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

Comparing CBOR-XS/XS.pm (file contents):
Revision 1.28 by root, Thu Nov 28 16:09:04 2013 UTC vs.
Revision 1.73 by root, Sun Nov 29 21:35:51 2020 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 = 1.8;
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	->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	}
117		142
118	=item $cbor = $cbor->max_depth ([$maximum_nesting_depth])	143	=item $cbor = $cbor->max_depth ([$maximum_nesting_depth])
119		144
120	=item $max_depth = $cbor->get_max_depth	145	=item $max_depth = $cbor->get_max_depth
121		146
…		…
137		162
138	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
139	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
140	crashing.	165	crashing.
141		166
142	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.
143		168
144	=item $cbor = $cbor->max_size ([$maximum_string_size])	169	=item $cbor = $cbor->max_size ([$maximum_string_size])
145		170
146	=item $max_size = $cbor->get_max_size	171	=item $max_size = $cbor->get_max_size
147		172
…		…
152	effect on C<encode> (yet).	177	effect on C<encode> (yet).
153		178
154	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
155	C<0> is specified).	180	C<0> is specified).
156		181
157	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.
158		183
159	=item $cbor = $cbor->allow_unknown ([$enable])	184	=item $cbor = $cbor->allow_unknown ([$enable])
160		185
161	=item $enabled = $cbor->get_allow_unknown	186	=item $enabled = $cbor->get_allow_unknown
162		187
…		…
180	reference to the earlier value.	205	reference to the earlier value.
181		206
182	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
183	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
184	sharing extension. This also makes it possible to encode cyclic data	209	sharing extension. This also makes it possible to encode cyclic data
185	structures.	210	structures (which need C<allow_cycles> to be enabled to be decoded by this
		211	module).
186		212
187	It is recommended to leave it off unless you know your	213	It is recommended to leave it off unless you know your
188	communication partner supports the value sharing extensions to CBOR	214	communication partner supports the value sharing extensions to CBOR
189	(L<http://cbor.schmorp.de/value-sharing>), as without decoder support, the	215	(L<http://cbor.schmorp.de/value-sharing>), as without decoder support, the
190	resulting data structure might be unusable.	216	resulting data structure might be unusable.
191		217
192	Detecting shared values incurs a runtime overhead when values are encoded	218	Detecting shared values incurs a runtime overhead when values are encoded
193	that have a reference counter large than one, and might unnecessarily	219	that have a reference counter large than one, and might unnecessarily
194	increase the encoded size, as potentially shared values are encode as	220	increase the encoded size, as potentially shared values are encoded as
195	sharable whether or not they are actually shared.	221	shareable whether or not they are actually shared.
196		222
197	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,
198	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
199	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
200	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
…		…
205	structures cannot be encoded in this mode.	231	structures cannot be encoded in this mode.
206		232
207	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
208	references will always be decoded properly if present.	234	references will always be decoded properly if present.
209		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
210	=item $cbor = $cbor->pack_strings ([$enable])	275	=item $cbor = $cbor->pack_strings ([$enable])
211		276
212	=item $enabled = $cbor->get_pack_strings	277	=item $enabled = $cbor->get_pack_strings
213		278
214	If C<$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
…		…
226	the standard CBOR way.	291	the standard CBOR way.
227		292
228	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
229	always be decoded properly if present.	294	always be decoded properly if present.
230		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
231	=item $cbor = $cbor->filter ([$cb->($tag, $value)])	366	=item $cbor = $cbor->filter ([$cb->($tag, $value)])
232		367
233	=item $cb_or_undef = $cbor->get_filter	368	=item $cb_or_undef = $cbor->get_filter
234		369
235	Sets or replaces the tagged value decoding filter (when C<$cb> is	370	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,	382	replace the tagged value in the decoded data structure, or no values,
248	which will result in default handling, which currently means the decoder	383	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.	384	creates a C<CBOR::XS::Tagged> object to hold the tag and the value.
250		385
251	When the filter is cleared (the default state), the default filter	386	When the filter is cleared (the default state), the default filter
252	function, C<CBOR::XS::default_filter>, is used. This function simply looks	387	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	388	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	389	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.	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.
256		404
257	Example: decode all tags not handled internally into C<CBOR::XS::Tagged>	405	Example: decode all tags not handled internally into C<CBOR::XS::Tagged>
258	objects, with no other special handling (useful when working with	406	objects, with no other special handling (useful when working with
259	potentially "unsafe" CBOR data).	407	potentially "unsafe" CBOR data).
260		408
…		…
267	my ($tag, $value);	415	my ($tag, $value);
268		416
269	"tag 1347375694 value $value"	417	"tag 1347375694 value $value"
270	};	418	};
271		419
		420	Example: provide your own filter function that looks up tags in your own
		421	hash:
		422
		423	my %my_filter = (
		424	998347484 => sub {
		425	my ($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);
		440
272	=item $cbor_data = $cbor->encode ($perl_scalar)	441	=item $cbor_data = $cbor->encode ($perl_scalar)
273		442
274	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
275	representation.	444	representation.
276		445
…		…
285	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
286	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.
287		456
288	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
289	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
290	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.
291		461
292	CBOR::XS->new->decode_prefix ("......")	462	CBOR::XS->new->decode_prefix ("......")
293	=> ("...", 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.
