Examples with ExpressionType org.apache.druid.math.expr.ExpressionType used on opensource projects

Example 11 with ExpressionType

use of org.apache.druid.math.expr.ExpressionType in project druid by apache.

the class ExpressionPlanner method plan.

/**
 * Druid tries to be chill to expressions to make up for not having a well defined table schema across segments. This
 * method performs some analysis to determine what sort of selectors can be constructed on top of an expression,
 * whether or not the expression will need implicitly mapped across multi-valued inputs, if the expression produces
 * multi-valued outputs, is vectorizable, and everything else interesting when making a selector.
 *
 * Results are stored in a {@link ExpressionPlan}, which can be examined to do whatever is necessary to make things
 * function properly.
 */
public static ExpressionPlan plan(ColumnInspector inspector, Expr expression) {
    final Expr.BindingAnalysis analysis = expression.analyzeInputs();
    Parser.validateExpr(expression, analysis);
    EnumSet<ExpressionPlan.Trait> traits = EnumSet.noneOf(ExpressionPlan.Trait.class);
    Set<String> noCapabilities = new HashSet<>();
    Set<String> maybeMultiValued = new HashSet<>();
    List<String> needsApplied = ImmutableList.of();
    ColumnType singleInputType = null;
    ExpressionType outputType = null;
    final Set<String> columns = analysis.getRequiredBindings();
    // check and set traits which allow optimized selectors to be created
    if (columns.isEmpty()) {
        traits.add(ExpressionPlan.Trait.CONSTANT);
    } else if (expression.isIdentifier()) {
        traits.add(ExpressionPlan.Trait.IDENTIFIER);
    } else if (columns.size() == 1) {
        final String column = Iterables.getOnlyElement(columns);
        final ColumnCapabilities capabilities = inspector.getColumnCapabilities(column);
        // (i.e. the expression is not treating its input as an array and not wanting to output an array)
        if (capabilities != null && !analysis.hasInputArrays() && !analysis.isOutputArray()) {
            boolean isSingleInputMappable = false;
            boolean isSingleInputScalar = capabilities.hasMultipleValues().isFalse();
            if (capabilities.is(ValueType.STRING)) {
                isSingleInputScalar &= capabilities.isDictionaryEncoded().isTrue();
                isSingleInputMappable = capabilities.isDictionaryEncoded().isTrue() && !capabilities.hasMultipleValues().isUnknown();
            }
            // if satisfied, set single input output type and flags
            if (isSingleInputScalar || isSingleInputMappable) {
                singleInputType = capabilities.toColumnType();
                if (isSingleInputScalar) {
                    traits.add(ExpressionPlan.Trait.SINGLE_INPUT_SCALAR);
                }
                if (isSingleInputMappable) {
                    traits.add(ExpressionPlan.Trait.SINGLE_INPUT_MAPPABLE);
                }
            }
        }
    }
    // automatic transformation to map across multi-valued inputs (or row by row detection in the worst case)
    if (ExpressionPlan.none(traits, ExpressionPlan.Trait.SINGLE_INPUT_SCALAR, ExpressionPlan.Trait.CONSTANT, ExpressionPlan.Trait.IDENTIFIER)) {
        final Set<String> definitelyMultiValued = new HashSet<>();
        final Set<String> definitelyArray = new HashSet<>();
        for (String column : analysis.getRequiredBindings()) {
            final ColumnCapabilities capabilities = inspector.getColumnCapabilities(column);
            if (capabilities != null) {
                if (capabilities.isArray()) {
                    definitelyArray.add(column);
                } else if (capabilities.is(ValueType.STRING) && capabilities.hasMultipleValues().isTrue()) {
                    definitelyMultiValued.add(column);
                } else if (capabilities.is(ValueType.STRING) && capabilities.hasMultipleValues().isMaybeTrue() && !analysis.getArrayBindings().contains(column)) {
                    maybeMultiValued.add(column);
                }
            } else {
                noCapabilities.add(column);
            }
        }
        // find any inputs which will need implicitly mapped across multi-valued rows
        needsApplied = columns.stream().filter(c -> !definitelyArray.contains(c) && definitelyMultiValued.contains(c) && !analysis.getArrayBindings().contains(c)).collect(Collectors.toList());
        // if any multi-value inputs, set flag for non-scalar inputs
        if (analysis.hasInputArrays()) {
            traits.add(ExpressionPlan.Trait.NON_SCALAR_INPUTS);
        }
        if (!noCapabilities.isEmpty()) {
            traits.add(ExpressionPlan.Trait.UNKNOWN_INPUTS);
        }
        if (!maybeMultiValued.isEmpty()) {
            traits.add(ExpressionPlan.Trait.INCOMPLETE_INPUTS);
        }
        // if expression needs transformed, lets do it
        if (!needsApplied.isEmpty()) {
            traits.add(ExpressionPlan.Trait.NEEDS_APPLIED);
        }
    }
    // only set output type if we are pretty confident about input types
    final boolean shouldComputeOutput = ExpressionPlan.none(traits, ExpressionPlan.Trait.UNKNOWN_INPUTS, ExpressionPlan.Trait.INCOMPLETE_INPUTS);
    if (shouldComputeOutput) {
        outputType = expression.getOutputType(inspector);
    }
    // if analysis predicts output, or inferred output type, is array, output will be arrays
    if (analysis.isOutputArray() || (outputType != null && outputType.isArray())) {
        traits.add(ExpressionPlan.Trait.NON_SCALAR_OUTPUT);
        // single input mappable may not produce array output explicitly, only through implicit mapping
        traits.remove(ExpressionPlan.Trait.SINGLE_INPUT_SCALAR);
        traits.remove(ExpressionPlan.Trait.SINGLE_INPUT_MAPPABLE);
    }
    // vectorized expressions do not support incomplete, multi-valued inputs or outputs, or implicit mapping
    // they also do not support unknown inputs, but they also do not currently have to deal with them, as missing
    // capabilites is indicative of a non-existent column instead of an unknown schema. If this ever changes,
    // this check should also change
    boolean supportsVector = ExpressionPlan.none(traits, ExpressionPlan.Trait.INCOMPLETE_INPUTS, ExpressionPlan.Trait.NEEDS_APPLIED, ExpressionPlan.Trait.NON_SCALAR_INPUTS, ExpressionPlan.Trait.NON_SCALAR_OUTPUT);
    if (supportsVector && expression.canVectorize(inspector)) {
        // make sure to compute the output type for a vector expression though, because we might have skipped it earlier
        // due to unknown inputs, but that's ok here since it just means it doesnt exist
        outputType = expression.getOutputType(inspector);
        traits.add(ExpressionPlan.Trait.VECTORIZABLE);
    }
    return new ExpressionPlan(inspector, expression, analysis, traits, outputType, singleInputType, Sets.union(noCapabilities, maybeMultiValued), needsApplied);
}

