maropu commented on a change in pull request #29966:
URL: https://github.com/apache/spark/pull/29966#discussion_r533820823
##########
File path: core/src/test/scala/org/apache/spark/SparkContextSuite.scala
##########
@@ -366,6 +366,29 @@ class SparkContextSuite extends SparkFunSuite with
LocalSparkContext with Eventu
}
}
+ test("SPARK-33084: add jar when path contains comma") {
+ withTempDir { tmpDir =>
+ val tmpJar = File.createTempFile("Test,UDTF", ".jar", tmpDir)
+ sc = new SparkContext(new
SparkConf().setAppName("test").setMaster("local"))
+ sc.addJar(tmpJar.getAbsolutePath)
+ assert(sc.listJars().exists(_.contains("Test,UDTF")))
+
+ val jarPath = "hdfs:///no/path/to/Test,UDTF1.jar"
+ sc.addJar(jarPath)
+ // Add jar failed since file not exists
+ assert(!sc.listJars().exists(_.contains("/no/path/to/Test,UDTF.jar")))
+
+ Seq("http", "https", "ftp").foreach { scheme =>
+ val badURL = s"$scheme://user:pwd/path/Test,UDTF_${scheme}.jar"
+ val e1 = intercept[MalformedURLException] {
Review comment:
nit: `e1` -> `e`
##########
File path: core/src/test/scala/org/apache/spark/SparkContextSuite.scala
##########
@@ -955,6 +978,121 @@ class SparkContextSuite extends SparkFunSuite with
LocalSparkContext with Eventu
.set(EXECUTOR_ALLOW_SPARK_CONTEXT, true)).stop()
}
}
+
+ test("SPARK-33084: Add jar support ivy url -- default transitive = false") {
+ sc = new SparkContext(new
SparkConf().setAppName("test").setMaster("local-cluster[3, 1, 1024]"))
+ sc.addJar("ivy://org.apache.hive:hive-storage-api:2.7.0")
+
assert(sc.listJars().exists(_.contains("org.apache.hive_hive-storage-api-2.7.0.jar")))
+
assert(!sc.listJars().exists(_.contains("commons-lang_commons-lang-2.6.jar")))
+
+ sc.addJar("ivy://org.apache.hive:hive-storage-api:2.7.0?transitive=true")
+
assert(sc.listJars().exists(_.contains("commons-lang_commons-lang-2.6.jar")))
+ }
+
+ test("SPARK-33084: Add jar support ivy url -- invalid transitive use default
false") {
+ sc = new SparkContext(new
SparkConf().setAppName("test").setMaster("local-cluster[3, 1, 1024]"))
+ sc.addJar("ivy://org.apache.hive:hive-storage-api:2.7.0?transitive=foo")
+
assert(sc.listJars().exists(_.contains("org.apache.hive_hive-storage-api-2.7.0.jar")))
+ assert(!sc.listJars().exists(_.contains("org.slf4j_slf4j-api-1.7.10.jar")))
+
assert(!sc.listJars().exists(_.contains("commons-lang_commons-lang-2.6.jar")))
+ }
+
+ test("SPARK-33084: Add jar support ivy url -- transitive=true will download
dependency jars") {
+ sc = new SparkContext(new
SparkConf().setAppName("test").setMaster("local-cluster[3, 1, 1024]"))
+ sc.addJar("ivy://org.apache.hive:hive-storage-api:2.7.0?transitive=true")
+
assert(sc.listJars().exists(_.contains("org.apache.hive_hive-storage-api-2.7.0.jar")))
+ assert(sc.listJars().exists(_.contains("org.slf4j_slf4j-api-1.7.10.jar")))
+
assert(sc.listJars().exists(_.contains("commons-lang_commons-lang-2.6.jar")))
+ }
+
+ test("SPARK-33084: Add jar support ivy url -- test exclude param when
transitive=true") {
+ sc = new SparkContext(new
SparkConf().setAppName("test").setMaster("local-cluster[3, 1, 1024]"))
+ sc.addJar("ivy://org.apache.hive:hive-storage-api:2.7.0" +
+ "?exclude=commons-lang:commons-lang&transitive=true")
+
assert(sc.listJars().exists(_.contains("org.apache.hive_hive-storage-api-2.7.0.jar")))
+ assert(sc.listJars().exists(_.contains("org.slf4j_slf4j-api-1.7.10.jar")))
+
assert(!sc.listJars().exists(_.contains("commons-lang_commons-lang-2.6.jar")))
+ }
+
+ test("SPARK-33084: Add jar support ivy url -- test different version") {
+ sc = new SparkContext(new
SparkConf().setAppName("test").setMaster("local-cluster[3, 1, 1024]"))
+ sc.addJar("ivy://org.apache.hive:hive-storage-api:2.7.0")
+
assert(sc.listJars().exists(_.contains("org.apache.hive_hive-storage-api-2.7.0.jar")))
+ sc.addJar("ivy://org.apache.hive:hive-storage-api:2.6.0")
+
assert(sc.listJars().exists(_.contains("org.apache.hive_hive-storage-api-2.6.0.jar")))
Review comment:
Btw, this behaviour is the same with hive?
