[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 1.28 by root, Thu Nov 28 16:09:04 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 knows two way to serialise a Perl object: The CBOR-specific
		471	way, and the generic way.
		472
		473	Whenever the encoder encounters a Perl object that it cnanot serialise
		474	directly (most of them), it will first look up the C<TO_CBOR> method on
		475	it.
		476
		477	If it has a C<TO_CBOR> method, it will call it with the object as only
		478	argument, and expects exactly one return value, which it will then
		479	substitute and encode it in the place of the object.
		480
		481	Otherwise, it will look up the C<FREEZE> method. If it exists, it will
		482	call it with the object as first argument, and the constant string C<CBOR>
		483	as the second argument, to distinguish it from other serialisers.
		484
		485	The C<FREEZE> method can return any number of values (i.e. zero or
		486	more). These will be encoded as CBOR perl object, together with the
		487	classname.
		488
		489	If an object supports neither C<TO_CBOR> nor C<FREEZE>, encoding will fail
		490	with an error.
		491
		492	Objects encoded via C<TO_CBOR> cannot be automatically decoded, but
		493	objects encoded via C<FREEZE> can be decoded using the following protocol:
		494
		495	When an encoded CBOR perl object is encountered by the decoder, it will
		496	look up the C<THAW> method, by using the stored classname, and will fail
		497	if the method cannot be found.
		498
		499	After the lookup it will call the C<THAW> method with the stored classname
		500	as first argument, the constant string C<CBOR> as second argument, and all
		501	values returned by C<FREEZE> as remaining arguments.
		502
		503	=head4 EXAMPLES
		504
		505	Here is an example C<TO_CBOR> method:
		506
		507	sub My::Object::TO_CBOR {
		508	my ($obj) = @_;
		509
		510	["this is a serialised My::Object object", $obj->{id}]
		511	}
		512
		513	When a C<My::Object> is encoded to CBOR, it will instead encode a simple
		514	array with two members: a string, and the "object id". Decoding this CBOR
		515	string will yield a normal perl array reference in place of the object.
		516
		517	A more useful and practical example would be a serialisation method for
		518	the URI module. CBOR has a custom tag value for URIs, namely 32:
		519
		520	sub URI::TO_CBOR {
		521	my ($self) = @_;
		522	my $uri = "$self"; # stringify uri
		523	utf8::upgrade $uri; # make sure it will be encoded as UTF-8 string
		524	CBOR::XS::tag 32, "$_[0]"
		525	}
		526
		527	This will encode URIs as a UTF-8 string with tag 32, which indicates an
		528	URI.
		529
		530	Decoding such an URI will not (currently) give you an URI object, but
		531	instead a CBOR::XS::Tagged object with tag number 32 and the string -
		532	exactly what was returned by C<TO_CBOR>.
		533
		534	To serialise an object so it can automatically be deserialised, you need
		535	to use C<FREEZE> and C<THAW>. To take the URI module as example, this
		536	would be a possible implementation:
		537
		538	sub URI::FREEZE {
		539	my ($self, $serialiser) = @_;
		540	"$self" # encode url string
		541	}
		542
		543	sub URI::THAW {
		544	my ($class, $serialiser, $uri) = @_;
		545
		546	$class->new ($uri)
		547	}
		548
		549	Unlike C<TO_CBOR>, multiple values can be returned by C<FREEZE>. For
		550	example, a C<FREEZE> method that returns "type", "id" and "variant" values
		551	would cause an invocation of C<THAW> with 5 arguments:
		552
		553	sub My::Object::FREEZE {
		554	my ($self, $serialiser) = @_;
		555
		556	($self->{type}, $self->{id}, $self->{variant})
		557	}
		558
		559	sub My::Object::THAW {
		560	my ($class, $serialiser, $type, $id, $variant) = @_;
		561
		562	$class-<new (type => $type, id => $id, variant => $variant)
		563	}
		564
		565
319	=head2 MAGIC HEADER	566	=head1 MAGIC HEADER
320		567
321	There is no way to distinguish CBOR from other formats	568	There is no way to distinguish CBOR from other formats
322	programmatically. To make it easier to distinguish CBOR from other	569	programmatically. To make it easier to distinguish CBOR from other
323	formats, the CBOR specification has a special "magic string" that can be	570	formats, the CBOR specification has a special "magic string" that can be
324	prepended to any CBOR string without changing it's meaning.	571	prepended to any CBOR string without changing its meaning.
