… | |
… | |
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<allow_stringref>) 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 = 0.07; |
76 | our $VERSION = 0.08; |
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; |
… | |
… | |
156 | |
161 | |
157 | If no argument is given, the limit check will be deactivated (same as when |
162 | If no argument is given, the limit check will be deactivated (same as when |
158 | C<0> is specified). |
163 | C<0> is specified). |
159 | |
164 | |
160 | See SECURITY CONSIDERATIONS, below, for more info on why this is useful. |
165 | See SECURITY CONSIDERATIONS, below, for more info on why this is useful. |
|
|
166 | |
|
|
167 | =item $cbor = $cbor->allow_unknown ([$enable]) |
|
|
168 | |
|
|
169 | =item $enabled = $cbor->get_allow_unknown |
|
|
170 | |
|
|
171 | If C<$enable> is true (or missing), then C<encode> will I<not> throw an |
|
|
172 | exception when it encounters values it cannot represent in CBOR (for |
|
|
173 | example, filehandles) but instead will encode a CBOR C<error> value. |
|
|
174 | |
|
|
175 | If C<$enable> is false (the default), then C<encode> will throw an |
|
|
176 | exception when it encounters anything it cannot encode as CBOR. |
|
|
177 | |
|
|
178 | This option does not affect C<decode> in any way, and it is recommended to |
|
|
179 | leave it off unless you know your communications partner. |
|
|
180 | |
|
|
181 | =item $cbor = $cbor->allow_sharing ([$enable]) |
|
|
182 | |
|
|
183 | =item $enabled = $cbor->get_allow_sharing |
|
|
184 | |
|
|
185 | If C<$enable> is true (or missing), then C<encode> will not double-encode |
|
|
186 | values that have been referenced before (e.g. when the same object, such |
|
|
187 | as an array, is referenced multiple times), but instead will emit a |
|
|
188 | reference to the earlier value. |
|
|
189 | |
|
|
190 | This means that such values will only be encoded once, and will not result |
|
|
191 | in a deep cloning of the value on decode, in decoders supporting the value |
|
|
192 | sharing extension. |
|
|
193 | |
|
|
194 | It is recommended to leave it off unless you know your |
|
|
195 | communication partner supports the value sharing extensions to CBOR |
|
|
196 | (http://cbor.schmorp.de/value-sharing). |
|
|
197 | |
|
|
198 | Detecting shared values incurs a runtime overhead when values are encoded |
|
|
199 | that have a reference counter large than one, and might unnecessarily |
|
|
200 | increase the encoded size, as potentially shared values are encode as |
|
|
201 | sharable whether or not they are actually shared. |
|
|
202 | |
|
|
203 | At the moment, only targets of references can be shared (e.g. scalars, |
|
|
204 | arrays or hashes pointed to by a reference). Weirder constructs, such as |
|
|
205 | an array with multiple "copies" of the I<same> string, which are hard but |
|
|
206 | not impossible to create in Perl, are not supported (this is the same as |
|
|
207 | for L<Storable>). |
|
|
208 | |
|
|
209 | If C<$enable> is false (the default), then C<encode> will encode |
|
|
210 | exception when it encounters anything it cannot encode as CBOR. |
|
|
211 | |
|
|
212 | This option does not affect C<decode> in any way - shared values and |
|
|
213 | references will always be decoded properly if present. |
|
|
214 | |
|
|
215 | =item $cbor = $cbor->allow_stringref ([$enable]) |
|
|
216 | |
|
|
217 | =item $enabled = $cbor->get_allow_stringref |
|
|
218 | |
|
|
219 | If C<$enable> is true (or missing), then C<encode> will try not to encode |
|
|
220 | the same string twice, but will instead encode a reference to the string |
|
|
221 | instead. Depending on your data format. this can save a lot of space, but |
|
|
222 | also results in a very large runtime overhead (expect encoding times to be |
