Tighten Seriatim input validation

internal/modules/input/seriatim/model.go

@@ -45,13 +45,21 @@ func decodeTranscript(raw []byte) (transcript, error) {
 	if !ok {
 		return transcript{}, fmt.Errorf("segments are required")
 	}
-	var segments []segment
-	if err := decodeJSON(segmentsRaw, &segments); err != nil {
+	var segmentValues []json.RawMessage
+	if err := decodeJSON(segmentsRaw, &segmentValues); err != nil {
 		return transcript{}, fmt.Errorf("segments must be an array: %w", err)
 	}
-	if segments == nil {
+	if segmentValues == nil {
 		return transcript{}, fmt.Errorf("segments must be an array")
 	}
+	segments := make([]segment, 0, len(segmentValues))
+	for i, rawSegment := range segmentValues {
+		segment, err := decodeSegment(rawSegment, i)
+		if err != nil {
+			return transcript{}, err
+		}
+		segments = append(segments, segment)
+	}
 
 	return transcript{
 		Metadata: metadata,
@@ -59,6 +67,50 @@ func decodeTranscript(raw []byte) (transcript, error) {
 	}, nil
 }
 
+func decodeSegment(raw []byte, index int) (segment, error) {
+	var fields map[string]json.RawMessage
+	if err := decodeJSON(raw, &fields); err != nil {
+		return segment{}, fmt.Errorf("segment[%d] must be an object: %w", index, err)
+	}
+	if fields == nil {
+		return segment{}, fmt.Errorf("segment[%d] must be an object", index)
+	}
+
+	var decoded segment
+	if err := decodeOptionalString(fields, "id", &decoded.ID); err != nil {
+		return segment{}, fmt.Errorf("segment[%d] id must be a string: %w", index, err)
+	}
+	if err := decodeOptionalNumber(fields, "start", &decoded.Start); err != nil {
+		return segment{}, fmt.Errorf("segment[%d] start must be a number: %w", index, err)
+	}
+	if err := decodeOptionalNumber(fields, "end", &decoded.End); err != nil {
+		return segment{}, fmt.Errorf("segment[%d] end must be a number: %w", index, err)
+	}
+	if err := decodeOptionalString(fields, "speaker", &decoded.Speaker); err != nil {
+		return segment{}, fmt.Errorf("segment[%d] speaker must be a string: %w", index, err)
+	}
+	if err := decodeOptionalString(fields, "text", &decoded.Text); err != nil {
+		return segment{}, fmt.Errorf("segment[%d] text must be a string: %w", index, err)
+	}
+	return decoded, nil
+}
+
+func decodeOptionalString(fields map[string]json.RawMessage, key string, out *string) error {
+	raw, ok := fields[key]
+	if !ok {
+		return nil
+	}
+	return decodeJSON(raw, out)
+}
+
+func decodeOptionalNumber(fields map[string]json.RawMessage, key string, out *json.Number) error {
+	raw, ok := fields[key]
+	if !ok {
+		return nil
+	}
+	return decodeJSON(raw, out)
+}
+
 func decodeJSON(raw []byte, out any) error {
 	decoder := json.NewDecoder(bytes.NewReader(raw))
 	decoder.UseNumber()