Repository: spark Updated Branches: refs/heads/master 9a2b65a3c -> b29702913
http://git-wip-us.apache.org/repos/asf/spark/blob/b2970291/sql/core/src/main/java/org/apache/spark/sql/vectorized/ColumnarRow.java ---------------------------------------------------------------------- diff --git a/sql/core/src/main/java/org/apache/spark/sql/vectorized/ColumnarRow.java b/sql/core/src/main/java/org/apache/spark/sql/vectorized/ColumnarRow.java new file mode 100644 index 0000000..3c6656d --- /dev/null +++ b/sql/core/src/main/java/org/apache/spark/sql/vectorized/ColumnarRow.java @@ -0,0 +1,205 @@ +/* + * 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.spark.sql.vectorized; + +import org.apache.spark.sql.catalyst.InternalRow; +import org.apache.spark.sql.catalyst.expressions.GenericInternalRow; +import org.apache.spark.sql.catalyst.util.MapData; +import org.apache.spark.sql.types.*; +import org.apache.spark.unsafe.types.CalendarInterval; +import org.apache.spark.unsafe.types.UTF8String; + +/** + * Row abstraction in {@link ColumnVector}. + */ +public final class ColumnarRow extends InternalRow { + // The data for this row. + // E.g. the value of 3rd int field is `data.getChildColumn(3).getInt(rowId)`. + private final ColumnVector data; + private final int rowId; + private final int numFields; + + public ColumnarRow(ColumnVector data, int rowId) { + assert (data.dataType() instanceof StructType); + this.data = data; + this.rowId = rowId; + this.numFields = ((StructType) data.dataType()).size(); + } + + @Override + public int numFields() { return numFields; } + + /** + * Revisit this. This is expensive. This is currently only used in test paths. + */ + @Override + public InternalRow copy() { + GenericInternalRow row = new GenericInternalRow(numFields); + for (int i = 0; i < numFields(); i++) { + if (isNullAt(i)) { + row.setNullAt(i); + } else { + DataType dt = data.getChildColumn(i).dataType(); + if (dt instanceof BooleanType) { + row.setBoolean(i, getBoolean(i)); + } else if (dt instanceof ByteType) { + row.setByte(i, getByte(i)); + } else if (dt instanceof ShortType) { + row.setShort(i, getShort(i)); + } else if (dt instanceof IntegerType) { + row.setInt(i, getInt(i)); + } else if (dt instanceof LongType) { + row.setLong(i, getLong(i)); + } else if (dt instanceof FloatType) { + row.setFloat(i, getFloat(i)); + } else if (dt instanceof DoubleType) { + row.setDouble(i, getDouble(i)); + } else if (dt instanceof StringType) { + row.update(i, getUTF8String(i).copy()); + } else if (dt instanceof BinaryType) { + row.update(i, getBinary(i)); + } else if (dt instanceof DecimalType) { + DecimalType t = (DecimalType)dt; + row.setDecimal(i, getDecimal(i, t.precision(), t.scale()), t.precision()); + } else if (dt instanceof DateType) { + row.setInt(i, getInt(i)); + } else if (dt instanceof TimestampType) { + row.setLong(i, getLong(i)); + } else { + throw new RuntimeException("Not implemented. " + dt); + } + } + } + return row; + } + + @Override + public boolean anyNull() { + throw new UnsupportedOperationException(); + } + + @Override + public boolean isNullAt(int ordinal) { return data.getChildColumn(ordinal).isNullAt(rowId); } + + @Override + public boolean getBoolean(int ordinal) { return data.getChildColumn(ordinal).getBoolean(rowId); } + + @Override + public byte getByte(int ordinal) { return data.getChildColumn(ordinal).getByte(rowId); } + + @Override + public short getShort(int ordinal) { return data.getChildColumn(ordinal).getShort(rowId); } + + @Override + public int getInt(int ordinal) { return data.getChildColumn(ordinal).getInt(rowId); } + + @Override + public long getLong(int ordinal) { return data.getChildColumn(ordinal).getLong(rowId); } + + @Override + public float getFloat(int ordinal) { return data.getChildColumn(ordinal).getFloat(rowId); } + + @Override + public double getDouble(int ordinal) { return data.getChildColumn(ordinal).getDouble(rowId); } + + @Override + public Decimal getDecimal(int ordinal, int precision, int scale) { + if (data.getChildColumn(ordinal).isNullAt(rowId)) return null; + return data.getChildColumn(ordinal).getDecimal(rowId, precision, scale); + } + + @Override + public UTF8String getUTF8String(int ordinal) { + if (data.getChildColumn(ordinal).isNullAt(rowId)) return null; + return data.getChildColumn(ordinal).getUTF8String(rowId); + } + + @Override + public byte[] getBinary(int ordinal) { + if (data.getChildColumn(ordinal).isNullAt(rowId)) return null; + return data.getChildColumn(ordinal).getBinary(rowId); + } + + @Override + public CalendarInterval getInterval(int