[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 1.32 by root, Sat Nov 30 18:42:27 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	This module converts Perl data structures to the Concise Binary Object
22	EAT YOUR CHILDREN!	32	Representation (CBOR) and vice versa. CBOR is a fast binary serialisation
		33	format that aims to use an (almost) superset of the JSON data model, i.e.
		34	when you can represent something useful in JSON, you should be able to
		35	represent it in CBOR.
23		36
24	This module converts Perl data structures to CBOR and vice versa. Its	37	In short, CBOR is a faster and quite compact binary alternative to JSON,
		38	with the added ability of supporting serialisation of Perl objects. (JSON
		39	often compresses better than CBOR though, so if you plan to compress the
		40	data later and speed is less important you might want to compare both
		41	formats first).
		42
		43	To give you a general idea about speed, with texts in the megabyte range,
		44	C<CBOR::XS> usually encodes roughly twice as fast as L<Storable> or
		45	L<JSON::XS> and decodes about 15%-30% faster than those. The shorter the
		46	data, the worse L<Storable> performs in comparison.
		47
		48	Regarding compactness, C<CBOR::XS>-encoded data structures are usually
		49	about 20% smaller than the same data encoded as (compact) JSON or
		50	L<Storable>.
		51
		52	In addition to the core CBOR data format, this module implements a
		53	number of extensions, to support cyclic and shared data structures
		54	(see C<allow_sharing> and C<allow_cycles>), string deduplication (see
		55	C<pack_strings>) and scalar references (always enabled).
		56
25	primary goal is to be I<correct> and its secondary goal is to be	57	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.	58	is to be I<fast>. To reach the latter goal it was written in C.
27		59
28	See MAPPING, below, on how CBOR::XS maps perl values to CBOR values and	60	See MAPPING, below, on how CBOR::XS maps perl values to CBOR values and
29	vice versa.	61	vice versa.
30		62
31	=cut	63	=cut
32		64
33	package CBOR::XS;	65	package CBOR::XS;
34		66
35	use common::sense;	67	use common::sense;
36		68
37	our $VERSION = 0.02;	69	our $VERSION = 1.1;
38	our @ISA = qw(Exporter);	70	our @ISA = qw(Exporter);
39		71
40	our @EXPORT = qw(encode_cbor decode_cbor);	72	our @EXPORT = qw(encode_cbor decode_cbor);
41		73
42	use Exporter;	74	use Exporter;
43	use XSLoader;	75	use XSLoader;
44		76
		77	use Types::Serialiser;
		78
45	our $MAGIC = "\xd9\xd9\xf7";	79	our $MAGIC = "\xd9\xd9\xf7";
46		80
47	=head1 FUNCTIONAL INTERFACE	81	=head1 FUNCTIONAL INTERFACE
48		82
49	The following convenience methods are provided by this module. They are	83	The following convenience methods are provided by this module. They are
…		…
77	strings. All boolean flags described below are by default I<disabled>.	111	strings. All boolean flags described below are by default I<disabled>.
78		112
79	The mutators for flags all return the CBOR object again and thus calls can	113	The mutators for flags all return the CBOR object again and thus calls can
80	be chained:	114	be chained:
81		115
82	#TODO
83	my $cbor = CBOR::XS->new->encode ({a => [1,2]});	116	my $cbor = CBOR::XS->new->encode ({a => [1,2]});
84		117
85	=item $cbor = $cbor->max_depth ([$maximum_nesting_depth])	118	=item $cbor = $cbor->max_depth ([$maximum_nesting_depth])
86		119
87	=item $max_depth = $cbor->get_max_depth	120	=item $max_depth = $cbor->get_max_depth
…		…
121	If no argument is given, the limit check will be deactivated (same as when	154	If no argument is given, the limit check will be deactivated (same as when
122	C<0> is specified).	155	C<0> is specified).
123		156
124	See SECURITY CONSIDERATIONS, below, for more info on why this is useful.	157	See SECURITY CONSIDERATIONS, below, for more info on why this is useful.
125		158
		159	=item $cbor = $cbor->allow_unknown ([$enable])
		160
		161	=item $enabled = $cbor->get_allow_unknown
		162
		163	If C<$enable> is true (or missing), then C<encode> will I<not> throw an
		164	exception when it encounters values it cannot represent in CBOR (for
		165	example, filehandles) but instead will encode a CBOR C<error> value.
		166
		167	If C<$enable> is false (the default), then C<encode> will throw an
		168	exception when it encounters anything it cannot encode as CBOR.
		169
		170	This option does not affect C<decode> in any way, and it is recommended to
		171	leave it off unless you know your communications partner.
		172
		173	=item $cbor = $cbor->allow_sharing ([$enable])
		174
		175	=item $enabled = $cbor->get_allow_sharing
		176
		177	If C<$enable> is true (or missing), then C<encode> will not double-encode
		178	values that have been referenced before (e.g. when the same object, such
		179	as an array, is referenced multiple times), but instead will emit a
		180	reference to the earlier value.
