--- CBOR-XS/XS.pm 2013/11/28 16:09:04 1.28 +++ CBOR-XS/XS.pm 2014/01/05 14:24:54 1.40 @@ -50,9 +50,9 @@ L. In addition to the core CBOR data format, this module implements a -number of extensions, to support cyclic and shared data structures (see -C), string deduplication (see C) and scalar -references (always enabled). +number of extensions, to support cyclic and shared data structures +(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. @@ -66,7 +66,7 @@ use common::sense; -our $VERSION = '1.0'; +our $VERSION = 1.25; our @ISA = qw(Exporter); our @EXPORT = qw(encode_cbor decode_cbor); @@ -182,7 +182,8 @@ 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. +structures (which need C to ne enabled to be decoded by this +module). It is recommended to leave it off unless you know your communication partner supports the value sharing extensions to CBOR @@ -192,7 +193,7 @@ 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 -sharable whether or not they are actually shared. +shareable whether or not they are actually shared. At the moment, only targets of references can be shared (e.g. scalars, arrays or hashes pointed to by a reference). Weirder constructs, such as @@ -207,6 +208,21 @@ This option does not affect C in any way - shared values and references will always be decoded properly if present. +=item $cbor = $cbor->allow_cycles ([$enable]) + +=item $enabled = $cbor->get_allow_cycles + +If C<$enable> is true (or missing), then C will happily decode +self-referential (cyclic) data structures. By default these will not be +decoded, as they need manual cleanup to avoid memory leaks, so code that +isn't prepared for this will not leak memory. + +If C<$enable> is false (the default), then C will throw an error +when it encounters a self-referential/cyclic data structure. + +This option does not affect C in any way - shared values and +references will always be decoded properly if present. + =item $cbor = $cbor->pack_strings ([$enable]) =item $enabled = $cbor->get_pack_strings @@ -228,6 +244,31 @@ This option does not affect C in any way - string references will always be decoded properly if present. +=item $cbor = $cbor->validate_utf8 ([$enable]) + +=item $enabled = $cbor->get_validate_utf8 + +If C<$enable> is true (or missing), then C will validate that +elements (text strings) containing UTF-8 data in fact contain valid UTF-8 +data (instead of blindly accepting it). This validation obviously takes +extra time during decoding. + +The concept of "valid UTF-8" used is perl's concept, which is a superset +of the official UTF-8. + +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. + +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 +so forgiving, so it's recommended to turn on this setting if you receive +untrusted CBOR. + +This option does not affect C in any way - strings that are +supposedly valid UTF-8 will simply be dumped into the resulting CBOR +string without checking whether that is, in fact, true or not. + =item $cbor = $cbor->filter ([$cb->($tag, $value)]) =item $cb_or_undef = $cbor->get_filter @@ -294,6 +335,70 @@ =back +=head2 INCREMENTAL PARSING + +In some cases, there is the need for incremental parsing of JSON +texts. While this module always has to keep both CBOR text and resulting +Perl data structure in memory at one time, it does allow you to parse a +CBOR stream incrementally, using a similar to using "decode_prefix" to see +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, +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. + +A typical use case would be a network protocol that consists of sending +and receiving CBOR-encoded messages. The solution that works with CBOR and +about anything else is by prepending a length to every CBOR value, so the +receiver knows how many octets to read. More compact (and slightly slower) +would be to just send CBOR values back-to-back, as C knows where +a CBOR value ends, and doesn't need an explicit length. + +The following methods help with this: + +=over 4 + +=item @decoded = $cbor->incr_parse ($buffer) + +This method attempts to decode exactly one CBOR value from the beginning +of the given C<$buffer>. The value is removed from the C<$buffer> on +success. When C<$buffer> doesn't contain a complete value yet, it returns +nothing. Finally, when the C<$buffer> doesn't start with something +that could ever be a valid CBOR value, it raises an exception, just as +C would. In the latter case the decoder state is undefined and +must be reset before being able to parse further. + +This method modifies the C<$buffer> in place. When no CBOR value can be +decoded, the decoder stores the current string offset. On the next call, +continues decoding at the place where it stopped before. For this to make +sense, the C<$buffer> must begin with the same octets as on previous +unsuccessful calls. + +You can call this method in scalar context, in which case it either +returns a decoded value or C. This makes it impossible to +distinguish between CBOR null values (which decode to C) and an +unsuccessful decode, which is often acceptable. + +=item @decoded = $cbor->incr_parse_multiple ($buffer) + +Same as C, but attempts to decode as many CBOR values as +possible in one go, instead of at most one. Calls to C and +C can be interleaved. + +=item $cbor->incr_reset + +Resets the incremental decoder. This throws away any saved state, so that +subsequent calls to C or C start to parse +a new CBOR value from the beginning of the C<$buffer> again. + +This method can be caled at any time, but it I be called if you want +to change