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

Comparing CBOR-XS/XS.pm (file contents):
Revision 1.5 by root, Sat Oct 26 23:02:55 2013 UTC vs.
Revision 1.30 by root, Sat Nov 30 16:19:59 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
21	WARNING! THIS IS A PRE-ALPHA RELEASE! IT WILL CRASH, CORRUPT YOUR DATA
22	AND EAT YOUR CHILDREN! (Actually, apart from being untested and a bit
23	feature-limited, it might already be useful).
24		30
25	This module converts Perl data structures to the Concise Binary Object	31	This module converts Perl data structures to the Concise Binary Object
26	Representation (CBOR) and vice versa. CBOR is a fast binary serialisation	32	Representation (CBOR) and vice versa. CBOR is a fast binary serialisation
27	format that aims to use a superset of the JSON data model, i.e. when you	33	format that aims to use an (almost) superset of the JSON data model, i.e.
28	can represent something in JSON, you should be able to represent it in	34	when you can represent something useful in JSON, you should be able to
29	CBOR.	35	represent it in CBOR.
30		36
31	This makes it a faster and more compact binary alternative to JSON.	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 (see
		54	C<allow_sharing>), string deduplication (see C<pack_strings>) and scalar
		55	references (always enabled).
32		56
33	The primary goal of this module is to be I<correct> and the secondary goal	57	The primary goal of this module is to be I<correct> and the secondary goal
34	is to be 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.
35		59
36	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
…		…
40		64
41	package CBOR::XS;	65	package CBOR::XS;
42		66
43	use common::sense;	67	use common::sense;
44		68
45	our $VERSION = 0.03;	69	our $VERSION = '1.0';
46	our @ISA = qw(Exporter);	70	our @ISA = qw(Exporter);
47		71
48	our @EXPORT = qw(encode_cbor decode_cbor);	72	our @EXPORT = qw(encode_cbor decode_cbor);
49		73
50	use Exporter;	74	use Exporter;
51	use XSLoader;	75	use XSLoader;
52		76
		77	use Types::Serialiser;
		78
53	our $MAGIC = "\xd9\xd9\xf7";	79	our $MAGIC = "\xd9\xd9\xf7";
54		80
55	=head1 FUNCTIONAL INTERFACE	81	=head1 FUNCTIONAL INTERFACE
56		82
57	The following convenience methods are provided by this module. They are	83	The following convenience methods are provided by this module. They are
…		…
85	strings. All boolean flags described below are by default I<disabled>.	111	strings. All boolean flags described below are by default I<disabled>.
86		112
87	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
88	be chained:	114	be chained:
89		115
90	#TODO
91	my $cbor = CBOR::XS->new->encode ({a => [1,2]});	116	my $cbor = CBOR::XS->new->encode ({a => [1,2]});
92		117
93	=item $cbor = $cbor->max_depth ([$maximum_nesting_depth])	118	=item $cbor = $cbor->max_depth ([$maximum_nesting_depth])
94		119
95	=item $max_depth = $cbor->get_max_depth	120	=item $max_depth = $cbor->get_max_depth
…		…
129	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
130	C<0> is specified).	155	C<0> is specified).
131		156
132	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.
133		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.
		186
		187	It is recommended to leave it off unless you know your
		188	communication partner supports the value sharing extensions to CBOR
		189	(L<http://cbor.schmorp.de/value-sharing>), as without decoder support, the
		190	resulting data structure might be unusable.
		191
		192	Detecting shared values incurs a runtime overhead when values are encoded
		193	that have a reference counter large than one, and might unnecessarily
		194	increase the encoded size, as potentially shared values are encode as
		195	sharable whether or not they are actually shared.
		196
		197	At the moment, only targets of references can be shared (e.g. scalars,
		198	arrays or hashes pointed to by a reference). Weirder constructs, such as
		199	an array with multiple "copies" of the I<same> string, which are hard but
		200	not impossible to create in Perl, are not supported (this is the same as
		201	with L<Storable>).
		202
		203	If C<$enable> is false (the default), then C<encode> will encode shared
		204	data structures repeatedly, unsharing them in the process. Cyclic data
		205	structures cannot be encoded in this mode.
		206
		207	This option does not affect C<decode> in any way - shared values and
		208	references will always be decoded properly if present.
		209
		210	=item $cbor = $cbor->pack_strings ([$enable])
		211
		212	=item $enabled = $cbor->get_pack_strings
		213
		214	If C<$enable> is true (or missing), then C<encode> will try not to encode
		215	the same string twice, but will instead encode a reference to the string
		216	instead. Depending on your data format, this can save a lot of space, but
		217	also results in a very large runtime overhead (expect encoding times to be
		218	2-4 times as high as without).