		181
		182	This means that such values will only be encoded once, and will not result
		183	in a deep cloning of the value on decode, in decoders supporting the value
		184	sharing extension. This also makes it possible to encode cyclic data
		185	structures (which need C<allow_cycles> to ne enabled to be decoded by this
		186	module).
		187
		188	It is recommended to leave it off unless you know your
		189	communication partner supports the value sharing extensions to CBOR
		190	(L<http://cbor.schmorp.de/value-sharing>), as without decoder support, the
		191	resulting data structure might be unusable.
		192
		193	Detecting shared values incurs a runtime overhead when values are encoded
		194	that have a reference counter large than one, and might unnecessarily
		195	increase the encoded size, as potentially shared values are encode as
		196	shareable whether or not they are actually shared.
		197
		198	At the moment, only targets of references can be shared (e.g. scalars,
		199	arrays or hashes pointed to by a reference). Weirder constructs, such as
		200	an array with multiple "copies" of the I<same> string, which are hard but
		201	not impossible to create in Perl, are not supported (this is the same as
		202	with L<Storable>).
		203
		204	If C<$enable> is false (the default), then C<encode> will encode shared
		205	data structures repeatedly, unsharing them in the process. Cyclic data
		206	structures cannot be encoded in this mode.
		207
		208	This option does not affect C<decode> in any way - shared values and
		209	references will always be decoded properly if present.
		210
		211	=item $cbor = $cbor->allow_cycles ([$enable])
		212
		213	=item $enabled = $cbor->get_allow_cycles
		214
		215	If C<$enable> is true (or missing), then C<decode> will happily decode
		216	self-referential (cyclic) data structures. By default these will not be
		217	decoded, as they need manual cleanup to avoid memory leaks, so code that
		218	isn't prepared for this will not leak memory.
		219
		220	If C<$enable> is false (the default), then C<decode> will throw an error
		221	when it encounters a self-referential/cyclic data structure.
		222
		223	This option does not affect C<encode> in any way - shared values and
		224	references will always be decoded properly if present.
		225
		226	=item $cbor = $cbor->pack_strings ([$enable])
		227
		228	=item $enabled = $cbor->get_pack_strings
		229
		230	If C<$enable> is true (or missing), then C<encode> will try not to encode
		231	the same string twice, but will instead encode a reference to the string
		232	instead. Depending on your data format, this can save a lot of space, but
		233	also results in a very large runtime overhead (expect encoding times to be
		234	2-4 times as high as without).
		235
		236	It is recommended to leave it off unless you know your
		237	communications partner supports the stringref extension to CBOR
		238	(L<http://cbor.schmorp.de/stringref>), as without decoder support, the
		239	resulting data structure might not be usable.
		240
		241	If C<$enable> is false (the default), then C<encode> will encode strings
		242	the standard CBOR way.
		243
		244	This option does not affect C<decode> in any way - string references will
		245	always be decoded properly if present.
		246
		247	=item $cbor = $cbor->filter ([$cb->($tag, $value)])
		248
		249	=item $cb_or_undef = $cbor->get_filter
		250
		251	Sets or replaces the tagged value decoding filter (when C<$cb> is
		252	specified) or clears the filter (if no argument or C<undef> is provided).
		253
		254	The filter callback is called only during decoding, when a non-enforced
		255	tagged value has been decoded (see L<TAG HANDLING AND EXTENSIONS> for a
		256	list of enforced tags). For specific tags, it's often better to provide a
		257	default converter using the C<%CBOR::XS::FILTER> hash (see below).
		258
		259	The first argument is the numerical tag, the second is the (decoded) value
		260	that has been tagged.
		261
		262	The filter function should return either exactly one value, which will
		263	replace the tagged value in the decoded data structure, or no values,
		264	which will result in default handling, which currently means the decoder
		265	creates a C<CBOR::XS::Tagged> object to hold the tag and the value.
		266
		267	When the filter is cleared (the default state), the default filter
		268	function, C<CBOR::XS::default_filter>, is used. This function simply looks
		269	up the tag in the C<%CBOR::XS::FILTER> hash. If an entry exists it must be
		270	a code reference that is called with tag and value, and is responsible for
		271	decoding the value. If no entry exists, it returns no values.
		272
		273	Example: decode all tags not handled internally into C<CBOR::XS::Tagged>
		274	objects, with no other special handling (useful when working with
		275	potentially "unsafe" CBOR data).
		276
		277	CBOR::XS->new->filter (sub { })->decode ($cbor_data);
		278
		279	Example: provide a global filter for tag 1347375694, converting the value
		280	into some string form.
