Examples with HiveDruidSplit org.apache.hadoop.hive.druid.io.HiveDruidSplit used on opensource projects

Example 1 with HiveDruidSplit

use of org.apache.hadoop.hive.druid.io.HiveDruidSplit in project hive by apache.

the class TestHiveDruidQueryBasedInputFormat method testTimeZone.

@Test
public void testTimeZone() throws Exception {
    DruidQueryBasedInputFormat input = new DruidQueryBasedInputFormat();
    Method method1 = DruidQueryBasedInputFormat.class.getDeclaredMethod("getInputSplits", Configuration.class);
    method1.setAccessible(true);
    // Create, initialize, and test
    Configuration conf = createPropertiesQuery("sample_datasource", Query.TIMESERIES, TIMESERIES_QUERY);
    HiveDruidSplit[] resultSplits = (HiveDruidSplit[]) method1.invoke(input, conf);
    assertEquals(TIMESERIES_QUERY_SPLIT, Arrays.toString(resultSplits));
    conf = createPropertiesQuery("sample_datasource", Query.TOPN, TOPN_QUERY);
    resultSplits = (HiveDruidSplit[]) method1.invoke(input, conf);
    assertEquals(TOPN_QUERY_SPLIT, Arrays.toString(resultSplits));
    conf = createPropertiesQuery("sample_datasource", Query.GROUP_BY, GROUP_BY_QUERY);
    resultSplits = (HiveDruidSplit[]) method1.invoke(input, conf);
    assertEquals(GROUP_BY_QUERY_SPLIT, Arrays.toString(resultSplits));
    conf = createPropertiesQuery("sample_datasource", Query.SELECT, SELECT_QUERY);
    resultSplits = (HiveDruidSplit[]) method1.invoke(input, conf);
    assertEquals(SELECT_QUERY_SPLIT, Arrays.toString(resultSplits));
}

Example 2 with HiveDruidSplit

use of org.apache.hadoop.hive.druid.io.HiveDruidSplit in project hive by apache.

the class DruidQueryRecordReader method initialize.

public void initialize(InputSplit split, Configuration conf) throws IOException {
    HiveDruidSplit hiveDruidSplit = (HiveDruidSplit) split;
    // Create query
    query = createQuery(hiveDruidSplit.getDruidQuery());
    // Execute query
    if (LOG.isInfoEnabled()) {
        LOG.info("Retrieving from druid using query:\n " + query);
    }
    final Lifecycle lifecycle = new Lifecycle();
    final int numConnection = HiveConf.getIntVar(conf, HiveConf.ConfVars.HIVE_DRUID_NUM_HTTP_CONNECTION);
    final Period readTimeout = new Period(HiveConf.getVar(conf, HiveConf.ConfVars.HIVE_DRUID_HTTP_READ_TIMEOUT));
    HttpClient client = HttpClientInit.createClient(HttpClientConfig.builder().withReadTimeout(readTimeout.toStandardDuration()).withNumConnections(numConnection).build(), lifecycle);
    try {
        lifecycle.start();
    } catch (Exception e) {
        LOG.error("Issues with lifecycle start", e);
    }
    InputStream response;
    try {
        response = DruidStorageHandlerUtils.submitRequest(client, DruidStorageHandlerUtils.createRequest(hiveDruidSplit.getLocations()[0], query));
    } catch (Exception e) {
        lifecycle.stop();
        throw new IOException(org.apache.hadoop.util.StringUtils.stringifyException(e));
    }
    // Retrieve results
    List<R> resultsList;
    try {
        resultsList = createResultsList(response);
    } catch (IOException e) {
        response.close();
        throw e;
    } finally {
        lifecycle.stop();
    }
    if (resultsList == null || resultsList.isEmpty()) {
        return;
    }
    results = resultsList.iterator();
}