add option to not parse beyond end of structure (ipld#435)

codec/dagjson/nongreedy_test.go

@@ -0,0 +1,42 @@
+package dagjson
+
+import (
+	"bytes"
+	"testing"
+
+	"github.com/ipld/go-ipld-prime/datamodel"
+	"github.com/ipld/go-ipld-prime/node/basicnode"
+)
+
+func TestNonGreedy(t *testing.T) {
+	buf := bytes.NewBufferString(`{"a": 1}{"b": 2}`)
+	opts := DecodeOptions{
+		ParseLinks:         false,
+		ParseBytes:         false,
+		DontParseBeyondEnd: true,
+	}
+	nb1 := basicnode.Prototype.Map.NewBuilder()
+	err := opts.Decode(nb1, buf)
+	if err != nil {
+		t.Fatalf("first decode (%v)", err)
+	}
+	n1 := nb1.Build()
+	if n1.Kind() != datamodel.Kind_Map {
+		t.Errorf("expecting a map")
+	}
+	if _, err := n1.LookupByString("a"); err != nil {
+		t.Fatalf("missing fist key")
+	}
+	nb2 := basicnode.Prototype.Map.NewBuilder()
+	err = opts.Decode(nb2, buf)
+	if err != nil {
+		t.Fatalf("second decode (%v)", err)
+	}
+	n2 := nb2.Build()
+	if n2.Kind() != datamodel.Kind_Map {
+		t.Errorf("expecting a map")
+	}
+	if _, err := n2.LookupByString("b"); err != nil {
+		t.Fatalf("missing second key")
+	}
+}

codec/dagjson/unmarshal.go

@@ -32,6 +32,13 @@ type DecodeOptions struct {
 	// If true, parse DAG-JSON `{"/":{"bytes":"base64 bytes..."}}` as a Bytes kind
 	// node rather than nested plain maps
 	ParseBytes bool
+
+	// If true, the decoder stops reading from the stream at the end of the JSON structure.
+	// i.e. it does not slurp remaining whitespaces and EOF.
+	// As per standard IPLD behavior, the parser considers the entire block to be
+	// part of the JSON structure and will error if there is extraneous
+	// non-whitespace data.
+	DontParseBeyondEnd bool
 }
 
 // Decode deserializes data from the given io.Reader and feeds it into the given datamodel.NodeAssembler.
@@ -43,6 +50,9 @@ func (cfg DecodeOptions) Decode(na datamodel.NodeAssembler, r io.Reader) error {
 	if err != nil {
 		return err
 	}
+	if cfg.DontParseBeyondEnd {
+		return nil
+	}
 	// Slurp any remaining whitespace.
 	//  This behavior may be due for review.
 	//  (This is relevant if our reader is tee'ing bytes to a hasher, and