Example 12 with ExpressionType

use of org.apache.druid.math.expr.ExpressionType in project druid by apache.

the class Projection method postAggregatorDirectColumnIsOk.

/**
 * Returns true if a post-aggregation "expression" can be realized as a direct field access. This is true if it's
 * a direct column access that doesn't require an implicit cast.
 *
 * @param aggregateRowSignature signature of the aggregation
 * @param expression            post-aggregation expression
 * @param rexNode               RexNode for the post-aggregation expression
 *
 * @return yes or no
 */
private static boolean postAggregatorDirectColumnIsOk(final RowSignature aggregateRowSignature, final DruidExpression expression, final RexNode rexNode) {
    if (!expression.isDirectColumnAccess()) {
        return false;
    }
    // We don't really have a way to cast complex type. So might as well not do anything and return.
    final ColumnType columnValueType = aggregateRowSignature.getColumnType(expression.getDirectColumn()).orElseThrow(() -> new ISE("Encountered null type for column[%s]", expression.getDirectColumn()));
    if (columnValueType.is(ValueType.COMPLEX)) {
        return true;
    }
    // Check if a cast is necessary.
    final ExpressionType toExprType = ExpressionType.fromColumnTypeStrict(columnValueType);
    final ExpressionType fromExprType = ExpressionType.fromColumnTypeStrict(Calcites.getColumnTypeForRelDataType(rexNode.getType()));
    return toExprType.equals(fromExprType);
}

Example 13 with ExpressionType

use of org.apache.druid.math.expr.ExpressionType in project druid by apache.

the class VectorComparisonProcessors method makeComparisonProcessor.

