aromanenko-dev commented on a change in pull request #10815: [BEAM-9279] Make
HBase.ReadAll based on Reads instead of HBaseQuery
URL: https://github.com/apache/beam/pull/10815#discussion_r394534093
##########
File path:
sdks/java/io/hbase/src/main/java/org/apache/beam/sdk/io/hbase/HBaseReadSplittableDoFn.java
##########
@@ -32,65 +31,50 @@
import org.apache.hadoop.hbase.client.ConnectionFactory;
import org.apache.hadoop.hbase.client.Result;
import org.apache.hadoop.hbase.client.ResultScanner;
-import org.apache.hadoop.hbase.client.Scan;
import org.apache.hadoop.hbase.client.Table;
/** A SplittableDoFn to read from HBase. */
@BoundedPerElement
-class HBaseReadSplittableDoFn extends DoFn<HBaseQuery, Result> {
- private final SerializableConfiguration serializableConfiguration;
-
- private transient Connection connection;
-
- HBaseReadSplittableDoFn(SerializableConfiguration serializableConfiguration)
{
- this.serializableConfiguration = serializableConfiguration;
- }
-
- @Setup
- public void setup() throws Exception {
- connection =
ConnectionFactory.createConnection(serializableConfiguration.get());
- }
-
- private static Scan newScanInRange(Scan scan, ByteKeyRange range) throws
IOException {
- return new Scan(scan)
- .setStartRow(range.getStartKey().getBytes())
- .setStopRow(range.getEndKey().getBytes());
- }
+class HBaseReadSplittableDoFn extends DoFn<Read, Result> {
+ HBaseReadSplittableDoFn() {}
@ProcessElement
- public void processElement(ProcessContext c,
RestrictionTracker<ByteKeyRange, ByteKey> tracker)
+ public void processElement(
+ @Element Read read,
+ OutputReceiver<Result> out,
+ RestrictionTracker<ByteKeyRange, ByteKey> tracker)
throws Exception {
- final HBaseQuery query = c.element();
- TableName tableName = TableName.valueOf(query.getTableId());
+ Connection connection =
ConnectionFactory.createConnection(read.getConfiguration());
Review comment:
Please, add TODO about that. Did you try to run performance test to see how
much it's slower?
----------------------------------------------------------------
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:
[email protected]
With regards,
Apache Git Services
