consolidate json and auto indexers, remove v4 nested column serializer (

#14456)

benchmarks/src/test/java/org/apache/druid/benchmark/query/SqlNestedDataBenchmark.java

@@ -34,8 +34,8 @@
 import org.apache.druid.query.QueryContexts;
 import org.apache.druid.query.QueryRunnerFactoryConglomerate;
 import org.apache.druid.query.expression.TestExprMacroTable;
+import org.apache.druid.segment.AutoTypeColumnSchema;
 import org.apache.druid.segment.IndexSpec;
-import org.apache.druid.segment.NestedDataDimensionSchema;
 import org.apache.druid.segment.QueryableIndex;
 import org.apache.druid.segment.column.StringEncodingStrategy;
 import org.apache.druid.segment.data.FrontCodedIndexed;
@@ -298,7 +298,7 @@ public void setup()
     );
     List<DimensionSchema> dims = ImmutableList.<DimensionSchema>builder()
                                               .addAll(schemaInfo.getDimensionsSpec().getDimensions())
-                                              .add(new NestedDataDimensionSchema("nested"))
+                                              .add(new AutoTypeColumnSchema("nested"))
                                               .build();
     DimensionsSpec dimsSpec = new DimensionsSpec(dims);
 

docs/querying/nested-columns.md

@@ -27,12 +27,14 @@ import TabItem from '@theme/TabItem';
   ~ under the License.
   -->
 
-Apache Druid supports directly storing nested data structures in `COMPLEX<json>` columns. `COMPLEX<json>` columns store a copy of the structured data in JSON format and specialized internal columns and indexes for nested literal values&mdash;STRING, LONG, and DOUBLE types. An optimized [virtual column](./virtual-columns.md#nested-field-virtual-column) allows Druid to read and filter these values at speeds consistent with standard Druid LONG, DOUBLE, and STRING columns.
+Apache Druid supports directly storing nested data structures in `COMPLEX<json>` columns. `COMPLEX<json>` columns store a copy of the structured data in JSON format and specialized internal columns and indexes for nested literal values&mdash;STRING, LONG, and DOUBLE types, as well as ARRAY of STRING, LONG, and DOUBLE values. An optimized [virtual column](./virtual-columns.md#nested-field-virtual-column) allows Druid to read and filter these values at speeds consistent with standard Druid LONG, DOUBLE, and STRING columns.
 
 Druid [SQL JSON functions](./sql-json-functions.md) allow you to extract, transform, and create `COMPLEX<json>` values in SQL queries, using the specialized virtual columns where appropriate. You can use the [JSON nested columns functions](math-expr.md#json-functions) in [native queries](./querying.md) using [expression virtual columns](./virtual-columns.md#expression-virtual-column), and in native ingestion with a [`transformSpec`](../ingestion/ingestion-spec.md#transformspec).
 
 You can use the JSON functions in INSERT and REPLACE statements in SQL-based ingestion, or in a `transformSpec` in native ingestion as an alternative to using a [`flattenSpec`](../ingestion/data-formats.md#flattenspec) object to "flatten" nested data for ingestion.
 
+Columns ingested as `COMPLEX<json>` are automatically optimized to store the most appropriate physical column based on the data processed. For example, if only LONG values are processed, Druid stores a LONG column, ARRAY columns if the data consists of arrays, or `COMPLEX<json>` in the general case if the data is actually nested. This is the same functionality that powers ['type aware' schema discovery](../ingestion/schema-design.md#type-aware-schema-discovery).
+
 Druid supports directly ingesting nested data with the following formats: JSON, Parquet, Avro, ORC, Protobuf.
 
