aokolnychyi commented on code in PR #6716: URL: https://github.com/apache/iceberg/pull/6716#discussion_r1108060309
########## spark/v3.3/spark/src/main/java/org/apache/iceberg/spark/source/PositionDeletesRowReader.java: ########## @@ -0,0 +1,110 @@ +/* + * 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.source; + +import java.util.Map; +import java.util.Set; +import java.util.stream.Collectors; +import java.util.stream.Stream; +import org.apache.iceberg.ContentFile; +import org.apache.iceberg.PositionDeletesScanTask; +import org.apache.iceberg.ScanTaskGroup; +import org.apache.iceberg.Schema; +import org.apache.iceberg.Table; +import org.apache.iceberg.expressions.Expression; +import org.apache.iceberg.expressions.ExpressionUtil; +import org.apache.iceberg.io.CloseableIterator; +import org.apache.iceberg.io.InputFile; +import org.apache.iceberg.relocated.com.google.common.base.Preconditions; +import org.apache.iceberg.relocated.com.google.common.primitives.Ints; +import org.apache.spark.rdd.InputFileBlockHolder; +import org.apache.spark.sql.catalyst.InternalRow; +import org.apache.spark.sql.connector.read.PartitionReader; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +class PositionDeletesRowReader extends BaseRowReader<PositionDeletesScanTask> + implements PartitionReader<InternalRow> { + + private static final Logger LOG = LoggerFactory.getLogger(PositionDeletesRowReader.class); + + PositionDeletesRowReader(SparkInputPartition partition) { + this( + partition.table(), + partition.taskGroup(), + partition.expectedSchema(), + partition.isCaseSensitive()); + } + + PositionDeletesRowReader( + Table table, + ScanTaskGroup<PositionDeletesScanTask> taskGroup, + Schema expectedSchema, + boolean caseSensitive) { + + super(table, taskGroup, expectedSchema, caseSensitive); + + int numSplits = taskGroup.tasks().size(); + LOG.debug("Reading {} position delete file split(s) for table {}", numSplits, table.name()); + } + + @Override + protected Stream<ContentFile<?>> referencedFiles(PositionDeletesScanTask task) { + return Stream.of(task.file()); + } + + @Override + protected CloseableIterator<InternalRow> open(PositionDeletesScanTask task) { + Schema schema = expectedSchema(); + Map<Integer, ?> idToConstant = constantsMap(task, schema); + String filePath = task.file().path().toString(); + LOG.debug("Opening position delete file {}", filePath); + + // update the current file for Spark's filename() function + InputFileBlockHolder.set(filePath, task.start(), task.length()); + + InputFile inputFile = getInputFile(task.file().path().toString()); + Preconditions.checkNotNull( + inputFile, "Could not find InputFile associated with PositionDeleteScanTask"); + + // select out constant fields when pushing down filter to row reader Review Comment: What about defining a helper method with a reasonable name to abstract this logic away? ########## spark/v3.3/spark/src/main/java/org/apache/iceberg/spark/source/PositionDeletesRowReader.java: ########## @@ -0,0 +1,110 @@ +/* + * 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.source; + +import java.util.Map; +import java.util.Set; +import java.util.stream.Collectors; +import java.util.stream.Stream; +import org.apache.iceberg.ContentFile; +import org.apache.iceberg.PositionDeletesScanTask; +import org.apache.iceberg.ScanTaskGroup; +import org.apache.iceberg.Schema; +import org.apache.iceberg.Table; +import org.apache.iceberg.expressions.Expression; +import org.apache.iceberg.expressions.ExpressionUtil; +import org.apache.iceberg.io.CloseableIterator; +import org.apache.iceberg.io.InputFile; +import org.apache.iceberg.relocated.com.google.common.base.Preconditions; +import org.apache.iceberg.relocated.com.google.common.primitives.Ints; +import org.apache.spark.rdd.InputFileBlockHolder; +import org.apache.spark.sql.catalyst.InternalRow; +import