
|
|
903 | 4 => sub { # decimal fraction, array |
|
|
904 | require Math::BigFloat; |
|
|
905 | Math::BigFloat->new ($_[1][1] . "E" . $_[1][0]) |
|
|
906 | }, |
|
|
907 | |
|
|
908 | 5 => sub { # bigfloat, array |
|
|
909 | require Math::BigFloat; |
|
|
910 | scalar Math::BigFloat->new ($_[1][1])->blsft ($_[1][0], 2) |
|
|
911 | }, |
|
|
912 | |
|
|
913 | 21 => sub { pop }, # expected conversion to base64url encoding |
|
|
914 | 22 => sub { pop }, # expected conversion to base64 encoding |
|
|
915 | 23 => sub { pop }, # expected conversion to base16 encoding |
|
|
916 | |
|
|
917 | # 24 # embedded cbor, byte string |
|
|
918 | |
|
|
919 | 32 => sub { |
|
|
920 | require URI; |
|
|
921 | URI->new (pop) |
|
|
922 | }, |
|
|
923 | |
|
|
924 | # 33 # base64url rfc4648, utf-8 |
|
|
925 | # 34 # base64 rfc46484, utf-8 |
|
|
926 | # 35 # regex pcre/ecma262, utf-8 |
|
|
927 | # 36 # mime message rfc2045, utf-8 |
|
|
928 | ); |
|
|
929 | |
|
|
930 | sub CBOR::XS::default_filter { |
|
|
931 | &{ $FILTER{$_[0]} or return } |
|
|
932 | } |
|
|
933 | |
|
|
934 | sub URI::TO_CBOR { |
|
|
935 | my $uri = $_[0]->as_string; |
|
|
936 | utf8::upgrade $uri; |
|
|
937 | CBOR::XS::tag 32, $uri |
|
|
938 | } |
|
|
939 | |
|
|
940 | sub Math::BigInt::TO_CBOR { |
|
|
941 | if ($_[0] >= -2147483648 && $_[0] <= 2147483647) { |
|
|
942 | $_[0]->numify |
|
|
943 | } else { |
|
|
944 | my $hex = substr $_[0]->as_hex, 2; |
|
|
945 | $hex = "0$hex" if 1 & length $hex; # sigh |
|
|
946 | CBOR::XS::tag $_[0] >= 0 ? 2 : 3, pack "H*", $hex |
|
|
947 | } |
|
|
948 | } |
|
|
949 | |
|
|
950 | sub Math::BigFloat::TO_CBOR { |
|
|
951 | my ($m, $e) = $_[0]->parts; |
|
|
952 | CBOR::XS::tag 4, [$e->numify, $m] |
|
|
953 | } |
|
|
954 | |
763 | XSLoader::load "CBOR::XS", $VERSION; |
955 | XSLoader::load "CBOR::XS", $VERSION; |
764 | |
956 | |
765 | =head1 SEE ALSO |
957 | =head1 SEE ALSO |
766 | |
958 | |
767 | The L<JSON> and L<JSON::XS> modules that do similar, but human-readable, |
959 | The L<JSON> and L<JSON::XS> modules that do similar, but human-readable, |