Github user holdenk commented on a diff in the pull request: https://github.com/apache/spark/pull/14087#discussion_r70121449 --- Diff: sql/core/src/main/scala/org/apache/spark/sql/streaming/DataStreamReader.scala --- @@ -281,6 +281,31 @@ final class DataStreamReader private[sql](sparkSession: SparkSession) extends Lo @Experimental def text(path: String): DataFrame = format("text").load(path) + /** + * Loads text files and returns a [[Dataset]] of String. The underlying schema of the Dataset + * contains a single string column named "value". + * + * If the directory structure of the text files contains partitioning information, those are + * ignored in the resulting Dataset. To include partitioning information as columns, use `text`. + * + * Each line in the text files is a new element in the resulting Dataset. For example: + * {{{ + * // Scala: + * spark.read.textFile("/path/to/spark/README.md") + * + * // Java: + * spark.read().textFile("/path/to/spark/README.md") + * }}} + * + * @param path input path + * @since 2.0.0 + */ + def textFile(path: String): Dataset[String] = { + if (userSpecifiedSchema.nonEmpty) { + throw new AnalysisException("User specified schema not supported with `textFile`") --- End diff -- Since this check is presumably copied from the similar function in DataFrameReader, we should probably keep the exception the same as DataFrameReader (so either update it too or leave this as is). Also In the SQL code base we use "User specified" 24 times and "User-specified" 5 times.
--- 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