Github user cloud-fan commented on a diff in the pull request:
https://github.com/apache/spark/pull/15443#discussion_r83368143
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/StringHistogram.scala
---
@@ -0,0 +1,209 @@
+/*
+ * 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.catalyst.expressions.aggregate
+
+import java.nio.ByteBuffer
+
+import scala.collection.immutable.TreeMap
+import scala.collection.mutable
+
+import com.google.common.primitives.{Ints, Longs}
+
+import org.apache.spark.sql.catalyst.InternalRow
+import org.apache.spark.sql.catalyst.analysis.TypeCheckResult
+import
org.apache.spark.sql.catalyst.analysis.TypeCheckResult.{TypeCheckFailure,
TypeCheckSuccess}
+import org.apache.spark.sql.catalyst.expressions.{Expression,
ExpressionDescription}
+import
org.apache.spark.sql.catalyst.expressions.aggregate.StringHistogram.StringHistogramInfo
+import org.apache.spark.sql.catalyst.util.ArrayBasedMapData
+import org.apache.spark.sql.types._
+import org.apache.spark.unsafe.types.UTF8String
+
+/**
+ * The StringHistogram function returns the histogram bins - (distinct
value, frequency) pairs
+ * for a string column.
+ * @param child child expression that can produce column value with
`child.eval(inputRow)`
+ * @param numBinsExpression The maximum number of bins. When the number of
distinct values is
+ * larger than this, the function will return an
empty result.
+ */
+@ExpressionDescription(
+ usage = "_FUNC_(col, numBins) - Returns histogram bins with the maximum
number of bins allowed.")
+case class StringHistogram(
+ child: Expression,
+ numBinsExpression: Expression,
+ override val mutableAggBufferOffset: Int,
+ override val inputAggBufferOffset: Int) extends
TypedImperativeAggregate[StringHistogramInfo] {
+
+ def this(child: Expression, numBinsExpression: Expression) = {
+ this(child, numBinsExpression, 0, 0)
+ }
+
+ // Mark as lazy so that numBinsExpression is not evaluated during tree
transformation.
+ private lazy val numBins: Int =
numBinsExpression.eval().asInstanceOf[Int]
+
+ override def checkInputDataTypes(): TypeCheckResult = {
+ val defaultCheck = super.checkInputDataTypes()
+ if (defaultCheck.isFailure) {
+ defaultCheck
+ } else if (!numBinsExpression.foldable) {
+ TypeCheckFailure(s"The maximum number of bins provided must be a
constant literal")
+ } else if (numBins <= 0) {
+ TypeCheckFailure(
+ s"The maximum number of bins provided must be a positive integer
literal (current value" +
+ s" = $numBins)")
+ } else {
+ TypeCheckSuccess
+ }
+ }
+
+ override def update(buffer: StringHistogramInfo, input: InternalRow):
Unit = {
+ if (buffer.invalid) {
+ return
+ }
+ val evaluated = child.eval(input)
+ if (evaluated != null) {
+ val str = evaluated.asInstanceOf[UTF8String]
+ if (buffer.bins.contains(str)) {
+ buffer.bins.update(str, buffer.bins(str) + 1)
+ } else {
+ if (buffer.bins.size >= numBins) {
+ // clear the buffer and mark it as invalid
+ buffer.bins.clear()
+ buffer.invalid = true
+ } else {
+ buffer.bins.put(str, 1)
+ }
+ }
+ }
+ }
+
+ override def merge(buffer: StringHistogramInfo, other:
StringHistogramInfo): Unit = {
+ if (buffer.invalid || other.invalid) {
+ buffer.bins.clear()
+ return
+ }
+ other.bins.foreach { case (key, value) =>
+ if (buffer.bins.contains(key)) {
+ buffer.bins.update(key, buffer.bins(key) + value)
+ } else {
+ if (buffer.bins.size >= numBins) {
+ // clear the buffer and mark it as invalid
+ buffer.bins.clear()
+ buffer.invalid = true
+ return
+ } else {
+ buffer.bins.put(key, value)
+ }
+ }
+ }
+ }
+
+ override def eval(buffer: StringHistogramInfo): Any = {
+ val sorted = TreeMap[UTF8String, Long](buffer.bins.toSeq: _*)
--- End diff --
why sort it?
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