|
|
223 | 2-4 times as high as without). |
|
|
224 | |
|
|
225 | It is recommended to leave it off unless you know your |
|
|
226 | communications partner supports the stringref extension to CBOR |
|
|
227 | (http://cbor.schmorp.de/stringref). |
|
|
228 | |
|
|
229 | If C<$enable> is false (the default), then C<encode> will encode |
|
|
230 | exception when it encounters anything it cannot encode as CBOR. |
|
|
231 | |
|
|
232 | This option does not affect C<decode> in any way - string references will |
|
|
233 | always be decoded properly if present. |
161 | |
234 | |
162 | =item $cbor_data = $cbor->encode ($perl_scalar) |
235 | =item $cbor_data = $cbor->encode ($perl_scalar) |
163 | |
236 | |
164 | Converts the given Perl data structure (a scalar value) to its CBOR |
237 | Converts the given Perl data structure (a scalar value) to its CBOR |
165 | representation. |
238 | representation. |
… | |
… | |
455 | =head1 MAGIC HEADER |
528 | =head1 MAGIC HEADER |
456 | |
529 | |
457 | There is no way to distinguish CBOR from other formats |
530 | There is no way to distinguish CBOR from other formats |
458 | programmatically. To make it easier to distinguish CBOR from other |
531 | programmatically. To make it easier to distinguish CBOR from other |
459 | formats, the CBOR specification has a special "magic string" that can be |
532 | formats, the CBOR specification has a special "magic string" that can be |
460 | prepended to any CBOR string without changing it's meaning. |
533 | prepended to any CBOR string without changing its meaning. |
461 | |
534 | |
462 | This string is available as C<$CBOR::XS::MAGIC>. This module does not |
535 | This string is available as C<$CBOR::XS::MAGIC>. This module does not |
463 | prepend this string tot he CBOR data it generates, but it will ignroe it |
536 | 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 |
537 | if present, so users can prepend this string as a "file type" indicator as |
465 | required. |
538 | required. |
466 | |
539 | |
467 | |
540 | |
468 | =head1 THE CBOR::XS::Tagged CLASS |
541 | =head1 THE CBOR::XS::Tagged CLASS |
… | |
… | |
551 | Wrap CBOR data in CBOR: |
624 | Wrap CBOR data in CBOR: |
552 | |
625 | |
553 | my $cbor_cbor = encode_cbor |
626 | my $cbor_cbor = encode_cbor |
554 | CBOR::XS::tag 24, |
627 | CBOR::XS::tag 24, |
555 | encode_cbor [1, 2, 3]; |
628 | encode_cbor [1, 2, 3]; |
|
|
629 | |
|
|
630 | =head1 TAG HANDLING AND EXTENSIONS |
|
|
631 | |
|
|
632 | This section describes how this module handles specific tagged values |
|
|
633 | and extensions. If a tag is not mentioned here and no additional filters |
|
|
634 | are provided for it, then the default handling applies (creating a |
|
|
635 | CBOR::XS::Tagged object on decoding, and only encoding the tag when |
|
|
636 | explicitly requested). |
|
|
637 | |
|
|
638 | Future versions of this module reserve the right to special case |
|
|
639 | additional tags (such as base64url). |
|
|
640 | |
|
|
641 | =head2 ENFORCED TAGS |
|
|
642 | |
|
|
643 | These tags are always handled when decoding, and their handling cannot be |
|
|
644 | overriden by the user. |
|
|
645 | |
|
|
646 | =over 4 |
|
|
647 | |
|
|
648 | =item <unassigned> (perl-object, L<http://cbor.schmorp.de/perl-object>) |
|
|
649 | |
|
|
650 | These tags are automatically created for serialisable objects using the |
|
|
651 | C<FREEZE/THAW> methods (the L<Types::Serialier> object serialisation |
|
|
652 | protocol). |
|
|
653 | |
|
|
654 | =item <unassigned>, <unassigned> (sharable, sharedref, L <http://cbor.schmorp.de/value-sharing>) |
|
|
655 | |
|
|
656 | These tags are automatically decoded when encountered, resulting in |
|
|
657 | shared values in the decoded object. They are only encoded, however, when |
|
|
658 | C<allow_sharable> is enabled. |
