--- CBOR-XS/XS.pm 2013/12/01 14:30:52 1.33 +++ CBOR-XS/XS.pm 2016/04/24 09:11:14 1.50 @@ -66,7 +66,7 @@ use common::sense; -our $VERSION = 1.1; +our $VERSION = 1.41; our @ISA = qw(Exporter); our @EXPORT = qw(encode_cbor decode_cbor); @@ -220,8 +220,13 @@ If C<$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 decoded properly if present. +references will always be encoded properly if present. =item $cbor = $cbor->pack_strings ([$enable]) @@ -335,6 +340,70 @@ =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 @@ -414,7 +483,7 @@ Perl hash references become CBOR maps. As there is no inherent ordering in hash keys (or CBOR maps), they will usually be encoded in a pseudo-random -order. This order can be different each time a hahs is encoded. +order. This order can be different each time a hash is encoded. Currently, tied hashes will use the indefinite-length format, while normal hashes will use the fixed-length format. @@ -747,7 +816,7 @@ objects using the C methods (the L object serialisation protocol). See L for details. -=item 28, 29 (shareable, sharedref, L ) +=item 28, 29 (shareable, sharedref, L) These tags are automatically decoded when encountered (and they do not result in a cyclic data structure, see C), resulting in @@ -767,7 +836,7 @@ to be supported in the encoder. The decoder, however, will decode these values as shared values. -=item 256, 25 (stringref-namespace, stringref, L ) +=item 256, 25 (stringref-namespace, stringref, L) These tags are automatically decoded when encountered. They are only encoded, however, when C is enabled. @@ -801,6 +870,15 @@ =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 @@ -832,48 +910,6 @@ =cut -our %FILTER = ( - # 0 # rfc4287 datetime, utf-8 - # 1 # unix timestamp, any - - 2 => sub { # pos bigint - require Math::BigInt; - Math::BigInt->new ("0x" . unpack "H*", pop) - }, - - 3 => sub { # neg bigint - require Math::BigInt; - -Math::BigInt->new ("0x" . unpack "H*", pop) - }, - - 4 => sub { # decimal fraction, array - require Math::BigFloat; - Math::BigFloat->new ($_[1][1] . "E" . $_[1][0]) - }, - - 5 => sub { # bigfloat, array - require Math::BigFloat; - scalar Math::BigFloat->new ($_[1][1])->blsft ($_[1][0], 2) - }, - - 21 => sub { pop }, # expected conversion to base64url encoding - 22 => sub { pop }, # expected conversion to base64 encoding - 23 => sub { pop }, # expected conversion to base16 encoding - - # 24 # embedded cbor, byte string - - 32 => sub { - require URI; - URI->new (pop) - }, - - # 33 # base64url rfc4648, utf-8 - # 34 # base64 rfc46484, utf-8 - # 35 # regex pcre/ecma262, utf-8 - # 36 # mime message rfc2045, utf-8 -); - - =head1 CBOR and JSON CBOR is supposed to implement a superset of the JSON data model, and is, @@ -946,7 +982,8 @@ =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 +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 be truncated, corrupted, or otherwise not decoded correctly. This also includes string, array and map sizes that are stored as 64 bit integers. @@ -974,8 +1011,33 @@ =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 incompatible. 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; @@ -994,7 +1056,7 @@ 5 => sub { # bigfloat, array require Math::BigFloat; - scalar Math::BigFloat->new ($_[1][1])->blsft ($_[1][0], 2) + scalar Math::BigFloat->new ($_[1][1]) * Math::BigFloat->new (2)->bpow ($_[1][0]) }, 21 => sub { pop }, # expected conversion to base64url encoding @@ -1021,7 +1083,7 @@ 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 { @@ -1030,13 +1092,17 @@ } 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;