HeartSaVioR commented on a change in pull request #35676:
URL: https://github.com/apache/spark/pull/35676#discussion_r818274250
##########
File path:
sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/FileMetadataStructSuite.scala
##########
@@ -510,4 +510,58 @@ class FileMetadataStructSuite extends QueryTest with
SharedSparkSession {
)
}
}
+
+ metadataColumnsTest("file metadata in streaming", schema) { (df, _, _) =>
+ withTempDir { dir =>
+ df.coalesce(1).write.format("json").save(dir.getCanonicalPath +
"/source/new-streaming-data")
+
+ val stream = spark.readStream.format("json")
+ .schema(schema)
+ .load(dir.getCanonicalPath + "/source/new-streaming-data")
+ .select("*", "_metadata")
+ .writeStream.format("json")
+ .option("checkpointLocation", dir.getCanonicalPath +
"/target/checkpoint")
+ .start(dir.getCanonicalPath + "/target/new-streaming-data")
+
+ stream.processAllAvailable()
+ stream.stop()
+
+ val newDF = spark.read.format("json")
+ .load(dir.getCanonicalPath + "/target/new-streaming-data")
+
+ val sourceFile = new File(dir, "/source/new-streaming-data").listFiles()
+ .filter(_.getName.endsWith(".json")).head
+ val sourceFileMetadata = Map(
+ METADATA_FILE_PATH -> sourceFile.toURI.toString,
+ METADATA_FILE_NAME -> sourceFile.getName,
+ METADATA_FILE_SIZE -> sourceFile.length(),
+ METADATA_FILE_MODIFICATION_TIME -> new
Timestamp(sourceFile.lastModified())
+ )
+
+ // SELECT * will have: name, age, info, _metadata of
/source/new-streaming-data
+ assert(newDF.select("*").columns.toSet == Set("name", "age", "info",
"_metadata"))
Review comment:
Ah OK my bad. That is just checking the output.
`dropDuplicate()` still remains a question. How we deal with this? We
removed the column by default for Kafka header to not break compatibility with
`dropDuplicate()`, but not sure we would like to add more config.
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
