[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 1.27 by root, Thu Nov 28 15:43:24 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<pack_strings>) 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 = 0.09;
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
45	our $MAGIC = "\xd9\xd9\xf7";	86	our $MAGIC = "\xd9\xd9\xf7";
46		87
47	=head1 FUNCTIONAL INTERFACE	88	=head1 FUNCTIONAL INTERFACE
48		89
49	The following convenience methods are provided by this module. They are	90	The following convenience methods are provided by this module. They are
…		…
77	strings. All boolean flags described below are by default I<disabled>.	118	strings. All boolean flags described below are by default I<disabled>.
78		119
79	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
80	be chained:	121	be chained:
81		122
82	#TODO
83	my $cbor = CBOR::XS->new->encode ({a => [1,2]});	123	my $cbor = CBOR::XS->new->encode ({a => [1,2]});
84		124
85	=item $cbor = $cbor->max_depth ([$maximum_nesting_depth])	125	=item $cbor = $cbor->max_depth ([$maximum_nesting_depth])
86		126
87	=item $max_depth = $cbor->get_max_depth	127	=item $max_depth = $cbor->get_max_depth
…		…
121	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
122	C<0> is specified).	162	C<0> is specified).
123		163
124	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.
125		165
		166	=item $cbor = $cbor->allow_unknown ([$enable])
		167
		168	=item $enabled = $cbor->get_allow_unknown
		169
		170	If C<$enable> is true (or missing), then C<encode> will I<not> throw an
		171	exception when it encounters values it cannot represent in CBOR (for
		172	example, filehandles) but instead will encode a CBOR C<error> value.
		173
		174	If C<$enable> is false (the default), then C<encode> will throw an
		175	exception when it encounters anything it cannot encode as CBOR.
		176
		177	This option does not affect C<decode> in any way, and it is recommended to
		178	leave it off unless you know your communications partner.
		179
		180	=item $cbor = $cbor->allow_sharing ([$enable])
		181
		182	=item $enabled = $cbor->get_allow_sharing
		183
		184	If C<$enable> is true (or missing), then C<encode> will not double-encode
		185	values that have been referenced before (e.g. when the same object, such
		186	as an array, is referenced multiple times), but instead will emit a
		187	reference to the earlier value.
		188
		189	This means that such values will only be encoded once, and will not result
		190	in a deep cloning of the value on decode, in decoders supporting the value
		191	sharing extension. This also makes it possible to encode cyclic data
		192	structures.
		193
		194	It is recommended to leave it off unless you know your
		195	communication partner supports the value sharing extensions to CBOR
		196	(L<http://cbor.schmorp.de/value-sharing>), as without decoder support, the
		197	resulting data structure might be unusable.
		198
		199	Detecting shared values incurs a runtime overhead when values are encoded
		200	that have a reference counter large than one, and might unnecessarily
		201	increase the encoded size, as potentially shared values are encode as
		202	sharable whether or not they are actually shared.
		203
		204	At the moment, only targets of references can be shared (e.g. scalars,
		205	arrays or hashes pointed to by a reference). Weirder constructs, such as
		206	an array with multiple "copies" of the I<same> string, which are hard but
		207	not impossible to create in Perl, are not supported (this is the same as
		208	with L<Storable>).
		209
		210	If C<$enable> is false (the default), then C<encode> will encode shared
		211	data structures repeatedly, unsharing them in the process. Cyclic data
		212	structures cannot be encoded in this mode.
		213
		214	This option does not affect C<decode> in any way - shared values and
		215	references will always be decoded properly if present.
		216
		217	=item $cbor = $cbor->pack_strings ([$enable])
		218
		219	=item $enabled = $cbor->get_pack_strings
		220
		221	If C<$enable> is true (or missing), then C<encode> will try not to encode
		222	the same string twice, but will instead encode a reference to the string
		223	instead. Depending on your data format, this can save a lot of space, but
		224	also results in a very large runtime overhead (expect encoding times to be
		225	2-4 times as high as without).