your C<$buffer> or there was a decoding error and you want to +reuse the C<$cbor> object for future incremental parsings. + +=back + =head1 MAPPING @@ -467,10 +572,16 @@ =head2 OBJECT SERIALISATION +This module implements both a CBOR-specific and the generic +L object serialisation protocol. The following +subsections explain both methods. + +=head3 ENCODING + This module knows two way to serialise a Perl object: The CBOR-specific way, and the generic way. -Whenever the encoder encounters a Perl object that it cnanot serialise +Whenever the encoder encounters a Perl object that it cannot serialise directly (most of them), it will first look up the C method on it. @@ -486,11 +597,18 @@ more). These will be encoded as CBOR perl object, together with the classname. +These methods I change the data structure that is being +serialised. Failure to comply to this can result in memory corruption - +and worse. + If an object supports neither C nor C, encoding will fail with an error. -Objects encoded via C cannot be automatically decoded, but -objects encoded via C can be decoded using the following protocol: +=head3 DECODING + +Objects encoded via C cannot (normally) be automatically decoded, +but objects encoded via C can be decoded using the following +protocol: When an encoded CBOR perl object is encountered by the decoder, it will look up the C method, by using the stored classname, and will fail @@ -500,7 +618,7 @@ as first argument, the constant string C as second argument, and all values returned by C as remaining arguments. -=head4 EXAMPLES +=head3 EXAMPLES Here is an example C method: @@ -693,11 +811,25 @@ objects using the C methods (the L object serialisation protocol). See L for details. -=item 28, 29 (sharable, sharedref, L ) +=item 28, 29 (shareable, sharedref, L ) -These tags are automatically decoded when encountered, resulting in +These tags are automatically decoded when encountered (and they do not +result in a cyclic data structure, see C), resulting in shared values in the decoded object. They are only encoded, however, when -C is enabled. +C is enabled. + +Not all shared values can be successfully decoded: values that reference +themselves will I decode as C (this is not the same +as a reference pointing to itself, which will be represented as a value +that contains an indirect reference to itself - these will be decoded +properly). + +Note that considerably more shared value data structures can be decoded +than will be encoded - currently, only values pointed to by references +will be shared, others will not. While non-reference shared values can be +generated in Perl with some effort, they were considered too unimportant +to be supported in the encoder. The decoder, however, will decode these +values as shared values. =item 256, 25 (stringref-namespace, stringref, L ) @@ -733,6 +865,15 @@ =over 4 +=item 0, 1 (date/time string, seconds since the epoch) + +These tags are decoded into L objects. The corresponding +C method always encodes into tag 1 values currently. + +The L API is generally surprisingly bad, and fractional +seconds are only accidentally kept intact, so watch out. On the plus side, +the module comes with perl since 5.10, which has to count for something. + =item 2, 3 (positive/negative bignum) These tags are decoded into L objects. The corresponding @@ -875,6 +1016,15 @@ Strict mode and canonical mode are not implemented. +=head1 LIMITATIONS ON PERLS WITHOUT 64-BIT INTEGER SUPPORT + +On perls that were built without 64 bit integer support (these are rare +nowadays, even on 32 bit architectures), support for any kind of 64 bit +integer 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. + + =head1 THREADS This module is I guaranteed to be thread safe and there are no @@ -897,8 +1047,33 @@ =cut our %FILTER = ( - # 0 # rfc4287 datetime, utf-8 - # 1 # unix timestamp, any + 0 => sub { # rfc4287 datetime, utf-8 + require Time::Piece; + # Time::Piece::Strptime uses the "incredibly flexible date parsing routine" + # from FreeBSD, which can't parse ISO 8601, RFC3339, RFC4287 or much of anything + # else either. Whats incredibe over standard strptime totally escapes me. + # doesn't do fractional times, either. sigh. + # In fact, it's all a lie, it uses whatever strptime it wants, and of course, + # they are all incomptible. The openbsd one simply ignores %z (but according to the + # docs, it would be much more incredibly flexible indeed. If it worked, that is.). + scalar eval { + my $s = $_[1]; + + $s =~ s/Z$/+00:00/; + $s =~ s/(\.[0-9]+)?([+-][0-9][0-9]):([0-9][0-9])$// + or die; + + my $b = $1 - ($2 * 60 + $3) * 60; # fractional part + offset. hopefully + my $d = Time::Piece->strptime ($s, "%Y-%m-%dT%H:%M:%S"); + + Time::Piece::gmtime ($d->epoch + $b) + } || die "corrupted CBOR date/time string ($_[0])"; + }, + + 1 => sub { # seconds since the epoch, possibly fractional + require Time::Piece; + scalar Time::Piece::gmtime (pop) + }, 2 => sub { # pos bigint require Math::BigInt; @@ -944,7 +1119,7 @@ sub URI::TO_CBOR { my $uri = $_[0]->as_string; utf8::upgrade $uri; - CBOR::XS::tag 32, $uri + tag 32, $uri } sub Math::BigInt::TO_CBOR { @@ -953,13 +1128,17 @@ } else { my $hex = substr $_[0]->as_hex, 2; $hex = "0$hex" if 1 & length $hex; # sigh - CBOR::XS::tag $_[0] >= 0 ? 2 : 3, pack "H*", $hex + tag $_[0] >= 0 ? 2 : 3, pack "H*", $hex } } sub Math::BigFloat::TO_CBOR { my ($m, $e) = $_[0]->parts; - CBOR::XS::tag 4, [$e->numify, $m] + tag 4, [$e->numify, $m] +} + +sub Time::Piece::TO_CBOR { + tag 1, 0 + $_[0]->epoch } XSLoader::load "CBOR::XS", $VERSION;