spark git commit: [SPARK-12318][SPARKR] Save mode in SparkR should be error by default
Repository: spark Updated Branches: refs/heads/branch-1.6 16edd933d -> f81512729 [SPARK-12318][SPARKR] Save mode in SparkR should be error by default shivaram Please help review. Author: Jeff Zhang Closes #10290 from zjffdu/SPARK-12318. (cherry picked from commit 2eb5af5f0d3c424dc617bb1a18dd0210ea9ba0bc) Signed-off-by: Shivaram Venkataraman Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/f8151272 Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/f8151272 Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/f8151272 Branch: refs/heads/branch-1.6 Commit: f815127294c06320204d9affa4f35da7ec3a710d Parents: 16edd93 Author: Jeff Zhang Authored: Wed Dec 16 10:32:32 2015 -0800 Committer: Shivaram Venkataraman Committed: Wed Dec 16 10:48:54 2015 -0800 -- R/pkg/R/DataFrame.R | 10 +- docs/sparkr.md | 9 - 2 files changed, 13 insertions(+), 6 deletions(-) -- http://git-wip-us.apache.org/repos/asf/spark/blob/f8151272/R/pkg/R/DataFrame.R -- diff --git a/R/pkg/R/DataFrame.R b/R/pkg/R/DataFrame.R index 7292433..0cfa12b9 100644 --- a/R/pkg/R/DataFrame.R +++ b/R/pkg/R/DataFrame.R @@ -1925,7 +1925,7 @@ setMethod("except", #' @param df A SparkSQL DataFrame #' @param path A name for the table #' @param source A name for external data source -#' @param mode One of 'append', 'overwrite', 'error', 'ignore' save mode +#' @param mode One of 'append', 'overwrite', 'error', 'ignore' save mode (it is 'error' by default) #' #' @family DataFrame functions #' @rdname write.df @@ -1942,7 +1942,7 @@ setMethod("except", #' } setMethod("write.df", signature(df = "DataFrame", path = "character"), - function(df, path, source = NULL, mode = "append", ...){ + function(df, path, source = NULL, mode = "error", ...){ if (is.null(source)) { sqlContext <- get(".sparkRSQLsc", envir = .sparkREnv) source <- callJMethod(sqlContext, "getConf", "spark.sql.sources.default", @@ -1967,7 +1967,7 @@ setMethod("write.df", #' @export setMethod("saveDF", signature(df = "DataFrame", path = "character"), - function(df, path, source = NULL, mode = "append", ...){ + function(df, path, source = NULL, mode = "error", ...){ write.df(df, path, source, mode, ...) }) @@ -1990,7 +1990,7 @@ setMethod("saveDF", #' @param df A SparkSQL DataFrame #' @param tableName A name for the table #' @param source A name for external data source -#' @param mode One of 'append', 'overwrite', 'error', 'ignore' save mode +#' @param mode One of 'append', 'overwrite', 'error', 'ignore' save mode (it is 'error' by default) #' #' @family DataFrame functions #' @rdname saveAsTable @@ -2007,7 +2007,7 @@ setMethod("saveDF", setMethod("saveAsTable", signature(df = "DataFrame", tableName = "character", source = "character", mode = "character"), - function(df, tableName, source = NULL, mode="append", ...){ + function(df, tableName, source = NULL, mode="error", ...){ if (is.null(source)) { sqlContext <- get(".sparkRSQLsc", envir = .sparkREnv) source <- callJMethod(sqlContext, "getConf", "spark.sql.sources.default", http://git-wip-us.apache.org/repos/asf/spark/blob/f8151272/docs/sparkr.md -- diff --git a/docs/sparkr.md b/docs/sparkr.md index 0114878..9ddd2ed 100644 --- a/docs/sparkr.md +++ b/docs/sparkr.md @@ -148,7 +148,7 @@ printSchema(people) The data sources API can also be used to save out DataFrames into multiple file formats. For example we can save the DataFrame from the previous example -to a Parquet file using `write.df` +to a Parquet file using `write.df` (Until Spark 1.6, the default mode for writes was `append`. It was changed in Spark 1.7 to `error` to match the Scala API) {% highlight r %} @@ -387,3 +387,10 @@ The following functions are masked by the SparkR package: Since part of SparkR is modeled on the `dplyr` package, certain functions in SparkR share the same names with those in `dplyr`. Depending on the load order of the two packages, some functions from the package loaded first are masked by those in the package loaded after. In such case, prefix such calls with the package name, for instance, `SparkR::cume_dist(x)` or `dplyr::cume_dist(x)`. You can inspect the search path in R with [`search()`](https://stat.ethz.ch/R-manual/R-devel/library/base/html/search.html) + + +# Migration Guide + +## Upgrading From SparkR 1.6 to 1.7 + + - Until Spark 1.6, the default mode for writes was `append`. It was changed in Spark 1.7 to `error` to matc