		226
		227	It is recommended to leave it off unless you know your
		228	communications partner supports the stringref extension to CBOR
		229	(L<http://cbor.schmorp.de/stringref>), as without decoder support, the
		230	resulting data structure might not be usable.
		231
		232	If C<$enable> is false (the default), then C<encode> will encode strings
		233	the standard CBOR way.
		234
		235	This option does not affect C<decode> in any way - string references will
		236	always be decoded properly if present.
		237
		238	=item $cbor = $cbor->filter ([$cb->($tag, $value)])
		239
		240	=item $cb_or_undef = $cbor->get_filter
		241
		242	Sets or replaces the tagged value decoding filter (when C<$cb> is
		243	specified) or clears the filter (if no argument or C<undef> is provided).
		244
		245	The filter callback is called only during decoding, when a non-enforced
		246	tagged value has been decoded (see L<TAG HANDLING AND EXTENSIONS> for a
		247	list of enforced tags). For specific tags, it's often better to provide a
		248	default converter using the C<%CBOR::XS::FILTER> hash (see below).
		249
		250	The first argument is the numerical tag, the second is the (decoded) value
		251	that has been tagged.
		252
		253	The filter function should return either exactly one value, which will
		254	replace the tagged value in the decoded data structure, or no values,
		255	which will result in default handling, which currently means the decoder
		256	creates a C<CBOR::XS::Tagged> object to hold the tag and the value.
		257
		258	When the filter is cleared (the default state), the default filter
		259	function, C<CBOR::XS::default_filter>, is used. This function simply looks
		260	up the tag in the C<%CBOR::XS::FILTER> hash. If an entry exists it must be
		261	a code reference that is called with tag and value, and is responsible for
		262	decoding the value. If no entry exists, it returns no values.
		263
		264	Example: decode all tags not handled internally into CBOR::XS::Tagged
		265	objects, with no other special handling (useful when working with
		266	potentially "unsafe" CBOR data).
		267
		268	CBOR::XS->new->filter (sub { })->decode ($cbor_data);
		269
		270	Example: provide a global filter for tag 1347375694, converting the value
		271	into some string form.
		272
		273	$CBOR::XS::FILTER{1347375694} = sub {
		274	my ($tag, $value);
		275
		276	"tag 1347375694 value $value"
		277	};
		278
126	=item $cbor_data = $cbor->encode ($perl_scalar)	279	=item $cbor_data = $cbor->encode ($perl_scalar)
127		280
128	Converts the given Perl data structure (a scalar value) to its CBOR	281	Converts the given Perl data structure (a scalar value) to its CBOR
129	representation.	282	representation.
130		283
…		…
163		316
164	=head2 CBOR -> PERL	317	=head2 CBOR -> PERL
165		318
166	=over 4	319	=over 4
167		320
168	=item True, False	321	=item integers
169		322
170	These CBOR values become C<CBOR::XS::true> and C<CBOR::XS::false>,	323	CBOR integers become (numeric) perl scalars. On perls without 64 bit
		324	support, 64 bit integers will be truncated or otherwise corrupted.
		325
		326	=item byte strings
		327
		328	Byte strings will become octet strings in Perl (the Byte values 0..255
		329	will simply become characters of the same value in Perl).
		330
		331	=item UTF-8 strings
		332
		333	UTF-8 strings in CBOR will be decoded, i.e. the UTF-8 octets will be
		334	decoded into proper Unicode code points. At the moment, the validity of
		335	the UTF-8 octets will not be validated - corrupt input will result in
		336	corrupted Perl strings.
		337
		338	=item arrays, maps
		339
		340	CBOR arrays and CBOR maps will be converted into references to a Perl
		341	array or hash, respectively. The keys of the map will be stringified
		342	during this process.
		343
		344	=item null
		345
		346	CBOR null becomes C<undef> in Perl.
		347
		348	=item true, false, undefined
		349
		350	These CBOR values become C<Types:Serialiser::true>,
		351	C<Types:Serialiser::false> and C<Types::Serialiser::error>,
171	respectively. They are overloaded to act almost exactly like the numbers	352	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	353	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.	354	error). See the L<Types::Serialiser> manpage for details.