##########
File path: core/src/main/scala/org/apache/spark/SparkContext.scala
##########
@@ -1919,18 +1919,26 @@ class SparkContext(config: SparkConf) extends Logging {
// A JAR file which exists only on the driver node
case "file" => addLocalJarFile(new File(uri.getPath))
// A JAR file which exists locally on every worker node
- case "local" => "file:" + uri.getPath
+ case "local" => Seq("file:" + uri.getPath)
+ case "ivy" =>
+ // Since `new Path(path).toUri` will lose query information,
+ // so here we use `URI.create(path)`
+ DependencyUtils.resolveMavenDependencies(URI.create(path))
case _ => checkRemoteJarFile(path)
}
}
- if (key != null) {
+ if (keys.nonEmpty) {
val timestamp = if (addedOnSubmit) startTime else
System.currentTimeMillis
- if (addedJars.putIfAbsent(key, timestamp).isEmpty) {
- logInfo(s"Added JAR $path at $key with timestamp $timestamp")
+ val (added, existed) = keys.partition(addedJars.putIfAbsent(_,
timestamp).isEmpty)
+ if (added.nonEmpty) {
+ logInfo(s"Added jar or dependency jars of ivy URI with $path" +
Review comment:
nit: How about changing this message depending on the schema?
##########
File path: core/src/test/scala/org/apache/spark/SparkContextSuite.scala
##########
@@ -955,6 +978,121 @@ class SparkContextSuite extends SparkFunSuite with
LocalSparkContext with Eventu
.set(EXECUTOR_ALLOW_SPARK_CONTEXT, true)).stop()
}
}
+
+ test("SPARK-33084: Add jar support ivy url -- default transitive = false") {
+ sc = new SparkContext(new
SparkConf().setAppName("test").setMaster("local-cluster[3, 1, 1024]"))
+ sc.addJar("ivy://org.apache.hive:hive-storage-api:2.7.0")
+
assert(sc.listJars().exists(_.contains("org.apache.hive_hive-storage-api-2.7.0.jar")))
+
assert(!sc.listJars().exists(_.contains("commons-lang_commons-lang-2.6.jar")))
+
+ sc.addJar("ivy://org.apache.hive:hive-storage-api:2.7.0?transitive=true")
+
assert(sc.listJars().exists(_.contains("commons-lang_commons-lang-2.6.jar")))
+ }
+
+ test("SPARK-33084: Add jar support ivy url -- invalid transitive use default
false") {
+ sc = new SparkContext(new
SparkConf().setAppName("test").setMaster("local-cluster[3, 1, 1024]"))
+ sc.addJar("ivy://org.apache.hive:hive-storage-api:2.7.0?transitive=foo")
+
assert(sc.listJars().exists(_.contains("org.apache.hive_hive-storage-api-2.7.0.jar")))
+ assert(!sc.listJars().exists(_.contains("org.slf4j_slf4j-api-1.7.10.jar")))
+
assert(!sc.listJars().exists(_.contains("commons-lang_commons-lang-2.6.jar")))
+ }
+
+ test("SPARK-33084: Add jar support ivy url -- transitive=true will download
dependency jars") {
+ sc = new SparkContext(new
SparkConf().setAppName("test").setMaster("local-cluster[3, 1, 1024]"))
+ sc.addJar("ivy://org.apache.hive:hive-storage-api:2.7.0?transitive=true")
+
assert(sc.listJars().exists(_.contains("org.apache.hive_hive-storage-api-2.7.0.jar")))
+ assert(sc.listJars().exists(_.contains("org.slf4j_slf4j-api-1.7.10.jar")))
+
assert(sc.listJars().exists(_.contains("commons-lang_commons-lang-2.6.jar")))
+ }
+
+ test("SPARK-33084: Add jar support ivy url -- test exclude param when
transitive=true") {
+ sc = new SparkContext(new
SparkConf().setAppName("test").setMaster("local-cluster[3, 1, 1024]"))
+ sc.addJar("ivy://org.apache.hive:hive-storage-api:2.7.0" +
+ "?exclude=commons-lang:commons-lang&transitive=true")
+
assert(sc.listJars().exists(_.contains("org.apache.hive_hive-storage-api-2.7.0.jar")))
+ assert(sc.listJars().exists(_.contains("org.slf4j_slf4j-api-1.7.10.jar")))
+
assert(!sc.listJars().exists(_.contains("commons-lang_commons-lang-2.6.jar")))
+ }
+
+ test("SPARK-33084: Add jar support ivy url -- test different version") {
+ sc = new SparkContext(new
SparkConf().setAppName("test").setMaster("local-cluster[3, 1, 1024]"))
