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

Comparing CBOR-XS/XS.pm (file contents):
Revision 1.22 by root, Fri Nov 22 15:28:38 2013 UTC vs.
Revision 1.80 by root, Fri Dec 11 06:05:33 2020 UTC

…		…
26	substr $many_cbor_strings, 0, $length, ""; # remove decoded cbor string	26	substr $many_cbor_strings, 0, $length, ""; # remove decoded cbor string
27	}	27	}
28		28
29	=head1 DESCRIPTION	29	=head1 DESCRIPTION
30		30
31	WARNING! This module is very new, and not very well tested (that's up
32	to you to do). Furthermore, details of the implementation might change
33	freely before version 1.0. And lastly, most extensions depend on an IANA
34	assignment, and until that assignment is official, this implementation is
35	not interoperable with other implementations (even future versions of this
36	module) until the assignment is done.
37
38	You are still invited to try out CBOR, and this module.
39
40	This module converts Perl data structures to the Concise Binary Object	31	This module converts Perl data structures to the Concise Binary Object
41	Representation (CBOR) and vice versa. CBOR is a fast binary serialisation	32	Representation (CBOR) and vice versa. CBOR is a fast binary serialisation
42	format that aims to use a superset of the JSON data model, i.e. when you	33	format that aims to use an (almost) superset of the JSON data model, i.e.
43	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
44	CBOR.	35	represent it in CBOR.
45		36
46	In short, CBOR is a faster and very compact binary alternative to JSON,	37	In short, CBOR is a faster and quite compact binary alternative to JSON,
47	with the added ability of supporting serialisation of Perl objects. (JSON	38	with the added ability of supporting serialisation of Perl objects. (JSON
48	often compresses better than CBOR though, so if you plan to compress the	39	often compresses better than CBOR though, so if you plan to compress the
49	data later you might want to compare both formats first).	40	data later and speed is less important you might want to compare both
		41	formats first).
		42
		43	The primary goal of this module is to be I<correct> and the secondary goal
		44	is to be I<fast>. To reach the latter goal it was written in C.
50		45
51	To give you a general idea about speed, with texts in the megabyte range,	46	To give you a general idea about speed, with texts in the megabyte range,
52	C<CBOR::XS> usually encodes roughly twice as fast as L<Storable> or	47	C<CBOR::XS> usually encodes roughly twice as fast as L<Storable> or
53	L<JSON::XS> and decodes about 15%-30% faster than those. The shorter the	48	L<JSON::XS> and decodes about 15%-30% faster than those. The shorter the
54	data, the worse L<Storable> performs in comparison.	49	data, the worse L<Storable> performs in comparison.
55		50
56	As for compactness, C<CBOR::XS> encoded data structures are usually about	51	Regarding compactness, C<CBOR::XS>-encoded data structures are usually
57	20% smaller than the same data encoded as (compact) JSON or L<Storable>.	52	about 20% smaller than the same data encoded as (compact) JSON or
		53	L<Storable>.
58		54
59	In addition to the core CBOR data format, this module implements a number	55	In addition to the core CBOR data format, this module implements a
60	of extensions, to support cyclic and self-referencing data structures	56	number of extensions, to support cyclic and shared data structures
61	(see C<allow_sharing>), string deduplication (see C<allow_stringref>) and	57	(see C<allow_sharing> and C<allow_cycles>), string deduplication (see
62	scalar references (always enabled).	58	C<pack_strings>) and scalar references (always enabled).
63
64	The primary goal of this module is to be I<correct> and the secondary goal
65	is to be I<fast>. To reach the latter goal it was written in C.
66		59
67	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
68	vice versa.	61	vice versa.
69		62
70	=cut	63	=cut
71		64
72	package CBOR::XS;	65	package CBOR::XS;
73		66
74	use common::sense;	67	use common::sense;
75		68
76	our $VERSION = 0.08;	69	our $VERSION = 1.83;
77	our @ISA = qw(Exporter);	70	our @ISA = qw(Exporter);
78		71
79	our @EXPORT = qw(encode_cbor decode_cbor);	72	our @EXPORT = qw(encode_cbor decode_cbor);
80		73
81	use Exporter;	74	use Exporter;
…		…
118	strings. All boolean flags described below are by default I<disabled>.	111	strings. All boolean flags described below are by default I<disabled>.
119		112
120	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
121	be chained:	114	be chained:
122		115
123	#TODO
124	my $cbor = CBOR::XS->new->encode ({a => [1,2]});	116	my $cbor = CBOR::XS->new->encode ({a => [1,2]});
		117
		118	=item $cbor = new_safe CBOR::XS
		119
		120	Create a new, safe/secure CBOR::XS object. This is similar to C<new>,
		121	but configures the coder object to be safe to use with untrusted
		122	data. Currently, this is equivalent to:
		123
		124	my $cbor = CBOR::XS
		125	->new
		126	->forbid_objects
		127	->filter (\&CBOR::XS::safe_filter)
		128	->max_size (1e8);
		129
		130	But is more future proof (it is better to crash because of a change than
		131	to be exploited in other ways).
		132
		133	=cut
		134
		135	sub new_safe {
		136	CBOR::XS
		137	->new
		138	->forbid_objects
		139	->filter (\&CBOR::XS::safe_filter)
		140	->max_size (1e8)
		141	}
125		142
126	=item $cbor = $cbor->max_depth ([$maximum_nesting_depth])	143	=item $cbor = $cbor->max_depth ([$maximum_nesting_depth])
127		144
128	=item $max_depth = $cbor->get_max_depth	145	=item $max_depth = $cbor->get_max_depth
129		146
…		…
145		162
146	Note that nesting is implemented by recursion in C. The default value has	163	Note that nesting is implemented by recursion in C. The default value has
147	been chosen to be as large as typical operating systems allow without	164	been chosen to be as large as typical operating systems allow without
148	crashing.	165	crashing.
149		166
150	See SECURITY CONSIDERATIONS, below, for more info on why this is useful.	167	See L<SECURITY CONSIDERATIONS>, below, for more info on why this is useful.
151		168
152	=item $cbor = $cbor->max_size ([$maximum_string_size])	169	=item $cbor = $cbor->max_size ([$maximum_string_size])
153		170
154	=item $max_size = $cbor->get_max_size	171	=item $max_size = $cbor->get_max_size
155		172
…		…
160	effect on C<encode> (yet).	177	effect on C<encode> (yet).
161		178
162	If no argument is given, the limit check will be deactivated (same as when	179	If no argument is given, the limit check will be deactivated (same as when
163	C<0> is specified).	180	C<0> is specified).
164		181
165	See SECURITY CONSIDERATIONS, below, for more info on why this is useful.	182	See L<SECURITY CONSIDERATIONS>, below, for more info on why this is useful.
166		183
167	=item $cbor = $cbor->allow_unknown ([$enable])	184	=item $cbor = $cbor->allow_unknown ([$enable])
168		185
169	=item $enabled = $cbor->get_allow_unknown	186	=item $enabled = $cbor->get_allow_unknown
170		187
…		…
187	as an array, is referenced multiple times), but instead will emit a	204	as an array, is referenced multiple times), but instead will emit a
188	reference to the earlier value.	205	reference to the earlier value.
189		206
190	This means that such values will only be encoded once, and will not result	207	This means that such values will only be encoded once, and will not result
191	in a deep cloning of the value on decode, in decoders supporting the value	208	in a deep cloning of the value on decode, in decoders supporting the value
192	sharing extension.	209	sharing extension. This also makes it possible to encode cyclic data
		210	structures (which need C<allow_cycles> to be enabled to be decoded by this
		211	module).
193		212
194	It is recommended to leave it off unless you know your	213	It is recommended to leave it off unless you know your
195	communication partner supports the value sharing extensions to CBOR	214	communication partner supports the value sharing extensions to CBOR
196	(http://cbor.schmorp.de/value-sharing).	215	(L<http://cbor.schmorp.de/value-sharing>), as without decoder support, the
		216	resulting data structure might be unusable.
197		217
198	Detecting shared values incurs a runtime overhead when values are encoded	218	Detecting shared values incurs a runtime overhead when values are encoded
199	that have a reference counter large than one, and might unnecessarily	219	that have a reference counter large than one, and might unnecessarily
200	increase the encoded size, as potentially shared values are encode as	220	increase the encoded size, as potentially shared values are encoded as
201	sharable whether or not they are actually shared.	221	shareable whether or not they are actually shared.
202		222
203	At the moment, only targets of references can be shared (e.g. scalars,	223	At the moment, only targets of references can be shared (e.g. scalars,
204	arrays or hashes pointed to by a reference). Weirder constructs, such as	224	arrays or hashes pointed to by a reference). Weirder constructs, such as
205	an array with multiple "copies" of the I<same> string, which are hard but	225	an array with multiple "copies" of the I<same> string, which are hard but
206	not impossible to create in Perl, are not supported (this is the same as	226	not impossible to create in Perl, are not supported (this is the same as
207	for L<Storable>).	227	with L<Storable>).