|
|
659 | |
|
|
660 | =item <unassigned>, <unassigned> (stringref-namespace, stringref, L <http://cbor.schmorp.de/stringref>) |
|
|
661 | |
|
|
662 | These tags are automatically decoded when encountered. They are only |
|
|
663 | encoded, however, when C<allow_stringref> is enabled. |
|
|
664 | |
|
|
665 | =item 22098 (indirection, L<http://cbor.schmorp.de/indirection>) |
|
|
666 | |
|
|
667 | This tag is automatically generated when a reference are encountered (with |
|
|
668 | the exception of hash and array refernces). It is converted to a reference |
|
|
669 | when decoding. |
|
|
670 | |
|
|
671 | =item 55799 (self-describe CBOR, RFC 7049) |
|
|
672 | |
|
|
673 | This value is not generated on encoding (unless explicitly requested by |
|
|
674 | the user), and is simply ignored when decoding. |
|
|
675 | |
|
|
676 | =back |
|
|
677 | |
|
|
678 | =head2 OPTIONAL TAGS |
|
|
679 | |
|
|
680 | These tags have default filters provided when decoding. Their handling can |
|
|
681 | be overriden by changing the C<%CBOR::XS::FILTER> entry for the tag, or by |
|
|
682 | providing a custom C<filter> function when decoding. |
|
|
683 | |
|
|
684 | When they result in decoding into a specific Perl class, the module |
|
|
685 | usually provides a corresponding C<TO_CBOR> method as well. |
|
|
686 | |
|
|
687 | When any of these need to load additional modules that are not part of the |
|
|
688 | perl core distribution (e.g. L<URI>), it is (currently) up to the user to |
|
|
689 | provide these modules. The decoding usually fails with an exception if the |
|
|
690 | required module cannot be loaded. |
|
|
691 | |
|
|
692 | =over 4 |
|
|
693 | |
|
|
694 | =item 2, 3 (positive/negative bignum) |
|
|
695 | |
|
|
696 | These tags are decoded into L<Math::BigInt> objects. The corresponding |
|
|
697 | C<Math::BigInt::TO_CBOR> method encodes "small" bigints into normal CBOR |
|
|
698 | integers, and others into positive/negative CBOR bignums. |
|
|
699 | |
|
|
700 | =item 4, 5 (decimal fraction/bigfloat) |
|
|
701 | |
|
|
702 | Both decimal fractions and bigfloats are decoded into L<Math::BigFloat> |
|
|
703 | objects. The corresponding C<Math::BigFloat::TO_CBOR> method I<always> |
|
|
704 | encodes into a decimal fraction. |
|
|
705 | |
|
|
706 | CBOR cannot represent bigfloats with I<very> large exponents - conversion |
|
|
707 | of such big float objects is undefined. |
|
|
708 | |
|
|
709 | Also, NaN and infinities are not encoded properly. |
|
|
710 | |
|
|
711 | =item 21, 22, 23 (expected later JSON conversion) |
|
|
712 | |
|
|
713 | CBOR::XS is not a CBOR-to-JSON converter, and will simply ignore these |
|
|
714 | tags. |
|
|
715 | |
|
|
716 | =item 32 (URI) |
|
|
717 | |
|
|
718 | These objects decode into L<URI> objects. The corresponding |
|
|
719 | C<URI::TO_CBOR> method again results in a CBOR URI value. |
|
|
720 | |
|
|
721 | =back |
|
|
722 | |
|
|
723 | =cut |
|
|
724 | |
|
|
725 | our %FILTER = ( |
|
|
726 | # 0 # rfc4287 datetime, utf-8 |
|
|
727 | # 1 # unix timestamp, any |
|
|
728 | |
|
|
729 | 2 => sub { # pos bigint |
|
|
730 | require Math::BigInt; |
|
|
731 | Math::BigInt->new ("0x" . unpack "H*", pop) |
|
|
732 | }, |
|
|
733 | |
|
|
734 | 3 => sub { # neg bigint |
|
|
735 | require Math::BigInt; |
|
|
736 | -Math::BigInt->new ("0x" . unpack "H*", pop) |
|
|
737 | }, |
|
|
738 | |
|
|
739 | 4 => sub { # decimal fraction, array |
|
|
740 | require Math::BigFloat; |
|
|
741 | Math::BigFloat->new ($_[1][1] . "E" . $_[1][0]) |
|
|
742 | }, |
|
|
743 | |
|
|
744 | 5 => sub { # bigfloat, array |
|
|
745 | require Math::BigFloat; |
|
|
746 | scalar Math::BigFloat->new ($_[1][1])->blsft ($_[1][0], 2) |
|
|
747 | }, |
|
|
748 | |
|
|
749 | 21 => sub { pop }, # expected conversion to base64url encoding |