+ sc.addJar("ivy://org.apache.hive:hive-storage-api:2.7.0")
+
assert(sc.listJars().exists(_.contains("org.apache.hive_hive-storage-api-2.7.0.jar")))
+ sc.addJar("ivy://org.apache.hive:hive-storage-api:2.6.0")
+
assert(sc.listJars().exists(_.contains("org.apache.hive_hive-storage-api-2.6.0.jar")))
+ }
+
+ test("SPARK-33084: Add jar support ivy url -- test invalid param") {
+ sc = new SparkContext(new
SparkConf().setAppName("test").setMaster("local-cluster[3, 1, 1024]"))
+ sc.addJar("ivy://org.apache.hive:hive-storage-api:2.7.0?invalidParam=foo")
+
assert(sc.listJars().exists(_.contains("org.apache.hive_hive-storage-api-2.7.0.jar")))
+ }
+
+ test("SPARK-33084: Add jar support ivy url -- test multiple transitive
params") {
+ sc = new SparkContext(new
SparkConf().setAppName("test").setMaster("local-cluster[3, 1, 1024]"))
+ sc.addJar("ivy://org.apache.hive:hive-storage-api:2.7.0?" +
+ "transitive=true&transitive=false&transitive=invalidValue")
Review comment:
Could you leave some comments about which param should win when having
multiple transitives?
##########
File path: core/src/test/scala/org/apache/spark/SparkContextSuite.scala
##########
@@ -955,6 +978,121 @@ class SparkContextSuite extends SparkFunSuite with
LocalSparkContext with Eventu
.set(EXECUTOR_ALLOW_SPARK_CONTEXT, true)).stop()
}
}
+
+ test("SPARK-33084: Add jar support ivy url -- default transitive = false") {
+ sc = new SparkContext(new
SparkConf().setAppName("test").setMaster("local-cluster[3, 1, 1024]"))
+ sc.addJar("ivy://org.apache.hive:hive-storage-api:2.7.0")
+
assert(sc.listJars().exists(_.contains("org.apache.hive_hive-storage-api-2.7.0.jar")))
+
assert(!sc.listJars().exists(_.contains("commons-lang_commons-lang-2.6.jar")))
+
+ sc.addJar("ivy://org.apache.hive:hive-storage-api:2.7.0?transitive=true")
+
assert(sc.listJars().exists(_.contains("commons-lang_commons-lang-2.6.jar")))
+ }
+
+ test("SPARK-33084: Add jar support ivy url -- invalid transitive use default
false") {
+ sc = new SparkContext(new
SparkConf().setAppName("test").setMaster("local-cluster[3, 1, 1024]"))
+ sc.addJar("ivy://org.apache.hive:hive-storage-api:2.7.0?transitive=foo")
+
assert(sc.listJars().exists(_.contains("org.apache.hive_hive-storage-api-2.7.0.jar")))
+ assert(!sc.listJars().exists(_.contains("org.slf4j_slf4j-api-1.7.10.jar")))
+
assert(!sc.listJars().exists(_.contains("commons-lang_commons-lang-2.6.jar")))
+ }
+
+ test("SPARK-33084: Add jar support ivy url -- transitive=true will download
dependency jars") {
+ sc = new SparkContext(new
SparkConf().setAppName("test").setMaster("local-cluster[3, 1, 1024]"))
+ sc.addJar("ivy://org.apache.hive:hive-storage-api:2.7.0?transitive=true")
+
assert(sc.listJars().exists(_.contains("org.apache.hive_hive-storage-api-2.7.0.jar")))
+ assert(sc.listJars().exists(_.contains("org.slf4j_slf4j-api-1.7.10.jar")))
+
assert(sc.listJars().exists(_.contains("commons-lang_commons-lang-2.6.jar")))
+ }
+
+ test("SPARK-33084: Add jar support ivy url -- test exclude param when
transitive=true") {
+ sc = new SparkContext(new
SparkConf().setAppName("test").setMaster("local-cluster[3, 1, 1024]"))
+ sc.addJar("ivy://org.apache.hive:hive-storage-api:2.7.0" +
+ "?exclude=commons-lang:commons-lang&transitive=true")
+
assert(sc.listJars().exists(_.contains("org.apache.hive_hive-storage-api-2.7.0.jar")))
+ assert(sc.listJars().exists(_.contains("org.slf4j_slf4j-api-1.7.10.jar")))
+
assert(!sc.listJars().exists(_.contains("commons-lang_commons-lang-2.6.jar")))
+ }
+
+ test("SPARK-33084: Add jar support ivy url -- test different version") {
+ sc = new SparkContext(new
SparkConf().setAppName("test").setMaster("local-cluster[3, 1, 1024]"))
