diff --git a/binder/postBuild b/binder/postBuild index b1eed6a8b5575..26e23b5a940ae 100644 --- a/binder/postBuild +++ b/binder/postBuild @@ -57,6 +57,6 @@ echo "export SPARK_VERSION=${SPARK_VERSION}" >> ~/.profile # Suppress warnings from Spark jobs, and UI progress bar. mkdir -p ~/.ipython/profile_default/startup -echo """from pyspark.sql import SparkSession +echo "from pyspark.sql import SparkSession SparkSession.builder.config('spark.ui.showConsoleProgress', 'false').getOrCreate().sparkContext.setLogLevel('FATAL') -""" > ~/.ipython/profile_default/startup/00-init.py +" > ~/.ipython/profile_default/startup/00-init.py diff --git a/common/utils/src/main/resources/error/error-classes.json b/common/utils/src/main/resources/error/error-classes.json index c38171c3d9e63..3cf166ba36db7 100644 --- a/common/utils/src/main/resources/error/error-classes.json +++ b/common/utils/src/main/resources/error/error-classes.json @@ -3525,7 +3525,7 @@ }, "PYTHON_UDF_IN_ON_CLAUSE" : { "message" : [ - "Python UDF in the ON clause of a JOIN. In case of an INNNER JOIN consider rewriting to a CROSS JOIN with a WHERE clause." + "Python UDF in the ON clause of a JOIN. In case of an INNER JOIN consider rewriting to a CROSS JOIN with a WHERE clause." ] }, "REMOVE_NAMESPACE_COMMENT" : { @@ -5954,7 +5954,7 @@ "Please move the data from the incorrect directory to the correct one, delete the", "incorrect directory, and then restart this query. If you believe you are receiving", "this message in error, you can disable it with the SQL conf", - "." + "." ] }, "_LEGACY_ERROR_TEMP_2201" : { @@ -6184,7 +6184,7 @@ }, "_LEGACY_ERROR_TEMP_2250" : { "message" : [ - "Not enough memory to build and broadcast the table to all worker nodes. As a workaround, you can either disable broadcast by setting to -1 or increase the spark driver memory by setting to a higher value" + "Not enough memory to build and broadcast the table to all worker nodes. As a workaround, you can either disable broadcast by setting to -1 or increase the spark driver memory by setting to a higher value" ] }, "_LEGACY_ERROR_TEMP_2251" : { diff --git a/connector/docker-integration-tests/src/test/scala/org/apache/spark/sql/jdbc/OracleIntegrationSuite.scala b/connector/docker-integration-tests/src/test/scala/org/apache/spark/sql/jdbc/OracleIntegrationSuite.scala index 102a85e0080da..eb7373e99e08a 100644 --- a/connector/docker-integration-tests/src/test/scala/org/apache/spark/sql/jdbc/OracleIntegrationSuite.scala +++ b/connector/docker-integration-tests/src/test/scala/org/apache/spark/sql/jdbc/OracleIntegrationSuite.scala @@ -58,7 +58,7 @@ import org.apache.spark.tags.DockerTest * $ ./buildContainerImage.sh -v 23.2.0 -f * $ export ORACLE_DOCKER_IMAGE_NAME=oracle/database:23.2.0-free * - * This procedure has been validated with Oracle Databae Free version 23.2.0, + * This procedure has been validated with Oracle Database Free version 23.2.0, * and with Oracle Express Edition versions 18.4.0 and 21.3.0 */ @DockerTest diff --git a/connector/docker-integration-tests/src/test/scala/org/apache/spark/sql/jdbc/v2/OracleIntegrationSuite.scala b/connector/docker-integration-tests/src/test/scala/org/apache/spark/sql/jdbc/v2/OracleIntegrationSuite.scala index 83ba1e1592ccb..5584a56e51d98 100644 --- a/connector/docker-integration-tests/src/test/scala/org/apache/spark/sql/jdbc/v2/OracleIntegrationSuite.scala +++ b/connector/docker-integration-tests/src/test/scala/org/apache/spark/sql/jdbc/v2/OracleIntegrationSuite.scala @@ -53,7 +53,7 @@ import org.apache.spark.tags.DockerTest * $ ./buildContainerImage.sh -v 23.2.0 -f * $ export ORACLE_DOCKER_IMAGE_NAME=oracle/database:23.2.0-free * - * This procedure has been