208		228
209	If C<$enable> is false (the default), then C<encode> will encode	229	If C<$enable> is false (the default), then C<encode> will encode shared
210	exception when it encounters anything it cannot encode as CBOR.	230	data structures repeatedly, unsharing them in the process. Cyclic data
		231	structures cannot be encoded in this mode.
211		232
212	This option does not affect C<decode> in any way - shared values and	233	This option does not affect C<decode> in any way - shared values and
213	references will always be decoded properly if present.	234	references will always be decoded properly if present.
214		235
		236	=item $cbor = $cbor->allow_cycles ([$enable])
		237
		238	=item $enabled = $cbor->get_allow_cycles
		239
		240	If C<$enable> is true (or missing), then C<decode> will happily decode
		241	self-referential (cyclic) data structures. By default these will not be
		242	decoded, as they need manual cleanup to avoid memory leaks, so code that
		243	isn't prepared for this will not leak memory.
		244
		245	If C<$enable> is false (the default), then C<decode> will throw an error
		246	when it encounters a self-referential/cyclic data structure.
		247
		248	FUTURE DIRECTION: the motivation behind this option is to avoid I<real>
		249	cycles - future versions of this module might chose to decode cyclic data
		250	structures using weak references when this option is off, instead of
		251	throwing an error.
		252
		253	This option does not affect C<encode> in any way - shared values and
		254	references will always be encoded properly if present.
		255
		256	=item $cbor = $cbor->forbid_objects ([$enable])
		257
		258	=item $enabled = $cbor->get_forbid_objects
		259
		260	Disables the use of the object serialiser protocol.
		261
		262	If C<$enable> is true (or missing), then C<encode> will will throw an
		263	exception when it encounters perl objects that would be encoded using the
		264	perl-object tag (26). When C<decode> encounters such tags, it will fall
		265	back to the general filter/tagged logic as if this were an unknown tag (by
		266	default resulting in a C<CBOR::XC::Tagged> object).
		267
		268	If C<$enable> is false (the default), then C<encode> will use the
		269	L<Types::Serialiser> object serialisation protocol to serialise objects
		270	into perl-object tags, and C<decode> will do the same to decode such tags.
		271
		272	See L<SECURITY CONSIDERATIONS>, below, for more info on why forbidding this
		273	protocol can be useful.
		274
215	=item $cbor = $cbor->allow_stringref ([$enable])	275	=item $cbor = $cbor->pack_strings ([$enable])
216		276
217	=item $enabled = $cbor->get_allow_stringref	277	=item $enabled = $cbor->get_pack_strings
218		278
219	If C<$enable> is true (or missing), then C<encode> will try not to encode	279	If C<$enable> is true (or missing), then C<encode> will try not to encode
220	the same string twice, but will instead encode a reference to the string	280	the same string twice, but will instead encode a reference to the string
221	instead. Depending on your data format. this can save a lot of space, but	281	instead. Depending on your data format, this can save a lot of space, but
222	also results in a very large runtime overhead (expect encoding times to be	282	also results in a very large runtime overhead (expect encoding times to be
223	2-4 times as high as without).	283	2-4 times as high as without).
224		284
225	It is recommended to leave it off unless you know your	285	It is recommended to leave it off unless you know your
226	communications partner supports the stringref extension to CBOR	286	communications partner supports the stringref extension to CBOR
227	(http://cbor.schmorp.de/stringref).	287	(L<http://cbor.schmorp.de/stringref>), as without decoder support, the
		288	resulting data structure might not be usable.
228		289
229	If C<$enable> is false (the default), then C<encode> will encode	290	If C<$enable> is false (the default), then C<encode> will encode strings
230	exception when it encounters anything it cannot encode as CBOR.	291	the standard CBOR way.
231		292
232	This option does not affect C<decode> in any way - string references will	293	This option does not affect C<decode> in any way - string references will
233	always be decoded properly if present.	294	always be decoded properly if present.
		295
		296	=item $cbor = $cbor->text_keys ([$enable])
		297
		298	=item $enabled = $cbor->get_text_keys
		299
		300	If C<$enabled> is true (or missing), then C<encode> will encode all
		301	perl hash keys as CBOR text strings/UTF-8 string, upgrading them as needed.
		302
		303	If C<$enable> is false (the default), then C<encode> will encode hash keys
		304	normally - upgraded perl strings (strings internally encoded as UTF-8) as
		305	CBOR text strings, and downgraded perl strings as CBOR byte strings.
		306
		307	This option does not affect C<decode> in any way.
		308
		309	This option is useful for interoperability with CBOR decoders that don't
		310	treat byte strings as a form of text. It is especially useful as Perl
		311	gives very little control over hash keys.
		312
		313	Enabling this option can be slow, as all downgraded hash keys that are
		314	encoded need to be scanned and converted to UTF-8.
		315
		316	=item $cbor = $cbor->text_strings ([$enable])
		317
		318	=item $enabled = $cbor->get_text_strings
		319
		320	This option works similar to C<text_keys>, above, but works on all strings
		321	(including hash keys), so C<text_keys> has no further effect after
		322	enabling C<text_strings>.
		323
		324	If C<$enabled> is true (or missing), then C<encode> will encode all perl
		325	strings as CBOR text strings/UTF-8 strings, upgrading them as needed.
		326
		327	If C<$enable> is false (the default), then C<encode> will encode strings
		328	normally (but see C<text_keys>) - upgraded perl strings (strings
		329	internally encoded as UTF-8) as CBOR text strings, and downgraded perl
		330	strings as CBOR byte strings.
		331
		332	This option does not affect C<decode> in any way.
		333
		334	This option has similar advantages and disadvantages as C<text_keys>. In
		335	addition, this option effectively removes the ability to automatically
		336	encode byte strings, which might break some C<FREEZE> and C<TO_CBOR>
		337	methods that rely on this.
		338
		339	A workaround is to use explicit type casts, which are unaffected by this option.
		340
		341	=item $cbor = $cbor->validate_utf8 ([$enable])
		342
		343	=item $enabled = $cbor->get_validate_utf8
		344
		345	If C<$enable> is true (or missing), then C<decode> will validate that
		346	elements (text strings) containing UTF-8 data in fact contain valid UTF-8
		347	data (instead of blindly accepting it). This validation obviously takes
		348	extra time during decoding.
		349
		350	The concept of "valid UTF-8" used is perl's concept, which is a superset
		351	of the official UTF-8.
		352
		353	If C<$enable> is false (the default), then C<decode> will blindly accept
		354	UTF-8 data, marking them as valid UTF-8 in the resulting data structure
		355	regardless of whether that's true or not.
		356
		357	Perl isn't too happy about corrupted UTF-8 in strings, but should
		358	generally not crash or do similarly evil things. Extensions might be not
		359	so forgiving, so it's recommended to turn on this setting if you receive
		360	untrusted CBOR.
		361
		362	This option does not affect C<encode> in any way - strings that are
		363	supposedly valid UTF-8 will simply be dumped into the resulting CBOR
		364	string without checking whether that is, in fact, true or not.
		365
		366	=item $cbor = $cbor->filter ([$cb->($tag, $value)])
		367
		368	=item $cb_or_undef = $cbor->get_filter
		369
		370	Sets or replaces the tagged value decoding filter (when C<$cb> is
		371	specified) or clears the filter (if no argument or C<undef> is provided).
		372
		373	The filter callback is called only during decoding, when a non-enforced
		374	tagged value has been decoded (see L<TAG HANDLING AND EXTENSIONS> for a
		375	list of enforced tags). For specific tags, it's often better to provide a
		376	default converter using the C<%CBOR::XS::FILTER> hash (see below).
		377
		378	The first argument is the numerical tag, the second is the (decoded) value
		379	that has been tagged.
		380
		381	The filter function should return either exactly one value, which will
		382	replace the tagged value in the decoded data structure, or no values,
		383	which will result in default handling, which currently means the decoder
		384	creates a C<CBOR::XS::Tagged> object to hold the tag and the value.
		385
		386	When the filter is cleared (the default state), the default filter
		387	function, C<CBOR::XS::default_filter>, is used. This function simply
		388	looks up the tag in the C<%CBOR::XS::FILTER> hash. If an entry exists
		389	it must be a code reference that is called with tag and value, and is
		390	responsible for decoding the value. If no entry exists, it returns no
		391	values. C<CBOR::XS> provides a number of default filter functions already,
		392	the the C<%CBOR::XS::FILTER> hash can be freely extended with more.