294		528
295	=back	529	=back
296		530
297		531
298	=head1 MAPPING	532	=head1 MAPPING
…		…
371		605
372	=item hash references	606	=item hash references
373		607
374	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
375	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
376	order. This order can be different each time a hahs is encoded.	610	order. This order can be different each time a hash is encoded.
377		611
378	Currently, tied hashes will use the indefinite-length format, while normal	612	Currently, tied hashes will use the indefinite-length format, while normal
379	hashes will use the fixed-length format.	613	hashes will use the fixed-length format.
380		614
381	=item array references	615	=item array references
…		…
434	my $x = 3.1; # some variable containing a number	668	my $x = 3.1; # some variable containing a number
435	"$x"; # stringified	669	"$x"; # stringified
436	$x .= ""; # another, more awkward way to stringify	670	$x .= ""; # another, more awkward way to stringify
437	print $x; # perl does it for you, too, quite often	671	print $x; # perl does it for you, too, quite often
438		672
439	You can force whether a string ie encoded as byte or text string by using	673	You can force whether a string is encoded as byte or text string by using
440	C<utf8::upgrade> and C<utf8::downgrade>):	674	C<utf8::upgrade> and C<utf8::downgrade> (if C<text_strings> is disabled).
441		675
442	utf8::upgrade $x; # encode $x as text string	676	utf8::upgrade $x; # encode $x as text string
443	utf8::downgrade $x; # encode $x as byte string	677	utf8::downgrade $x; # encode $x as byte string
444		678
		679	More options are available, see L<TYPE CASTS>, below, and the C<text_keys>
		680	and C<text_strings> options.
		681
445	Perl doesn't define what operations up- and downgrade strings, so if the	682	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	683	difference between byte and text is important, you should up- or downgrade
447	your string as late as possible before encoding.	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>.
448		686
449	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:
450		688
451	my $x = "3"; # some variable containing a string	689	my $x = "3"; # some variable containing a string
452	$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
…		…
463	represent numerical values are supported, but might suffer loss of	701	represent numerical values are supported, but might suffer loss of
464	precision.	702	precision.
465		703
466	=back	704	=back
467		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 operators):
		718
		719	=over
		720
		721	=item CBOR::XS::as_int $value
		722
		723	Forces the value to be encoded as some form of (basic, not bignum) integer
		724	type.
		725
		726	=item CBOR::XS::as_text $value
		727
		728	Forces the value to be encoded as (UTF-8) text values.
		729
		730	=item CBOR::XS::as_bytes $value
		731
		732	Forces the value to be encoded as a (binary) string value.
		733
		734	=item CBOR::XS::as_float16 $value
		735
		736	Forces half-float (IEEE 754 binary16) encoding of the given value.
		737
		738	=item CBOR::XS::as_float32 $value
		739
		740	Forces single-float (IEEE 754 binary32) encoding of the given value.
		741
		742	=item CBOR::XS::as_float64 $value
		743
		744	Forces double-float (IEEE 754 binary64) encoding of the given value.
		745
		746	=item, CBOR::XS::as_cbor $cbor_text
		747
		748	Bot a type cast per-se, this type cast forces the argument to eb encoded
		749	as-is. This can be used to embed pre-encoded CBOR data.
		750
		751	Note that no checking on the validity of the C<$cbor_text> is done - it's
		752	the callers responsibility to correctly encode values.
		753
		754	=back
		755
		756	Example: encode a perl string as binary even though C<text_strings> is in
		757	effect.
		758
		759	CBOR::XS->new->text_strings->encode ([4, "text", CBOR::XS::bytes "bytevalue"]);
		760
		761	=cut
		762
		763	sub CBOR::XS::as_int ($) { bless [$_[0], 0, undef], CBOR::XS::Tagged:: }
		764	sub CBOR::XS::as_cbor ($) { bless [$_[0], 1, undef], CBOR::XS::Tagged:: }
		765	sub CBOR::XS::as_bytes ($) { bless [$_[0], 2, undef], CBOR::XS::Tagged:: }
		766	sub CBOR::XS::as_text ($) { bless [$_[0], 3, undef], CBOR::XS::Tagged:: }
		767	sub CBOR::XS::as_float16 ($) { bless [$_[0], 4, undef], CBOR::XS::Tagged:: }
		768	sub CBOR::XS::as_float32 ($) { bless [$_[0], 5, undef], CBOR::XS::Tagged:: }
		769	sub CBOR::XS::as_float64 ($) { bless [$_[0], 6, undef], CBOR::XS::Tagged:: }
		770
468	=head2 OBJECT SERIALISATION	771	=head2 OBJECT SERIALISATION
		772
		773	This module implements both a CBOR-specific and the generic
		774	L<Types::Serialier> object serialisation protocol. The following
		775	subsections explain both methods.
		776
		777	=head3 ENCODING
469		778
470	This module knows two way to serialise a Perl object: The CBOR-specific	779	This module knows two way to serialise a Perl object: The CBOR-specific
471	way, and the generic way.	780	way, and the generic way.