		281
		282	$CBOR::XS::FILTER{1347375694} = sub {
		283	my ($tag, $value);
		284
		285	"tag 1347375694 value $value"
		286	};
		287
126	=item $cbor_data = $cbor->encode ($perl_scalar)	288	=item $cbor_data = $cbor->encode ($perl_scalar)
127		289
128	Converts the given Perl data structure (a scalar value) to its CBOR	290	Converts the given Perl data structure (a scalar value) to its CBOR
129	representation.	291	representation.
130		292
…		…
163		325
164	=head2 CBOR -> PERL	326	=head2 CBOR -> PERL
165		327
166	=over 4	328	=over 4
167		329
168	=item True, False	330	=item integers
169		331
170	These CBOR values become C<CBOR::XS::true> and C<CBOR::XS::false>,	332	CBOR integers become (numeric) perl scalars. On perls without 64 bit
		333	support, 64 bit integers will be truncated or otherwise corrupted.
		334
		335	=item byte strings
		336
		337	Byte strings will become octet strings in Perl (the Byte values 0..255
		338	will simply become characters of the same value in Perl).
		339
		340	=item UTF-8 strings
		341
		342	UTF-8 strings in CBOR will be decoded, i.e. the UTF-8 octets will be
		343	decoded into proper Unicode code points. At the moment, the validity of
		344	the UTF-8 octets will not be validated - corrupt input will result in
		345	corrupted Perl strings.
		346
		347	=item arrays, maps
		348
		349	CBOR arrays and CBOR maps will be converted into references to a Perl
		350	array or hash, respectively. The keys of the map will be stringified
		351	during this process.
		352
		353	=item null
		354
		355	CBOR null becomes C<undef> in Perl.
		356
		357	=item true, false, undefined
		358
		359	These CBOR values become C<Types:Serialiser::true>,
		360	C<Types:Serialiser::false> and C<Types::Serialiser::error>,
171	respectively. They are overloaded to act almost exactly like the numbers	361	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	362	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.	363	error). See the L<Types::Serialiser> manpage for details.
174		364
175	=item Null, Undefined	365	=item tagged values
176		366
177	CBOR Null and Undefined values becomes C<undef> in Perl (in the future,	367	Tagged items consists of a numeric tag and another CBOR value.
178	Undefined may raise an exception).	368
		369	See L<TAG HANDLING AND EXTENSIONS> and the description of C<< ->filter >>
		370	for details on which tags are handled how.
		371
		372	=item anything else
		373
		374	Anything else (e.g. unsupported simple values) will raise a decoding
		375	error.
179		376
180	=back	377	=back
181		378
182		379
183	=head2 PERL -> CBOR	380	=head2 PERL -> CBOR
184		381
185	The mapping from Perl to CBOR is slightly more difficult, as Perl is a	382	The mapping from Perl to CBOR is slightly more difficult, as Perl is a
186	truly typeless language, so we can only guess which CBOR type is meant by	383	typeless language. That means this module can only guess which CBOR type
187	a Perl value.	384	is meant by a perl value.
188		385
189	=over 4	386	=over 4
190		387
191	=item hash references	388	=item hash references
192		389
193	Perl hash references become CBOR maps. As there is no inherent ordering	390	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	391	hash keys (or CBOR maps), they will usually be encoded in a pseudo-random
195	pseudo-random order.	392	order. This order can be different each time a hahs is encoded.
		393
		394	Currently, tied hashes will use the indefinite-length format, while normal
		395	hashes will use the fixed-length format.
196		396
197	=item array references	397	=item array references
198		398
199	Perl array references become CBOR arrays.	399	Perl array references become fixed-length CBOR arrays.
200		400
201	=item other references	401	=item other references
202		402
203	Other unblessed references are generally not allowed and will cause an	403	Other unblessed references will be represented using
204	exception to be thrown, except for references to the integers C<0> and	404	the indirection tag extension (tag value C<22098>,
205	C<1>, which get turned into C<False> and C<True> in CBOR.	405	L<http://cbor.schmorp.de/indirection>). CBOR decoders are guaranteed
		406	to be able to decode these values somehow, by either "doing the right
		407	thing", decoding into a generic tagged object, simply ignoring the tag, or
		408	something else.
206		409
207	=item CBOR::XS::true, CBOR::XS::false	410	=item CBOR::XS::Tagged objects
208		411
		412	Objects of this type must be arrays consisting of a single C<[tag, value]>
		413	pair. The (numerical) tag will be encoded as a CBOR tag, the value will
		414	be encoded as appropriate for the value. You must use C<CBOR::XS::tag> to
		415	create such objects.
		416
		417	=item Types::Serialiser::true, Types::Serialiser::false, Types::Serialiser::error
		418
209	These special values become CBOR True and CBOR False values,	419	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.	420	values, respectively. You can also use C<\1>, C<\0> and C<\undef> directly
		421	if you want.
