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

Comparing CBOR-XS/XS.pm (file contents):
Revision 1.2 by root, Sat Oct 26 10:41:12 2013 UTC vs.
Revision 1.24 by root, Fri Nov 22 16:18:59 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 = 0.01;	76	our $VERSION = 0.09;
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;
44		83
		84	use Types::Serialiser;
		85
		86	our $MAGIC = "\xd9\xd9\xf7";
		87
45	=head1 FUNCTIONAL INTERFACE	88	=head1 FUNCTIONAL INTERFACE
46		89
47	The following convenience methods are provided by this module. They are	90	The following convenience methods are provided by this module. They are
48	exported by default:	91	exported by default:
49		92
…		…
75	strings. All boolean flags described below are by default I<disabled>.	118	strings. All boolean flags described below are by default I<disabled>.
76		119
77	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
78	be chained:	121	be chained:
79		122
80	#TODO
81	my $cbor = CBOR::XS->new->encode ({a => [1,2]});	123	my $cbor = CBOR::XS->new->encode ({a => [1,2]});
82		124
83	=item $cbor = $cbor->max_depth ([$maximum_nesting_depth])	125	=item $cbor = $cbor->max_depth ([$maximum_nesting_depth])
84		126
85	=item $max_depth = $cbor->get_max_depth	127	=item $max_depth = $cbor->get_max_depth
…		…
119	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
120	C<0> is specified).	162	C<0> is specified).
121		163
122	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.
123		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.
		192
		193	It is recommended to leave it off unless you know your
		194	communication partner supports the value sharing extensions to CBOR
		195	(http://cbor.schmorp.de/value-sharing).
		196
		197	Detecting shared values incurs a runtime overhead when values are encoded
		198	that have a reference counter large than one, and might unnecessarily
		199	increase the encoded size, as potentially shared values are encode as
		200	sharable whether or not they are actually shared.
		201
		202	At the moment, only targets of references can be shared (e.g. scalars,
		203	arrays or hashes pointed to by a reference). Weirder constructs, such as
		204	an array with multiple "copies" of the I<same> string, which are hard but
		205	not impossible to create in Perl, are not supported (this is the same as
		206	for L<Storable>).
		207
		208	If C<$enable> is false (the default), then C<encode> will encode
		209	exception when it encounters anything it cannot encode as CBOR.
		210
		211	This option does not affect C<decode> in any way - shared values and
		212	references will always be decoded properly if present.
		213
		214	=item $cbor = $cbor->allow_stringref ([$enable])
		215
		216	=item $enabled = $cbor->get_allow_stringref
		217
		218	If C<$enable> is true (or missing), then C<encode> will try not to encode
		219	the same string twice, but will instead encode a reference to the string
		220	instead. Depending on your data format. this can save a lot of space, but
		221	also results in a very large runtime overhead (expect encoding times to be
		222	2-4 times as high as without).
		223
		224	It is recommended to leave it off unless you know your
		225	communications partner supports the stringref extension to CBOR
		226	(http://cbor.schmorp.de/stringref).
		227
		228	If C<$enable> is false (the default), then C<encode> will encode
		229	exception when it encounters anything it cannot encode as CBOR.
		230
		231	This option does not affect C<decode> in any way - string references will
		232	always be decoded properly if present.
		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
124	=item $cbor_data = $cbor->encode ($perl_scalar)	275	=item $cbor_data = $cbor->encode ($perl_scalar)
125		276
126	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
127	representation.	278	representation.
128		279
…		…
161		312
162	=head2 CBOR -> PERL	313	=head2 CBOR -> PERL
163		314
164	=over 4	315	=over 4
165		316
166	=item True, False	317	=item integers
167		318
168	These CBOR values become C<CBOR::XS::true> and C<CBOR::XS::false>,	319	CBOR integers become (numeric) perl scalars. On perls without 64 bit
		320	support, 64 bit integers will be truncated or otherwise corrupted.
		321
		322	=item byte strings
		323
		324	Byte strings will become octet strings in Perl (the byte values 0..255
		325	will simply become characters of the same value in Perl).
		326
		327	=item UTF-8 strings
		328
		329	UTF-8 strings in CBOR will be decoded, i.e. the UTF-8 octets will be
		330	decoded into proper Unicode code points. At the moment, the validity of
		331	the UTF-8 octets will not be validated - corrupt input will result in
		332	corrupted Perl strings.
		333
		334	=item arrays, maps
		335
		336	CBOR arrays and CBOR maps will be converted into references to a Perl
		337	array or hash, respectively. The keys of the map will be stringified
		338	during this process.
