Github user cloud-fan commented on a diff in the pull request: https://github.com/apache/spark/pull/21299#discussion_r187611167 --- Diff: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonDataSource.scala --- @@ -99,12 +99,7 @@ object TextInputJsonDataSource extends JsonDataSource { def inferFromDataset(json: Dataset[String], parsedOptions: JSONOptions): StructType = { val sampled: Dataset[String] = JsonUtils.sample(json, parsedOptions) - val rdd: RDD[InternalRow] = sampled.queryExecution.toRdd - val rowParser = parsedOptions.encoding.map { enc => - CreateJacksonParser.internalRow(enc, _: JsonFactory, _: InternalRow) - }.getOrElse(CreateJacksonParser.internalRow(_: JsonFactory, _: InternalRow)) - - JsonInferSchema.infer(rdd, parsedOptions, rowParser) + JsonInferSchema.infer(sampled, parsedOptions, CreateJacksonParser.string) --- End diff -- @HyukjinKwon @MaxGekk can you take a look at the json changes? Thanks!
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org