Github user felixcheung commented on a diff in the pull request:
https://github.com/apache/spark/pull/10480#discussion_r48515246
--- Diff: R/pkg/R/SQLContext.R ---
@@ -556,3 +556,61 @@ createExternalTable <- function(sqlContext, tableName,
path = NULL, source = NUL
sdf <- callJMethod(sqlContext, "createExternalTable", tableName, source,
options)
dataFrame(sdf)
}
+
+#' Create a DataFrame representing the database table accessible via JDBC
URL
+#'
+#' Additional JDBC database connection properties can be set (...)
+#'
+#' Only one of partitionColumn or predicates should be set. Partitions of
the table will be
+#' retrieved in parallel based on the `numPartitions` or by the predicates.
+#'
+#' Don't create too many partitions in parallel on a large cluster;
otherwise Spark might crash
+#' your external database systems.
+#'
+#' @param sqlContext SQLContext to use
+#' @param url JDBC database url of the form `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 lowerBound the minimum value of `partitionColumn` used to decide
partition stride
+#' @param upperBound the maximum value of `partitionColumn` used to decide
partition stride
+#' @param numPartitions the number of partitions, This, along with
`lowerBound` (inclusive),
+#' `upperBound` (exclusive), form partition strides
for generated WHERE
+#' clause expressions used to split the column
`partitionColumn` evenly.
+#' This defaults to SparkContext.defaultParallelism
when unset.
+#' @param predicates a list of conditions in the where clause; each one
defines one partition
+#' @return DataFrame
+#' @rdname read.jdbc
+#' @name read.jdbc
+#' @export
+#' @examples
+#'\dontrun{
+#' sc <- sparkR.init()
+#' sqlContext <- sparkRSQL.init(sc)
+#' jdbcUrl <- "jdbc:mysql://localhost:3306/databasename"
+#' df <- read.jdbc(sqlContext, jdbcUrl, "table", predicates =
list("field<=123"), user = "username")
+#' df2 <- read.jdbc(sqlContext, jdbcUrl, "table2", partitionColumn =
"index", lowerBound = 0,
+#' upperBound = 10000, user = "username", password =
"password")
+#' }
+
+read.jdbc <- function(sqlContext, url, tableName,
+ partitionColumn = NULL, lowerBound = NULL,
upperBound = NULL,
+ numPartitions = 0L, predicates = list(), ...) {
+ jprops <- envToJProperties(varargsToEnv(...))
+
+ read <- callJMethod(sqlContext, "read")
+ if (!is.null(partitionColumn)) {
+ if (is.null(numPartitions) || numPartitions == 0) {
--- End diff --
this is the matching behavior in Python API.
---
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 [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