 ## Example nested data

extensions-core/avro-extensions/src/test/java/org/apache/druid/data/input/AvroStreamInputFormatTest.java

@@ -47,7 +47,7 @@
 import org.apache.druid.java.util.common.parsers.JSONPathFieldType;
 import org.apache.druid.java.util.common.parsers.JSONPathSpec;
 import org.apache.druid.query.expression.TestExprMacroTable;
-import org.apache.druid.segment.NestedDataDimensionSchema;
+import org.apache.druid.segment.AutoTypeColumnSchema;
 import org.apache.druid.segment.nested.StructuredData;
 import org.apache.druid.segment.transform.ExpressionTransform;
 import org.apache.druid.segment.transform.TransformSpec;
@@ -303,15 +303,15 @@ public void testParseTransformNested() throws SchemaValidationException, IOExcep
 
     DimensionsSpec dimensionsSpec = new DimensionsSpec(
         ImmutableList.of(
-            new NestedDataDimensionSchema("someIntValueMap"),
-            new NestedDataDimensionSchema("someStringValueMap"),
-            new NestedDataDimensionSchema("someRecord"),
-            new NestedDataDimensionSchema("someRecordArray"),
+            new AutoTypeColumnSchema("someIntValueMap"),
+            new AutoTypeColumnSchema("someStringValueMap"),
+            new AutoTypeColumnSchema("someRecord"),
+            new AutoTypeColumnSchema("someRecordArray"),
             new LongDimensionSchema("tSomeIntValueMap8"),
             new LongDimensionSchema("tSomeIntValueMap8_2"),
             new StringDimensionSchema("tSomeStringValueMap8"),
             new LongDimensionSchema("tSomeRecordSubLong"),
-            new NestedDataDimensionSchema("tSomeRecordArray0"),
+            new AutoTypeColumnSchema("tSomeRecordArray0"),
             new StringDimensionSchema("tSomeRecordArray0nestedString")
         )
     );

extensions-core/orc-extensions/src/test/java/org/apache/druid/data/input/orc/OrcReaderTest.java

@@ -37,7 +37,7 @@
 import org.apache.druid.java.util.common.parsers.JSONPathFieldType;
 import org.apache.druid.java.util.common.parsers.JSONPathSpec;
 import org.apache.druid.query.expression.TestExprMacroTable;
-import org.apache.druid.segment.NestedDataDimensionSchema;
+import org.apache.druid.segment.AutoTypeColumnSchema;
 import org.apache.druid.segment.transform.ExpressionTransform;
 import org.apache.druid.segment.transform.TransformSpec;
 import org.apache.druid.segment.transform.TransformingInputEntityReader;
@@ -333,9 +333,9 @@ public void testNestedColumn() throws IOException
         new TimestampSpec("ts", "millis", null),
         new DimensionsSpec(
             ImmutableList.of(
-                new NestedDataDimensionSchema("middle"),
-                new NestedDataDimensionSchema("list"),
-                new NestedDataDimensionSchema("map")
+                new AutoTypeColumnSchema("middle"),
+                new AutoTypeColumnSchema("list"),
+                new AutoTypeColumnSchema("map")
             )
         ),
         inputFormat,
@@ -542,8 +542,8 @@ public void testListMap() throws IOException
         new TimestampSpec("timestamp", "auto", null),
         new DimensionsSpec(
             ImmutableList.of(
-                new NestedDataDimensionSchema("a"),
-                new NestedDataDimensionSchema("b")
+                new AutoTypeColumnSchema("a"),
+                new AutoTypeColumnSchema("b")
             )
         ),
         inputFormat,
@@ -608,11 +608,11 @@ public void testNestedArray() throws IOException
         new TimestampSpec("timestamp", "auto", null),
         new DimensionsSpec(
             ImmutableList.of(
-                new NestedDataDimensionSchema("a"),
-                new NestedDataDimensionSchema("b"),
-                new NestedDataDimensionSchema("c"),
-                new NestedDataDimensionSchema("d"),
-                new NestedDataDimensionSchema("t_d_0")
+                new AutoTypeColumnSchema("a"),
+                new AutoTypeColumnSchema("b"),
+                new AutoTypeColumnSchema("c"),
+                new AutoTypeColumnSchema("d"),
+                new AutoTypeColumnSchema("t_d_0")
             )
         ),
         inputFormat,

extensions-core/parquet-extensions/src/test/java/org/apache/druid/data/input/parquet/NestedColumnParquetReaderTest.java

