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

Comparing CBOR-XS/XS.pm (file contents):
Revision 1.29 by root, Sat Nov 30 15:23:59 2013 UTC vs.
Revision 1.88 by root, Thu Sep 7 23:52:24 2023 UTC

…		…
38	with the added ability of supporting serialisation of Perl objects. (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	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	40	data later and speed is less important you might want to compare both
41	formats first).	41	formats first).
42		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.
		45
43	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,
44	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
45	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
46	data, the worse L<Storable> performs in comparison.	49	data, the worse L<Storable> performs in comparison.
47		50
48	Regarding compactness, C<CBOR::XS>-encoded data structures are usually	51	Regarding compactness, C<CBOR::XS>-encoded data structures are usually
49	about 20% smaller than the same data encoded as (compact) JSON or	52	about 20% smaller than the same data encoded as (compact) JSON or
50	L<Storable>.	53	L<Storable>.
51		54
52	In addition to the core CBOR data format, this module implements a	55	In addition to the core CBOR data format, this module implements a
53	number of extensions, to support cyclic and shared data structures (see	56	number of extensions, to support cyclic and shared data structures
54	C<allow_sharing>), string deduplication (see C<pack_strings>) and scalar	57	(see C<allow_sharing> and C<allow_cycles>), string deduplication (see
55	references (always enabled).	58	C<pack_strings>) and scalar references (always enabled).
56
57	The primary goal of this module is to be I<correct> and the secondary goal
58	is to be I<fast>. To reach the latter goal it was written in C.
59		59
60	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
61	vice versa.	61	vice versa.
62		62
63	=cut	63	=cut
64		64
65	package CBOR::XS;	65	package CBOR::XS;
66		66
67	use common::sense;	67	use common::sense;
68		68
69	our $VERSION = '1.0';	69	our $VERSION = 1.86;
70	our @ISA = qw(Exporter);	70	our @ISA = qw(Exporter);
71		71
72	our @EXPORT = qw(encode_cbor decode_cbor);	72	our @EXPORT = qw(encode_cbor decode_cbor);
73		73
74	use Exporter;	74	use Exporter;
…		…
112		112
113	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
114	be chained:	114	be chained:
115		115
116	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	->validate_utf8
		127	->forbid_objects
		128	->filter (\&CBOR::XS::safe_filter)
		129	->max_size (1e8);
		130
		131	But is more future proof (it is better to crash because of a change than
		132	to be exploited in other ways).
		133
		134	=cut
		135
		136	sub new_safe {
		137	CBOR::XS
		138	->new
		139	->validate_utf8
		140	->forbid_objects
		141	->filter (\&CBOR::XS::safe_filter)
		142	->max_size (1e8)
		143	}
117		144
118	=item $cbor = $cbor->max_depth ([$maximum_nesting_depth])	145	=item $cbor = $cbor->max_depth ([$maximum_nesting_depth])
119		146
120	=item $max_depth = $cbor->get_max_depth	147	=item $max_depth = $cbor->get_max_depth
121		148
…		…
137		164
138	Note that nesting is implemented by recursion in C. The default value has	165	Note that nesting is implemented by recursion in C. The default value has
139	been chosen to be as large as typical operating systems allow without	166	been chosen to be as large as typical operating systems allow without
140	crashing.	167	crashing.
141		168
142	See SECURITY CONSIDERATIONS, below, for more info on why this is useful.	169	See L<SECURITY CONSIDERATIONS>, below, for more info on why this is useful.
143		170
144	=item $cbor = $cbor->max_size ([$maximum_string_size])	171	=item $cbor = $cbor->max_size ([$maximum_string_size])
145		172
146	=item $max_size = $cbor->get_max_size	173	=item $max_size = $cbor->get_max_size
147		174
…		…
152	effect on C<encode> (yet).	179	effect on C<encode> (yet).
153		180
154	If no argument is given, the limit check will be deactivated (same as when	181	If no argument is given, the limit check will be deactivated (same as when
155	C<0> is specified).	182	C<0> is specified).
156		183
157	See SECURITY CONSIDERATIONS, below, for more info on why this is useful.	184	See L<SECURITY CONSIDERATIONS>, below, for more info on why this is useful.
158		185
159	=item $cbor = $cbor->allow_unknown ([$enable])	186	=item $cbor = $cbor->allow_unknown ([$enable])
160		187
161	=item $enabled = $cbor->get_allow_unknown	188	=item $enabled = $cbor->get_allow_unknown
162		189
…		…
180	reference to the earlier value.	207	reference to the earlier value.
181		208
182	This means that such values will only be encoded once, and will not result	209	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	210	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	211	sharing extension. This also makes it possible to encode cyclic data
185	structures.	212	structures (which need C<allow_cycles> to be enabled to be decoded by this
		213	module).
186		214
187	It is recommended to leave it off unless you know your	215	It is recommended to leave it off unless you know your
188	communication partner supports the value sharing extensions to CBOR	216	communication partner supports the value sharing extensions to CBOR
189	(L<http://cbor.schmorp.de/value-sharing>), as without decoder support, the	217	(L<http://cbor.schmorp.de/value-sharing>), as without decoder support, the
190	resulting data structure might be unusable.	218	resulting data structure might be unusable.
191		219
192	Detecting shared values incurs a runtime overhead when values are encoded	220	Detecting shared values incurs a runtime overhead when values are encoded
193	that have a reference counter large than one, and might unnecessarily	221	that have a reference counter larger than one, and might unnecessarily
194	increase the encoded size, as potentially shared values are encode as	222	increase the encoded size, as potentially shared values are encoded as
195	sharable whether or not they are actually shared.	223	shareable whether or not they are actually shared.
196		224
197	At the moment, only targets of references can be shared (e.g. scalars,	225	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	226	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	227	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	228	not impossible to create in Perl, are not supported (this is the same as
…		…
205	structures cannot be encoded in this mode.	233	structures cannot be encoded in this mode.
206		234
207	This option does not affect C<decode> in any way - shared values and	235	This option does not affect C<decode> in any way - shared values and
208	references will always be decoded properly if present.	236	references will always be decoded properly if present.
209		237
		238	=item $cbor = $cbor->allow_cycles ([$enable])
		239
		240	=item $enabled = $cbor->get_allow_cycles
		241
		242	If C<$enable> is true (or missing), then C<decode> will happily decode
		243	self-referential (cyclic) data structures. By default these will not be
		244	decoded, as they need manual cleanup to avoid memory leaks, so code that
		245	isn't prepared for this will not leak memory.
		246
		247	If C<$enable> is false (the default), then C<decode> will throw an error
		248	when it encounters a self-referential/cyclic data structure.
		249
		250	FUTURE DIRECTION: the motivation behind this option is to avoid I<real>
		251	cycles - future versions of this module might chose to decode cyclic data
		252	structures using weak references when this option is off, instead of
		253	throwing an error.
		254
		255	This option does not affect C<encode> in any way - shared values and
		256	references will always be encoded properly if present.