org.apache.spark.sql.connector.read.PartitionReader; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +class PositionDeletesRowReader extends BaseRowReader<PositionDeletesScanTask> + implements PartitionReader<InternalRow> { + + private static final Logger LOG = LoggerFactory.getLogger(PositionDeletesRowReader.class); + + PositionDeletesRowReader(SparkInputPartition partition) { + this( + partition.table(), + partition.taskGroup(), + partition.expectedSchema(), + partition.isCaseSensitive()); + } + + PositionDeletesRowReader( + Table table, + ScanTaskGroup<PositionDeletesScanTask> taskGroup, + Schema expectedSchema, + boolean caseSensitive) { + + super(table, taskGroup, expectedSchema, caseSensitive); + + int numSplits = taskGroup.tasks().size(); + LOG.debug("Reading {} position delete file split(s) for table {}", numSplits, table.name()); + } + + @Override + protected Stream<ContentFile<?>> referencedFiles(PositionDeletesScanTask task) { + return Stream.of(task.file()); + } + + @Override + protected CloseableIterator<InternalRow> open(PositionDeletesScanTask task) { + Schema schema = expectedSchema(); Review Comment: nit: Do we gain much by defining this var? Isn't `expectedSchema()` simply a getter? ########## spark/v3.3/spark/src/main/java/org/apache/iceberg/spark/source/PositionDeletesRowReader.java: ########## @@ -0,0 +1,110 @@ +/* + * 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.source; + +import java.util.Map; +import java.util.Set; +import java.util.stream.Collectors; +import java.util.stream.Stream; +import org.apache.iceberg.ContentFile; +import org.apache.iceberg.PositionDeletesScanTask; +import org.apache.iceberg.ScanTaskGroup; +import org.apache.iceberg.Schema; +import org.apache.iceberg.Table; +import org.apache.iceberg.expressions.Expression; +import org.apache.iceberg.expressions.ExpressionUtil; +import org.apache.iceberg.io.CloseableIterator; +import org.apache.iceberg.io.InputFile; +import org.apache.iceberg.relocated.com.google.common.base.Preconditions; +import org.apache.iceberg.relocated.com.google.common.primitives.Ints; +import org.apache.spark.rdd.InputFileBlockHolder; +import org.apache.spark.sql.catalyst.InternalRow; +import org.apache.spark.sql.connector.read.PartitionReader; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +class PositionDeletesRowReader extends BaseRowReader<PositionDeletesScanTask> + implements PartitionReader<InternalRow> { + + private static final Logger LOG = LoggerFactory.getLogger(PositionDeletesRowReader.class); + + PositionDeletesRowReader(SparkInputPartition partition) { + this( + partition.table(), + partition.taskGroup(), + partition.expectedSchema(), + partition.isCaseSensitive()); + } + + PositionDeletesRowReader( + Table table, + ScanTaskGroup<PositionDeletesScanTask> taskGroup, + Schema expectedSchema, + boolean caseSensitive) { + + super(table, taskGroup, expectedSchema, caseSensitive); + + int numSplits = taskGroup.tasks().size(); + LOG.debug("Reading {} position delete file split(s) for table {}", numSplits, table.name()); + } + + @Override + protected Stream<ContentFile<?>> referencedFiles(PositionDeletesScanTask task) { + return Stream.of(task.file()); + } + + @Override + protected CloseableIterator<InternalRow> open(PositionDeletesScanTask task) { + Schema schema = expectedSchema(); + Map<Integer, ?