		339
		340	=item null
		341
		342	CBOR null becomes C<undef> in Perl.
		343
		344	=item true, false, undefined
		345
		346	These CBOR values become C<Types:Serialiser::true>,
		347	C<Types:Serialiser::false> and C<Types::Serialiser::error>,
169	respectively. They are overloaded to act almost exactly like the numbers	348	respectively. They are overloaded to act almost exactly like the numbers
170	C<1> and C<0>. You can check whether a scalar is a CBOR boolean by using	349	C<1> and C<0> (for true and false) or to throw an exception on access (for
171	the C<CBOR::XS::is_bool> function.	350	error). See the L<Types::Serialiser> manpage for details.
172		351
173	=item Null, Undefined	352	=item tagged values
174		353
175	CBOR Null and Undefined values becomes C<undef> in Perl (in the future,	354	Tagged items consists of a numeric tag and another CBOR value.
176	Undefined may raise an exception).	355
		356	See L<TAG HANDLING AND EXTENSIONS> and the description of C<< ->filter >>
		357	for details.
		358
		359	=item anything else
		360
		361	Anything else (e.g. unsupported simple values) will raise a decoding
		362	error.
177		363
178	=back	364	=back
179		365
180		366
181	=head2 PERL -> CBOR	367	=head2 PERL -> CBOR
…		…
186		372
187	=over 4	373	=over 4
188		374
189	=item hash references	375	=item hash references
190		376
191	Perl hash references become CBOR maps. As there is no inherent ordering	377	Perl hash references become CBOR maps. As there is no inherent ordering in
192	in hash keys (or CBOR maps), they will usually be encoded in a	378	hash keys (or CBOR maps), they will usually be encoded in a pseudo-random
193	pseudo-random order.	379	order.
		380
		381	Currently, tied hashes will use the indefinite-length format, while normal
		382	hashes will use the fixed-length format.
194		383
195	=item array references	384	=item array references
196		385
197	Perl array references become CBOR arrays.	386	Perl array references become fixed-length CBOR arrays.
198		387
199	=item other references	388	=item other references
200		389
201	Other unblessed references are generally not allowed and will cause an	390	Other unblessed references are generally not allowed and will cause an
202	exception to be thrown, except for references to the integers C<0> and	391	exception to be thrown, except for references to the integers C<0> and
203	C<1>, which get turned into C<False> and C<True> in CBOR.	392	C<1>, which get turned into false and true in CBOR.
204		393
205	=item CBOR::XS::true, CBOR::XS::false	394	=item CBOR::XS::Tagged objects
206		395
		396	Objects of this type must be arrays consisting of a single C<[tag, value]>
		397	pair. The (numerical) tag will be encoded as a CBOR tag, the value will
		398	be encoded as appropriate for the value. You cna use C<CBOR::XS::tag> to
		399	create such objects.
		400
		401	=item Types::Serialiser::true, Types::Serialiser::false, Types::Serialiser::error
		402
207	These special values become CBOR True and CBOR False values,	403	These special values become CBOR true, CBOR false and CBOR undefined
208	respectively. You can also use C<\1> and C<\0> directly if you want.	404	values, respectively. You can also use C<\1>, C<\0> and C<\undef> directly
		405	if you want.
209		406
210	=item blessed objects	407	=item other blessed objects
211		408
212	Blessed objects are not directly representable in CBOR. TODO	409	Other blessed objects are serialised via C<TO_CBOR> or C<FREEZE>. See
213	See the	410	L<TAG HANDLING AND EXTENSIONS> for specific classes handled by this
214	C<allow_blessed> and C<convert_blessed> methods on various options on	411	module, and L<OBJECT SERIALISATION> for generic object serialisation.
215	how to deal with this: basically, you can choose between throwing an
216	exception, encoding the reference as if it weren't blessed, or provide
217	your own serialiser method.
218		412
219	=item simple scalars	413	=item simple scalars
220		414
221	TODO
222	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
223	difficult objects to encode: CBOR::XS will encode undefined scalars as	416	difficult objects to encode: CBOR::XS will encode undefined scalars as
224	CBOR C<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
225	before encoding as CBOR strings, and anything else as number value:	418	before encoding as CBOR strings, and anything else as number value:
226		419
227	# dump as number	420	# dump as number
228	encode_cbor [2] # yields [2]	421	encode_cbor [2] # yields [2]
229	encode_cbor [-3.0e17] # yields [-3e+17]	422	encode_cbor [-3.0e17] # yields [-3e+17]
…		…
251		444
252	You can not currently force the type in other, less obscure, ways. Tell me	445	You can not currently force the type in other, less obscure, ways. Tell me
253	if you need this capability (but don't forget to explain why it's needed	446	if you need this capability (but don't forget to explain why it's needed
254	:).	447	:).
