arekusuri commented on a change in pull request #2722: GOBBLIN-865: Add feature that enables PK-chunking in partition URL: https://github.com/apache/incubator-gobblin/pull/2722#discussion_r325354169
########## File path: gobblin-salesforce/src/main/java/org/apache/gobblin/salesforce/SalesforceExtractor.java ########## @@ -979,39 +1118,33 @@ private void fetchResultBatchWithRetry(RecordSetList<JsonElement> rs) @Override public void closeConnection() throws Exception { if (this.bulkConnection != null - && !this.bulkConnection.getJobStatus(this.bulkJob.getId()).getState().toString().equals("Closed")) { + && !this.bulkConnection.getJobStatus(this.getBulkJobId()).getState().toString().equals("Closed")) { log.info("Closing salesforce bulk job connection"); - this.bulkConnection.closeJob(this.bulkJob.getId()); + this.bulkConnection.closeJob(this.getBulkJobId()); } } - public static List<Command> constructGetCommand(String restQuery) { + private static List<Command> constructGetCommand(String restQuery) { return Arrays.asList(new RestApiCommand().build(Arrays.asList(restQuery), RestApiCommandType.GET)); } /** * Waits for the PK batches to complete. The wait will stop after all batches are complete or on the first failed batch * @param batchInfoList list of batch info - * @param retryInterval the polling interval + * @param waitInterval the polling interval * @return the last {@link BatchInfo} processed * @throws InterruptedException * @throws AsyncApiException */ - private BatchInfo waitForPkBatches(BatchInfoList batchInfoList, int retryInterval) + private BatchInfo waitForPkBatches(BatchInfoList batchInfoList, int waitInterval) throws InterruptedException, AsyncApiException { BatchInfo batchInfo = null; BatchInfo[] batchInfos = batchInfoList.getBatchInfo(); - // Wait for all batches other than the first one. The first one is not processed in PK chunking mode - for (int i = 1; i < batchInfos.length; i++) { - BatchInfo bi = batchInfos[i]; - - // get refreshed job status - bi = this.bulkConnection.getBatchInfo(this.bulkJob.getId(), bi.getId()); - - while ((bi.getState() != BatchStateEnum.Completed) - && (bi.getState() != BatchStateEnum.Failed)) { - Thread.sleep(retryInterval * 1000); + for (BatchInfo bi: batchInfos) { + BatchStateEnum state = bi.getState(); + while (state != BatchStateEnum.Completed && state != BatchStateEnum.Failed && state != BatchStateEnum.NotProcessed) { + Thread.sleep(waitInterval * 1000); bi = this.bulkConnection.getBatchInfo(this.bulkJob.getId(), bi.getId()); Review comment: Good catch! Thanks! I should not use the state variable. My test worked, because I was using break point, the time was enough to let sfdc execute. I did more refactoring for this part. Pushing code advance. Will do test during today. and update you. Thanks! ---------------------------------------------------------------- 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