211		422
212	=item blessed objects	423	=item other blessed objects
213		424
214	Blessed objects are not directly representable in CBOR. TODO	425	Other blessed objects are serialised via C<TO_CBOR> or C<FREEZE>. See
215	See the	426	L<TAG HANDLING AND EXTENSIONS> for specific classes handled by this
216	C<allow_blessed> and C<convert_blessed> methods on various options on	427	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		428
221	=item simple scalars	429	=item simple scalars
222		430
223	TODO
224	Simple Perl scalars (any scalar that is not a reference) are the most	431	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	432	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	433	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:	434	before encoding as CBOR strings, and anything else as number value:
228		435
229	# dump as number	436	# dump as number
230	encode_cbor [2] # yields [2]	437	encode_cbor [2] # yields [2]
231	encode_cbor [-3.0e17] # yields [-3e+17]	438	encode_cbor [-3.0e17] # yields [-3e+17]
232	my $value = 5; encode_cbor [$value] # yields [5]	439	my $value = 5; encode_cbor [$value] # yields [5]
233		440
234	# used as string, so dump as string	441	# used as string, so dump as string (either byte or text)
235	print $value;	442	print $value;
236	encode_cbor [$value] # yields ["5"]	443	encode_cbor [$value] # yields ["5"]
237		444
238	# undef becomes null	445	# undef becomes null
239	encode_cbor [undef] # yields [null]	446	encode_cbor [undef] # yields [null]
…		…
243	my $x = 3.1; # some variable containing a number	450	my $x = 3.1; # some variable containing a number
244	"$x"; # stringified	451	"$x"; # stringified
245	$x .= ""; # another, more awkward way to stringify	452	$x .= ""; # another, more awkward way to stringify
246	print $x; # perl does it for you, too, quite often	453	print $x; # perl does it for you, too, quite often
247		454
		455	You can force whether a string ie encoded as byte or text string by using
		456	C<utf8::upgrade> and C<utf8::downgrade>):
		457
		458	utf8::upgrade $x; # encode $x as text string
		459	utf8::downgrade $x; # encode $x as byte string
		460
		461	Perl doesn't define what operations up- and downgrade strings, so if the
		462	difference between byte and text is important, you should up- or downgrade
		463	your string as late as possible before encoding.
		464
248	You can force the type to be a CBOR number by numifying it:	465	You can force the type to be a CBOR number by numifying it:
249		466
250	my $x = "3"; # some variable containing a string	467	my $x = "3"; # some variable containing a string
251	$x += 0; # numify it, ensuring it will be dumped as a number	468	$x += 0; # numify it, ensuring it will be dumped as a number
252	$x *= 1; # same thing, the choice is yours.	469	$x *= 1; # same thing, the choice is yours.
253		470
254	You can not currently force the type in other, less obscure, ways. Tell me	471	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	472	if you need this capability (but don't forget to explain why it's needed
256	:).	473	:).
257		474
258	Note that numerical precision has the same meaning as under Perl (so	475	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	476	representation. Floating-point values will use either the IEEE single
260	can differ to other languages). Also, your perl interpreter might expose	477	format if possible without loss of precision, otherwise the IEEE double
261	extensions to the floating point numbers of your platform, such as	478	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	479	represent numerical values are supported, but might suffer loss of
263	error to pass those in.	480	precision.
264		481
265	=back	482	=back
266		483
		484	=head2 OBJECT SERIALISATION
267		485
		486	This module implements both a CBOR-specific and the generic
		487	L<Types::Serialier> object serialisation protocol. The following
		488	subsections explain both methods.
		489
		490	=head3 ENCODING
		491
		492	This module knows two way to serialise a Perl object: The CBOR-specific
		493	way, and the generic way.
		494
		495	Whenever the encoder encounters a Perl object that it cannot serialise
		496	directly (most of them), it will first look up the C<TO_CBOR> method on
		497	it.
		498
		499	If it has a C<TO_CBOR> method, it will call it with the object as only
		500	argument, and expects exactly one return value, which it will then
		501	substitute and encode it in the place of the object.
		502
		503	Otherwise, it will look up the C<FREEZE> method. If it exists, it will
		504	call it with the object as first argument, and the constant string C<CBOR>
		505	as the second argument, to distinguish it from other serialisers.
		506
		507	The C<FREEZE> method can return any number of values (i.e. zero or
		508	more). These will be encoded as CBOR perl object, together with the
		509	classname.
		510
		511	These methods I<MUST NOT> change the data structure that is being
		512	serialised. Failure to comply to this can result in memory corruption -
		513	and worse.
		514
		515	If an object supports neither C<TO_CBOR> nor C<FREEZE>, encoding will fail
		516	with an error.
