diff options
Diffstat (limited to 'sql')
17 files changed, 19 insertions, 19 deletions
diff --git a/sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeRow.java b/sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeRow.java index d205547698..86de90984c 100644 --- a/sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeRow.java +++ b/sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeRow.java @@ -196,7 +196,7 @@ public final class UnsafeRow extends InternalRow implements Externalizable, Kryo assertIndexIsValid(i); BitSetMethods.set(baseObject, baseOffset, i); // To preserve row equality, zero out the value when setting the column to null. - // Since this row does does not currently support updates to variable-length values, we don't + // Since this row does not currently support updates to variable-length values, we don't // have to worry about zeroing out that data. Platform.putLong(baseObject, getFieldOffset(i), 0); } diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/windowExpressions.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/windowExpressions.scala index 13115f4728..07d294b108 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/windowExpressions.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/windowExpressions.scala @@ -516,7 +516,7 @@ case class CumeDist() extends RowNumberLike with SizeBasedWindowFunction { * into the number of buckets); both variables are based on the size of the current partition. * During the calculation process the function keeps track of the current row number, the current * bucket number, and the row number at which the bucket will change (bucketThreshold). When the - * current row number reaches bucket threshold, the bucket value is increased by one and the the + * current row number reaches bucket threshold, the bucket value is increased by one and the * threshold is increased by the bucket size (plus one extra if the current bucket is padded). * * This documentation has been based upon similar documentation for the Hive and Presto projects. diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/basicLogicalOperators.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/basicLogicalOperators.scala index d583fa31b0..c977e788b0 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/basicLogicalOperators.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/basicLogicalOperators.scala @@ -795,7 +795,7 @@ case object OneRowRelation extends LeafNode { /** * Computes [[Statistics]] for this plan. The default implementation assumes the output - * cardinality is the product of of all child plan's cardinality, i.e. applies in the case + * cardinality is the product of all child plan's cardinality, i.e. applies in the case * of cartesian joins. * * [[LeafNode]]s must override this. diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/DateTimeUtils.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/DateTimeUtils.scala index 235ca8d263..a96a3b7af2 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/DateTimeUtils.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/DateTimeUtils.scala @@ -142,7 +142,7 @@ object DateTimeUtils { } /** - * Returns the number of days since epoch from from java.sql.Date. + * Returns the number of days since epoch from java.sql.Date. */ def fromJavaDate(date: Date): SQLDate = { millisToDays(date.getTime) @@ -503,7 +503,7 @@ object DateTimeUtils { } /** - * Calculates the year and and the number of the day in the year for the given + * Calculates the year and the number of the day in the year for the given * number of days. The given days is the number of days since 1.1.1970. * * The calculation uses the fact that the period 1.1.2001 until 31.12.2400 is diff --git a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/AttributeSetSuite.scala b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/AttributeSetSuite.scala index 97cfb5f06d..273f95f91e 100644 --- a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/AttributeSetSuite.scala +++ b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/AttributeSetSuite.scala @@ -52,7 +52,7 @@ class AttributeSetSuite extends SparkFunSuite { assert((aSet ++ bSet).contains(aLower) === true) } - test("extracts all references references") { + test("extracts all references ") { val addSet = AttributeSet(Add(aUpper, Alias(bUpper, "test")()):: Nil) assert(addSet.contains(aUpper)) assert(addSet.contains(aLower)) 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 c1cedd8541..2a06f3c47c 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 @@ -361,7 +361,7 @@ class Dataset[T] private[sql]( * method used to map columns depend on the type of `U`: * - When `U` is a class, fields for the class will be mapped to columns of the same name * (case sensitivity is determined by `spark.sql.caseSensitive`). - * - When `U` is a tuple, the columns will be be mapped by ordinal (i.e. the first column will + * - When `U` is a tuple, the columns will be mapped by ordinal (i.e. the first column will * be assigned to `_1`). * - When `U` is a primitive type (i.e. String, Int, etc), then the first column of the * `DataFrame` will be used. diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/PartitioningUtils.