[ViewVC] Diff of: cvs/CBOR-XS/XS.pm

Comparing CBOR-XS/XS.pm (file contents):
Revision 1.3 by root, Sat Oct 26 11:08:34 2013 UTC vs.
Revision 1.22 by root, Fri Nov 22 15:28:38 2013 UTC

…		…
12	$perl_value = decode_cbor $binary_cbor_data;	12	$perl_value = decode_cbor $binary_cbor_data;
13		13
14	# OO-interface	14	# OO-interface
15		15
16	$coder = CBOR::XS->new;	16	$coder = CBOR::XS->new;
17	#TODO	17	$binary_cbor_data = $coder->encode ($perl_value);
		18	$perl_value = $coder->decode ($binary_cbor_data);
		19
		20	# prefix decoding
		21
		22	my $many_cbor_strings = ...;
		23	while (length $many_cbor_strings) {
		24	my ($data, $length) = $cbor->decode_prefix ($many_cbor_strings);
		25	# data was decoded
		26	substr $many_cbor_strings, 0, $length, ""; # remove decoded cbor string
		27	}
18		28
19	=head1 DESCRIPTION	29	=head1 DESCRIPTION
20		30
21	WARNING! THIS IS A PRE-ALPHA RELEASE! IT WILL CRASH, CORRUPT YOUR DATA AND	31	WARNING! This module is very new, and not very well tested (that's up
22	EAT YOUR CHILDREN!	32	to you to do). Furthermore, details of the implementation might change
		33	freely before version 1.0. And lastly, most extensions depend on an IANA
		34	assignment, and until that assignment is official, this implementation is
		35	not interoperable with other implementations (even future versions of this
		36	module) until the assignment is done.
23		37
24	This module converts Perl data structures to CBOR and vice versa. Its	38	You are still invited to try out CBOR, and this module.
		39
		40	This module converts Perl data structures to the Concise Binary Object
		41	Representation (CBOR) and vice versa. CBOR is a fast binary serialisation
		42	format that aims to use a superset of the JSON data model, i.e. when you
		43	can represent something in JSON, you should be able to represent it in
		44	CBOR.
		45
		46	In short, CBOR is a faster and very compact binary alternative to JSON,
		47	with the added ability of supporting serialisation of Perl objects. (JSON
		48	often compresses better than CBOR though, so if you plan to compress the
		49	data later you might want to compare both formats first).
		50
		51	To give you a general idea about speed, with texts in the megabyte range,
		52	C<CBOR::XS> usually encodes roughly twice as fast as L<Storable> or
		53	L<JSON::XS> and decodes about 15%-30% faster than those. The shorter the
		54	data, the worse L<Storable> performs in comparison.
		55
		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>.
		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
25	primary goal is to be I<correct> and its secondary goal is to be	64	The primary goal of this module is to be I<correct> and the secondary goal
26	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.
27		66
28	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
29	vice versa.	68	vice versa.
30		69
31	=cut	70	=cut
32		71
33	package CBOR::XS;	72	package CBOR::XS;
34		73
35	use common::sense;	74	use common::sense;
36		75
37	our $VERSION = 0.02;	76	our $VERSION = 0.08;
38	our @ISA = qw(Exporter);	77	our @ISA = qw(Exporter);
39		78
40	our @EXPORT = qw(encode_cbor decode_cbor);	79	our @EXPORT = qw(encode_cbor decode_cbor);
41		80
42	use Exporter;	81	use Exporter;
43	use XSLoader;	82	use XSLoader;
		83
		84	use Types::Serialiser;
44		85
45	our $MAGIC = "\xd9\xd9\xf7";	86	our $MAGIC = "\xd9\xd9\xf7";
46		87
47	=head1 FUNCTIONAL INTERFACE	88	=head1 FUNCTIONAL INTERFACE
48		89
…		…
121	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
122	C<0> is specified).	163	C<0> is specified).
123		164
124	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.
125		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.
		234
126	=item $cbor_data = $cbor->encode ($perl_scalar)	235	=item $cbor_data = $cbor->encode ($perl_scalar)
127		236
128	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
129	representation.	238	representation.
130		239
…		…
163		272
164	=head2 CBOR -> PERL	273	=head2 CBOR -> PERL
165		274
166	=over 4	275	=over 4
167		276
168	=item True, False	277	=item integers
169		278
170	These CBOR values become C<CBOR::XS::true> and C<CBOR::XS::false>,	279	CBOR integers become (numeric) perl scalars. On perls without 64 bit
		280	support, 64 bit integers will be truncated or otherwise corrupted.
