diff --git a/graphx/src/main/scala/org/apache/spark/graphx/Graph.scala b/graphx/src/main/scala/org/apache/spark/graphx/Graph.scala
index 5485e30f5a2c9f5720649416b65a638f40254d0e..922ec7955fd6d6875fa3c96c453aac6352ea0952 100644
--- a/graphx/src/main/scala/org/apache/spark/graphx/Graph.scala
+++ b/graphx/src/main/scala/org/apache/spark/graphx/Graph.scala
@@ -365,7 +365,7 @@ abstract class Graph[VD: ClassTag, ED: ClassTag] protected () extends Serializab
*
* @note By expressing computation at the edge level we achieve
* maximum parallelism. This is one of the core functions in the
- * Graph API in that enables neighborhood level computation. For
+ * Graph API that enables neighborhood level computation. For
* example this function can be used to count neighbors satisfying a
* predicate or implement PageRank.
*
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/Row.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/Row.scala
index 1219d4d453e13778f879d87415076997f27ed6c2..726291b96c29d6938ec7da2caa754ee3dd80a0ab 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/Row.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/Row.scala
@@ -338,7 +338,7 @@ trait Row extends Serializable {
* Returns the index of a given field name.
*
* @throws UnsupportedOperationException when schema is not defined.
- * @throws IllegalArgumentException when fieldName do not exist.
+ * @throws IllegalArgumentException when a field `name` does not exist.
*/
def fieldIndex(name: String): Int = {
throw new UnsupportedOperationException("fieldIndex on a Row without schema is undefined.")
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/Dataset.scala b/sql/core/src/main/scala/org/apache/spark/sql/Dataset.scala
index b3064fd531362e3ec67c3709d10e3f86876c7823..4c2bf12ac9ba82593c0e8b4603aa991b232c87fd 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/Dataset.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/Dataset.scala
@@ -458,8 +458,8 @@ class Dataset[T] protected[sql](
* Returns true if this [[Dataset]] contains one or more sources that continuously
* return data as it arrives. A [[Dataset]] that reads data from a streaming source
* must be executed as a [[ContinuousQuery]] using the `startStream()` method in
- * [[DataFrameWriter]]. Methods that return a single answer, (e.g., `count()` or
- * `collect()`) will throw an [[AnalysisException]] when there is a streaming
+ * [[DataFrameWriter]]. Methods that return a single answer, e.g. `count()` or
+ * `collect()`, will throw an [[AnalysisException]] when there is a streaming
* source present.
*
* @group basic
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/DataSource.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/DataSource.scala
index ef626ef5fcc7baac190bd05d826d0ac8a304560d..8e72e06b1f36f4e82b50257b922b916f0741a4e6 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/DataSource.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/DataSource.scala
@@ -143,7 +143,7 @@ case class DataSource(
caseInsensitiveOptions,
fileCatalog.allFiles())
}.getOrElse {
- throw new AnalysisException("Unable to infer schema. It must be specified manually.")
+ throw new AnalysisException("Unable to infer schema. It must be specified manually.")
}
}
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/HDFSMetadataLog.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/HDFSMetadataLog.scala
index ddba3ccb1ba50173f09f133d4ccac3e061a1e502..99bf20c746afec5bdd480800ccada521494528bb 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/HDFSMetadataLog.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/HDFSMetadataLog.scala
@@ -46,8 +46,7 @@ import org.apache.spark.sql.SparkSession
* files in a directory always shows the latest files.
*/
class HDFSMetadataLog[T: ClassTag](sparkSession: SparkSession, path: String)
- extends MetadataLog[T]
- with Logging {
+ extends MetadataLog[T] with Logging {
import HDFSMetadataLog._
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/Source.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/Source.scala
index 6457f928ed88725e9f5cfc6eb94c3ced75fd5af5..1d2f7a87538f4950764caf79f53262935b724874 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/Source.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/Source.scala
@@ -34,8 +34,8 @@ trait Source {
def getOffset: Option[Offset]
/**
- * Returns the data that is is between the offsets (`start`, `end`]. When `start` is `None` then
- * the batch should begin with the first available record. This method must always return the
+ * Returns the data that is between the offsets (`start`, `end`]. When `start` is `None` then
+ * the batch should begin with the first available record. This method must always return the
* same data for a particular `start` and `end` pair.
