szehon-ho commented on code in PR #6980:
URL: https://github.com/apache/iceberg/pull/6980#discussion_r1123588098
##########
spark/v3.3/spark-extensions/src/test/java/org/apache/iceberg/spark/extensions/TestMetadataTables.java:
##########
@@ -488,6 +493,60 @@ public void testMetadataLogEntries() throws Exception {
metadataLogWithProjection);
}
+ @Test
+ public void testFilesVersionAsOf() throws Exception {
+ // Create table and insert data
+ sql(
+ "CREATE TABLE %s (id bigint, data string) "
+ + "USING iceberg "
+ + "PARTITIONED BY (data) "
+ + "TBLPROPERTIES"
+ + "('format-version'='2', 'write.delete.mode'='merge-on-read')",
+ tableName);
+
+ List<SimpleRecord> recordsA =
+ Lists.newArrayList(new SimpleRecord(1, "a"), new SimpleRecord(2, "a"));
+ spark
+ .createDataset(recordsA, Encoders.bean(SimpleRecord.class))
+ .coalesce(1)
+ .writeTo(tableName)
+ .append();
+
+ Table table = Spark3Util.loadIcebergTable(spark, tableName);
+
+ table.updateSchema().addColumn("category",
Types.StringType.get()).commit();
+
+ List<Row> newRecords =
+ Lists.newArrayList(RowFactory.create(3, "b", "c"),
RowFactory.create(4, "b", "c"));
+
+ StructType newSparkSchema =
+ SparkSchemaUtil.convert(
+ new Schema(
+ optional(1, "id", Types.IntegerType.get()),
+ optional(2, "data", Types.StringType.get()),
+ optional(3, "category", Types.StringType.get())));
+
+ spark.createDataFrame(newRecords,
newSparkSchema).coalesce(1).writeTo(tableName).append();
+
+ Long currentSnapshotId = table.currentSnapshot().snapshotId();
+
+ Dataset<Row> actualFilesDs =
+ spark.sql(
+ "SELECT * FROM "
+ + tableName
+ + ".files VERSION AS OF "
+ + currentSnapshotId
+ + " ORDER BY content");
+ List<Row> actualFiles =
TestHelpers.selectNonDerived(actualFilesDs).collectAsList();
+ Schema entriesTableSchema = Spark3Util.loadIcebergTable(spark, tableName +
".entries").schema();
+ List<ManifestFile> expectedDataManifests =
TestHelpers.dataManifests(table);
+ List<Record> expectedFiles =
+ expectedEntries(table, FileContent.DATA, entriesTableSchema,
expectedDataManifests, null);
+
+ TestHelpers.assertEqualsSafe(
Review Comment:
Thanks, I'm really glad this worked.
Can we also add an assert on actualFiles size? And if its more than 0,
could we add an assert for the other row too? (can do it in a for loop, i
guess).
--
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]