255		448
256	Note that numerical precision has the same meaning as under Perl (so	449	Perl values that seem to be integers generally use the shortest possible
257	binary to decimal conversion follows the same rules as in Perl, which	450	representation. Floating-point values will use either the IEEE single
258	can differ to other languages). Also, your perl interpreter might expose	451	format if possible without loss of precision, otherwise the IEEE double
259	extensions to the floating point numbers of your platform, such as	452	format will be used. Perls that use formats other than IEEE double to
260	infinities or NaN's - these cannot be represented in CBOR, and it is an	453	represent numerical values are supported, but might suffer loss of
261	error to pass those in.	454	precision.
262		455
263	=back	456	=back
264		457
		458	=head2 OBJECT SERIALISATION
265		459
		460	This module knows two way to serialise a Perl object: The CBOR-specific
		461	way, and the generic way.
		462
		463	Whenever the encoder encounters a Perl object that it cnanot serialise
		464	directly (most of them), it will first look up the C<TO_CBOR> method on
		465	it.
		466
		467	If it has a C<TO_CBOR> method, it will call it with the object as only
		468	argument, and expects exactly one return value, which it will then
		469	substitute and encode it in the place of the object.
		470
		471	Otherwise, it will look up the C<FREEZE> method. If it exists, it will
		472	call it with the object as first argument, and the constant string C<CBOR>
		473	as the second argument, to distinguish it from other serialisers.
		474
		475	The C<FREEZE> method can return any number of values (i.e. zero or
		476	more). These will be encoded as CBOR perl object, together with the
		477	classname.
		478
		479	If an object supports neither C<TO_CBOR> nor C<FREEZE>, encoding will fail
		480	with an error.
		481
		482	Objects encoded via C<TO_CBOR> cannot be automatically decoded, but
		483	objects encoded via C<FREEZE> can be decoded using the following protocol:
		484
		485	When an encoded CBOR perl object is encountered by the decoder, it will
		486	look up the C<THAW> method, by using the stored classname, and will fail
		487	if the method cannot be found.
		488
		489	After the lookup it will call the C<THAW> method with the stored classname
		490	as first argument, the constant string C<CBOR> as second argument, and all
		491	values returned by C<FREEZE> as remaining arguments.
		492
		493	=head4 EXAMPLES
		494
		495	Here is an example C<TO_CBOR> method:
		496
		497	sub My::Object::TO_CBOR {
		498	my ($obj) = @_;
		499
		500	["this is a serialised My::Object object", $obj->{id}]
		501	}
		502
		503	When a C<My::Object> is encoded to CBOR, it will instead encode a simple
		504	array with two members: a string, and the "object id". Decoding this CBOR
		505	string will yield a normal perl array reference in place of the object.
		506
		507	A more useful and practical example would be a serialisation method for
		508	the URI module. CBOR has a custom tag value for URIs, namely 32:
		509
		510	sub URI::TO_CBOR {
		511	my ($self) = @_;
		512	my $uri = "$self"; # stringify uri
		513	utf8::upgrade $uri; # make sure it will be encoded as UTF-8 string
		514	CBOR::XS::tagged 32, "$_[0]"
		515	}
		516
		517	This will encode URIs as a UTF-8 string with tag 32, which indicates an
		518	URI.
		519
		520	Decoding such an URI will not (currently) give you an URI object, but
		521	instead a CBOR::XS::Tagged object with tag number 32 and the string -
		522	exactly what was returned by C<TO_CBOR>.
		523
		524	To serialise an object so it can automatically be deserialised, you need
		525	to use C<FREEZE> and C<THAW>. To take the URI module as example, this
		526	would be a possible implementation:
		527
		528	sub URI::FREEZE {
		529	my ($self, $serialiser) = @_;
		530	"$self" # encode url string
		531	}
		532
		533	sub URI::THAW {
		534	my ($class, $serialiser, $uri) = @_;
		535
		536	$class->new ($uri)
		537	}
		538
		539	Unlike C<TO_CBOR>, multiple values can be returned by C<FREEZE>. For
		540	example, a C<FREEZE> method that returns "type", "id" and "variant" values
		541	would cause an invocation of C<THAW> with 5 arguments:
		542
		543	sub My::Object::FREEZE {
		544	my ($self, $serialiser) = @_;
		545
		546	($self->{type}, $self->{id}, $self->{variant})
		547	}
		548
		549	sub My::Object::THAW {
		550	my ($class, $serialiser, $type, $id, $variant) = @_;
		551
		552	$class-<new (type => $type, id => $id, variant => $variant)
		553	}
		554
		555
		556	=head1 MAGIC HEADER
		557
		558	There is no way to distinguish CBOR from other formats
		559	programmatically. To make it easier to distinguish CBOR from other
		560	formats, the CBOR specification has a special "magic string" that can be
		561	prepended to any CBOR string without changing its meaning.