174		355
175	=item Null, Undefined	356	=item tagged values
176		357
177	CBOR Null and Undefined values becomes C<undef> in Perl (in the future,	358	Tagged items consists of a numeric tag and another CBOR value.
178	Undefined may raise an exception).	359
		360	See L<TAG HANDLING AND EXTENSIONS> and the description of C<< ->filter >>
		361	for details.
		362
		363	=item anything else
		364
		365	Anything else (e.g. unsupported simple values) will raise a decoding
		366	error.
179		367
180	=back	368	=back
181		369
182		370
183	=head2 PERL -> CBOR	371	=head2 PERL -> CBOR
…		…
188		376
189	=over 4	377	=over 4
190		378
191	=item hash references	379	=item hash references
192		380
193	Perl hash references become CBOR maps. As there is no inherent ordering	381	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	382	hash keys (or CBOR maps), they will usually be encoded in a pseudo-random
195	pseudo-random order.	383	order.
		384
		385	Currently, tied hashes will use the indefinite-length format, while normal
		386	hashes will use the fixed-length format.
196		387
197	=item array references	388	=item array references
198		389
199	Perl array references become CBOR arrays.	390	Perl array references become fixed-length CBOR arrays.
200		391
201	=item other references	392	=item other references
202		393
203	Other unblessed references are generally not allowed and will cause an	394	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	395	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.	396	C<1>, which get turned into false and true in CBOR.
206		397
207	=item CBOR::XS::true, CBOR::XS::false	398	=item CBOR::XS::Tagged objects
208		399
		400	Objects of this type must be arrays consisting of a single C<[tag, value]>
		401	pair. The (numerical) tag will be encoded as a CBOR tag, the value will
		402	be encoded as appropriate for the value. You cna use C<CBOR::XS::tag> to
		403	create such objects.
		404
		405	=item Types::Serialiser::true, Types::Serialiser::false, Types::Serialiser::error
		406
209	These special values become CBOR True and CBOR False values,	407	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.	408	values, respectively. You can also use C<\1>, C<\0> and C<\undef> directly
		409	if you want.
211		410
212	=item blessed objects	411	=item other blessed objects
213		412
214	Blessed objects are not directly representable in CBOR. TODO	413	Other blessed objects are serialised via C<TO_CBOR> or C<FREEZE>. See
215	See the	414	L<TAG HANDLING AND EXTENSIONS> for specific classes handled by this
216	C<allow_blessed> and C<convert_blessed> methods on various options on	415	module, and L<OBJECT SERIALISATION> for generic object serialisation.
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		416
221	=item simple scalars	417	=item simple scalars
222		418
223	TODO
224	Simple Perl scalars (any scalar that is not a reference) are the most	419	Simple Perl scalars (any scalar that is not a reference) are the most
225	difficult objects to encode: CBOR::XS will encode undefined scalars as	420	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	421	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:	422	before encoding as CBOR strings, and anything else as number value:
228		423
229	# dump as number	424	# dump as number
230	encode_cbor [2] # yields [2]	425	encode_cbor [2] # yields [2]
231	encode_cbor [-3.0e17] # yields [-3e+17]	426	encode_cbor [-3.0e17] # yields [-3e+17]
232	my $value = 5; encode_cbor [$value] # yields [5]	427	my $value = 5; encode_cbor [$value] # yields [5]
233		428
234	# used as string, so dump as string	429	# used as string, so dump as string (either byte or text)
235	print $value;	430	print $value;
236	encode_cbor [$value] # yields ["5"]	431	encode_cbor [$value] # yields ["5"]
237		432
238	# undef becomes null	433	# undef becomes null
239	encode_cbor [undef] # yields [null]	434	encode_cbor [undef] # yields [null]
…		…
243	my $x = 3.1; # some variable containing a number	438	my $x = 3.1; # some variable containing a number
244	"$x"; # stringified	439	"$x"; # stringified
245	$x .= ""; # another, more awkward way to stringify	440	$x .= ""; # another, more awkward way to stringify
246	print $x; # perl does it for you, too, quite often	441	print $x; # perl does it for you, too, quite often
247		442
		443	You can force whether a string ie encoded as byte or text string by using
		444	C<utf8::upgrade> and C<utf8::downgrade>):
		445
		446	utf8::upgrade $x; # encode $x as text string
		447	utf8::downgrade $x; # encode $x as byte string
		448
		449	Perl doesn't define what operations up- and downgrade strings, so if the
		450	difference between byte and text is important, you should up- or downgrade
		451	your string as late as possible before encoding.
