--- CBOR-XS/XS.pm 2016/04/24 09:11:14 1.50 +++ CBOR-XS/XS.pm 2023/09/08 20:03:06 1.89 @@ -40,6 +40,9 @@ data later and speed is less important you might want to compare both formats first). +The primary goal of this module is to be I and the secondary goal +is to be I. To reach the latter goal it was written in C. + To give you a general idea about speed, with texts in the megabyte range, C usually encodes roughly twice as fast as L or L and decodes about 15%-30% faster than those. The shorter the @@ -54,9 +57,6 @@ (see C and C), string deduplication (see C) and scalar references (always enabled). -The primary goal of this module is to be I and the secondary goal -is to be I. To reach the latter goal it was written in C. - See MAPPING, below, on how CBOR::XS maps perl values to CBOR values and vice versa. @@ -66,7 +66,7 @@ use common::sense; -our $VERSION = 1.41; +our $VERSION = 1.87; our @ISA = qw(Exporter); our @EXPORT = qw(encode_cbor decode_cbor); @@ -115,6 +115,33 @@ my $cbor = CBOR::XS->new->encode ({a => [1,2]}); +=item $cbor = new_safe CBOR::XS + +Create a new, safe/secure CBOR::XS object. This is similar to C, +but configures the coder object to be safe to use with untrusted +data. Currently, this is equivalent to: + + my $cbor = CBOR::XS + ->new + ->validate_utf8 + ->forbid_objects + ->filter (\&CBOR::XS::safe_filter) + ->max_size (1e8); + +But is more future proof (it is better to crash because of a change than +to be exploited in other ways). + +=cut + +sub new_safe { + CBOR::XS + ->new + ->validate_utf8 + ->forbid_objects + ->filter (\&CBOR::XS::safe_filter) + ->max_size (1e8) +} + =item $cbor = $cbor->max_depth ([$maximum_nesting_depth]) =item $max_depth = $cbor->get_max_depth @@ -139,7 +166,7 @@ been chosen to be as large as typical operating systems allow without crashing. -See SECURITY CONSIDERATIONS, below, for more info on why this is useful. +See L, below, for more info on why this is useful. =item $cbor = $cbor->max_size ([$maximum_string_size]) @@ -154,7 +181,7 @@ If no argument is given, the limit check will be deactivated (same as when C<0> is specified). -See SECURITY CONSIDERATIONS, below, for more info on why this is useful. +See L, below, for more info on why this is useful. =item $cbor = $cbor->allow_unknown ([$enable]) @@ -182,7 +209,7 @@ This means that such values will only be encoded once, and will not result in a deep cloning of the value on decode, in decoders supporting the value sharing extension. This also makes it possible to encode cyclic data -structures (which need C to ne enabled to be decoded by this +structures (which need C to be enabled to be decoded by this module). It is recommended to leave it off unless you know your @@ -191,8 +218,8 @@ resulting data structure might be unusable. Detecting shared values incurs a runtime overhead when values are encoded -that have a reference counter large than one, and might unnecessarily -increase the encoded size, as potentially shared values are encode as +that have a reference counter larger than one, and might unnecessarily +increase the encoded size, as potentially shared values are encoded as shareable whether or not they are actually shared. At the moment, only targets of references can be shared (e.g. scalars, @@ -220,14 +247,45 @@ If C<$enable> is false (the default), then C will throw an error when it encounters a self-referential/cyclic data structure. -FUTURE DIRECTION: the motivation behind this option is to avoid I -cycles - future versions of this module might chose to decode cyclic data -structures using weak references when this option is off, instead of -throwing an error. +This option does not affect C in any way - shared values and +references will always be encoded properly if present. + +=item $cbor = $cbor->allow_weak_cycles ([$enable]) + +=item $enabled = $cbor->get_allow_weak_cycles + +This works like C in that it allows the resulting data +structures to contain cycles, but unlike C, those cyclic +rreferences will be weak. That means that code that recurrsively