+ sc.addJar("ivy://org.apache.hive:hive-storage-api:2.7.0")
+
assert(sc.listJars().exists(_.contains("org.apache.hive_hive-storage-api-2.7.0.jar")))
+ sc.addJar("ivy://org.apache.hive:hive-storage-api:2.6.0")
+
assert(sc.listJars().exists(_.contains("org.apache.hive_hive-storage-api-2.6.0.jar")))
Review comment:
Could you add the jars first, then check if the dependent jars co-exist
in `sc.listJars`?
##########
File path: core/src/test/scala/org/apache/spark/SparkContextSuite.scala
##########
@@ -955,6 +978,121 @@ class SparkContextSuite extends SparkFunSuite with
LocalSparkContext with Eventu
.set(EXECUTOR_ALLOW_SPARK_CONTEXT, true)).stop()
}
}
+
+ test("SPARK-33084: Add jar support ivy url -- default transitive = false") {
+ sc = new SparkContext(new
SparkConf().setAppName("test").setMaster("local-cluster[3, 1, 1024]"))
+ sc.addJar("ivy://org.apache.hive:hive-storage-api:2.7.0")
+
assert(sc.listJars().exists(_.contains("org.apache.hive_hive-storage-api-2.7.0.jar")))
+
assert(!sc.listJars().exists(_.contains("commons-lang_commons-lang-2.6.jar")))
+
+ sc.addJar("ivy://org.apache.hive:hive-storage-api:2.7.0?transitive=true")
+
assert(sc.listJars().exists(_.contains("commons-lang_commons-lang-2.6.jar")))
+ }
+
+ test("SPARK-33084: Add jar support ivy url -- invalid transitive use default
false") {
+ sc = new SparkContext(new
SparkConf().setAppName("test").setMaster("local-cluster[3, 1, 1024]"))
+ sc.addJar("ivy://org.apache.hive:hive-storage-api:2.7.0?transitive=foo")
+
assert(sc.listJars().exists(_.contains("org.apache.hive_hive-storage-api-2.7.0.jar")))
+ assert(!sc.listJars().exists(_.contains("org.slf4j_slf4j-api-1.7.10.jar")))
+
assert(!sc.listJars().exists(_.contains("commons-lang_commons-lang-2.6.jar")))
+ }
+
+ test("SPARK-33084: Add jar support ivy url -- transitive=true will download
dependency jars") {
+ sc = new SparkContext(new
SparkConf().setAppName("test").setMaster("local-cluster[3, 1, 1024]"))
+ sc.addJar("ivy://org.apache.hive:hive-storage-api:2.7.0?transitive=true")
+
assert(sc.listJars().exists(_.contains("org.apache.hive_hive-storage-api-2.7.0.jar")))
+ assert(sc.listJars().exists(_.contains("org.slf4j_slf4j-api-1.7.10.jar")))
+
assert(sc.listJars().exists(_.contains("commons-lang_commons-lang-2.6.jar")))
+ }
+
+ test("SPARK-33084: Add jar support ivy url -- test exclude param when
transitive=true") {
+ sc = new SparkContext(new
SparkConf().setAppName("test").setMaster("local-cluster[3, 1, 1024]"))
+ sc.addJar("ivy://org.apache.hive:hive-storage-api:2.7.0" +
+ "?exclude=commons-lang:commons-lang&transitive=true")
+
assert(sc.listJars().exists(_.contains("org.apache.hive_hive-storage-api-2.7.0.jar")))
+ assert(sc.listJars().exists(_.contains("org.slf4j_slf4j-api-1.7.10.jar")))
+
assert(!sc.listJars().exists(_.contains("commons-lang_commons-lang-2.6.jar")))
+ }
+
+ test("SPARK-33084: Add jar support ivy url -- test different version") {
+ sc = new SparkContext(new
SparkConf().setAppName("test").setMaster("local-cluster[3, 1, 1024]"))
+ sc.addJar("ivy://org.apache.hive:hive-storage-api:2.7.0")
+
assert(sc.listJars().exists(_.contains("org.apache.hive_hive-storage-api-2.7.0.jar")))
+ sc.addJar("ivy://org.apache.hive:hive-storage-api:2.6.0")
+
assert(sc.listJars().exists(_.contains("org.apache.hive_hive-storage-api-2.6.0.jar")))
+ }
+
+ test("SPARK-33084: Add jar support ivy url -- test invalid param") {
+ sc = new SparkContext(new
SparkConf().setAppName("test").setMaster("local-cluster[3, 1, 1024]"))
+ sc.addJar("ivy://org.apache.hive:hive-storage-api:2.7.0?invalidParam=foo")
Review comment:
https://github.com/apache/spark/pull/29966/files#r533579040
If we show a warning message for this case, we need tests for that.
