MaxGekk commented on code in PR #39258:
URL: https://github.com/apache/spark/pull/39258#discussion_r1062158983
##########
sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/csv/CSVSuite.scala:
##########
@@ -3138,13 +3141,54 @@ class CSVv1Suite extends CSVSuite {
super
.sparkConf
.set(SQLConf.USE_V1_SOURCE_LIST, "csv")
+
+ private val carsFile = "test-data/cars.csv"
+
+ test("test for FAILFAST parsing mode on CSV v1") {
+ Seq(false, true).foreach { multiLine =>
+ val exception = intercept[SparkException] {
+ spark.read
+ .format("csv")
+ .option("multiLine", multiLine)
+ .options(Map("header" -> "true", "mode" -> "failfast"))
+ .load(testFile(carsFile)).collect()
+ }
+
+ checkError(
+ exception = exception.getCause.asInstanceOf[SparkException],
+ errorClass = "_LEGACY_ERROR_TEMP_2177",
Review Comment:
Could you explain why did you add the test for the error class in the PR.
##########
sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/csv/CSVSuite.scala:
##########
@@ -3138,13 +3141,54 @@ class CSVv1Suite extends CSVSuite {
super
.sparkConf
.set(SQLConf.USE_V1_SOURCE_LIST, "csv")
+
+ private val carsFile = "test-data/cars.csv"
Review Comment:
The same is defined in the parent class (just make it as `protected`).
Please, remove it.
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/csv/UnivocityParser.scala:
##########
@@ -319,15 +319,17 @@ class UnivocityParser(
throw BadRecordException(
() => getCurrentInput,
() => None,
- QueryExecutionErrors.malformedCSVRecordError())
+ QueryExecutionErrors.malformedCSVRecordError(""))
}
+ val currentInput = getCurrentInput
Review Comment:
It is not used in regular cases, correct? Don't think we should introduce
additional overhead. Please, use `getCurrentInput` directly in errors.
##########
sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/csv/CSVSuite.scala:
##########
@@ -3138,13 +3141,54 @@ class CSVv1Suite extends CSVSuite {
super
.sparkConf
.set(SQLConf.USE_V1_SOURCE_LIST, "csv")
+
+ private val carsFile = "test-data/cars.csv"
+
+ test("test for FAILFAST parsing mode on CSV v1") {
+ Seq(false, true).foreach { multiLine =>
+ val exception = intercept[SparkException] {
+ spark.read
+ .format("csv")
+ .option("multiLine", multiLine)
+ .options(Map("header" -> "true", "mode" -> "failfast"))
+ .load(testFile(carsFile)).collect()
+ }
+
+ checkError(
+ exception = exception.getCause.asInstanceOf[SparkException],
+ errorClass = "_LEGACY_ERROR_TEMP_2177",
+ parameters = Map("failFastMode" -> "FAILFAST")
+ )
+ }
+ }
}
class CSVv2Suite extends CSVSuite {
override protected def sparkConf: SparkConf =
super
.sparkConf
.set(SQLConf.USE_V1_SOURCE_LIST, "")
+
+ private val carsFile = "test-data/cars.csv"
+
+ test("test for FAILFAST parsing mode on CSV v2") {
+ Seq(false, true).foreach { multiLine =>
+ val exception = intercept[SparkException] {
+ spark.read
+ .format("csv")
+ .option("multiLine", multiLine)
+ .options(Map("header" -> "true", "mode" -> "failfast"))
+ .load(testFile(carsFile)).collect()
+ }
+
+ checkError(
+ exception = exception.getCause.asInstanceOf[SparkException],
+ errorClass = "_LEGACY_ERROR_TEMP_2064",
Review Comment:
The same question like above. How this is related to assigning a name to
`_LEGACY_ERROR_TEMP_2149`?
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