		219
		220	It is recommended to leave it off unless you know your
		221	communications partner supports the stringref extension to CBOR
		222	(L<http://cbor.schmorp.de/stringref>), as without decoder support, the
		223	resulting data structure might not be usable.
		224
		225	If C<$enable> is false (the default), then C<encode> will encode strings
		226	the standard CBOR way.
		227
		228	This option does not affect C<decode> in any way - string references will
		229	always be decoded properly if present.
		230
		231	=item $cbor = $cbor->filter ([$cb->($tag, $value)])
		232
		233	=item $cb_or_undef = $cbor->get_filter
		234
		235	Sets or replaces the tagged value decoding filter (when C<$cb> is
		236	specified) or clears the filter (if no argument or C<undef> is provided).
		237
		238	The filter callback is called only during decoding, when a non-enforced
		239	tagged value has been decoded (see L<TAG HANDLING AND EXTENSIONS> for a
		240	list of enforced tags). For specific tags, it's often better to provide a
		241	default converter using the C<%CBOR::XS::FILTER> hash (see below).
		242
		243	The first argument is the numerical tag, the second is the (decoded) value
		244	that has been tagged.
		245
		246	The filter function should return either exactly one value, which will
		247	replace the tagged value in the decoded data structure, or no values,
		248	which will result in default handling, which currently means the decoder
		249	creates a C<CBOR::XS::Tagged> object to hold the tag and the value.
		250
		251	When the filter is cleared (the default state), the default filter
		252	function, C<CBOR::XS::default_filter>, is used. This function simply looks
		253	up the tag in the C<%CBOR::XS::FILTER> hash. If an entry exists it must be
		254	a code reference that is called with tag and value, and is responsible for
		255	decoding the value. If no entry exists, it returns no values.
		256
		257	Example: decode all tags not handled internally into C<CBOR::XS::Tagged>
		258	objects, with no other special handling (useful when working with
		259	potentially "unsafe" CBOR data).
		260
		261	CBOR::XS->new->filter (sub { })->decode ($cbor_data);
		262
		263	Example: provide a global filter for tag 1347375694, converting the value
		264	into some string form.
		265
		266	$CBOR::XS::FILTER{1347375694} = sub {
		267	my ($tag, $value);
		268
		269	"tag 1347375694 value $value"
		270	};
		271
134	=item $cbor_data = $cbor->encode ($perl_scalar)	272	=item $cbor_data = $cbor->encode ($perl_scalar)
135		273
136	Converts the given Perl data structure (a scalar value) to its CBOR	274	Converts the given Perl data structure (a scalar value) to its CBOR
137	representation.	275	representation.
138		276
…		…
178	CBOR integers become (numeric) perl scalars. On perls without 64 bit	316	CBOR integers become (numeric) perl scalars. On perls without 64 bit
179	support, 64 bit integers will be truncated or otherwise corrupted.	317	support, 64 bit integers will be truncated or otherwise corrupted.
180		318
181	=item byte strings	319	=item byte strings
182		320
183	Byte strings will become octet strings in Perl (the byte values 0..255	321	Byte strings will become octet strings in Perl (the Byte values 0..255
184	will simply become characters of the same value in Perl).	322	will simply become characters of the same value in Perl).
185		323
186	=item UTF-8 strings	324	=item UTF-8 strings
187		325
188	UTF-8 strings in CBOR will be decoded, i.e. the UTF-8 octets will be	326	UTF-8 strings in CBOR will be decoded, i.e. the UTF-8 octets will be
…		…
194		332
195	CBOR arrays and CBOR maps will be converted into references to a Perl	333	CBOR arrays and CBOR maps will be converted into references to a Perl
196	array or hash, respectively. The keys of the map will be stringified	334	array or hash, respectively. The keys of the map will be stringified
197	during this process.	335	during this process.
198		336
		337	=item null
		338
		339	CBOR null becomes C<undef> in Perl.
		340
199	=item true, false	341	=item true, false, undefined
200		342
201	These CBOR values become C<CBOR::XS::true> and C<CBOR::XS::false>,	343	These CBOR values become C<Types:Serialiser::true>,
		344	C<Types:Serialiser::false> and C<Types::Serialiser::error>,
202	respectively. They are overloaded to act almost exactly like the numbers	345	respectively. They are overloaded to act almost exactly like the numbers
203	C<1> and C<0>. You can check whether a scalar is a CBOR boolean by using	346	C<1> and C<0> (for true and false) or to throw an exception on access (for
204	the C<CBOR::XS::is_bool> function.	347	error). See the L<Types::Serialiser> manpage for details.
