diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/csv/CSVOptions.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/csv/CSVOptions.scala index ec405994eadef..c6a80611ea7c4 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/csv/CSVOptions.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/csv/CSVOptions.scala @@ -166,8 +166,6 @@ class CSVOptions( val quoteAll = getBool("quoteAll", false) - val inputBufferSize = 128 - /** * The max error content length in CSV parser/writer exception message. */ @@ -259,7 +257,6 @@ class CSVOptions( settings.setIgnoreLeadingWhitespaces(ignoreLeadingWhiteSpaceInRead) settings.setIgnoreTrailingWhitespaces(ignoreTrailingWhiteSpaceInRead) settings.setReadInputOnSeparateThread(false) - settings.setInputBufferSize(inputBufferSize) settings.setMaxColumns(maxColumns) settings.setNullValue(nullValue) settings.setEmptyValue(emptyValueInRead) diff --git a/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/csv/CSVSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/csv/CSVSuite.scala index 30f0e45d04eab..3fe6ce773c012 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/csv/CSVSuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/csv/CSVSuite.scala @@ -2452,6 +2452,17 @@ abstract class CSVSuite assert(result.sameElements(exceptResults)) } } + + test("SPARK-34768: counting a long record with ignoreTrailingWhiteSpace set to true") { + val bufSize = 128 + val line = "X" * (bufSize - 1) + "| |" + withTempPath { path => + Seq(line).toDF.write.text(path.getAbsolutePath) + assert(spark.read.format("csv") + .option("delimiter", "|") + .option("ignoreTrailingWhiteSpace", "true").load(path.getAbsolutePath).count() == 1) + } + } } class CSVv1Suite extends CSVSuite {