Examples with TableScanOperator org.apache.hadoop.hive.ql.exec.TableScanOperator used on opensource projects

Example 1 with TableScanOperator

use of org.apache.hadoop.hive.ql.exec.TableScanOperator in project hive by apache.

the class GenMapRedUtils method createMRWorkForMergingFiles.

/**
   * @param fsInput The FileSink operator.
   * @param ctx The MR processing context.
   * @param finalName the final destination path the merge job should output.
   * @param dependencyTask
   * @param mvTasks
   * @param conf
   * @param currTask
   * @throws SemanticException

   * create a Map-only merge job using CombineHiveInputFormat for all partitions with
   * following operators:
   *          MR job J0:
   *          ...
   *          |
   *          v
   *          FileSinkOperator_1 (fsInput)
   *          |
   *          v
   *          Merge job J1:
   *          |
   *          v
   *          TableScan (using CombineHiveInputFormat) (tsMerge)
   *          |
   *          v
   *          FileSinkOperator (fsMerge)
   *
   *          Here the pathToPartitionInfo & pathToAlias will remain the same, which means the paths
   *          do
   *          not contain the dynamic partitions (their parent). So after the dynamic partitions are
   *          created (after the first job finished before the moveTask or ConditionalTask start),
   *          we need to change the pathToPartitionInfo & pathToAlias to include the dynamic
   *          partition
   *          directories.
   *
   */
public static void createMRWorkForMergingFiles(FileSinkOperator fsInput, Path finalName, DependencyCollectionTask dependencyTask, List<Task<MoveWork>> mvTasks, HiveConf conf, Task<? extends Serializable> currTask) throws SemanticException {
    //
    // 1. create the operator tree
    //
    FileSinkDesc fsInputDesc = fsInput.getConf();
    // Create a TableScan operator
    RowSchema inputRS = fsInput.getSchema();
    TableScanOperator tsMerge = GenMapRedUtils.createTemporaryTableScanOperator(fsInput.getCompilationOpContext(), inputRS);
    // Create a FileSink operator
    TableDesc ts = (TableDesc) fsInputDesc.getTableInfo().clone();
    FileSinkDesc fsOutputDesc = new FileSinkDesc(finalName, ts, conf.getBoolVar(ConfVars.COMPRESSRESULT));
    FileSinkOperator fsOutput = (FileSinkOperator) OperatorFactory.getAndMakeChild(fsOutputDesc, inputRS, tsMerge);
    // If the input FileSinkOperator is a dynamic partition enabled, the tsMerge input schema
    // needs to include the partition column, and the fsOutput should have
    // a DynamicPartitionCtx to indicate that it needs to dynamically partitioned.
    DynamicPartitionCtx dpCtx = fsInputDesc.getDynPartCtx();
    if (dpCtx != null && dpCtx.getNumDPCols() > 0) {
        // adding DP ColumnInfo to the RowSchema signature
        ArrayList<ColumnInfo> signature = inputRS.getSignature();
        String tblAlias = fsInputDesc.getTableInfo().getTableName();
        for (String dpCol : dpCtx.getDPColNames()) {
            ColumnInfo colInfo = new ColumnInfo(dpCol, // all partition column type should be string
            TypeInfoFactory.stringTypeInfo, tblAlias, // partition column is virtual column
            true);
            signature.add(colInfo);
        }
        inputRS.setSignature(signature);
        // create another DynamicPartitionCtx, which has a different input-to-DP column mapping
        DynamicPartitionCtx dpCtx2 = new DynamicPartitionCtx(dpCtx);
        fsOutputDesc.setDynPartCtx(dpCtx2);
        // update the FileSinkOperator to include partition columns
        usePartitionColumns(fsInputDesc.getTableInfo().getProperties(), dpCtx.getDPColNames());
    } else {
        // non-partitioned table
        fsInputDesc.getTableInfo().getProperties().remove(org.apache.hadoop.hive.metastore.api.hive_metastoreConstants.META_TABLE_PARTITION_COLUMNS);
    }
    //
    // 2. Constructing a conditional task consisting of a move task and a map reduce task
    //
    MoveWork dummyMv = new MoveWork(null, null, null, new LoadFileDesc(fsInputDesc.getFinalDirName(), finalName, true, null, null), false);
    MapWork cplan;
    Serializable work;
    if ((conf.getBoolVar(ConfVars.HIVEMERGERCFILEBLOCKLEVEL) && fsInputDesc.getTableInfo().getInputFileFormatClass().equals(RCFileInputFormat.class)) || (conf.getBoolVar(ConfVars.HIVEMERGEORCFILESTRIPELEVEL) && fsInputDesc.getTableInfo().getInputFileFormatClass().equals(OrcInputFormat.class))) {
        cplan = GenMapRedUtils.createMergeTask(fsInputDesc, finalName, dpCtx != null && dpCtx.getNumDPCols() > 0, fsInput.getCompilationOpContext());
        if (conf.getVar(ConfVars.HIVE_EXECUTION_ENGINE).equals("tez")) {
            work = new TezWork(conf.getVar(HiveConf.ConfVars.HIVEQUERYID), conf);
            cplan.setName("File Merge");
            ((TezWork) work).add(cplan);
        } else if (conf.getVar(ConfVars.HIVE_EXECUTION_ENGINE).equals("spark")) {
            work = new SparkWork(conf.getVar(HiveConf.ConfVars.HIVEQUERYID));
            cplan.setName("Spark Merge File Work");
            ((SparkWork) work).add(cplan);
        } else {
            work = cplan;
        }
    } else {
        cplan = createMRWorkForMergingFiles(conf, tsMerge, fsInputDesc);
        if (conf.getVar(ConfVars.HIVE_EXECUTION_ENGINE).equals("tez")) {
            work = new TezWork(conf.getVar(HiveConf.ConfVars.HIVEQUERYID), conf);
            cplan.setName("File Merge");
            ((TezWork) work).add(cplan);
        } else if (conf.getVar(ConfVars.HIVE_EXECUTION_ENGINE).equals("spark")) {
            work = new SparkWork(conf.getVar(HiveConf.ConfVars.HIVEQUERYID));
            cplan.setName("Spark Merge File Work");
            ((SparkWork) work).add(cplan);
        } else {
            work = new MapredWork();
            ((MapredWork) work).setMapWork(cplan);
        }
    }
    // use CombineHiveInputFormat for map-only merging
    cplan.setInputformat("org.apache.hadoop.hive.ql.io.CombineHiveInputFormat");
    // NOTE: we should gather stats in MR1 rather than MR2 at merge job since we don't
    // know if merge MR2 will be triggered at execution time
    Task<MoveWork> mvTask = GenMapRedUtils.findMoveTask(mvTasks, fsOutput);
    ConditionalTask cndTsk = GenMapRedUtils.createCondTask(conf, currTask, dummyMv, work, fsInputDesc.getFinalDirName(), finalName, mvTask, dependencyTask);
    // keep the dynamic partition context in conditional task resolver context
    ConditionalResolverMergeFilesCtx mrCtx = (ConditionalResolverMergeFilesCtx) cndTsk.getResolverCtx();
    mrCtx.setDPCtx(fsInputDesc.getDynPartCtx());
    mrCtx.setLbCtx(fsInputDesc.getLbCtx());
}