205		348
206	=item null, undefined	349	=item tagged values
207		350
208	CBOR null and undefined values becomes C<undef> in Perl (in the future,
209	Undefined may raise an exception or something else).
210
211	=item tags
212
213	Tagged items consists of a numeric tag and another CBOR value. The tag	351	Tagged items consists of a numeric tag and another CBOR value.
214	55799 is ignored (this tag implements the magic header).
215		352
216	All other tags are currently converted into a L<CBOR::XS::Tagged> object,	353	See L<TAG HANDLING AND EXTENSIONS> and the description of C<< ->filter >>
217	which is simply a blessed array reference consistsing of the numeric tag	354	for details on which tags are handled how.
218	value followed by the (decoded) BOR value.
219		355
220	=item anything else	356	=item anything else
221		357
222	Anything else (e.g. unsupported simple values) will raise a decoding	358	Anything else (e.g. unsupported simple values) will raise a decoding
223	error.	359	error.
…		…
226		362
227		363
228	=head2 PERL -> CBOR	364	=head2 PERL -> CBOR
229		365
230	The mapping from Perl to CBOR is slightly more difficult, as Perl is a	366	The mapping from Perl to CBOR is slightly more difficult, as Perl is a
231	truly typeless language, so we can only guess which CBOR type is meant by	367	typeless language. That means this module can only guess which CBOR type
232	a Perl value.	368	is meant by a perl value.
233		369
234	=over 4	370	=over 4
235		371
236	=item hash references	372	=item hash references
237		373
238	Perl hash references become CBOR maps. As there is no inherent ordering in	374	Perl hash references become CBOR maps. As there is no inherent ordering in
239	hash keys (or CBOR maps), they will usually be encoded in a pseudo-random	375	hash keys (or CBOR maps), they will usually be encoded in a pseudo-random
240	order.	376	order. This order can be different each time a hahs is encoded.
241		377
242	Currently, tied hashes will use the indefinite-length format, while normal	378	Currently, tied hashes will use the indefinite-length format, while normal
243	hashes will use the fixed-length format.	379	hashes will use the fixed-length format.
244		380
245	=item array references	381	=item array references
246		382
247	Perl array references become fixed-length CBOR arrays.	383	Perl array references become fixed-length CBOR arrays.
248		384
249	=item other references	385	=item other references
250		386
251	Other unblessed references are generally not allowed and will cause an	387	Other unblessed references will be represented using
252	exception to be thrown, except for references to the integers C<0> and	388	the indirection tag extension (tag value C<22098>,
253	C<1>, which get turned into false and true in CBOR.	389	L<http://cbor.schmorp.de/indirection>). CBOR decoders are guaranteed
		390	to be able to decode these values somehow, by either "doing the right
		391	thing", decoding into a generic tagged object, simply ignoring the tag, or
		392	something else.
254		393
255	=item CBOR::XS::Tagged objects	394	=item CBOR::XS::Tagged objects
256		395
257	Objects of this type must be arrays consisting of a single C<[tag, value]>	396	Objects of this type must be arrays consisting of a single C<[tag, value]>
258	pair. The (numerical) tag will be encoded as a CBOR tag, the value will be	397	pair. The (numerical) tag will be encoded as a CBOR tag, the value will
259	encoded as appropriate for the value.	398	be encoded as appropriate for the value. You must use C<CBOR::XS::tag> to
		399	create such objects.
260		400
261	=item CBOR::XS::true, CBOR::XS::false	401	=item Types::Serialiser::true, Types::Serialiser::false, Types::Serialiser::error
262		402
263	These special values become CBOR true and CBOR false values,	403	These special values become CBOR true, CBOR false and CBOR undefined
264	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.
265		406
266	=item blessed objects	407	=item other blessed objects
267		408
268	Other blessed objects currently need to have a C<TO_CBOR> method. It	409	Other blessed objects are serialised via C<TO_CBOR> or C<FREEZE>. See
269	will be called on every object that is being serialised, and must return	410	L<TAG HANDLING AND EXTENSIONS> for specific classes handled by this
270	something that can be encoded in CBOR.	411	module, and L<OBJECT SERIALISATION> for generic object serialisation.
