Github user bhupeshchawda commented on a diff in the pull request:
https://github.com/apache/apex-malhar/pull/292#discussion_r68176757
--- Diff:
contrib/src/main/java/com/datatorrent/contrib/hbase/HBaseScanOperator.java ---
@@ -40,27 +51,107 @@
* @tags hbase, scan, input operator
* @since 0.3.2
*/
-public abstract class HBaseScanOperator<T> extends HBaseInputOperator<T>
+public abstract class HBaseScanOperator<T> extends HBaseInputOperator<T>
implements Operator.ActivationListener<Context>
{
+ public static final int DEF_HINT_SCAN_LOOKAHEAD = 2;
+ public static final int DEF_QUEUE_SIZE = 1000;
+ public static final int DEF_SLEEP_MILLIS = 10;
+
+ private String startRow;
+ private String endRow;
+ private String lastReadRow;
+ private int hintScanLookahead = DEF_HINT_SCAN_LOOKAHEAD;
+ private int queueSize = DEF_QUEUE_SIZE;
+ private int sleepMillis = DEF_SLEEP_MILLIS;
+ private Queue<Result> resultQueue;
+ private boolean threadFailed = false;
+
+ @AutoMetric
+ protected long tuplesRead;
+
+ // Transients
+ protected transient Scan scan;
+ protected transient ResultScanner scanner;
+ protected transient Thread readThread;
+
+ @Override
+ public void setup(OperatorContext context)
+ {
+ super.setup(context);
+ resultQueue = Queues.newLinkedBlockingQueue(queueSize);
+ }
+
+ @Override
+ public void activate(Context context)
+ {
+ startReadThread();
+ }
+
+ protected void startReadThread()
+ {
+ try {
+ scan = operationScan();
+ scanner = getStore().getTable().getScanner(scan);
+ } catch (IOException e) {
+ throw new RuntimeException(e);
+ }
+ readThread = new Thread(new Runnable() {
+ @Override
+ public void run()
+ {
+ try {
+ Result result;
+ while ((result = scanner.next()) != null) {
+ while (!resultQueue.offer(result)) {
+ Thread.sleep(sleepMillis);
+ }
+ }
+ } catch (Exception e) {
+ logger.debug("Exception in fetching results {}", e.getMessage());
+ threadFailed = true;
+ throw new RuntimeException(e);
+ } finally {
+ scanner.close();
+ }
+ }
+ });
+ readThread.start();
+ }
+
+ @Override
+ public void beginWindow(long windowId)
+ {
+ super.beginWindow(windowId);
+ tuplesRead = 0;
+ }
@Override
public void emitTuples()
{
+ if (!readThread.isAlive() && threadFailed) {
+ throw new RuntimeException("Exception in scan thread");
+ }
try {
- HTable table = getTable();
- Scan scan = operationScan();
- ResultScanner scanner = table.getScanner(scan);
- for (Result result : scanner) {
- //KeyValue[] kvs = result.raw();
- //T t = getTuple(kvs);
- T t = getTuple(result);
- outputPort.emit(t);
+ Result result = resultQueue.poll();
+ if (result == null) {
+ return;
+ }
+ T tuple = getTuple(result);
+ if (tuple != null) {
+ outputPort.emit(tuple);
+ tuplesRead++;
}
} catch (Exception e) {
- e.printStackTrace();
+ throw new RuntimeException(e);
}
}
+ @Override
+ public void deactivate()
+ {
+ readThread.interrupt();
--- End diff --
I have introduced a control variable for running and pausing the thread.
However, the interrupt in deactivate would not cause any problems, since it is
not affecting the state of the application at all. In normal functioning, we
never stop the running thread, just pause it.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
