parthchandra commented on code in PR #2680: URL: https://github.com/apache/datafusion-comet/pull/2680#discussion_r2491481325
########## common/src/main/java/org/apache/comet/parquet/IcebergCometNativeBatchReader.java: ########## @@ -0,0 +1,79 @@ +/* + * 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.comet.parquet; + +import java.util.Map; + +import org.apache.hadoop.conf.Configuration; +import org.apache.spark.sql.catalyst.InternalRow; +import org.apache.spark.sql.execution.metric.SQLMetric; +import org.apache.spark.sql.types.StructType; + +/** + * A specialized NativeBatchReader for Iceberg that accepts ParquetMetadata as a JSON string. This + * allows Iceberg to pass metadata in serialized form with a two-step initialization pattern. + */ +public class IcebergCometNativeBatchReader extends NativeBatchReader { + + public IcebergCometNativeBatchReader(StructType requiredSchema) { + super(); + this.sparkSchema = requiredSchema; + } + + /** Initialize the reader using FileInfo instead of PartitionedFile. */ + public void init( + Configuration conf, + FileInfo fileInfo, + byte[] parquetMetadataBytes, + byte[] nativeFilter, + int capacity, + StructType dataSchema, + boolean isCaseSensitive, + boolean useFieldId, + boolean ignoreMissingIds, + boolean useLegacyDateTimestamp, + StructType partitionSchema, + InternalRow partitionValues, + AbstractColumnReader[] preInitializedReaders, + Map<String, SQLMetric> metrics) + throws Throwable { + + // Set parent fields + this.conf = conf; + this.fileInfo = fileInfo; + this.footer = new ParquetMetadataSerializer().deserialize(parquetMetadataBytes); + this.nativeFilter = nativeFilter; + this.capacity = capacity; + this.dataSchema = dataSchema; + this.isCaseSensitive = isCaseSensitive; + this.useFieldId = useFieldId; + this.ignoreMissingIds = ignoreMissingIds; Review Comment: Done ########## native/core/Cargo.toml: ########## @@ -76,8 +76,8 @@ datafusion-comet-objectstore-hdfs = { path = "../hdfs", optional = true, default reqwest = { version = "0.12", default-features = false, features = ["rustls-tls-native-roots", "http2"] } object_store_opendal = {version = "0.54.0", optional = true} hdfs-sys = {version = "0.3", optional = true, features = ["hdfs_3_3"]} -opendal = { version ="0.54.1", optional = true, features = ["services-hdfs"] } -uuid = "1.0" +opendal = { version ="0.54.0", optional = true, features = ["services-hdfs"] } Review Comment: Looks like this happened due to rebasing. Reverted. ########## common/src/main/java/org/apache/comet/parquet/NativeBatchReader.java: ########## @@ -421,9 +516,30 @@ public void init() throws Throwable { CometFileKeyUnwrapper keyUnwrapper = null; if (encryptionEnabled) { keyUnwrapper = new CometFileKeyUnwrapper(); - keyUnwrapper.storeDecryptionKeyRetriever(file.filePath().toString(), conf); + keyUnwrapper.storeDecryptionKeyRetriever(filePath, conf); } + // Filter out columns with preinitialized readers from sparkSchema before making the + // call to native + if (preInitializedReaders != null) { + StructType filteredSchema = new StructType(); + StructField[] sparkFields = sparkSchema.fields(); + for (int i = 0; i < sparkFields.length; i++) { + if (i >= preInitializedReaders.length || preInitializedReaders[i] == null) { + filteredSchema = filteredSchema.add(sparkFields[i]); + } + } + sparkSchema = filteredSchema; Review Comment: Yup. Fixed to match the fields by name. ########## common/src/main/java/org/apache/comet/parquet/NativeBatchReader.java: ########## @@ -421,9 +516,30 @@ public void init() throws Throwable { CometFileKeyUnwrapper keyUnwrapper = null; if (encryptionEnabled) { keyUnwrapper = new CometFileKeyUnwrapper(); - keyUnwrapper.storeDecryptionKeyRetriever(file.filePath().toString(), conf); + keyUnwrapper.storeDecryptionKeyRetriever(filePath, conf); } + // Filter out columns with preinitialized readers from sparkSchema before making the + // call to native + if (preInitializedReaders != null) { + StructType filteredSchema = new StructType(); + StructField[] sparkFields = sparkSchema.fields(); + for (int i = 0; i < sparkFields.length; i++) { + if (i >= preInitializedReaders.length || preInitializedReaders[i] == null) { + filteredSchema = filteredSchema.add(sparkFields[i]); + } + } + sparkSchema = filteredSchema; Review Comment: Yes, you're right. This is not entirely correct. Let me fix this. ########## common/src/main/java/org/apache/comet/parquet/IcebergCometNativeBatchReader.java: ########## @@ -0,0 +1,79 @@ +/* + * 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.comet.parquet; + +import java.util.Map; + +import org.apache.hadoop.conf.Configuration; +import org.apache.spark.sql.catalyst.InternalRow; +import org.apache.spark.sql.execution.metric.SQLMetric; +import org.apache.spark.sql.types.StructType; + +/** + * A specialized NativeBatchReader for Iceberg that accepts ParquetMetadata as a JSON string. This + * allows Iceberg to pass metadata in serialized form with a two-step initialization pattern. + */ +public class IcebergCometNativeBatchReader extends NativeBatchReader { + + public IcebergCometNativeBatchReader(StructType requiredSchema) { + super(); + this.sparkSchema = requiredSchema; + } + + /** Initialize the reader using FileInfo instead of PartitionedFile. */ + public void init( + Configuration conf, + FileInfo fileInfo, + byte[] parquetMetadataBytes, + byte[] nativeFilter, + int capacity, + StructType dataSchema, + boolean isCaseSensitive, + boolean useFieldId, + boolean ignoreMissingIds, + boolean useLegacyDateTimestamp, + StructType partitionSchema, + InternalRow partitionValues, + AbstractColumnReader[] preInitializedReaders, + Map<String, SQLMetric> metrics) + throws Throwable { + + // Set parent fields + this.conf = conf; + this.fileInfo = fileInfo; + this.footer = new ParquetMetadataSerializer().deserialize(parquetMetadataBytes); + this.nativeFilter = nativeFilter; + this.capacity = capacity; + this.dataSchema = dataSchema; + this.isCaseSensitive = isCaseSensitive; + this.useFieldId = useFieldId; + this.ignoreMissingIds = ignoreMissingIds; + this.partitionSchema = partitionSchema; + this.partitionValues = partitionValues; + this.preInitializedReaders = preInitializedReaders; Review Comment: Done ########## common/src/main/java/org/apache/comet/parquet/IcebergCometNativeBatchReader.java: ########## @@ -0,0 +1,79 @@ +/* + * 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.comet.parquet; + +import java.util.Map; + +import org.apache.hadoop.conf.Configuration; +import org.apache.spark.sql.catalyst.InternalRow; +import org.apache.spark.sql.execution.metric.SQLMetric; +import org.apache.spark.sql.types.StructType; + +/** + * A specialized NativeBatchReader for Iceberg that accepts ParquetMetadata as a JSON string. This Review Comment: Thank you for catching this. The first version I did used JSON, but this is more efficient. -- 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: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