271		412
272	=item simple scalars	413	=item simple scalars
273		414
274	TODO
275	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
276	difficult objects to encode: CBOR::XS will encode undefined scalars as	416	difficult objects to encode: CBOR::XS will encode undefined scalars as
277	CBOR 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
278	before encoding as CBOR strings, and anything else as number value:	418	before encoding as CBOR strings, and anything else as number value:
279		419
280	# dump as number	420	# dump as number
281	encode_cbor [2] # yields [2]	421	encode_cbor [2] # yields [2]
282	encode_cbor [-3.0e17] # yields [-3e+17]	422	encode_cbor [-3.0e17] # yields [-3e+17]
283	my $value = 5; encode_cbor [$value] # yields [5]	423	my $value = 5; encode_cbor [$value] # yields [5]
284		424
285	# used as string, so dump as string	425	# used as string, so dump as string (either byte or text)
286	print $value;	426	print $value;
287	encode_cbor [$value] # yields ["5"]	427	encode_cbor [$value] # yields ["5"]
288		428
289	# undef becomes null	429	# undef becomes null
290	encode_cbor [undef] # yields [null]	430	encode_cbor [undef] # yields [null]
…		…
293		433
294	my $x = 3.1; # some variable containing a number	434	my $x = 3.1; # some variable containing a number
295	"$x"; # stringified	435	"$x"; # stringified
296	$x .= ""; # another, more awkward way to stringify	436	$x .= ""; # another, more awkward way to stringify
297	print $x; # perl does it for you, too, quite often	437	print $x; # perl does it for you, too, quite often
		438
		439	You can force whether a string ie encoded as byte or text string by using
		440	C<utf8::upgrade> and C<utf8::downgrade>):
		441
		442	utf8::upgrade $x; # encode $x as text string
		443	utf8::downgrade $x; # encode $x as byte string
		444
		445	Perl doesn't define what operations up- and downgrade strings, so if the
		446	difference between byte and text is important, you should up- or downgrade
		447	your string as late as possible before encoding.
298		448
299	You can force the type to be a CBOR number by numifying it:	449	You can force the type to be a CBOR number by numifying it:
300		450
301	my $x = "3"; # some variable containing a string	451	my $x = "3"; # some variable containing a string
302	$x += 0; # numify it, ensuring it will be dumped as a number	452	$x += 0; # numify it, ensuring it will be dumped as a number
…		…
313	represent numerical values are supported, but might suffer loss of	463	represent numerical values are supported, but might suffer loss of
314	precision.	464	precision.
315		465
316	=back	466	=back
317		467
		468	=head2 OBJECT SERIALISATION
318		469
		470	This module implements both a CBOR-specific and the generic
		471	L<Types::Serialier> object serialisation protocol. The following
		472	subsections explain both methods.
		473
		474	=head3 ENCODING
		475
		476	This module knows two way to serialise a Perl object: The CBOR-specific
		477	way, and the generic way.
		478
		479	Whenever the encoder encounters a Perl object that it cannot serialise
		480	directly (most of them), it will first look up the C<TO_CBOR> method on
		481	it.
		482
		483	If it has a C<TO_CBOR> method, it will call it with the object as only
		484	argument, and expects exactly one return value, which it will then
		485	substitute and encode it in the place of the object.
		486
		487	Otherwise, it will look up the C<FREEZE> method. If it exists, it will
		488	call it with the object as first argument, and the constant string C<CBOR>
		489	as the second argument, to distinguish it from other serialisers.
		490
		491	The C<FREEZE> method can return any number of values (i.e. zero or
		492	more). These will be encoded as CBOR perl object, together with the
		493	classname.
		494
		495	These methods I<MUST NOT> change the data structure that is being
		496	serialised. Failure to comply to this can result in memory corruption -
		497	and worse.
		498
		499	If an object supports neither C<TO_CBOR> nor C<FREEZE>, encoding will fail
		500	with an error.
		501
		502	=head3 DECODING
		503
		504	Objects encoded via C<TO_CBOR> cannot (normally) be automatically decoded,
		505	but objects encoded via C<FREEZE> can be decoded using the following
		506	protocol:
		507
		508	When an encoded CBOR perl object is encountered by the decoder, it will
		509	look up the C<THAW> method, by using the stored classname, and will fail
		510	if the method cannot be found.
		511
		512	After the lookup it will call the C<THAW> method with the stored classname
		513	as first argument, the constant string C<CBOR> as second argument, and all
		514	values returned by C<FREEZE> as remaining arguments.
		515
		516	=head3 EXAMPLES
		517
		518	Here is an example C<TO_CBOR> method:
		519
		520	sub My::Object::TO_CBOR {
		521	my ($obj) = @_;
		522
		523	["this is a serialised My::Object object", $obj->{id}]
		524	}
		525
		526	When a C<My::Object> is encoded to CBOR, it will instead encode a simple
		527	array with two members: a string, and the "object id". Decoding this CBOR
		528	string will yield a normal perl array reference in place of the object.
