You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@iceberg.apache.org by GitBox <gi...@apache.org> on 2020/07/31 11:29:30 UTC

[GitHub] [iceberg] chenjunjiedada commented on a change in pull request #1266: Flink: update parquet reader with schema visitor

chenjunjiedada commented on a change in pull request #1266:
URL: https://github.com/apache/iceberg/pull/1266#discussion_r463556929



##########
File path: flink/src/main/java/org/apache/iceberg/flink/data/FlinkParquetReaders.java
##########
@@ -19,64 +19,719 @@
 
 package org.apache.iceberg.flink.data;
 
+import java.math.BigDecimal;
+import java.math.BigInteger;
+import java.nio.ByteBuffer;
+import java.time.Instant;
 import java.util.List;
-import org.apache.flink.types.Row;
+import java.util.Map;
+import org.apache.commons.lang3.ArrayUtils;
+import org.apache.flink.table.data.ArrayData;
+import org.apache.flink.table.data.DecimalData;
+import org.apache.flink.table.data.GenericRowData;
+import org.apache.flink.table.data.MapData;
+import org.apache.flink.table.data.RawValueData;
+import org.apache.flink.table.data.RowData;
+import org.apache.flink.table.data.StringData;
+import org.apache.flink.table.data.TimestampData;
 import org.apache.iceberg.Schema;
-import org.apache.iceberg.data.parquet.BaseParquetReaders;
+import org.apache.iceberg.parquet.ParquetSchemaUtil;
 import org.apache.iceberg.parquet.ParquetValueReader;
 import org.apache.iceberg.parquet.ParquetValueReaders;
+import org.apache.iceberg.parquet.TypeWithSchemaVisitor;
+import org.apache.iceberg.relocated.com.google.common.collect.ImmutableList;
+import org.apache.iceberg.relocated.com.google.common.collect.ImmutableMap;
+import org.apache.iceberg.relocated.com.google.common.collect.Lists;
+import org.apache.iceberg.relocated.com.google.common.collect.Maps;
 import org.apache.iceberg.types.Types;
+import org.apache.parquet.column.ColumnDescriptor;
+import org.apache.parquet.io.api.Binary;
+import org.apache.parquet.schema.GroupType;
+import org.apache.parquet.schema.LogicalTypeAnnotation.DecimalLogicalTypeAnnotation;
 import org.apache.parquet.schema.MessageType;
+import org.apache.parquet.schema.PrimitiveType;
 import org.apache.parquet.schema.Type;
 
-public class FlinkParquetReaders extends BaseParquetReaders<Row> {
+class FlinkParquetReaders {
+  private FlinkParquetReaders() {
+  }
 
-  private static final FlinkParquetReaders INSTANCE = new FlinkParquetReaders();
+  public static ParquetValueReader<RowData> buildReader(Schema expectedSchema, MessageType fileSchema) {
+    return buildReader(expectedSchema, fileSchema, ImmutableMap.of());
+  }
 
-  private FlinkParquetReaders() {
+  @SuppressWarnings("unchecked")
+  public static ParquetValueReader<RowData> buildReader(Schema expectedSchema,
+                                                        MessageType fileSchema,
+                                                        Map<Integer, ?> idToConstant) {
+    ReadBuilder builder = new ReadBuilder(fileSchema, idToConstant);
+    if (ParquetSchemaUtil.hasIds(fileSchema)) {
+      return (ParquetValueReader<RowData>)
+          TypeWithSchemaVisitor.visit(expectedSchema.asStruct(), fileSchema, builder);
+    } else {
+      return (ParquetValueReader<RowData>)
+          TypeWithSchemaVisitor.visit(expectedSchema.asStruct(), fileSchema,
+              new FallbackReadBuilder(builder));
+    }
+  }
+
+  private static class FallbackReadBuilder extends TypeWithSchemaVisitor<ParquetValueReader<?>> {
+    private MessageType type;
+    private final TypeWithSchemaVisitor<ParquetValueReader<?>> builder;

Review comment:
       You are right.  Let me remove `FallbackReaderBuilder` at first since we don't use it. Will add it back when this is ready.




----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

For queries about this service, please contact Infrastructure at:
users@infra.apache.org



---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@iceberg.apache.org
For additional commands, e-mail: issues-help@iceberg.apache.org