		562
		563	This string is available as C<$CBOR::XS::MAGIC>. This module does not
		564	prepend this string to the CBOR data it generates, but it will ignore it
		565	if present, so users can prepend this string as a "file type" indicator as
		566	required.
		567
		568
		569	=head1 THE CBOR::XS::Tagged CLASS
		570
		571	CBOR has the concept of tagged values - any CBOR value can be tagged with
		572	a numeric 64 bit number, which are centrally administered.
		573
		574	C<CBOR::XS> handles a few tags internally when en- or decoding. You can
		575	also create tags yourself by encoding C<CBOR::XS::Tagged> objects, and the
		576	decoder will create C<CBOR::XS::Tagged> objects itself when it hits an
		577	unknown tag.
		578
		579	These objects are simply blessed array references - the first member of
		580	the array being the numerical tag, the second being the value.
		581
		582	You can interact with C<CBOR::XS::Tagged> objects in the following ways:
		583
		584	=over 4
		585
		586	=item $tagged = CBOR::XS::tag $tag, $value
		587
		588	This function(!) creates a new C<CBOR::XS::Tagged> object using the given
		589	C<$tag> (0..2**64-1) to tag the given C<$value> (which can be any Perl
		590	value that can be encoded in CBOR, including serialisable Perl objects and
		591	C<CBOR::XS::Tagged> objects).
		592
		593	=item $tagged->[0]
		594
		595	=item $tagged->[0] = $new_tag
		596
		597	=item $tag = $tagged->tag
		598
		599	=item $new_tag = $tagged->tag ($new_tag)
		600
		601	Access/mutate the tag.
		602
		603	=item $tagged->[1]
		604
		605	=item $tagged->[1] = $new_value
		606
		607	=item $value = $tagged->value
		608
		609	=item $new_value = $tagged->value ($new_value)
		610
		611	Access/mutate the tagged value.
		612
		613	=back
		614
		615	=cut
		616
		617	sub tag($$) {
		618	bless [@_], CBOR::XS::Tagged::;
		619	}
		620
		621	sub CBOR::XS::Tagged::tag {
		622	$_[0][0] = $_[1] if $#_;
		623	$_[0][0]
		624	}
		625
		626	sub CBOR::XS::Tagged::value {
		627	$_[0][1] = $_[1] if $#_;
		628	$_[0][1]
		629	}
		630
		631	=head2 EXAMPLES
		632
		633	Here are some examples of C<CBOR::XS::Tagged> uses to tag objects.
		634
		635	You can look up CBOR tag value and emanings in the IANA registry at
		636	L<http://www.iana.org/assignments/cbor-tags/cbor-tags.xhtml>.
		637
		638	Prepend a magic header (C<$CBOR::XS::MAGIC>):
		639
		640	my $cbor = encode_cbor CBOR::XS::tag 55799, $value;
		641	# same as:
		642	my $cbor = $CBOR::XS::MAGIC . encode_cbor $value;
		643
		644	Serialise some URIs and a regex in an array:
		645
		646	my $cbor = encode_cbor [
		647	(CBOR::XS::tag 32, "http://www.nethype.de/"),
		648	(CBOR::XS::tag 32, "http://software.schmorp.de/"),
		649	(CBOR::XS::tag 35, "^[Pp][Ee][Rr][lL]\$"),
		650	];
		651
		652	Wrap CBOR data in CBOR:
		653
		654	my $cbor_cbor = encode_cbor
		655	CBOR::XS::tag 24,
		656	encode_cbor [1, 2, 3];
		657
		658	=head1 TAG HANDLING AND EXTENSIONS
		659
		660	This section describes how this module handles specific tagged values
		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
		663	CBOR::XS::Tagged object on decoding, and only encoding the tag when
		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.
		669
		670	Future versions of this module reserve the right to special case
		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.
		677
		678	=over 4
		679
		680	=item <unassigned> (perl-object, L<http://cbor.schmorp.de/perl-object>)
		681
		682	These tags are automatically created (and decoded) for serialisable
		683	objects using the C<FREEZE/THAW> methods (the L<Types::Serialier> object
		684	serialisation protocol). See L<OBJECT SERIALISATION> for details.