walks +the data structure must be prepared with cycles, but at least not special +precautions must be implemented to free these data structures. + +Only those references leading to actual cycles will be weakened - other +references, e.g. when the same hash or arrray is referenced multiple times +in an arrray, will be normal references. This option does not affect C in any way - shared values and references will always be encoded properly if present. +=item $cbor = $cbor->forbid_objects ([$enable]) + +=item $enabled = $cbor->get_forbid_objects + +Disables the use of the object serialiser protocol. + +If C<$enable> is true (or missing), then C will will throw an +exception when it encounters perl objects that would be encoded using the +perl-object tag (26). When C encounters such tags, it will fall +back to the general filter/tagged logic as if this were an unknown tag (by +default resulting in a C object). + +If C<$enable> is false (the default), then C will use the +L object serialisation protocol to serialise objects +into perl-object tags, and C will do the same to decode such tags. + +See L, below, for more info on why forbidding this +protocol can be useful. + =item $cbor = $cbor->pack_strings ([$enable]) =item $enabled = $cbor->get_pack_strings @@ -249,6 +307,51 @@ This option does not affect C in any way - string references will always be decoded properly if present. +=item $cbor = $cbor->text_keys ([$enable]) + +=item $enabled = $cbor->get_text_keys + +If C<$enabled> is true (or missing), then C will encode all +perl hash keys as CBOR text strings/UTF-8 string, upgrading them as needed. + +If C<$enable> is false (the default), then C will encode hash keys +normally - upgraded perl strings (strings internally encoded as UTF-8) as +CBOR text strings, and downgraded perl strings as CBOR byte strings. + +This option does not affect C in any way. + +This option is useful for interoperability with CBOR decoders that don't +treat byte strings as a form of text. It is especially useful as Perl +gives very little control over hash keys. + +Enabling this option can be slow, as all downgraded hash keys that are +encoded need to be scanned and converted to UTF-8. + +=item $cbor = $cbor->text_strings ([$enable]) + +=item $enabled = $cbor->get_text_strings + +This option works similar to C, above, but works on all strings +(including hash keys), so C has no further effect after +enabling C. + +If C<$enabled> is true (or missing), then C will encode all perl +strings as CBOR text strings/UTF-8 strings, upgrading them as needed. + +If C<$enable> is false (the default), then C will encode strings +normally (but see C) - upgraded perl strings (strings +internally encoded as UTF-8) as CBOR text strings, and downgraded perl +strings as CBOR byte strings. + +This option does not affect C in any way. + +This option has similar advantages and disadvantages as C. In +addition, this option effectively removes the ability to automatically +encode byte strings, which might break some C and C +methods that rely on this. + +A workaround is to use explicit type casts, which are unaffected by this option. + =item $cbor = $cbor->validate_utf8 ([$enable]) =item $enabled = $cbor->get_validate_utf8 @@ -263,7 +366,7 @@ If C<$enable> is false (the default), then C will blindly accept UTF-8 data, marking them as valid UTF-8 in the resulting data structure -regardless of whether thats true or not. +regardless of whether that's true or not. Perl isn't too happy about corrupted UTF-8 in strings, but should generally not crash or do similarly evil things. Extensions might be not @@ -295,10 +398,23 @@ creates a C object to hold the tag and the value. When the filter is cleared (the default state), the default filter -function, C, is used. This function simply looks -up the tag in the C<%CBOR::XS::FILTER> hash. If an entry exists it must be -a code reference that is called with tag and value, and is responsible for -decoding the value. If no entry exists, it returns no values. +function, C, is used. This