Examples with FileSinkDesc org.apache.hadoop.hive.ql.plan.FileSinkDesc used on opensource projects

Example 6 with FileSinkDesc

use of org.apache.hadoop.hive.ql.plan.FileSinkDesc in project hive by apache.

the class TestUtilities method getFileSinkDesc.

private FileSinkDesc getFileSinkDesc(Path tempDirPath) {
    Table table = mock(Table.class);
    when(table.getNumBuckets()).thenReturn(NUM_BUCKETS);
    FileSinkDesc conf = new FileSinkDesc(tempDirPath, null, false);
    conf.setTable(table);
    return conf;
}

Example 7 with FileSinkDesc

use of org.apache.hadoop.hive.ql.plan.FileSinkDesc in project hive by apache.

the class TestGenTezWork method setUp.

/**
   * @throws java.lang.Exception
   */
@SuppressWarnings("unchecked")
@Before
public void setUp() throws Exception {
    // Init conf
    final HiveConf conf = new HiveConf(SemanticAnalyzer.class);
    SessionState.start(conf);
    // Init parse context
    final ParseContext pctx = new ParseContext();
    pctx.setContext(new Context(conf));
    ctx = new GenTezProcContext(conf, pctx, Collections.EMPTY_LIST, new ArrayList<Task<? extends Serializable>>(), Collections.EMPTY_SET, Collections.EMPTY_SET);
    proc = new GenTezWork(new GenTezUtils() {

        @Override
        protected void setupMapWork(MapWork mapWork, GenTezProcContext context, PrunedPartitionList partitions, TableScanOperator root, String alias) throws SemanticException {
            LinkedHashMap<String, Operator<? extends OperatorDesc>> map = new LinkedHashMap<String, Operator<? extends OperatorDesc>>();
            map.put("foo", root);
            mapWork.setAliasToWork(map);
            return;
        }
    });
    CompilationOpContext cCtx = new CompilationOpContext();
    fs = new FileSinkOperator(cCtx);
    fs.setConf(new FileSinkDesc());
    rs = new ReduceSinkOperator(cCtx);
    rs.setConf(new ReduceSinkDesc());
    TableDesc tableDesc = new TableDesc();
    tableDesc.setProperties(new Properties());
    rs.getConf().setKeySerializeInfo(tableDesc);
    ts = new TableScanOperator(cCtx);
    ts.setConf(new TableScanDesc(null));
    ts.getChildOperators().add(rs);
    rs.getParentOperators().add(ts);
    rs.getChildOperators().add(fs);
    fs.getParentOperators().add(rs);
    ctx.preceedingWork = null;
    ctx.currentRootOperator = ts;
}

Example 8 with FileSinkDesc

use of org.apache.hadoop.hive.ql.plan.FileSinkDesc in project hive by apache.

the class Utilities method createTmpDirs.

private static void createTmpDirs(Configuration conf, List<Operator<? extends OperatorDesc>> ops) throws IOException {
    while (!ops.isEmpty()) {
        Operator<? extends OperatorDesc> op = ops.remove(0);
        if (op instanceof FileSinkOperator) {
            FileSinkDesc fdesc = ((FileSinkOperator) op).getConf();
            Path tempDir = fdesc.getDirName();
            if (tempDir != null) {
                Path tempPath = Utilities.toTempPath(tempDir);
                FileSystem fs = tempPath.getFileSystem(conf);
                fs.mkdirs(tempPath);
            }
        }
        if (op.getChildOperators() != null) {
            ops.addAll(op.getChildOperators());
        }
    }
}

Example 9 with FileSinkDesc

use of org.apache.hadoop.hive.ql.plan.FileSinkDesc in project hive by apache.

the class GenMRFileSink1 method process.

/**
   * File Sink Operator encountered.
   *
   * @param nd
   *          the file sink operator encountered
   * @param opProcCtx
   *          context
   */
@Override
public Object process(Node nd, Stack<Node> stack, NodeProcessorCtx opProcCtx, Object... nodeOutputs) throws SemanticException {
    GenMRProcContext ctx = (GenMRProcContext) opProcCtx;
    ParseContext parseCtx = ctx.getParseCtx();
    boolean chDir = false;
    Task<? extends Serializable> currTask = ctx.getCurrTask();
    ctx.addRootIfPossible(currTask);
    FileSinkOperator fsOp = (FileSinkOperator) nd;
    // is INSERT OVERWRITE TABLE
    boolean isInsertTable = GenMapRedUtils.isInsertInto(parseCtx, fsOp);
    HiveConf hconf = parseCtx.getConf();
    // Mark this task as a final map reduce task (ignoring the optional merge task)
    ((MapredWork) currTask.getWork()).setFinalMapRed(true);
    // If this file sink desc has been processed due to a linked file sink desc,
    // use that task
    Map<FileSinkDesc, Task<? extends Serializable>> fileSinkDescs = ctx.getLinkedFileDescTasks();
    if (fileSinkDescs != null) {
        Task<? extends Serializable> childTask = fileSinkDescs.get(fsOp.getConf());
        processLinkedFileDesc(ctx, childTask);
        return true;
    }
    // So, no need to attempt to merge the files again.
    if ((ctx.getSeenFileSinkOps() == null) || (!ctx.getSeenFileSinkOps().contains(nd))) {
        chDir = GenMapRedUtils.isMergeRequired(ctx.getMvTask(), hconf, fsOp, currTask, isInsertTable);
    }
    Path finalName = processFS(fsOp, stack, opProcCtx, chDir);
    if (chDir) {
        // Merge the files in the destination table/partitions by creating Map-only merge job
        // If underlying data is RCFile or OrcFile, RCFileBlockMerge task or
        // OrcFileStripeMerge task would be created.
        LOG.info("using CombineHiveInputformat for the merge job");
        GenMapRedUtils.createMRWorkForMergingFiles(fsOp, finalName, ctx.getDependencyTaskForMultiInsert(), ctx.getMvTask(), hconf, currTask);
    }
    FileSinkDesc fileSinkDesc = fsOp.getConf();
    if (fileSinkDesc.isLinkedFileSink()) {
        Map<FileSinkDesc, Task<? extends Serializable>> linkedFileDescTasks = ctx.getLinkedFileDescTasks();
        if (linkedFileDescTasks == null) {
            linkedFileDescTasks = new HashMap<FileSinkDesc, Task<? extends Serializable>>();
            ctx.setLinkedFileDescTasks(linkedFileDescTasks);
        }
        // The child tasks may be null in case of a select
        if ((currTask.getChildTasks() != null) && (currTask.getChildTasks().size() == 1)) {
            for (FileSinkDesc fileDesc : fileSinkDesc.getLinkedFileSinkDesc()) {
                linkedFileDescTasks.put(fileDesc, currTask.getChildTasks().get(0));
            }
        }
    }
    FetchTask fetchTask = parseCtx.getFetchTask();
    if (fetchTask != null && currTask.getNumChild() == 0) {
        if (fetchTask.isFetchFrom(fileSinkDesc)) {
            currTask.setFetchSource(true);
        }
    }
    return true;
}

Example 10 with FileSinkDesc

use of org.apache.hadoop.hive.ql.plan.FileSinkDesc 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());
}