##########
File path: core/src/main/scala/org/apache/spark/SparkContext.scala
##########
@@ -1919,18 +1919,26 @@ class SparkContext(config: SparkConf) extends Logging {
// A JAR file which exists only on the driver node
case "file" => addLocalJarFile(new File(uri.getPath))
// A JAR file which exists locally on every worker node
- case "local" => "file:" + uri.getPath
+ case "local" => Seq("file:" + uri.getPath)
+ case "ivy" =>
+ // Since `new Path(path).toUri` will lose query information,
+ // so here we use `URI.create(path)`
+ DependencyUtils.resolveMavenDependencies(URI.create(path))
case _ => checkRemoteJarFile(path)
}
}
- if (key != null) {
+ if (keys.nonEmpty) {
val timestamp = if (addedOnSubmit) startTime else
System.currentTimeMillis
- if (addedJars.putIfAbsent(key, timestamp).isEmpty) {
- logInfo(s"Added JAR $path at $key with timestamp $timestamp")
+ val (added, existed) = keys.partition(addedJars.putIfAbsent(_,
timestamp).isEmpty)
+ if (added.nonEmpty) {
+ logInfo(s"Added jar or dependency jars of ivy URI with $path" +
+ s" at ${added.mkString(",")} 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.")
+ }
+ if (existed.nonEmpty) {
Review comment:
Could you add tests to check if this warning message is shown only once
by using `LogAppender`?
##########
File path: core/src/test/scala/org/apache/spark/SparkContextSuite.scala
##########
@@ -955,6 +978,121 @@ class SparkContextSuite extends SparkFunSuite with
LocalSparkContext with Eventu
.set(EXECUTOR_ALLOW_SPARK_CONTEXT, true)).stop()
}
}
+
+ test("SPARK-33084: Add jar support ivy url -- default transitive = false") {
+ sc = new SparkContext(new
SparkConf().setAppName("test").setMaster("local-cluster[3, 1, 1024]"))
+ sc.addJar("ivy://org.apache.hive:hive-storage-api:2.7.0")
+
assert(sc.listJars().exists(_.contains("org.apache.hive_hive-storage-api-2.7.0.jar")))
+
assert(!sc.listJars().exists(_.contains("commons-lang_commons-lang-2.6.jar")))
+
+ sc.addJar("ivy://org.apache.hive:hive-storage-api:2.7.0?transitive=true")
+
assert(sc.listJars().exists(_.contains("commons-lang_commons-lang-2.6.jar")))
+ }
+
+ test("SPARK-33084: Add jar support ivy url -- invalid transitive use default
false") {
+ sc = new SparkContext(new
SparkConf().setAppName("test").setMaster("local-cluster[3, 1, 1024]"))
+ sc.addJar("ivy://org.apache.hive:hive-storage-api:2.7.0?transitive=foo")
+
assert(sc.listJars().exists(_.contains("org.apache.hive_hive-storage-api-2.7.0.jar")))
+ assert(!sc.listJars().exists(_.contains("org.slf4j_slf4j-api-1.7.10.jar")))
+
assert(!sc.listJars().exists(_.contains("commons-lang_commons-lang-2.6.jar")))
+ }
+
+ test("SPARK-33084: Add jar support ivy url -- transitive=true will download
dependency jars") {
+ sc = new SparkContext(new
SparkConf().setAppName("test").setMaster("local-cluster[3, 1, 1024]"))
+ sc.addJar("ivy://org.apache.hive:hive-storage-api:2.7.0?transitive=true")
+
assert(sc.listJars().exists(_.contains("org.apache.hive_hive-storage-api-2.7.0.jar")))
+ assert(sc.listJars().exists(_.contains("org.slf4j_slf4j-api-1.7.10.jar")))
+
assert(sc.listJars().exists(_.contains("commons-lang_commons-lang-2.6.jar")))
+ }
+
+ test("SPARK-33084: Add jar support ivy url -- test exclude param when
transitive=true") {
+ sc = new SparkContext(new
SparkConf().setAppName("test").setMaster("local-cluster[3, 1, 1024]"))