		517
		518	=head3 DECODING
		519
		520	Objects encoded via C<TO_CBOR> cannot (normally) be automatically decoded,
		521	but objects encoded via C<FREEZE> can be decoded using the following
		522	protocol:
		523
		524	When an encoded CBOR perl object is encountered by the decoder, it will
		525	look up the C<THAW> method, by using the stored classname, and will fail
		526	if the method cannot be found.
		527
		528	After the lookup it will call the C<THAW> method with the stored classname
		529	as first argument, the constant string C<CBOR> as second argument, and all
		530	values returned by C<FREEZE> as remaining arguments.
		531
		532	=head3 EXAMPLES
		533
		534	Here is an example C<TO_CBOR> method:
		535
		536	sub My::Object::TO_CBOR {
		537	my ($obj) = @_;
		538
		539	["this is a serialised My::Object object", $obj->{id}]
		540	}
		541
		542	When a C<My::Object> is encoded to CBOR, it will instead encode a simple
		543	array with two members: a string, and the "object id". Decoding this CBOR
		544	string will yield a normal perl array reference in place of the object.
		545
		546	A more useful and practical example would be a serialisation method for
		547	the URI module. CBOR has a custom tag value for URIs, namely 32:
		548
		549	sub URI::TO_CBOR {
		550	my ($self) = @_;
		551	my $uri = "$self"; # stringify uri
		552	utf8::upgrade $uri; # make sure it will be encoded as UTF-8 string
		553	CBOR::XS::tag 32, "$_[0]"
		554	}
		555
		556	This will encode URIs as a UTF-8 string with tag 32, which indicates an
		557	URI.
		558
		559	Decoding such an URI will not (currently) give you an URI object, but
		560	instead a CBOR::XS::Tagged object with tag number 32 and the string -
		561	exactly what was returned by C<TO_CBOR>.
		562
		563	To serialise an object so it can automatically be deserialised, you need
		564	to use C<FREEZE> and C<THAW>. To take the URI module as example, this
		565	would be a possible implementation:
		566
		567	sub URI::FREEZE {
		568	my ($self, $serialiser) = @_;
		569	"$self" # encode url string
		570	}
		571
		572	sub URI::THAW {
		573	my ($class, $serialiser, $uri) = @_;
		574
		575	$class->new ($uri)
		576	}
		577
		578	Unlike C<TO_CBOR>, multiple values can be returned by C<FREEZE>. For
		579	example, a C<FREEZE> method that returns "type", "id" and "variant" values
		580	would cause an invocation of C<THAW> with 5 arguments:
		581
		582	sub My::Object::FREEZE {
		583	my ($self, $serialiser) = @_;
		584
		585	($self->{type}, $self->{id}, $self->{variant})
		586	}
		587
		588	sub My::Object::THAW {
		589	my ($class, $serialiser, $type, $id, $variant) = @_;
		590
		591	$class-<new (type => $type, id => $id, variant => $variant)
		592	}
		593
		594
268	=head2 MAGIC HEADER	595	=head1 MAGIC HEADER
269		596
270	There is no way to distinguish CBOR from other formats	597	There is no way to distinguish CBOR from other formats
271	programmatically. To make it easier to distinguish CBOR from other	598	programmatically. To make it easier to distinguish CBOR from other
272	formats, the CBOR specification has a special "magic string" that can be	599	formats, the CBOR specification has a special "magic string" that can be
273	prepended to any CBOR string without changing it's meaning.	600	prepended to any CBOR string without changing its meaning.
274		601
275	This string is available as C<$CBOR::XS::MAGIC>. This module does not	602	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	603	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	604	if present, so users can prepend this string as a "file type" indicator as
278	required.	605	required.
279		606
280		607
		608	=head1 THE CBOR::XS::Tagged CLASS
		609
		610	CBOR has the concept of tagged values - any CBOR value can be tagged with
		611	a numeric 64 bit number, which are centrally administered.
		612
		613	C<CBOR::XS> handles a few tags internally when en- or decoding. You can
		614	also create tags yourself by encoding C<CBOR::XS::Tagged> objects, and the
		615	decoder will create C<CBOR::XS::Tagged> objects itself when it hits an
		616	unknown tag.
		617
		618	These objects are simply blessed array references - the first member of
		619	the array being the numerical tag, the second being the value.