		257
		258	=item $cbor = $cbor->forbid_objects ([$enable])
		259
		260	=item $enabled = $cbor->get_forbid_objects
		261
		262	Disables the use of the object serialiser protocol.
		263
		264	If C<$enable> is true (or missing), then C<encode> will will throw an
		265	exception when it encounters perl objects that would be encoded using the
		266	perl-object tag (26). When C<decode> encounters such tags, it will fall
		267	back to the general filter/tagged logic as if this were an unknown tag (by
		268	default resulting in a C<CBOR::XC::Tagged> object).
		269
		270	If C<$enable> is false (the default), then C<encode> will use the
		271	L<Types::Serialiser> object serialisation protocol to serialise objects
		272	into perl-object tags, and C<decode> will do the same to decode such tags.
		273
		274	See L<SECURITY CONSIDERATIONS>, below, for more info on why forbidding this
		275	protocol can be useful.
		276
210	=item $cbor = $cbor->pack_strings ([$enable])	277	=item $cbor = $cbor->pack_strings ([$enable])
211		278
212	=item $enabled = $cbor->get_pack_strings	279	=item $enabled = $cbor->get_pack_strings
213		280
214	If C<$enable> is true (or missing), then C<encode> will try not to encode	281	If C<$enable> is true (or missing), then C<encode> will try not to encode
…		…
226	the standard CBOR way.	293	the standard CBOR way.
227		294
228	This option does not affect C<decode> in any way - string references will	295	This option does not affect C<decode> in any way - string references will
229	always be decoded properly if present.	296	always be decoded properly if present.
230		297
		298	=item $cbor = $cbor->text_keys ([$enable])
		299
		300	=item $enabled = $cbor->get_text_keys
		301
		302	If C<$enabled> is true (or missing), then C<encode> will encode all
		303	perl hash keys as CBOR text strings/UTF-8 string, upgrading them as needed.
		304
		305	If C<$enable> is false (the default), then C<encode> will encode hash keys
		306	normally - upgraded perl strings (strings internally encoded as UTF-8) as
		307	CBOR text strings, and downgraded perl strings as CBOR byte strings.
		308
		309	This option does not affect C<decode> in any way.
		310
		311	This option is useful for interoperability with CBOR decoders that don't
		312	treat byte strings as a form of text. It is especially useful as Perl
		313	gives very little control over hash keys.
		314
		315	Enabling this option can be slow, as all downgraded hash keys that are
		316	encoded need to be scanned and converted to UTF-8.
		317
		318	=item $cbor = $cbor->text_strings ([$enable])
		319
		320	=item $enabled = $cbor->get_text_strings
		321
		322	This option works similar to C<text_keys>, above, but works on all strings
		323	(including hash keys), so C<text_keys> has no further effect after
		324	enabling C<text_strings>.
		325
		326	If C<$enabled> is true (or missing), then C<encode> will encode all perl
		327	strings as CBOR text strings/UTF-8 strings, upgrading them as needed.
		328
		329	If C<$enable> is false (the default), then C<encode> will encode strings
		330	normally (but see C<text_keys>) - upgraded perl strings (strings
		331	internally encoded as UTF-8) as CBOR text strings, and downgraded perl
		332	strings as CBOR byte strings.
		333
		334	This option does not affect C<decode> in any way.
		335
		336	This option has similar advantages and disadvantages as C<text_keys>. In
		337	addition, this option effectively removes the ability to automatically
		338	encode byte strings, which might break some C<FREEZE> and C<TO_CBOR>
		339	methods that rely on this.
		340
		341	A workaround is to use explicit type casts, which are unaffected by this option.
		342
		343	=item $cbor = $cbor->validate_utf8 ([$enable])
		344
		345	=item $enabled = $cbor->get_validate_utf8
		346
		347	If C<$enable> is true (or missing), then C<decode> will validate that
		348	elements (text strings) containing UTF-8 data in fact contain valid UTF-8
		349	data (instead of blindly accepting it). This validation obviously takes
		350	extra time during decoding.
		351
		352	The concept of "valid UTF-8" used is perl's concept, which is a superset
		353	of the official UTF-8.
		354
		355	If C<$enable> is false (the default), then C<decode> will blindly accept
		356	UTF-8 data, marking them as valid UTF-8 in the resulting data structure
		357	regardless of whether that's true or not.
		358
		359	Perl isn't too happy about corrupted UTF-8 in strings, but should
		360	generally not crash or do similarly evil things. Extensions might be not
		361	so forgiving, so it's recommended to turn on this setting if you receive
		362	untrusted CBOR.
		363
		364	This option does not affect C<encode> in any way - strings that are
		365	supposedly valid UTF-8 will simply be dumped into the resulting CBOR
		366	string without checking whether that is, in fact, true or not.
		367
231	=item $cbor = $cbor->filter ([$cb->($tag, $value)])	368	=item $cbor = $cbor->filter ([$cb->($tag, $value)])
232		369
233	=item $cb_or_undef = $cbor->get_filter	370	=item $cb_or_undef = $cbor->get_filter
234		371
235	Sets or replaces the tagged value decoding filter (when C<$cb> is	372	Sets or replaces the tagged value decoding filter (when C<$cb> is
…		…
247	replace the tagged value in the decoded data structure, or no values,	384	replace the tagged value in the decoded data structure, or no values,
248	which will result in default handling, which currently means the decoder	385	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.	386	creates a C<CBOR::XS::Tagged> object to hold the tag and the value.
250		387
251	When the filter is cleared (the default state), the default filter	388	When the filter is cleared (the default state), the default filter
252	function, C<CBOR::XS::default_filter>, is used. This function simply looks	389	function, C<CBOR::XS::default_filter>, is used. This function simply
253	up the tag in the C<%CBOR::XS::FILTER> hash. If an entry exists it must be	390	looks up the tag in the C<%CBOR::XS::FILTER> hash. If an entry exists
254	a code reference that is called with tag and value, and is responsible for	391	it must be a code reference that is called with tag and value, and is
255	decoding the value. If no entry exists, it returns no values.	392	responsible for decoding the value. If no entry exists, it returns no
		393	values. C<CBOR::XS> provides a number of default filter functions already,
		394	the the C<%CBOR::XS::FILTER> hash can be freely extended with more.
		395
		396	C<CBOR::XS> additionally provides an alternative filter function that is
		397	supposed to be safe to use with untrusted data (which the default filter
		398	might not), called C<CBOR::XS::safe_filter>, which works the same as
		399	the C<default_filter> but uses the C<%CBOR::XS::SAFE_FILTER> variable
		400	instead. It is prepopulated with the tag decoding functions that are
		401	deemed safe (basically the same as C<%CBOR::XS::FILTER> without all
		402	the bignum tags), and can be extended by user code as wlel, although,
		403	obviously, one should be very careful about adding decoding functions
		404	here, since the expectation is that they are safe to use on untrusted
		405	data, after all.
256		406
257	Example: decode all tags not handled internally into C<CBOR::XS::Tagged>	407	Example: decode all tags not handled internally into C<CBOR::XS::Tagged>
258	objects, with no other special handling (useful when working with	408	objects, with no other special handling (useful when working with
259	potentially "unsafe" CBOR data).	409	potentially "unsafe" CBOR data).