ordinal) { + if (data.getChildColumn(ordinal).isNullAt(rowId)) return null; + final int months = data.getChildColumn(ordinal).getChildColumn(0).getInt(rowId); + final long microseconds = data.getChildColumn(ordinal).getChildColumn(1).getLong(rowId); + return new CalendarInterval(months, microseconds); + } + + @Override + public ColumnarRow getStruct(int ordinal, int numFields) { + if (data.getChildColumn(ordinal).isNullAt(rowId)) return null; + return data.getChildColumn(ordinal).getStruct(rowId); + } + + @Override + public ColumnarArray getArray(int ordinal) { + if (data.getChildColumn(ordinal).isNullAt(rowId)) return null; + return data.getChildColumn(ordinal).getArray(rowId); + } + + @Override + public MapData getMap(int ordinal) { + throw new UnsupportedOperationException(); + } + + @Override + public Object get(int ordinal, DataType dataType) { + if (dataType instanceof BooleanType) { + return getBoolean(ordinal); + } else if (dataType instanceof ByteType) { + return getByte(ordinal); + } else if (dataType instanceof ShortType) { + return getShort(ordinal); + } else if (dataType instanceof IntegerType) { + return getInt(ordinal); + } else if (dataType instanceof LongType) { + return getLong(ordinal); + } else if (dataType instanceof FloatType) { + return getFloat(ordinal); + } else if (dataType instanceof DoubleType) { + return getDouble(ordinal); + } else if (dataType instanceof StringType) { + return getUTF8String(ordinal); + } else if (dataType instanceof BinaryType) { + return getBinary(ordinal); + } else if (dataType instanceof DecimalType) { + DecimalType t = (DecimalType) dataType; + return getDecimal(ordinal, t.precision(), t.scale()); + } else if (dataType instanceof DateType) { + return getInt(ordinal); + } else if (dataType instanceof TimestampType) { + return getLong(ordinal); + } else if (dataType instanceof ArrayType) { + return getArray(ordinal); + } else if (dataType instanceof StructType) { + return getStruct(ordinal, ((StructType)dataType).fields().length); + } else if (dataType instanceof MapType) { + return getMap(ordinal); + } else { + throw new UnsupportedOperationException("Datatype not supported " + dataType); + } + } + + @Override + public void update(int ordinal, Object value) { throw new UnsupportedOperationException(); } + + @Override + public void setNullAt(int ordinal) { throw new UnsupportedOperationException(); } +} http://git-wip-us.apache.org/repos/asf/spark/blob/b2970291/sql/core/src/main/scala/org/apache/spark/sql/execution/ColumnarBatchScan.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/ColumnarBatchScan.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/ColumnarBatchScan.scala index 782cec5..5617046 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/execution/ColumnarBatchScan.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/ColumnarBatchScan.scala @@ -20,13 +20,13 @@ package org.apache.spark.sql.execution import org.apache.spark.sql.catalyst.expressions.UnsafeRow import org.apache.spark.sql.catalyst.expressions.codegen.{CodegenContext, ExprCode} import org.apache.spark.sql.execution.metric.SQLMetrics -import org.apache.spark.sql.execution.vectorized.{ColumnarBatch, ColumnVector} import org.apache.spark.sql.types.DataType +import org.apache.spark.sql.vectorized.{ColumnarBatch, ColumnVector} /** * Helper trait for abstracting scan functionality using - * [[org.apache.spark.sql.execution.vectorized.ColumnarBatch]]es. + * [[ColumnarBatch]]es. */ private[sql] trait ColumnarBatchScan extends CodegenSupport { http://git-wip-us.apache.org/repos/asf/spark/blob/b2970291/sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/HashAggregateExec.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/HashAggregateExec.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/HashAggregateExec.scala index 9a6f1c6..ce3c688 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/HashAggregateExec.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/HashAggregateExec.scala @@ -28,7 +28,7 @@ import org.apache.spark.sql.catalyst.expressions.codegen._ import org.apache.spark.sql.catalyst.plans.physical._ import org.apache.spark.sql.execution._ import org.apache.spark.sql.execution.metric.{SQLMetric, SQLMetrics} -import org.apache.spark.sql.execution.vectorized.{ColumnarRow, MutableColumnarRow} +import org.apache.spark.sql.execution.vectorized.MutableColumnarRow import org.apache.spark.sql.types.{DecimalType, StringType, StructType} import org.apache.spark.unsafe.KVIterator import org.apache.spark.util.Utils http://git-wip-us.apache.org/repos/asf/spark/blob/b2970291/sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/VectorizedHashMapGenerator.