Examples with PhoenixInputFormat org.apache.phoenix.mapreduce.PhoenixInputFormat used on opensource projects

Example 1 with PhoenixInputFormat

use of org.apache.phoenix.mapreduce.PhoenixInputFormat in project DataX by alibaba.

the class HbaseSQLHelper method split.

public static List<Configuration> split(HbaseSQLReaderConfig readerConfig) {
    PhoenixInputFormat inputFormat = new PhoenixInputFormat<PhoenixRecordWritable>();
    org.apache.hadoop.conf.Configuration conf = generatePhoenixConf(readerConfig);
    JobID jobId = new JobID(Key.MOCK_JOBID_IDENTIFIER, Key.MOCK_JOBID);
    JobContextImpl jobContext = new JobContextImpl(conf, jobId);
    List<Configuration> resultConfigurations = new ArrayList<Configuration>();
    List<InputSplit> rawSplits = null;
    try {
        rawSplits = inputFormat.getSplits(jobContext);
        LOG.info("split size is " + rawSplits.size());
        for (InputSplit split : rawSplits) {
            Configuration cfg = readerConfig.getOriginalConfig().clone();
            byte[] splitSer = HadoopSerializationUtil.serialize((PhoenixInputSplit) split);
            String splitBase64Str = org.apache.commons.codec.binary.Base64.encodeBase64String(splitSer);
            cfg.set(Key.SPLIT_KEY, splitBase64Str);
            resultConfigurations.add(cfg);
        }
    } catch (IOException e) {
        throw DataXException.asDataXException(HbaseSQLReaderErrorCode.GET_PHOENIX_SPLITS_ERROR, "获取表的split信息时出现了异常，请检查hbase集群服务是否正常," + e.getMessage(), e);
    } catch (InterruptedException e) {
        throw DataXException.asDataXException(HbaseSQLReaderErrorCode.GET_PHOENIX_SPLITS_ERROR, "获取表的split信息时被中断，请重试，若还有问题请联系datax管理员," + e.getMessage(), e);
    }
    return resultConfigurations;
}

Example 2 with PhoenixInputFormat

use of org.apache.phoenix.mapreduce.PhoenixInputFormat in project Datax by n-kong.

the class HbaseSQLHelper method split.

public static List<Configuration> split(HbaseSQLReaderConfig readerConfig) {
    PhoenixInputFormat inputFormat = new PhoenixInputFormat<PhoenixRecordWritable>();
    org.apache.hadoop.conf.Configuration conf = generatePhoenixConf(readerConfig);
    JobID jobId = new JobID(Key.MOCK_JOBID_IDENTIFIER, Key.MOCK_JOBID);
    JobContextImpl jobContext = new JobContextImpl(conf, jobId);
    List<Configuration> resultConfigurations = new ArrayList<Configuration>();
    List<InputSplit> rawSplits = null;
    try {
        rawSplits = inputFormat.getSplits(jobContext);
        LOG.info("split size is " + rawSplits.size());
        for (InputSplit split : rawSplits) {
            Configuration cfg = readerConfig.getOriginalConfig().clone();
            byte[] splitSer = HadoopSerializationUtil.serialize((PhoenixInputSplit) split);
            String splitBase64Str = org.apache.commons.codec.binary.Base64.encodeBase64String(splitSer);
            cfg.set(Key.SPLIT_KEY, splitBase64Str);
            resultConfigurations.add(cfg);
        }
    } catch (IOException e) {
        throw DataXException.asDataXException(HbaseSQLReaderErrorCode.GET_PHOENIX_SPLITS_ERROR, "获取表的split信息时出现了异常，请检查hbase集群服务是否正常," + e.getMessage(), e);
    } catch (InterruptedException e) {
        throw DataXException.asDataXException(HbaseSQLReaderErrorCode.GET_PHOENIX_SPLITS_ERROR, "获取表的split信息时被中断，请重试，若还有问题请联系datax管理员," + e.getMessage(), e);
    }
    return resultConfigurations;
}