function simply +looks up the tag in the C<%CBOR::XS::FILTER> hash. If an entry exists +it must be a code reference that is called with tag and value, and is +responsible for decoding the value. If no entry exists, it returns no +values. C provides a number of default filter functions already, +the the C<%CBOR::XS::FILTER> hash can be freely extended with more. + +C additionally provides an alternative filter function that is +supposed to be safe to use with untrusted data (which the default filter +might not), called C, which works the same as +the C but uses the C<%CBOR::XS::SAFE_FILTER> variable +instead. It is prepopulated with the tag decoding functions that are +deemed safe (basically the same as C<%CBOR::XS::FILTER> without all +the bignum tags), and can be extended by user code as wlel, although, +obviously, one should be very careful about adding decoding functions +here, since the expectation is that they are safe to use on untrusted +data, after all. Example: decode all tags not handled internally into C objects, with no other special handling (useful when working with @@ -315,6 +431,27 @@ "tag 1347375694 value $value" }; +Example: provide your own filter function that looks up tags in your own +hash: + + my %my_filter = ( + 998347484 => sub { + my ($tag, $value); + + "tag 998347484 value $value" + }; + ); + + my $coder = CBOR::XS->new->filter (sub { + &{ $my_filter{$_[0]} or return } + }); + + +Example: use the safe filter function (see L for +more considerations on security). + + CBOR::XS->new->filter (\&CBOR::XS::safe_filter)->decode ($cbor_data); + =item $cbor_data = $cbor->encode ($perl_scalar) Converts the given Perl data structure (a scalar value) to its CBOR @@ -333,7 +470,8 @@ This is useful if your CBOR texts are not delimited by an outer protocol and you need to know where the first CBOR string ends amd the next one -starts. +starts - CBOR strings are self-delimited, so it is possible to concatenate +CBOR strings without any delimiters or size fields and recover their data. CBOR::XS->new->decode_prefix ("......") => ("...", 3) @@ -349,7 +487,7 @@ if a full CBOR object is available, but is much more efficient. It basically works by parsing as much of a CBOR string as possible - if -the CBOR data is not complete yet, the pasrer will remember where it was, +the CBOR data is not complete yet, the parser will remember where it was, to be able to restart when more data has been accumulated. Once enough data is available to either decode a complete CBOR value or raise an error, a real decode will be attempted. @@ -398,7 +536,7 @@ subsequent calls to C or C start to parse a new CBOR value from the beginning of the C<$buffer> again. -This method can be caled at any time, but it I be called if you want +This method can be called at any time, but it I be called if you want to change your C<$buffer> or there was a decoding error and you want to reuse the C<$cbor> object for future incremental parsings. @@ -511,8 +649,7 @@ =item Types::Serialiser::true, Types::Serialiser::false, Types::Serialiser::error These special values become CBOR true, CBOR false and CBOR undefined -values, respectively. You can also use C<\1>, C<\0> and C<\undef> directly -if you want. +values, respectively. =item other blessed objects @@ -546,15 +683,19 @@ $x .= ""; # another, more awkward way to stringify print $x; # perl does it for you, too, quite often -You can force whether a string ie encoded as byte or text string by using -C and C): +You can force whether a string is encoded as byte or text string by using +C and C (if C is disabled). utf8::upgrade $x; # encode $x as text string utf8::downgrade $x; # encode $x as byte string +More options are available, see L, below, and the C +and C options. + Perl doesn't define what operations up- and downgrade strings, so if the difference between byte and text is important, you should up- or downgrade -your string as late as possible before encoding. +your string as late as possible before encoding. You can also force the +use of CBOR