diff options
author | hyukjinkwon <gurwls223@gmail.com> | 2017-04-12 12:38:48 +0100 |
---|---|---|
committer | Sean Owen <sowen@cloudera.com> | 2017-04-12 12:38:48 +0100 |
commit | ceaf77ae43a14e993ac6d1ff34b50256eacd6abb (patch) | |
tree | 34bdb8c1ebbf4df008dc95a6c1234f203fa1dc49 /sql/core/src/test/scala/org/apache | |
parent | 2e1fd46e12bf948490ece2caa73d227b6a924a14 (diff) | |
download | spark-ceaf77ae43a14e993ac6d1ff34b50256eacd6abb.tar.gz spark-ceaf77ae43a14e993ac6d1ff34b50256eacd6abb.tar.bz2 spark-ceaf77ae43a14e993ac6d1ff34b50256eacd6abb.zip |
[SPARK-18692][BUILD][DOCS] Test Java 8 unidoc build on Jenkins
## What changes were proposed in this pull request?
This PR proposes to run Spark unidoc to test Javadoc 8 build as Javadoc 8 is easily re-breakable.
There are several problems with it:
- It introduces little extra bit of time to run the tests. In my case, it took 1.5 mins more (`Elapsed :[94.8746569157]`). How it was tested is described in "How was this patch tested?".
- > One problem that I noticed was that Unidoc appeared to be processing test sources: if we can find a way to exclude those from being processed in the first place then that might significantly speed things up.
(see joshrosen's [comment](https://issues.apache.org/jira/browse/SPARK-18692?focusedCommentId=15947627&page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel#comment-15947627))
To complete this automated build, It also suggests to fix existing Javadoc breaks / ones introduced by test codes as described above.
There fixes are similar instances that previously fixed. Please refer https://github.com/apache/spark/pull/15999 and https://github.com/apache/spark/pull/16013
Note that this only fixes **errors** not **warnings**. Please see my observation https://github.com/apache/spark/pull/17389#issuecomment-288438704 for spurious errors by warnings.
## How was this patch tested?
Manually via `jekyll build` for building tests. Also, tested via running `./dev/run-tests`.
This was tested via manually adding `time.time()` as below:
```diff
profiles_and_goals = build_profiles + sbt_goals
print("[info] Building Spark unidoc (w/Hive 1.2.1) using SBT with these arguments: ",
" ".join(profiles_and_goals))
+ import time
+ st = time.time()
exec_sbt(profiles_and_goals)
+ print("Elapsed :[%s]" % str(time.time() - st))
```
produces
```
...
========================================================================
Building Unidoc API Documentation
========================================================================
...
[info] Main Java API documentation successful.
...
Elapsed :[94.8746569157]
...
Author: hyukjinkwon <gurwls223@gmail.com>
Closes #17477 from HyukjinKwon/SPARK-18692.
Diffstat (limited to 'sql/core/src/test/scala/org/apache')
6 files changed, 26 insertions, 18 deletions
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/DatasetSerializerRegistratorSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/DatasetSerializerRegistratorSuite.scala index 0f3d0cefe3..92c5656f65 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/DatasetSerializerRegistratorSuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/DatasetSerializerRegistratorSuite.scala @@ -56,7 +56,9 @@ object TestRegistrator { def apply(): TestRegistrator = new TestRegistrator() } -/** A [[Serializer]] that takes a [[KryoData]] and serializes it as KryoData(0). */ +/** + * A `Serializer` that takes a [[KryoData]] and serializes it as KryoData(0). + */ class ZeroKryoDataSerializer extends Serializer[KryoData] { override def write(kryo: Kryo, output: Output, t: KryoData): Unit = { output.writeInt(0) diff --git a/sql/core/src/test/scala/org/apache/spark/sql/streaming/FileStreamSourceSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/streaming/FileStreamSourceSuite.scala index 26967782f7..2108b118bf 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/streaming/FileStreamSourceSuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/streaming/FileStreamSourceSuite.scala @@ -44,8 +44,8 @@ abstract class FileStreamSourceTest import testImplicits._ /** - * A subclass [[AddData]] for adding data to files. This is meant to use the - * [[FileStreamSource]] actually being used in the execution. + * A subclass `AddData` for adding data to files. This is meant to use the + * `FileStreamSource` actually being used in the execution. */ abstract class AddFileData extends AddData { override def addData(query: Option[StreamExecution]): (Source, Offset) = { diff --git a/sql/core/src/test/scala/org/apache/spark/sql/streaming/StreamSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/streaming/StreamSuite.scala index 5ab9dc2bc7..13fe51a557 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/streaming/StreamSuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/streaming/StreamSuite.scala @@ -569,7 +569,7 @@ class ThrowingIOExceptionLikeHadoop12074 extends FakeSource { object ThrowingIOExceptionLikeHadoop12074 { /** - * A latch to allow the user to wait until [[ThrowingIOExceptionLikeHadoop12074.createSource]] is + * A latch to allow the user to wait until `ThrowingIOExceptionLikeHadoop12074.createSource` is * called. */ @volatile var createSourceLatch: CountDownLatch = null @@ -600,7 +600,7 @@ class ThrowingInterruptedIOException extends FakeSource { object ThrowingInterruptedIOException { /** - * A latch to allow the user to wait until [[ThrowingInterruptedIOException.createSource]] is + * A latch to allow the user to wait until `ThrowingInterruptedIOException.createSource` is * called. */ @volatile var createSourceLatch: CountDownLatch = null diff --git a/sql/core/src/test/scala/org/apache/spark/sql/streaming/StreamingQuerySuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/streaming/StreamingQuerySuite.scala index 2ebbfcd22b..b69536ed37 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/streaming/StreamingQuerySuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/streaming/StreamingQuerySuite.scala @@ -642,8 +642,10 @@ class StreamingQuerySuite extends StreamTest with BeforeAndAfter with Logging wi * * @param expectedBehavior Expected behavior (not blocked, blocked, or exception thrown) * @param timeoutMs Timeout in milliseconds - * When timeoutMs <= 0, awaitTermination() is tested (i.e. w/o timeout) - * When timeoutMs > 0, awaitTermination(timeoutMs) is tested + * When timeoutMs is less than or equal to 0, awaitTermination() is + * tested (i.e. w/o timeout) + * When timeoutMs is greater than 0, awaitTermination(timeoutMs) is + * tested * @param expectedReturnValue Expected return value when awaitTermination(timeoutMs) is used */ case class TestAwaitTermination( @@ -667,8 +669,10 @@ class StreamingQuerySuite extends StreamTest with BeforeAndAfter with Logging wi * * @param expectedBehavior Expected behavior (not blocked, blocked, or exception thrown) * @param timeoutMs Timeout in milliseconds - * When timeoutMs <= 0, awaitTermination() is tested (i.e. w/o timeout) - * When timeoutMs > 0, awaitTermination(timeoutMs) is tested + * When timeoutMs is less than or equal to 0, awaitTermination() is + * tested (i.e. w/o timeout) + * When timeoutMs is greater than 0, awaitTermination(timeoutMs) is + * tested * @param expectedReturnValue Expected return value when awaitTermination(timeoutMs) is used */ def assertOnQueryCondition( diff --git a/sql/core/src/test/scala/org/apache/spark/sql/test/SQLTestUtils.scala b/sql/core/src/test/scala/org/apache/spark/sql/test/SQLTestUtils.scala index cab219216d..6a4cc95d36 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/test/SQLTestUtils.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/test/SQLTestUtils.scala @@ -41,11 +41,11 @@ import org.apache.spark.util.{UninterruptibleThread, Utils} /** * Helper trait that should be extended by all SQL test suites. * - * This allows subclasses to plugin a custom [[SQLContext]]. It comes with test data + * This allows subclasses to plugin a custom `SQLContext`. It comes with test data * prepared in advance as well as all implicit conversions used extensively by dataframes. - * To use implicit methods, import `testImplicits._` instead of through the [[SQLContext]]. + * To use implicit methods, import `testImplicits._` instead of through the `SQLContext`. * - * Subclasses should *not* create [[SQLContext]]s in the test suite constructor, which is + * Subclasses should *not* create `SQLContext`s in the test suite constructor, which is * prone to leaving multiple overlapping [[org.apache.spark.SparkContext]]s in the same JVM. */ private[sql] trait SQLTestUtils @@ -65,7 +65,7 @@ private[sql] trait SQLTestUtils * A helper object for importing SQL implicits. * * Note that the alternative of importing `spark.implicits._` is not possible here. - * This is because we create the [[SQLContext]] immediately before the first test is run, + * This is because we create the `SQLContext` immediately before the first test is run, * but the implicits import is needed in the constructor. */ protected object testImplicits extends SQLImplicits { @@ -73,7 +73,7 @@ private[sql] trait SQLTestUtils } /** - * Materialize the test data immediately after the [[SQLContext]] is set up. + * Materialize the test data immediately after the `SQLContext` is set up. * This is necessary if the data is accessed by name but not through direct reference. */ protected def setupTestData(): Unit = { @@ -250,8 +250,8 @@ private[sql] trait SQLTestUtils } /** - * Turn a logical plan into a [[DataFrame]]. This should be removed once we have an easier - * way to construct [[DataFrame]] directly out of local data without relying on implicits. + * Turn a logical plan into a `DataFrame`. This should be removed once we have an easier + * way to construct `DataFrame` directly out of local data without relying on implicits. */ protected implicit def logicalPlanToSparkQuery(plan: LogicalPlan): DataFrame = { Dataset.ofRows(spark, plan) @@ -271,7 +271,9 @@ private[sql] trait SQLTestUtils } } - /** Run a test on a separate [[UninterruptibleThread]]. */ + /** + * Run a test on a separate `UninterruptibleThread`. + */ protected def testWithUninterruptibleThread(name: String, quietly: Boolean = false) (body: => Unit): Unit = { val timeoutMillis = 10000 diff --git a/sql/core/src/test/scala/org/apache/spark/sql/test/TestSQLContext.scala b/sql/core/src/test/scala/org/apache/spark/sql/test/TestSQLContext.scala index b01977a238..959edf9a49 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/test/TestSQLContext.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/test/TestSQLContext.scala @@ -22,7 +22,7 @@ import org.apache.spark.sql.SparkSession import org.apache.spark.sql.internal.{SessionState, SessionStateBuilder, SQLConf, WithTestConf} /** - * A special [[SparkSession]] prepared for testing. + * A special `SparkSession` prepared for testing. */ private[sql] class TestSparkSession(sc: SparkContext) extends SparkSession(sc) { self => def this(sparkConf: SparkConf) { |