Github user ravipesala commented on a diff in the pull request: https://github.com/apache/incubator-carbondata/pull/263#discussion_r87170789 --- Diff: integration/spark/src/main/java/org/apache/carbondata/spark/load/CarbonLoaderUtil.java --- @@ -215,6 +227,105 @@ public static void executeGraph(CarbonLoadModel loadModel, String storeLocation, info, loadModel.getPartitionId(), loadModel.getCarbonDataLoadSchema()); } + public static void executeNewDataLoad(CarbonLoadModel loadModel, String storeLocation, + String hdfsStoreLocation, RecordReader<NullWritable, StringArrayWritable>[] recordReaders) + throws Exception { + if (!new File(storeLocation).mkdirs()) { + LOGGER.error("Error while creating the temp store path: " + storeLocation); + } + CarbonDataLoadConfiguration configuration = new CarbonDataLoadConfiguration(); + String databaseName = loadModel.getDatabaseName(); + String tableName = loadModel.getTableName(); + String tempLocationKey = databaseName + CarbonCommonConstants.UNDERSCORE + tableName + + CarbonCommonConstants.UNDERSCORE + loadModel.getTaskNo(); + CarbonProperties.getInstance().addProperty(tempLocationKey, storeLocation); + CarbonProperties.getInstance() + .addProperty(CarbonCommonConstants.STORE_LOCATION_HDFS, hdfsStoreLocation); + // CarbonProperties.getInstance().addProperty("store_output_location", outPutLoc); + CarbonProperties.getInstance().addProperty("send.signal.load", "false"); + + CarbonTable carbonTable = loadModel.getCarbonDataLoadSchema().getCarbonTable(); + AbsoluteTableIdentifier identifier = + carbonTable.getAbsoluteTableIdentifier(); + configuration.setTableIdentifier(identifier); + String csvHeader = loadModel.getCsvHeader(); + String csvFileName = null; + if (csvHeader != null && !csvHeader.isEmpty()) { + configuration.setHeader(CarbonDataProcessorUtil.getColumnFields(csvHeader, ",")); + } else { + CarbonFile csvFile = + CarbonDataProcessorUtil.getCsvFileToRead(loadModel.getFactFilesToProcess().get(0)); + csvFileName = csvFile.getName(); + csvHeader = CarbonDataProcessorUtil.getFileHeader(csvFile); + configuration.setHeader( + CarbonDataProcessorUtil.getColumnFields(csvHeader, loadModel.getCsvDelimiter())); + } + CarbonDataProcessorUtil + .validateHeader(loadModel.getTableName(), csvHeader, loadModel.getCarbonDataLoadSchema(), + loadModel.getCsvDelimiter(), csvFileName); --- End diff -- Ok. Modified.
--- 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 infrastruct...@apache.org or file a JIRA ticket with INFRA. ---