260		410
…		…
267	my ($tag, $value);	417	my ($tag, $value);
268		418
269	"tag 1347375694 value $value"	419	"tag 1347375694 value $value"
270	};	420	};
271		421
		422	Example: provide your own filter function that looks up tags in your own
		423	hash:
		424
		425	my %my_filter = (
		426	998347484 => sub {
		427	my ($tag, $value);
		428
		429	"tag 998347484 value $value"
		430	};
		431	);
		432
		433	my $coder = CBOR::XS->new->filter (sub {
		434	&{ $my_filter{$_[0]} or return }
		435	});
		436
		437
		438	Example: use the safe filter function (see L<SECURITY CONSIDERATIONS> for
		439	more considerations on security).
		440
		441	CBOR::XS->new->filter (\&CBOR::XS::safe_filter)->decode ($cbor_data);
		442
272	=item $cbor_data = $cbor->encode ($perl_scalar)	443	=item $cbor_data = $cbor->encode ($perl_scalar)
273		444
274	Converts the given Perl data structure (a scalar value) to its CBOR	445	Converts the given Perl data structure (a scalar value) to its CBOR
275	representation.	446	representation.
276		447
…		…
285	when there is trailing garbage after the CBOR string, it will silently	456	when there is trailing garbage after the CBOR string, it will silently
286	stop parsing there and return the number of characters consumed so far.	457	stop parsing there and return the number of characters consumed so far.
287		458
288	This is useful if your CBOR texts are not delimited by an outer protocol	459	This is useful if your CBOR texts are not delimited by an outer protocol
289	and you need to know where the first CBOR string ends amd the next one	460	and you need to know where the first CBOR string ends amd the next one
290	starts.	461	starts - CBOR strings are self-delimited, so it is possible to concatenate
		462	CBOR strings without any delimiters or size fields and recover their data.
291		463
292	CBOR::XS->new->decode_prefix ("......")	464	CBOR::XS->new->decode_prefix ("......")
293	=> ("...", 3)	465	=> ("...", 3)
		466
		467	=back
		468
		469	=head2 INCREMENTAL PARSING
		470
		471	In some cases, there is the need for incremental parsing of JSON
		472	texts. While this module always has to keep both CBOR text and resulting
		473	Perl data structure in memory at one time, it does allow you to parse a
		474	CBOR stream incrementally, using a similar to using "decode_prefix" to see
		475	if a full CBOR object is available, but is much more efficient.
		476
		477	It basically works by parsing as much of a CBOR string as possible - if
		478	the CBOR data is not complete yet, the parser will remember where it was,
		479	to be able to restart when more data has been accumulated. Once enough
		480	data is available to either decode a complete CBOR value or raise an
		481	error, a real decode will be attempted.
		482
		483	A typical use case would be a network protocol that consists of sending
		484	and receiving CBOR-encoded messages. The solution that works with CBOR and
		485	about anything else is by prepending a length to every CBOR value, so the
		486	receiver knows how many octets to read. More compact (and slightly slower)
		487	would be to just send CBOR values back-to-back, as C<CBOR::XS> knows where
		488	a CBOR value ends, and doesn't need an explicit length.
		489
		490	The following methods help with this:
		491
		492	=over 4
		493
		494	=item @decoded = $cbor->incr_parse ($buffer)
		495
		496	This method attempts to decode exactly one CBOR value from the beginning
		497	of the given C<$buffer>. The value is removed from the C<$buffer> on
		498	success. When C<$buffer> doesn't contain a complete value yet, it returns
		499	nothing. Finally, when the C<$buffer> doesn't start with something
		500	that could ever be a valid CBOR value, it raises an exception, just as
		501	C<decode> would. In the latter case the decoder state is undefined and
		502	must be reset before being able to parse further.
		503
		504	This method modifies the C<$buffer> in place. When no CBOR value can be
		505	decoded, the decoder stores the current string offset. On the next call,
		506	continues decoding at the place where it stopped before. For this to make
		507	sense, the C<$buffer> must begin with the same octets as on previous
		508	unsuccessful calls.
		509
		510	You can call this method in scalar context, in which case it either
		511	returns a decoded value or C<undef>. This makes it impossible to
		512	distinguish between CBOR null values (which decode to C<undef>) and an
		513	unsuccessful decode, which is often acceptable.
		514
		515	=item @decoded = $cbor->incr_parse_multiple ($buffer)
		516
		517	Same as C<incr_parse>, but attempts to decode as many CBOR values as
		518	possible in one go, instead of at most one. Calls to C<incr_parse> and
		519	C<incr_parse_multiple> can be interleaved.
		520
		521	=item $cbor->incr_reset
		522
		523	Resets the incremental decoder. This throws away any saved state, so that
		524	subsequent calls to C<incr_parse> or C<incr_parse_multiple> start to parse
		525	a new CBOR value from the beginning of the C<$buffer> again.
		526
		527	This method can be called at any time, but it I<must> be called if you want
		528	to change your C<$buffer> or there was a decoding error and you want to
		529	reuse the C<$cbor> object for future incremental parsings.
294		530
295	=back	531	=back
296		532
297		533
298	=head1 MAPPING	534	=head1 MAPPING
…		…
371		607
372	=item hash references	608	=item hash references
373		609
374	Perl hash references become CBOR maps. As there is no inherent ordering in	610	Perl hash references become CBOR maps. As there is no inherent ordering in
375	hash keys (or CBOR maps), they will usually be encoded in a pseudo-random	611	hash keys (or CBOR maps), they will usually be encoded in a pseudo-random
376	order. This order can be different each time a hahs is encoded.	612	order. This order can be different each time a hash is encoded.
377		613
378	Currently, tied hashes will use the indefinite-length format, while normal	614	Currently, tied hashes will use the indefinite-length format, while normal
379	hashes will use the fixed-length format.	615	hashes will use the fixed-length format.
380		616
381	=item array references	617	=item array references
…		…
399	create such objects.	635	create such objects.
400		636
401	=item Types::Serialiser::true, Types::Serialiser::false, Types::Serialiser::error	637	=item Types::Serialiser::true, Types::Serialiser::false, Types::Serialiser::error
402		638
403	These special values become CBOR true, CBOR false and CBOR undefined	639	These special values become CBOR true, CBOR false and CBOR undefined
404	values, respectively. You can also use C<\1>, C<\0> and C<\undef> directly	640	values, respectively.
405	if you want.
406		641
407	=item other blessed objects	642	=item other blessed objects
408		643
409	Other blessed objects are serialised via C<TO_CBOR> or C<FREEZE>. See	644	Other blessed objects are serialised via C<TO_CBOR> or C<FREEZE>. See
410	L<TAG HANDLING AND EXTENSIONS> for specific classes handled by this	645	L<TAG HANDLING AND EXTENSIONS> for specific classes handled by this
…		…
434	my $x = 3.1; # some variable containing a number	669	my $x = 3.1; # some variable containing a number
435	"$x"; # stringified	670	"$x"; # stringified
436	$x .= ""; # another, more awkward way to stringify	671	$x .= ""; # another, more awkward way to stringify
437	print $x; # perl does it for you, too, quite often	672	print $x; # perl does it for you, too, quite often
438		673
439	You can force whether a string ie encoded as byte or text string by using	674	You can force whether a string is encoded as byte or text string by using
440	C<utf8::upgrade> and C<utf8::downgrade>):	675	C<utf8::upgrade> and C<utf8::downgrade> (if C<text_strings> is disabled).