		452
248	You can force the type to be a CBOR number by numifying it:	453	You can force the type to be a CBOR number by numifying it:
249		454
250	my $x = "3"; # some variable containing a string	455	my $x = "3"; # some variable containing a string
251	$x += 0; # numify it, ensuring it will be dumped as a number	456	$x += 0; # numify it, ensuring it will be dumped as a number
252	$x *= 1; # same thing, the choice is yours.	457	$x *= 1; # same thing, the choice is yours.
253		458
254	You can not currently force the type in other, less obscure, ways. Tell me	459	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	460	if you need this capability (but don't forget to explain why it's needed
256	:).	461	:).
257		462
258	Note that numerical precision has the same meaning as under Perl (so	463	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	464	representation. Floating-point values will use either the IEEE single
260	can differ to other languages). Also, your perl interpreter might expose	465	format if possible without loss of precision, otherwise the IEEE double
261	extensions to the floating point numbers of your platform, such as	466	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	467	represent numerical values are supported, but might suffer loss of
263	error to pass those in.	468	precision.
264		469
265	=back	470	=back
266		471
		472	=head2 OBJECT SERIALISATION
267		473
		474	This module knows two way to serialise a Perl object: The CBOR-specific
		475	way, and the generic way.
		476
		477	Whenever the encoder encounters a Perl object that it cnanot serialise
		478	directly (most of them), it will first look up the C<TO_CBOR> method on
		479	it.
		480
		481	If it has a C<TO_CBOR> method, it will call it with the object as only
		482	argument, and expects exactly one return value, which it will then
		483	substitute and encode it in the place of the object.
		484
		485	Otherwise, it will look up the C<FREEZE> method. If it exists, it will
		486	call it with the object as first argument, and the constant string C<CBOR>
		487	as the second argument, to distinguish it from other serialisers.
		488
		489	The C<FREEZE> method can return any number of values (i.e. zero or
		490	more). These will be encoded as CBOR perl object, together with the
		491	classname.
		492
		493	If an object supports neither C<TO_CBOR> nor C<FREEZE>, encoding will fail
		494	with an error.
		495
		496	Objects encoded via C<TO_CBOR> cannot be automatically decoded, but
		497	objects encoded via C<FREEZE> can be decoded using the following protocol:
		498
		499	When an encoded CBOR perl object is encountered by the decoder, it will
		500	look up the C<THAW> method, by using the stored classname, and will fail
		501	if the method cannot be found.
		502
		503	After the lookup it will call the C<THAW> method with the stored classname
		504	as first argument, the constant string C<CBOR> as second argument, and all
		505	values returned by C<FREEZE> as remaining arguments.
		506
		507	=head4 EXAMPLES
		508
		509	Here is an example C<TO_CBOR> method:
		510
		511	sub My::Object::TO_CBOR {
		512	my ($obj) = @_;
		513
		514	["this is a serialised My::Object object", $obj->{id}]
		515	}
		516
		517	When a C<My::Object> is encoded to CBOR, it will instead encode a simple
		518	array with two members: a string, and the "object id". Decoding this CBOR
		519	string will yield a normal perl array reference in place of the object.