		393
		394	C<CBOR::XS> additionally provides an alternative filter function that is
		395	supposed to be safe to use with untrusted data (which the default filter
		396	might not), called C<CBOR::XS::safe_filter>, which works the same as
		397	the C<default_filter> but uses the C<%CBOR::XS::SAFE_FILTER> variable
		398	instead. It is prepopulated with the tag decoding functions that are
		399	deemed safe (basically the same as C<%CBOR::XS::FILTER> without all
		400	the bignum tags), and can be extended by user code as wlel, although,
		401	obviously, one should be very careful about adding decoding functions
		402	here, since the expectation is that they are safe to use on untrusted
		403	data, after all.
		404
		405	Example: decode all tags not handled internally into C<CBOR::XS::Tagged>
		406	objects, with no other special handling (useful when working with
		407	potentially "unsafe" CBOR data).
		408
		409	CBOR::XS->new->filter (sub { })->decode ($cbor_data);
		410
		411	Example: provide a global filter for tag 1347375694, converting the value
		412	into some string form.
		413
		414	$CBOR::XS::FILTER{1347375694} = sub {
		415	my ($tag, $value);
		416
		417	"tag 1347375694 value $value"
		418	};
		419
		420	Example: provide your own filter function that looks up tags in your own
		421	hash:
		422
		423	my %my_filter = (
		424	998347484 => sub {
		425	my ($tag, $value);
		426
		427	"tag 998347484 value $value"
		428	};
		429	);
		430
		431	my $coder = CBOR::XS->new->filter (sub {
		432	&{ $my_filter{$_[0]} or return }
		433	});
		434
		435
		436	Example: use the safe filter function (see L<SECURITY CONSIDERATIONS> for
		437	more considerations on security).
		438
		439	CBOR::XS->new->filter (\&CBOR::XS::safe_filter)->decode ($cbor_data);
234		440
235	=item $cbor_data = $cbor->encode ($perl_scalar)	441	=item $cbor_data = $cbor->encode ($perl_scalar)
236		442
237	Converts the given Perl data structure (a scalar value) to its CBOR	443	Converts the given Perl data structure (a scalar value) to its CBOR
238	representation.	444	representation.
…		…
248	when there is trailing garbage after the CBOR string, it will silently	454	when there is trailing garbage after the CBOR string, it will silently
249	stop parsing there and return the number of characters consumed so far.	455	stop parsing there and return the number of characters consumed so far.
250		456
251	This is useful if your CBOR texts are not delimited by an outer protocol	457	This is useful if your CBOR texts are not delimited by an outer protocol
252	and you need to know where the first CBOR string ends amd the next one	458	and you need to know where the first CBOR string ends amd the next one
253	starts.	459	starts - CBOR strings are self-delimited, so it is possible to concatenate
		460	CBOR strings without any delimiters or size fields and recover their data.
254		461
255	CBOR::XS->new->decode_prefix ("......")	462	CBOR::XS->new->decode_prefix ("......")
256	=> ("...", 3)	463	=> ("...", 3)
		464
		465	=back
		466
		467	=head2 INCREMENTAL PARSING
		468
		469	In some cases, there is the need for incremental parsing of JSON
		470	texts. While this module always has to keep both CBOR text and resulting
		471	Perl data structure in memory at one time, it does allow you to parse a
		472	CBOR stream incrementally, using a similar to using "decode_prefix" to see
		473	if a full CBOR object is available, but is much more efficient.
		474
		475	It basically works by parsing as much of a CBOR string as possible - if
		476	the CBOR data is not complete yet, the pasrer will remember where it was,
		477	to be able to restart when more data has been accumulated. Once enough
		478	data is available to either decode a complete CBOR value or raise an
		479	error, a real decode will be attempted.
		480
		481	A typical use case would be a network protocol that consists of sending
		482	and receiving CBOR-encoded messages. The solution that works with CBOR and
		483	about anything else is by prepending a length to every CBOR value, so the
		484	receiver knows how many octets to read. More compact (and slightly slower)
		485	would be to just send CBOR values back-to-back, as C<CBOR::XS> knows where
		486	a CBOR value ends, and doesn't need an explicit length.
		487
		488	The following methods help with this:
		489
		490	=over 4
		491
		492	=item @decoded = $cbor->incr_parse ($buffer)
		493
		494	This method attempts to decode exactly one CBOR value from the beginning
		495	of the given C<$buffer>. The value is removed from the C<$buffer> on
		496	success. When C<$buffer> doesn't contain a complete value yet, it returns
		497	nothing. Finally, when the C<$buffer> doesn't start with something
		498	that could ever be a valid CBOR value, it raises an exception, just as
		499	C<decode> would. In the latter case the decoder state is undefined and
		500	must be reset before being able to parse further.
		501
		502	This method modifies the C<$buffer> in place. When no CBOR value can be
		503	decoded, the decoder stores the current string offset. On the next call,
		504	continues decoding at the place where it stopped before. For this to make
		505	sense, the C<$buffer> must begin with the same octets as on previous
		506	unsuccessful calls.
		507
		508	You can call this method in scalar context, in which case it either
		509	returns a decoded value or C<undef>. This makes it impossible to
		510	distinguish between CBOR null values (which decode to C<undef>) and an
		511	unsuccessful decode, which is often acceptable.
		512
		513	=item @decoded = $cbor->incr_parse_multiple ($buffer)
		514
		515	Same as C<incr_parse>, but attempts to decode as many CBOR values as
		516	possible in one go, instead of at most one. Calls to C<incr_parse> and
		517	C<incr_parse_multiple> can be interleaved.
		518
		519	=item $cbor->incr_reset
		520
		521	Resets the incremental decoder. This throws away any saved state, so that
		522	subsequent calls to C<incr_parse> or C<incr_parse_multiple> start to parse
		523	a new CBOR value from the beginning of the C<$buffer> again.
		524
		525	This method can be called at any time, but it I<must> be called if you want
		526	to change your C<$buffer> or there was a decoding error and you want to
		527	reuse the C<$cbor> object for future incremental parsings.
257		528
258	=back	529	=back
259		530
260		531
261	=head1 MAPPING	532	=head1 MAPPING
…		…
279	CBOR integers become (numeric) perl scalars. On perls without 64 bit	550	CBOR integers become (numeric) perl scalars. On perls without 64 bit
280	support, 64 bit integers will be truncated or otherwise corrupted.	551	support, 64 bit integers will be truncated or otherwise corrupted.
281		552
282	=item byte strings	553	=item byte strings
283		554
284	Byte strings will become octet strings in Perl (the byte values 0..255	555	Byte strings will become octet strings in Perl (the Byte values 0..255
285	will simply become characters of the same value in Perl).	556	will simply become characters of the same value in Perl).
286		557
287	=item UTF-8 strings	558	=item UTF-8 strings
288		559
289	UTF-8 strings in CBOR will be decoded, i.e. the UTF-8 octets will be	560	UTF-8 strings in CBOR will be decoded, i.e. the UTF-8 octets will be
…		…
307	C<Types:Serialiser::false> and C<Types::Serialiser::error>,	578	C<Types:Serialiser::false> and C<Types::Serialiser::error>,
308	respectively. They are overloaded to act almost exactly like the numbers	579	respectively. They are overloaded to act almost exactly like the numbers
309	C<1> and C<0> (for true and false) or to throw an exception on access (for	580	C<1> and C<0> (for true and false) or to throw an exception on access (for
310	error). See the L<Types::Serialiser> manpage for details.	581	error). See the L<Types::Serialiser> manpage for details.
311		582
312	=item CBOR tag 256 (perl object)	583	=item tagged values
313		584
314	The tag value C<256> (TODO: pending iana registration) will be used
315	to deserialise a Perl object serialised with C<FREEZE>. See L<OBJECT
316	SERIALISATION>, below, for details.
317
318	=item CBOR tag 55799 (magic header)
319
320	The tag 55799 is ignored (this tag implements the magic header).
321
322	=item other CBOR tags
323
324	Tagged items consists of a numeric tag and another CBOR value. Tags not	585	Tagged items consists of a numeric tag and another CBOR value.
325	handled internally are currently converted into a L<CBOR::XS::Tagged>
326	object, which is simply a blessed array reference consisting of the
327	numeric tag value followed by the (decoded) CBOR value.
328		586
329	In the future, support for user-supplied conversions might get added.	587	See L<TAG HANDLING AND EXTENSIONS> and the description of C<< ->filter >>
		588	for details on which tags are handled how.
330		589
331	=item anything else	590	=item anything else
332		591
333	Anything else (e.g. unsupported simple values) will raise a decoding	592	Anything else (e.g. unsupported simple values) will raise a decoding
334	error.	593	error.