validated with Oracle Databae Free version 23.2.0, + * This procedure has been validated with Oracle Database Free version 23.2.0, * and with Oracle Express Edition versions 18.4.0 and 21.3.0 */ @DockerTest diff --git a/connector/docker-integration-tests/src/test/scala/org/apache/spark/sql/jdbc/v2/OracleNamespaceSuite.scala b/connector/docker-integration-tests/src/test/scala/org/apache/spark/sql/jdbc/v2/OracleNamespaceSuite.scala index 7d4716ac5c24f..daffb5a2d4a3d 100644 --- a/connector/docker-integration-tests/src/test/scala/org/apache/spark/sql/jdbc/v2/OracleNamespaceSuite.scala +++ b/connector/docker-integration-tests/src/test/scala/org/apache/spark/sql/jdbc/v2/OracleNamespaceSuite.scala @@ -49,7 +49,7 @@ import org.apache.spark.tags.DockerTest * $ ./buildContainerImage.sh -v 23.2.0 -f * $ export ORACLE_DOCKER_IMAGE_NAME=oracle/database:23.2.0-free * - * This procedure has been validated with Oracle Databae Free version 23.2.0, + * This procedure has been validated with Oracle Database Free version 23.2.0, * and with Oracle Express Edition versions 18.4.0 and 21.3.0 */ @DockerTest diff --git a/docs/cloud-integration.md b/docs/cloud-integration.md index 6b376c2f95c51..52a7552fe8d4a 100644 --- a/docs/cloud-integration.md +++ b/docs/cloud-integration.md @@ -291,7 +291,7 @@ Amazon EMR has its own S3-aware committers for parquet data. For instructions on use, see [the EMRFS S3-optimized committer](https://docs.aws.amazon.com/emr/latest/ReleaseGuide/emr-spark-s3-optimized-committer.html) -For implementation and performanc details, see +For implementation and performance details, see ["Improve Apache Spark write performance on Apache Parquet formats with the EMRFS S3-optimized committer"](https://aws.amazon.com/blogs/big-data/improve-apache-spark-write-performance-on-apache-parquet-formats-with-the-emrfs-s3-optimized-committer/ diff --git a/docs/sql-error-conditions-unsupported-feature-error-class.md b/docs/sql-error-conditions-unsupported-feature-error-class.md index 790b5c88e461d..0541b9d0589e3 100644 --- a/docs/sql-error-conditions-unsupported-feature-error-class.md +++ b/docs/sql-error-conditions-unsupported-feature-error-class.md @@ -151,7 +151,7 @@ Purge table. ## PYTHON_UDF_IN_ON_CLAUSE -Python UDF in the ON clause of a `` JOIN. In case of an INNNER JOIN consider rewriting to a CROSS JOIN with a WHERE clause. +Python UDF in the ON clause of a `` JOIN. In case of an INNER JOIN consider rewriting to a CROSS JOIN with a WHERE clause. ## REMOVE_NAMESPACE_COMMENT diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryExecutionErrors.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryExecutionErrors.scala index 0d315f526d9e0..0abb202a10f04 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryExecutionErrors.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryExecutionErrors.scala @@ -1716,7 +1716,7 @@ private[sql] object QueryExecutionErrors extends QueryErrorsBase with ExecutionE messageParameters = Map( "metadataPath" -> metadataPath.toString(), "legacyMetadataPath" -> legacyMetadataPath.toString(), - "StreamingCheckpointEscaptedPathCheckEnabled" -> + "StreamingCheckpointEscapedPathCheckEnabled" -> SQLConf.STREAMING_CHECKPOINT_ESCAPED_PATH_CHECK_ENABLED.key), cause = null) } @@ -2093,7 +2093,7 @@ private[sql] object QueryExecutionErrors extends QueryErrorsBase with ExecutionE new SparkException( errorClass = "_LEGACY_ERROR_TEMP_2250", messageParameters = Map( - "autoBroadcastjoinThreshold" -> SQLConf.AUTO_BROADCASTJOIN_THRESHOLD.key, + "autoBroadcastJoinThreshold" -> SQLConf.AUTO_BROADCASTJOIN_THRESHOLD.key, "driverMemory" -> SparkLauncher.DRIVER_MEMORY, "analyzeTblMsg" -> analyzeTblMsg), cause = oe.getCause)