zhengzengprc commented on a change in pull request #3039:
URL: https://github.com/apache/iceberg/pull/3039#discussion_r704131209



##########
File path: 
spark3/src/test/java/org/apache/iceberg/spark/source/TestStructuredStreamingRead3.java
##########
@@ -165,6 +166,86 @@ public void 
testReadStreamOnIcebergTableWithMultipleSnapshots() throws Exception
     
Assertions.assertThat(actual).containsExactlyInAnyOrderElementsOf(Iterables.concat(expected));
   }
 
+  @SuppressWarnings("unchecked")
+  @Test
+  public void testReadingStreamFromTimestamp() throws Exception {
+    List<SimpleRecord> dataBeforeTimestamp = Lists.newArrayList(
+        new SimpleRecord(-2, "minustwo"),
+        new SimpleRecord(-1, "minusone"),
+        new SimpleRecord(0, "zero"));
+    appendData(dataBeforeTimestamp, tableIdentifier, "parquet");
+
+    table.refresh();
+    long streamStartTimestamp = table.currentSnapshot().timestampMillis() + 1;
+
+    List<List<SimpleRecord>> expected = TEST_DATA_MULTIPLE_SNAPSHOTS;
+    appendDataAsMultipleSnapshots(expected, tableIdentifier);
+
+    table.refresh();
+
+    Dataset<Row> df = spark.readStream()
+        .format("iceberg")
+        .option(SparkReadOptions.STREAM_FROM_TIMESTAMP, 
Long.toString(streamStartTimestamp))
+        .load(tableIdentifier);
+    List<SimpleRecord> actual = processAvailable(df);
+
+    
Assertions.assertThat(actual).containsExactlyInAnyOrderElementsOf(Iterables.concat(expected));
+  }
+
+  @SuppressWarnings("unchecked")
+  @Test
+  public void testReadingStreamFromTimestampStartWithExistingTimestamp() 
throws Exception {
+    List<SimpleRecord> dataBeforeTimestamp = Lists.newArrayList(
+            new SimpleRecord(-2, "minustwo"),
+            new SimpleRecord(-1, "minusone"),
+            new SimpleRecord(0, "zero"));
+    appendData(dataBeforeTimestamp, tableIdentifier, "parquet");
+
+    table.refresh();
+    long seedDataTimestamp = table.currentSnapshot().timestampMillis();
+
+    List<List<SimpleRecord>> expected = TEST_DATA_MULTIPLE_SNAPSHOTS;
+    appendDataAsMultipleSnapshots(expected, tableIdentifier);
+
+    table.refresh();
+
+    // Find most recent available timestamp after seedDataTimestamp
+    Snapshot mostRecentSnapshotAfterSeedData = table.currentSnapshot();
+    while (mostRecentSnapshotAfterSeedData.parentId() != null
+            && 
table.snapshot(mostRecentSnapshotAfterSeedData.parentId()).timestampMillis() > 
seedDataTimestamp) {
+      mostRecentSnapshotAfterSeedData = 
table.snapshot(mostRecentSnapshotAfterSeedData.parentId());
+    }

Review comment:
       This looks like cleaner, change per suggestion.




-- 
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]

Reply via email to