…		…
337		596
338		597
339	=head2 PERL -> CBOR	598	=head2 PERL -> CBOR
340		599
341	The mapping from Perl to CBOR is slightly more difficult, as Perl is a	600	The mapping from Perl to CBOR is slightly more difficult, as Perl is a
342	truly typeless language, so we can only guess which CBOR type is meant by	601	typeless language. That means this module can only guess which CBOR type
343	a Perl value.	602	is meant by a perl value.
344		603
345	=over 4	604	=over 4
346		605
347	=item hash references	606	=item hash references
348		607
349	Perl hash references become CBOR maps. As there is no inherent ordering in	608	Perl hash references become CBOR maps. As there is no inherent ordering in
350	hash keys (or CBOR maps), they will usually be encoded in a pseudo-random	609	hash keys (or CBOR maps), they will usually be encoded in a pseudo-random
351	order.	610	order. This order can be different each time a hash is encoded.
352		611
353	Currently, tied hashes will use the indefinite-length format, while normal	612	Currently, tied hashes will use the indefinite-length format, while normal
354	hashes will use the fixed-length format.	613	hashes will use the fixed-length format.
355		614
356	=item array references	615	=item array references
357		616
358	Perl array references become fixed-length CBOR arrays.	617	Perl array references become fixed-length CBOR arrays.
359		618
360	=item other references	619	=item other references
361		620
362	Other unblessed references are generally not allowed and will cause an	621	Other unblessed references will be represented using
363	exception to be thrown, except for references to the integers C<0> and	622	the indirection tag extension (tag value C<22098>,
364	C<1>, which get turned into false and true in CBOR.	623	L<http://cbor.schmorp.de/indirection>). CBOR decoders are guaranteed
		624	to be able to decode these values somehow, by either "doing the right
		625	thing", decoding into a generic tagged object, simply ignoring the tag, or
		626	something else.
365		627
366	=item CBOR::XS::Tagged objects	628	=item CBOR::XS::Tagged objects
367		629
368	Objects of this type must be arrays consisting of a single C<[tag, value]>	630	Objects of this type must be arrays consisting of a single C<[tag, value]>
369	pair. The (numerical) tag will be encoded as a CBOR tag, the value will	631	pair. The (numerical) tag will be encoded as a CBOR tag, the value will
370	be encoded as appropriate for the value. You cna use C<CBOR::XS::tag> to	632	be encoded as appropriate for the value. You must use C<CBOR::XS::tag> to
371	create such objects.	633	create such objects.
372		634
373	=item Types::Serialiser::true, Types::Serialiser::false, Types::Serialiser::error	635	=item Types::Serialiser::true, Types::Serialiser::false, Types::Serialiser::error
374		636
375	These special values become CBOR true, CBOR false and CBOR undefined	637	These special values become CBOR true, CBOR false and CBOR undefined
…		…
377	if you want.	639	if you want.
378		640
379	=item other blessed objects	641	=item other blessed objects
380		642
381	Other blessed objects are serialised via C<TO_CBOR> or C<FREEZE>. See	643	Other blessed objects are serialised via C<TO_CBOR> or C<FREEZE>. See
382	L<OBJECT SERIALISATION>, below, for details.	644	L<TAG HANDLING AND EXTENSIONS> for specific classes handled by this
		645	module, and L<OBJECT SERIALISATION> for generic object serialisation.
383		646
384	=item simple scalars	647	=item simple scalars
385		648
386	TODO
387	Simple Perl scalars (any scalar that is not a reference) are the most	649	Simple Perl scalars (any scalar that is not a reference) are the most
388	difficult objects to encode: CBOR::XS will encode undefined scalars as	650	difficult objects to encode: CBOR::XS will encode undefined scalars as
389	CBOR null values, scalars that have last been used in a string context	651	CBOR null values, scalars that have last been used in a string context
390	before encoding as CBOR strings, and anything else as number value:	652	before encoding as CBOR strings, and anything else as number value:
391		653
392	# dump as number	654	# dump as number
393	encode_cbor [2] # yields [2]	655	encode_cbor [2] # yields [2]
394	encode_cbor [-3.0e17] # yields [-3e+17]	656	encode_cbor [-3.0e17] # yields [-3e+17]
395	my $value = 5; encode_cbor [$value] # yields [5]	657	my $value = 5; encode_cbor [$value] # yields [5]
396		658
397	# used as string, so dump as string	659	# used as string, so dump as string (either byte or text)
398	print $value;	660	print $value;
399	encode_cbor [$value] # yields ["5"]	661	encode_cbor [$value] # yields ["5"]
400		662
401	# undef becomes null	663	# undef becomes null
402	encode_cbor [undef] # yields [null]	664	encode_cbor [undef] # yields [null]
…		…
405		667
406	my $x = 3.1; # some variable containing a number	668	my $x = 3.1; # some variable containing a number
407	"$x"; # stringified	669	"$x"; # stringified
408	$x .= ""; # another, more awkward way to stringify	670	$x .= ""; # another, more awkward way to stringify
409	print $x; # perl does it for you, too, quite often	671	print $x; # perl does it for you, too, quite often
		672
		673	You can force whether a string is encoded as byte or text string by using
		674	C<utf8::upgrade> and C<utf8::downgrade> (if C<text_strings> is disabled).
		675
		676	utf8::upgrade $x; # encode $x as text string
		677	utf8::downgrade $x; # encode $x as byte string
		678
		679	More options are available, see L<TYPE CASTS>, below, and the C<text_keys>
		680	and C<text_strings> options.
		681
		682	Perl doesn't define what operations up- and downgrade strings, so if the
		683	difference between byte and text is important, you should up- or downgrade
		684	your string as late as possible before encoding. You can also force the
		685	use of CBOR text strings by using C<text_keys> or C<text_strings>.
410		686
411	You can force the type to be a CBOR number by numifying it:	687	You can force the type to be a CBOR number by numifying it:
412		688
413	my $x = "3"; # some variable containing a string	689	my $x = "3"; # some variable containing a string
414	$x += 0; # numify it, ensuring it will be dumped as a number	690	$x += 0; # numify it, ensuring it will be dumped as a number
…		…
425	represent numerical values are supported, but might suffer loss of	701	represent numerical values are supported, but might suffer loss of
426	precision.	702	precision.
427		703
428	=back	704	=back
429		705
		706	=head2 TYPE CASTS
		707
		708	B<EXPERIMENTAL>: As an experimental extension, C<CBOR::XS> allows you to
		709	force specific cbor types to be used when encoding. That allows you to
		710	encode types not normally accessible (e.g. half floats) as well as force
		711	string types even when C<text_strings> is in effect.
		712
		713	Type forcing is done by calling a special "cast" function which keeps a
		714	copy of the value and returns a new value that can be handed over to any
		715	CBOR encoder function.
		716
		717	The following casts are currently available (all of which are unary
		718	operators, that is, have a prototype of C<$>):
		719
		720	=over
		721
		722	=item CBOR::XS::as_int $value
		723
		724	Forces the value to be encoded as some form of (basic, not bignum) integer
		725	type.
		726
		727	=item CBOR::XS::as_text $value
		728
		729	Forces the value to be encoded as (UTF-8) text values.
		730
		731	=item CBOR::XS::as_bytes $value
		732
		733	Forces the value to be encoded as a (binary) string value.
		734
		735	Example: encode a perl string as binary even though C<text_strings> is in
		736	effect.
		737
		738	CBOR::XS->new->text_strings->encode ([4, "text", CBOR::XS::bytes "bytevalue"]);
		739
		740	=item CBOR::XS::as_bool $value
		741
		742	Converts a Perl boolean (which can be any kind of scalar) into a CBOR
		743	boolean. Strictly the same, but shorter to write, than:
		744
		745	$value ? Types::Serialiser::true : Types::Serialiser::false
		746
		747	=item CBOR::XS::as_float16 $value
		748
		749	Forces half-float (IEEE 754 binary16) encoding of the given value.
		750
		751	=item CBOR::XS::as_float32 $value
		752
		753	Forces single-float (IEEE 754 binary32) encoding of the given value.
		754
		755	=item CBOR::XS::as_float64 $value
		756
		757	Forces double-float (IEEE 754 binary64) encoding of the given value.
		758
		759	=item CBOR::XS::as_cbor $cbor_text
		760
		761	Not a type cast per-se, this type cast forces the argument to eb encoded
		762	as-is. This can be used to embed pre-encoded CBOR data.
		763
		764	Note that no checking on the validity of the C<$cbor_text> is done - it's
		765	the callers responsibility to correctly encode values.
		766
		767	=item CBOR::XS::as_map [key => value...]
		768
		769	Treat the array reference as key value pairs and output a CBOR map. This
		770	allows you to generate CBOR maps with arbitrary key types (or, if you
		771	don't care about semantics, duplicate keys or pairs in a custom order),
		772	which is otherwise hard to do with Perl.
		773
		774	The single argument must be an array reference with an even number of
		775	elements.