325		572
326	This string is available as C<$CBOR::XS::MAGIC>. This module does not	573	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	574	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	575	if present, so users can prepend this string as a "file type" indicator as
329	required.	576	required.
330		577
331		578
		579	=head1 THE CBOR::XS::Tagged CLASS
		580
		581	CBOR has the concept of tagged values - any CBOR value can be tagged with
		582	a numeric 64 bit number, which are centrally administered.
		583
		584	C<CBOR::XS> handles a few tags internally when en- or decoding. You can
		585	also create tags yourself by encoding C<CBOR::XS::Tagged> objects, and the
		586	decoder will create C<CBOR::XS::Tagged> objects itself when it hits an
		587	unknown tag.
		588
		589	These objects are simply blessed array references - the first member of
		590	the array being the numerical tag, the second being the value.
		591
		592	You can interact with C<CBOR::XS::Tagged> objects in the following ways:
		593
		594	=over 4
		595
		596	=item $tagged = CBOR::XS::tag $tag, $value
		597
		598	This function(!) creates a new C<CBOR::XS::Tagged> object using the given
		599	C<$tag> (0..2**64-1) to tag the given C<$value> (which can be any Perl
		600	value that can be encoded in CBOR, including serialisable Perl objects and
		601	C<CBOR::XS::Tagged> objects).
		602
		603	=item $tagged->[0]
		604
		605	=item $tagged->[0] = $new_tag
		606
		607	=item $tag = $tagged->tag
		608
		609	=item $new_tag = $tagged->tag ($new_tag)
		610
		611	Access/mutate the tag.
		612
		613	=item $tagged->[1]
		614
		615	=item $tagged->[1] = $new_value
		616
		617	=item $value = $tagged->value
		618
		619	=item $new_value = $tagged->value ($new_value)
		620
		621	Access/mutate the tagged value.
		622
		623	=back
		624
		625	=cut
		626
		627	sub tag($$) {
		628	bless [@_], CBOR::XS::Tagged::;
		629	}
		630
		631	sub CBOR::XS::Tagged::tag {
		632	$_[0][0] = $_[1] if $#_;
		633	$_[0][0]
		634	}
		635
		636	sub CBOR::XS::Tagged::value {
		637	$_[0][1] = $_[1] if $#_;
		638	$_[0][1]
		639	}
		640
		641	=head2 EXAMPLES
		642
		643	Here are some examples of C<CBOR::XS::Tagged> uses to tag objects.
		644
		645	You can look up CBOR tag value and emanings in the IANA registry at
		646	L<http://www.iana.org/assignments/cbor-tags/cbor-tags.xhtml>.
		647
		648	Prepend a magic header (C<$CBOR::XS::MAGIC>):
		649
		650	my $cbor = encode_cbor CBOR::XS::tag 55799, $value;
		651	# same as:
		652	my $cbor = $CBOR::XS::MAGIC . encode_cbor $value;
		653
		654	Serialise some URIs and a regex in an array:
		655
		656	my $cbor = encode_cbor [
		657	(CBOR::XS::tag 32, "http://www.nethype.de/"),
		658	(CBOR::XS::tag 32, "http://software.schmorp.de/"),
		659	(CBOR::XS::tag 35, "^[Pp][Ee][Rr][lL]\$"),
		660	];
		661
		662	Wrap CBOR data in CBOR:
		663
		664	my $cbor_cbor = encode_cbor
		665	CBOR::XS::tag 24,
		666	encode_cbor [1, 2, 3];
		667
		668	=head1 TAG HANDLING AND EXTENSIONS
		669
		670	This section describes how this module handles specific tagged values
		671	and extensions. If a tag is not mentioned here and no additional filters
		672	are provided for it, then the default handling applies (creating a
		673	CBOR::XS::Tagged object on decoding, and only encoding the tag when
		674	explicitly requested).
		675
		676	Tags not handled specifically are currently converted into a
		677	L<CBOR::XS::Tagged> object, which is simply a blessed array reference
		678	consisting of the numeric tag value followed by the (decoded) CBOR value.
		679
		680	Future versions of this module reserve the right to special case
		681	additional tags (such as base64url).
		682
		683	=head2 ENFORCED TAGS
		684
		685	These tags are always handled when decoding, and their handling cannot be
		686	overriden by the user.