@@ -31,7 +31,7 @@
 import org.apache.druid.data.input.impl.TimestampSpec;
 import org.apache.druid.java.util.common.parsers.JSONPathSpec;
 import org.apache.druid.query.expression.TestExprMacroTable;
-import org.apache.druid.segment.NestedDataDimensionSchema;
+import org.apache.druid.segment.AutoTypeColumnSchema;
 import org.apache.druid.segment.transform.ExpressionTransform;
 import org.apache.druid.segment.transform.TransformSpec;
 import org.apache.druid.segment.transform.TransformingInputEntityReader;
@@ -51,8 +51,8 @@ public void testNestedColumnTransformsNestedTestFile() throws IOException
         new TimestampSpec("timestamp", "auto", null),
         new DimensionsSpec(
             ImmutableList.of(
-                new NestedDataDimensionSchema("nestedData"),
-                new NestedDataDimensionSchema("t_nestedData_listDim"),
+                new AutoTypeColumnSchema("nestedData"),
+                new AutoTypeColumnSchema("t_nestedData_listDim"),
                 new StringDimensionSchema("t_nestedData_listDim_string"),
                 new StringDimensionSchema("t_nestedData_dim2"),
                 new LongDimensionSchema("t_nestedData_dim3"),
@@ -105,10 +105,10 @@ public void testNestedColumnTransformsNestedNullableListFile() throws IOExceptio
         new TimestampSpec("timestamp", "auto", null),
         new DimensionsSpec(
             ImmutableList.of(
-                new NestedDataDimensionSchema("a1"),
-                new NestedDataDimensionSchema("a2"),
-                new NestedDataDimensionSchema("t_a2"),
-                new NestedDataDimensionSchema("t_a1_b1"),
+                new AutoTypeColumnSchema("a1"),
+                new AutoTypeColumnSchema("a2"),
+                new AutoTypeColumnSchema("t_a2"),
+                new AutoTypeColumnSchema("t_a1_b1"),
                 new LongDimensionSchema("t_a1_b1_c1"),
                 new LongDimensionSchema("t_e2_0_b1"),
                 new LongDimensionSchema("tt_a2_0_b1")

indexing-service/src/test/java/org/apache/druid/indexing/overlord/sampler/InputSourceSamplerDiscoveryTest.java

@@ -33,7 +33,6 @@
 import org.apache.druid.jackson.DefaultObjectMapper;
 import org.apache.druid.math.expr.ExpressionProcessing;
 import org.apache.druid.segment.AutoTypeColumnSchema;
-import org.apache.druid.segment.NestedDataDimensionSchema;
 import org.apache.druid.segment.column.ColumnType;
 import org.apache.druid.segment.column.RowSignature;
 import org.apache.druid.segment.indexing.DataSchema;
@@ -257,9 +256,9 @@ public void testTypesNoDiscoveryExplicitSchema()
                              new LongDimensionSchema("long"),
                              new DoubleDimensionSchema("double"),
                              new StringDimensionSchema("bool"),
-                             new NestedDataDimensionSchema("variant"),
-                             new NestedDataDimensionSchema("array"),
-                             new NestedDataDimensionSchema("nested")
+                             new AutoTypeColumnSchema("variant"),
+                             new AutoTypeColumnSchema("array"),
+                             new AutoTypeColumnSchema("nested")
             )
         ).build(),
         null,
@@ -292,8 +291,8 @@ public void testTypesNoDiscoveryExplicitSchema()
                     .add("long", ColumnType.LONG)
                     .add("double", ColumnType.DOUBLE)
                     .add("bool", ColumnType.STRING)
-                    .add("variant", ColumnType.NESTED_DATA)
-                    .add("array", ColumnType.NESTED_DATA)
+                    .add("variant", ColumnType.STRING)
+                    .add("array", ColumnType.LONG_ARRAY)
                     .add("nested", ColumnType.NESTED_DATA)
                     .build(),
         response.getLogicalSegmentSchema()

indexing-service/src/test/java/org/apache/druid/indexing/overlord/sampler/SamplerResponseTest.java

