Details
Minor Description
lineSep documentation says -
`lineSep` (default covers all `\r`, `\r\n` and `\n`): defines the line separator that should be used for parsing. Maximum length is 1 character.
Reference:
https://spark.apache.org/docs/latest/api/python/pyspark.sql.html#pyspark.sql.DataFrameReader
When reading csv file using spark
src_df = (spark.read
.option("header", "true")
.option("multiLine","true")
.option("escape", "ǁ")
.option("lineSep","\r\n")
.schema(materialusetype_Schema)
.option("badRecordsPath","/fh_badfile")
.csv("<path-to-csv>/crlf.csv")
)
Below is the stack trace:
java.lang.IllegalArgumentException: requirement failed: 'lineSep' can contain only 1 character.java.lang.IllegalArgumentException: requirement failed: 'lineSep' can contain only 1 character. at scala.Predef$.require(Predef.scala:281) at org.apache.spark.sql.catalyst.csv.CSVOptions.$anonfun$lineSeparator$1(CSVOptions.scala:209) at scala.Option.map(Option.scala:230) at org.apache.spark.sql.catalyst.csv.CSVOptions.<init>(CSVOptions.scala:207) at org.apache.spark.sql.catalyst.csv.CSVOptions.<init>(CSVOptions.scala:58) at org.apache.spark.sql.execution.datasources.csv.CSVFileFormat.buildReader(CSVFileFormat.scala:108) at org.apache.spark.sql.execution.datasources.FileFormat.buildReaderWithPartitionValues(FileFormat.scala:132) at org.apache.spark.sql.execution.datasources.FileFormat.buildReaderWithPartitionValues$(FileFormat.scala:123) at org.apache.spark.sql.execution.datasources.TextBasedFileFormat.buildReaderWithPartitionValues(FileFormat.scala:162) at org.apache.spark.sql.execution.FileSourceScanExec.inputRDD$lzycompute(DataSourceScanExec.scala:510) at org.apache.spark.sql.execution.FileSourceScanExec.inputRDD(DataSourceScanExec.scala:497) at org.apache.spark.sql.execution.FileSourceScanExec.doExecute(DataSourceScanExec.scala:692) at org.apache.spark.sql.execution.SparkPlan.$anonfun$execute$1(SparkPlan.scala:196) at org.apache.spark.sql.execution.SparkPlan.$anonfun$executeQuery$1(SparkPlan.scala:240) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:165) at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:236) at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:192) at org.apache.spark.sql.execution.collect.Collector$.collect(Collector.scala:79) at org.apache.spark.sql.execution.collect.Collector$.collect(Collector.scala:88) at org.apache.spark.sql.execution.collect.InternalRowFormat$.collect(cachedSparkResults.scala:61) at org.apache.spark.sql.execution.collect.InternalRowFormat$.collect(cachedSparkResults.scala:57) at org.apache.spark.sql.execution.ResultCacheManager.$anonfun$getOrComputeResultInternal$1(ResultCacheManager.scala:483) at scala.Option.getOrElse(Option.scala:189) at org.apache.spark.sql.execution.ResultCacheManager.getOrComputeResultInternal(ResultCacheManager.scala:483) at org.apache.spark.sql.execution.ResultCacheManager.getOrComputeResult(ResultCacheManager.scala:427) at org.apache.spark.sql.execution.CollectLimitExec.executeCollectResult(limit.scala:58) at org.apache.spark.sql.Dataset.collectResult(Dataset.scala:3013) at org.apache.spark.sql.Dataset.$anonfun$collectResult$1(Dataset.scala:3004) at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:3728) at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withCustomExecutionEnv$5(SQLExecution.scala:116) at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:248) at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withCustomExecutionEnv$1(SQLExecution.scala:101) at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:841) at org.apache.spark.sql.execution.SQLExecution$.withCustomExecutionEnv(SQLExecution.scala:77) at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:198) at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3726) at org.apache.spark.sql.Dataset.collectResult(Dataset.scala:3003)