> idToConstant = constantsMap(task, schema); Review Comment: nit: What about moving `idToConstant` after `getInputFile` cause it is first used only 30 lines later? ########## spark/v3.3/spark/src/main/java/org/apache/iceberg/spark/source/PositionDeletesRowReader.java: ########## @@ -0,0 +1,110 @@ +/* + * 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.source; + +import java.util.Map; +import java.util.Set; +import java.util.stream.Collectors; +import java.util.stream.Stream; +import org.apache.iceberg.ContentFile; +import org.apache.iceberg.PositionDeletesScanTask; +import org.apache.iceberg.ScanTaskGroup; +import org.apache.iceberg.Schema; +import org.apache.iceberg.Table; +import org.apache.iceberg.expressions.Expression; +import org.apache.iceberg.expressions.ExpressionUtil; +import org.apache.iceberg.io.CloseableIterator; +import org.apache.iceberg.io.InputFile; +import org.apache.iceberg.relocated.com.google.common.base.Preconditions; +import org.apache.iceberg.relocated.com.google.common.primitives.Ints; +import org.apache.spark.rdd.InputFileBlockHolder; +import org.apache.spark.sql.catalyst.InternalRow; +import org.apache.spark.sql.connector.read.PartitionReader; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +class PositionDeletesRowReader extends BaseRowReader<PositionDeletesScanTask> + implements PartitionReader<InternalRow> { + + private static final Logger LOG = LoggerFactory.getLogger(PositionDeletesRowReader.class); + + PositionDeletesRowReader(SparkInputPartition partition) { + this( + partition.table(), + partition.taskGroup(), + partition.expectedSchema(), + partition.isCaseSensitive()); + } + + PositionDeletesRowReader( + Table table, + ScanTaskGroup<PositionDeletesScanTask> taskGroup, + Schema expectedSchema, + boolean caseSensitive) { + + super(table, taskGroup, expectedSchema, caseSensitive); + + int numSplits = taskGroup.tasks().size(); + LOG.debug("Reading {} position delete file split(s) for table {}", numSplits, table.name()); + } + + @Override + protected Stream<ContentFile<?>> referencedFiles(PositionDeletesScanTask task) { + return Stream.of(task.file()); + } + + @Override + protected CloseableIterator<InternalRow> open(PositionDeletesScanTask task) { + Schema schema = expectedSchema(); + Map<Integer, ?> idToConstant = constantsMap(task, schema); + String filePath = task.file().path().toString(); + LOG.debug("Opening position delete file {}", filePath); + + // update the current file for Spark's filename() function + InputFileBlockHolder.set(filePath, task.start(), task.length()); + + InputFile inputFile = getInputFile(task.file().path().toString()); + Preconditions.checkNotNull( + inputFile, "Could not find InputFile associated with PositionDeleteScanTask"); + + // select out constant fields when pushing down filter to row reader + Set<Integer> fields = schema.idToName().keySet(); + Set<Integer> nonConstantFields = + fields.stream() + .filter(id -> schema.findField(id).type().isPrimitiveType()) + .collect(Collectors.toSet()); + nonConstantFields.removeAll(idToConstant.keySet()); + Expression residualWithoutConstants = + ExpressionUtil.extractByIdInclusive( + task.residual(), + task.spec().schema(), Review Comment: Question: Shouldn't this be `expectedSchema()`? ########## spark/v3.3/spark/src/main/java/org/apache/iceberg/spark/source/PositionDeletesRowReader.java: ########## @@ -0,0 +1,110 @@ +/* + * 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.source; + +import java.util.Map; +import java.util.Set; +import java.util.stream.Collectors; +import java.util.stream.Stream; +import org.apache.iceberg.ContentFile; +import org.apache.iceberg.PositionDeletesScanTask; +import org.apache.iceberg.ScanTaskGroup; +import org.apache.iceberg.Schema; +import org.apache.iceberg.Table; +import org.apache.iceberg.expressions.Expression; +import org.apache.iceberg.expressions.ExpressionUtil; +import org.apache.iceberg.io.CloseableIterator; +import org.apache.iceberg.io.InputFile; +import org.apache.iceberg.relocated.com.google.common.base.Preconditions; +import org.apache.iceberg.relocated.com.google.common.primitives.Ints; +import org.apache.spark.rdd.InputFileBlockHolder; +import org.apache.spark.sql.catalyst.InternalRow; +import org.apache.spark.sql.connector.read.PartitionReader; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +class PositionDeletesRowReader extends