text strings by using C or C. You can force the type to be a CBOR number by numifying it: @@ -575,6 +716,107 @@ =back +=head2 TYPE CASTS + +B: As an experimental extension, C allows you to +force specific CBOR types to be used when encoding. That allows you to +encode types not normally accessible (e.g. half floats) as well as force +string types even when C is in effect. + +Type forcing is done by calling a special "cast" function which keeps a +copy of the value and returns a new value that can be handed over to any +CBOR encoder function. + +The following casts are currently available (all of which are unary +operators, that is, have a prototype of C<$>): + +=over + +=item CBOR::XS::as_int $value + +Forces the value to be encoded as some form of (basic, not bignum) integer +type. + +=item CBOR::XS::as_text $value + +Forces the value to be encoded as (UTF-8) text values. + +=item CBOR::XS::as_bytes $value + +Forces the value to be encoded as a (binary) string value. + +Example: encode a perl string as binary even though C is in +effect. + + CBOR::XS->new->text_strings->encode ([4, "text", CBOR::XS::bytes "bytevalue"]); + +=item CBOR::XS::as_bool $value + +Converts a Perl boolean (which can be any kind of scalar) into a CBOR +boolean. Strictly the same, but shorter to write, than: + + $value ? Types::Serialiser::true : Types::Serialiser::false + +=item CBOR::XS::as_float16 $value + +Forces half-float (IEEE 754 binary16) encoding of the given value. + +=item CBOR::XS::as_float32 $value + +Forces single-float (IEEE 754 binary32) encoding of the given value. + +=item CBOR::XS::as_float64 $value + +Forces double-float (IEEE 754 binary64) encoding of the given value. + +=item CBOR::XS::as_cbor $cbor_text + +Not a type cast per-se, this type cast forces the argument to be encoded +as-is. This can be used to embed pre-encoded CBOR data. + +Note that no checking on the validity of the C<$cbor_text> is done - it's +the callers responsibility to correctly encode values. + +=item CBOR::XS::as_map [key => value...] + +Treat the array reference as key value pairs and output a CBOR map. This +allows you to generate CBOR maps with arbitrary key types (or, if you +don't care about semantics, duplicate keys or pairs in a custom order), +which is otherwise hard to do with Perl. + +The single argument must be an array reference with an even number of +elements. + +Note that only the reference to the array is copied, the array itself is +not. Modifications done to the array before calling an encoding function +will be reflected in the encoded output. + +Example: encode a CBOR map with a string and an integer as keys. + + encode_cbor CBOR::XS::as_map [string => "value", 5 => "value"] + +=back + +=cut + +sub CBOR::XS::as_cbor ($) { bless [$_[0], 0, undef], CBOR::XS::Tagged:: } +sub CBOR::XS::as_int ($) { bless [$_[0], 1, undef], CBOR::XS::Tagged:: } +sub CBOR::XS::as_bytes ($) { bless [$_[0], 2, undef], CBOR::XS::Tagged:: } +sub CBOR::XS::as_text ($) { bless [$_[0], 3, undef], CBOR::XS::Tagged:: } +sub CBOR::XS::as_float16 ($) { bless [$_[0], 4, undef], CBOR::XS::Tagged:: } +sub CBOR::XS::as_float32 ($) { bless [$_[0], 5, undef], CBOR::XS::Tagged:: } +sub CBOR::XS::as_float64 ($) { bless [$_[0], 6, undef], CBOR::XS::Tagged:: } + +sub CBOR::XS::as_bool ($) { $_[0] ? $Types::Serialiser::true : $Types::Serialiser::false } + +sub CBOR::XS::as_map ($) { + ARRAY:: eq ref $_[0] + and $#{ $_[0] } & 1 + or do { require Carp; Carp::croak ("CBOR::XS::as_map only acepts array references with an even number of elements, caught") }; + + bless [$_[0], 7, undef], CBOR::XS::Tagged:: +} + =head2 OBJECT SERIALISATION This module implements both a CBOR-specific and the generic @@ -665,7 +907,6 @@ sub URI::THAW { my ($class, $serialiser, $uri) = @_; - $class->new ($uri) } @@ -806,7 +1047,7 @@ =head2 ENFORCED TAGS These tags are always handled when decoding, and their handling cannot be -overriden by the user. +overridden by the user. =over 4 @@ -844,7 +1085,7 @@ =item 22098 (indirection, L) This tag is