beliefer commented on code in PR #49961:
URL: https://github.com/apache/spark/pull/49961#discussion_r1990448785
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/python/PythonScan.scala:
##########
@@ -16,26 +16,44 @@
*/
package org.apache.spark.sql.execution.datasources.v2.python
+import org.apache.commons.lang3.StringUtils
+
import org.apache.spark.JobArtifactSet
+import org.apache.spark.sql.SparkSession
import org.apache.spark.sql.connector.metric.CustomMetric
import org.apache.spark.sql.connector.read._
import org.apache.spark.sql.connector.read.streaming.MicroBatchStream
+import org.apache.spark.sql.internal.connector.SupportsMetadata
+import org.apache.spark.sql.sources.Filter
import org.apache.spark.sql.types.StructType
import org.apache.spark.sql.util.CaseInsensitiveStringMap
-
+import org.apache.spark.util.Utils
class PythonScan(
- ds: PythonDataSourceV2,
- shortName: String,
- outputSchema: StructType,
- options: CaseInsensitiveStringMap) extends Scan {
+ ds: PythonDataSourceV2,
+ shortName: String,
+ outputSchema: StructType,
+ options: CaseInsensitiveStringMap,
+ supportedFilters: Array[Filter]
+) extends Scan
+ with SupportsMetadata {
+ private lazy val sparkSession = SparkSession.active
override def toBatch: Batch = new PythonBatch(ds, shortName, outputSchema,
options)
override def toMicroBatchStream(checkpointLocation: String):
MicroBatchStream =
new PythonMicroBatchStream(ds, shortName, outputSchema, options)
- override def description: String = "(Python)"
+ override def description: String = {
+ val metadataStr = getMetaData().toSeq.sorted.map {
+ case (key, value) =>
+ val maxMetadataValueLength =
sparkSession.sessionState.conf.maxMetadataStringLength
+ val redactedValue =
+ Utils.redact(sparkSession.sessionState.conf.stringRedactionPattern,
value)
+ key + ": " + StringUtils.abbreviate(redactedValue,
maxMetadataValueLength)
Review Comment:
```suggestion
val redactedValue =
Utils.redact(sparkSession.sessionState.conf.stringRedactionPattern, value)
key + ": " + StringUtils.abbreviate(
redactedValue,
sparkSession.sessionState.conf.maxMetadataStringLength)
```
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