|
|
750 | 22 => sub { pop }, # expected conversion to base64 encoding |
|
|
751 | 23 => sub { pop }, # expected conversion to base16 encoding |
|
|
752 | |
|
|
753 | # 24 # embedded cbor, byte string |
|
|
754 | |
|
|
755 | 32 => sub { |
|
|
756 | require URI; |
|
|
757 | URI->new (pop) |
|
|
758 | }, |
|
|
759 | |
|
|
760 | # 33 # base64url rfc4648, utf-8 |
|
|
761 | # 34 # base64 rfc46484, utf-8 |
|
|
762 | # 35 # regex pcre/ecma262, utf-8 |
|
|
763 | # 36 # mime message rfc2045, utf-8 |
|
|
764 | ); |
|
|
765 | |
556 | |
766 | |
557 | =head1 CBOR and JSON |
767 | =head1 CBOR and JSON |
558 | |
768 | |
559 | CBOR is supposed to implement a superset of the JSON data model, and is, |
769 | CBOR is supposed to implement a superset of the JSON data model, and is, |
560 | with some coercion, able to represent all JSON texts (something that other |
770 | with some coercion, able to represent all JSON texts (something that other |
… | |
… | |
642 | Please refrain from using rt.cpan.org or any other bug reporting |
852 | Please refrain from using rt.cpan.org or any other bug reporting |
643 | service. I put the contact address into my modules for a reason. |
853 | service. I put the contact address into my modules for a reason. |
644 | |
854 | |
645 | =cut |
855 | =cut |
646 | |
856 | |
|
|
857 | our %FILTER = ( |
|
|
858 | # 0 # rfc4287 datetime, utf-8 |
|
|
859 | # 1 # unix timestamp, any |
|
|
860 | |
|
|
861 | 2 => sub { # pos bigint |
|
|
862 | require Math::BigInt; |
|
|
863 | Math::BigInt->new ("0x" . unpack "H*", pop) |
|
|
864 | }, |
|
|
865 | |
|
|
866 | 3 => sub { # neg bigint |
|
|
867 | require Math::BigInt; |
|
|
868 | -Math::BigInt->new ("0x" . unpack "H*", pop) |
|
|
869 | }, |
|
|
870 | |
|
|
871 | 4 => sub { # decimal fraction, array |
|
|
872 | require Math::BigFloat; |
|
|
873 | Math::BigFloat->new ($_[1][1] . "E" . $_[1][0]) |
|
|
874 | }, |
|
|
875 | |
|
|
876 | 5 => sub { # bigfloat, array |
|
|
877 | require Math::BigFloat; |
|
|
878 | scalar Math::BigFloat->new ($_[1][1])->blsft ($_[1][0], 2) |
|
|
879 | }, |
|
|
880 | |
|
|
881 | 21 => sub { pop }, # expected conversion to base64url encoding |
|
|
882 | 22 => sub { pop }, # expected conversion to base64 encoding |
|
|
883 | 23 => sub { pop }, # expected conversion to base16 encoding |
|
|
884 | |
|
|
885 | # 24 # embedded cbor, byte string |
|
|
886 | |
|
|
887 | 32 => sub { |
|
|
888 | require URI; |
|
|
889 | URI->new (pop) |
|
|
890 | }, |
|
|
891 | |
|
|
892 | # 33 # base64url rfc4648, utf-8 |
|
|
893 | # 34 # base64 rfc46484, utf-8 |
|
|
894 | # 35 # regex pcre/ecma262, utf-8 |
|
|
895 | # 36 # mime message rfc2045, utf-8 |
|
|
896 | ); |
|
|
897 | |
|
|
898 | sub CBOR::XS::default_filter { |
|
|
899 | &{ $FILTER{$_[0]} or return } |
|
|
900 | } |
|
|
901 | |
|
|
902 | sub URI::TO_CBOR { |
|
|
903 | my $uri = $_[0]->as_string; |
|
|
904 | utf8::upgrade $uri; |
|
|
905 | CBOR::XS::tag 32, $uri |
|
|
906 | } |
|
|
907 | |
|
|
908 | sub Math::BigInt::TO_CBOR { |
|
|
909 | if ($_[0] >= -2147483648 && $_[0] <= 2147483647) { |
|
|
910 | $_[0]->numify |
|
|
911 | } else { |
|
|
912 | my $hex = substr $_[0]->as_hex, 2; |
|
|
913 | $hex = "0$hex" if 1 & length $hex; # sigh |
|
|
914 | CBOR::XS::tag $_[0] >= 0 ? 2 : 3, pack "H*", $hex |
|
|
915 | } |
|
|
916 | } |
|
|
917 | |
|
|
918 | sub Math::BigFloat::TO_CBOR { |
|
|
919 | my ($m, $e) = $_[0]->parts; |
|
|
920 | CBOR::XS::tag 4, [$e->numify, $m] |
|
|
921 | } |
|
|
922 | |
647 | XSLoader::load "CBOR::XS", $VERSION; |
923 | XSLoader::load "CBOR::XS", $VERSION; |
648 | |
924 | |
649 | =head1 SEE ALSO |
925 | =head1 SEE ALSO |
650 | |
926 | |
651 | The L<JSON> and L<JSON::XS> modules that do similar, but human-readable, |
927 | The L<JSON> and L<JSON::XS> modules that do similar, but human-readable, |