automatically generated when a reference are encountered (with -the exception of hash and array refernces). It is converted to a reference +the exception of hash and array references). It is converted to a reference when decoding. =item 55799 (self-describe CBOR, RFC 7049) @@ -857,7 +1098,7 @@ =head2 NON-ENFORCED TAGS These tags have default filters provided when decoding. Their handling can -be overriden by changing the C<%CBOR::XS::FILTER> entry for the tag, or by +be overridden by changing the C<%CBOR::XS::FILTER> entry for the tag, or by providing a custom C callback when decoding. When they result in decoding into a specific Perl class, the module @@ -885,16 +1126,25 @@ C method encodes "small" bigints into normal CBOR integers, and others into positive/negative CBOR bignums. -=item 4, 5 (decimal fraction/bigfloat) +=item 4, 5, 264, 265 (decimal fraction/bigfloat) Both decimal fractions and bigfloats are decoded into L objects. The corresponding C method I -encodes into a decimal fraction. +encodes into a decimal fraction (either tag 4 or 264). + +NaN and infinities are not encoded properly, as they cannot be represented +in CBOR. -CBOR cannot represent bigfloats with I large exponents - conversion -of such big float objects is undefined. +See L for more info. -Also, NaN and infinities are not encoded properly. +=item 30 (rational numbers) + +These tags are decoded into L objects. The corresponding +C method encodes rational numbers with denominator +C<1> via their numerator only, i.e., they become normal integers or +C. + +See L for more info. =item 21, 22, 23 (expected later JSON conversion) @@ -927,38 +1177,152 @@ =head1 SECURITY CONSIDERATIONS -When you are using CBOR in a protocol, talking to untrusted potentially -hostile creatures requires relatively few measures. +Tl;dr... if you want to decode or encode CBOR from untrusted sources, you +should start with a coder object created via C (which implements +the mitigations explained below): + + my $coder = CBOR::XS->new_safe; + + my $data = $coder->decode ($cbor_text); + my $cbor = $coder->encode ($data); + +Longer version: When you are using CBOR in a protocol, talking to +untrusted potentially hostile creatures requires some thought: + +=over 4 + +=item Security of the CBOR decoder itself + +First and foremost, your CBOR decoder should be secure, that is, should +not have any buffer overflows or similar bugs that could potentially be +exploited. Obviously, this module should ensure that and I am trying hard +on making that true, but you never know. + +=item CBOR::XS can invoke almost arbitrary callbacks during decoding + +CBOR::XS supports object serialisation - decoding CBOR can cause calls +to I C method in I package that exists in your process +(that is, CBOR::XS will not try to load modules, but any existing C +method or function can be called, so they all have to be secure). + +Less obviously, it will also invoke C and C methods - +even if all your C methods are secure, encoding data structures from +untrusted sources can invoke those and trigger bugs in those. + +So, if you are not sure about the security of all the modules you +have loaded (you shouldn't), you should disable this part using +C or using C. + +=item CBOR can be extended with tags that call library code + +CBOR can be extended with tags, and C has a registry of +conversion functions for many existing tags that can be extended via +third-party modules (see the C method). + +If you don't trust these, you should configure the "safe" filter function, +C (C does this), which by default only +includes conversion functions that are considered "safe" by the author +(but again, they can be extended by third party modules). + +Depending on your level of paranoia, you can use the "safe" filter: -First of all, your CBOR decoder should be secure, that is, should not have -any buffer overflows. Obviously, this module should ensure that and I am -trying hard on making that true, but you never know. - -Second, you need to avoid resource-starving attacks. That