472		781
473	Whenever the encoder encounters a Perl object that it cnanot serialise	782	Whenever the encoder encounters a Perl object that it cannot serialise
474	directly (most of them), it will first look up the C<TO_CBOR> method on	783	directly (most of them), it will first look up the C<TO_CBOR> method on
475	it.	784	it.
476		785
477	If it has a C<TO_CBOR> method, it will call it with the object as only	786	If it has a C<TO_CBOR> method, it will call it with the object as only
478	argument, and expects exactly one return value, which it will then	787	argument, and expects exactly one return value, which it will then
…		…
484		793
485	The C<FREEZE> method can return any number of values (i.e. zero or	794	The C<FREEZE> method can return any number of values (i.e. zero or
486	more). These will be encoded as CBOR perl object, together with the	795	more). These will be encoded as CBOR perl object, together with the
487	classname.	796	classname.
488		797
		798	These methods I<MUST NOT> change the data structure that is being
		799	serialised. Failure to comply to this can result in memory corruption -
		800	and worse.
		801
489	If an object supports neither C<TO_CBOR> nor C<FREEZE>, encoding will fail	802	If an object supports neither C<TO_CBOR> nor C<FREEZE>, encoding will fail
490	with an error.	803	with an error.
491		804
		805	=head3 DECODING
		806
492	Objects encoded via C<TO_CBOR> cannot be automatically decoded, but	807	Objects encoded via C<TO_CBOR> cannot (normally) be automatically decoded,
493	objects encoded via C<FREEZE> can be decoded using the following protocol:	808	but objects encoded via C<FREEZE> can be decoded using the following
		809	protocol:
494		810
495	When an encoded CBOR perl object is encountered by the decoder, it will	811	When an encoded CBOR perl object is encountered by the decoder, it will
496	look up the C<THAW> method, by using the stored classname, and will fail	812	look up the C<THAW> method, by using the stored classname, and will fail
497	if the method cannot be found.	813	if the method cannot be found.
498		814
499	After the lookup it will call the C<THAW> method with the stored classname	815	After the lookup it will call the C<THAW> method with the stored classname
500	as first argument, the constant string C<CBOR> as second argument, and all	816	as first argument, the constant string C<CBOR> as second argument, and all
501	values returned by C<FREEZE> as remaining arguments.	817	values returned by C<FREEZE> as remaining arguments.
502		818
503	=head4 EXAMPLES	819	=head3 EXAMPLES
504		820
505	Here is an example C<TO_CBOR> method:	821	Here is an example C<TO_CBOR> method:
506		822
507	sub My::Object::TO_CBOR {	823	sub My::Object::TO_CBOR {
508	my ($obj) = @_;	824	my ($obj) = @_;
…		…
540	"$self" # encode url string	856	"$self" # encode url string
541	}	857	}
542		858
543	sub URI::THAW {	859	sub URI::THAW {
544	my ($class, $serialiser, $uri) = @_;	860	my ($class, $serialiser, $uri) = @_;
545
546	$class->new ($uri)	861	$class->new ($uri)
547	}	862	}
548		863
549	Unlike C<TO_CBOR>, multiple values can be returned by C<FREEZE>. For	864	Unlike C<TO_CBOR>, multiple values can be returned by C<FREEZE>. For
550	example, a C<FREEZE> method that returns "type", "id" and "variant" values	865	example, a C<FREEZE> method that returns "type", "id" and "variant" values
…		…
681	additional tags (such as base64url).	996	additional tags (such as base64url).
682		997
683	=head2 ENFORCED TAGS	998	=head2 ENFORCED TAGS
684		999
685	These tags are always handled when decoding, and their handling cannot be	1000	These tags are always handled when decoding, and their handling cannot be
686	overriden by the user.	1001	overridden by the user.
687		1002
688	=over 4	1003	=over 4
689		1004
690	=item 26 (perl-object, L<http://cbor.schmorp.de/perl-object>)	1005	=item 26 (perl-object, L<http://cbor.schmorp.de/perl-object>)
691		1006
692	These tags are automatically created (and decoded) for serialisable	1007	These tags are automatically created (and decoded) for serialisable
693	objects using the C<FREEZE/THAW> methods (the L<Types::Serialier> object	1008	objects using the C<FREEZE/THAW> methods (the L<Types::Serialier> object
694	serialisation protocol). See L<OBJECT SERIALISATION> for details.	1009	serialisation protocol). See L<OBJECT SERIALISATION> for details.
695		1010
696	=item 28, 29 (sharable, sharedref, L <http://cbor.schmorp.de/value-sharing>)	1011	=item 28, 29 (shareable, sharedref, L<http://cbor.schmorp.de/value-sharing>)
697		1012
698	These tags are automatically decoded when encountered, resulting in	1013	These tags are automatically decoded when encountered (and they do not
		1014	result in a cyclic data structure, see C<allow_cycles>), resulting in
699	shared values in the decoded object. They are only encoded, however, when	1015	shared values in the decoded object. They are only encoded, however, when
700	C<allow_sharable> is enabled.	1016	C<allow_sharing> is enabled.
701		1017
		1018	Not all shared values can be successfully decoded: values that reference
		1019	themselves will I<currently> decode as C<undef> (this is not the same
		1020	as a reference pointing to itself, which will be represented as a value
		1021	that contains an indirect reference to itself - these will be decoded
		1022	properly).