		520
		521	A more useful and practical example would be a serialisation method for
		522	the URI module. CBOR has a custom tag value for URIs, namely 32:
		523
		524	sub URI::TO_CBOR {
		525	my ($self) = @_;
		526	my $uri = "$self"; # stringify uri
		527	utf8::upgrade $uri; # make sure it will be encoded as UTF-8 string
		528	CBOR::XS::tagged 32, "$_[0]"
		529	}
		530
		531	This will encode URIs as a UTF-8 string with tag 32, which indicates an
		532	URI.
		533
		534	Decoding such an URI will not (currently) give you an URI object, but
		535	instead a CBOR::XS::Tagged object with tag number 32 and the string -
		536	exactly what was returned by C<TO_CBOR>.
		537
		538	To serialise an object so it can automatically be deserialised, you need
		539	to use C<FREEZE> and C<THAW>. To take the URI module as example, this
		540	would be a possible implementation:
		541
		542	sub URI::FREEZE {
		543	my ($self, $serialiser) = @_;
		544	"$self" # encode url string
		545	}
		546
		547	sub URI::THAW {
		548	my ($class, $serialiser, $uri) = @_;
		549
		550	$class->new ($uri)
		551	}
		552
		553	Unlike C<TO_CBOR>, multiple values can be returned by C<FREEZE>. For
		554	example, a C<FREEZE> method that returns "type", "id" and "variant" values
		555	would cause an invocation of C<THAW> with 5 arguments:
		556
		557	sub My::Object::FREEZE {
		558	my ($self, $serialiser) = @_;
		559
		560	($self->{type}, $self->{id}, $self->{variant})
		561	}
		562
		563	sub My::Object::THAW {
		564	my ($class, $serialiser, $type, $id, $variant) = @_;
		565
		566	$class-<new (type => $type, id => $id, variant => $variant)
		567	}
		568
		569
268	=head2 MAGIC HEADER	570	=head1 MAGIC HEADER
269		571
270	There is no way to distinguish CBOR from other formats	572	There is no way to distinguish CBOR from other formats
271	programmatically. To make it easier to distinguish CBOR from other	573	programmatically. To make it easier to distinguish CBOR from other
272	formats, the CBOR specification has a special "magic string" that can be	574	formats, the CBOR specification has a special "magic string" that can be
273	prepended to any CBOR string without changing it's meaning.	575	prepended to any CBOR string without changing its meaning.
274		576
275	This string is available as C<$CBOR::XS::MAGIC>. This module does not	577	This string is available as C<$CBOR::XS::MAGIC>. This module does not
276	prepend this string tot he CBOR data it generates, but it will ignroe it	578	prepend this string to the CBOR data it generates, but it will ignore it
277	if present, so users can prepend this string as a "file type" indicator as	579	if present, so users can prepend this string as a "file type" indicator as
278	required.	580	required.
279		581
280		582
		583	=head1 THE CBOR::XS::Tagged CLASS
		584
		585	CBOR has the concept of tagged values - any CBOR value can be tagged with
		586	a numeric 64 bit number, which are centrally administered.
		587
		588	C<CBOR::XS> handles a few tags internally when en- or decoding. You can
		589	also create tags yourself by encoding C<CBOR::XS::Tagged> objects, and the
		590	decoder will create C<CBOR::XS::Tagged> objects itself when it hits an
		591	unknown tag.
		592
		593	These objects are simply blessed array references - the first member of
		594	the array being the numerical tag, the second being the value.
		595
		596	You can interact with C<CBOR::XS::Tagged> objects in the following ways:
		597
		598	=over 4
		599
		600	=item $tagged = CBOR::XS::tag $tag, $value
		601
		602	This function(!) creates a new C<CBOR::XS::Tagged> object using the given
		603	C<$tag> (0..2**64-1) to tag the given C<$value> (which can be any Perl
		604	value that can be encoded in CBOR, including serialisable Perl objects and
		605	C<CBOR::XS::Tagged> objects).
		606
		607	=item $tagged->[0]
		608
		609	=item $tagged->[0] = $new_tag
		610
		611	=item $tag = $tagged->tag
		612
		613	=item $new_tag = $tagged->tag ($new_tag)
		614
		615	Access/mutate the tag.
		616
		617	=item $tagged->[1]
		618
		619	=item $tagged->[1] = $new_value
		620
		621	=item $value = $tagged->value
		622
		623	=item $new_value = $tagged->value ($new_value)