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/VectorizedHashMapGenerator.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/VectorizedHashMapGenerator.scala index 0380ee8..0cf9b53 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/VectorizedHashMapGenerator.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/VectorizedHashMapGenerator.scala @@ -20,8 +20,9 @@ package org.apache.spark.sql.execution.aggregate import org.apache.spark.sql.catalyst.InternalRow import org.apache.spark.sql.catalyst.expressions.aggregate.AggregateExpression import org.apache.spark.sql.catalyst.expressions.codegen.CodegenContext -import org.apache.spark.sql.execution.vectorized.{ColumnarBatch, MutableColumnarRow, OnHeapColumnVector} +import org.apache.spark.sql.execution.vectorized.{MutableColumnarRow, OnHeapColumnVector} import org.apache.spark.sql.types._ +import org.apache.spark.sql.vectorized.ColumnarBatch /** * This is a helper class to generate an append-only vectorized hash map that can act as a 'cache' http://git-wip-us.apache.org/repos/asf/spark/blob/b2970291/sql/core/src/main/scala/org/apache/spark/sql/execution/arrow/ArrowConverters.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/arrow/ArrowConverters.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/arrow/ArrowConverters.scala index bcfc412..bcd1aa0 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/execution/arrow/ArrowConverters.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/arrow/ArrowConverters.scala @@ -32,8 +32,8 @@ import org.apache.spark.TaskContext import org.apache.spark.api.java.JavaRDD import org.apache.spark.sql.{DataFrame, SQLContext} import org.apache.spark.sql.catalyst.InternalRow -import org.apache.spark.sql.execution.vectorized.{ArrowColumnVector, ColumnarBatch, ColumnVector} import org.apache.spark.sql.types._ +import org.apache.spark.sql.vectorized.{ArrowColumnVector, ColumnarBatch, ColumnVector} import org.apache.spark.util.Utils http://git-wip-us.apache.org/repos/asf/spark/blob/b2970291/sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/InMemoryTableScanExec.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/InMemoryTableScanExec.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/InMemoryTableScanExec.scala index 3e73393..933b975 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/InMemoryTableScanExec.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/InMemoryTableScanExec.scala @@ -27,6 +27,7 @@ import org.apache.spark.sql.catalyst.plans.physical.{HashPartitioning, Partition import org.apache.spark.sql.execution.{ColumnarBatchScan, LeafExecNode, WholeStageCodegenExec} import org.apache.spark.sql.execution.vectorized._ import org.apache.spark.sql.types._ +import org.apache.spark.sql.vectorized.{ColumnarBatch, ColumnVector} case class InMemoryTableScanExec( http://git-wip-us.apache.org/repos/asf/spark/blob/b2970291/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FileScanRDD.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FileScanRDD.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FileScanRDD.scala index 8731ee8..835ce98 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FileScanRDD.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FileScanRDD.scala @@ -26,7 +26,7 @@ import org.apache.spark.deploy.SparkHadoopUtil import org.apache.spark.rdd.{InputFileBlockHolder, RDD} import org.apache.spark.sql.SparkSession import org.apache.spark.sql.catalyst.InternalRow -import org.apache.spark.sql.execution.vectorized.ColumnarBatch +import org.apache.spark.sql.vectorized.ColumnarBatch import org.apache.spark.util.NextIterator /** http://git-wip-us.apache.org/repos/asf/spark/blob/b2970291/sql/core/src/main/scala/org/apache/spark/sql/execution/python/ArrowPythonRunner.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/python/ArrowPythonRunner.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/python/ArrowPythonRunner.scala index 5cc8ed3..dc5ba96 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/execution/python/ArrowPythonRunner.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/python/ArrowPythonRunner.scala @@ -30,8 +30,8 @@ import org.apache.spark._ import org.apache.spark.api.python._ import org.apache.spark.sql.catalyst.InternalRow import org.apache.spark.sql.execution.arrow.{ArrowUtils, ArrowWriter} -import org.apache.spark.sql.execution.vectorized.{ArrowColumnVector, ColumnarBatch, ColumnVector} import org.apache.spark.sql.types._ +import org.apache.spark.sql.vectorized.