		1023
		1024	Note that considerably more shared value data structures can be decoded
		1025	than will be encoded - currently, only values pointed to by references
		1026	will be shared, others will not. While non-reference shared values can be
		1027	generated in Perl with some effort, they were considered too unimportant
		1028	to be supported in the encoder. The decoder, however, will decode these
		1029	values as shared values.
		1030
702	=item 256, 25 (stringref-namespace, stringref, L <http://cbor.schmorp.de/stringref>)	1031	=item 256, 25 (stringref-namespace, stringref, L<http://cbor.schmorp.de/stringref>)
703		1032
704	These tags are automatically decoded when encountered. They are only	1033	These tags are automatically decoded when encountered. They are only
705	encoded, however, when C<pack_strings> is enabled.	1034	encoded, however, when C<pack_strings> is enabled.
706		1035
707	=item 22098 (indirection, L<http://cbor.schmorp.de/indirection>)	1036	=item 22098 (indirection, L<http://cbor.schmorp.de/indirection>)
708		1037
709	This tag is automatically generated when a reference are encountered (with	1038	This tag is automatically generated when a reference are encountered (with
710	the exception of hash and array refernces). It is converted to a reference	1039	the exception of hash and array references). It is converted to a reference
711	when decoding.	1040	when decoding.
712		1041
713	=item 55799 (self-describe CBOR, RFC 7049)	1042	=item 55799 (self-describe CBOR, RFC 7049)
714		1043
715	This value is not generated on encoding (unless explicitly requested by	1044	This value is not generated on encoding (unless explicitly requested by
…		…
718	=back	1047	=back
719		1048
720	=head2 NON-ENFORCED TAGS	1049	=head2 NON-ENFORCED TAGS
721		1050
722	These tags have default filters provided when decoding. Their handling can	1051	These tags have default filters provided when decoding. Their handling can
723	be overriden by changing the C<%CBOR::XS::FILTER> entry for the tag, or by	1052	be overridden by changing the C<%CBOR::XS::FILTER> entry for the tag, or by
724	providing a custom C<filter> callback when decoding.	1053	providing a custom C<filter> callback when decoding.
725		1054
726	When they result in decoding into a specific Perl class, the module	1055	When they result in decoding into a specific Perl class, the module
727	usually provides a corresponding C<TO_CBOR> method as well.	1056	usually provides a corresponding C<TO_CBOR> method as well.
728		1057
…		…
731	provide these modules. The decoding usually fails with an exception if the	1060	provide these modules. The decoding usually fails with an exception if the
732	required module cannot be loaded.	1061	required module cannot be loaded.
733		1062
734	=over 4	1063	=over 4
735		1064
		1065	=item 0, 1 (date/time string, seconds since the epoch)
		1066
		1067	These tags are decoded into L<Time::Piece> objects. The corresponding
		1068	C<Time::Piece::TO_CBOR> method always encodes into tag 1 values currently.
		1069
		1070	The L<Time::Piece> API is generally surprisingly bad, and fractional
		1071	seconds are only accidentally kept intact, so watch out. On the plus side,
		1072	the module comes with perl since 5.10, which has to count for something.
		1073
736	=item 2, 3 (positive/negative bignum)	1074	=item 2, 3 (positive/negative bignum)
737		1075
738	These tags are decoded into L<Math::BigInt> objects. The corresponding	1076	These tags are decoded into L<Math::BigInt> objects. The corresponding
739	C<Math::BigInt::TO_CBOR> method encodes "small" bigints into normal CBOR	1077	C<Math::BigInt::TO_CBOR> method encodes "small" bigints into normal CBOR
740	integers, and others into positive/negative CBOR bignums.	1078	integers, and others into positive/negative CBOR bignums.
741		1079
742	=item 4, 5 (decimal fraction/bigfloat)	1080	=item 4, 5, 264, 265 (decimal fraction/bigfloat)
743		1081
744	Both decimal fractions and bigfloats are decoded into L<Math::BigFloat>	1082	Both decimal fractions and bigfloats are decoded into L<Math::BigFloat>
745	objects. The corresponding C<Math::BigFloat::TO_CBOR> method I<always>	1083	objects. The corresponding C<Math::BigFloat::TO_CBOR> method I<always>
746	encodes into a decimal fraction.	1084	encodes into a decimal fraction (either tag 4 or 264).
747		1085
748	CBOR cannot represent bigfloats with I<very> large exponents - conversion	1086	NaN and infinities are not encoded properly, as they cannot be represented
749	of such big float objects is undefined.	1087	in CBOR.
750		1088
751	Also, NaN and infinities are not encoded properly.	1089	See L<BIGNUM SECURITY CONSIDERATIONS> for more info.
		1090
		1091	=item 30 (rational numbers)
		1092
		1093	These tags are decoded into L<Math::BigRat> objects. The corresponding
		1094	C<Math::BigRat::TO_CBOR> method encodes rational numbers with denominator
		1095	C<1> via their numerator only, i.e., they become normal integers or
		1096	C<bignums>.
		1097
		1098	See L<BIGNUM SECURITY CONSIDERATIONS> for more info.
752		1099
753	=item 21, 22, 23 (expected later JSON conversion)	1100	=item 21, 22, 23 (expected later JSON conversion)
754		1101
755	CBOR::XS is not a CBOR-to-JSON converter, and will simply ignore these	1102	CBOR::XS is not a CBOR-to-JSON converter, and will simply ignore these
756	tags.	1103	tags.