		624
		625	Access/mutate the tagged value.
		626
		627	=back
		628
		629	=cut
		630
		631	sub tag($$) {
		632	bless [@_], CBOR::XS::Tagged::;
		633	}
		634
		635	sub CBOR::XS::Tagged::tag {
		636	$_[0][0] = $_[1] if $#_;
		637	$_[0][0]
		638	}
		639
		640	sub CBOR::XS::Tagged::value {
		641	$_[0][1] = $_[1] if $#_;
		642	$_[0][1]
		643	}
		644
		645	=head2 EXAMPLES
		646
		647	Here are some examples of C<CBOR::XS::Tagged> uses to tag objects.
		648
		649	You can look up CBOR tag value and emanings in the IANA registry at
		650	L<http://www.iana.org/assignments/cbor-tags/cbor-tags.xhtml>.
		651
		652	Prepend a magic header (C<$CBOR::XS::MAGIC>):
		653
		654	my $cbor = encode_cbor CBOR::XS::tag 55799, $value;
		655	# same as:
		656	my $cbor = $CBOR::XS::MAGIC . encode_cbor $value;
		657
		658	Serialise some URIs and a regex in an array:
		659
		660	my $cbor = encode_cbor [
		661	(CBOR::XS::tag 32, "http://www.nethype.de/"),
		662	(CBOR::XS::tag 32, "http://software.schmorp.de/"),
		663	(CBOR::XS::tag 35, "^[Pp][Ee][Rr][lL]\$"),
		664	];
		665
		666	Wrap CBOR data in CBOR:
		667
		668	my $cbor_cbor = encode_cbor
		669	CBOR::XS::tag 24,
		670	encode_cbor [1, 2, 3];
		671
		672	=head1 TAG HANDLING AND EXTENSIONS
		673
		674	This section describes how this module handles specific tagged values
		675	and extensions. If a tag is not mentioned here and no additional filters
		676	are provided for it, then the default handling applies (creating a
		677	CBOR::XS::Tagged object on decoding, and only encoding the tag when
		678	explicitly requested).
		679
		680	Tags not handled specifically are currently converted into a
		681	L<CBOR::XS::Tagged> object, which is simply a blessed array reference
		682	consisting of the numeric tag value followed by the (decoded) CBOR value.
		683
		684	Future versions of this module reserve the right to special case
		685	additional tags (such as base64url).
		686
		687	=head2 ENFORCED TAGS
		688
		689	These tags are always handled when decoding, and their handling cannot be
		690	overriden by the user.
		691
		692	=over 4
		693
		694	=item 26 (perl-object, L<http://cbor.schmorp.de/perl-object>)
		695
		696	These tags are automatically created (and decoded) for serialisable
		697	objects using the C<FREEZE/THAW> methods (the L<Types::Serialier> object
		698	serialisation protocol). See L<OBJECT SERIALISATION> for details.
		699
		700	=item 28, 29 (sharable, sharedref, L <http://cbor.schmorp.de/value-sharing>)
		701
		702	These tags are automatically decoded when encountered, resulting in
		703	shared values in the decoded object. They are only encoded, however, when
		704	C<allow_sharable> is enabled.
		705
		706	=item 256, 25 (stringref-namespace, stringref, L <http://cbor.schmorp.de/stringref>)
		707
		708	These tags are automatically decoded when encountered. They are only
		709	encoded, however, when C<pack_strings> is enabled.
		710
		711	=item 22098 (indirection, L<http://cbor.schmorp.de/indirection>)
		712
		713	This tag is automatically generated when a reference are encountered (with
		714	the exception of hash and array refernces). It is converted to a reference
		715	when decoding.
		716
		717	=item 55799 (self-describe CBOR, RFC 7049)
		718
		719	This value is not generated on encoding (unless explicitly requested by
		720	the user), and is simply ignored when decoding.
		721
		722	=back
		723
		724	=head2 NON-ENFORCED TAGS
		725
		726	These tags have default filters provided when decoding. Their handling can
		727	be overriden by changing the C<%CBOR::XS::FILTER> entry for the tag, or by
		728	providing a custom C<filter> callback when decoding.