441		676
442	utf8::upgrade $x; # encode $x as text string	677	utf8::upgrade $x; # encode $x as text string
443	utf8::downgrade $x; # encode $x as byte string	678	utf8::downgrade $x; # encode $x as byte string
444		679
		680	More options are available, see L<TYPE CASTS>, below, and the C<text_keys>
		681	and C<text_strings> options.
		682
445	Perl doesn't define what operations up- and downgrade strings, so if the	683	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	684	difference between byte and text is important, you should up- or downgrade
447	your string as late as possible before encoding.	685	your string as late as possible before encoding. You can also force the
		686	use of CBOR text strings by using C<text_keys> or C<text_strings>.
448		687
449	You can force the type to be a CBOR number by numifying it:	688	You can force the type to be a CBOR number by numifying it:
450		689
451	my $x = "3"; # some variable containing a string	690	my $x = "3"; # some variable containing a string
452	$x += 0; # numify it, ensuring it will be dumped as a number	691	$x += 0; # numify it, ensuring it will be dumped as a number
…		…
463	represent numerical values are supported, but might suffer loss of	702	represent numerical values are supported, but might suffer loss of
464	precision.	703	precision.
465		704
466	=back	705	=back
467		706
		707	=head2 TYPE CASTS
		708
		709	B<EXPERIMENTAL>: As an experimental extension, C<CBOR::XS> allows you to
		710	force specific CBOR types to be used when encoding. That allows you to
		711	encode types not normally accessible (e.g. half floats) as well as force
		712	string types even when C<text_strings> is in effect.
		713
		714	Type forcing is done by calling a special "cast" function which keeps a
		715	copy of the value and returns a new value that can be handed over to any
		716	CBOR encoder function.
		717
		718	The following casts are currently available (all of which are unary
		719	operators, that is, have a prototype of C<$>):
		720
		721	=over
		722
		723	=item CBOR::XS::as_int $value
		724
		725	Forces the value to be encoded as some form of (basic, not bignum) integer
		726	type.
		727
		728	=item CBOR::XS::as_text $value
		729
		730	Forces the value to be encoded as (UTF-8) text values.
		731
		732	=item CBOR::XS::as_bytes $value
		733
		734	Forces the value to be encoded as a (binary) string value.
		735
		736	Example: encode a perl string as binary even though C<text_strings> is in
		737	effect.
		738
		739	CBOR::XS->new->text_strings->encode ([4, "text", CBOR::XS::bytes "bytevalue"]);
		740
		741	=item CBOR::XS::as_bool $value
		742
		743	Converts a Perl boolean (which can be any kind of scalar) into a CBOR
		744	boolean. Strictly the same, but shorter to write, than:
		745
		746	$value ? Types::Serialiser::true : Types::Serialiser::false
		747
		748	=item CBOR::XS::as_float16 $value
		749
		750	Forces half-float (IEEE 754 binary16) encoding of the given value.
		751
		752	=item CBOR::XS::as_float32 $value
		753
		754	Forces single-float (IEEE 754 binary32) encoding of the given value.
		755
		756	=item CBOR::XS::as_float64 $value
		757
		758	Forces double-float (IEEE 754 binary64) encoding of the given value.
		759
		760	=item CBOR::XS::as_cbor $cbor_text
		761
		762	Not a type cast per-se, this type cast forces the argument to be encoded
		763	as-is. This can be used to embed pre-encoded CBOR data.
		764
		765	Note that no checking on the validity of the C<$cbor_text> is done - it's
		766	the callers responsibility to correctly encode values.
		767
		768	=item CBOR::XS::as_map [key => value...]
		769
		770	Treat the array reference as key value pairs and output a CBOR map. This
		771	allows you to generate CBOR maps with arbitrary key types (or, if you
		772	don't care about semantics, duplicate keys or pairs in a custom order),
		773	which is otherwise hard to do with Perl.
		774
		775	The single argument must be an array reference with an even number of
		776	elements.
		777
		778	Note that only the reference to the array is copied, the array itself is
		779	not. Modifications done to the array before calling an encoding function
		780	will be reflected in the encoded output.
		781
		782	Example: encode a CBOR map with a string and an integer as keys.
		783
		784	encode_cbor CBOR::XS::as_map [string => "value", 5 => "value"]
		785
		786	=back
		787
		788	=cut
		789
		790	sub CBOR::XS::as_cbor ($) { bless [$_[0], 0, undef], CBOR::XS::Tagged:: }
		791	sub CBOR::XS::as_int ($) { bless [$_[0], 1, undef], CBOR::XS::Tagged:: }
		792	sub CBOR::XS::as_bytes ($) { bless [$_[0], 2, undef], CBOR::XS::Tagged:: }
		793	sub CBOR::XS::as_text ($) { bless [$_[0], 3, undef], CBOR::XS::Tagged:: }
		794	sub CBOR::XS::as_float16 ($) { bless [$_[0], 4, undef], CBOR::XS::Tagged:: }
		795	sub CBOR::XS::as_float32 ($) { bless [$_[0], 5, undef], CBOR::XS::Tagged:: }
		796	sub CBOR::XS::as_float64 ($) { bless [$_[0], 6, undef], CBOR::XS::Tagged:: }
		797
		798	sub CBOR::XS::as_bool ($) { $_[0] ? $Types::Serialiser::true : $Types::Serialiser::false }
		799
		800	sub CBOR::XS::as_map ($) {
		801	ARRAY:: eq ref $_[0]
		802	and $#{ $_[0] } & 1
		803	or do { require Carp; Carp::croak ("CBOR::XS::as_map only acepts array references with an even number of elements, caught") };
		804
		805	bless [$_[0], 7, undef], CBOR::XS::Tagged::
		806	}
		807
468	=head2 OBJECT SERIALISATION	808	=head2 OBJECT SERIALISATION
469		809
470	This module implements both a CBOR-specific and the generic	810	This module implements both a CBOR-specific and the generic
471	L<Types::Serialier> object serialisation protocol. The following	811	L<Types::Serialier> object serialisation protocol. The following
472	subsections explain both methods.	812	subsections explain both methods.
…		…
553	"$self" # encode url string	893	"$self" # encode url string
554	}	894	}
555		895
556	sub URI::THAW {	896	sub URI::THAW {
557	my ($class, $serialiser, $uri) = @_;	897	my ($class, $serialiser, $uri) = @_;
558
559	$class->new ($uri)	898	$class->new ($uri)
560	}	899	}
561		900
562	Unlike C<TO_CBOR>, multiple values can be returned by C<FREEZE>. For	901	Unlike C<TO_CBOR>, multiple values can be returned by C<FREEZE>. For
563	example, a C<FREEZE> method that returns "type", "id" and "variant" values	902	example, a C<FREEZE> method that returns "type", "id" and "variant" values
…		…
694	additional tags (such as base64url).	1033	additional tags (such as base64url).
