chenjunjiedada commented on a change in pull request #374: Migrate spark table
to iceberg table
URL: https://github.com/apache/incubator-iceberg/pull/374#discussion_r315162272
##########
File path: spark/src/main/scala/org/apache/iceberg/spark/SparkTableUtil.scala
##########
@@ -297,5 +301,88 @@ object SparkTableUtil {
)
}
}
+
+ def buildManifest(table: Table,
+ sparkDataFiles: Seq[SparkDataFile],
+ partitionSpec: PartitionSpec): ManifestFile = {
+ val outputFile = table.io
+ .newOutputFile(FileFormat.AVRO.addExtension("/tmp/" +
UUID.randomUUID.toString))
+ val writer = ManifestWriter.write(partitionSpec, outputFile)
+ try {
+ for (file <- sparkDataFiles) {
+ writer.add(file.toDataFile(partitionSpec))
+ }
+ } finally {
+ writer.close()
+ }
+
+ writer.toManifestFile
+ }
+
+ def partitionToMap(partition: String): Map[String, String] = {
+ val map = new mutable.HashMap[String, String]()
+ val list = partition.split("/")
+ list.foreach { str =>
+ val kv = str.split("=")
+ map.put(kv(0), kv(1))
+ }
+
+ map.toMap
+ }
+
+ /**
+ * Migrate a spark table to a iceberg table.
+ *
+ * The migration uses the spark session to get table metadata. It assumes no
+ * operation is going on original table and target table and thus is not
+ * thread-safe.
+ *
+ * @param dbName the database name of the table to be migrated
+ * @param tableName the table to be migrated
+ * @param table the target table to migrate in
+ *
+ * @return table the target table
+ */
+ def migrateSparkTable(dbName: String, tableName: String, table: Table):
Table = {
Review comment:
Aha, it does like the "import data" behaviour. When I tried to use the
iceberg, the first thing I had to do is to "import table". If we want to
implement a migration include replace the pointer, more steps should be needed.
I can have a look further. At this stage, I 'd like to implement "import data"
since that should also be needed at first in the migration IIUC.
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org
For additional commands, e-mail: issues-h...@iceberg.apache.org
