Merge pull request #153 from ipld/codec/cbor

implement non-dag cbor codec

Author: warpfork

codec/cbor/multicodec.go

@@ -0,0 +1,29 @@
+package cbor
+
+import (
+	"io"
+
+	"github.com/polydawn/refmt/cbor"
+
+	"github.com/ipld/go-ipld-prime"
+	"github.com/ipld/go-ipld-prime/codec/dagcbor"
+	"github.com/ipld/go-ipld-prime/multicodec"
+)
+
+var (
+	_ ipld.Decoder = Decode
+	_ ipld.Encoder = Encode
+)
+
+func init() {
+	multicodec.RegisterEncoder(0x51, Encode)
+	multicodec.RegisterDecoder(0x51, Decode)
+}
+
+func Decode(na ipld.NodeAssembler, r io.Reader) error {
+	return dagcbor.Unmarshal(na, cbor.NewDecoder(cbor.DecodeOptions{}, r), false)
+}
+
+func Encode(n ipld.Node, w io.Writer) error {
+	return dagcbor.Marshal(n, cbor.NewEncoder(w), false)
+}

codec/dagcbor/marshal.go

@@ -13,12 +13,12 @@ import (
 // This should be identical to the general feature in the parent package,
 // except for the `case ipld.Kind_Link` block,
 // which is dag-cbor's special sauce for schemafree links.
-func Marshal(n ipld.Node, sink shared.TokenSink) error {
+func Marshal(n ipld.Node, sink shared.TokenSink, allowLinks bool) error {
 	var tk tok.Token
-	return marshal(n, &tk, sink)
+	return marshal(n, &tk, sink, allowLinks)
 }
 
-func marshal(n ipld.Node, tk *tok.Token, sink shared.TokenSink) error {
+func marshal(n ipld.Node, tk *tok.Token, sink shared.TokenSink, allowLinks bool) error {
 	switch n.Kind() {
 	case ipld.Kind_Invalid:
 		return fmt.Errorf("cannot traverse a node that is absent")
@@ -47,7 +47,7 @@ func marshal(n ipld.Node, tk *tok.Token, sink shared.TokenSink) error {
 			if _, err := sink.Step(tk); err != nil {
 				return err
 			}
-			if err := marshal(v, tk, sink); err != nil {
+			if err := marshal(v, tk, sink, allowLinks); err != nil {
 				return err
 			}
 		}
@@ -69,7 +69,7 @@ func marshal(n ipld.Node, tk *tok.Token, sink shared.TokenSink) error {
 			if err != nil {
 				return err
 			}
-			if err := marshal(v, tk, sink); err != nil {
+			if err := marshal(v, tk, sink, allowLinks); err != nil {
 				return err
 			}
 		}
@@ -123,6 +123,9 @@ func marshal(n ipld.Node, tk *tok.Token, sink shared.TokenSink) error {
 		_, err = sink.Step(tk)
 		return err
 	case ipld.Kind_Link:
+		if !allowLinks {
+			return fmt.Errorf("cannot Marshal ipld links to CBOR")
+		}
 		v, err := n.AsLink()
 		if err != nil {
 			return err

codec/dagcbor/multicodec.go

@@ -28,7 +28,7 @@ func Decode(na ipld.NodeAssembler, r io.Reader) error {
 		return na2.DecodeDagCbor(r)
 	}
 	// Okay, generic builder path.
-	return Unmarshal(na, cbor.NewDecoder(cbor.DecodeOptions{}, r))
+	return Unmarshal(na, cbor.NewDecoder(cbor.DecodeOptions{}, r), true)
 }
 
 func Encode(n ipld.Node, w io.Writer) error {
@@ -40,5 +40,5 @@ func Encode(n ipld.Node, w io.Writer) error {
 		return n2.EncodeDagCbor(w)
 	}
 	// Okay, generic inspection path.
-	return Marshal(n, cbor.NewEncoder(w))
+	return Marshal(n, cbor.NewEncoder(w), true)
 }

codec/dagcbor/unmarshal.go

@@ -27,16 +27,16 @@ const (
 // except for the `case tok.TBytes` block,
 // which has dag-cbor's special sauce for detecting schemafree links.
 