		620
		621	You can interact with C<CBOR::XS::Tagged> objects in the following ways:
		622
		623	=over 4
		624
		625	=item $tagged = CBOR::XS::tag $tag, $value
		626
		627	This function(!) creates a new C<CBOR::XS::Tagged> object using the given
		628	C<$tag> (0..2**64-1) to tag the given C<$value> (which can be any Perl
		629	value that can be encoded in CBOR, including serialisable Perl objects and
		630	C<CBOR::XS::Tagged> objects).
		631
		632	=item $tagged->[0]
		633
		634	=item $tagged->[0] = $new_tag
		635
		636	=item $tag = $tagged->tag
		637
		638	=item $new_tag = $tagged->tag ($new_tag)
		639
		640	Access/mutate the tag.
		641
		642	=item $tagged->[1]
		643
		644	=item $tagged->[1] = $new_value
		645
		646	=item $value = $tagged->value
		647
		648	=item $new_value = $tagged->value ($new_value)
		649
		650	Access/mutate the tagged value.
		651
		652	=back
		653
		654	=cut
		655
		656	sub tag($$) {
		657	bless [@_], CBOR::XS::Tagged::;
		658	}
		659
		660	sub CBOR::XS::Tagged::tag {
		661	$_[0][0] = $_[1] if $#_;
		662	$_[0][0]
		663	}
		664
		665	sub CBOR::XS::Tagged::value {
		666	$_[0][1] = $_[1] if $#_;
		667	$_[0][1]
		668	}
		669
		670	=head2 EXAMPLES
		671
		672	Here are some examples of C<CBOR::XS::Tagged> uses to tag objects.
		673
		674	You can look up CBOR tag value and emanings in the IANA registry at
		675	L<http://www.iana.org/assignments/cbor-tags/cbor-tags.xhtml>.
		676
		677	Prepend a magic header (C<$CBOR::XS::MAGIC>):
		678
		679	my $cbor = encode_cbor CBOR::XS::tag 55799, $value;
		680	# same as:
		681	my $cbor = $CBOR::XS::MAGIC . encode_cbor $value;
		682
		683	Serialise some URIs and a regex in an array:
		684
		685	my $cbor = encode_cbor [
		686	(CBOR::XS::tag 32, "http://www.nethype.de/"),
		687	(CBOR::XS::tag 32, "http://software.schmorp.de/"),
		688	(CBOR::XS::tag 35, "^[Pp][Ee][Rr][lL]\$"),
		689	];
		690
		691	Wrap CBOR data in CBOR:
		692
		693	my $cbor_cbor = encode_cbor
		694	CBOR::XS::tag 24,
		695	encode_cbor [1, 2, 3];
		696
		697	=head1 TAG HANDLING AND EXTENSIONS
		698
		699	This section describes how this module handles specific tagged values
		700	and extensions. If a tag is not mentioned here and no additional filters
		701	are provided for it, then the default handling applies (creating a
		702	CBOR::XS::Tagged object on decoding, and only encoding the tag when
		703	explicitly requested).
		704
		705	Tags not handled specifically are currently converted into a
		706	L<CBOR::XS::Tagged> object, which is simply a blessed array reference
		707	consisting of the numeric tag value followed by the (decoded) CBOR value.
		708
		709	Future versions of this module reserve the right to special case
		710	additional tags (such as base64url).
		711
		712	=head2 ENFORCED TAGS
		713
		714	These tags are always handled when decoding, and their handling cannot be
		715	overriden by the user.
		716
		717	=over 4
		718
		719	=item 26 (perl-object, L<http://cbor.schmorp.de/perl-object>)
		720
		721	These tags are automatically created (and decoded) for serialisable
		722	objects using the C<FREEZE/THAW> methods (the L<Types::Serialier> object
		723	serialisation protocol). See L<OBJECT SERIALISATION> for details.
		724
		725	=item 28, 29 (shareable, sharedref, L <http://cbor.schmorp.de/value-sharing>)
		726
		727	These tags are automatically decoded when encountered (and they do not
		728	result in a cyclic data structure, see C<allow_cycles>), resulting in
		729	shared values in the decoded object. They are only encoded, however, when
		730	C<allow_sharing> is enabled.
		731
		732	Not all shared values can be successfully decoded: values that reference
		733	themselves will I<currently> decode as C<undef> (this is not the same
		734	as a reference pointing to itself, which will be represented as a value
		735	that contains an indirect reference to itself - these will be decoded
		736	properly).
		737
		738	Note that considerably more shared value data structures can be decoded
		739	than will be encoded - currently, only values pointed to by references
		740	will be shared, others will not. While non-reference shared values can be
		741	generated in Perl with some effort, they were considered too unimportant
		742	to be supported in the encoder. The decoder, however, will decode these
		743	values as shared values.
		744
		745	=item 256, 25 (stringref-namespace, stringref, L <http://cbor.schmorp.de/stringref>)
		746
		747	These tags are automatically decoded when encountered. They are only
		748	encoded, however, when C<pack_strings> is enabled.
		749
		750	=item 22098 (indirection, L<http://cbor.schmorp.de/indirection>)
		751
		752	This tag is automatically generated when a reference are encountered (with
		753	the exception of hash and array refernces). It is converted to a reference
		754	when decoding.
		755
		756	=item 55799 (self-describe CBOR, RFC 7049)
		757
		758	This value is not generated on encoding (unless explicitly requested by
		759	the user), and is simply ignored when decoding.