means you should -limit the size of CBOR data you accept, or make sure then when your -resources run out, that's just fine (e.g. by using a separate process that -can crash safely). The size of a CBOR string in octets is usually a good + $cbor->filter (\&CBOR::XS::safe_filter); + +... your own filter... + + $cbor->filter (sub { ... do your stuffs here ... }); + +... or even no filter at all, disabling all tag decoding: + + $cbor->filter (sub { }); + +This is never a problem for encoding, as the tag mechanism only exists in +CBOR texts. + +=item Resource-starving attacks: object memory usage + +You need to avoid resource-starving attacks. That means you should limit +the size of CBOR data you accept, or make sure then when your resources +run out, that's just fine (e.g. by using a separate process that can +crash safely). The size of a CBOR string in octets is usually a good indication of the size of the resources required to decode it into a Perl -structure. While CBOR::XS can check the size of the CBOR text, it might be -too late when you already have it in memory, so you might want to check -the size before you accept the string. - -Third, CBOR::XS recurses using the C stack when decoding objects and -arrays. The C stack is a limited resource: for instance, on my amd64 -machine with 8MB of stack size I can decode around 180k nested arrays but -only 14k nested CBOR objects (due to perl itself recursing deeply on croak -to free the temporary). If that is exceeded, the program crashes. To be -conservative, the default nesting limit is set to 512. If your process -has a smaller stack, you should adjust this setting accordingly with the -C method. +structure. While CBOR::XS can check the size of the CBOR text (using +C - done by C), it might be too late when you already +have it in memory, so you might want to check the size before you accept +the string. + +As for encoding, it is possible to construct data structures that are +relatively small but result in large CBOR texts (for example by having an +array full of references to the same big data structure, which will all be +deep-cloned during encoding by default). This is rarely an actual issue +(and the worst case is still just running out of memory), but you can +reduce this risk by using C. + +=item Resource-starving attacks: stack overflows + +CBOR::XS recurses using the C stack when decoding objects and arrays. The +C stack is a limited resource: for instance, on my amd64 machine with 8MB +of stack size I can decode around 180k nested arrays but only 14k nested +CBOR objects (due to perl itself recursing deeply on croak to free the +temporary). If that is exceeded, the program crashes. To be conservative, +the default nesting limit is set to 512. If your process has a smaller +stack, you should adjust this setting accordingly with the C +method. + +=item Resource-starving attacks: CPU en-/decoding complexity + +CBOR::XS will use the L, L and +L libraries to represent encode/decode bignums. These can be +very slow (as in, centuries of CPU time) and can even crash your program +(and are generally not very trustworthy). See the next section on bignum +security for details. + +=item Data breaches: leaking information in error messages + +CBOR::XS might leak contents of your Perl data structures in its error +messages, so when you serialise sensitive information you might want to +make sure that exceptions thrown by CBOR::XS will not end up in front of +untrusted eyes. + +=item Something else... Something else could bomb you, too, that I forgot to think of. In that case, you get to keep the pieces. I am always open for hints, though... -Also keep in mind that CBOR::XS might leak contents of your Perl data -structures in its error messages, so when you serialise sensitive -information you might want to make sure that exceptions thrown by CBOR::XS -will not end up in front of untrusted eyes. +=back + + +=head1 BIGNUM SECURITY CONSIDERATIONS + +CBOR::XS provides a C method for both L and +L that tries to encode the number