		729
		730	When they result in decoding into a specific Perl class, the module
		731	usually provides a corresponding C<TO_CBOR> method as well.
		732
		733	When any of these need to load additional modules that are not part of the
		734	perl core distribution (e.g. L<URI>), it is (currently) up to the user to
		735	provide these modules. The decoding usually fails with an exception if the
		736	required module cannot be loaded.
		737
		738	=over 4
		739
		740	=item 2, 3 (positive/negative bignum)
		741
		742	These tags are decoded into L<Math::BigInt> objects. The corresponding
		743	C<Math::BigInt::TO_CBOR> method encodes "small" bigints into normal CBOR
		744	integers, and others into positive/negative CBOR bignums.
		745
		746	=item 4, 5 (decimal fraction/bigfloat)
		747
		748	Both decimal fractions and bigfloats are decoded into L<Math::BigFloat>
		749	objects. The corresponding C<Math::BigFloat::TO_CBOR> method I<always>
		750	encodes into a decimal fraction.
		751
		752	CBOR cannot represent bigfloats with I<very> large exponents - conversion
		753	of such big float objects is undefined.
		754
		755	Also, NaN and infinities are not encoded properly.
		756
		757	=item 21, 22, 23 (expected later JSON conversion)
		758
		759	CBOR::XS is not a CBOR-to-JSON converter, and will simply ignore these
		760	tags.
		761
		762	=item 32 (URI)
		763
		764	These objects decode into L<URI> objects. The corresponding
		765	C<URI::TO_CBOR> method again results in a CBOR URI value.
		766
		767	=back
		768
		769	=cut
		770
		771	our %FILTER = (
		772	# 0 # rfc4287 datetime, utf-8
		773	# 1 # unix timestamp, any
		774
		775	2 => sub { # pos bigint
		776	require Math::BigInt;
		777	Math::BigInt->new ("0x" . unpack "H*", pop)
		778	},
		779
		780	3 => sub { # neg bigint
		781	require Math::BigInt;
		782	-Math::BigInt->new ("0x" . unpack "H*", pop)
		783	},
		784
		785	4 => sub { # decimal fraction, array
		786	require Math::BigFloat;
		787	Math::BigFloat->new ($_[1][1] . "E" . $_[1][0])
		788	},
		789
		790	5 => sub { # bigfloat, array
		791	require Math::BigFloat;
		792	scalar Math::BigFloat->new ($_[1][1])->blsft ($_[1][0], 2)
		793	},
		794
		795	21 => sub { pop }, # expected conversion to base64url encoding
		796	22 => sub { pop }, # expected conversion to base64 encoding
		797	23 => sub { pop }, # expected conversion to base16 encoding
		798
		799	# 24 # embedded cbor, byte string
		800
		801	32 => sub {
		802	require URI;
		803	URI->new (pop)
		804	},
		805
		806	# 33 # base64url rfc4648, utf-8
		807	# 34 # base64 rfc46484, utf-8
		808	# 35 # regex pcre/ecma262, utf-8
		809	# 36 # mime message rfc2045, utf-8
		810	);
		811
		812
281	=head2 CBOR and JSON	813	=head1 CBOR and JSON
282		814
283	TODO	815	CBOR is supposed to implement a superset of the JSON data model, and is,
		816	with some coercion, able to represent all JSON texts (something that other
		817	"binary JSON" formats such as BSON generally do not support).
		818
		819	CBOR implements some extra hints and support for JSON interoperability,
		820	and the spec offers further guidance for conversion between CBOR and
		821	JSON. None of this is currently implemented in CBOR, and the guidelines
		822	in the spec do not result in correct round-tripping of data. If JSON
		823	interoperability is improved in the future, then the goal will be to
		824	ensure that decoded JSON data will round-trip encoding and decoding to
		825	CBOR intact.
284		826
285		827
286	=head1 SECURITY CONSIDERATIONS	828	=head1 SECURITY CONSIDERATIONS
287		829
288	When you are using CBOR in a protocol, talking to untrusted potentially	830	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	898	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.	899	service. I put the contact address into my modules for a reason.