695		1034
696	=head2 ENFORCED TAGS	1035	=head2 ENFORCED TAGS
697		1036
698	These tags are always handled when decoding, and their handling cannot be	1037	These tags are always handled when decoding, and their handling cannot be
699	overriden by the user.	1038	overridden by the user.
700		1039
701	=over 4	1040	=over 4
702		1041
703	=item 26 (perl-object, L<http://cbor.schmorp.de/perl-object>)	1042	=item 26 (perl-object, L<http://cbor.schmorp.de/perl-object>)
704		1043
705	These tags are automatically created (and decoded) for serialisable	1044	These tags are automatically created (and decoded) for serialisable
706	objects using the C<FREEZE/THAW> methods (the L<Types::Serialier> object	1045	objects using the C<FREEZE/THAW> methods (the L<Types::Serialier> object
707	serialisation protocol). See L<OBJECT SERIALISATION> for details.	1046	serialisation protocol). See L<OBJECT SERIALISATION> for details.
708		1047
709	=item 28, 29 (sharable, sharedref, L <http://cbor.schmorp.de/value-sharing>)	1048	=item 28, 29 (shareable, sharedref, L<http://cbor.schmorp.de/value-sharing>)
710		1049
711	These tags are automatically decoded when encountered, resulting in	1050	These tags are automatically decoded when encountered (and they do not
		1051	result in a cyclic data structure, see C<allow_cycles>), resulting in
712	shared values in the decoded object. They are only encoded, however, when	1052	shared values in the decoded object. They are only encoded, however, when
713	C<allow_sharable> is enabled.	1053	C<allow_sharing> is enabled.
714		1054
		1055	Not all shared values can be successfully decoded: values that reference
		1056	themselves will I<currently> decode as C<undef> (this is not the same
		1057	as a reference pointing to itself, which will be represented as a value
		1058	that contains an indirect reference to itself - these will be decoded
		1059	properly).
		1060
		1061	Note that considerably more shared value data structures can be decoded
		1062	than will be encoded - currently, only values pointed to by references
		1063	will be shared, others will not. While non-reference shared values can be
		1064	generated in Perl with some effort, they were considered too unimportant
		1065	to be supported in the encoder. The decoder, however, will decode these
		1066	values as shared values.
		1067
715	=item 256, 25 (stringref-namespace, stringref, L <http://cbor.schmorp.de/stringref>)	1068	=item 256, 25 (stringref-namespace, stringref, L<http://cbor.schmorp.de/stringref>)
716		1069
717	These tags are automatically decoded when encountered. They are only	1070	These tags are automatically decoded when encountered. They are only
718	encoded, however, when C<pack_strings> is enabled.	1071	encoded, however, when C<pack_strings> is enabled.
719		1072
720	=item 22098 (indirection, L<http://cbor.schmorp.de/indirection>)	1073	=item 22098 (indirection, L<http://cbor.schmorp.de/indirection>)
721		1074
722	This tag is automatically generated when a reference are encountered (with	1075	This tag is automatically generated when a reference are encountered (with
723	the exception of hash and array refernces). It is converted to a reference	1076	the exception of hash and array references). It is converted to a reference
724	when decoding.	1077	when decoding.
725		1078
726	=item 55799 (self-describe CBOR, RFC 7049)	1079	=item 55799 (self-describe CBOR, RFC 7049)
727		1080
728	This value is not generated on encoding (unless explicitly requested by	1081	This value is not generated on encoding (unless explicitly requested by
…		…
731	=back	1084	=back
732		1085
733	=head2 NON-ENFORCED TAGS	1086	=head2 NON-ENFORCED TAGS
734		1087
735	These tags have default filters provided when decoding. Their handling can	1088	These tags have default filters provided when decoding. Their handling can
736	be overriden by changing the C<%CBOR::XS::FILTER> entry for the tag, or by	1089	be overridden by changing the C<%CBOR::XS::FILTER> entry for the tag, or by
737	providing a custom C<filter> callback when decoding.	1090	providing a custom C<filter> callback when decoding.
738		1091
739	When they result in decoding into a specific Perl class, the module	1092	When they result in decoding into a specific Perl class, the module
740	usually provides a corresponding C<TO_CBOR> method as well.	1093	usually provides a corresponding C<TO_CBOR> method as well.
741		1094
…		…
744	provide these modules. The decoding usually fails with an exception if the	1097	provide these modules. The decoding usually fails with an exception if the
745	required module cannot be loaded.	1098	required module cannot be loaded.
746		1099
747	=over 4	1100	=over 4
748		1101
		1102	=item 0, 1 (date/time string, seconds since the epoch)
		1103
		1104	These tags are decoded into L<Time::Piece> objects. The corresponding
		1105	C<Time::Piece::TO_CBOR> method always encodes into tag 1 values currently.
		1106
		1107	The L<Time::Piece> API is generally surprisingly bad, and fractional
		1108	seconds are only accidentally kept intact, so watch out. On the plus side,
		1109	the module comes with perl since 5.10, which has to count for something.
		1110
749	=item 2, 3 (positive/negative bignum)	1111	=item 2, 3 (positive/negative bignum)
750		1112
751	These tags are decoded into L<Math::BigInt> objects. The corresponding	1113	These tags are decoded into L<Math::BigInt> objects. The corresponding
752	C<Math::BigInt::TO_CBOR> method encodes "small" bigints into normal CBOR	1114	C<Math::BigInt::TO_CBOR> method encodes "small" bigints into normal CBOR
753	integers, and others into positive/negative CBOR bignums.	1115	integers, and others into positive/negative CBOR bignums.
754		1116
755	=item 4, 5 (decimal fraction/bigfloat)	1117	=item 4, 5, 264, 265 (decimal fraction/bigfloat)
756		1118
757	Both decimal fractions and bigfloats are decoded into L<Math::BigFloat>	1119	Both decimal fractions and bigfloats are decoded into L<Math::BigFloat>
758	objects. The corresponding C<Math::BigFloat::TO_CBOR> method I<always>	1120	objects. The corresponding C<Math::BigFloat::TO_CBOR> method I<always>
759	encodes into a decimal fraction.	1121	encodes into a decimal fraction (either tag 4 or 264).
760		1122
761	CBOR cannot represent bigfloats with I<very> large exponents - conversion	1123	NaN and infinities are not encoded properly, as they cannot be represented
762	of such big float objects is undefined.	1124	in CBOR.