		776
		777	Note that only the reference to the array is copied, the array itself is
		778	not. Modifications done to the array before calling an encoding fuinction
		779	will be reflected in the encoded output.
		780
		781	Example: encode a CBOR map with a string and an integer as keys.
		782
		783	encode_cbor CBOR::XS::as_map [string => "value", 5 => "value"]
		784
		785	=back
		786
		787	=cut
		788
		789	sub CBOR::XS::as_cbor ($) { bless [$_[0], 0, undef], CBOR::XS::Tagged:: }
		790	sub CBOR::XS::as_int ($) { bless [$_[0], 1, undef], CBOR::XS::Tagged:: }
		791	sub CBOR::XS::as_bytes ($) { bless [$_[0], 2, undef], CBOR::XS::Tagged:: }
		792	sub CBOR::XS::as_text ($) { bless [$_[0], 3, undef], CBOR::XS::Tagged:: }
		793	sub CBOR::XS::as_float16 ($) { bless [$_[0], 4, undef], CBOR::XS::Tagged:: }
		794	sub CBOR::XS::as_float32 ($) { bless [$_[0], 5, undef], CBOR::XS::Tagged:: }
		795	sub CBOR::XS::as_float64 ($) { bless [$_[0], 6, undef], CBOR::XS::Tagged:: }
		796
		797	sub CBOR::XS::as_bool ($) { $_[0] ? $Types::Serialiser::true : $Types::Serialiser::false }
		798
		799	sub CBOR::XS::as_map ($) {
		800	ARRAY:: eq ref $_[0]
		801	and $#{ $_[0] } & 1
		802	or do { require Carp; Carp::croak ("CBOR::XS::as_map only acepts array references with an even number of elements, caught") };
		803
		804	bless [$_[0], 7, undef], CBOR::XS::Tagged::
		805	}
		806
430	=head2 OBJECT SERIALISATION	807	=head2 OBJECT SERIALISATION
		808
		809	This module implements both a CBOR-specific and the generic
		810	L<Types::Serialier> object serialisation protocol. The following
		811	subsections explain both methods.
		812
		813	=head3 ENCODING
431		814
432	This module knows two way to serialise a Perl object: The CBOR-specific	815	This module knows two way to serialise a Perl object: The CBOR-specific
433	way, and the generic way.	816	way, and the generic way.
434		817
435	Whenever the encoder encounters a Perl object that it cnanot serialise	818	Whenever the encoder encounters a Perl object that it cannot serialise
436	directly (most of them), it will first look up the C<TO_CBOR> method on	819	directly (most of them), it will first look up the C<TO_CBOR> method on
437	it.	820	it.
438		821
439	If it has a C<TO_CBOR> method, it will call it with the object as only	822	If it has a C<TO_CBOR> method, it will call it with the object as only
440	argument, and expects exactly one return value, which it will then	823	argument, and expects exactly one return value, which it will then
…		…
446		829
447	The C<FREEZE> method can return any number of values (i.e. zero or	830	The C<FREEZE> method can return any number of values (i.e. zero or
448	more). These will be encoded as CBOR perl object, together with the	831	more). These will be encoded as CBOR perl object, together with the
449	classname.	832	classname.
450		833
		834	These methods I<MUST NOT> change the data structure that is being
		835	serialised. Failure to comply to this can result in memory corruption -
		836	and worse.
		837
451	If an object supports neither C<TO_CBOR> nor C<FREEZE>, encoding will fail	838	If an object supports neither C<TO_CBOR> nor C<FREEZE>, encoding will fail
452	with an error.	839	with an error.
453		840
		841	=head3 DECODING
		842
454	Objects encoded via C<TO_CBOR> cannot be automatically decoded, but	843	Objects encoded via C<TO_CBOR> cannot (normally) be automatically decoded,
455	objects encoded via C<FREEZE> can be decoded using the following protocol:	844	but objects encoded via C<FREEZE> can be decoded using the following
		845	protocol:
456		846
457	When an encoded CBOR perl object is encountered by the decoder, it will	847	When an encoded CBOR perl object is encountered by the decoder, it will
458	look up the C<THAW> method, by using the stored classname, and will fail	848	look up the C<THAW> method, by using the stored classname, and will fail
459	if the method cannot be found.	849	if the method cannot be found.
460		850
461	After the lookup it will call the C<THAW> method with the stored classname	851	After the lookup it will call the C<THAW> method with the stored classname
462	as first argument, the constant string C<CBOR> as second argument, and all	852	as first argument, the constant string C<CBOR> as second argument, and all
463	values returned by C<FREEZE> as remaining arguments.	853	values returned by C<FREEZE> as remaining arguments.
464		854
465	=head4 EXAMPLES	855	=head3 EXAMPLES
466		856
467	Here is an example C<TO_CBOR> method:	857	Here is an example C<TO_CBOR> method:
468		858
469	sub My::Object::TO_CBOR {	859	sub My::Object::TO_CBOR {
470	my ($obj) = @_;	860	my ($obj) = @_;
…		…
481		871
482	sub URI::TO_CBOR {	872	sub URI::TO_CBOR {
483	my ($self) = @_;	873	my ($self) = @_;
484	my $uri = "$self"; # stringify uri	874	my $uri = "$self"; # stringify uri
485	utf8::upgrade $uri; # make sure it will be encoded as UTF-8 string	875	utf8::upgrade $uri; # make sure it will be encoded as UTF-8 string
486	CBOR::XS::tagged 32, "$_[0]"	876	CBOR::XS::tag 32, "$_[0]"
487	}	877	}
488		878
489	This will encode URIs as a UTF-8 string with tag 32, which indicates an	879	This will encode URIs as a UTF-8 string with tag 32, which indicates an
490	URI.	880	URI.
491		881
…		…
502	"$self" # encode url string	892	"$self" # encode url string
503	}	893	}
504		894
505	sub URI::THAW {	895	sub URI::THAW {
506	my ($class, $serialiser, $uri) = @_;	896	my ($class, $serialiser, $uri) = @_;
507
508	$class->new ($uri)	897	$class->new ($uri)
509	}	898	}
510		899
511	Unlike C<TO_CBOR>, multiple values can be returned by C<FREEZE>. For	900	Unlike C<TO_CBOR>, multiple values can be returned by C<FREEZE>. For
512	example, a C<FREEZE> method that returns "type", "id" and "variant" values	901	example, a C<FREEZE> method that returns "type", "id" and "variant" values
…		…
633	and extensions. If a tag is not mentioned here and no additional filters	1022	and extensions. If a tag is not mentioned here and no additional filters
634	are provided for it, then the default handling applies (creating a	1023	are provided for it, then the default handling applies (creating a
635	CBOR::XS::Tagged object on decoding, and only encoding the tag when	1024	CBOR::XS::Tagged object on decoding, and only encoding the tag when
636	explicitly requested).	1025	explicitly requested).
637		1026
		1027	Tags not handled specifically are currently converted into a
		1028	L<CBOR::XS::Tagged> object, which is simply a blessed array reference
		1029	consisting of the numeric tag value followed by the (decoded) CBOR value.
		1030
638	Future versions of this module reserve the right to special case	1031	Future versions of this module reserve the right to special case
639	additional tags (such as base64url).	1032	additional tags (such as base64url).
640		1033
641	=head2 ENFORCED TAGS	1034	=head2 ENFORCED TAGS
642		1035
643	These tags are always handled when decoding, and their handling cannot be	1036	These tags are always handled when decoding, and their handling cannot be
644	overriden by the user.	1037	overridden by the user.
645		1038
646	=over 4	1039	=over 4
647		1040
648	=item <unassigned> (perl-object, L<http://cbor.schmorp.de/perl-object>)	1041	=item 26 (perl-object, L<http://cbor.schmorp.de/perl-object>)
649		1042
650	These tags are automatically created for serialisable objects using the	1043	These tags are automatically created (and decoded) for serialisable
651	C<FREEZE/THAW> methods (the L<Types::Serialier> object serialisation	1044	objects using the C<FREEZE/THAW> methods (the L<Types::Serialier> object
652	protocol).	1045	serialisation protocol). See L<OBJECT SERIALISATION> for details.
653		1046
654	=item <unassigned>, <unassigned> (sharable, sharedref, L <http://cbor.schmorp.de/value-sharing>)	1047	=item 28, 29 (shareable, sharedref, L<http://cbor.schmorp.de/value-sharing>)
655		1048
656	These tags are automatically decoded when encountered, resulting in	1049	These tags are automatically decoded when encountered (and they do not
		1050	result in a cyclic data structure, see C<allow_cycles>), resulting in
657	shared values in the decoded object. They are only encoded, however, when	1051	shared values in the decoded object. They are only encoded, however, when
658	C<allow_sharable> is enabled.	1052	C<allow_sharing> is enabled.
659		1053
		1054	Not all shared values can be successfully decoded: values that reference
		1055	themselves will I<currently> decode as C<undef> (this is not the same
		1056	as a reference pointing to itself, which will be represented as a value
		1057	that contains an indirect reference to itself - these will be decoded
		1058	properly).
