parthchandra commented on code in PR #9841: URL: https://github.com/apache/iceberg/pull/9841#discussion_r1934545952
########## spark/v3.4/spark/src/main/java/org/apache/iceberg/spark/data/vectorized/CometColumnReader.java: ########## @@ -0,0 +1,149 @@ +/* + * 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; + +class CometColumnReader implements VectorizedReader<CometVector> { + public static final int DEFAULT_BATCH_SIZE = 5000; + + private final DataType sparkType; + // the delegated column reader from Comet side + private AbstractColumnReader delegate; + private final CometVector vector; + private final ColumnDescriptor descriptor; + private boolean initialized = false; + private 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 delegate() { + return delegate; + } + + void setDelegate(AbstractColumnReader delegate) { + this.delegate = delegate; + } + + void setInitialized(boolean initialized) { + this.initialized = initialized; + } + + public int batchSize() { + return batchSize; + } + + /** + * 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()); Review Comment: Ideally, we should call `close` on the importer after the column reader is done. ########## spark/v3.4/spark/src/main/java/org/apache/iceberg/spark/data/vectorized/CometColumnReader.java: ########## @@ -0,0 +1,149 @@ +/* + * 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; + +class CometColumnReader implements VectorizedReader<CometVector> { + public static final int DEFAULT_BATCH_SIZE = 5000; + + private final DataType sparkType; + // the delegated column reader from Comet side + private AbstractColumnReader delegate; + private final CometVector vector; + private final ColumnDescriptor descriptor; + private boolean initialized = false; + private int batchSize = DEFAULT_BATCH_SIZE; Review Comment: Should this natch the Comet batch size? https://github.com/apache/datafusion-comet/blob/e9649477c4f8b4c6906244c3cc6828b83f32f735/common/src/main/scala/org/apache/comet/CometConf.scala#L492 ########## .baseline/checkstyle/checkstyle-suppressions.xml: ########## @@ -48,4 +48,7 @@ <!-- Referencing guava classes should be allowed in classes within bundled-guava module --> <suppress files="org.apache.iceberg.GuavaClasses" id="BanUnrelocatedGuavaClasses"/> + Review Comment: @huaxingao can you log an issue in Comet to address this? `CometSchemaImporter` is a Comet class but is in the `org.apache.arrow.c` package to overcome access restrictions (Arrow's SchemaImporter is package private). We can create a wrapper class to access the schema importer. Also, we should ideally use the allocator from `BatchReader`, but that too can be in the wrapper class, I think. There is no issue with using a new allocator for each column, but the arrow allocator has powerful features in memory accounting that we can take advantage of down the road. ########## spark/v3.4/spark/src/main/java/org/apache/iceberg/spark/data/vectorized/CometColumnReader.java: ########## @@ -0,0 +1,149 @@ +/* + * 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; + +class CometColumnReader implements VectorizedReader<CometVector> { + public static final int DEFAULT_BATCH_SIZE = 5000; + + private final DataType sparkType; + // the delegated column reader from Comet side + private AbstractColumnReader delegate; Review Comment: The interaction between `CometColumnarBatchReader.delegate` and CometColumnReader.delegate` is a little confusing. A comment explaining it would be useful. ########## spark/v3.4/spark/src/main/java/org/apache/iceberg/spark/data/vectorized/CometColumnarBatchReader.java: ########## @@ -0,0 +1,199 @@ +/* + * 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.io.UncheckedIOException; +import java.util.List; +import java.util.Map; +import org.apache.comet.parquet.AbstractColumnReader; +import org.apache.comet.parquet.BatchReader; +import org.apache.iceberg.Schema; +import org.apache.iceberg.data.DeleteFilter; +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.util.Pair; +import org.apache.parquet.column.page.PageReadStore; +import org.apache.parquet.hadoop.metadata.ColumnChunkMetaData; +import org.apache.parquet.hadoop.metadata.ColumnPath; +import org.apache.spark.sql.catalyst.InternalRow; +import org.apache.spark.sql.vectorized.ColumnVector; +import