		281
		282	=item byte strings
		283
		284	Byte strings will become octet strings in Perl (the byte values 0..255
		285	will simply become characters of the same value in Perl).
		286
		287	=item UTF-8 strings
		288
		289	UTF-8 strings in CBOR will be decoded, i.e. the UTF-8 octets will be
		290	decoded into proper Unicode code points. At the moment, the validity of
		291	the UTF-8 octets will not be validated - corrupt input will result in
		292	corrupted Perl strings.
		293
		294	=item arrays, maps
		295
		296	CBOR arrays and CBOR maps will be converted into references to a Perl
		297	array or hash, respectively. The keys of the map will be stringified
		298	during this process.
		299
		300	=item null
		301
		302	CBOR null becomes C<undef> in Perl.
		303
		304	=item true, false, undefined
		305
		306	These CBOR values become C<Types:Serialiser::true>,
		307	C<Types:Serialiser::false> and C<Types::Serialiser::error>,
171	respectively. They are overloaded to act almost exactly like the numbers	308	respectively. They are overloaded to act almost exactly like the numbers
172	C<1> and C<0>. You can check whether a scalar is a CBOR boolean by using	309	C<1> and C<0> (for true and false) or to throw an exception on access (for
173	the C<CBOR::XS::is_bool> function.	310	error). See the L<Types::Serialiser> manpage for details.
174		311
175	=item Null, Undefined	312	=item CBOR tag 256 (perl object)
176		313
177	CBOR Null and Undefined values becomes C<undef> in Perl (in the future,	314	The tag value C<256> (TODO: pending iana registration) will be used
178	Undefined may raise an exception).	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
		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
		329	In the future, support for user-supplied conversions might get added.
		330
		331	=item anything else
		332
		333	Anything else (e.g. unsupported simple values) will raise a decoding
		334	error.
179		335
180	=back	336	=back
181		337
182		338
183	=head2 PERL -> CBOR	339	=head2 PERL -> CBOR
…		…
188		344
189	=over 4	345	=over 4
190		346
191	=item hash references	347	=item hash references
192		348
193	Perl hash references become CBOR maps. As there is no inherent ordering	349	Perl hash references become CBOR maps. As there is no inherent ordering in
194	in hash keys (or CBOR maps), they will usually be encoded in a	350	hash keys (or CBOR maps), they will usually be encoded in a pseudo-random
195	pseudo-random order.	351	order.
		352
		353	Currently, tied hashes will use the indefinite-length format, while normal
		354	hashes will use the fixed-length format.
196		355
197	=item array references	356	=item array references
198		357
199	Perl array references become CBOR arrays.	358	Perl array references become fixed-length CBOR arrays.
200		359
201	=item other references	360	=item other references
202		361
203	Other unblessed references are generally not allowed and will cause an	362	Other unblessed references are generally not allowed and will cause an
204	exception to be thrown, except for references to the integers C<0> and	363	exception to be thrown, except for references to the integers C<0> and
205	C<1>, which get turned into C<False> and C<True> in CBOR.	364	C<1>, which get turned into false and true in CBOR.
206		365
207	=item CBOR::XS::true, CBOR::XS::false	366	=item CBOR::XS::Tagged objects
208		367
		368	Objects of this type must be arrays consisting of a single C<[tag, value]>
		369	pair. The (numerical) tag will be encoded as a CBOR tag, the value will
		370	be encoded as appropriate for the value. You cna use C<CBOR::XS::tag> to
		371	create such objects.
		372
		373	=item Types::Serialiser::true, Types::Serialiser::false, Types::Serialiser::error
		374
209	These special values become CBOR True and CBOR False values,	375	These special values become CBOR true, CBOR false and CBOR undefined
210	respectively. You can also use C<\1> and C<\0> directly if you want.	376	values, respectively. You can also use C<\1>, C<\0> and C<\undef> directly
		377	if you want.
211		378
212	=item blessed objects	379	=item other blessed objects
213		380
214	Blessed objects are not directly representable in CBOR. TODO	381	Other blessed objects are serialised via C<TO_CBOR> or C<FREEZE>. See
215	See the	382	L<OBJECT SERIALISATION>, below, for details.
216	C<allow_blessed> and C<convert_blessed> methods on various options on
217	how to deal with this: basically, you can choose between throwing an
218	exception, encoding the reference as if it weren't blessed, or provide
219	your own serialiser method.