…		…
761	C<URI::TO_CBOR> method again results in a CBOR URI value.	1108	C<URI::TO_CBOR> method again results in a CBOR URI value.
762		1109
763	=back	1110	=back
764		1111
765	=cut	1112	=cut
766
767	our %FILTER = (
768	# 0 # rfc4287 datetime, utf-8
769	# 1 # unix timestamp, any
770
771	2 => sub { # pos bigint
772	require Math::BigInt;
773	Math::BigInt->new ("0x" . unpack "H*", pop)
774	},
775
776	3 => sub { # neg bigint
777	require Math::BigInt;
778	-Math::BigInt->new ("0x" . unpack "H*", pop)
779	},
780
781	4 => sub { # decimal fraction, array
782	require Math::BigFloat;
783	Math::BigFloat->new ($_[1][1] . "E" . $_[1][0])
784	},
785
786	5 => sub { # bigfloat, array
787	require Math::BigFloat;
788	scalar Math::BigFloat->new ($_[1][1])->blsft ($_[1][0], 2)
789	},
790
791	21 => sub { pop }, # expected conversion to base64url encoding
792	22 => sub { pop }, # expected conversion to base64 encoding
793	23 => sub { pop }, # expected conversion to base16 encoding
794
795	# 24 # embedded cbor, byte string
796
797	32 => sub {
798	require URI;
799	URI->new (pop)
800	},
801
802	# 33 # base64url rfc4648, utf-8
803	# 34 # base64 rfc46484, utf-8
804	# 35 # regex pcre/ecma262, utf-8
805	# 36 # mime message rfc2045, utf-8
806	);
807
808		1113
809	=head1 CBOR and JSON	1114	=head1 CBOR and JSON
810		1115
811	CBOR is supposed to implement a superset of the JSON data model, and is,	1116	CBOR is supposed to implement a superset of the JSON data model, and is,
812	with some coercion, able to represent all JSON texts (something that other	1117	with some coercion, able to represent all JSON texts (something that other
…		…
821	CBOR intact.	1126	CBOR intact.
822		1127
823		1128
824	=head1 SECURITY CONSIDERATIONS	1129	=head1 SECURITY CONSIDERATIONS
825		1130
826	When you are using CBOR in a protocol, talking to untrusted potentially	1131	Tl;dr... if you want to decode or encode CBOR from untrusted sources, you
827	hostile creatures requires relatively few measures.	1132	should start with a coder object created via C<new_safe> (which implements
		1133	the mitigations explained below):
828		1134
		1135	my $coder = CBOR::XS->new_safe;
		1136
		1137	my $data = $coder->decode ($cbor_text);
		1138	my $cbor = $coder->encode ($data);
		1139
		1140	Longer version: When you are using CBOR in a protocol, talking to
		1141	untrusted potentially hostile creatures requires some thought:
		1142
		1143	=over 4
		1144
		1145	=item Security of the CBOR decoder itself
		1146
829	First of all, your CBOR decoder should be secure, that is, should not have	1147	First and foremost, your CBOR decoder should be secure, that is, should
		1148	not have any buffer overflows or similar bugs that could potentially be
830	any buffer overflows. Obviously, this module should ensure that and I am	1149	exploited. Obviously, this module should ensure that and I am trying hard
831	trying hard on making that true, but you never know.	1150	on making that true, but you never know.
832		1151
		1152	=item CBOR::XS can invoke almost arbitrary callbacks during decoding
		1153
		1154	CBOR::XS supports object serialisation - decoding CBOR can cause calls
		1155	to I<any> C<THAW> method in I<any> package that exists in your process
		1156	(that is, CBOR::XS will not try to load modules, but any existing C<THAW>
		1157	method or function can be called, so they all have to be secure).
		1158
		1159	Less obviously, it will also invoke C<TO_CBOR> and C<FREEZE> methods -
		1160	even if all your C<THAW> methods are secure, encoding data structures from
		1161	untrusted sources can invoke those and trigger bugs in those.
		1162
		1163	So, if you are not sure about the security of all the modules you
		1164	have loaded (you shouldn't), you should disable this part using
		1165	C<forbid_objects> or using C<new_safe>.
		1166
		1167	=item CBOR can be extended with tags that call library code
		1168
		1169	CBOR can be extended with tags, and C<CBOR::XS> has a registry of
		1170	conversion functions for many existing tags that can be extended via
		1171	third-party modules (see the C<filter> method).
		1172
		1173	If you don't trust these, you should configure the "safe" filter function,
		1174	C<CBOR::XS::safe_filter> (C<new_safe> does this), which by default only
		1175	includes conversion functions that are considered "safe" by the author
		1176	(but again, they can be extended by third party modules).
		1177
		1178	Depending on your level of paranoia, you can use the "safe" filter:
		1179
		1180	$cbor->filter (\&CBOR::XS::safe_filter);
		1181
		1182	... your own filter...