in the simplest possible +way, that is, either a CBOR integer, a CBOR bigint/decimal fraction (tag +4) or an arbitrary-exponent decimal fraction (tag 264). Rational numbers +(L, tag 30) can also contain bignums as members. + +CBOR::XS will also understand base-2 bigfloat or arbitrary-exponent +bigfloats (tags 5 and 265), but it will never generate these on its own. + +Using the built-in L support, encoding and decoding +decimal fractions is generally fast. Decoding bigints can be slow for very +big numbers (tens of thousands of digits, something that could potentially +be caught by limiting the size of CBOR texts), and decoding bigfloats or +arbitrary-exponent bigfloats can be I slow (minutes, decades) +for large exponents (roughly 40 bit and longer). + +Additionally, L can take advantage of other bignum +libraries, such as L, which cannot handle big floats with large +exponents, and might simply abort or crash your program, due to their code +quality. + +This can be a concern if you want to parse untrusted CBOR. If it is, you +might want to disable decoding of tag 2 (bigint) and 3 (negative bigint) +types. You should also disable types 5 and 265, as these can be slow even +without bigints. + +Disabling bigints will also partially or fully disable types that rely on +them, e.g. rational numbers that use bignums. + =head1 CBOR IMPLEMENTATION NOTES @@ -984,9 +1348,10 @@ On perls that were built without 64 bit integer support (these are rare nowadays, even on 32 bit architectures, as all major Perl distributions are built with 64 bit integer support), support for any kind of 64 bit -integer in CBOR is very limited - most likely, these 64 bit values will +value in CBOR is very limited - most likely, these 64 bit values will be truncated, corrupted, or otherwise not decoded correctly. This also -includes string, array and map sizes that are stored as 64 bit integers. +includes string, float, array and map sizes that are stored as 64 bit +integers. =head1 THREADS @@ -1010,6 +1375,11 @@ =cut +# clumsy and slow hv_store-in-hash helper function +sub _hv_store { + $_[0]{$_[1]} = $_[2]; +} + our %FILTER = ( 0 => sub { # rfc4287 datetime, utf-8 require Time::Piece; @@ -1054,11 +1424,26 @@ Math::BigFloat->new ($_[1][1] . "E" . $_[1][0]) }, + 264 => sub { # decimal fraction with arbitrary exponent + require Math::BigFloat; + Math::BigFloat->new ($_[1][1] . "E" . $_[1][0]) + }, + 5 => sub { # bigfloat, array require Math::BigFloat; scalar Math::BigFloat->new ($_[1][1]) * Math::BigFloat->new (2)->bpow ($_[1][0]) }, + 265 => sub { # bigfloat with arbitrary exponent + require Math::BigFloat; + scalar Math::BigFloat->new ($_[1][1]) * Math::BigFloat->new (2)->bpow ($_[1][0]) + }, + + 30 => sub { # rational number + require Math::BigRat; + Math::BigRat->new ("$_[1][0]/$_[1][1]") # separate parameters only work in recent versons + }, + 21 => sub { pop }, # expected conversion to base64url encoding 22 => sub { pop }, # expected conversion to base64 encoding 23 => sub { pop }, # expected conversion to base16 encoding @@ -1076,10 +1461,16 @@ # 36 # mime message rfc2045, utf-8 ); -sub CBOR::XS::default_filter { +sub default_filter { &{ $FILTER{$_[0]} or return } } +our %SAFE_FILTER = map { $_ => $FILTER{$_} } 0, 1, 21, 22, 23, 32; + +sub safe_filter { + &{ $SAFE_FILTER{$_[0]} or return } +} + sub URI::TO_CBOR { my $uri = $_[0]->as_string; utf8::upgrade $uri; @@ -1087,7 +1478,7 @@ } sub Math::BigInt::TO_CBOR { - if ($_[0] >= -2147483648 && $_[0] <= 2147483647) { + if (-2147483648 <= $_[0] && $_[0] <= 2147483647) { $_[0]->numify } else { my $hex = substr $_[0]->as_hex, 2; @@ -1098,7 +1489,20 @@ sub Math::BigFloat::TO_CBOR { my ($m, $e) = $_[0]->parts; - tag 4, [$e->numify, $m] + + -9223372036854775808 <= $e && $e <= 18446744073709551615 + ? tag 4, [$e->numify, $m] + : tag 264, [$e, $m] +} + +sub Math::BigRat::TO_CBOR { + my ($n, $d) = $_[0]->parts; + + # older versions of BigRat need *1, as they not always return numbers + + $d*1 == 1 + ? $n*1 + : tag 30, [$n*1, $d*1] } sub Time::Piece::TO_CBOR {