Github user cloud-fan commented on a diff in the pull request:
https://github.com/apache/spark/pull/17492#discussion_r109307156
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonInferSchema.scala
---
@@ -202,41 +206,54 @@ private[sql] object JsonInferSchema {
private def withCorruptField(
struct: StructType,
- columnNameOfCorruptRecords: String): StructType = {
- if (!struct.fieldNames.contains(columnNameOfCorruptRecords)) {
- // If this given struct does not have a column used for corrupt
records,
- // add this field.
- val newFields: Array[StructField] =
- StructField(columnNameOfCorruptRecords, StringType, nullable =
true) +: struct.fields
- // Note: other code relies on this sorting for correctness, so don't
remove it!
- java.util.Arrays.sort(newFields, structFieldComparator)
- StructType(newFields)
- } else {
- // Otherwise, just return this struct.
+ other: DataType,
+ columnNameOfCorruptRecords: String,
+ parseMode: ParseMode) = parseMode match {
+ case PermissiveMode =>
+ // If we see any other data type at the root level, we get records
that cannot be
+ // parsed. So, we use the struct as the data type and add the
corrupt field to the schema.
+ if (!struct.fieldNames.contains(columnNameOfCorruptRecords)) {
+ // If this given struct does not have a column used for corrupt
records,
+ // add this field.
+ val newFields: Array[StructField] =
+ StructField(columnNameOfCorruptRecords, StringType, nullable =
true) +: struct.fields
+ // Note: other code relies on this sorting for correctness, so
don't remove it!
+ java.util.Arrays.sort(newFields, structFieldComparator)
+ StructType(newFields)
+ } else {
+ // Otherwise, just return this struct.
+ struct
+ }
+
+ case DropMalformedMode =>
+ // If corrupt record handling is disabled we retain the valid schema
and discard the other.
struct
- }
+
+ case FailFastMode =>
--- End diff --
When will we hit this branch? Seems never?
---
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 [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
