encoding/json: fix extra data regression under goexperiment.jsonv2

When operating under v1 semantics in the v2 implementation,
a extra data error should take precedence over any semantic error
that could theoretically occur within the value itself.

This change only affects code compiled under goexperiment.jsonv2.

Fixes #74614

Change-Id: I055a606b053fa66b0c766ae205487b8290109285
Reviewed-on: https://go-review.googlesource.com/c/go/+/689919
Reviewed-by: Damien Neil <[email protected]>
Reviewed-by: Michael Knyszek <[email protected]>
Auto-Submit: Michael Knyszek <[email protected]>
LUCI-TryBot-Result: Go LUCI <[email protected]>

Author: dsnet

src/encoding/json/jsontext/decode.go

@@ -776,7 +776,8 @@ func (d *decoderState) ReadValue(flags *jsonwire.ValueFlags) (Value, error) {
 
 // CheckNextValue checks whether the next value is syntactically valid,
 // but does not advance the read offset.
-func (d *decoderState) CheckNextValue() error {
+// If last, it verifies that the stream cleanly terminates with [io.EOF].
+func (d *decoderState) CheckNextValue(last bool) error {
 	d.PeekKind() // populates d.peekPos and d.peekErr
 	pos, err := d.peekPos, d.peekErr
 	d.peekPos, d.peekErr = 0, nil
@@ -787,13 +788,18 @@ func (d *decoderState) CheckNextValue() error {
 	var flags jsonwire.ValueFlags
 	if pos, err := d.consumeValue(&flags, pos, d.Tokens.Depth()); err != nil {
 		return wrapSyntacticError(d, err, pos, +1)
+	} else if last {
+		return d.checkEOF(pos)
 	}
 	return nil
 }
 
 // CheckEOF verifies that the input has no more data.
 func (d *decoderState) CheckEOF() error {
-	switch pos, err := d.consumeWhitespace(d.prevEnd); err {
+	return d.checkEOF(d.prevEnd)
+}
+func (d *decoderState) checkEOF(pos int) error {
+	switch pos, err := d.consumeWhitespace(pos); err {
 	case nil:
 		err := jsonwire.NewInvalidCharacterError(d.buf[pos:], "after top-level value")
 		return wrapSyntacticError(d, err, pos, 0)

src/encoding/json/v2/arshal.go

@@ -409,7 +409,7 @@ func Unmarshal(in []byte, out any, opts ...Options) (err error) {
 	dec := export.GetBufferedDecoder(in, opts...)
 	defer export.PutBufferedDecoder(dec)
 	xd := export.Decoder(dec)
-	err = unmarshalFull(dec, out, &xd.Struct)
+	err = unmarshalDecode(dec, out, &xd.Struct, true)
 	if err != nil && xd.Flags.Get(jsonflags.ReportErrorsWithLegacySemantics) {
 		return internal.TransformUnmarshalError(out, err)
 	}
@@ -426,25 +426,13 @@ func UnmarshalRead(in io.Reader, out any, opts ...Options) (err error) {
 	dec := export.GetStreamingDecoder(in, opts...)
 	defer export.PutStreamingDecoder(dec)
 	xd := export.Decoder(dec)
-	err = unmarshalFull(dec, out, &xd.Struct)
+	err = unmarshalDecode(dec, out, &xd.Struct, true)
 	if err != nil && xd.Flags.Get(jsonflags.ReportErrorsWithLegacySemantics) {
 		return internal.TransformUnmarshalError(out, err)
 	}
 	return err
 }
 
-func unmarshalFull(in *jsontext.Decoder, out any, uo *jsonopts.Struct) error {
-	switch err := unmarshalDecode(in, out, uo); err {
-	case nil:
-		return export.Decoder(in).CheckEOF()
-	case io.EOF:
-		offset := in.InputOffset() + int64(len(in.UnreadBuffer()))
-		return &jsontext.SyntacticError{ByteOffset: offset, Err: io.ErrUnexpectedEOF}
-	default:
-		return err
-	}
-}
-
 // UnmarshalDecode deserializes a Go value from a [jsontext.Decoder] according to
 // the provided unmarshal options (while ignoring marshal, encode, or decode options).
 // Any unmarshal options already specified on the [jsontext.Decoder]
@@ -463,14 +451,14 @@ func UnmarshalDecode(in *jsontext.Decoder, out any, opts ...Options) (err error)
 		defer func() { xd.Struct = optsOriginal }()
 		xd.Struct.JoinWithoutCoderOptions(opts...)
 	}
-	err = unmarshalDecode(in, out, &xd.Struct)
+	err = unmarshalDecode(in, out, &xd.Struct, false)
 	if err != nil && xd.Flags.Get(jsonflags.ReportErrorsWithLegacySemantics) {
 		return internal.TransformUnmarshalError(out, err)
 	}
 	return err
 }
 
-func unmarshalDecode(in *jsontext.Decoder, out any, uo *jsonopts.Struct) (err error) {
+func unmarshalDecode(in *jsontext.Decoder, out any, uo *jsonopts.Struct, last bool) (err error) {
 	v := reflect.ValueOf(out)
 	if v.Kind() != reflect.Pointer || v.IsNil() {
 		return &SemanticError{action: "unmarshal", GoType: reflect.TypeOf(out), Err: internal.ErrNonNilReference}
@@ -481,7 +469,11 @@ func unmarshalDecode(in *jsontext.Decoder, out any, uo *jsonopts.Struct) (err er
 	// In legacy semantics, the entirety of the next JSON value
 	// was validated before attempting to unmarshal it.
 	if uo.Flags.Get(jsonflags.ReportErrorsWithLegacySemantics) {
-		if err := export.Decoder(in).CheckNextValue(); err != nil {
+		if err := export.Decoder(in).CheckNextValue(last); err != nil {
+			if err == io.EOF {
+				offset := in.InputOffset() + int64(len(in.UnreadBuffer()))
+				return &jsontext.SyntacticError{ByteOffset: offset, Err: io.ErrUnexpectedEOF}
+			}
 			return err
 		}
 	}
@@ -495,8 +487,15 @@ func unmarshalDecode(in *jsontext.Decoder, out any, uo *jsonopts.Struct) (err er
 		if !uo.Flags.Get(jsonflags.AllowDuplicateNames) {
 			export.Decoder(in).Tokens.InvalidateDisabledNamespaces()
 		}
+		if err == io.EOF {
+			offset := in.InputOffset() + int64(len(in.UnreadBuffer()))
+			return &jsontext.SyntacticError{ByteOffset: offset, Err: io.ErrUnexpectedEOF}
+		}
 		return err
 	}
+	if last {
+		return export.Decoder(in).CheckEOF()
+	}
 	return nil
 }