220		383
221	=item simple scalars	384	=item simple scalars
222		385
223	TODO	386	TODO
224	Simple Perl scalars (any scalar that is not a reference) are the most	387	Simple Perl scalars (any scalar that is not a reference) are the most
225	difficult objects to encode: CBOR::XS will encode undefined scalars as	388	difficult objects to encode: CBOR::XS will encode undefined scalars as
226	CBOR C<Null> values, scalars that have last been used in a string context	389	CBOR null values, scalars that have last been used in a string context
227	before encoding as CBOR strings, and anything else as number value:	390	before encoding as CBOR strings, and anything else as number value:
228		391
229	# dump as number	392	# dump as number
230	encode_cbor [2] # yields [2]	393	encode_cbor [2] # yields [2]
231	encode_cbor [-3.0e17] # yields [-3e+17]	394	encode_cbor [-3.0e17] # yields [-3e+17]
…		…
253		416
254	You can not currently force the type in other, less obscure, ways. Tell me	417	You can not currently force the type in other, less obscure, ways. Tell me
255	if you need this capability (but don't forget to explain why it's needed	418	if you need this capability (but don't forget to explain why it's needed
256	:).	419	:).
257		420
258	Note that numerical precision has the same meaning as under Perl (so	421	Perl values that seem to be integers generally use the shortest possible
259	binary to decimal conversion follows the same rules as in Perl, which	422	representation. Floating-point values will use either the IEEE single
260	can differ to other languages). Also, your perl interpreter might expose	423	format if possible without loss of precision, otherwise the IEEE double
261	extensions to the floating point numbers of your platform, such as	424	format will be used. Perls that use formats other than IEEE double to
262	infinities or NaN's - these cannot be represented in CBOR, and it is an	425	represent numerical values are supported, but might suffer loss of
263	error to pass those in.	426	precision.
264		427
265	=back	428	=back
266		429
		430	=head2 OBJECT SERIALISATION
267		431
		432	This module knows two way to serialise a Perl object: The CBOR-specific
		433	way, and the generic way.
		434
		435	Whenever the encoder encounters a Perl object that it cnanot serialise
		436	directly (most of them), it will first look up the C<TO_CBOR> method on
		437	it.
		438
		439	If it has a C<TO_CBOR> method, it will call it with the object as only
		440	argument, and expects exactly one return value, which it will then
		441	substitute and encode it in the place of the object.
		442
		443	Otherwise, it will look up the C<FREEZE> method. If it exists, it will
		444	call it with the object as first argument, and the constant string C<CBOR>
		445	as the second argument, to distinguish it from other serialisers.
		446
		447	The C<FREEZE> method can return any number of values (i.e. zero or
		448	more). These will be encoded as CBOR perl object, together with the
		449	classname.
		450
		451	If an object supports neither C<TO_CBOR> nor C<FREEZE>, encoding will fail
		452	with an error.
		453
		454	Objects encoded via C<TO_CBOR> cannot be automatically decoded, but
		455	objects encoded via C<FREEZE> can be decoded using the following protocol:
		456
		457	When an encoded CBOR perl object is encountered by the decoder, it will
		458	look up the C<THAW> method, by using the stored classname, and will fail
		459	if the method cannot be found.
		460
		461	After the lookup it will call the C<THAW> method with the stored classname
		462	as first argument, the constant string C<CBOR> as second argument, and all
		463	values returned by C<FREEZE> as remaining arguments.
		464
		465	=head4 EXAMPLES
		466
		467	Here is an example C<TO_CBOR> method:
		468
		469	sub My::Object::TO_CBOR {
		470	my ($obj) = @_;
		471
		472	["this is a serialised My::Object object", $obj->{id}]
		473	}
		474
		475	When a C<My::Object> is encoded to CBOR, it will instead encode a simple
		476	array with two members: a string, and the "object id". Decoding this CBOR
		477	string will yield a normal perl array reference in place of the object.
		478
		479	A more useful and practical example would be a serialisation method for
		480	the URI module. CBOR has a custom tag value for URIs, namely 32:
		481
		482	sub URI::TO_CBOR {
		483	my ($self) = @_;
		484	my $uri = "$self"; # stringify uri
		485	utf8::upgrade $uri; # make sure it will be encoded as UTF-8 string
		486	CBOR::XS::tagged 32, "$_[0]"
		487	}
		488
		489	This will encode URIs as a UTF-8 string with tag 32, which indicates an
		490	URI.
		491
		492	Decoding such an URI will not (currently) give you an URI object, but
		493	instead a CBOR::XS::Tagged object with tag number 32 and the string -
		494	exactly what was returned by C<TO_CBOR>.
