huaxingao commented on code in PR #9841:
URL: https://github.com/apache/iceberg/pull/9841#discussion_r1933314992


##########
spark/v3.4/spark/src/main/java/org/apache/iceberg/spark/data/vectorized/CometColumnReader.java:
##########
@@ -0,0 +1,138 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements.  See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership.  The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License.  You may obtain a copy of the License at
+ *
+ *   http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing,
+ * software distributed under the License is distributed on an
+ * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+ * KIND, either express or implied.  See the License for the
+ * specific language governing permissions and limitations
+ * under the License.
+ */
+package org.apache.iceberg.spark.data.vectorized;
+
+import java.io.IOException;
+import java.util.Map;
+import org.apache.comet.parquet.AbstractColumnReader;
+import org.apache.comet.parquet.ColumnReader;
+import org.apache.comet.parquet.TypeUtil;
+import org.apache.comet.parquet.Utils;
+import org.apache.comet.shaded.arrow.c.CometSchemaImporter;
+import org.apache.comet.shaded.arrow.memory.RootAllocator;
+import org.apache.iceberg.parquet.VectorizedReader;
+import org.apache.iceberg.relocated.com.google.common.base.Preconditions;
+import org.apache.iceberg.spark.SparkSchemaUtil;
+import org.apache.iceberg.types.Types;
+import org.apache.parquet.column.ColumnDescriptor;
+import org.apache.parquet.column.page.PageReadStore;
+import org.apache.parquet.column.page.PageReader;
+import org.apache.parquet.hadoop.metadata.ColumnChunkMetaData;
+import org.apache.parquet.hadoop.metadata.ColumnPath;
+import org.apache.spark.sql.types.DataType;
+import org.apache.spark.sql.types.Metadata;
+import org.apache.spark.sql.types.StructField;
+
+@SuppressWarnings("checkstyle:VisibilityModifier")
+class CometColumnReader implements VectorizedReader<CometVector> {
+  public static final int DEFAULT_BATCH_SIZE = 5000;
+
+  private final DataType sparkType;
+  // the delegated column reader from Comet side
+  protected AbstractColumnReader delegate;
+  private final CometVector vector;
+  private final ColumnDescriptor descriptor;
+  protected boolean initialized = false;
+  protected int batchSize = DEFAULT_BATCH_SIZE;
+
+  CometColumnReader(DataType sparkType, ColumnDescriptor descriptor) {
+    this.sparkType = sparkType;
+    this.descriptor = descriptor;
+    this.vector = new CometVector(sparkType, false);
+  }
+
+  CometColumnReader(Types.NestedField field) {
+    DataType dataType = SparkSchemaUtil.convert(field.type());
+    StructField structField = new StructField(field.name(), dataType, false, 
Metadata.empty());
+    this.sparkType = dataType;
+    this.descriptor = TypeUtil.convertToParquet(structField);
+    this.vector = new CometVector(sparkType, false);
+  }
+
+  public AbstractColumnReader getDelegate() {
+    return delegate;
+  }
+
+  /**
+   * This method is to initialized/reset the CometColumnReader. This needs to 
be called for each row
+   * group after readNextRowGroup, so a new dictionary encoding can be set for 
each of the new row
+   * groups.
+   */
+  public void reset() {
+    if (delegate != null) {
+      delegate.close();
+    }
+
+    CometSchemaImporter importer = new CometSchemaImporter(new 
RootAllocator());
+
+    delegate = Utils.getColumnReader(sparkType, descriptor, importer, 
batchSize, false, false);

Review Comment:
   Changed. Thanks!



-- 
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.

To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org

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


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

Reply via email to