Update the test to pass avro read schema

Author: aihuaxu

parquet-avro/src/main/java/org/apache/parquet/avro/AvroSchemaConverter.java

@@ -470,8 +470,11 @@ public Optional<Schema> visit(
               @Override
               public Optional<Schema> visit(
                   LogicalTypeAnnotation.VariantLogicalTypeAnnotation variantLogicalType) {
-                return of(
-                    convertFields(parquetGroupType.getName(), parquetGroupType.getFields(), names));
+                String name = parquetGroupType.getName();
+                List<Schema.Field> fields = new ArrayList<>();
+                fields.add(new Schema.Field("metadata", Schema.create(Schema.Type.BYTES)));
+                fields.add(new Schema.Field("value", Schema.create(Schema.Type.BYTES)));
+                return of(Schema.createRecord(name, null, namespace(name, names), false, fields));
               }
             })
             .orElseThrow(

parquet-avro/src/main/java/org/apache/parquet/avro/AvroVariantConverter.java

@@ -21,7 +21,6 @@
 import java.nio.ByteBuffer;
 import java.util.function.Consumer;
 import org.apache.avro.Schema;
-import org.apache.avro.SchemaBuilder;
 import org.apache.avro.generic.GenericData;
 import org.apache.parquet.Preconditions;
 import org.apache.parquet.io.api.Converter;
@@ -35,27 +34,21 @@
  * Converter for Variant values.
  */
 class AvroVariantConverter extends GroupConverter implements VariantConverters.ParentConverter<VariantBuilder> {
-  private static final Schema VARIANT_SCHEMA = SchemaBuilder.record("VariantRecord")
-      .fields()
-      .name("metadata")
-      .type()
-      .bytesType()
-      .noDefault()
-      .name("value")
-      .type()
-      .bytesType()
-      .noDefault()
-      .endRecord();
-
   private final ParentValueContainer parent;
+  private final Schema avroSchema;
   private final GenericData model;
+  private final int metadataPos;
+  private final int valuePos;
   private final GroupConverter wrappedConverter;
 
   private VariantBuilder builder = null;
   private ImmutableMetadata metadata = null;
 
   AvroVariantConverter(ParentValueContainer parent, GroupType variantGroup, Schema avroSchema, GenericData model) {
     this.parent = parent;
+    this.avroSchema = avroSchema;
+    this.metadataPos = avroSchema.getField("metadata").pos();
+    this.valuePos = avroSchema.getField("value").pos();
     this.model = model;
     this.wrappedConverter = VariantConverters.newVariantConverter(variantGroup, this::setMetadata, this);
   }
@@ -84,9 +77,9 @@ public void end() {
 
     builder.appendNullIfEmpty();
 
-    Object record = model.newRecord(null, VARIANT_SCHEMA);
-    model.setField(record, "metadata", 0, metadata.getEncodedBuffer());
-    model.setField(record, "value", 1, builder.encodedValue());
+    Object record = model.newRecord(null, avroSchema);
+    model.setField(record, "metadata", metadataPos, metadata.getEncodedBuffer());
+    model.setField(record, "value", valuePos, builder.encodedValue());
     parent.add(record);
 
     this.builder = null;

parquet-avro/src/test/java/org/apache/parquet/variant/TestVariantReadsFromFile.java

@@ -32,12 +32,18 @@
 import java.nio.file.Paths;
 import java.util.List;
 import java.util.stream.Stream;
+import org.apache.avro.Schema;
 import org.apache.avro.generic.GenericData;
 import org.apache.avro.generic.GenericRecord;
+import org.apache.hadoop.conf.Configuration;
 import org.apache.parquet.Preconditions;
 import org.apache.parquet.avro.AvroParquetReader;
+import org.apache.parquet.avro.AvroReadSupport;
+import org.apache.parquet.avro.AvroSchemaConverter;
+import org.apache.parquet.hadoop.ParquetFileReader;
 import org.apache.parquet.io.InputFile;
 import org.apache.parquet.io.LocalInputFile;
+import org.apache.parquet.schema.MessageType;
 import org.assertj.core.api.Assertions;
 import org.junit.jupiter.params.ParameterizedTest;
 import org.junit.jupiter.params.provider.Arguments;
@@ -186,8 +192,17 @@ private GenericRecord readParquetRecord(String parquetFile) throws IOException {
   private List<GenericRecord> readParquet(String parquetFile) throws IOException {
     org.apache.parquet.io.InputFile inputFile = new LocalInputFile(Paths.get(CASE_LOCATION + "/" + parquetFile));
     List<GenericRecord> records = Lists.newArrayList();
+
+    // Set Avro read schema converted from the Parquet schema
+    Configuration conf = new Configuration(false);
+    try (ParquetFileReader fileReader = ParquetFileReader.open(inputFile)) {
+      final MessageType fileSchema = fileReader.getFileMetaData().getSchema();
+      Schema avroReadSchema = new AvroSchemaConverter().convert(fileSchema);
+      AvroReadSupport.setAvroReadSchema(conf, avroReadSchema);
+    }
+
     try (org.apache.parquet.hadoop.ParquetReader<GenericRecord> reader =
-        AvroParquetReader.<GenericRecord>builder(inputFile).build()) {
+        AvroParquetReader.<GenericRecord>builder(inputFile).withConf(conf).build()) {
       GenericRecord record;
       while ((record = reader.read()) != null) {
         records.add(record);