Skip to content
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions binder/postBuild
Original file line number Diff line number Diff line change
Expand Up @@ -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
6 changes: 3 additions & 3 deletions common/utils/src/main/resources/error/error-classes.json
Original file line number Diff line number Diff line change
Expand Up @@ -3525,7 +3525,7 @@
},
"PYTHON_UDF_IN_ON_CLAUSE" : {
"message" : [
"Python UDF in the ON clause of a <joinType> 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 <joinType> JOIN. In case of an INNER JOIN consider rewriting to a CROSS JOIN with a WHERE clause."
]
},
"REMOVE_NAMESPACE_COMMENT" : {
Expand Down Expand Up @@ -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",
"<StreamingCheckpointEscaptedPathCheckEnabled>."
"<StreamingCheckpointEscapedPathCheckEnabled>."
]
},
"_LEGACY_ERROR_TEMP_2201" : {
Expand Down Expand Up @@ -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 <autoBroadcastjoinThreshold> to -1 or increase the spark driver memory by setting <driverMemory> to a higher value<analyzeTblMsg>"
"Not enough memory to build and broadcast the table to all worker nodes. As a workaround, you can either disable broadcast by setting <autoBroadcastJoinThreshold> to -1 or increase the spark driver memory by setting <driverMemory> to a higher value<analyzeTblMsg>"
]
},
"_LEGACY_ERROR_TEMP_2251" : {
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -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
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -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
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -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
Expand Down
2 changes: 1 addition & 1 deletion docs/cloud-integration.md
Original file line number Diff line number Diff line change
Expand Up @@ -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/


Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -151,7 +151,7 @@ Purge table.

## PYTHON_UDF_IN_ON_CLAUSE

Python UDF in the ON clause of a `<joinType>` 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 `<joinType>` JOIN. In case of an INNER JOIN consider rewriting to a CROSS JOIN with a WHERE clause.

## REMOVE_NAMESPACE_COMMENT

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -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)
}
Expand Down Expand Up @@ -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)
Expand Down