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/PartitioningUtils.scala index bc290702dc..bad59961ac 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/PartitioningUtils.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/PartitioningUtils.scala @@ -41,7 +41,7 @@ object PartitionPath { } /** - * Holds a directory in a partitioned collection of files as well as as the partition values + * Holds a directory in a partitioned collection of files as well as the partition values * in the form of a Row. Before scanning, the files at `path` need to be enumerated. */ case class PartitionPath(values: InternalRow, path: Path) diff --git a/sql/core/src/main/scala/org/apache/spark/sql/streaming/DataStreamWriter.scala b/sql/core/src/main/scala/org/apache/spark/sql/streaming/DataStreamWriter.scala index 0ce47b152c..0b39965b31 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/streaming/DataStreamWriter.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/streaming/DataStreamWriter.scala @@ -285,7 +285,7 @@ final class DataStreamWriter[T] private[sql](ds: Dataset[T]) { /** * Starts the execution of the streaming query, which will continually send results to the given - * `ForeachWriter` as as new data arrives. The `ForeachWriter` can be used to send the data + * `ForeachWriter` as new data arrives. The `ForeachWriter` can be used to send the data * generated by the `DataFrame`/`Dataset` to an external system. * * Scala example: diff --git a/sql/core/src/test/scala/org/apache/spark/sql/DataFrameTimeWindowingSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/DataFrameTimeWindowingSuite.scala index 4296ec543e..22d5c47a6f 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/DataFrameTimeWindowingSuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/DataFrameTimeWindowingSuite.scala @@ -257,7 +257,7 @@ class DataFrameTimeWindowingSuite extends QueryTest with SharedSQLContext with B } } - test("time window in SQL with with two expressions") { + test("time window in SQL with two expressions") { withTempTable { table => checkAnswer( spark.sql( @@ -272,7 +272,7 @@ class DataFrameTimeWindowingSuite extends QueryTest with SharedSQLContext with B } } - test("time window in SQL with with three expressions") { + test("time window in SQL with three expressions") { withTempTable { table => checkAnswer( spark.sql( diff --git a/sql/core/src/test/scala/org/apache/spark/sql/execution/PlannerSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/execution/PlannerSuite.scala index 375da224aa..0bfc92fdb6 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/execution/PlannerSuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/execution/PlannerSuite.scala @@ -363,7 +363,7 @@ class PlannerSuite extends SharedSQLContext { // This is a regression test for SPARK-9703 test("EnsureRequirements should not repartition if only ordering requirement is unsatisfied") { // Consider an operator that imposes both output distribution and ordering requirements on its - // children, such as sort sort merge join. If the distribution requirements are satisfied but + // children, such as sort merge join. If the distribution requirements are satisfied but // the output ordering requirements are unsatisfied, then the planner should only add sorts and // should not need to add additional shuffles / exchanges. val outputOrdering = Seq(SortOrder(Literal(1), Ascending)) diff --git a/sql/core/src/test/scala/org/apache/spark/sql/streaming/FileStreamSinkSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/streaming/FileStreamSinkSuite.scala index 22f59f63d6..f67444fbc4 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/streaming/FileStreamSinkSuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/streaming/FileStreamSinkSuite.scala @@ -144,7 +144,7 @@ class FileStreamSinkSuite extends StreamTest { } // This tests whether FileStreamSink works with aggregations. Specifically, it tests - // whether the the correct streaming QueryExecution (i.e. IncrementalExecution) is used to + // whether the correct streaming QueryExecution (i.e. IncrementalExecution) is used to // to execute the trigger