mayursrivastava commented on a change in pull request #2286:
URL: https://github.com/apache/iceberg/pull/2286#discussion_r591983868
##########
File path: data/src/main/java/org/apache/iceberg/data/IcebergGenerics.java
##########
@@ -47,6 +47,10 @@ public ScanBuilder(Table table) {
this.tableScan = table.newScan();
}
+ public TableScan getTableScan() {
Review comment:
I'll revert this change
##########
File path:
data/src/main/java/org/apache/iceberg/data/arrow/ArrowFileScanTaskReader.java
##########
@@ -0,0 +1,102 @@
+/*
+ * 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.data.arrow;
+
+import org.apache.arrow.vector.NullCheckingForGet;
+import org.apache.arrow.vector.VectorSchemaRoot;
+import org.apache.iceberg.CombinedScanTask;
+import org.apache.iceberg.FileFormat;
+import org.apache.iceberg.FileScanTask;
+import org.apache.iceberg.Schema;
+import org.apache.iceberg.encryption.EncryptionManager;
+import org.apache.iceberg.io.CloseableIterable;
+import org.apache.iceberg.io.CloseableIterator;
+import org.apache.iceberg.io.FileIO;
+import org.apache.iceberg.io.InputFile;
+import org.apache.iceberg.mapping.NameMappingParser;
+import org.apache.iceberg.parquet.Parquet;
+import org.apache.iceberg.relocated.com.google.common.base.Preconditions;
+
+/**
+ * Reads the data file and returns an iterator of {@link VectorSchemaRoot}.
Only Parquet data file format is supported.
+ */
+public class ArrowFileScanTaskReader extends
BaseArrowFileScanTaskReader<VectorSchemaRoot> {
+
+ private final Schema expectedSchema;
+ private final String nameMapping;
+ private final boolean caseSensitive;
+ private final int batchSize;
+ private final boolean reuseContainers;
+
+ /**
+ * Create a new instance.
+ *
+ * @param task Combined file scan task.
+ * @param expectedSchema Read schema. The returned data will have this
schema.
+ * @param nameMapping Mapping from external schema names to Iceberg
type IDs.
+ * @param fileIo File I/O.
+ * @param encryptionManager Encryption manager.
+ * @param caseSensitive Indicates whether column names are case
sensitive.
+ * @param batchSize Batch size in number of rows. Each Arrow batch
({@link VectorSchemaRoot}) contains a
+ * maximum of {@code batchSize} rows.
+ * @param reuseContainers Reuse Arrow vectors from the previous {@link
VectorSchemaRoot} in the next {@link
Review comment:
will do
----------------------------------------------------------------
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:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