		1059
		1060	Note that considerably more shared value data structures can be decoded
		1061	than will be encoded - currently, only values pointed to by references
		1062	will be shared, others will not. While non-reference shared values can be
		1063	generated in Perl with some effort, they were considered too unimportant
		1064	to be supported in the encoder. The decoder, however, will decode these
		1065	values as shared values.
		1066
660	=item <unassigned>, <unassigned> (stringref-namespace, stringref, L <http://cbor.schmorp.de/stringref>)	1067	=item 256, 25 (stringref-namespace, stringref, L<http://cbor.schmorp.de/stringref>)
661		1068
662	These tags are automatically decoded when encountered. They are only	1069	These tags are automatically decoded when encountered. They are only
663	encoded, however, when C<allow_stringref> is enabled.	1070	encoded, however, when C<pack_strings> is enabled.
664		1071
665	=item 22098 (indirection, L<http://cbor.schmorp.de/indirection>)	1072	=item 22098 (indirection, L<http://cbor.schmorp.de/indirection>)
666		1073
667	This tag is automatically generated when a reference are encountered (with	1074	This tag is automatically generated when a reference are encountered (with
668	the exception of hash and array refernces). It is converted to a reference	1075	the exception of hash and array references). It is converted to a reference
669	when decoding.	1076	when decoding.
670		1077
671	=item 55799 (self-describe CBOR, RFC 7049)	1078	=item 55799 (self-describe CBOR, RFC 7049)
672		1079
673	This value is not generated on encoding (unless explicitly requested by	1080	This value is not generated on encoding (unless explicitly requested by
674	the user), and is simply ignored when decoding.	1081	the user), and is simply ignored when decoding.
675		1082
676	=back	1083	=back
677		1084
678	=head2 OPTIONAL TAGS	1085	=head2 NON-ENFORCED TAGS
679		1086
680	These tags have default filters provided when decoding. Their handling can	1087	These tags have default filters provided when decoding. Their handling can
681	be overriden by changing the C<%CBOR::XS::FILTER> entry for the tag, or by	1088	be overridden by changing the C<%CBOR::XS::FILTER> entry for the tag, or by
682	providing a custom C<filter> function when decoding.	1089	providing a custom C<filter> callback when decoding.
683		1090
684	When they result in decoding into a specific Perl class, the module	1091	When they result in decoding into a specific Perl class, the module
685	usually provides a corresponding C<TO_CBOR> method as well.	1092	usually provides a corresponding C<TO_CBOR> method as well.
686		1093
687	When any of these need to load additional modules that are not part of the	1094	When any of these need to load additional modules that are not part of the
…		…
689	provide these modules. The decoding usually fails with an exception if the	1096	provide these modules. The decoding usually fails with an exception if the
690	required module cannot be loaded.	1097	required module cannot be loaded.
691		1098
692	=over 4	1099	=over 4
693		1100
		1101	=item 0, 1 (date/time string, seconds since the epoch)
		1102
		1103	These tags are decoded into L<Time::Piece> objects. The corresponding
		1104	C<Time::Piece::TO_CBOR> method always encodes into tag 1 values currently.
		1105
		1106	The L<Time::Piece> API is generally surprisingly bad, and fractional
		1107	seconds are only accidentally kept intact, so watch out. On the plus side,
		1108	the module comes with perl since 5.10, which has to count for something.
		1109
694	=item 2, 3 (positive/negative bignum)	1110	=item 2, 3 (positive/negative bignum)
695		1111
696	These tags are decoded into L<Math::BigInt> objects. The corresponding	1112	These tags are decoded into L<Math::BigInt> objects. The corresponding
697	C<Math::BigInt::TO_CBOR> method encodes "small" bigints into normal CBOR	1113	C<Math::BigInt::TO_CBOR> method encodes "small" bigints into normal CBOR
698	integers, and others into positive/negative CBOR bignums.	1114	integers, and others into positive/negative CBOR bignums.
699		1115
700	=item 4, 5 (decimal fraction/bigfloat)	1116	=item 4, 5, 264, 265 (decimal fraction/bigfloat)
701		1117
702	Both decimal fractions and bigfloats are decoded into L<Math::BigFloat>	1118	Both decimal fractions and bigfloats are decoded into L<Math::BigFloat>
703	objects. The corresponding C<Math::BigFloat::TO_CBOR> method I<always>	1119	objects. The corresponding C<Math::BigFloat::TO_CBOR> method I<always>
704	encodes into a decimal fraction.	1120	encodes into a decimal fraction (either tag 4 or 264).
705		1121
706	CBOR cannot represent bigfloats with I<very> large exponents - conversion	1122	NaN and infinities are not encoded properly, as they cannot be represented
707	of such big float objects is undefined.	1123	in CBOR.
708		1124
709	Also, NaN and infinities are not encoded properly.	1125	See L<BIGNUM SECURITY CONSIDERATIONS> for more info.
		1126
		1127	=item 30 (rational numbers)
		1128
		1129	These tags are decoded into L<Math::BigRat> objects. The corresponding
		1130	C<Math::BigRat::TO_CBOR> method encodes rational numbers with denominator
		1131	C<1> via their numerator only, i.e., they become normal integers or
		1132	C<bignums>.
		1133
		1134	See L<BIGNUM SECURITY CONSIDERATIONS> for more info.
710		1135
711	=item 21, 22, 23 (expected later JSON conversion)	1136	=item 21, 22, 23 (expected later JSON conversion)
712		1137
713	CBOR::XS is not a CBOR-to-JSON converter, and will simply ignore these	1138	CBOR::XS is not a CBOR-to-JSON converter, and will simply ignore these
714	tags.	1139	tags.
…		…
719	C<URI::TO_CBOR> method again results in a CBOR URI value.	1144	C<URI::TO_CBOR> method again results in a CBOR URI value.
720		1145
721	=back	1146	=back
722		1147
723	=cut	1148	=cut
724
725	our %FILTER = (
726	# 0 # rfc4287 datetime, utf-8
727	# 1 # unix timestamp, any
728
729	2 => sub { # pos bigint
730	require Math::BigInt;
731	Math::BigInt->new ("0x" . unpack "H*", pop)
732	},
733
734	3 => sub { # neg bigint
735	require Math::BigInt;
736	-Math::BigInt->new ("0x" . unpack "H*", pop)
737	},
738
739	4 => sub { # decimal fraction, array
740	require Math::BigFloat;
741	Math::BigFloat->new ($_[1][1] . "E" . $_[1][0])
742	},
743
744	5 => sub { # bigfloat, array
745	require Math::BigFloat;
746	scalar Math::BigFloat->new ($_[1][1])->blsft ($_[1][0], 2)
747	},
748
749	21 => sub { pop }, # expected conversion to base64url encoding
750	22 => sub { pop }, # expected conversion to base64 encoding
751	23 => sub { pop }, # expected conversion to base16 encoding
752
753	# 24 # embedded cbor, byte string
754
755	32 => sub {
756	require URI;
757	URI->new (pop)
758	},
759
760	# 33 # base64url rfc4648, utf-8
761	# 34 # base64 rfc46484, utf-8
762	# 35 # regex pcre/ecma262, utf-8
763	# 36 # mime message rfc2045, utf-8
764	);
765
766		1149
767	=head1 CBOR and JSON	1150	=head1 CBOR and JSON
768		1151
769	CBOR is supposed to implement a superset of the JSON data model, and is,	1152	CBOR is supposed to implement a superset of the JSON data model, and is,
770	with some coercion, able to represent all JSON texts (something that other	1153	with some coercion, able to represent all JSON texts (something that other
…		…
779	CBOR intact.	1162	CBOR intact.
780		1163
781		1164
782	=head1 SECURITY CONSIDERATIONS	1165	=head1 SECURITY CONSIDERATIONS
783		1166
784	When you are using CBOR in a protocol, talking to untrusted potentially	1167	Tl;dr... if you want to decode or encode CBOR from untrusted sources, you
785	hostile creatures requires relatively few measures.	1168	should start with a coder object created via C<new_safe> (which implements
		1169	the mitigations explained below):
786		1170
		1171	my $coder = CBOR::XS->new_safe;
		1172
		1173	my $data = $coder->decode ($cbor_text);
		1174	my $cbor = $coder->encode ($data);
		1175
		1176	Longer version: When you are using CBOR in a protocol, talking to
		1177	untrusted potentially hostile creatures requires some thought:
		1178
		1179	=over 4
		1180
		1181	=item Security of the CBOR decoder itself
		1182
787	First of all, your CBOR decoder should be secure, that is, should not have	1183	First and foremost, your CBOR decoder should be secure, that is, should
		1184	not have any buffer overflows or similar bugs that could potentially be
788	any buffer overflows. Obviously, this module should ensure that and I am	1185	exploited. Obviously, this module should ensure that and I am trying hard
789	trying hard on making that true, but you never know.	1186	on making that true, but you never know.