-func Unmarshal(na ipld.NodeAssembler, tokSrc shared.TokenSource) error {
+func Unmarshal(na ipld.NodeAssembler, tokSrc shared.TokenSource, allowLinks bool) error {
 	// Have a gas budget, which will be decremented as we allocate memory, and an error returned when execeeded (or about to be exceeded).
 	//  This is a DoS defense mechanism.
 	//  It's *roughly* in units of bytes (but only very, VERY roughly) -- it also treats words as 1 in many cases.
 	// FUTURE: this ought be configurable somehow.  (How, and at what granularity though?)
 	var gas int = 1048576 * 10
-	return unmarshal1(na, tokSrc, &gas)
+	return unmarshal1(na, tokSrc, &gas, allowLinks)
 }
 
-func unmarshal1(na ipld.NodeAssembler, tokSrc shared.TokenSource, gas *int) error {
+func unmarshal1(na ipld.NodeAssembler, tokSrc shared.TokenSource, gas *int, allowLinks bool) error {
 	var tk tok.Token
 	done, err := tokSrc.Step(&tk)
 	if err != nil {
@@ -45,12 +45,12 @@ func unmarshal1(na ipld.NodeAssembler, tokSrc shared.TokenSource, gas *int) erro
 	if done && !tk.Type.IsValue() {
 		return fmt.Errorf("unexpected eof")
 	}
-	return unmarshal2(na, tokSrc, &tk, gas)
+	return unmarshal2(na, tokSrc, &tk, gas, allowLinks)
 }
 
 // starts with the first token already primed.  Necessary to get recursion
 //  to flow right without a peek+unpeek system.
-func unmarshal2(na ipld.NodeAssembler, tokSrc shared.TokenSource, tk *tok.Token, gas *int) error {
+func unmarshal2(na ipld.NodeAssembler, tokSrc shared.TokenSource, tk *tok.Token, gas *int, allowLinks bool) error {
 	// FUTURE: check for schema.TypedNodeBuilder that's going to parse a Link (they can slurp any token kind they want).
 	switch tk.Type {
 	case tok.TMapOpen:
@@ -97,7 +97,7 @@ func unmarshal2(na ipld.NodeAssembler, tokSrc shared.TokenSource, tk *tok.Token,
 			if err != nil { // return in error if the key was rejected
 				return err
 			}
-			err = unmarshal1(mva, tokSrc, gas)
+			err = unmarshal1(mva, tokSrc, gas, allowLinks)
 			if err != nil { // return in error if some part of the recursion errored
 				return err
 			}
@@ -140,7 +140,7 @@ func unmarshal2(na ipld.NodeAssembler, tokSrc shared.TokenSource, tk *tok.Token,
 				if observedLen > expectLen {
 					return fmt.Errorf("unexpected continuation of array elements beyond declared length")
 				}
-				err := unmarshal2(la.AssembleValue(), tokSrc, tk, gas)
+				err := unmarshal2(la.AssembleValue(), tokSrc, tk, gas, allowLinks)
 				if err != nil { // return in error if some part of the recursion errored
 					return err
 				}
@@ -166,14 +166,17 @@ func unmarshal2(na ipld.NodeAssembler, tokSrc shared.TokenSource, tk *tok.Token,
 		}
 		switch tk.Tag {
 		case linkTag:
+			if !allowLinks {
+				return fmt.Errorf("unhandled cbor tag %d", tk.Tag)
+			}
 			if len(tk.Bytes) < 1 || tk.Bytes[0] != 0 {
 				return ErrInvalidMultibase
 			}
 			elCid, err := cid.Cast(tk.Bytes[1:])
 			if err != nil {
 				return err
 			}
-			return na.AssignLink(cidlink.Link{elCid})
+			return na.AssignLink(cidlink.Link{Cid: elCid})
 		default:
 			return fmt.Errorf("unhandled cbor tag %d", tk.Tag)
 		}