763		1125
764	Also, NaN and infinities are not encoded properly.	1126	See L<BIGNUM SECURITY CONSIDERATIONS> for more info.
		1127
		1128	=item 30 (rational numbers)
		1129
		1130	These tags are decoded into L<Math::BigRat> objects. The corresponding
		1131	C<Math::BigRat::TO_CBOR> method encodes rational numbers with denominator
		1132	C<1> via their numerator only, i.e., they become normal integers or
		1133	C<bignums>.
		1134
		1135	See L<BIGNUM SECURITY CONSIDERATIONS> for more info.
765		1136
766	=item 21, 22, 23 (expected later JSON conversion)	1137	=item 21, 22, 23 (expected later JSON conversion)
767		1138
768	CBOR::XS is not a CBOR-to-JSON converter, and will simply ignore these	1139	CBOR::XS is not a CBOR-to-JSON converter, and will simply ignore these
769	tags.	1140	tags.
…		…
774	C<URI::TO_CBOR> method again results in a CBOR URI value.	1145	C<URI::TO_CBOR> method again results in a CBOR URI value.
775		1146
776	=back	1147	=back
777		1148
778	=cut	1149	=cut
779
780	our %FILTER = (
781	# 0 # rfc4287 datetime, utf-8
782	# 1 # unix timestamp, any
783
784	2 => sub { # pos bigint
785	require Math::BigInt;
786	Math::BigInt->new ("0x" . unpack "H*", pop)
787	},
788
789	3 => sub { # neg bigint
790	require Math::BigInt;
791	-Math::BigInt->new ("0x" . unpack "H*", pop)
792	},
793
794	4 => sub { # decimal fraction, array
795	require Math::BigFloat;
796	Math::BigFloat->new ($_[1][1] . "E" . $_[1][0])
797	},
798
799	5 => sub { # bigfloat, array
800	require Math::BigFloat;
801	scalar Math::BigFloat->new ($_[1][1])->blsft ($_[1][0], 2)
802	},
803
804	21 => sub { pop }, # expected conversion to base64url encoding
805	22 => sub { pop }, # expected conversion to base64 encoding
806	23 => sub { pop }, # expected conversion to base16 encoding
807
808	# 24 # embedded cbor, byte string
809
810	32 => sub {
811	require URI;
812	URI->new (pop)
813	},
814
815	# 33 # base64url rfc4648, utf-8
816	# 34 # base64 rfc46484, utf-8
817	# 35 # regex pcre/ecma262, utf-8
818	# 36 # mime message rfc2045, utf-8
819	);
820
821		1150
822	=head1 CBOR and JSON	1151	=head1 CBOR and JSON
823		1152
824	CBOR is supposed to implement a superset of the JSON data model, and is,	1153	CBOR is supposed to implement a superset of the JSON data model, and is,
825	with some coercion, able to represent all JSON texts (something that other	1154	with some coercion, able to represent all JSON texts (something that other
…		…
834	CBOR intact.	1163	CBOR intact.
835		1164
836		1165
837	=head1 SECURITY CONSIDERATIONS	1166	=head1 SECURITY CONSIDERATIONS
838		1167
839	When you are using CBOR in a protocol, talking to untrusted potentially	1168	Tl;dr... if you want to decode or encode CBOR from untrusted sources, you
840	hostile creatures requires relatively few measures.	1169	should start with a coder object created via C<new_safe> (which implements
		1170	the mitigations explained below):
841		1171
		1172	my $coder = CBOR::XS->new_safe;
		1173
		1174	my $data = $coder->decode ($cbor_text);
		1175	my $cbor = $coder->encode ($data);
		1176
		1177	Longer version: When you are using CBOR in a protocol, talking to
		1178	untrusted potentially hostile creatures requires some thought:
		1179
		1180	=over 4
		1181
		1182	=item Security of the CBOR decoder itself
		1183
842	First of all, your CBOR decoder should be secure, that is, should not have	1184	First and foremost, your CBOR decoder should be secure, that is, should
		1185	not have any buffer overflows or similar bugs that could potentially be
843	any buffer overflows. Obviously, this module should ensure that and I am	1186	exploited. Obviously, this module should ensure that and I am trying hard
844	trying hard on making that true, but you never know.	1187	on making that true, but you never know.
845		1188
		1189	=item CBOR::XS can invoke almost arbitrary callbacks during decoding
		1190
		1191	CBOR::XS supports object serialisation - decoding CBOR can cause calls
		1192	to I<any> C<THAW> method in I<any> package that exists in your process
		1193	(that is, CBOR::XS will not try to load modules, but any existing C<THAW>
		1194	method or function can be called, so they all have to be secure).
		1195
		1196	Less obviously, it will also invoke C<TO_CBOR> and C<FREEZE> methods -
		1197	even if all your C<THAW> methods are secure, encoding data structures from
		1198	untrusted sources can invoke those and trigger bugs in those.
		1199
		1200	So, if you are not sure about the security of all the modules you
		1201	have loaded (you shouldn't), you should disable this part using
		1202	C<forbid_objects> or using C<new_safe>.
		1203
		1204	=item CBOR can be extended with tags that call library code
		1205
		1206	CBOR can be extended with tags, and C<CBOR::XS> has a registry of
		1207	conversion functions for many existing tags that can be extended via
		1208	third-party modules (see the C<filter> method).
		1209
		1210	If you don't trust these, you should configure the "safe" filter function,
		1211	C<CBOR::XS::safe_filter> (C<new_safe> does this), which by default only
		1212	includes conversion functions that are considered "safe" by the author
		1213	(but again, they can be extended by third party modules).
		1214
		1215	Depending on your level of paranoia, you can use the "safe" filter:
		1216
		1217	$cbor->filter (\&CBOR::XS::safe_filter);
		1218
		1219	... your own filter...
		1220
		1221	$cbor->filter (sub { ... do your stuffs here ... });
		1222
		1223	... or even no filter at all, disabling all tag decoding:
		1224
		1225	$cbor->filter (sub { });
		1226
		1227	This is never a problem for encoding, as the tag mechanism only exists in
		1228	CBOR texts.
		1229
		1230	=item Resource-starving attacks: object memory usage
		1231
846	Second, you need to avoid resource-starving attacks. That means you should	1232	You need to avoid resource-starving attacks. That means you should limit
847	limit the size of CBOR data you accept, or make sure then when your	1233	the size of CBOR data you accept, or make sure then when your resources
848	resources run out, that's just fine (e.g. by using a separate process that	1234	run out, that's just fine (e.g. by using a separate process that can
849	can crash safely). The size of a CBOR string in octets is usually a good	1235	crash safely). The size of a CBOR string in octets is usually a good
850	indication of the size of the resources required to decode it into a Perl	1236	indication of the size of the resources required to decode it into a Perl
851	structure. While CBOR::XS can check the size of the CBOR text, it might be	1237	structure. While CBOR::XS can check the size of the CBOR text (using
852	too late when you already have it in memory, so you might want to check	1238	C<max_size> - done by C<new_safe>), it might be too late when you already
853	the size before you accept the string.	1239	have it in memory, so you might want to check the size before you accept
		1240	the string.
854		1241
		1242	As for encoding, it is possible to construct data structures that are
		1243	relatively small but result in large CBOR texts (for example by having an
		1244	array full of references to the same big data structure, which will all be
		1245	deep-cloned during encoding by default). This is rarely an actual issue
		1246	(and the worst case is still just running out of memory), but you can
		1247	reduce this risk by using C<allow_sharing>.