		1183
		1184	$cbor->filter (sub { ... do your stuffs here ... });
		1185
		1186	... or even no filter at all, disabling all tag decoding:
		1187
		1188	$cbor->filter (sub { });
		1189
		1190	This is never a problem for encoding, as the tag mechanism only exists in
		1191	CBOR texts.
		1192
		1193	=item Resource-starving attacks: object memory usage
		1194
833	Second, you need to avoid resource-starving attacks. That means you should	1195	You need to avoid resource-starving attacks. That means you should limit
834	limit the size of CBOR data you accept, or make sure then when your	1196	the size of CBOR data you accept, or make sure then when your resources
835	resources run out, that's just fine (e.g. by using a separate process that	1197	run out, that's just fine (e.g. by using a separate process that can
836	can crash safely). The size of a CBOR string in octets is usually a good	1198	crash safely). The size of a CBOR string in octets is usually a good
837	indication of the size of the resources required to decode it into a Perl	1199	indication of the size of the resources required to decode it into a Perl
838	structure. While CBOR::XS can check the size of the CBOR text, it might be	1200	structure. While CBOR::XS can check the size of the CBOR text (using
839	too late when you already have it in memory, so you might want to check	1201	C<max_size> - done by C<new_safe>), it might be too late when you already
840	the size before you accept the string.	1202	have it in memory, so you might want to check the size before you accept
		1203	the string.
841		1204
		1205	As for encoding, it is possible to construct data structures that are
		1206	relatively small but result in large CBOR texts (for example by having an
		1207	array full of references to the same big data structure, which will all be
		1208	deep-cloned during encoding by default). This is rarely an actual issue
		1209	(and the worst case is still just running out of memory), but you can
		1210	reduce this risk by using C<allow_sharing>.
		1211
		1212	=item Resource-starving attacks: stack overflows
		1213
842	Third, CBOR::XS recurses using the C stack when decoding objects and	1214	CBOR::XS recurses using the C stack when decoding objects and arrays. The
843	arrays. The C stack is a limited resource: for instance, on my amd64	1215	C stack is a limited resource: for instance, on my amd64 machine with 8MB
844	machine with 8MB of stack size I can decode around 180k nested arrays but	1216	of stack size I can decode around 180k nested arrays but only 14k nested
845	only 14k nested CBOR objects (due to perl itself recursing deeply on croak	1217	CBOR objects (due to perl itself recursing deeply on croak to free the
846	to free the temporary). If that is exceeded, the program crashes. To be	1218	temporary). If that is exceeded, the program crashes. To be conservative,
847	conservative, the default nesting limit is set to 512. If your process	1219	the default nesting limit is set to 512. If your process has a smaller
848	has a smaller stack, you should adjust this setting accordingly with the	1220	stack, you should adjust this setting accordingly with the C<max_depth>
849	C<max_depth> method.	1221	method.
		1222
		1223	=item Resource-starving attacks: CPU en-/decoding complexity
		1224
		1225	CBOR::XS will use the L<Math::BigInt>, L<Math::BigFloat> and
		1226	L<Math::BigRat> libraries to represent encode/decode bignums. These can be
		1227	very slow (as in, centuries of CPU time) and can even crash your program
		1228	(and are generally not very trustworthy). See the next section on bignum
		1229	security for details.
		1230
		1231	=item Data breaches: leaking information in error messages
		1232
		1233	CBOR::XS might leak contents of your Perl data structures in its error
		1234	messages, so when you serialise sensitive information you might want to
		1235	make sure that exceptions thrown by CBOR::XS will not end up in front of
		1236	untrusted eyes.
		1237
		1238	=item Something else...
850		1239
851	Something else could bomb you, too, that I forgot to think of. In that	1240	Something else could bomb you, too, that I forgot to think of. In that
852	case, you get to keep the pieces. I am always open for hints, though...	1241	case, you get to keep the pieces. I am always open for hints, though...
853		1242
854	Also keep in mind that CBOR::XS might leak contents of your Perl data	1243	=back
855	structures in its error messages, so when you serialise sensitive	1244
856	information you might want to make sure that exceptions thrown by CBOR::XS	1245
857	will not end up in front of untrusted eyes.	1246	=head1 BIGNUM SECURITY CONSIDERATIONS
		1247
		1248	CBOR::XS provides a C<TO_CBOR> method for both L<Math::BigInt> and
		1249	L<Math::BigFloat> that tries to encode the number in the simplest possible
		1250	way, that is, either a CBOR integer, a CBOR bigint/decimal fraction (tag
		1251	4) or an arbitrary-exponent decimal fraction (tag 264). Rational numbers
		1252	(L<Math::BigRat>, tag 30) can also contain bignums as members.
		1253
		1254	CBOR::XS will also understand base-2 bigfloat or arbitrary-exponent
		1255	bigfloats (tags 5 and 265), but it will never generate these on its own.
		1256
		1257	Using the built-in L<Math::BigInt::Calc> support, encoding and decoding
		1258	decimal fractions is generally fast. Decoding bigints can be slow for very
		1259	big numbers (tens of thousands of digits, something that could potentially
		1260	be caught by limiting the size of CBOR texts), and decoding bigfloats or
		1261	arbitrary-exponent bigfloats can be I<extremely> slow (minutes, decades)
		1262	for large exponents (roughly 40 bit and longer).