Example 2 with TableScanOperator

use of org.apache.hadoop.hive.ql.exec.TableScanOperator in project hive by apache.

the class RewriteGBUsingIndex method getIndexesForRewrite.

/**
   * Get a list of indexes which can be used for rewrite.
   * @return
   * @throws SemanticException
   */
private Map<Table, List<Index>> getIndexesForRewrite() throws SemanticException {
    List<String> supportedIndexes = new ArrayList<String>();
    supportedIndexes.add(AggregateIndexHandler.class.getName());
    // query the metastore to know what columns we have indexed
    Collection<TableScanOperator> topTables = parseContext.getTopOps().values();
    Map<Table, List<Index>> indexes = new HashMap<Table, List<Index>>();
    for (TableScanOperator op : topTables) {
        TableScanOperator tsOP = op;
        List<Index> tblIndexes = IndexUtils.getIndexes(tsOP.getConf().getTableMetadata(), supportedIndexes);
        if (tblIndexes.size() > 0) {
            indexes.put(tsOP.getConf().getTableMetadata(), tblIndexes);
        }
    }
    return indexes;
}

Example 3 with TableScanOperator

use of org.apache.hadoop.hive.ql.exec.TableScanOperator in project hive by apache.

the class GenTezUtils method processDynamicMinMaxPushDownOperator.