		495
		496	To serialise an object so it can automatically be deserialised, you need
		497	to use C<FREEZE> and C<THAW>. To take the URI module as example, this
		498	would be a possible implementation:
		499
		500	sub URI::FREEZE {
		501	my ($self, $serialiser) = @_;
		502	"$self" # encode url string
		503	}
		504
		505	sub URI::THAW {
		506	my ($class, $serialiser, $uri) = @_;
		507
		508	$class->new ($uri)
		509	}
		510
		511	Unlike C<TO_CBOR>, multiple values can be returned by C<FREEZE>. For
		512	example, a C<FREEZE> method that returns "type", "id" and "variant" values
		513	would cause an invocation of C<THAW> with 5 arguments:
		514
		515	sub My::Object::FREEZE {
		516	my ($self, $serialiser) = @_;
		517
		518	($self->{type}, $self->{id}, $self->{variant})
		519	}
		520
		521	sub My::Object::THAW {
		522	my ($class, $serialiser, $type, $id, $variant) = @_;
		523
		524	$class-<new (type => $type, id => $id, variant => $variant)
		525	}
		526
		527
268	=head2 MAGIC HEADER	528	=head1 MAGIC HEADER
269		529
270	There is no way to distinguish CBOR from other formats	530	There is no way to distinguish CBOR from other formats
271	programmatically. To make it easier to distinguish CBOR from other	531	programmatically. To make it easier to distinguish CBOR from other
272	formats, the CBOR specification has a special "magic string" that can be	532	formats, the CBOR specification has a special "magic string" that can be
273	prepended to any CBOR string without changing it's meaning.	533	prepended to any CBOR string without changing its meaning.
274		534
275	This string is available as C<$CBOR::XS::MAGIC>. This module does not	535	This string is available as C<$CBOR::XS::MAGIC>. This module does not
276	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
277	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
278	required.	538	required.
279		539
280		540
		541	=head1 THE CBOR::XS::Tagged CLASS
		542
		543	CBOR has the concept of tagged values - any CBOR value can be tagged with
		544	a numeric 64 bit number, which are centrally administered.
		545
		546	C<CBOR::XS> handles a few tags internally when en- or decoding. You can
		547	also create tags yourself by encoding C<CBOR::XS::Tagged> objects, and the
		548	decoder will create C<CBOR::XS::Tagged> objects itself when it hits an
		549	unknown tag.
		550
		551	These objects are simply blessed array references - the first member of
		552	the array being the numerical tag, the second being the value.
		553
		554	You can interact with C<CBOR::XS::Tagged> objects in the following ways:
		555
		556	=over 4
		557
		558	=item $tagged = CBOR::XS::tag $tag, $value
		559
		560	This function(!) creates a new C<CBOR::XS::Tagged> object using the given
		561	C<$tag> (0..2**64-1) to tag the given C<$value> (which can be any Perl
		562	value that can be encoded in CBOR, including serialisable Perl objects and
		563	C<CBOR::XS::Tagged> objects).
		564
		565	=item $tagged->[0]
		566
		567	=item $tagged->[0] = $new_tag
		568
		569	=item $tag = $tagged->tag
		570
		571	=item $new_tag = $tagged->tag ($new_tag)
		572
		573	Access/mutate the tag.
		574
		575	=item $tagged->[1]
		576
		577	=item $tagged->[1] = $new_value
		578
		579	=item $value = $tagged->value
		580
		581	=item $new_value = $tagged->value ($new_value)
		582
		583	Access/mutate the tagged value.
		584
		585	=back
		586
		587	=cut
		588
		589	sub tag($$) {
		590	bless [@_], CBOR::XS::Tagged::;
		591	}
		592
		593	sub CBOR::XS::Tagged::tag {
		594	$_[0][0] = $_[1] if $#_;
		595	$_[0][0]
		596	}
		597
		598	sub CBOR::XS::Tagged::value {
		599	$_[0][1] = $_[1] if $#_;
		600	$_[0][1]