		1263
		1264	Additionally, L<Math::BigInt> can take advantage of other bignum
		1265	libraries, such as L<Math::GMP>, which cannot handle big floats with large
		1266	exponents, and might simply abort or crash your program, due to their code
		1267	quality.
		1268
		1269	This can be a concern if you want to parse untrusted CBOR. If it is, you
		1270	might want to disable decoding of tag 2 (bigint) and 3 (negative bigint)
		1271	types. You should also disable types 5 and 265, as these can be slow even
		1272	without bigints.
		1273
		1274	Disabling bigints will also partially or fully disable types that rely on
		1275	them, e.g. rational numbers that use bignums.
		1276
858		1277
859	=head1 CBOR IMPLEMENTATION NOTES	1278	=head1 CBOR IMPLEMENTATION NOTES
860		1279
861	This section contains some random implementation notes. They do not	1280	This section contains some random implementation notes. They do not
862	describe guaranteed behaviour, but merely behaviour as-is implemented	1281	describe guaranteed behaviour, but merely behaviour as-is implemented
…		…
871	Only the double data type is supported for NV data types - when Perl uses	1290	Only the double data type is supported for NV data types - when Perl uses
872	long double to represent floating point values, they might not be encoded	1291	long double to represent floating point values, they might not be encoded
873	properly. Half precision types are accepted, but not encoded.	1292	properly. Half precision types are accepted, but not encoded.
874		1293
875	Strict mode and canonical mode are not implemented.	1294	Strict mode and canonical mode are not implemented.
		1295
		1296
		1297	=head1 LIMITATIONS ON PERLS WITHOUT 64-BIT INTEGER SUPPORT
		1298
		1299	On perls that were built without 64 bit integer support (these are rare
		1300	nowadays, even on 32 bit architectures, as all major Perl distributions
		1301	are built with 64 bit integer support), support for any kind of 64 bit
		1302	value in CBOR is very limited - most likely, these 64 bit values will
		1303	be truncated, corrupted, or otherwise not decoded correctly. This also
		1304	includes string, float, array and map sizes that are stored as 64 bit
		1305	integers.
876		1306
877		1307
878	=head1 THREADS	1308	=head1 THREADS
879		1309
880	This module is I<not> guaranteed to be thread safe and there are no	1310	This module is I<not> guaranteed to be thread safe and there are no
…		…
894	Please refrain from using rt.cpan.org or any other bug reporting	1324	Please refrain from using rt.cpan.org or any other bug reporting
895	service. I put the contact address into my modules for a reason.	1325	service. I put the contact address into my modules for a reason.
896		1326
897	=cut	1327	=cut
898		1328
		1329	# clumsy and slow hv_store-in-hash helper function
		1330	sub _hv_store {
		1331	$_[0]{$_[1]} = $_[2];
		1332	}
		1333
899	our %FILTER = (	1334	our %FILTER = (
900	# 0 # rfc4287 datetime, utf-8	1335	0 => sub { # rfc4287 datetime, utf-8
901	# 1 # unix timestamp, any	1336	require Time::Piece;
		1337	# Time::Piece::Strptime uses the "incredibly flexible date parsing routine"
		1338	# from FreeBSD, which can't parse ISO 8601, RFC3339, RFC4287 or much of anything
		1339	# else either. Whats incredibe over standard strptime totally escapes me.
		1340	# doesn't do fractional times, either. sigh.
		1341	# In fact, it's all a lie, it uses whatever strptime it wants, and of course,
		1342	# they are all incompatible. The openbsd one simply ignores %z (but according to the
		1343	# docs, it would be much more incredibly flexible indeed. If it worked, that is.).
		1344	scalar eval {
		1345	my $s = $_[1];
		1346
		1347	$s =~ s/Z$/+00:00/;
		1348	$s =~ s/(\.[0-9]+)?([+-][0-9][0-9]):([0-9][0-9])$//
		1349	or die;
		1350
		1351	my $b = $1 - ($2 * 60 + $3) * 60; # fractional part + offset. hopefully
		1352	my $d = Time::Piece->strptime ($s, "%Y-%m-%dT%H:%M:%S");
		1353
		1354	Time::Piece::gmtime ($d->epoch + $b)
		1355	} \|\| die "corrupted CBOR date/time string ($_[0])";
		1356	},
		1357
		1358	1 => sub { # seconds since the epoch, possibly fractional
		1359	require Time::Piece;
		1360	scalar Time::Piece::gmtime (pop)
		1361	},
902		1362