*/
def getBatch(start: Option[Offset], end: Offset): DataFrame
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/StreamExecution.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/StreamExecution.scala
index ea3c73d9840eba70aeef31fc69ce337277f33f2b..fc18e5f065a04bf3a2187cfd32d64ef47b4deac0 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/StreamExecution.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/StreamExecution.scala
@@ -75,7 +75,7 @@ class StreamExecution(
/** The current batchId or -1 if execution has not yet been initialized. */
private var currentBatchId: Long = -1
- /** All stream sources present the query plan. */
+ /** All stream sources present in the query plan. */
private val sources =
logicalPlan.collect { case s: StreamingExecutionRelation => s.source }
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/StreamingRelation.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/StreamingRelation.scala
index 3341580fc4c4974fa439f8d6292a81c02cd090e6..4d65d2f4f57fca210af5be2efe4ceb4a18fec713 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/StreamingRelation.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/StreamingRelation.scala
@@ -33,7 +33,7 @@ object StreamingRelation {
* [[org.apache.spark.sql.catalyst.plans.logical.LogicalPlan]]. This is only used for creating
* a streaming [[org.apache.spark.sql.DataFrame]] from [[org.apache.spark.sql.DataFrameReader]].
* It should be used to create [[Source]] and converted to [[StreamingExecutionRelation]] when
- * passing to [StreamExecution]] to run a query.
+ * passing to [[StreamExecution]] to run a query.
*/
case class StreamingRelation(dataSource: DataSource, sourceName: String, output: Seq[Attribute])
extends LeafNode {
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 8ff82a3c746365893dcfe0563a5f8d1a147961a7..6b1ecd08c13c32c85edd0da5105e8f332d3b7cc9 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
@@ -204,7 +204,7 @@ class FileStreamSourceSuite extends FileStreamSourceTest with SharedSQLContext {
createFileStreamSourceAndGetSchema(
format = Some("parquet"), path = Some(new File(src, "1").getCanonicalPath), schema = None)
}
- assert("Unable to infer schema. It must be specified manually.;" === e.getMessage)
+ assert("Unable to infer schema. It must be specified manually.;" === e.getMessage)
}
}
@@ -235,7 +235,7 @@ class FileStreamSourceSuite extends FileStreamSourceTest with SharedSQLContext {
createFileStreamSourceAndGetSchema(
format = Some("json"), path = Some(src.getCanonicalPath), schema = None)
}
- assert("Unable to infer schema. It must be specified manually.;" === e.getMessage)
+ assert("Unable to infer schema. It must be specified manually.;" === e.getMessage)
}
}
diff --git a/streaming/src/main/scala/org/apache/spark/streaming/dstream/PairDStreamFunctions.scala b/streaming/src/main/scala/org/apache/spark/streaming/dstream/PairDStreamFunctions.scala
index d6ff96e1fc696840bcd1bee30a7396782b7e432a..b6394e36b51520462c1896eadd82ff95ce4c52ad 100644
--- a/streaming/src/main/scala/org/apache/spark/streaming/dstream/PairDStreamFunctions.scala
+++ b/streaming/src/main/scala/org/apache/spark/streaming/dstream/PairDStreamFunctions.scala
@@ -418,7 +418,7 @@ class PairDStreamFunctions[K, V](self: DStream[(K, V)])
/**
* Return a new "state" DStream where the state for each key is updated by applying
* the given function on the previous state of the key and the new values of the key.
- * org.apache.spark.Partitioner is used to control the partitioning of each RDD.
+ * [[org.apache.spark.Partitioner]] is used to control the partitioning of each RDD.
* @param updateFunc State update function. If `this` function returns None, then
* corresponding state key-value pair will be eliminated.
* @param partitioner Partitioner for controlling the partitioning of each RDD in the new
@@ -439,7 +439,7 @@ class PairDStreamFunctions[K, V](self: DStream[(K, V)])
/**
* Return a new "state" DStream where the state for each key is updated by applying
* the given function on the previous state of the key and the new values of each key.
- * org.apache.spark.Partitioner is used to control the partitioning of each RDD.
+ * [[org.apache.spark.Partitioner]] is used to control the partitioning of each RDD.
* @param updateFunc State update function. Note, that this function may generate a different
* tuple with a different key than the input key. Therefore keys may be removed
* or added in this way. It is up to the developer to decide whether to