for writing data to file sink. See SPARK-18440 for more details. test("writing with aggregation") { diff --git a/sql/hive-thriftserver/src/main/java/org/apache/hive/service/AbstractService.java b/sql/hive-thriftserver/src/main/java/org/apache/hive/service/AbstractService.java index c2a2b2d478..9dd0efc039 100644 --- a/sql/hive-thriftserver/src/main/java/org/apache/hive/service/AbstractService.java +++ b/sql/hive-thriftserver/src/main/java/org/apache/hive/service/AbstractService.java @@ -151,7 +151,7 @@ public abstract class AbstractService implements Service { } /** - * Verify that that a service is in a given state. + * Verify that a service is in a given state. * * @param currentState * the desired state diff --git a/sql/hive-thriftserver/src/main/java/org/apache/hive/service/ServiceOperations.java b/sql/hive-thriftserver/src/main/java/org/apache/hive/service/ServiceOperations.java index 8946219d85..a2c580d6ac 100644 --- a/sql/hive-thriftserver/src/main/java/org/apache/hive/service/ServiceOperations.java +++ b/sql/hive-thriftserver/src/main/java/org/apache/hive/service/ServiceOperations.java @@ -33,7 +33,7 @@ public final class ServiceOperations { } /** - * Verify that that a service is in a given state. + * Verify that a service is in a given state. * @param state the actual state a service is in * @param expectedState the desired state * @throws IllegalStateException if the service state is different from diff --git a/sql/hive-thriftserver/src/main/java/org/apache/hive/service/ServiceStateChangeListener.java b/sql/hive-thriftserver/src/main/java/org/apache/hive/service/ServiceStateChangeListener.java index d1aadad04c..a1ff10dc2b 100644 --- a/sql/hive-thriftserver/src/main/java/org/apache/hive/service/ServiceStateChangeListener.java +++ b/sql/hive-thriftserver/src/main/java/org/apache/hive/service/ServiceStateChangeListener.java @@ -29,7 +29,7 @@ public interface ServiceStateChangeListener { * have changed state before this callback is invoked. * * This operation is invoked on the thread that initiated the state change, - * while the service itself in in a synchronized section. + * while the service itself in a synchronized section. * <ol> * <li>Any long-lived operation here will prevent the service state * change from completing in a timely manner.</li> diff --git a/sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/TypeDescriptor.java b/sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/TypeDescriptor.java index 562b3f5e67..b80fd67884 100644 --- a/sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/TypeDescriptor.java +++ b/sql/hive-thriftserver/src/main/java/org/apache/hive/service/cli/TypeDescriptor.java @@ -98,7 +98,7 @@ public class TypeDescriptor { * For datetime types this is the length in characters of the String representation * (assuming the maximum allowed precision of the fractional seconds component). * For binary data this is the length in bytes. - * Null is returned for for data types where the column size is not applicable. + * Null is returned for data types where the column size is not applicable. */ public Integer getColumnSize() { if (type.isNumericType()) { diff --git a/sql/hive/compatibility/src/test/scala/org/apache/spark/sql/hive/execution/HiveCompatibilitySuite.scala b/sql/hive/compatibility/src/test/scala/org/apache/spark/sql/hive/execution/HiveCompatibilitySuite.scala index 5cd4935e22..d217e9b4fe 100644 --- a/sql/hive/compatibility/src/test/scala/org/apache/spark/sql/hive/execution/HiveCompatibilitySuite.scala +++ b/sql/hive/compatibility/src/test/scala/org/apache/spark/sql/hive/execution/HiveCompatibilitySuite.scala @@ -178,7 +178,7 @@ class HiveCompatibilitySuite extends HiveQueryFileTest with BeforeAndAfter { "skewjoin", "database", - // These tests fail and and exit the JVM. + // These tests fail and exit the JVM. "auto_join18_multi_distinct", "join18_multi_distinct", "input44", diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/HiveTableScanExec.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/HiveTableScanExec.scala index c80695bd3e..7ee5fc543c 100644 --- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/HiveTableScanExec.scala +++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/HiveTableScanExec.scala @@ -40,7 +40,7 @@ import org.apache.spark.util.Utils * The Hive table scan operator. Column and partition pruning are both handled. * * @param requestedAttributes Attributes to be fetched from the Hive table. - * @param relation The Hive table be be scanned. + * @param relation The Hive table be scanned. * @param partitionPruningPred An optional partition pruning predicate for partitioned table. */ private[hive] |