903	2 => sub { # pos bigint	1363	2 => sub { # pos bigint
904	require Math::BigInt;	1364	require Math::BigInt;
905	Math::BigInt->new ("0x" . unpack "H*", pop)	1365	Math::BigInt->new ("0x" . unpack "H*", pop)
906	},	1366	},
…		…
913	4 => sub { # decimal fraction, array	1373	4 => sub { # decimal fraction, array
914	require Math::BigFloat;	1374	require Math::BigFloat;
915	Math::BigFloat->new ($_[1][1] . "E" . $_[1][0])	1375	Math::BigFloat->new ($_[1][1] . "E" . $_[1][0])
916	},	1376	},
917		1377
		1378	264 => sub { # decimal fraction with arbitrary exponent
		1379	require Math::BigFloat;
		1380	Math::BigFloat->new ($_[1][1] . "E" . $_[1][0])
		1381	},
		1382
918	5 => sub { # bigfloat, array	1383	5 => sub { # bigfloat, array
919	require Math::BigFloat;	1384	require Math::BigFloat;
920	scalar Math::BigFloat->new ($_[1][1])->blsft ($_[1][0], 2)	1385	scalar Math::BigFloat->new ($_[1][1]) * Math::BigFloat->new (2)->bpow ($_[1][0])
		1386	},
		1387
		1388	265 => sub { # bigfloat with arbitrary exponent
		1389	require Math::BigFloat;
		1390	scalar Math::BigFloat->new ($_[1][1]) * Math::BigFloat->new (2)->bpow ($_[1][0])
		1391	},
		1392
		1393	30 => sub { # rational number
		1394	require Math::BigRat;
		1395	Math::BigRat->new ("$_[1][0]/$_[1][1]") # separate parameters only work in recent versons
921	},	1396	},
922		1397
923	21 => sub { pop }, # expected conversion to base64url encoding	1398	21 => sub { pop }, # expected conversion to base64url encoding
924	22 => sub { pop }, # expected conversion to base64 encoding	1399	22 => sub { pop }, # expected conversion to base64 encoding
925	23 => sub { pop }, # expected conversion to base16 encoding	1400	23 => sub { pop }, # expected conversion to base16 encoding
…		…
935	# 34 # base64 rfc46484, utf-8	1410	# 34 # base64 rfc46484, utf-8
936	# 35 # regex pcre/ecma262, utf-8	1411	# 35 # regex pcre/ecma262, utf-8
937	# 36 # mime message rfc2045, utf-8	1412	# 36 # mime message rfc2045, utf-8
938	);	1413	);
939		1414
940	sub CBOR::XS::default_filter {	1415	sub default_filter {
941	&{ $FILTER{$_[0]} or return }	1416	&{ $FILTER{$_[0]} or return }
		1417	}
		1418
		1419	our %SAFE_FILTER = map { $_ => $FILTER{$_} } 0, 1, 21, 22, 23, 32;
		1420
		1421	sub safe_filter {
		1422	&{ $SAFE_FILTER{$_[0]} or return }
942	}	1423	}
943		1424
944	sub URI::TO_CBOR {	1425	sub URI::TO_CBOR {
945	my $uri = $_[0]->as_string;	1426	my $uri = $_[0]->as_string;
946	utf8::upgrade $uri;	1427	utf8::upgrade $uri;
947	CBOR::XS::tag 32, $uri	1428	tag 32, $uri
948	}	1429	}
949		1430
950	sub Math::BigInt::TO_CBOR {	1431	sub Math::BigInt::TO_CBOR {
951	if ($_[0] >= -2147483648 && $_[0] <= 2147483647) {	1432	if (-2147483648 <= $_[0] && $_[0] <= 2147483647) {
952	$_[0]->numify	1433	$_[0]->numify
953	} else {	1434	} else {
954	my $hex = substr $_[0]->as_hex, 2;	1435	my $hex = substr $_[0]->as_hex, 2;
955	$hex = "0$hex" if 1 & length $hex; # sigh	1436	$hex = "0$hex" if 1 & length $hex; # sigh
956	CBOR::XS::tag $_[0] >= 0 ? 2 : 3, pack "H*", $hex	1437	tag $_[0] >= 0 ? 2 : 3, pack "H*", $hex
957	}	1438	}
958	}	1439	}
959		1440
960	sub Math::BigFloat::TO_CBOR {	1441	sub Math::BigFloat::TO_CBOR {
961	my ($m, $e) = $_[0]->parts;	1442	my ($m, $e) = $_[0]->parts;
		1443
		1444	-9223372036854775808 <= $e && $e <= 18446744073709551615
962	CBOR::XS::tag 4, [$e->numify, $m]	1445	? tag 4, [$e->numify, $m]
		1446	: tag 264, [$e, $m]
		1447	}
		1448
		1449	sub Math::BigRat::TO_CBOR {
		1450	my ($n, $d) = $_[0]->parts;
		1451
		1452	# older versions of BigRat need *1, as they not always return numbers
		1453
		1454	$d*1 == 1
		1455	? $n*1
		1456	: tag 30, [$n1, $d1]
		1457	}
		1458
		1459	sub Time::Piece::TO_CBOR {
		1460	tag 1, 0 + $_[0]->epoch
963	}	1461	}
964		1462
965	XSLoader::load "CBOR::XS", $VERSION;	1463	XSLoader::load "CBOR::XS", $VERSION;
966		1464
967	=head1 SEE ALSO	1465	=head1 SEE ALSO

Diff Legend

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

Comparing CBOR-XS/XS.pm (file contents): Revision 1.28 by root, Thu Nov 28 16:09:04 2013 UTC vs. Revision 1.73 by root, Sun Nov 29 21:35:51 2020 UTC

Diff Legend

Comparing CBOR-XS/XS.pm (file contents):
Revision 1.28 by root, Thu Nov 28 16:09:04 2013 UTC vs.
Revision 1.73 by root, Sun Nov 29 21:35:51 2020 UTC