		601	}
		602
		603	=head2 EXAMPLES
		604
		605	Here are some examples of C<CBOR::XS::Tagged> uses to tag objects.
		606
		607	You can look up CBOR tag value and emanings in the IANA registry at
		608	L<http://www.iana.org/assignments/cbor-tags/cbor-tags.xhtml>.
		609
		610	Prepend a magic header (C<$CBOR::XS::MAGIC>):
		611
		612	my $cbor = encode_cbor CBOR::XS::tag 55799, $value;
		613	# same as:
		614	my $cbor = $CBOR::XS::MAGIC . encode_cbor $value;
		615
		616	Serialise some URIs and a regex in an array:
		617
		618	my $cbor = encode_cbor [
		619	(CBOR::XS::tag 32, "http://www.nethype.de/"),
		620	(CBOR::XS::tag 32, "http://software.schmorp.de/"),
		621	(CBOR::XS::tag 35, "^[Pp][Ee][Rr][lL]\$"),
		622	];
		623
		624	Wrap CBOR data in CBOR:
		625
		626	my $cbor_cbor = encode_cbor
		627	CBOR::XS::tag 24,
		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
		766
281	=head2 CBOR and JSON	767	=head1 CBOR and JSON
282		768
283	TODO	769	CBOR is supposed to implement a superset of the JSON data model, and is,
		770	with some coercion, able to represent all JSON texts (something that other
		771	"binary JSON" formats such as BSON generally do not support).
		772
		773	CBOR implements some extra hints and support for JSON interoperability,
		774	and the spec offers further guidance for conversion between CBOR and
		775	JSON. None of this is currently implemented in CBOR, and the guidelines
		776	in the spec do not result in correct round-tripping of data. If JSON
		777	interoperability is improved in the future, then the goal will be to
		778	ensure that decoded JSON data will round-trip encoding and decoding to
		779	CBOR intact.
284		780
285		781
286	=head1 SECURITY CONSIDERATIONS	782	=head1 SECURITY CONSIDERATIONS
287		783
288	When you are using CBOR in a protocol, talking to untrusted potentially	784	When you are using CBOR in a protocol, talking to untrusted potentially
…		…
356	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
357	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.
358		854
359	=cut	855	=cut
360		856
361	our $true = do { bless \(my $dummy = 1), "CBOR::XS::Boolean" };	857	our %FILTER = (
362	our $false = do { bless \(my $dummy = 0), "CBOR::XS::Boolean" };	858	# 0 # rfc4287 datetime, utf-8
		859	# 1 # unix timestamp, any
363		860
364	sub true() { $true }	861	2 => sub { # pos bigint
365	sub false() { $false }	862	require Math::BigInt;
		863	Math::BigInt->new ("0x" . unpack "H*", pop)
		864	},
366		865
367	sub is_bool($) {	866	3 => sub { # neg bigint
368	UNIVERSAL::isa $_[0], "CBOR::XS::Boolean"	867	require Math::BigInt;
369	# or UNIVERSAL::isa $_[0], "CBOR::Literal"	868	-Math::BigInt->new ("0x" . unpack "H*", pop)
		869	},
		870
		871	4 => sub { # decimal fraction, array
		872	require Math::BigFloat;
		873	Math::BigFloat->new ($_[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 }
370	}	900	}
371		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
372	XSLoader::load "CBOR::XS", $VERSION;	923	XSLoader::load "CBOR::XS", $VERSION;
373
374	package CBOR::XS::Boolean;
375
376	use overload
377	"0+" => sub { ${$_[0]} },
378	"++" => sub { $_[0] = ${$_[0]} + 1 },
379	"--" => sub { $_[0] = ${$_[0]} - 1 },
380	fallback => 1;
381
382	1;
383		924
384	=head1 SEE ALSO	925	=head1 SEE ALSO
385		926
386	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,
387	serialisation.	928	serialisation.
388		929
		930	The L<Types::Serialiser> module provides the data model for true, false
		931	and error values.
		932
389	=head1 AUTHOR	933	=head1 AUTHOR
390		934
391	Marc Lehmann <schmorp@schmorp.de>	935	Marc Lehmann <schmorp@schmorp.de>
392	http://home.schmorp.de/	936	http://home.schmorp.de/
393		937
394	=cut	938	=cut
395		939
		940	1
		941

Diff Legend

-–
+Removed lines
-+
+Added lines
-<
+Changed lines
->
+Changed lines

Comparing CBOR-XS/XS.pm (file contents): Revision 1.3 by root, Sat Oct 26 11:08:34 2013 UTC vs. Revision 1.22 by root, Fri Nov 22 15:28:38 2013 UTC

Diff Legend

Comparing CBOR-XS/XS.pm (file contents):
Revision 1.3 by root, Sat Oct 26 11:08:34 2013 UTC vs.
Revision 1.22 by root, Fri Nov 22 15:28:38 2013 UTC