+ sc.addJar("ivy://org.apache.hive:hive-storage-api:2.7.0" +
+ "?exclude=commons-lang:commons-lang&transitive=true")
+
assert(sc.listJars().exists(_.contains("org.apache.hive_hive-storage-api-2.7.0.jar")))
+ assert(sc.listJars().exists(_.contains("org.slf4j_slf4j-api-1.7.10.jar")))
+
assert(!sc.listJars().exists(_.contains("commons-lang_commons-lang-2.6.jar")))
+ }
+
+ test("SPARK-33084: Add jar support ivy url -- test different version") {
+ sc = new SparkContext(new
SparkConf().setAppName("test").setMaster("local-cluster[3, 1, 1024]"))
+ sc.addJar("ivy://org.apache.hive:hive-storage-api:2.7.0")
+
assert(sc.listJars().exists(_.contains("org.apache.hive_hive-storage-api-2.7.0.jar")))
+ sc.addJar("ivy://org.apache.hive:hive-storage-api:2.6.0")
+
assert(sc.listJars().exists(_.contains("org.apache.hive_hive-storage-api-2.6.0.jar")))
+ }
+
+ test("SPARK-33084: Add jar support ivy url -- test invalid param") {
+ sc = new SparkContext(new
SparkConf().setAppName("test").setMaster("local-cluster[3, 1, 1024]"))
+ sc.addJar("ivy://org.apache.hive:hive-storage-api:2.7.0?invalidParam=foo")
+
assert(sc.listJars().exists(_.contains("org.apache.hive_hive-storage-api-2.7.0.jar")))
+ }
+
+ test("SPARK-33084: Add jar support ivy url -- test multiple transitive
params") {
+ sc = new SparkContext(new
SparkConf().setAppName("test").setMaster("local-cluster[3, 1, 1024]"))
+ sc.addJar("ivy://org.apache.hive:hive-storage-api:2.7.0?" +
+ "transitive=true&transitive=false&transitive=invalidValue")
+
assert(sc.listJars().exists(_.contains("org.apache.hive_hive-storage-api-2.7.0.jar")))
+
assert(!sc.listJars().exists(_.contains("commons-lang_commons-lang-2.6.jar")))
+
+ sc.addJar("ivy://org.apache.hive:hive-storage-api:2.7.0?" +
+ "transitive=false&transitive=invalidValue&transitive=true")
+
assert(sc.listJars().exists(_.contains("org.apache.hive_hive-storage-api-2.7.0.jar")))
+
assert(sc.listJars().exists(_.contains("commons-lang_commons-lang-2.6.jar")))
+ }
+
+ test("SPARK-33084: Add jar support ivy url -- test param case sensitive") {
+ sc = new SparkContext(new
SparkConf().setAppName("test").setMaster("local-cluster[3, 1, 1024]"))
+ sc.addJar("ivy://org.apache.hive:hive-storage-api:2.7.0?TRANSITIVE=true")
+
assert(sc.listJars().exists(_.contains("org.apache.hive_hive-storage-api-2.7.0.jar")))
+
assert(!sc.listJars().exists(_.contains("commons-lang_commons-lang-2.6.jar")))
+
+ sc.addJar("ivy://org.apache.hive:hive-storage-api:2.7.0?transitive=true")
+
assert(sc.listJars().exists(_.contains("org.apache.hive_hive-storage-api-2.7.0.jar")))
+
assert(sc.listJars().exists(_.contains("commons-lang_commons-lang-2.6.jar")))
+ }
+
+ test("SPARK-33084: Add jar support ivy url -- test transitive value case
sensitive") {
+ sc = new SparkContext(new
SparkConf().setAppName("test").setMaster("local-cluster[3, 1, 1024]"))
+ sc.addJar("ivy://org.apache.hive:hive-storage-api:2.7.0?transitive=TRUE")
+
assert(sc.listJars().exists(_.contains("org.apache.hive_hive-storage-api-2.7.0.jar")))
+
assert(!sc.listJars().exists(_.contains("commons-lang_commons-lang-2.6.jar")))
+
+ sc.addJar("ivy://org.apache.hive:hive-storage-api:2.7.0?transitive=true")
+
assert(sc.listJars().exists(_.contains("org.apache.hive_hive-storage-api-2.7.0.jar")))
+
assert(sc.listJars().exists(_.contains("commons-lang_commons-lang-2.6.jar")))
+ }
+
+