790		1187
		1188	=item CBOR::XS can invoke almost arbitrary callbacks during decoding
		1189
		1190	CBOR::XS supports object serialisation - decoding CBOR can cause calls
		1191	to I<any> C<THAW> method in I<any> package that exists in your process
		1192	(that is, CBOR::XS will not try to load modules, but any existing C<THAW>
		1193	method or function can be called, so they all have to be secure).
		1194
		1195	Less obviously, it will also invoke C<TO_CBOR> and C<FREEZE> methods -
		1196	even if all your C<THAW> methods are secure, encoding data structures from
		1197	untrusted sources can invoke those and trigger bugs in those.
		1198
		1199	So, if you are not sure about the security of all the modules you
		1200	have loaded (you shouldn't), you should disable this part using
		1201	C<forbid_objects> or using C<new_safe>.
		1202
		1203	=item CBOR can be extended with tags that call library code
		1204
		1205	CBOR can be extended with tags, and C<CBOR::XS> has a registry of
		1206	conversion functions for many existing tags that can be extended via
		1207	third-party modules (see the C<filter> method).
		1208
		1209	If you don't trust these, you should configure the "safe" filter function,
		1210	C<CBOR::XS::safe_filter> (C<new_safe> does this), which by default only
		1211	includes conversion functions that are considered "safe" by the author
		1212	(but again, they can be extended by third party modules).
		1213
		1214	Depending on your level of paranoia, you can use the "safe" filter:
		1215
		1216	$cbor->filter (\&CBOR::XS::safe_filter);
		1217
		1218	... your own filter...
		1219
		1220	$cbor->filter (sub { ... do your stuffs here ... });
		1221
		1222	... or even no filter at all, disabling all tag decoding:
		1223
		1224	$cbor->filter (sub { });
		1225
		1226	This is never a problem for encoding, as the tag mechanism only exists in
		1227	CBOR texts.
		1228
		1229	=item Resource-starving attacks: object memory usage
		1230
791	Second, you need to avoid resource-starving attacks. That means you should	1231	You need to avoid resource-starving attacks. That means you should limit
792	limit the size of CBOR data you accept, or make sure then when your	1232	the size of CBOR data you accept, or make sure then when your resources
793	resources run out, that's just fine (e.g. by using a separate process that	1233	run out, that's just fine (e.g. by using a separate process that can
794	can crash safely). The size of a CBOR string in octets is usually a good	1234	crash safely). The size of a CBOR string in octets is usually a good
795	indication of the size of the resources required to decode it into a Perl	1235	indication of the size of the resources required to decode it into a Perl
796	structure. While CBOR::XS can check the size of the CBOR text, it might be	1236	structure. While CBOR::XS can check the size of the CBOR text (using
797	too late when you already have it in memory, so you might want to check	1237	C<max_size> - done by C<new_safe>), it might be too late when you already
798	the size before you accept the string.	1238	have it in memory, so you might want to check the size before you accept
		1239	the string.
799		1240
		1241	As for encoding, it is possible to construct data structures that are
		1242	relatively small but result in large CBOR texts (for example by having an
		1243	array full of references to the same big data structure, which will all be
		1244	deep-cloned during encoding by default). This is rarely an actual issue
		1245	(and the worst case is still just running out of memory), but you can
		1246	reduce this risk by using C<allow_sharing>.
		1247
		1248	=item Resource-starving attacks: stack overflows
		1249
800	Third, CBOR::XS recurses using the C stack when decoding objects and	1250	CBOR::XS recurses using the C stack when decoding objects and arrays. The
801	arrays. The C stack is a limited resource: for instance, on my amd64	1251	C stack is a limited resource: for instance, on my amd64 machine with 8MB
802	machine with 8MB of stack size I can decode around 180k nested arrays but	1252	of stack size I can decode around 180k nested arrays but only 14k nested
803	only 14k nested CBOR objects (due to perl itself recursing deeply on croak	1253	CBOR objects (due to perl itself recursing deeply on croak to free the
804	to free the temporary). If that is exceeded, the program crashes. To be	1254	temporary). If that is exceeded, the program crashes. To be conservative,
805	conservative, the default nesting limit is set to 512. If your process	1255	the default nesting limit is set to 512. If your process has a smaller
806	has a smaller stack, you should adjust this setting accordingly with the	1256	stack, you should adjust this setting accordingly with the C<max_depth>
807	C<max_depth> method.	1257	method.
		1258
		1259	=item Resource-starving attacks: CPU en-/decoding complexity
		1260
		1261	CBOR::XS will use the L<Math::BigInt>, L<Math::BigFloat> and
		1262	L<Math::BigRat> libraries to represent encode/decode bignums. These can be
		1263	very slow (as in, centuries of CPU time) and can even crash your program
		1264	(and are generally not very trustworthy). See the next section on bignum
		1265	security for details.
		1266
		1267	=item Data breaches: leaking information in error messages
		1268
		1269	CBOR::XS might leak contents of your Perl data structures in its error
		1270	messages, so when you serialise sensitive information you might want to
		1271	make sure that exceptions thrown by CBOR::XS will not end up in front of
		1272	untrusted eyes.
		1273
		1274	=item Something else...
808		1275
809	Something else could bomb you, too, that I forgot to think of. In that	1276	Something else could bomb you, too, that I forgot to think of. In that
810	case, you get to keep the pieces. I am always open for hints, though...	1277	case, you get to keep the pieces. I am always open for hints, though...
811		1278
812	Also keep in mind that CBOR::XS might leak contents of your Perl data	1279	=back
813	structures in its error messages, so when you serialise sensitive	1280
814	information you might want to make sure that exceptions thrown by CBOR::XS	1281
815	will not end up in front of untrusted eyes.	1282	=head1 BIGNUM SECURITY CONSIDERATIONS
		1283
		1284	CBOR::XS provides a C<TO_CBOR> method for both L<Math::BigInt> and
		1285	L<Math::BigFloat> that tries to encode the number in the simplest possible
		1286	way, that is, either a CBOR integer, a CBOR bigint/decimal fraction (tag
		1287	4) or an arbitrary-exponent decimal fraction (tag 264). Rational numbers
		1288	(L<Math::BigRat>, tag 30) can also contain bignums as members.
		1289
		1290	CBOR::XS will also understand base-2 bigfloat or arbitrary-exponent
		1291	bigfloats (tags 5 and 265), but it will never generate these on its own.
		1292
		1293	Using the built-in L<Math::BigInt::Calc> support, encoding and decoding
		1294	decimal fractions is generally fast. Decoding bigints can be slow for very
		1295	big numbers (tens of thousands of digits, something that could potentially
		1296	be caught by limiting the size of CBOR texts), and decoding bigfloats or
		1297	arbitrary-exponent bigfloats can be I<extremely> slow (minutes, decades)
		1298	for large exponents (roughly 40 bit and longer).
		1299
		1300	Additionally, L<Math::BigInt> can take advantage of other bignum
		1301	libraries, such as L<Math::GMP>, which cannot handle big floats with large
		1302	exponents, and might simply abort or crash your program, due to their code
		1303	quality.
		1304
		1305	This can be a concern if you want to parse untrusted CBOR. If it is, you
		1306	might want to disable decoding of tag 2 (bigint) and 3 (negative bigint)
		1307	types. You should also disable types 5 and 265, as these can be slow even
		1308	without bigints.
		1309
		1310	Disabling bigints will also partially or fully disable types that rely on
		1311	them, e.g. rational numbers that use bignums.
		1312
816		1313
817	=head1 CBOR IMPLEMENTATION NOTES	1314	=head1 CBOR IMPLEMENTATION NOTES
818		1315
819	This section contains some random implementation notes. They do not	1316	This section contains some random implementation notes. They do not
820	describe guaranteed behaviour, but merely behaviour as-is implemented	1317	describe guaranteed behaviour, but merely behaviour as-is implemented
…		…
829	Only the double data type is supported for NV data types - when Perl uses	1326	Only the double data type is supported for NV data types - when Perl uses
830	long double to represent floating point values, they might not be encoded	1327	long double to represent floating point values, they might not be encoded
831	properly. Half precision types are accepted, but not encoded.	1328	properly. Half precision types are accepted, but not encoded.