@@ -24,7 +24,7 @@
 import com.google.common.collect.ImmutableMap;
 import org.apache.druid.client.indexing.SamplerResponse;
 import org.apache.druid.data.input.impl.StringDimensionSchema;
-import org.apache.druid.segment.NestedDataDimensionSchema;
+import org.apache.druid.segment.AutoTypeColumnSchema;
 import org.apache.druid.segment.TestHelper;
 import org.apache.druid.segment.column.ColumnType;
 import org.apache.druid.segment.column.RowSignature;
@@ -65,7 +65,7 @@ public void testSerde() throws IOException
                 new StringDimensionSchema("dim1")
             ),
             ImmutableList.of(
-                new NestedDataDimensionSchema("dim1")
+                new AutoTypeColumnSchema("dim1")
             ),
             RowSignature.builder().addTimeColumn().add("dim1", ColumnType.STRING).add("met1", ColumnType.LONG).build(),
             data

processing/src/main/java/org/apache/druid/data/input/impl/DimensionSchema.java

@@ -32,7 +32,6 @@
 import org.apache.druid.segment.AutoTypeColumnSchema;
 import org.apache.druid.segment.DimensionHandler;
 import org.apache.druid.segment.DimensionHandlerUtils;
-import org.apache.druid.segment.NestedDataDimensionSchema;
 import org.apache.druid.segment.column.ColumnType;
 import org.apache.druid.segment.column.TypeSignature;
 import org.apache.druid.segment.column.ValueType;
@@ -51,7 +50,7 @@
     @JsonSubTypes.Type(name = DimensionSchema.FLOAT_TYPE_NAME, value = FloatDimensionSchema.class),
     @JsonSubTypes.Type(name = DimensionSchema.DOUBLE_TYPE_NAME, value = DoubleDimensionSchema.class),
     @JsonSubTypes.Type(name = DimensionSchema.SPATIAL_TYPE_NAME, value = NewSpatialDimensionSchema.class),
-    @JsonSubTypes.Type(name = NestedDataComplexTypeSerde.TYPE_NAME, value = NestedDataDimensionSchema.class),
+    @JsonSubTypes.Type(name = NestedDataComplexTypeSerde.TYPE_NAME, value = AutoTypeColumnSchema.class),
     @JsonSubTypes.Type(name = AutoTypeColumnSchema.TYPE, value = AutoTypeColumnSchema.class)
 })
 public abstract class DimensionSchema

processing/src/main/java/org/apache/druid/guice/NestedDataModule.java

@@ -26,7 +26,7 @@
 import com.google.inject.Binder;
 import org.apache.druid.initialization.DruidModule;
 import org.apache.druid.segment.DimensionHandlerUtils;
-import org.apache.druid.segment.NestedDataDimensionHandler;
+import org.apache.druid.segment.NestedCommonFormatColumnHandler;
 import org.apache.druid.segment.nested.NestedDataComplexTypeSerde;
 import org.apache.druid.segment.nested.StructuredData;
 import org.apache.druid.segment.nested.StructuredDataJsonSerializer;
@@ -56,21 +56,18 @@ public static void registerHandlersAndSerde()
   {
     if (ComplexMetrics.getSerdeForType(NestedDataComplexTypeSerde.TYPE_NAME) == null) {
       ComplexMetrics.registerSerde(NestedDataComplexTypeSerde.TYPE_NAME, NestedDataComplexTypeSerde.INSTANCE);
-
     }
     DimensionHandlerUtils.registerDimensionHandlerProvider(
         NestedDataComplexTypeSerde.TYPE_NAME,
-        NestedDataDimensionHandler::new
+        NestedCommonFormatColumnHandler::new
     );
   }
 
   public static List<SimpleModule> getJacksonModulesList()
   {
     return Collections.singletonList(
         new SimpleModule("NestedDataModule")
-            .registerSubtypes(
-                new NamedType(NestedFieldVirtualColumn.class, "nested-field")
-            )
+            .registerSubtypes(new NamedType(NestedFieldVirtualColumn.class, "nested-field"))
             .addSerializer(StructuredData.class, new StructuredDataJsonSerializer())
     );
   }

processing/src/main/java/org/apache/druid/segment/AutoTypeColumnMerger.java

@@ -66,8 +66,7 @@
  */
 public class AutoTypeColumnMerger implements DimensionMergerV9
 {
-  private static final Logger log = new Logger(NestedDataColumnMerger.class);
-
+  private static final Logger log = new Logger(AutoTypeColumnMerger.class);
   public static final Comparator<PeekingIterator<String>> STRING_MERGING_COMPARATOR =
       SimpleDictionaryMergingIterator.makePeekingComparator();
   public static final Comparator<PeekingIterator<Long>> LONG_MERGING_COMPARATOR =