+ test("SPARK-33084: Add jar support ivy url -- test invalid ivy URI") {
+ sc = new SparkContext(new
SparkConf().setAppName("test").setMaster("local-cluster[3, 1, 1024]"))
+ val e1 = intercept[IllegalArgumentException] {
+ sc.addJar("ivy://")
+ }.getMessage
+ assert(e1.contains("Expected authority at index 6: ivy://"))
+
+ val e2 = intercept[URISyntaxException] {
+ sc.addJar("ivy://org.apache.hive:hive-contrib")
+ }.getMessage
+ assert(e2.contains("Invalid url: Expected 'org:module:version'," +
+ " found org.apache.hive:hive-contrib"))
+
+ val e3 = intercept[URISyntaxException] {
+ sc.addJar("ivy://org.apache.hive:hive-contrib:2.3.7?foo=")
+ }.getMessage
+ assert(e3.contains("Invalid query string: foo="))
+
+ val e4 = intercept[URISyntaxException] {
+ sc.addJar("ivy://org.apache.hive:hive-contrib:2.3.7?bar=&baz=foo")
+ }.getMessage
+ assert(e4.contains("Invalid query string: bar=&baz=foo"))
+
+ val e5 = intercept[URISyntaxException] {
Review comment:
For consistent error handling,
`URISyntaxException`->`IllegalArgumentException` looks better? I meant it looks
better to catch library exception in the Spark side, and then re-throw it as
`IllegalArgumentException`.
##########
File path: core/src/test/scala/org/apache/spark/SparkContextSuite.scala
##########
@@ -955,6 +978,121 @@ class SparkContextSuite extends SparkFunSuite with
LocalSparkContext with Eventu
.set(EXECUTOR_ALLOW_SPARK_CONTEXT, true)).stop()
}
}
+
+ test("SPARK-33084: Add jar support ivy url -- default transitive = false") {
+ sc = new SparkContext(new
SparkConf().setAppName("test").setMaster("local-cluster[3, 1, 1024]"))
+ sc.addJar("ivy://org.apache.hive:hive-storage-api:2.7.0")
+
assert(sc.listJars().exists(_.contains("org.apache.hive_hive-storage-api-2.7.0.jar")))
+
assert(!sc.listJars().exists(_.contains("commons-lang_commons-lang-2.6.jar")))
+
+ sc.addJar("ivy://org.apache.hive:hive-storage-api:2.7.0?transitive=true")
+
assert(sc.listJars().exists(_.contains("commons-lang_commons-lang-2.6.jar")))
+ }
+
+ test("SPARK-33084: Add jar support ivy url -- invalid transitive use default
false") {
+ sc = new SparkContext(new
SparkConf().setAppName("test").setMaster("local-cluster[3, 1, 1024]"))
+ sc.addJar("ivy://org.apache.hive:hive-storage-api:2.7.0?transitive=foo")
+
assert(sc.listJars().exists(_.contains("org.apache.hive_hive-storage-api-2.7.0.jar")))
+ assert(!sc.listJars().exists(_.contains("org.slf4j_slf4j-api-1.7.10.jar")))
+
assert(!sc.listJars().exists(_.contains("commons-lang_commons-lang-2.6.jar")))
+ }
+
+ test("SPARK-33084: Add jar support ivy url -- transitive=true will download
dependency jars") {
+ sc = new SparkContext(new
SparkConf().setAppName("test").setMaster("local-cluster[3, 1, 1024]"))
+ sc.addJar("ivy://org.apache.hive:hive-storage-api:2.7.0?transitive=true")
+
assert(sc.listJars().exists(_.contains("org.apache.hive_hive-storage-api-2.7.0.jar")))
+ assert(sc.listJars().exists(_.contains("org.slf4j_slf4j-api-1.7.10.jar")))
+
assert(sc.listJars().exists(_.contains("commons-lang_commons-lang-2.6.jar")))
+ }
+
+ test("SPARK-33084: Add jar support ivy url -- test exclude param when
transitive=true") {
+ sc = new SparkContext(new
SparkConf().setAppName("test").setMaster("local-cluster[3, 1, 1024]"))
+ sc.addJar("ivy://org.apache.hive:hive-storage-api:2.7.0" +
+ "?exclude=commons-lang:commons-lang&transitive=true")
