Github user gatorsmile commented on a diff in the pull request:
https://github.com/apache/spark/pull/20894#discussion_r191026857
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVDataSource.scala
---
@@ -110,14 +114,81 @@ abstract class CSVDataSource extends Serializable {
}
}
-object CSVDataSource {
+object CSVDataSource extends Logging {
def apply(options: CSVOptions): CSVDataSource = {
if (options.multiLine) {
MultiLineCSVDataSource
} else {
TextInputCSVDataSource
}
}
+
+ /**
+ * Checks that column names in a CSV header and field names in the
schema are the same
+ * by taking into account case sensitivity.
+ */
+ def checkHeaderColumnNames(
+ schema: StructType,
+ columnNames: Array[String],
+ fileName: String,
+ enforceSchema: Boolean,
+ caseSensitive: Boolean): Unit = {
+ if (columnNames != null) {
+ val fieldNames = schema.map(_.name).toIndexedSeq
+ val (headerLen, schemaSize) = (columnNames.size, fieldNames.length)
+ var errorMessage: Option[String] = None
+
+ if (headerLen == schemaSize) {
+ var i = 0
+ while (errorMessage.isEmpty && i < headerLen) {
+ var (nameInSchema, nameInHeader) = (fieldNames(i),
columnNames(i))
+ if (!caseSensitive) {
+ nameInSchema = nameInSchema.toLowerCase
+ nameInHeader = nameInHeader.toLowerCase
+ }
+ if (nameInHeader != nameInSchema) {
+ errorMessage = Some(
+ s"""|CSV header is not conform to the schema.
--- End diff --
`is not conform` -> `does not conform`
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