org.apache.spark.sql.vectorized.ColumnarBatch; + +/** + * {@link VectorizedReader} that returns Spark's {@link ColumnarBatch} to support Spark's vectorized + * read path. The {@link ColumnarBatch} returned is created by passing in the Arrow vectors + * populated via delegated read calls to {@link CometColumnReader VectorReader(s)}. + */ +@SuppressWarnings("checkstyle:VisibilityModifier") +class CometColumnarBatchReader implements VectorizedReader<ColumnarBatch> { + + private final CometColumnReader[] readers; + private final boolean hasIsDeletedColumn; + // The delegated batch reader on Comet side + private final BatchReader delegate; Review Comment: Why do we have this and not use the `nextBatch` call directly (instead we are explicitly calling `readBatch` on each column reader). A comment to explain why would be helpful. ########## spark/v3.4/spark/src/main/java/org/apache/iceberg/spark/data/vectorized/CometConstantColumnReader.java: ########## @@ -0,0 +1,61 @@ +/* + * 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.math.BigDecimal; +import java.nio.ByteBuffer; +import org.apache.comet.parquet.ConstantColumnReader; +import org.apache.iceberg.types.Types; +import org.apache.spark.sql.types.DataType; +import org.apache.spark.sql.types.DataTypes; +import org.apache.spark.sql.types.Decimal; +import org.apache.spark.sql.types.DecimalType; +import org.apache.spark.unsafe.types.UTF8String; + +class CometConstantColumnReader<T> extends CometColumnReader { + + CometConstantColumnReader(T value, Types.NestedField field) { + super(field); + // use delegate to set constant value on the native side to be consumed by native execution. + delegate = + new ConstantColumnReader(sparkType(), descriptor(), convertToSparkValue(value), false); + } + + @Override + public void setBatchSize(int batchSize) { + delegate.setBatchSize(batchSize); + this.batchSize = batchSize; + initialized = true; + } + + private Object convertToSparkValue(T value) { Review Comment: These conversions look correct to me - they match the internal type specified in Spark for these datatypes ########## spark/v3.4/spark/src/main/java/org/apache/iceberg/spark/data/vectorized/CometConstantColumnReader.java: ########## @@ -0,0 +1,61 @@ +/* + * 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.math.BigDecimal; +import java.nio.ByteBuffer; +import org.apache.comet.parquet.ConstantColumnReader; +import org.apache.iceberg.types.Types; +import org.apache.spark.sql.types.DataType; +import org.apache.spark.sql.types.DataTypes; +import org.apache.spark.sql.types.Decimal; +import org.apache.spark.sql.types.DecimalType; +import org.apache.spark.unsafe.types.UTF8String; + +class CometConstantColumnReader<T> extends CometColumnReader { + + CometConstantColumnReader(T value, Types.NestedField field) { + super(field); + // use delegate to set constant value on the native side to be consumed by native execution. + setDelegate( + new ConstantColumnReader(sparkType(), descriptor(), convertToSparkValue(value), false)); + } + + @Override + public void setBatchSize(int batchSize) { + delegate().setBatchSize(batchSize); + setBatchSize(batchSize); + setInitialized(true); + } + + private Object convertToSparkValue(T value) { + DataType dataType = sparkType(); + if (dataType == DataTypes.StringType && value instanceof String) { + return UTF8String.fromString((String) value); + } else if (dataType instanceof DecimalType && value instanceof BigDecimal) { + return Decimal.apply((BigDecimal) value); Review Comment: This looked dangerous at first. Maybe a comment to clarify that this is the Spark Decimal class (which can handle BigDecimal precision)? ########## spark/v3.4/spark/src/main/java/org/apache/iceberg/spark/data/vectorized/CometColumnReader.java: ########## @@ -0,0 +1,149 @@ +/* + * 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; + +class CometColumnReader implements VectorizedReader<CometVector> { + public static final int DEFAULT_BATCH_SIZE = 5000; Review Comment: Should this match the Comet batch size? https://github.com/apache/datafusion-comet/blob/e9649477c4f8b4c6906244c3cc6828b83f32f735/common/src/main/scala/org/apache/comet/CometConf.scala#L492 -- 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
