Examples with GraphWalker org.apache.hadoop.hive.ql.lib.GraphWalker used on opensource projects

Example 21 with GraphWalker

use of org.apache.hadoop.hive.ql.lib.GraphWalker in project hive by apache.

the class TypeCheckProcFactory method genExprNode.

protected static Map<ASTNode, ExprNodeDesc> genExprNode(ASTNode expr, TypeCheckCtx tcCtx, TypeCheckProcFactory tf) throws SemanticException {
    // Create the walker, the rules dispatcher and the context.
    // create a walker which walks the tree in a DFS manner while maintaining
    // the operator stack. The dispatcher
    // generates the plan from the operator tree
    Map<Rule, NodeProcessor> opRules = new LinkedHashMap<Rule, NodeProcessor>();
    opRules.put(new RuleRegExp("R1", HiveParser.TOK_NULL + "%"), tf.getNullExprProcessor());
    opRules.put(new RuleRegExp("R2", HiveParser.Number + "%|" + HiveParser.IntegralLiteral + "%|" + HiveParser.NumberLiteral + "%"), tf.getNumExprProcessor());
    opRules.put(new RuleRegExp("R3", HiveParser.Identifier + "%|" + HiveParser.StringLiteral + "%|" + HiveParser.TOK_CHARSETLITERAL + "%|" + HiveParser.TOK_STRINGLITERALSEQUENCE + "%|" + "%|" + HiveParser.KW_IF + "%|" + HiveParser.KW_CASE + "%|" + HiveParser.KW_WHEN + "%|" + HiveParser.KW_IN + "%|" + HiveParser.KW_ARRAY + "%|" + HiveParser.KW_MAP + "%|" + HiveParser.KW_STRUCT + "%|" + HiveParser.KW_EXISTS + "%|" + HiveParser.TOK_SUBQUERY_OP_NOTIN + "%"), tf.getStrExprProcessor());
    opRules.put(new RuleRegExp("R4", HiveParser.KW_TRUE + "%|" + HiveParser.KW_FALSE + "%"), tf.getBoolExprProcessor());
    opRules.put(new RuleRegExp("R5", HiveParser.TOK_DATELITERAL + "%|" + HiveParser.TOK_TIMESTAMPLITERAL + "%"), tf.getDateTimeExprProcessor());
    opRules.put(new RuleRegExp("R6", HiveParser.TOK_INTERVAL_YEAR_MONTH_LITERAL + "%|" + HiveParser.TOK_INTERVAL_DAY_TIME_LITERAL + "%|" + HiveParser.TOK_INTERVAL_YEAR_LITERAL + "%|" + HiveParser.TOK_INTERVAL_MONTH_LITERAL + "%|" + HiveParser.TOK_INTERVAL_DAY_LITERAL + "%|" + HiveParser.TOK_INTERVAL_HOUR_LITERAL + "%|" + HiveParser.TOK_INTERVAL_MINUTE_LITERAL + "%|" + HiveParser.TOK_INTERVAL_SECOND_LITERAL + "%"), tf.getIntervalExprProcessor());
    opRules.put(new RuleRegExp("R7", HiveParser.TOK_TABLE_OR_COL + "%"), tf.getColumnExprProcessor());
    opRules.put(new RuleRegExp("R8", HiveParser.TOK_SUBQUERY_EXPR + "%"), tf.getSubQueryExprProcessor());
    // The dispatcher fires the processor corresponding to the closest matching
    // rule and passes the context along
    Dispatcher disp = new DefaultRuleDispatcher(tf.getDefaultExprProcessor(), opRules, tcCtx);
    GraphWalker ogw = new ExpressionWalker(disp);
    // Create a list of top nodes
    ArrayList<Node> topNodes = Lists.<Node>newArrayList(expr);
    HashMap<Node, Object> nodeOutputs = new LinkedHashMap<Node, Object>();
    ogw.startWalking(topNodes, nodeOutputs);
    return convert(nodeOutputs);
}

Example 22 with GraphWalker

use of org.apache.hadoop.hive.ql.lib.GraphWalker in project hive by apache.

the class SparkCompiler method generateTaskTree.