public static void processDynamicMinMaxPushDownOperator(GenTezProcContext procCtx, RuntimeValuesInfo runtimeValuesInfo, ReduceSinkOperator rs) throws SemanticException {
    TableScanOperator ts = procCtx.parseContext.getRsOpToTsOpMap().get(rs);
    List<BaseWork> rsWorkList = procCtx.childToWorkMap.get(rs);
    if (ts == null || rsWorkList == null) {
        // detection logic. Nothing to do here.
        return;
    }
    LOG.debug("ResduceSink " + rs + " to TableScan " + ts);
    if (rsWorkList.size() != 1) {
        StringBuilder sb = new StringBuilder();
        for (BaseWork curWork : rsWorkList) {
            if (sb.length() > 0) {
                sb.append(", ");
            }
            sb.append(curWork.getName());
        }
        throw new SemanticException(rs + " belongs to multiple BaseWorks: " + sb.toString());
    }
    BaseWork parentWork = rsWorkList.get(0);
    BaseWork childWork = procCtx.rootToWorkMap.get(ts);
    // Connect parent/child work with a brodacast edge.
    LOG.debug("Connecting Baswork - " + parentWork.getName() + " to " + childWork.getName());
    TezEdgeProperty edgeProperty = new TezEdgeProperty(EdgeType.BROADCAST_EDGE);
    TezWork tezWork = procCtx.currentTask.getWork();
    tezWork.connect(parentWork, childWork, edgeProperty);
    // Set output names in ReduceSink
    rs.getConf().setOutputName(childWork.getName());
    // Set up the dynamic values in the childWork.
    RuntimeValuesInfo childRuntimeValuesInfo = new RuntimeValuesInfo();
    childRuntimeValuesInfo.setTableDesc(runtimeValuesInfo.getTableDesc());
    childRuntimeValuesInfo.setDynamicValueIDs(runtimeValuesInfo.getDynamicValueIDs());
    childRuntimeValuesInfo.setColExprs(runtimeValuesInfo.getColExprs());
    childWork.setInputSourceToRuntimeValuesInfo(parentWork.getName(), childRuntimeValuesInfo);
}

Example 4 with TableScanOperator

use of org.apache.hadoop.hive.ql.exec.TableScanOperator in project hive by apache.

the class MapWork method checkVectorizerSupportedTypes.

private boolean checkVectorizerSupportedTypes(boolean hasLlap) {
    for (Map.Entry<String, Operator<? extends OperatorDesc>> entry : aliasToWork.entrySet()) {
        final String alias = entry.getKey();
        Operator<? extends OperatorDesc> op = entry.getValue();
        PartitionDesc partitionDesc = aliasToPartnInfo.get(alias);
        if (op instanceof TableScanOperator && partitionDesc != null && partitionDesc.getTableDesc() != null) {
            final TableScanOperator tsOp = (TableScanOperator) op;
            final List<String> readColumnNames = tsOp.getNeededColumns();
            final Properties props = partitionDesc.getTableDesc().getProperties();
            final List<TypeInfo> typeInfos = TypeInfoUtils.getTypeInfosFromTypeString(props.getProperty(serdeConstants.LIST_COLUMN_TYPES));
            final List<String> allColumnTypes = TypeInfoUtils.getTypeStringsFromTypeInfo(typeInfos);
            final List<String> allColumnNames = Utilities.getColumnNames(props);
            hasLlap = Utilities.checkVectorizerSupportedTypes(readColumnNames, allColumnNames, allColumnTypes);
        }
    }
    return hasLlap;
}

Example 5 with TableScanOperator

use of org.apache.hadoop.hive.ql.exec.TableScanOperator in project hive by apache.

the class SemanticAnalyzer method enforceScanLimits.

private void enforceScanLimits(ParseContext pCtx, FetchTask fTask) throws SemanticException {
    int scanLimit = HiveConf.getIntVar(conf, HiveConf.ConfVars.HIVELIMITTABLESCANPARTITION);
    if (scanLimit > -1) {
        // a scan limit on the number of partitions has been set by the user
        if (fTask != null) {
            // launch a job on the cluster
            if (!fTask.getWork().isNotPartitioned() && fTask.getWork().getLimit() == -1 && scanLimit < fTask.getWork().getPartDir().size()) {
                throw new SemanticException(ErrorMsg.PARTITION_SCAN_LIMIT_EXCEEDED, "" + fTask.getWork().getPartDir().size(), "" + fTask.getWork().getTblDesc().getTableName(), "" + scanLimit);
            }
        } else {
            // check whether any of them break the limit
            for (Operator<?> topOp : topOps.values()) {
                if (topOp instanceof TableScanOperator) {
                    TableScanOperator tsOp = (TableScanOperator) topOp;
                    if (tsOp.getConf().getIsMetadataOnly()) {
                        continue;
                    }
                    PrunedPartitionList parts = pCtx.getPrunedPartitions(tsOp);
                    if (!parts.getSourceTable().isPartitioned()) {
                        continue;
                    }
                    if (parts.getPartitions().size() > scanLimit) {
                        throw new SemanticException(ErrorMsg.PARTITION_SCAN_LIMIT_EXCEEDED, "" + parts.getPartitions().size(), "" + parts.getSourceTable().getTableName(), "" + scanLimit);
                    }
                }
            }
        }
    }
}