		529
		530	A more useful and practical example would be a serialisation method for
		531	the URI module. CBOR has a custom tag value for URIs, namely 32:
		532
		533	sub URI::TO_CBOR {
		534	my ($self) = @_;
		535	my $uri = "$self"; # stringify uri
		536	utf8::upgrade $uri; # make sure it will be encoded as UTF-8 string
		537	CBOR::XS::tag 32, "$_[0]"
		538	}
		539
		540	This will encode URIs as a UTF-8 string with tag 32, which indicates an
		541	URI.
		542
		543	Decoding such an URI will not (currently) give you an URI object, but
		544	instead a CBOR::XS::Tagged object with tag number 32 and the string -
		545	exactly what was returned by C<TO_CBOR>.
		546
		547	To serialise an object so it can automatically be deserialised, you need
		548	to use C<FREEZE> and C<THAW>. To take the URI module as example, this
		549	would be a possible implementation:
		550
		551	sub URI::FREEZE {
		552	my ($self, $serialiser) = @_;
		553	"$self" # encode url string
		554	}
		555
		556	sub URI::THAW {
		557	my ($class, $serialiser, $uri) = @_;
		558
		559	$class->new ($uri)
		560	}
		561
		562	Unlike C<TO_CBOR>, multiple values can be returned by C<FREEZE>. For
		563	example, a C<FREEZE> method that returns "type", "id" and "variant" values
		564	would cause an invocation of C<THAW> with 5 arguments:
		565
		566	sub My::Object::FREEZE {
		567	my ($self, $serialiser) = @_;
		568
		569	($self->{type}, $self->{id}, $self->{variant})
		570	}
		571
		572	sub My::Object::THAW {
		573	my ($class, $serialiser, $type, $id, $variant) = @_;
		574
		575	$class-<new (type => $type, id => $id, variant => $variant)
		576	}
		577
		578
319	=head2 MAGIC HEADER	579	=head1 MAGIC HEADER
320		580
321	There is no way to distinguish CBOR from other formats	581	There is no way to distinguish CBOR from other formats
322	programmatically. To make it easier to distinguish CBOR from other	582	programmatically. To make it easier to distinguish CBOR from other
323	formats, the CBOR specification has a special "magic string" that can be	583	formats, the CBOR specification has a special "magic string" that can be
324	prepended to any CBOR string without changing it's meaning.	584	prepended to any CBOR string without changing its meaning.
325		585
326	This string is available as C<$CBOR::XS::MAGIC>. This module does not	586	This string is available as C<$CBOR::XS::MAGIC>. This module does not
327	prepend this string tot he CBOR data it generates, but it will ignroe it	587	prepend this string to the CBOR data it generates, but it will ignore it
328	if present, so users can prepend this string as a "file type" indicator as	588	if present, so users can prepend this string as a "file type" indicator as
329	required.	589	required.
330		590
331		591
		592	=head1 THE CBOR::XS::Tagged CLASS
		593
		594	CBOR has the concept of tagged values - any CBOR value can be tagged with
		595	a numeric 64 bit number, which are centrally administered.
		596
		597	C<CBOR::XS> handles a few tags internally when en- or decoding. You can
		598	also create tags yourself by encoding C<CBOR::XS::Tagged> objects, and the
		599	decoder will create C<CBOR::XS::Tagged> objects itself when it hits an
		600	unknown tag.
		601
		602	These objects are simply blessed array references - the first member of
		603	the array being the numerical tag, the second being the value.
		604
		605	You can interact with C<CBOR::XS::Tagged> objects in the following ways:
		606
		607	=over 4
		608
		609	=item $tagged = CBOR::XS::tag $tag, $value
		610
		611	This function(!) creates a new C<CBOR::XS::Tagged> object using the given
		612	C<$tag> (0..2**64-1) to tag the given C<$value> (which can be any Perl
		613	value that can be encoded in CBOR, including serialisable Perl objects and
		614	C<CBOR::XS::Tagged> objects).
		615
		616	=item $tagged->[0]
		617
		618	=item $tagged->[0] = $new_tag
		619
		620	=item $tag = $tagged->tag
		621
		622	=item $new_tag = $tagged->tag ($new_tag)
		623
		624	Access/mutate the tag.
		625
		626	=item $tagged->[1]
		627
		628	=item $tagged->[1] = $new_value
		629
		630	=item $value = $tagged->value
		631
		632	=item $new_value = $tagged->value ($new_value)