		1248
		1249	=item Resource-starving attacks: stack overflows
		1250
855	Third, CBOR::XS recurses using the C stack when decoding objects and	1251	CBOR::XS recurses using the C stack when decoding objects and arrays. The
856	arrays. The C stack is a limited resource: for instance, on my amd64	1252	C stack is a limited resource: for instance, on my amd64 machine with 8MB
857	machine with 8MB of stack size I can decode around 180k nested arrays but	1253	of stack size I can decode around 180k nested arrays but only 14k nested
858	only 14k nested CBOR objects (due to perl itself recursing deeply on croak	1254	CBOR objects (due to perl itself recursing deeply on croak to free the
859	to free the temporary). If that is exceeded, the program crashes. To be	1255	temporary). If that is exceeded, the program crashes. To be conservative,
860	conservative, the default nesting limit is set to 512. If your process	1256	the default nesting limit is set to 512. If your process has a smaller
861	has a smaller stack, you should adjust this setting accordingly with the	1257	stack, you should adjust this setting accordingly with the C<max_depth>
862	C<max_depth> method.	1258	method.
		1259
		1260	=item Resource-starving attacks: CPU en-/decoding complexity
		1261
		1262	CBOR::XS will use the L<Math::BigInt>, L<Math::BigFloat> and
		1263	L<Math::BigRat> libraries to represent encode/decode bignums. These can be
		1264	very slow (as in, centuries of CPU time) and can even crash your program
		1265	(and are generally not very trustworthy). See the next section on bignum
		1266	security for details.
		1267
		1268	=item Data breaches: leaking information in error messages
		1269
		1270	CBOR::XS might leak contents of your Perl data structures in its error
		1271	messages, so when you serialise sensitive information you might want to
		1272	make sure that exceptions thrown by CBOR::XS will not end up in front of
		1273	untrusted eyes.
		1274
		1275	=item Something else...
863		1276
864	Something else could bomb you, too, that I forgot to think of. In that	1277	Something else could bomb you, too, that I forgot to think of. In that
865	case, you get to keep the pieces. I am always open for hints, though...	1278	case, you get to keep the pieces. I am always open for hints, though...
866		1279
867	Also keep in mind that CBOR::XS might leak contents of your Perl data	1280	=back
868	structures in its error messages, so when you serialise sensitive	1281
869	information you might want to make sure that exceptions thrown by CBOR::XS	1282
870	will not end up in front of untrusted eyes.	1283	=head1 BIGNUM SECURITY CONSIDERATIONS
		1284
		1285	CBOR::XS provides a C<TO_CBOR> method for both L<Math::BigInt> and
		1286	L<Math::BigFloat> that tries to encode the number in the simplest possible
		1287	way, that is, either a CBOR integer, a CBOR bigint/decimal fraction (tag
		1288	4) or an arbitrary-exponent decimal fraction (tag 264). Rational numbers
		1289	(L<Math::BigRat>, tag 30) can also contain bignums as members.
		1290
		1291	CBOR::XS will also understand base-2 bigfloat or arbitrary-exponent
		1292	bigfloats (tags 5 and 265), but it will never generate these on its own.
		1293
		1294	Using the built-in L<Math::BigInt::Calc> support, encoding and decoding
		1295	decimal fractions is generally fast. Decoding bigints can be slow for very
		1296	big numbers (tens of thousands of digits, something that could potentially
		1297	be caught by limiting the size of CBOR texts), and decoding bigfloats or
		1298	arbitrary-exponent bigfloats can be I<extremely> slow (minutes, decades)
		1299	for large exponents (roughly 40 bit and longer).
		1300
		1301	Additionally, L<Math::BigInt> can take advantage of other bignum
		1302	libraries, such as L<Math::GMP>, which cannot handle big floats with large
		1303	exponents, and might simply abort or crash your program, due to their code
		1304	quality.
		1305
		1306	This can be a concern if you want to parse untrusted CBOR. If it is, you
		1307	might want to disable decoding of tag 2 (bigint) and 3 (negative bigint)
		1308	types. You should also disable types 5 and 265, as these can be slow even
		1309	without bigints.
		1310
		1311	Disabling bigints will also partially or fully disable types that rely on
		1312	them, e.g. rational numbers that use bignums.
		1313
871		1314
872	=head1 CBOR IMPLEMENTATION NOTES	1315	=head1 CBOR IMPLEMENTATION NOTES
873		1316
874	This section contains some random implementation notes. They do not	1317	This section contains some random implementation notes. They do not
875	describe guaranteed behaviour, but merely behaviour as-is implemented	1318	describe guaranteed behaviour, but merely behaviour as-is implemented
…		…
884	Only the double data type is supported for NV data types - when Perl uses	1327	Only the double data type is supported for NV data types - when Perl uses
885	long double to represent floating point values, they might not be encoded	1328	long double to represent floating point values, they might not be encoded
886	properly. Half precision types are accepted, but not encoded.	1329	properly. Half precision types are accepted, but not encoded.
887		1330
888	Strict mode and canonical mode are not implemented.	1331	Strict mode and canonical mode are not implemented.
		1332
		1333
		1334	=head1 LIMITATIONS ON PERLS WITHOUT 64-BIT INTEGER SUPPORT
		1335
		1336	On perls that were built without 64 bit integer support (these are rare
		1337	nowadays, even on 32 bit architectures, as all major Perl distributions
		1338	are built with 64 bit integer support), support for any kind of 64 bit
		1339	value in CBOR is very limited - most likely, these 64 bit values will
		1340	be truncated, corrupted, or otherwise not decoded correctly. This also
		1341	includes string, float, array and map sizes that are stored as 64 bit
		1342	integers.
889		1343
890		1344
891	=head1 THREADS	1345	=head1 THREADS
892		1346
893	This module is I<not> guaranteed to be thread safe and there are no	1347	This module is I<not> guaranteed to be thread safe and there are no
…		…
907	Please refrain from using rt.cpan.org or any other bug reporting	1361	Please refrain from using rt.cpan.org or any other bug reporting
908	service. I put the contact address into my modules for a reason.	1362	service. I put the contact address into my modules for a reason.
909		1363
910	=cut	1364	=cut
911		1365
		1366	# clumsy and slow hv_store-in-hash helper function
		1367	sub _hv_store {
		1368	$_[0]{$_[1]} = $_[2];
		1369	}
		1370
912	our %FILTER = (	1371	our %FILTER = (
913	# 0 # rfc4287 datetime, utf-8	1372	0 => sub { # rfc4287 datetime, utf-8
914	# 1 # unix timestamp, any	1373	require Time::Piece;
		1374	# Time::Piece::Strptime uses the "incredibly flexible date parsing routine"
		1375	# from FreeBSD, which can't parse ISO 8601, RFC3339, RFC4287 or much of anything
		1376	# else either. Whats incredibe over standard strptime totally escapes me.
		1377	# doesn't do fractional times, either. sigh.
