Github user hvanhovell commented on a diff in the pull request: https://github.com/apache/spark/pull/12268#discussion_r61258077 --- Diff: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/InferSchema.scala --- @@ -30,22 +30,37 @@ import org.apache.spark.sql.catalyst.util.DateTimeUtils import org.apache.spark.sql.types._ import org.apache.spark.unsafe.types.UTF8String -private[csv] object CSVInferSchema { +private[csv] object InferSchema { /** * Similar to the JSON schema inference * 1. Infer type of each row * 2. Merge row types to find common type * 3. Replace any null types with string type */ - def infer( - tokenRdd: RDD[Array[String]], - header: Array[String], - nullValue: String = ""): StructType = { + def infer(csv: RDD[String], options: CSVOptions): StructType = { --- End diff -- This looks very similar to `DefaultSource.inferSchema` why not move the common functionality into a single method?
--- 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