Github user gatorsmile commented on a diff in the pull request:
https://github.com/apache/spark/pull/16976#discussion_r120033528
--- Diff:
sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/csv/CSVSuite.scala
---
@@ -961,56 +968,121 @@ class CSVSuite extends QueryTest with
SharedSQLContext with SQLTestUtils {
}
test("SPARK-18699 put malformed records in a `columnNameOfCorruptRecord`
field") {
- val schema = new StructType().add("a", IntegerType).add("b",
TimestampType)
- val df1 = spark
- .read
- .option("mode", "PERMISSIVE")
- .schema(schema)
- .csv(testFile(valueMalformedFile))
- checkAnswer(df1,
- Row(null, null) ::
- Row(1, java.sql.Date.valueOf("1983-08-04")) ::
- Nil)
-
- // If `schema` has `columnNameOfCorruptRecord`, it should handle
corrupt records
- val columnNameOfCorruptRecord = "_unparsed"
- val schemaWithCorrField1 = schema.add(columnNameOfCorruptRecord,
StringType)
- val df2 = spark
- .read
- .option("mode", "PERMISSIVE")
- .option("columnNameOfCorruptRecord", columnNameOfCorruptRecord)
- .schema(schemaWithCorrField1)
- .csv(testFile(valueMalformedFile))
- checkAnswer(df2,
- Row(null, null, "0,2013-111-11 12:13:14") ::
- Row(1, java.sql.Date.valueOf("1983-08-04"), null) ::
- Nil)
-
- // We put a `columnNameOfCorruptRecord` field in the middle of a schema
- val schemaWithCorrField2 = new StructType()
- .add("a", IntegerType)
- .add(columnNameOfCorruptRecord, StringType)
- .add("b", TimestampType)
- val df3 = spark
- .read
- .option("mode", "PERMISSIVE")
- .option("columnNameOfCorruptRecord", columnNameOfCorruptRecord)
- .schema(schemaWithCorrField2)
- .csv(testFile(valueMalformedFile))
- checkAnswer(df3,
- Row(null, "0,2013-111-11 12:13:14", null) ::
- Row(1, null, java.sql.Date.valueOf("1983-08-04")) ::
- Nil)
-
- val errMsg = intercept[AnalysisException] {
- spark
+ Seq(false, true).foreach { wholeFile =>
+ val schema = new StructType().add("a", IntegerType).add("b",
TimestampType)
+ val df1 = spark
+ .read
+ .option("mode", "PERMISSIVE")
+ .option("wholeFile", wholeFile)
+ .schema(schema)
+ .csv(testFile(valueMalformedFile))
+ checkAnswer(df1,
+ Row(null, null) ::
+ Row(1, java.sql.Date.valueOf("1983-08-04")) ::
+ Nil)
+
+ // If `schema` has `columnNameOfCorruptRecord`, it should handle
corrupt records
+ val columnNameOfCorruptRecord = "_unparsed"
+ val schemaWithCorrField1 = schema.add(columnNameOfCorruptRecord,
StringType)
+ val df2 = spark
.read
.option("mode", "PERMISSIVE")
.option("columnNameOfCorruptRecord", columnNameOfCorruptRecord)
- .schema(schema.add(columnNameOfCorruptRecord, IntegerType))
+ .option("wholeFile", wholeFile)
+ .schema(schemaWithCorrField1)
.csv(testFile(valueMalformedFile))
- .collect
- }.getMessage
- assert(errMsg.startsWith("The field for corrupt records must be string
type and nullable"))
+ checkAnswer(df2,
+ Row(null, null, "0,2013-111-11 12:13:14") ::
+ Row(1, java.sql.Date.valueOf("1983-08-04"), null) ::
+ Nil)
+
+ // We put a `columnNameOfCorruptRecord` field in the middle of a
schema
+ val schemaWithCorrField2 = new StructType()
+ .add("a", IntegerType)
+ .add(columnNameOfCorruptRecord, StringType)
+ .add("b", TimestampType)
+ val df3 = spark
+ .read
+ .option("mode", "PERMISSIVE")
+ .option("columnNameOfCorruptRecord", columnNameOfCorruptRecord)
+ .option("wholeFile", wholeFile)
+ .schema(schemaWithCorrField2)
+ .csv(testFile(valueMalformedFile))
+ checkAnswer(df3,
+ Row(null, "0,2013-111-11 12:13:14", null) ::
+ Row(1, null, java.sql.Date.valueOf("1983-08-04")) ::
+ Nil)
+
+ val errMsg = intercept[AnalysisException] {
+ spark
+ .read
+ .option("mode", "PERMISSIVE")
+ .option("columnNameOfCorruptRecord", columnNameOfCorruptRecord)
+ .option("wholeFile", wholeFile)
+ .schema(schema.add(columnNameOfCorruptRecord, IntegerType))
+ .csv(testFile(valueMalformedFile))
+ .collect
+ }.getMessage
+ assert(errMsg.startsWith("The field for corrupt records must be
string type and nullable"))
+ }
+ }
+
+ test("SPARK-19610: Parse normal multi-line CSV files") {
+ val primitiveFieldAndType = Seq(
+ """"
+ |string","integer
+ |
+ |
+ |","long
+ |
+ |","bigInteger",double,boolean,null""".stripMargin,
+ """"this is a
+ |simple
+ |string.","
+ |
+ |10","
+ |21474836470","92233720368547758070","
+ |
+ |1.7976931348623157E308",true,""".stripMargin)
+
+ withTempPath { path =>
+
primitiveFieldAndType.toDF("value").coalesce(1).write.text(path.getAbsolutePath)
+
+ val df = spark.read
+ .option("header", true)
--- End diff --
For non-whole-file parsing, we should skip the first line for each csv file
(after we combine the partitioned files to a single file), right?
---
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