BaseRowReader<PositionDeletesScanTask> + implements PartitionReader<InternalRow> { + + private static final Logger LOG = LoggerFactory.getLogger(PositionDeletesRowReader.class); + + PositionDeletesRowReader(SparkInputPartition partition) { + this( + partition.table(), + partition.taskGroup(), + partition.expectedSchema(), + partition.isCaseSensitive()); + } + + PositionDeletesRowReader( + Table table, + ScanTaskGroup<PositionDeletesScanTask> taskGroup, + Schema expectedSchema, + boolean caseSensitive) { + + super(table, taskGroup, expectedSchema, caseSensitive); + + int numSplits = taskGroup.tasks().size(); + LOG.debug("Reading {} position delete file split(s) for table {}", numSplits, table.name()); + } + + @Override + protected Stream<ContentFile<?>> referencedFiles(PositionDeletesScanTask task) { + return Stream.of(task.file()); + } + + @Override + protected CloseableIterator<InternalRow> open(PositionDeletesScanTask task) { + Schema schema = expectedSchema(); + Map<Integer, ?> idToConstant = constantsMap(task, schema); + String filePath = task.file().path().toString(); + LOG.debug("Opening position delete file {}", filePath); + + // update the current file for Spark's filename() function + InputFileBlockHolder.set(filePath, task.start(), task.length()); + + InputFile inputFile = getInputFile(task.file().path().toString()); + Preconditions.checkNotNull( Review Comment: nit: I know we do this in other readers but what about this to stay on one line? ``` Preconditions.checkNotNull(inputFile, "Could not find InputFile associated with %s", task); ``` ########## spark/v3.3/spark/src/main/java/org/apache/iceberg/spark/source/PositionDeletesRowReader.java: ########## @@ -0,0 +1,110 @@ +/* + * 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.source; + +import java.util.Map; +import java.util.Set; +import java.util.stream.Collectors; +import java.util.stream.Stream; +import org.apache.iceberg.ContentFile; +import org.apache.iceberg.PositionDeletesScanTask; +import org.apache.iceberg.ScanTaskGroup; +import org.apache.iceberg.Schema; +import org.apache.iceberg.Table; +import org.apache.iceberg.expressions.Expression; +import org.apache.iceberg.expressions.ExpressionUtil; +import org.apache.iceberg.io.CloseableIterator; +import org.apache.iceberg.io.InputFile; +import org.apache.iceberg.relocated.com.google.common.base.Preconditions; +import org.apache.iceberg.relocated.com.google.common.primitives.Ints; +import org.apache.spark.rdd.InputFileBlockHolder; +import org.apache.spark.sql.catalyst.InternalRow; +import org.apache.spark.sql.connector.read.PartitionReader; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +class PositionDeletesRowReader extends BaseRowReader<PositionDeletesScanTask> + implements PartitionReader<InternalRow> { + + private static final Logger LOG = LoggerFactory.getLogger(PositionDeletesRowReader.class); + + PositionDeletesRowReader(SparkInputPartition partition) { + this( + partition.table(), + partition.taskGroup(), + partition.expectedSchema(), + partition.isCaseSensitive()); + } + + PositionDeletesRowReader( + Table table, + ScanTaskGroup<PositionDeletesScanTask> taskGroup, + Schema expectedSchema, + boolean caseSensitive) { + + super(table, taskGroup, expectedSchema, caseSensitive); + + int numSplits = taskGroup.tasks().size(); + LOG.debug("Reading {} position delete file split(s) for table {}", numSplits, table.name()); + } + + @Override + protected Stream<ContentFile<?>> referencedFiles(PositionDeletesScanTask task) { + return Stream.of(task.file()); + } + + @Override + protected CloseableIterator<InternalRow> open(PositionDeletesScanTask task) { + Schema schema = expectedSchema(); + Map<Integer, ?