Merge branch '2.x' into 3.x

Author: cowtowncoder

.github/workflows/main.yml

@@ -55,7 +55,7 @@ jobs:
       run: ./mvnw -B -q -ff -ntp test
     - name: Publish code coverage
       if: ${{ matrix.release_build && github.event_name != 'pull_request' }}
-      uses: codecov/codecov-action@ad3126e916f78f00edff4ed0317cf185271ccc2d # v5.4.2
+      uses: codecov/codecov-action@18283e04ce6e62d37312384ff67231eb8fd56d24 # v5.4.3
       with:
         token: ${{ secrets.CODECOV_TOKEN }}
         files: ./target/site/jacoco/jacoco.xml

avro/src/main/java/tools/jackson/dataformat/avro/schema/RecordVisitor.java

@@ -29,58 +29,122 @@ public class RecordVisitor
     protected final VisitorFormatWrapperImpl _visitorWrapper;
 
     /**
-     * Tracks if the schema for this record has been overridden (by an annotation or other means), and calls to the {@code property} and
-     * {@code optionalProperty} methods should be ignored.
+     * Tracks if the schema for this record has been overridden (by an annotation or other means),
+     * and calls to the {@code property} and {@code optionalProperty} methods should be ignored.
      */
     protected final boolean _overridden;
 
     protected final boolean _cfgAddNullDefaults;
 
+    /**
+     * When Avro schema for this JavaType ({@code _type}) results in UNION of multiple Avro types,
+     * _typeSchema keeps track of which Avro type in the UNION represents this JavaType ({@code _type})
+     * so that fields of this JavaType can be set to the right Avro type by {@code builtAvroSchema()}.
+     *<br>
+     * Example:
+     * <pre>
+     *   @JsonSubTypes({
+     *     @JsonSubTypes.Type(value = Apple.class),
+     *     @JsonSubTypes.Type(value = Pear.class) })
+     *   class Fruit {}
+     *
+     *   class Apple extends Fruit {}
+     *   class Orange extends Fruit {}
+     * </pre>
+     * When {@code _type = Fruit.class}
+     * Then
+     * _avroSchema if Fruit.class is union of Fruit record, Apple record and Orange record schemas: [
+     *     { name: Fruit, type: record, fields: [..] }, <--- _typeSchema points here
+     *     { name: Apple, type: record, fields: [..] },
+     *     { name: Orange, type: record, fields: [..]}
+     *   ]
+     * _typeSchema points to Fruit.class without subtypes record schema
+     *
+     * FIXME: When _typeSchema is not null, then _overridden must be true, therefore (_overridden == true) can be replaced with (_typeSchema != null),
+     * but it might be considered API change cause _overridden has protected access modifier.
+     *
+     * @since 2.19.1
+     */
+    private final Schema _typeSchema;
+
+    // !!! 19-May-2025: TODO: make final in 2.20
     protected Schema _avroSchema;
 
+    // !!! 19-May-2025: TODO: make final in 2.20
     protected List<Schema.Field> _fields = new ArrayList<>();
 
-    public RecordVisitor(SerializationContext p, JavaType type, VisitorFormatWrapperImpl visitorWrapper)
+    public RecordVisitor(SerializationContext ctxt, JavaType type,
+            VisitorFormatWrapperImpl visitorWrapper)
     {
-        super(p);
+        super(ctxt);
         _type = type;
         _visitorWrapper = visitorWrapper;
 
-        AvroFactory avroFactory = (AvroFactory) p.tokenStreamFactory();
+        AvroFactory avroFactory = (AvroFactory) ctxt.tokenStreamFactory();
         _cfgAddNullDefaults = avroFactory.isEnabled(AvroWriteFeature.ADD_NULL_AS_DEFAULT_VALUE_IN_SCHEMA);
 
         // Check if the schema for this record is overridden
-        SerializationConfig config = p.getConfig();
+        SerializationConfig config = ctxt.getConfig();
 
