This is an automated email from the ASF dual-hosted git repository. srowen pushed a commit to branch branch-2.4 in repository https://gitbox.apache.org/repos/asf/spark.git
The following commit(s) were added to refs/heads/branch-2.4 by this push: new a1471f9 [SPARK-28977][DOCS][SQL] Fix DataFrameReader.json docs to doc that partition column can be numeric, date or timestamp type a1471f9 is described below commit a1471f95a4b2ff2ff5c70403458d796429ee857a Author: Sean Owen <sean.o...@databricks.com> AuthorDate: Thu Sep 5 18:32:45 2019 +0900 [SPARK-28977][DOCS][SQL] Fix DataFrameReader.json docs to doc that partition column can be numeric, date or timestamp type ### What changes were proposed in this pull request? `DataFrameReader.json()` accepts a partition column that is of numeric, date or timestamp type, according to the implementation in `JDBCRelation.scala`. Update the scaladoc accordingly, to match the documentation in `sql-data-sources-jdbc.md` too. ### Why are the changes needed? scaladoc is incorrect. ### Does this PR introduce any user-facing change? No. ### How was this patch tested? N/A Closes #25687 from srowen/SPARK-28977. Authored-by: Sean Owen <sean.o...@databricks.com> Signed-off-by: HyukjinKwon <gurwls...@apache.org> --- R/pkg/R/SQLContext.R | 3 ++- python/pyspark/sql/readwriter.py | 3 ++- sql/core/src/main/scala/org/apache/spark/sql/DataFrameReader.scala | 3 ++- 3 files changed, 6 insertions(+), 3 deletions(-) diff --git a/R/pkg/R/SQLContext.R b/R/pkg/R/SQLContext.R index c819a7d..c281aa0 100644 --- a/R/pkg/R/SQLContext.R +++ b/R/pkg/R/SQLContext.R @@ -655,7 +655,8 @@ loadDF <- function(x = NULL, ...) { #' #' @param url JDBC database url of the form \code{jdbc:subprotocol:subname} #' @param tableName the name of the table in the external database -#' @param partitionColumn the name of a column of integral type that will be used for partitioning +#' @param partitionColumn the name of a column of numeric, date, or timestamp type +#' that will be used for partitioning. #' @param lowerBound the minimum value of \code{partitionColumn} used to decide partition stride #' @param upperBound the maximum value of \code{partitionColumn} used to decide partition stride #' @param numPartitions the number of partitions, This, along with \code{lowerBound} (inclusive), diff --git a/python/pyspark/sql/readwriter.py b/python/pyspark/sql/readwriter.py index ea7cc80..4396699 100644 --- a/python/pyspark/sql/readwriter.py +++ b/python/pyspark/sql/readwriter.py @@ -526,7 +526,8 @@ class DataFrameReader(OptionUtils): :param url: a JDBC URL of the form ``jdbc:subprotocol:subname`` :param table: the name of the table - :param column: the name of an integer column that will be used for partitioning; + :param column: the name of a column of numeric, date, or timestamp type + that will be used for partitioning; if this parameter is specified, then ``numPartitions``, ``lowerBound`` (inclusive), and ``upperBound`` (exclusive) will form partition strides for generated WHERE clause expressions used to split the column diff --git a/sql/core/src/main/scala/org/apache/spark/sql/DataFrameReader.scala b/sql/core/src/main/scala/org/apache/spark/sql/DataFrameReader.scala index 85cd3f0..c71f871 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/DataFrameReader.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/DataFrameReader.scala @@ -248,7 +248,8 @@ class DataFrameReader private[sql](sparkSession: SparkSession) extends Logging { * * @param url JDBC database url of the form `jdbc:subprotocol:subname`. * @param table Name of the table in the external database. - * @param columnName the name of a column of integral type that will be used for partitioning. + * @param columnName the name of a column of numeric, date, or timestamp type + * that will be used for partitioning. * @param lowerBound the minimum value of `columnName` used to decide partition stride. * @param upperBound the maximum value of `columnName` used to decide partition stride. * @param numPartitions the number of partitions. This, along with `lowerBound` (inclusive), --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org