		633
		634	Access/mutate the tagged value.
		635
		636	=back
		637
		638	=cut
		639
		640	sub tag($$) {
		641	bless [@_], CBOR::XS::Tagged::;
		642	}
		643
		644	sub CBOR::XS::Tagged::tag {
		645	$_[0][0] = $_[1] if $#_;
		646	$_[0][0]
		647	}
		648
		649	sub CBOR::XS::Tagged::value {
		650	$_[0][1] = $_[1] if $#_;
		651	$_[0][1]
		652	}
		653
		654	=head2 EXAMPLES
		655
		656	Here are some examples of C<CBOR::XS::Tagged> uses to tag objects.
		657
		658	You can look up CBOR tag value and emanings in the IANA registry at
		659	L<http://www.iana.org/assignments/cbor-tags/cbor-tags.xhtml>.
		660
		661	Prepend a magic header (C<$CBOR::XS::MAGIC>):
		662
		663	my $cbor = encode_cbor CBOR::XS::tag 55799, $value;
		664	# same as:
		665	my $cbor = $CBOR::XS::MAGIC . encode_cbor $value;
		666
		667	Serialise some URIs and a regex in an array:
		668
		669	my $cbor = encode_cbor [
		670	(CBOR::XS::tag 32, "http://www.nethype.de/"),
		671	(CBOR::XS::tag 32, "http://software.schmorp.de/"),
		672	(CBOR::XS::tag 35, "^[Pp][Ee][Rr][lL]\$"),
		673	];
		674
		675	Wrap CBOR data in CBOR:
		676
		677	my $cbor_cbor = encode_cbor
		678	CBOR::XS::tag 24,
		679	encode_cbor [1, 2, 3];
		680
		681	=head1 TAG HANDLING AND EXTENSIONS
		682
		683	This section describes how this module handles specific tagged values
		684	and extensions. If a tag is not mentioned here and no additional filters
		685	are provided for it, then the default handling applies (creating a
		686	CBOR::XS::Tagged object on decoding, and only encoding the tag when
		687	explicitly requested).
		688
		689	Tags not handled specifically are currently converted into a
		690	L<CBOR::XS::Tagged> object, which is simply a blessed array reference
		691	consisting of the numeric tag value followed by the (decoded) CBOR value.
		692
		693	Future versions of this module reserve the right to special case
		694	additional tags (such as base64url).
		695
		696	=head2 ENFORCED TAGS
		697
		698	These tags are always handled when decoding, and their handling cannot be
		699	overriden by the user.
		700
		701	=over 4
		702
		703	=item 26 (perl-object, L<http://cbor.schmorp.de/perl-object>)
		704
		705	These tags are automatically created (and decoded) for serialisable
		706	objects using the C<FREEZE/THAW> methods (the L<Types::Serialier> object
		707	serialisation protocol). See L<OBJECT SERIALISATION> for details.
		708
		709	=item 28, 29 (sharable, sharedref, L <http://cbor.schmorp.de/value-sharing>)
		710
		711	These tags are automatically decoded when encountered, resulting in
		712	shared values in the decoded object. They are only encoded, however, when
		713	C<allow_sharable> is enabled.
		714
		715	=item 256, 25 (stringref-namespace, stringref, L <http://cbor.schmorp.de/stringref>)
		716
		717	These tags are automatically decoded when encountered. They are only
		718	encoded, however, when C<pack_strings> is enabled.
		719
		720	=item 22098 (indirection, L<http://cbor.schmorp.de/indirection>)
		721
		722	This tag is automatically generated when a reference are encountered (with
		723	the exception of hash and array refernces). It is converted to a reference
		724	when decoding.
		725
		726	=item 55799 (self-describe CBOR, RFC 7049)
		727
		728	This value is not generated on encoding (unless explicitly requested by
		729	the user), and is simply ignored when decoding.
		730
		731	=back
		732
		733	=head2 NON-ENFORCED TAGS
		734
		735	These tags have default filters provided when decoding. Their handling can
		736	be overriden by changing the C<%CBOR::XS::FILTER> entry for the tag, or by
		737	providing a custom C<filter> callback when decoding.
		738
		739	When they result in decoding into a specific Perl class, the module
		740	usually provides a corresponding C<TO_CBOR> method as well.
		741
		742	When any of these need to load additional modules that are not part of the
		743	perl core distribution (e.g. L<URI>), it is (currently) up to the user to
		744	provide these modules. The decoding usually fails with an exception if the
		745	required module cannot be loaded.