         // 12-Oct-2019, tatu: VERY important: only get direct annotations, not for supertypes --
         //   otherwise there's infinite loop awaiting for... some reason. Other parts of code
         //   should probably check for loops but bit hard for me to fix as I did not author
         //   code in question (so may be unaware of some nuances)
-        final AnnotatedClass annotations = p.introspectDirectClassAnnotations(_type);
-        final AnnotationIntrospector intr = p.getAnnotationIntrospector();
-        List<NamedType> subTypes = intr.findSubtypes(config, annotations);
+        final AnnotatedClass annotations = ctxt.introspectDirectClassAnnotations(_type);
+        final AnnotationIntrospector intr = ctxt.getAnnotationIntrospector();
+        //List<NamedType> subTypes = intr.findSubtypes(config, annotations);
         AvroSchema ann = annotations.getAnnotation(AvroSchema.class);
         if (ann != null) {
             _avroSchema = AvroSchemaHelper.parseJsonSchema(ann.value());
             _overridden = true;
-        } else if (subTypes != null && !subTypes.isEmpty()) {
-            List<Schema> unionSchemas = new ArrayList<>();
-            for (NamedType subType : subTypes) {
-                final JavaType subTypeType = getContext().getTypeFactory().constructType(subType.getType());
-                ValueSerializer<?> ser = getContext().findValueSerializer(subTypeType);
-                VisitorFormatWrapperImpl visitor = _visitorWrapper.createChildWrapper();
-                ser.acceptJsonFormatVisitor(visitor, subTypeType);
-                unionSchemas.add(visitor.getAvroSchema());
-            }
-            _avroSchema = Schema.createUnion(unionSchemas);
-            _overridden = true;
+            _typeSchema = null;
         } else {
-            _avroSchema = AvroSchemaHelper.initializeRecordSchema(p.getConfig(), _type, annotations);
+            // If Avro schema for this _type results in UNION I want to know Avro type where to assign fields
+            _avroSchema = AvroSchemaHelper.initializeRecordSchema(ctxt.getConfig(), _type, annotations);
+            _typeSchema = _avroSchema;
             _overridden = false;
             AvroMeta meta = annotations.getAnnotation(AvroMeta.class);
             if (meta != null) {
                 _avroSchema.addProp(meta.key(), meta.value());
             }
+
+            List<NamedType> subTypes = intr.findSubtypes(config, annotations);
+            if (subTypes != null && !subTypes.isEmpty()) {
+                // alreadySeenClasses prevents subType processing in endless loop
+                Set<Class<?>> alreadySeenClasses = new HashSet<>();
+                alreadySeenClasses.add(_type.getRawClass());
+
+                // At this point calculating hashCode for _typeSchema fails with
+                // NPE because RecordSchema.fields is NULL
+                // (see org.apache.avro.Schema.RecordSchema#computeHash).
+                // Therefore, unionSchemas must not be HashSet (or any other type
+                // using hashCode() for equality check).
+                // Set ensures that each subType schema is once in resulting union.
+                // IdentityHashMap is used because it is using reference-equality.
+                final Set<Schema> unionSchemas = Collections.newSetFromMap(new IdentityHashMap<>());
+                // Initialize with this schema
+                if (_type.isConcrete()) {
+                    unionSchemas.add(_typeSchema);
+                }
+
+                for (NamedType subType : subTypes) {
+                    if (!alreadySeenClasses.add(subType.getType())) {
+                        continue;
+                    }
+                    ValueSerializer<?> ser = ctxt.findValueSerializer(subType.getType());
+                    VisitorFormatWrapperImpl visitor = _visitorWrapper.createChildWrapper();
+                    ser.acceptJsonFormatVisitor(visitor,ctxt.constructType(subType.getType()));
+                    // Add subType schema into this union, unless it is already there.
+                    Schema subTypeSchema = visitor.getAvroSchema();
+                    // When subType schema is union itself, include each its type into this union if not there already
+                    if (subTypeSchema.getType() == Type.UNION) {
+                        unionSchemas.addAll(subTypeSchema.getTypes());
+                    } else {
+                        unionSchemas.add(subTypeSchema);
+                    }
+                }
+                _avroSchema = Schema.createUnion(new ArrayList<>(unionSchemas));
+            }
         }
         _visitorWrapper.getSchemas().addSchema(type, _avroSchema);
     }
@@ -89,7 +153,7 @@ public RecordVisitor(SerializationContext p, JavaType type, VisitorFormatWrapper
     public Schema builtAvroSchema() {
         if (!_overridden) {
             // Assumption now is that we are done, so let's assign fields
-            _avroSchema.setFields(_fields);
+            _typeSchema.setFields(_fields);
         }
         return _avroSchema;
     }