/**
   * TODO: need to turn on rules that's commented out and add more if necessary.
   */
@Override
protected void generateTaskTree(List<Task<? extends Serializable>> rootTasks, ParseContext pCtx, List<Task<MoveWork>> mvTask, Set<ReadEntity> inputs, Set<WriteEntity> outputs) throws SemanticException {
    PERF_LOGGER.PerfLogBegin(CLASS_NAME, PerfLogger.SPARK_GENERATE_TASK_TREE);
    GenSparkUtils utils = GenSparkUtils.getUtils();
    utils.resetSequenceNumber();
    ParseContext tempParseContext = getParseContext(pCtx, rootTasks);
    GenSparkProcContext procCtx = new GenSparkProcContext(conf, tempParseContext, mvTask, rootTasks, inputs, outputs, pCtx.getTopOps());
    // -------------------------------- First Pass ---------------------------------- //
    // Identify SparkPartitionPruningSinkOperators, and break OP tree if necessary
    Map<Rule, NodeProcessor> opRules = new LinkedHashMap<Rule, NodeProcessor>();
    opRules.put(new RuleRegExp("Clone OP tree for PartitionPruningSink", SparkPartitionPruningSinkOperator.getOperatorName() + "%"), new SplitOpTreeForDPP());
    Dispatcher disp = new DefaultRuleDispatcher(null, opRules, procCtx);
    GraphWalker ogw = new GenSparkWorkWalker(disp, procCtx);
    List<Node> topNodes = new ArrayList<Node>();
    topNodes.addAll(pCtx.getTopOps().values());
    ogw.startWalking(topNodes, null);
    // -------------------------------- Second Pass ---------------------------------- //
    // Process operator tree in two steps: first we process the extra op trees generated
    // in the first pass. Then we process the main op tree, and the result task will depend
    // on the task generated in the first pass.
    topNodes.clear();
    topNodes.addAll(procCtx.topOps.values());
    generateTaskTreeHelper(procCtx, topNodes);
    // the partitions used.
    if (!procCtx.clonedPruningTableScanSet.isEmpty()) {
        SparkTask pruningTask = SparkUtilities.createSparkTask(conf);
        SparkTask mainTask = procCtx.currentTask;
        pruningTask.addDependentTask(procCtx.currentTask);
        procCtx.rootTasks.remove(procCtx.currentTask);
        procCtx.rootTasks.add(pruningTask);
        procCtx.currentTask = pruningTask;
        topNodes.clear();
        topNodes.addAll(procCtx.clonedPruningTableScanSet);
        generateTaskTreeHelper(procCtx, topNodes);
        procCtx.currentTask = mainTask;
    }
    // we need to clone some operator plans and remove union operators still
    for (BaseWork w : procCtx.workWithUnionOperators) {
        GenSparkUtils.getUtils().removeUnionOperators(procCtx, w);
    }
    // we need to fill MapWork with 'local' work and bucket information for SMB Join.
    GenSparkUtils.getUtils().annotateMapWork(procCtx);
    // finally make sure the file sink operators are set up right
    for (FileSinkOperator fileSink : procCtx.fileSinkSet) {
        GenSparkUtils.getUtils().processFileSink(procCtx, fileSink);
    }
    // Process partition pruning sinks
    for (Operator<?> prunerSink : procCtx.pruningSinkSet) {
        utils.processPartitionPruningSink(procCtx, (SparkPartitionPruningSinkOperator) prunerSink);
    }
    PERF_LOGGER.PerfLogEnd(CLASS_NAME, PerfLogger.SPARK_GENERATE_TASK_TREE);
}

Example 23 with GraphWalker

use of org.apache.hadoop.hive.ql.lib.GraphWalker in project hive by apache.

the class SparkCompiler method runJoinOptimizations.

private void runJoinOptimizations(OptimizeSparkProcContext procCtx) throws SemanticException {
    ParseContext pCtx = procCtx.getParseContext();
    Map<Rule, NodeProcessor> opRules = new LinkedHashMap<Rule, NodeProcessor>();
    opRules.put(new TypeRule(JoinOperator.class), new SparkJoinOptimizer(pCtx));
    opRules.put(new TypeRule(MapJoinOperator.class), new SparkJoinHintOptimizer(pCtx));
    opRules.put(new RuleRegExp("Disabling Dynamic Partition Pruning By Size", SparkPartitionPruningSinkOperator.getOperatorName() + "%"), new SparkRemoveDynamicPruningBySize());
    // The dispatcher fires the processor corresponding to the closest matching
    // rule and passes the context along
    Dispatcher disp = new DefaultRuleDispatcher(null, opRules, procCtx);
    GraphWalker ogw = new DefaultGraphWalker(disp);
    // Create a list of topop nodes
    ArrayList<Node> topNodes = new ArrayList<Node>();
    topNodes.addAll(pCtx.getTopOps().values());
    ogw.startWalking(topNodes, null);
}

Example 24 with GraphWalker

use of org.apache.hadoop.hive.ql.lib.GraphWalker in project hive by apache.

the class AnnotateReduceSinkOutputOperator method transform.

@Override
public ParseContext transform(ParseContext pctx) throws SemanticException {
    // 1. We apply the transformation
    Map<Rule, NodeProcessor> opRules = new LinkedHashMap<Rule, NodeProcessor>();
    opRules.put(new RuleRegExp("R1", "(" + ReduceSinkOperator.getOperatorName() + "%)"), new ReduceSinkOutputOperatorAnnotator());
    GraphWalker ogw = new DefaultGraphWalker(new DefaultRuleDispatcher(null, opRules, null));
    ArrayList<Node> topNodes = new ArrayList<Node>();
    topNodes.addAll(pctx.getTopOps().values());
    ogw.startWalking(topNodes, null);
    return pctx;
}

Example 25 with GraphWalker

use of org.apache.hadoop.hive.ql.lib.GraphWalker in project hive by apache.

the class BucketMapJoinOptimizer method transform.

public ParseContext transform(ParseContext pctx) throws SemanticException {
    Map<Rule, NodeProcessor> opRules = new LinkedHashMap<Rule, NodeProcessor>();
    BucketJoinProcCtx bucketMapJoinOptimizeCtx = new BucketJoinProcCtx(pctx.getConf());
    // process map joins with no reducers pattern
    opRules.put(new RuleRegExp("R1", MapJoinOperator.getOperatorName() + "%"), getBucketMapjoinProc(pctx));
    // The dispatcher fires the processor corresponding to the closest matching
    // rule and passes the context along
    Dispatcher disp = new DefaultRuleDispatcher(getDefaultProc(), opRules, bucketMapJoinOptimizeCtx);
    GraphWalker ogw = new DefaultGraphWalker(disp);
    // Create a list of topop nodes
    List<Node> topNodes = new ArrayList<Node>();
    topNodes.addAll(pctx.getTopOps().values());
    ogw.startWalking(topNodes, null);
    return pctx;
}