spark git commit: [SPARK-12318][SPARKR] Save mode in SparkR should be error by default
Repository: spark Updated Branches: refs/heads/master 54c512ba9 -> 2eb5af5f0 [SPARK-12318][SPARKR] Save mode in SparkR should be error by default shivaram Please help review. Author: Jeff Zhang Closes #10290 from zjffdu/SPARK-12318. Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/2eb5af5f Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/2eb5af5f Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/2eb5af5f Branch: refs/heads/master Commit: 2eb5af5f0d3c424dc617bb1a18dd0210ea9ba0bc Parents: 54c512b Author: Jeff Zhang Authored: Wed Dec 16 10:32:32 2015 -0800 Committer: Shivaram Venkataraman Committed: Wed Dec 16 10:32:32 2015 -0800 -- R/pkg/R/DataFrame.R | 10 +- docs/sparkr.md | 9 - 2 files changed, 13 insertions(+), 6 deletions(-) -- http://git-wip-us.apache.org/repos/asf/spark/blob/2eb5af5f/R/pkg/R/DataFrame.R -- diff --git a/R/pkg/R/DataFrame.R b/R/pkg/R/DataFrame.R index 764597d..380a13f 100644 --- a/R/pkg/R/DataFrame.R +++ b/R/pkg/R/DataFrame.R @@ -1886,7 +1886,7 @@ setMethod("except", #' @param df A SparkSQL DataFrame #' @param path A name for the table #' @param source A name for external data source -#' @param mode One of 'append', 'overwrite', 'error', 'ignore' save mode +#' @param mode One of 'append', 'overwrite', 'error', 'ignore' save mode (it is 'error' by default) #' #' @family DataFrame functions #' @rdname write.df @@ -1903,7 +1903,7 @@ setMethod("except", #' } setMethod("write.df", signature(df = "DataFrame", path = "character"), - function(df, path, source = NULL, mode = "append", ...){ + function(df, path, source = NULL, mode = "error", ...){ if (is.null(source)) { sqlContext <- get(".sparkRSQLsc", envir = .sparkREnv) source <- callJMethod(sqlContext, "getConf", "spark.sql.sources.default", @@ -1928,7 +1928,7 @@ setMethod("write.df", #' @export setMethod("saveDF", signature(df = "DataFrame", path = "character"), - function(df, path, source = NULL, mode = "append", ...){ + function(df, path, source = NULL, mode = "error", ...){ write.df(df, path, source, mode, ...) }) @@ -1951,7 +1951,7 @@ setMethod("saveDF", #' @param df A SparkSQL DataFrame #' @param tableName A name for the table #' @param source A name for external data source -#' @param mode One of 'append', 'overwrite', 'error', 'ignore' save mode +#' @param mode One of 'append', 'overwrite', 'error', 'ignore' save mode (it is 'error' by default) #' #' @family DataFrame functions #' @rdname saveAsTable @@ -1968,7 +1968,7 @@ setMethod("saveDF", setMethod("saveAsTable", signature(df = "DataFrame", tableName = "character", source = "character", mode = "character"), - function(df, tableName, source = NULL, mode="append", ...){ + function(df, tableName, source = NULL, mode="error", ...){ if (is.null(source)) { sqlContext <- get(".sparkRSQLsc", envir = .sparkREnv) source <- callJMethod(sqlContext, "getConf", "spark.sql.sources.default", http://git-wip-us.apache.org/repos/asf/spark/blob/2eb5af5f/docs/sparkr.md -- diff --git a/docs/sparkr.md b/docs/sparkr.md index 0114878..9ddd2ed 100644 --- a/docs/sparkr.md +++ b/docs/sparkr.md @@ -148,7 +148,7 @@ printSchema(people) The data sources API can also be used to save out DataFrames into multiple file formats. For example we can save the DataFrame from the previous example -to a Parquet file using `write.df` +to a Parquet file using `write.df` (Until Spark 1.6, the default mode for writes was `append`. It was changed in Spark 1.7 to `error` to match the Scala API) {% highlight r %} @@ -387,3 +387,10 @@ The following functions are masked by the SparkR package: Since part of SparkR is modeled on the `dplyr` package, certain functions in SparkR share the same names with those in `dplyr`. Depending on the load order of the two packages, some functions from the package loaded first are masked by those in the package loaded after. In such case, prefix such calls with the package name, for instance, `SparkR::cume_dist(x)` or `dplyr::cume_dist(x)`. You can inspect the search path in R with [`search()`](https://stat.ethz.ch/R-manual/R-devel/library/base/html/search.html) + + +# Migration Guide + +## Upgrading From SparkR 1.6 to 1.7 + + - Until Spark 1.6, the default mode for writes was `append`. It was changed in Spark 1.7 to `error` to match the Scala API. - To unsubscribe, e-mail: comm