358		900
359	=cut	901	=cut
360		902
361	our $true = do { bless \(my $dummy = 1), "CBOR::XS::Boolean" };	903	our %FILTER = (
362	our $false = do { bless \(my $dummy = 0), "CBOR::XS::Boolean" };	904	# 0 # rfc4287 datetime, utf-8
		905	# 1 # unix timestamp, any
363		906
364	sub true() { $true }	907	2 => sub { # pos bigint
365	sub false() { $false }	908	require Math::BigInt;
		909	Math::BigInt->new ("0x" . unpack "H*", pop)
		910	},
366		911
367	sub is_bool($) {	912	3 => sub { # neg bigint
368	UNIVERSAL::isa $_[0], "CBOR::XS::Boolean"	913	require Math::BigInt;
369	# or UNIVERSAL::isa $_[0], "CBOR::Literal"	914	-Math::BigInt->new ("0x" . unpack "H*", pop)
		915	},
		916
		917	4 => sub { # decimal fraction, array
		918	require Math::BigFloat;
		919	Math::BigFloat->new ($_[1][1] . "E" . $_[1][0])
		920	},
		921
		922	5 => sub { # bigfloat, array
		923	require Math::BigFloat;
		924	scalar Math::BigFloat->new ($_[1][1])->blsft ($_[1][0], 2)
		925	},
		926
		927	21 => sub { pop }, # expected conversion to base64url encoding
		928	22 => sub { pop }, # expected conversion to base64 encoding
		929	23 => sub { pop }, # expected conversion to base16 encoding
		930
		931	# 24 # embedded cbor, byte string
		932
		933	32 => sub {
		934	require URI;
		935	URI->new (pop)
		936	},
		937
		938	# 33 # base64url rfc4648, utf-8
		939	# 34 # base64 rfc46484, utf-8
		940	# 35 # regex pcre/ecma262, utf-8
		941	# 36 # mime message rfc2045, utf-8
		942	);
		943
		944	sub CBOR::XS::default_filter {
		945	&{ $FILTER{$_[0]} or return }
370	}	946	}
371		947
		948	sub URI::TO_CBOR {
		949	my $uri = $_[0]->as_string;
		950	utf8::upgrade $uri;
		951	CBOR::XS::tag 32, $uri
		952	}
		953
		954	sub Math::BigInt::TO_CBOR {
		955	if ($_[0] >= -2147483648 && $_[0] <= 2147483647) {
		956	$_[0]->numify
		957	} else {
		958	my $hex = substr $_[0]->as_hex, 2;
		959	$hex = "0$hex" if 1 & length $hex; # sigh
		960	CBOR::XS::tag $_[0] >= 0 ? 2 : 3, pack "H*", $hex
		961	}
		962	}
		963
		964	sub Math::BigFloat::TO_CBOR {
		965	my ($m, $e) = $_[0]->parts;
		966	CBOR::XS::tag 4, [$e->numify, $m]
		967	}
		968
372	XSLoader::load "CBOR::XS", $VERSION;	969	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		970
384	=head1 SEE ALSO	971	=head1 SEE ALSO
385		972
386	The L<JSON> and L<JSON::XS> modules that do similar, but human-readable,	973	The L<JSON> and L<JSON::XS> modules that do similar, but human-readable,
387	serialisation.	974	serialisation.
388		975
		976	The L<Types::Serialiser> module provides the data model for true, false
		977	and error values.
		978
389	=head1 AUTHOR	979	=head1 AUTHOR
390		980
391	Marc Lehmann <schmorp@schmorp.de>	981	Marc Lehmann <schmorp@schmorp.de>
392	http://home.schmorp.de/	982	http://home.schmorp.de/
393		983
394	=cut	984	=cut
395		985
		986	1
		987

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 1.27 by root, Thu Nov 28 15:43:24 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 1.27 by root, Thu Nov 28 15:43:24 2013 UTC