Repository: spark Updated Branches: refs/heads/master 3e7dc8296 -> 69993217f
[SPARK-24807][CORE] Adding files/jars twice: output a warning and add a note ## What changes were proposed in this pull request? In the PR, I propose to output an warning if the `addFile()` or `addJar()` methods are callled more than once for the same path. Currently, overwriting of already added files is not supported. New comments and warning are reflected the existing behaviour. Author: Maxim Gekk <maxim.g...@databricks.com> Closes #21771 from MaxGekk/warning-on-adding-file. Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/69993217 Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/69993217 Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/69993217 Branch: refs/heads/master Commit: 69993217fc4f5e5e41a297702389e86fe534dc2f Parents: 3e7dc82 Author: Maxim Gekk <maxim.g...@databricks.com> Authored: Sat Jul 14 22:07:49 2018 -0700 Committer: Xiao Li <gatorsm...@gmail.com> Committed: Sat Jul 14 22:07:49 2018 -0700 ---------------------------------------------------------------------- R/pkg/R/context.R | 2 ++ core/src/main/scala/org/apache/spark/SparkContext.scala | 12 ++++++++++++ .../org/apache/spark/api/java/JavaSparkContext.scala | 6 ++++++ python/pyspark/context.py | 4 ++++ 4 files changed, 24 insertions(+) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/69993217/R/pkg/R/context.R ---------------------------------------------------------------------- diff --git a/R/pkg/R/context.R b/R/pkg/R/context.R index 8ec727d..3e996a5 100644 --- a/R/pkg/R/context.R +++ b/R/pkg/R/context.R @@ -305,6 +305,8 @@ setCheckpointDirSC <- function(sc, dirName) { #' Currently directories are only supported for Hadoop-supported filesystems. #' Refer Hadoop-supported filesystems at \url{https://wiki.apache.org/hadoop/HCFS}. #' +#' Note: A path can be added only once. Subsequent additions of the same path are ignored. +#' #' @rdname spark.addFile #' @param path The path of the file to be added #' @param recursive Whether to add files recursively from the path. Default is FALSE. http://git-wip-us.apache.org/repos/asf/spark/blob/69993217/core/src/main/scala/org/apache/spark/SparkContext.scala ---------------------------------------------------------------------- diff --git a/core/src/main/scala/org/apache/spark/SparkContext.scala b/core/src/main/scala/org/apache/spark/SparkContext.scala index 74bfb5d..531384a 100644 --- a/core/src/main/scala/org/apache/spark/SparkContext.scala +++ b/core/src/main/scala/org/apache/spark/SparkContext.scala @@ -1496,6 +1496,8 @@ class SparkContext(config: SparkConf) extends Logging { * @param path can be either a local file, a file in HDFS (or other Hadoop-supported * filesystems), or an HTTP, HTTPS or FTP URI. To access the file in Spark jobs, * use `SparkFiles.get(fileName)` to find its download location. + * + * @note A path can be added only once. Subsequent additions of the same path are ignored. */ def addFile(path: String): Unit = { addFile(path, false) @@ -1516,6 +1518,8 @@ class SparkContext(config: SparkConf) extends Logging { * use `SparkFiles.get(fileName)` to find its download location. * @param recursive if true, a directory can be given in `path`. Currently directories are * only supported for Hadoop-supported filesystems. + * + * @note A path can be added only once. Subsequent additions of the same path are ignored. */ def addFile(path: String, recursive: Boolean): Unit = { val uri = new Path(path).toUri @@ -1555,6 +1559,9 @@ class SparkContext(config: SparkConf) extends Logging { Utils.fetchFile(uri.toString, new File(SparkFiles.getRootDirectory()), conf, env.securityManager, hadoopConfiguration, timestamp, useCache = false) postEnvironmentUpdate() + } else { + logWarning(s"The path $path has been added already. Overwriting of added paths " + + "is not supported in the current version.") } } @@ -1803,6 +1810,8 @@ class SparkContext(config: SparkConf) extends Logging { * * @param path can be either a local file, a file in HDFS (or other Hadoop-supported filesystems), * an HTTP, HTTPS or FTP URI, or local:/path for a file on every worker node. + * + * @note A path can be added only once. Subsequent additions of the same path are ignored. */ def addJar(path: String) { def addJarFile(file: File): String = { @@ -1849,6 +1858,9 @@ class SparkContext(config: SparkConf) extends Logging { if (addedJars.putIfAbsent(key, timestamp).isEmpty) { logInfo(s"Added JAR $path at $key with timestamp $timestamp") postEnvironmentUpdate() + } else { + logWarning(s"The jar $path has been added already. Overwriting of added jars " + + "is not supported in the current version.") } } } http://git-wip-us.apache.org/repos/asf/spark/blob/69993217/core/src/main/scala/org/apache/spark/api/java/JavaSparkContext.scala ---------------------------------------------------------------------- diff --git a/core/src/main/scala/org/apache/spark/api/java/JavaSparkContext.scala b/core/src/main/scala/org/apache/spark/api/java/JavaSparkContext.scala index f1936bf..09c8384 100644 --- a/core/src/main/scala/org/apache/spark/api/java/JavaSparkContext.scala +++ b/core/src/main/scala/org/apache/spark/api/java/JavaSparkContext.scala @@ -668,6 +668,8 @@ class JavaSparkContext(val sc: SparkContext) * The `path` passed can be either a local file, a file in HDFS (or other Hadoop-supported * filesystems), or an HTTP, HTTPS or FTP URI. To access the file in Spark jobs, * use `SparkFiles.get(fileName)` to find its download location. + * + * @note A path can be added only once. Subsequent additions of the same path are ignored. */ def addFile(path: String) { sc.addFile(path) @@ -681,6 +683,8 @@ class JavaSparkContext(val sc: SparkContext) * * A directory can be given if the recursive option is set to true. Currently directories are only * supported for Hadoop-supported filesystems. + * + * @note A path can be added only once. Subsequent additions of the same path are ignored. */ def addFile(path: String, recursive: Boolean): Unit = { sc.addFile(path, recursive) @@ -690,6 +694,8 @@ class JavaSparkContext(val sc: SparkContext) * Adds a JAR dependency for all tasks to be executed on this SparkContext in the future. * The `path` passed can be either a local file, a file in HDFS (or other Hadoop-supported * filesystems), or an HTTP, HTTPS or FTP URI. + * + * @note A path can be added only once. Subsequent additions of the same path are ignored. */ def addJar(path: String) { sc.addJar(path) http://git-wip-us.apache.org/repos/asf/spark/blob/69993217/python/pyspark/context.py ---------------------------------------------------------------------- diff --git a/python/pyspark/context.py b/python/pyspark/context.py index ede3b6a..2cb3117 100644 --- a/python/pyspark/context.py +++ b/python/pyspark/context.py @@ -847,6 +847,8 @@ class SparkContext(object): A directory can be given if the recursive option is set to True. Currently directories are only supported for Hadoop-supported filesystems. + .. note:: A path can be added only once. Subsequent additions of the same path are ignored. + >>> from pyspark import SparkFiles >>> path = os.path.join(tempdir, "test.txt") >>> with open(path, "w") as testFile: @@ -867,6 +869,8 @@ class SparkContext(object): SparkContext in the future. The C{path} passed can be either a local file, a file in HDFS (or other Hadoop-supported filesystems), or an HTTP, HTTPS or FTP URI. + + .. note:: A path can be added only once. Subsequent additions of the same path are ignored. """ self.addFile(path) (dirname, filename) = os.path.split(path) # dirname may be directory or HDFS/S3 prefix --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org