		746
		747	=over 4
		748
		749	=item 2, 3 (positive/negative bignum)
		750
		751	These tags are decoded into L<Math::BigInt> objects. The corresponding
		752	C<Math::BigInt::TO_CBOR> method encodes "small" bigints into normal CBOR
		753	integers, and others into positive/negative CBOR bignums.
		754
		755	=item 4, 5 (decimal fraction/bigfloat)
		756
		757	Both decimal fractions and bigfloats are decoded into L<Math::BigFloat>
		758	objects. The corresponding C<Math::BigFloat::TO_CBOR> method I<always>
		759	encodes into a decimal fraction.
		760
		761	CBOR cannot represent bigfloats with I<very> large exponents - conversion
		762	of such big float objects is undefined.
		763
		764	Also, NaN and infinities are not encoded properly.
		765
		766	=item 21, 22, 23 (expected later JSON conversion)
		767
		768	CBOR::XS is not a CBOR-to-JSON converter, and will simply ignore these
		769	tags.
		770
		771	=item 32 (URI)
		772
		773	These objects decode into L<URI> objects. The corresponding
		774	C<URI::TO_CBOR> method again results in a CBOR URI value.
		775
		776	=back
		777
		778	=cut
		779
		780	our %FILTER = (
		781	# 0 # rfc4287 datetime, utf-8
		782	# 1 # unix timestamp, any
		783
		784	2 => sub { # pos bigint
		785	require Math::BigInt;
		786	Math::BigInt->new ("0x" . unpack "H*", pop)
		787	},
		788
		789	3 => sub { # neg bigint
		790	require Math::BigInt;
		791	-Math::BigInt->new ("0x" . unpack "H*", pop)
		792	},
		793
		794	4 => sub { # decimal fraction, array
		795	require Math::BigFloat;
		796	Math::BigFloat->new ($_[1][1] . "E" . $_[1][0])
		797	},
		798
		799	5 => sub { # bigfloat, array
		800	require Math::BigFloat;
		801	scalar Math::BigFloat->new ($_[1][1])->blsft ($_[1][0], 2)
		802	},
		803
		804	21 => sub { pop }, # expected conversion to base64url encoding
		805	22 => sub { pop }, # expected conversion to base64 encoding
		806	23 => sub { pop }, # expected conversion to base16 encoding
		807
		808	# 24 # embedded cbor, byte string
		809
		810	32 => sub {
		811	require URI;
		812	URI->new (pop)
		813	},
		814
		815	# 33 # base64url rfc4648, utf-8
		816	# 34 # base64 rfc46484, utf-8
		817	# 35 # regex pcre/ecma262, utf-8
		818	# 36 # mime message rfc2045, utf-8
		819	);
		820
		821
332	=head2 CBOR and JSON	822	=head1 CBOR and JSON
333		823
334	CBOR is supposed to implement a superset of the JSON data model, and is,	824	CBOR is supposed to implement a superset of the JSON data model, and is,
335	with some coercion, able to represent all JSON texts (something that other	825	with some coercion, able to represent all JSON texts (something that other
336	"binary JSON" formats such as BSON generally do not support).	826	"binary JSON" formats such as BSON generally do not support).
337		827
…		…
396	properly. Half precision types are accepted, but not encoded.	886	properly. Half precision types are accepted, but not encoded.
397		887
398	Strict mode and canonical mode are not implemented.	888	Strict mode and canonical mode are not implemented.
399		889
400		890
		891	=head1 LIMITATIONS ON PERLS WITHOUT 64-BIT INTEGER SUPPORT
		892
		893	On perls that were built without 64 bit integer support (these are rare
		894	nowadays, even on 32 bit architectures), support for any kind of 64 bit
		895	integer in CBOR is very limited - most likely, these 64 bit values will
		896	be truncated, corrupted, or otherwise not decoded correctly. This also
		897	includes string, array and map sizes that are stored as 64 bit integers.
		898
		899
401	=head1 THREADS	900	=head1 THREADS
402		901
403	This module is I<not> guaranteed to be thread safe and there are no	902	This module is I<not> guaranteed to be thread safe and there are no
404	plans to change this until Perl gets thread support (as opposed to the	903	plans to change this until Perl gets thread support (as opposed to the
405	horribly slow so-called "threads" which are simply slow and bloated	904	horribly slow so-called "threads" which are simply slow and bloated
…		…
417	Please refrain from using rt.cpan.org or any other bug reporting	916	Please refrain from using rt.cpan.org or any other bug reporting
418	service. I put the contact address into my modules for a reason.	917	service. I put the contact address into my modules for a reason.
