ODIn/spark-instrumented-optimizer
1
0
Fork 0
Code Issues Pull requests Projects Releases Wiki Activity

[SPARK-31261][SQL] Avoid npe when reading bad csv input with columnNameCorruptRecord specified

Browse source 
### What changes were proposed in this pull request?

SPARK-25387 avoids npe for bad csv input, but when reading bad csv input with `columnNameCorruptRecord` specified, `getCurrentInput` is called and it still throws npe.

### Why are the changes needed?

Bug fix.

### Does this PR introduce any user-facing change?

No.

### How was this patch tested?

Add a test.

Closes #28029 from wzhfy/corrupt_column_npe.

Authored-by: Zhenhua Wang <wzh_zju@163.com>
Signed-off-by: HyukjinKwon <gurwls223@apache.org>
This commit is contained in:
Zhenhua Wang 2020-03-29 13:30:14 +09:00 committed by HyukjinKwon
parent 34c7476cb5
commit 791d2ba346
2 changed files with 16 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

3
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/csv/UnivocityParser.scala
View file

@ -101,7 +101,8 @@ class UnivocityParser(
// Retrieve the raw record string.
private def getCurrentInput: UTF8String = {
UTF8String.fromString(tokenizer.getContext.currentParsedContent().stripLineEnd)
val currentContent = tokenizer.getContext.currentParsedContent()
if (currentContent == null) null else UTF8String.fromString(currentContent.stripLineEnd)
}
// This parser first picks some tokens from the input tokens, according to the required schema,

14
sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/csv/CSVSuite.scala
View file

@ -1897,6 +1897,20 @@ abstract class CSVSuite extends QueryTest with SharedSparkSession with TestCsvDa
assert(spark.read.csv(input).collect().toSet == Set(Row()))
}
test("SPARK-31261: bad csv input with `columnNameCorruptRecord` should not cause NPE") {
val schema = StructType(
StructField("a", IntegerType) :: StructField("_corrupt_record", StringType) :: Nil)
val input = spark.createDataset(Seq("\u0000\u0000\u0001234"))
checkAnswer(
spark.read
.option("columnNameOfCorruptRecord", "_corrupt_record")
.schema(schema)
.csv(input),
Row(null, null))
assert(spark.read.csv(input).collect().toSet == Set(Row()))
}
test("field names of inferred schema shouldn't compare to the first row") {
val input = Seq("1,2").toDS()
val df = spark.read.option("enforceSchema", false).csv(input)