Github user gatorsmile commented on a diff in the pull request: https://github.com/apache/spark/pull/17315#discussion_r106840034 --- Diff: sql/core/src/main/scala/org/apache/spark/sql/DataFrameReader.scala --- @@ -382,11 +383,17 @@ class DataFrameReader private[sql](sparkSession: SparkSession) extends Logging { } verifyColumnNameOfCorruptRecord(schema, parsedOptions.columnNameOfCorruptRecord) + val dataSchema = StructType(schema.filterNot(_.name == parsedOptions.columnNameOfCorruptRecord)) val createParser = CreateJacksonParser.string _ val parsed = jsonDataset.rdd.mapPartitions { iter => - val parser = new JacksonParser(schema, parsedOptions) - iter.flatMap(parser.parse(_, createParser, UTF8String.fromString)) + val rawParser = new JacksonParser(dataSchema, parsedOptions) + val parser = new FailureSafeParser[String]( + input => rawParser.parse(input, createParser, UTF8String.fromString), + parsedOptions.parseMode, + schema, --- End diff -- How about passing `dataSchema` to `FailureSafeParser`? It can simplify the codes in `FailureSafeParser`
--- 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