+
assert(sc.listJars().exists(_.contains("org.apache.hive_hive-storage-api-2.7.0.jar")))
+ assert(sc.listJars().exists(_.contains("org.slf4j_slf4j-api-1.7.10.jar")))
+
assert(!sc.listJars().exists(_.contains("commons-lang_commons-lang-2.6.jar")))
+ }
+
+ test("SPARK-33084: Add jar support ivy url -- test different version") {
+ sc = new SparkContext(new
SparkConf().setAppName("test").setMaster("local-cluster[3, 1, 1024]"))
+ sc.addJar("ivy://org.apache.hive:hive-storage-api:2.7.0")
+
assert(sc.listJars().exists(_.contains("org.apache.hive_hive-storage-api-2.7.0.jar")))
+ sc.addJar("ivy://org.apache.hive:hive-storage-api:2.6.0")
+
assert(sc.listJars().exists(_.contains("org.apache.hive_hive-storage-api-2.6.0.jar")))
+ }
+
+ test("SPARK-33084: Add jar support ivy url -- test invalid param") {
+ sc = new SparkContext(new
SparkConf().setAppName("test").setMaster("local-cluster[3, 1, 1024]"))
+ sc.addJar("ivy://org.apache.hive:hive-storage-api:2.7.0?invalidParam=foo")
+
assert(sc.listJars().exists(_.contains("org.apache.hive_hive-storage-api-2.7.0.jar")))
+ }
+
+ test("SPARK-33084: Add jar support ivy url -- test multiple transitive
params") {
+ sc = new SparkContext(new
SparkConf().setAppName("test").setMaster("local-cluster[3, 1, 1024]"))
+ sc.addJar("ivy://org.apache.hive:hive-storage-api:2.7.0?" +
+ "transitive=true&transitive=false&transitive=invalidValue")
+
assert(sc.listJars().exists(_.contains("org.apache.hive_hive-storage-api-2.7.0.jar")))
+
assert(!sc.listJars().exists(_.contains("commons-lang_commons-lang-2.6.jar")))
+
+ sc.addJar("ivy://org.apache.hive:hive-storage-api:2.7.0?" +
+ "transitive=false&transitive=invalidValue&transitive=true")
+
assert(sc.listJars().exists(_.contains("org.apache.hive_hive-storage-api-2.7.0.jar")))
+
assert(sc.listJars().exists(_.contains("commons-lang_commons-lang-2.6.jar")))
+ }
+
+ test("SPARK-33084: Add jar support ivy url -- test param case sensitive") {
+ sc = new SparkContext(new
SparkConf().setAppName("test").setMaster("local-cluster[3, 1, 1024]"))
+ sc.addJar("ivy://org.apache.hive:hive-storage-api:2.7.0?TRANSITIVE=true")
+
assert(sc.listJars().exists(_.contains("org.apache.hive_hive-storage-api-2.7.0.jar")))
+
assert(!sc.listJars().exists(_.contains("commons-lang_commons-lang-2.6.jar")))
+
+ sc.addJar("ivy://org.apache.hive:hive-storage-api:2.7.0?transitive=true")
+
assert(sc.listJars().exists(_.contains("org.apache.hive_hive-storage-api-2.7.0.jar")))
+
assert(sc.listJars().exists(_.contains("commons-lang_commons-lang-2.6.jar")))
+ }
+
+ test("SPARK-33084: Add jar support ivy url -- test transitive value case
sensitive") {
+ sc = new SparkContext(new
SparkConf().setAppName("test").setMaster("local-cluster[3, 1, 1024]"))
+ sc.addJar("ivy://org.apache.hive:hive-storage-api:2.7.0?transitive=TRUE")
+
assert(sc.listJars().exists(_.contains("org.apache.hive_hive-storage-api-2.7.0.jar")))
+
assert(!sc.listJars().exists(_.contains("commons-lang_commons-lang-2.6.jar")))
+
+ sc.addJar("ivy://org.apache.hive:hive-storage-api:2.7.0?transitive=true")
+
assert(sc.listJars().exists(_.contains("org.apache.hive_hive-storage-api-2.7.0.jar")))
+
assert(sc.listJars().exists(_.contains("commons-lang_commons-lang-2.6.jar")))
+ }
+
+
Review comment:
nit: remove the blank line.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