		760
		761	=back
		762
		763	=head2 NON-ENFORCED TAGS
		764
		765	These tags have default filters provided when decoding. Their handling can
		766	be overriden by changing the C<%CBOR::XS::FILTER> entry for the tag, or by
		767	providing a custom C<filter> callback when decoding.
		768
		769	When they result in decoding into a specific Perl class, the module
		770	usually provides a corresponding C<TO_CBOR> method as well.
		771
		772	When any of these need to load additional modules that are not part of the
		773	perl core distribution (e.g. L<URI>), it is (currently) up to the user to
		774	provide these modules. The decoding usually fails with an exception if the
		775	required module cannot be loaded.
		776
		777	=over 4
		778
		779	=item 2, 3 (positive/negative bignum)
		780
		781	These tags are decoded into L<Math::BigInt> objects. The corresponding
		782	C<Math::BigInt::TO_CBOR> method encodes "small" bigints into normal CBOR
		783	integers, and others into positive/negative CBOR bignums.
		784
		785	=item 4, 5 (decimal fraction/bigfloat)
		786
		787	Both decimal fractions and bigfloats are decoded into L<Math::BigFloat>
		788	objects. The corresponding C<Math::BigFloat::TO_CBOR> method I<always>
		789	encodes into a decimal fraction.
		790
		791	CBOR cannot represent bigfloats with I<very> large exponents - conversion
		792	of such big float objects is undefined.
		793
		794	Also, NaN and infinities are not encoded properly.
		795
		796	=item 21, 22, 23 (expected later JSON conversion)
		797
		798	CBOR::XS is not a CBOR-to-JSON converter, and will simply ignore these
		799	tags.
		800
		801	=item 32 (URI)
		802
		803	These objects decode into L<URI> objects. The corresponding
		804	C<URI::TO_CBOR> method again results in a CBOR URI value.
		805
		806	=back
		807
		808	=cut
		809
		810	our %FILTER = (
		811	# 0 # rfc4287 datetime, utf-8
		812	# 1 # unix timestamp, any
		813
		814	2 => sub { # pos bigint
		815	require Math::BigInt;
		816	Math::BigInt->new ("0x" . unpack "H*", pop)
		817	},
		818
		819	3 => sub { # neg bigint
		820	require Math::BigInt;
		821	-Math::BigInt->new ("0x" . unpack "H*", pop)
		822	},
		823
		824	4 => sub { # decimal fraction, array
		825	require Math::BigFloat;
		826	Math::BigFloat->new ($_[1][1] . "E" . $_[1][0])
		827	},
		828
		829	5 => sub { # bigfloat, array
		830	require Math::BigFloat;
		831	scalar Math::BigFloat->new ($_[1][1])->blsft ($_[1][0], 2)
		832	},
		833
		834	21 => sub { pop }, # expected conversion to base64url encoding
		835	22 => sub { pop }, # expected conversion to base64 encoding
		836	23 => sub { pop }, # expected conversion to base16 encoding
		837
		838	# 24 # embedded cbor, byte string
		839
		840	32 => sub {
		841	require URI;
		842	URI->new (pop)
		843	},
		844
		845	# 33 # base64url rfc4648, utf-8
		846	# 34 # base64 rfc46484, utf-8
		847	# 35 # regex pcre/ecma262, utf-8
		848	# 36 # mime message rfc2045, utf-8
		849	);
		850
		851
281	=head2 CBOR and JSON	852	=head1 CBOR and JSON
282		853
283	TODO	854	CBOR is supposed to implement a superset of the JSON data model, and is,
		855	with some coercion, able to represent all JSON texts (something that other
		856	"binary JSON" formats such as BSON generally do not support).
		857
		858	CBOR implements some extra hints and support for JSON interoperability,
		859	and the spec offers further guidance for conversion between CBOR and
		860	JSON. None of this is currently implemented in CBOR, and the guidelines
		861	in the spec do not result in correct round-tripping of data. If JSON
		862	interoperability is improved in the future, then the goal will be to
		863	ensure that decoded JSON data will round-trip encoding and decoding to
		864	CBOR intact.
284		865
285		866
286	=head1 SECURITY CONSIDERATIONS	867	=head1 SECURITY CONSIDERATIONS
287		868
288	When you are using CBOR in a protocol, talking to untrusted potentially	869	When you are using CBOR in a protocol, talking to untrusted potentially
…		…
335	properly. Half precision types are accepted, but not encoded.	916	properly. Half precision types are accepted, but not encoded.
336		917
337	Strict mode and canonical mode are not implemented.	918	Strict mode and canonical mode are not implemented.
338		919
339		920
		921	=head1 LIMITATIONS ON PERLS WITHOUT 64-BIT INTEGER SUPPORT
		922
		923	On perls that were built without 64 bit integer support (these are rare
		924	nowadays, even on 32 bit architectures), support for any kind of 64 bit
		925	integer in CBOR is very limited - most likely, these 64 bit values will
		926	be truncated, corrupted, or otherwise not decoded correctly. This also
		927	includes string, array and map sizes that are stored as 64 bit integers.