		1378	# In fact, it's all a lie, it uses whatever strptime it wants, and of course,
		1379	# they are all incompatible. The openbsd one simply ignores %z (but according to the
		1380	# docs, it would be much more incredibly flexible indeed. If it worked, that is.).
		1381	scalar eval {
		1382	my $s = $_[1];
		1383
		1384	$s =~ s/Z$/+00:00/;
		1385	$s =~ s/(\.[0-9]+)?([+-][0-9][0-9]):([0-9][0-9])$//
		1386	or die;
		1387
		1388	my $b = $1 - ($2 * 60 + $3) * 60; # fractional part + offset. hopefully
		1389	my $d = Time::Piece->strptime ($s, "%Y-%m-%dT%H:%M:%S");
		1390
		1391	Time::Piece::gmtime ($d->epoch + $b)
		1392	} \|\| die "corrupted CBOR date/time string ($_[0])";
		1393	},
		1394
		1395	1 => sub { # seconds since the epoch, possibly fractional
		1396	require Time::Piece;
		1397	scalar Time::Piece::gmtime (pop)
		1398	},
915		1399
916	2 => sub { # pos bigint	1400	2 => sub { # pos bigint
917	require Math::BigInt;	1401	require Math::BigInt;
918	Math::BigInt->new ("0x" . unpack "H*", pop)	1402	Math::BigInt->new ("0x" . unpack "H*", pop)
919	},	1403	},
…		…
926	4 => sub { # decimal fraction, array	1410	4 => sub { # decimal fraction, array
927	require Math::BigFloat;	1411	require Math::BigFloat;
928	Math::BigFloat->new ($_[1][1] . "E" . $_[1][0])	1412	Math::BigFloat->new ($_[1][1] . "E" . $_[1][0])
929	},	1413	},
930		1414
		1415	264 => sub { # decimal fraction with arbitrary exponent
		1416	require Math::BigFloat;
		1417	Math::BigFloat->new ($_[1][1] . "E" . $_[1][0])
		1418	},
		1419
931	5 => sub { # bigfloat, array	1420	5 => sub { # bigfloat, array
932	require Math::BigFloat;	1421	require Math::BigFloat;
933	scalar Math::BigFloat->new ($_[1][1])->blsft ($_[1][0], 2)	1422	scalar Math::BigFloat->new ($_[1][1]) * Math::BigFloat->new (2)->bpow ($_[1][0])
		1423	},
		1424
		1425	265 => sub { # bigfloat with arbitrary exponent
		1426	require Math::BigFloat;
		1427	scalar Math::BigFloat->new ($_[1][1]) * Math::BigFloat->new (2)->bpow ($_[1][0])
		1428	},
		1429
		1430	30 => sub { # rational number
		1431	require Math::BigRat;
		1432	Math::BigRat->new ("$_[1][0]/$_[1][1]") # separate parameters only work in recent versons
934	},	1433	},
935		1434
936	21 => sub { pop }, # expected conversion to base64url encoding	1435	21 => sub { pop }, # expected conversion to base64url encoding
937	22 => sub { pop }, # expected conversion to base64 encoding	1436	22 => sub { pop }, # expected conversion to base64 encoding
938	23 => sub { pop }, # expected conversion to base16 encoding	1437	23 => sub { pop }, # expected conversion to base16 encoding
…		…
948	# 34 # base64 rfc46484, utf-8	1447	# 34 # base64 rfc46484, utf-8
949	# 35 # regex pcre/ecma262, utf-8	1448	# 35 # regex pcre/ecma262, utf-8
950	# 36 # mime message rfc2045, utf-8	1449	# 36 # mime message rfc2045, utf-8
951	);	1450	);
952		1451
953	sub CBOR::XS::default_filter {	1452	sub default_filter {
954	&{ $FILTER{$_[0]} or return }	1453	&{ $FILTER{$_[0]} or return }
		1454	}
		1455
		1456	our %SAFE_FILTER = map { $_ => $FILTER{$_} } 0, 1, 21, 22, 23, 32;
		1457
		1458	sub safe_filter {
		1459	&{ $SAFE_FILTER{$_[0]} or return }
955	}	1460	}
956		1461
957	sub URI::TO_CBOR {	1462	sub URI::TO_CBOR {
958	my $uri = $_[0]->as_string;	1463	my $uri = $_[0]->as_string;
959	utf8::upgrade $uri;	1464	utf8::upgrade $uri;
960	CBOR::XS::tag 32, $uri	1465	tag 32, $uri
961	}	1466	}
962		1467
963	sub Math::BigInt::TO_CBOR {	1468	sub Math::BigInt::TO_CBOR {
964	if ($_[0] >= -2147483648 && $_[0] <= 2147483647) {	1469	if (-2147483648 <= $_[0] && $_[0] <= 2147483647) {
965	$_[0]->numify	1470	$_[0]->numify
966	} else {	1471	} else {
967	my $hex = substr $_[0]->as_hex, 2;	1472	my $hex = substr $_[0]->as_hex, 2;
968	$hex = "0$hex" if 1 & length $hex; # sigh	1473	$hex = "0$hex" if 1 & length $hex; # sigh
969	CBOR::XS::tag $_[0] >= 0 ? 2 : 3, pack "H*", $hex	1474	tag $_[0] >= 0 ? 2 : 3, pack "H*", $hex
970	}	1475	}
971	}	1476	}
972		1477
973	sub Math::BigFloat::TO_CBOR {	1478	sub Math::BigFloat::TO_CBOR {
974	my ($m, $e) = $_[0]->parts;	1479	my ($m, $e) = $_[0]->parts;
		1480
		1481	-9223372036854775808 <= $e && $e <= 18446744073709551615
975	CBOR::XS::tag 4, [$e->numify, $m]	1482	? tag 4, [$e->numify, $m]
		1483	: tag 264, [$e, $m]
		1484	}
		1485
		1486	sub Math::BigRat::TO_CBOR {
		1487	my ($n, $d) = $_[0]->parts;
		1488
		1489	# older versions of BigRat need *1, as they not always return numbers
		1490
		1491	$d*1 == 1
		1492	? $n*1
		1493	: tag 30, [$n1, $d1]
		1494	}
		1495
		1496	sub Time::Piece::TO_CBOR {
		1497	tag 1, 0 + $_[0]->epoch
976	}	1498	}
977		1499
978	XSLoader::load "CBOR::XS", $VERSION;	1500	XSLoader::load "CBOR::XS", $VERSION;
979		1501
980	=head1 SEE ALSO	1502	=head1 SEE ALSO

Diff Legend

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

Comparing CBOR-XS/XS.pm (file contents): Revision 1.29 by root, Sat Nov 30 15:23:59 2013 UTC vs. Revision 1.88 by root, Thu Sep 7 23:52:24 2023 UTC

Diff Legend

Comparing CBOR-XS/XS.pm (file contents):
Revision 1.29 by root, Sat Nov 30 15:23:59 2013 UTC vs.
Revision 1.88 by root, Thu Sep 7 23:52:24 2023 UTC