832		1329
833	Strict mode and canonical mode are not implemented.	1330	Strict mode and canonical mode are not implemented.
		1331
		1332
		1333	=head1 LIMITATIONS ON PERLS WITHOUT 64-BIT INTEGER SUPPORT
		1334
		1335	On perls that were built without 64 bit integer support (these are rare
		1336	nowadays, even on 32 bit architectures, as all major Perl distributions
		1337	are built with 64 bit integer support), support for any kind of 64 bit
		1338	value in CBOR is very limited - most likely, these 64 bit values will
		1339	be truncated, corrupted, or otherwise not decoded correctly. This also
		1340	includes string, float, array and map sizes that are stored as 64 bit
		1341	integers.
834		1342
835		1343
836	=head1 THREADS	1344	=head1 THREADS
837		1345
838	This module is I<not> guaranteed to be thread safe and there are no	1346	This module is I<not> guaranteed to be thread safe and there are no
…		…
852	Please refrain from using rt.cpan.org or any other bug reporting	1360	Please refrain from using rt.cpan.org or any other bug reporting
853	service. I put the contact address into my modules for a reason.	1361	service. I put the contact address into my modules for a reason.
854		1362
855	=cut	1363	=cut
856		1364
		1365	# clumsy and slow hv_store-in-hash helper function
		1366	sub _hv_store {
		1367	$_[0]{$_[1]} = $_[2];
		1368	}
		1369
857	our %FILTER = (	1370	our %FILTER = (
858	# 0 # rfc4287 datetime, utf-8	1371	0 => sub { # rfc4287 datetime, utf-8
859	# 1 # unix timestamp, any	1372	require Time::Piece;
		1373	# Time::Piece::Strptime uses the "incredibly flexible date parsing routine"
		1374	# from FreeBSD, which can't parse ISO 8601, RFC3339, RFC4287 or much of anything
		1375	# else either. Whats incredibe over standard strptime totally escapes me.
		1376	# doesn't do fractional times, either. sigh.
		1377	# In fact, it's all a lie, it uses whatever strptime it wants, and of course,
		1378	# they are all incompatible. The openbsd one simply ignores %z (but according to the
		1379	# docs, it would be much more incredibly flexible indeed. If it worked, that is.).
		1380	scalar eval {
		1381	my $s = $_[1];
		1382
		1383	$s =~ s/Z$/+00:00/;
		1384	$s =~ s/(\.[0-9]+)?([+-][0-9][0-9]):([0-9][0-9])$//
		1385	or die;
		1386
		1387	my $b = $1 - ($2 * 60 + $3) * 60; # fractional part + offset. hopefully
		1388	my $d = Time::Piece->strptime ($s, "%Y-%m-%dT%H:%M:%S");
		1389
		1390	Time::Piece::gmtime ($d->epoch + $b)
		1391	} \|\| die "corrupted CBOR date/time string ($_[0])";
		1392	},
		1393
		1394	1 => sub { # seconds since the epoch, possibly fractional
		1395	require Time::Piece;
		1396	scalar Time::Piece::gmtime (pop)
		1397	},
860		1398
861	2 => sub { # pos bigint	1399	2 => sub { # pos bigint
862	require Math::BigInt;	1400	require Math::BigInt;
863	Math::BigInt->new ("0x" . unpack "H*", pop)	1401	Math::BigInt->new ("0x" . unpack "H*", pop)
864	},	1402	},
…		…
871	4 => sub { # decimal fraction, array	1409	4 => sub { # decimal fraction, array
872	require Math::BigFloat;	1410	require Math::BigFloat;
873	Math::BigFloat->new ($_[1][1] . "E" . $_[1][0])	1411	Math::BigFloat->new ($_[1][1] . "E" . $_[1][0])
874	},	1412	},
875		1413
		1414	264 => sub { # decimal fraction with arbitrary exponent
		1415	require Math::BigFloat;
		1416	Math::BigFloat->new ($_[1][1] . "E" . $_[1][0])
		1417	},
		1418
876	5 => sub { # bigfloat, array	1419	5 => sub { # bigfloat, array
877	require Math::BigFloat;	1420	require Math::BigFloat;
878	scalar Math::BigFloat->new ($_[1][1])->blsft ($_[1][0], 2)	1421	scalar Math::BigFloat->new ($_[1][1]) * Math::BigFloat->new (2)->bpow ($_[1][0])
		1422	},
		1423
		1424	265 => sub { # bigfloat with arbitrary exponent
		1425	require Math::BigFloat;
		1426	scalar Math::BigFloat->new ($_[1][1]) * Math::BigFloat->new (2)->bpow ($_[1][0])
		1427	},
		1428
		1429	30 => sub { # rational number
		1430	require Math::BigRat;
		1431	Math::BigRat->new ("$_[1][0]/$_[1][1]") # separate parameters only work in recent versons
879	},	1432	},
880		1433
881	21 => sub { pop }, # expected conversion to base64url encoding	1434	21 => sub { pop }, # expected conversion to base64url encoding
882	22 => sub { pop }, # expected conversion to base64 encoding	1435	22 => sub { pop }, # expected conversion to base64 encoding
883	23 => sub { pop }, # expected conversion to base16 encoding	1436	23 => sub { pop }, # expected conversion to base16 encoding
…		…
893	# 34 # base64 rfc46484, utf-8	1446	# 34 # base64 rfc46484, utf-8
894	# 35 # regex pcre/ecma262, utf-8	1447	# 35 # regex pcre/ecma262, utf-8
895	# 36 # mime message rfc2045, utf-8	1448	# 36 # mime message rfc2045, utf-8
896	);	1449	);
897		1450
898	sub CBOR::XS::default_filter {	1451	sub default_filter {
899	&{ $FILTER{$_[0]} or return }	1452	&{ $FILTER{$_[0]} or return }
		1453	}
		1454
		1455	our %SAFE_FILTER = map { $_ => $FILTER{$_} } 0, 1, 21, 22, 23, 32;
		1456
		1457	sub safe_filter {
		1458	&{ $SAFE_FILTER{$_[0]} or return }
900	}	1459	}
901		1460
902	sub URI::TO_CBOR {	1461	sub URI::TO_CBOR {
903	my $uri = $_[0]->as_string;	1462	my $uri = $_[0]->as_string;
904	utf8::upgrade $uri;	1463	utf8::upgrade $uri;
905	CBOR::XS::tag 32, $uri	1464	tag 32, $uri
906	}	1465	}
907		1466
908	sub Math::BigInt::TO_CBOR {	1467	sub Math::BigInt::TO_CBOR {
909	if ($_[0] >= -2147483648 && $_[0] <= 2147483647) {	1468	if (-2147483648 <= $_[0] && $_[0] <= 2147483647) {
910	$_[0]->numify	1469	$_[0]->numify
911	} else {	1470	} else {
912	my $hex = substr $_[0]->as_hex, 2;	1471	my $hex = substr $_[0]->as_hex, 2;
913	$hex = "0$hex" if 1 & length $hex; # sigh	1472	$hex = "0$hex" if 1 & length $hex; # sigh
914	CBOR::XS::tag $_[0] >= 0 ? 2 : 3, pack "H*", $hex	1473	tag $_[0] >= 0 ? 2 : 3, pack "H*", $hex
915	}	1474	}
916	}	1475	}
917		1476
918	sub Math::BigFloat::TO_CBOR {	1477	sub Math::BigFloat::TO_CBOR {
919	my ($m, $e) = $_[0]->parts;	1478	my ($m, $e) = $_[0]->parts;
		1479
		1480	-9223372036854775808 <= $e && $e <= 18446744073709551615
920	CBOR::XS::tag 4, [$e->numify, $m]	1481	? tag 4, [$e->numify, $m]
		1482	: tag 264, [$e, $m]
		1483	}
		1484
		1485	sub Math::BigRat::TO_CBOR {
		1486	my ($n, $d) = $_[0]->parts;
		1487
		1488	# older versions of BigRat need *1, as they not always return numbers
		1489
		1490	$d*1 == 1
		1491	? $n*1
		1492	: tag 30, [$n1, $d1]
		1493	}
		1494
		1495	sub Time::Piece::TO_CBOR {
		1496	tag 1, 0 + $_[0]->epoch
921	}	1497	}
922		1498
923	XSLoader::load "CBOR::XS", $VERSION;	1499	XSLoader::load "CBOR::XS", $VERSION;
924		1500
925	=head1 SEE ALSO	1501	=head1 SEE ALSO

Diff Legend

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

Comparing CBOR-XS/XS.pm (file contents): Revision 1.22 by root, Fri Nov 22 15:28:38 2013 UTC vs. Revision 1.80 by root, Fri Dec 11 06:05:33 2020 UTC

Diff Legend

Comparing CBOR-XS/XS.pm (file contents):
Revision 1.22 by root, Fri Nov 22 15:28:38 2013 UTC vs.
Revision 1.80 by root, Fri Dec 11 06:05:33 2020 UTC