{ArrowColumnVector, ColumnarBatch, ColumnVector} import org.apache.spark.util.Utils /** http://git-wip-us.apache.org/repos/asf/spark/blob/b2970291/sql/core/src/test/scala/org/apache/spark/sql/execution/arrow/ArrowWriterSuite.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/test/scala/org/apache/spark/sql/execution/arrow/ArrowWriterSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/execution/arrow/ArrowWriterSuite.scala index 508c116..c42bc60 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/execution/arrow/ArrowWriterSuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/execution/arrow/ArrowWriterSuite.scala @@ -20,8 +20,8 @@ package org.apache.spark.sql.execution.arrow import org.apache.spark.SparkFunSuite import org.apache.spark.sql.catalyst.InternalRow import org.apache.spark.sql.catalyst.util.ArrayData -import org.apache.spark.sql.execution.vectorized.ArrowColumnVector import org.apache.spark.sql.types._ +import org.apache.spark.sql.vectorized.ArrowColumnVector import org.apache.spark.unsafe.types.UTF8String class ArrowWriterSuite extends SparkFunSuite { http://git-wip-us.apache.org/repos/asf/spark/blob/b2970291/sql/core/src/test/scala/org/apache/spark/sql/execution/vectorized/ArrowColumnVectorSuite.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/test/scala/org/apache/spark/sql/execution/vectorized/ArrowColumnVectorSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/execution/vectorized/ArrowColumnVectorSuite.scala index 03490ad..7304803 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/execution/vectorized/ArrowColumnVectorSuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/execution/vectorized/ArrowColumnVectorSuite.scala @@ -23,6 +23,7 @@ import org.apache.arrow.vector.complex._ import org.apache.spark.SparkFunSuite import org.apache.spark.sql.execution.arrow.ArrowUtils import org.apache.spark.sql.types._ +import org.apache.spark.sql.vectorized.ArrowColumnVector import org.apache.spark.unsafe.types.UTF8String class ArrowColumnVectorSuite extends SparkFunSuite { http://git-wip-us.apache.org/repos/asf/spark/blob/b2970291/sql/core/src/test/scala/org/apache/spark/sql/execution/vectorized/ColumnVectorSuite.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/test/scala/org/apache/spark/sql/execution/vectorized/ColumnVectorSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/execution/vectorized/ColumnVectorSuite.scala index 54b31ce..944240f 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/execution/vectorized/ColumnVectorSuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/execution/vectorized/ColumnVectorSuite.scala @@ -21,10 +21,10 @@ import org.scalatest.BeforeAndAfterEach import org.apache.spark.SparkFunSuite import org.apache.spark.sql.catalyst.expressions.SpecificInternalRow -import org.apache.spark.sql.catalyst.util.ArrayData import org.apache.spark.sql.execution.columnar.ColumnAccessor import org.apache.spark.sql.execution.columnar.compression.ColumnBuilderHelper import org.apache.spark.sql.types._ +import org.apache.spark.sql.vectorized.ColumnarArray import org.apache.spark.unsafe.types.UTF8String class ColumnVectorSuite extends SparkFunSuite with BeforeAndAfterEach { http://git-wip-us.apache.org/repos/asf/spark/blob/b2970291/sql/core/src/test/scala/org/apache/spark/sql/execution/vectorized/ColumnarBatchSuite.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/test/scala/org/apache/spark/sql/execution/vectorized/ColumnarBatchSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/execution/vectorized/ColumnarBatchSuite.scala index 7848ebd..675f06b 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/execution/vectorized/ColumnarBatchSuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/execution/vectorized/ColumnarBatchSuite.scala @@ -33,6 +33,7 @@ import org.apache.spark.sql.{RandomDataGenerator, Row} import org.apache.spark.sql.catalyst.InternalRow import org.apache.spark.sql.execution.arrow.ArrowUtils import org.apache.spark.sql.types._ +import org.apache.spark.sql.vectorized.{ArrowColumnVector, ColumnarBatch, ColumnVector} import org.apache.spark.unsafe.Platform import org.apache.spark.unsafe.types.CalendarInterval @@ -918,10 +919,7 @@ class ColumnarBatchSuite extends SparkFunSuite { assert(it.hasNext == false) // Reset and add 3 rows - batch.reset() - assert(batch.numRows() == 0) - assert(batch.rowIterator().hasNext == false) - + columns.foreach(_.reset()) // Add rows [NULL, 2.2, 2, "abc"], [3, NULL, 3, ""], [4, 4.4, 4, "world] columns(0).putNull(0) columns(1).putDouble(0, 2.2) --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org