		687
		688	=over 4
		689
		690	=item 26 (perl-object, L<http://cbor.schmorp.de/perl-object>)
		691
		692	These tags are automatically created (and decoded) for serialisable
		693	objects using the C<FREEZE/THAW> methods (the L<Types::Serialier> object
		694	serialisation protocol). See L<OBJECT SERIALISATION> for details.
		695
		696	=item 28, 29 (sharable, sharedref, L <http://cbor.schmorp.de/value-sharing>)
		697
		698	These tags are automatically decoded when encountered, resulting in
		699	shared values in the decoded object. They are only encoded, however, when
		700	C<allow_sharable> is enabled.
		701
		702	=item 256, 25 (stringref-namespace, stringref, L <http://cbor.schmorp.de/stringref>)
		703
		704	These tags are automatically decoded when encountered. They are only
		705	encoded, however, when C<pack_strings> is enabled.
		706
		707	=item 22098 (indirection, L<http://cbor.schmorp.de/indirection>)
		708
		709	This tag is automatically generated when a reference are encountered (with
		710	the exception of hash and array refernces). It is converted to a reference
		711	when decoding.
		712
		713	=item 55799 (self-describe CBOR, RFC 7049)
		714
		715	This value is not generated on encoding (unless explicitly requested by
		716	the user), and is simply ignored when decoding.
		717
		718	=back
		719
		720	=head2 NON-ENFORCED TAGS
		721
		722	These tags have default filters provided when decoding. Their handling can
		723	be overriden by changing the C<%CBOR::XS::FILTER> entry for the tag, or by
		724	providing a custom C<filter> callback when decoding.
		725
		726	When they result in decoding into a specific Perl class, the module
		727	usually provides a corresponding C<TO_CBOR> method as well.
		728
		729	When any of these need to load additional modules that are not part of the
		730	perl core distribution (e.g. L<URI>), it is (currently) up to the user to
		731	provide these modules. The decoding usually fails with an exception if the
		732	required module cannot be loaded.
		733
		734	=over 4
		735
		736	=item 2, 3 (positive/negative bignum)
		737
		738	These tags are decoded into L<Math::BigInt> objects. The corresponding
		739	C<Math::BigInt::TO_CBOR> method encodes "small" bigints into normal CBOR
		740	integers, and others into positive/negative CBOR bignums.
		741
		742	=item 4, 5 (decimal fraction/bigfloat)
		743
		744	Both decimal fractions and bigfloats are decoded into L<Math::BigFloat>
		745	objects. The corresponding C<Math::BigFloat::TO_CBOR> method I<always>
		746	encodes into a decimal fraction.
		747
		748	CBOR cannot represent bigfloats with I<very> large exponents - conversion
		749	of such big float objects is undefined.
		750
		751	Also, NaN and infinities are not encoded properly.
		752
		753	=item 21, 22, 23 (expected later JSON conversion)
		754
		755	CBOR::XS is not a CBOR-to-JSON converter, and will simply ignore these
		756	tags.
		757
		758	=item 32 (URI)
		759
		760	These objects decode into L<URI> objects. The corresponding
		761	C<URI::TO_CBOR> method again results in a CBOR URI value.
		762
		763	=back
		764
		765	=cut
		766
		767	our %FILTER = (
		768	# 0 # rfc4287 datetime, utf-8
		769	# 1 # unix timestamp, any
		770
		771	2 => sub { # pos bigint
		772	require Math::BigInt;
		773	Math::BigInt->new ("0x" . unpack "H*", pop)
		774	},
		775
		776	3 => sub { # neg bigint
		777	require Math::BigInt;
		778	-Math::BigInt->new ("0x" . unpack "H*", pop)
		779	},
		780
		781	4 => sub { # decimal fraction, array
		782	require Math::BigFloat;
		783	Math::BigFloat->new ($_[1][1] . "E" . $_[1][0])
		784	},
		785
		786	5 => sub { # bigfloat, array
		787	require Math::BigFloat;
		788	scalar Math::BigFloat->new ($_[1][1])->blsft ($_[1][0], 2)
		789	},
		790
		791	21 => sub { pop }, # expected conversion to base64url encoding
		792	22 => sub { pop }, # expected conversion to base64 encoding
		793	23 => sub { pop }, # expected conversion to base16 encoding
		794
		795	# 24 # embedded cbor, byte string
		796
		797	32 => sub {
		798	require URI;
		799	URI->new (pop)
		800	},
		801
		802	# 33 # base64url rfc4648, utf-8
		803	# 34 # base64 rfc46484, utf-8
		804	# 35 # regex pcre/ecma262, utf-8
		805	# 36 # mime message rfc2045, utf-8
		806	);
		807
		808
332	=head2 CBOR and JSON	809	=head1 CBOR and JSON
333		810
334	CBOR is supposed to implement a superset of the JSON data model, and is,	811	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	812	with some coercion, able to represent all JSON texts (something that other
336	"binary JSON" formats such as BSON generally do not support).	813	"binary JSON" formats such as BSON generally do not support).