419		918
420	=cut	919	=cut
421		920
422	our $true = do { bless \(my $dummy = 1), "CBOR::XS::Boolean" };	921	our %FILTER = (
423	our $false = do { bless \(my $dummy = 0), "CBOR::XS::Boolean" };	922	# 0 # rfc4287 datetime, utf-8
		923	# 1 # unix timestamp, any
424		924
425	sub true() { $true }	925	2 => sub { # pos bigint
426	sub false() { $false }	926	require Math::BigInt;
		927	Math::BigInt->new ("0x" . unpack "H*", pop)
		928	},
427		929
428	sub is_bool($) {	930	3 => sub { # neg bigint
429	UNIVERSAL::isa $_[0], "CBOR::XS::Boolean"	931	require Math::BigInt;
430	# or UNIVERSAL::isa $_[0], "CBOR::Literal"	932	-Math::BigInt->new ("0x" . unpack "H*", pop)
		933	},
		934
		935	4 => sub { # decimal fraction, array
		936	require Math::BigFloat;
		937	Math::BigFloat->new ($_[1][1] . "E" . $_[1][0])
		938	},
		939
		940	5 => sub { # bigfloat, array
		941	require Math::BigFloat;
		942	scalar Math::BigFloat->new ($_[1][1])->blsft ($_[1][0], 2)
		943	},
		944
		945	21 => sub { pop }, # expected conversion to base64url encoding
		946	22 => sub { pop }, # expected conversion to base64 encoding
		947	23 => sub { pop }, # expected conversion to base16 encoding
		948
		949	# 24 # embedded cbor, byte string
		950
		951	32 => sub {
		952	require URI;
		953	URI->new (pop)
		954	},
		955
		956	# 33 # base64url rfc4648, utf-8
		957	# 34 # base64 rfc46484, utf-8
		958	# 35 # regex pcre/ecma262, utf-8
		959	# 36 # mime message rfc2045, utf-8
		960	);
		961
		962	sub CBOR::XS::default_filter {
		963	&{ $FILTER{$_[0]} or return }
431	}	964	}
432		965
		966	sub URI::TO_CBOR {
		967	my $uri = $_[0]->as_string;
		968	utf8::upgrade $uri;
		969	CBOR::XS::tag 32, $uri
		970	}
		971
		972	sub Math::BigInt::TO_CBOR {
		973	if ($_[0] >= -2147483648 && $_[0] <= 2147483647) {
		974	$_[0]->numify
		975	} else {
		976	my $hex = substr $_[0]->as_hex, 2;
		977	$hex = "0$hex" if 1 & length $hex; # sigh
		978	CBOR::XS::tag $_[0] >= 0 ? 2 : 3, pack "H*", $hex
		979	}
		980	}
		981
		982	sub Math::BigFloat::TO_CBOR {
		983	my ($m, $e) = $_[0]->parts;
		984	CBOR::XS::tag 4, [$e->numify, $m]
		985	}
		986
433	XSLoader::load "CBOR::XS", $VERSION;	987	XSLoader::load "CBOR::XS", $VERSION;
434
435	package CBOR::XS::Boolean;
436
437	use overload
438	"0+" => sub { ${$_[0]} },
439	"++" => sub { $_[0] = ${$_[0]} + 1 },
440	"--" => sub { $_[0] = ${$_[0]} - 1 },
441	fallback => 1;
442
443	1;
444		988
445	=head1 SEE ALSO	989	=head1 SEE ALSO
446		990
447	The L<JSON> and L<JSON::XS> modules that do similar, but human-readable,	991	The L<JSON> and L<JSON::XS> modules that do similar, but human-readable,
448	serialisation.	992	serialisation.
449		993
		994	The L<Types::Serialiser> module provides the data model for true, false
		995	and error values.
		996
450	=head1 AUTHOR	997	=head1 AUTHOR
451		998
452	Marc Lehmann <schmorp@schmorp.de>	999	Marc Lehmann <schmorp@schmorp.de>
453	http://home.schmorp.de/	1000	http://home.schmorp.de/
454		1001
455	=cut	1002	=cut
456		1003
		1004	1
		1005

Diff Legend

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

Comparing CBOR-XS/XS.pm (file contents): Revision 1.5 by root, Sat Oct 26 23:02:55 2013 UTC vs. Revision 1.30 by root, Sat Nov 30 16:19:59 2013 UTC

Diff Legend

Comparing CBOR-XS/XS.pm (file contents):
Revision 1.5 by root, Sat Oct 26 23:02:55 2013 UTC vs.
Revision 1.30 by root, Sat Nov 30 16:19:59 2013 UTC