Github user QiangCai commented on a diff in the pull request: https://github.com/apache/incubator-carbondata/pull/518#discussion_r95518312 --- Diff: integration/spark-common/src/main/scala/org/apache/carbondata/spark/util/CommonUtil.scala --- @@ -301,4 +304,45 @@ object CommonUtil { LOGGER.info(s"mapreduce.input.fileinputformat.split.maxsize: ${ newSplitSize.toString }") } } + + def getCsvHeaderColumns(carbonLoadModel: CarbonLoadModel): Array[String] = { + val delimiter = if (StringUtils.isEmpty(carbonLoadModel.getCsvDelimiter)) { + CarbonCommonConstants.COMMA + } else { + CarbonUtil.delimiterConverter(carbonLoadModel.getCsvDelimiter) + } + var csvFile: String = null + var csvHeader: String = carbonLoadModel.getCsvHeader + val csvColumns = if (StringUtils.isBlank(csvHeader)) { + // read header from csv file + csvFile = carbonLoadModel.getFactFilePath.split(",")(0) + csvHeader = CarbonUtil.readHeader(csvFile) + if (StringUtils.isBlank(csvHeader)) { + throw new CarbonDataLoadingException("First line of the csv is not valid.") + } + csvHeader.toLowerCase().split(delimiter).map(_.replaceAll("\"", "").trim) + } else { + csvHeader.toLowerCase.split(CarbonCommonConstants.COMMA).map(_.trim) + } + + if (!CarbonDataProcessorUtil.isHeaderValid(carbonLoadModel.getTableName, csvColumns, + carbonLoadModel.getCarbonDataLoadSchema)) { + if (csvFile == null) { + LOGGER.error("CSV header provided in DDL is not proper." + + " Column names in schema and CSV header are not the same.") + throw new CarbonDataLoadingException( + "CSV header provided in DDL is not proper. Column names in schema and CSV header are " + + "not the same.") + } else { + LOGGER.error( + "CSV File provided is not proper. Column names in schema and csv header are not same. " --- End diff -- fixed
--- 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. ---