		928
		929
340	=head1 THREADS	930	=head1 THREADS
341		931
342	This module is I<not> guaranteed to be thread safe and there are no	932	This module is I<not> guaranteed to be thread safe and there are no
343	plans to change this until Perl gets thread support (as opposed to the	933	plans to change this until Perl gets thread support (as opposed to the
344	horribly slow so-called "threads" which are simply slow and bloated	934	horribly slow so-called "threads" which are simply slow and bloated
…		…
356	Please refrain from using rt.cpan.org or any other bug reporting	946	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.	947	service. I put the contact address into my modules for a reason.
358		948
359	=cut	949	=cut
360		950
361	our $true = do { bless \(my $dummy = 1), "CBOR::XS::Boolean" };	951	our %FILTER = (
362	our $false = do { bless \(my $dummy = 0), "CBOR::XS::Boolean" };	952	# 0 # rfc4287 datetime, utf-8
		953	# 1 # unix timestamp, any
363		954
364	sub true() { $true }	955	2 => sub { # pos bigint
365	sub false() { $false }	956	require Math::BigInt;
		957	Math::BigInt->new ("0x" . unpack "H*", pop)
		958	},
366		959
367	sub is_bool($) {	960	3 => sub { # neg bigint
368	UNIVERSAL::isa $_[0], "CBOR::XS::Boolean"	961	require Math::BigInt;
369	# or UNIVERSAL::isa $_[0], "CBOR::Literal"	962	-Math::BigInt->new ("0x" . unpack "H*", pop)
		963	},
		964
		965	4 => sub { # decimal fraction, array
		966	require Math::BigFloat;
		967	Math::BigFloat->new ($_[1][1] . "E" . $_[1][0])
		968	},
		969
		970	5 => sub { # bigfloat, array
		971	require Math::BigFloat;
		972	scalar Math::BigFloat->new ($_[1][1])->blsft ($_[1][0], 2)
		973	},
		974
		975	21 => sub { pop }, # expected conversion to base64url encoding
		976	22 => sub { pop }, # expected conversion to base64 encoding
		977	23 => sub { pop }, # expected conversion to base16 encoding
		978
		979	# 24 # embedded cbor, byte string
		980
		981	32 => sub {
		982	require URI;
		983	URI->new (pop)
		984	},
		985
		986	# 33 # base64url rfc4648, utf-8
		987	# 34 # base64 rfc46484, utf-8
		988	# 35 # regex pcre/ecma262, utf-8
		989	# 36 # mime message rfc2045, utf-8
		990	);
		991
		992	sub CBOR::XS::default_filter {
		993	&{ $FILTER{$_[0]} or return }
370	}	994	}
371		995
		996	sub URI::TO_CBOR {
		997	my $uri = $_[0]->as_string;
		998	utf8::upgrade $uri;
		999	CBOR::XS::tag 32, $uri
		1000	}
		1001
		1002	sub Math::BigInt::TO_CBOR {
		1003	if ($_[0] >= -2147483648 && $_[0] <= 2147483647) {
		1004	$_[0]->numify
		1005	} else {
		1006	my $hex = substr $_[0]->as_hex, 2;
		1007	$hex = "0$hex" if 1 & length $hex; # sigh
		1008	CBOR::XS::tag $_[0] >= 0 ? 2 : 3, pack "H*", $hex
		1009	}
		1010	}
		1011
		1012	sub Math::BigFloat::TO_CBOR {
		1013	my ($m, $e) = $_[0]->parts;
		1014	CBOR::XS::tag 4, [$e->numify, $m]
		1015	}
		1016
372	XSLoader::load "CBOR::XS", $VERSION;	1017	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		1018
384	=head1 SEE ALSO	1019	=head1 SEE ALSO
385		1020
386	The L<JSON> and L<JSON::XS> modules that do similar, but human-readable,	1021	The L<JSON> and L<JSON::XS> modules that do similar, but human-readable,
387	serialisation.	1022	serialisation.
388		1023
		1024	The L<Types::Serialiser> module provides the data model for true, false
		1025	and error values.
		1026
389	=head1 AUTHOR	1027	=head1 AUTHOR
390		1028
391	Marc Lehmann <schmorp@schmorp.de>	1029	Marc Lehmann <schmorp@schmorp.de>
392	http://home.schmorp.de/	1030	http://home.schmorp.de/
393		1031
394	=cut	1032	=cut
395		1033
		1034	1
		1035

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 1.32 by root, Sat Nov 30 18:42:27 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 1.32 by root, Sat Nov 30 18:42:27 2013 UTC