		685
		686	=item <unassigned>, <unassigned> (sharable, sharedref, L <http://cbor.schmorp.de/value-sharing>)
		687
		688	These tags are automatically decoded when encountered, resulting in
		689	shared values in the decoded object. They are only encoded, however, when
		690	C<allow_sharable> is enabled.
		691
		692	=item <unassigned>, <unassigned> (stringref-namespace, stringref, L <http://cbor.schmorp.de/stringref>)
		693
		694	These tags are automatically decoded when encountered. They are only
		695	encoded, however, when C<allow_stringref> is enabled.
		696
		697	=item 22098 (indirection, L<http://cbor.schmorp.de/indirection>)
		698
		699	This tag is automatically generated when a reference are encountered (with
		700	the exception of hash and array refernces). It is converted to a reference
		701	when decoding.
		702
		703	=item 55799 (self-describe CBOR, RFC 7049)
		704
		705	This value is not generated on encoding (unless explicitly requested by
		706	the user), and is simply ignored when decoding.
		707
		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	);
		797
		798
266	=head2 CBOR and JSON	799	=head1 CBOR and JSON
267		800
268	TODO	801	CBOR is supposed to implement a superset of the JSON data model, and is,
		802	with some coercion, able to represent all JSON texts (something that other
		803	"binary JSON" formats such as BSON generally do not support).
		804
		805	CBOR implements some extra hints and support for JSON interoperability,
		806	and the spec offers further guidance for conversion between CBOR and
		807	JSON. None of this is currently implemented in CBOR, and the guidelines
		808	in the spec do not result in correct round-tripping of data. If JSON
		809	interoperability is improved in the future, then the goal will be to
		810	ensure that decoded JSON data will round-trip encoding and decoding to
		811	CBOR intact.
269		812
270		813
271	=head1 SECURITY CONSIDERATIONS	814	=head1 SECURITY CONSIDERATIONS
272		815
273	When you are using CBOR in a protocol, talking to untrusted potentially	816	When you are using CBOR in a protocol, talking to untrusted potentially
…		…
341	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
342	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.
343		886
344	=cut	887	=cut
345		888
346	our $true = do { bless \(my $dummy = 1), "CBOR::XS::Boolean" };	889	our %FILTER = (
347	our $false = do { bless \(my $dummy = 0), "CBOR::XS::Boolean" };	890	# 0 # rfc4287 datetime, utf-8
		891	# 1 # unix timestamp, any
348		892
349	sub true() { $true }	893	2 => sub { # pos bigint
350	sub false() { $false }	894	require Math::BigInt;
		895	Math::BigInt->new ("0x" . unpack "H*", pop)
		896	},
351		897
352	sub is_bool($) {	898	3 => sub { # neg bigint
353	UNIVERSAL::isa $_[0], "CBOR::XS::Boolean"	899	require Math::BigInt;
354	# or UNIVERSAL::isa $_[0], "CBOR::Literal"	900	-Math::BigInt->new ("0x" . unpack "H*", pop)
		901	},
		902
		903	4 => sub { # decimal fraction, array
		904	require Math::BigFloat;
		905	Math::BigFloat->new ($_[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 }
355	}	932	}
356		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
357	XSLoader::load "CBOR::XS", $VERSION;	955	XSLoader::load "CBOR::XS", $VERSION;
358
359	package CBOR::XS::Boolean;
360
361	use overload
362	"0+" => sub { ${$_[0]} },
363	"++" => sub { $_[0] = ${$_[0]} + 1 },
364	"--" => sub { $_[0] = ${$_[0]} - 1 },
365	fallback => 1;
366
367	1;
368		956
369	=head1 SEE ALSO	957	=head1 SEE ALSO
370		958
371	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,
372	serialisation.	960	serialisation.
373		961
		962	The L<Types::Serialiser> module provides the data model for true, false
		963	and error values.
		964
374	=head1 AUTHOR	965	=head1 AUTHOR
375		966
376	Marc Lehmann <schmorp@schmorp.de>	967	Marc Lehmann <schmorp@schmorp.de>
377	http://home.schmorp.de/	968	http://home.schmorp.de/
378		969
379	=cut	970	=cut
380		971
		972	1
		973

Diff Legend

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

Comparing CBOR-XS/XS.pm (file contents): Revision 1.2 by root, Sat Oct 26 10:41:12 2013 UTC vs. Revision 1.24 by root, Fri Nov 22 16:18:59 2013 UTC

Diff Legend

Comparing CBOR-XS/XS.pm (file contents):
Revision 1.2 by root, Sat Oct 26 10:41:12 2013 UTC vs.
Revision 1.24 by root, Fri Nov 22 16:18:59 2013 UTC