> idToConstant = constantsMap(task, schema); + String filePath = task.file().path().toString(); + LOG.debug("Opening position delete file {}", filePath); + + // update the current file for Spark's filename() function + InputFileBlockHolder.set(filePath, task.start(), task.length()); + + InputFile inputFile = getInputFile(task.file().path().toString()); + Preconditions.checkNotNull( + inputFile, "Could not find InputFile associated with PositionDeleteScanTask"); + + // select out constant fields when pushing down filter to row reader + Set<Integer> fields = schema.idToName().keySet(); + Set<Integer> nonConstantFields = Review Comment: nit: Should this be called `nonConstantFieldIds` as it holds IDs? ########## spark/v3.3/spark/src/main/java/org/apache/iceberg/spark/source/PositionDeletesRowReader.java: ########## @@ -0,0 +1,110 @@ +/* + * 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.source; + +import java.util.Map; +import java.util.Set; +import java.util.stream.Collectors; +import java.util.stream.Stream; +import org.apache.iceberg.ContentFile; +import org.apache.iceberg.PositionDeletesScanTask; +import org.apache.iceberg.ScanTaskGroup; +import org.apache.iceberg.Schema; +import org.apache.iceberg.Table; +import org.apache.iceberg.expressions.Expression; +import org.apache.iceberg.expressions.ExpressionUtil; +import org.apache.iceberg.io.CloseableIterator; +import org.apache.iceberg.io.InputFile; +import org.apache.iceberg.relocated.com.google.common.base.Preconditions; +import org.apache.iceberg.relocated.com.google.common.primitives.Ints; +import org.apache.spark.rdd.InputFileBlockHolder; +import org.apache.spark.sql.catalyst.InternalRow; +import org.apache.spark.sql.connector.read.PartitionReader; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +class PositionDeletesRowReader extends BaseRowReader<PositionDeletesScanTask> + implements PartitionReader<InternalRow> { + + private static final Logger LOG = LoggerFactory.getLogger(PositionDeletesRowReader.class); + + PositionDeletesRowReader(SparkInputPartition partition) { + this( + partition.table(), + partition.taskGroup(), + partition.expectedSchema(), + partition.isCaseSensitive()); + } + + PositionDeletesRowReader( + Table table, + ScanTaskGroup<PositionDeletesScanTask> taskGroup, + Schema expectedSchema, + boolean caseSensitive) { + + super(table, taskGroup, expectedSchema, caseSensitive); + + int numSplits = taskGroup.tasks().size(); + LOG.debug("Reading {} position delete file split(s) for table {}", numSplits, table.name()); + } + + @Override + protected Stream<ContentFile<?>> referencedFiles(PositionDeletesScanTask task) { + return Stream.of(task.file()); + } + + @Override + protected CloseableIterator<InternalRow> open(PositionDeletesScanTask task) { + Schema schema = expectedSchema(); + Map<Integer, ?> idToConstant = constantsMap(task, schema); + String filePath = task.file().path().toString(); + LOG.debug("Opening position delete file {}", filePath); + + // update the current file for Spark's filename() function + InputFileBlockHolder.set(filePath, task.start(), task.length()); + + InputFile inputFile = getInputFile(task.file().path().toString()); + Preconditions.checkNotNull( + inputFile, "Could not find InputFile associated with PositionDeleteScanTask"); + + // select out constant fields when pushing down filter to row reader + Set<Integer> fields = schema.idToName().keySet(); + Set<Integer> nonConstantFields = + fields.stream() + .filter(id -> schema.findField(id).type().isPrimitiveType()) + .collect(Collectors.toSet()); + nonConstantFields.removeAll(idToConstant.keySet()); Review Comment: Would it be more readable to have two filter predicates in the stream instead of a temp set? ``` Set<Integer> nonConstantFieldIds = expectedSchema().idToName().keySet().stream() .filter(id -> expectedSchema().findField(id).type().isPrimitiveType()) .filter(id -> !idToConstant.containsKey(id)) .collect(Collectors.toSet()); ``` -- 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