337		814
…		…
417	Please refrain from using rt.cpan.org or any other bug reporting	894	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.	895	service. I put the contact address into my modules for a reason.
419		896
420	=cut	897	=cut
421		898
422	our $true = do { bless \(my $dummy = 1), "CBOR::XS::Boolean" };	899	our %FILTER = (
423	our $false = do { bless \(my $dummy = 0), "CBOR::XS::Boolean" };	900	# 0 # rfc4287 datetime, utf-8
		901	# 1 # unix timestamp, any
424		902
425	sub true() { $true }	903	2 => sub { # pos bigint
426	sub false() { $false }	904	require Math::BigInt;
		905	Math::BigInt->new ("0x" . unpack "H*", pop)
		906	},
427		907
428	sub is_bool($) {	908	3 => sub { # neg bigint
429	UNIVERSAL::isa $_[0], "CBOR::XS::Boolean"	909	require Math::BigInt;
430	# or UNIVERSAL::isa $_[0], "CBOR::Literal"	910	-Math::BigInt->new ("0x" . unpack "H*", pop)
		911	},
		912
		913	4 => sub { # decimal fraction, array
		914	require Math::BigFloat;
		915	Math::BigFloat->new ($_[1][1] . "E" . $_[1][0])
		916	},
		917
		918	5 => sub { # bigfloat, array
		919	require Math::BigFloat;
		920	scalar Math::BigFloat->new ($_[1][1])->blsft ($_[1][0], 2)
		921	},
		922
		923	21 => sub { pop }, # expected conversion to base64url encoding
		924	22 => sub { pop }, # expected conversion to base64 encoding
		925	23 => sub { pop }, # expected conversion to base16 encoding
		926
		927	# 24 # embedded cbor, byte string
		928
		929	32 => sub {
		930	require URI;
		931	URI->new (pop)
		932	},
		933
		934	# 33 # base64url rfc4648, utf-8
		935	# 34 # base64 rfc46484, utf-8
		936	# 35 # regex pcre/ecma262, utf-8
		937	# 36 # mime message rfc2045, utf-8
		938	);
		939
		940	sub CBOR::XS::default_filter {
		941	&{ $FILTER{$_[0]} or return }
431	}	942	}
432		943
		944	sub URI::TO_CBOR {
		945	my $uri = $_[0]->as_string;
		946	utf8::upgrade $uri;
		947	CBOR::XS::tag 32, $uri
		948	}
		949
		950	sub Math::BigInt::TO_CBOR {
		951	if ($_[0] >= -2147483648 && $_[0] <= 2147483647) {
		952	$_[0]->numify
		953	} else {
		954	my $hex = substr $_[0]->as_hex, 2;
		955	$hex = "0$hex" if 1 & length $hex; # sigh
		956	CBOR::XS::tag $_[0] >= 0 ? 2 : 3, pack "H*", $hex
		957	}
		958	}
		959
		960	sub Math::BigFloat::TO_CBOR {
		961	my ($m, $e) = $_[0]->parts;
		962	CBOR::XS::tag 4, [$e->numify, $m]
		963	}
		964
433	XSLoader::load "CBOR::XS", $VERSION;	965	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		966
445	=head1 SEE ALSO	967	=head1 SEE ALSO
446		968
447	The L<JSON> and L<JSON::XS> modules that do similar, but human-readable,	969	The L<JSON> and L<JSON::XS> modules that do similar, but human-readable,
448	serialisation.	970	serialisation.
449		971
		972	The L<Types::Serialiser> module provides the data model for true, false
		973	and error values.
		974
450	=head1 AUTHOR	975	=head1 AUTHOR
451		976
452	Marc Lehmann <schmorp@schmorp.de>	977	Marc Lehmann <schmorp@schmorp.de>
453	http://home.schmorp.de/	978	http://home.schmorp.de/
454		979
455	=cut	980	=cut
456		981
		982	1
		983

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 1.28 by root, Thu Nov 28 16:09:04 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 1.28 by root, Thu Nov 28 16:09:04 2013 UTC