@Deprecated
public static <T> ExprVectorProcessor<T> makeComparisonProcessor(Expr.VectorInputBindingInspector inspector, Expr left, Expr right, Supplier<LongOutStringsInFunctionVectorProcessor> longOutStringsInFunctionVectorProcessor, Supplier<LongOutLongsInFunctionVectorValueProcessor> longOutLongsInProcessor, Supplier<DoubleOutLongDoubleInFunctionVectorValueProcessor> doubleOutLongDoubleInProcessor, Supplier<DoubleOutDoubleLongInFunctionVectorValueProcessor> doubleOutDoubleLongInProcessor, Supplier<DoubleOutDoublesInFunctionVectorValueProcessor> doubleOutDoublesInProcessor) {
    assert !ExpressionProcessing.useStrictBooleans();
    final ExpressionType leftType = left.getOutputType(inspector);
    final ExpressionType rightType = right.getOutputType(inspector);
    ExprVectorProcessor<?> processor = null;
    if (Types.is(leftType, ExprType.STRING)) {
        if (Types.isNullOr(rightType, ExprType.STRING)) {
            processor = longOutStringsInFunctionVectorProcessor.get();
        } else {
            processor = doubleOutDoublesInProcessor.get();
        }
    } else if (leftType == null) {
        if (Types.isNullOr(rightType, ExprType.STRING)) {
            processor = longOutStringsInFunctionVectorProcessor.get();
        }
    } else if (leftType.is(ExprType.DOUBLE) || Types.is(rightType, ExprType.DOUBLE)) {
        processor = doubleOutDoublesInProcessor.get();
    }
    if (processor != null) {
        return (ExprVectorProcessor<T>) processor;
    }
    // fall through to normal math processor logic
    return VectorMathProcessors.makeMathProcessor(inspector, left, right, longOutLongsInProcessor, doubleOutLongDoubleInProcessor, doubleOutDoubleLongInProcessor, doubleOutDoublesInProcessor);
}

Example 14 with ExpressionType

use of org.apache.druid.math.expr.ExpressionType in project druid by apache.

the class VectorComparisonProcessors method makeBooleanProcessor.

public static <T> ExprVectorProcessor<T> makeBooleanProcessor(Expr.VectorInputBindingInspector inspector, Expr left, Expr right, Supplier<LongOutStringsInFunctionVectorProcessor> longOutStringsInFunctionVectorProcessor, Supplier<LongOutLongsInFunctionVectorValueProcessor> longOutLongsInProcessor, Supplier<LongOutLongDoubleInFunctionVectorValueProcessor> longOutLongDoubleInProcessor, Supplier<LongOutDoubleLongInFunctionVectorValueProcessor> longOutDoubleLongInProcessor, Supplier<LongOutDoublesInFunctionVectorValueProcessor> longOutDoublesInProcessor) {
    final ExpressionType leftType = left.getOutputType(inspector);
    final ExpressionType rightType = right.getOutputType(inspector);
    ExprVectorProcessor<?> processor = null;
    if (Types.is(leftType, ExprType.STRING)) {
        if (Types.isNullOr(rightType, ExprType.STRING)) {
            processor = longOutStringsInFunctionVectorProcessor.get();
        } else {
            processor = longOutDoublesInProcessor.get();
        }
    } else if (Types.is(rightType, ExprType.STRING)) {
        if (leftType == null) {
            processor = longOutStringsInFunctionVectorProcessor.get();
        } else {
            processor = longOutDoublesInProcessor.get();
        }
    } else if (leftType == null) {
        if (Types.isNullOr(rightType, ExprType.STRING)) {
            processor = longOutStringsInFunctionVectorProcessor.get();
        }
    } else if (leftType.is(ExprType.DOUBLE) || Types.is(rightType, ExprType.DOUBLE)) {
        processor = longOutDoublesInProcessor.get();
    }
    if (processor != null) {
        return (ExprVectorProcessor<T>) processor;
    }
    // fall through to normal math processor logic
    return VectorMathProcessors.makeLongMathProcessor(inspector, left, right, longOutLongsInProcessor, longOutLongDoubleInProcessor, longOutDoubleLongInProcessor, longOutDoublesInProcessor);
}

Example 15 with ExpressionType

use of org.apache.druid.math.expr.ExpressionType in project druid by apache.

the class VectorProcessors method isNull.

public static <T> ExprVectorProcessor<T> isNull(Expr.VectorInputBindingInspector inspector, Expr expr) {
    final ExpressionType type = expr.getOutputType(inspector);
    if (type == null) {
        return constant(1L, inspector.getMaxVectorSize());
    }
    final long[] outputValues = new long[inspector.getMaxVectorSize()];
    ExprVectorProcessor<?> processor = null;
    if (Types.is(type, ExprType.STRING)) {
        final ExprVectorProcessor<String[]> input = expr.buildVectorized(inspector);
        processor = new ExprVectorProcessor<long[]>() {

            @Override
            public ExprEvalVector<long[]> evalVector(Expr.VectorInputBinding bindings) {
                final ExprEvalVector<String[]> inputEval = input.evalVector(bindings);
                final int currentSize = bindings.getCurrentVectorSize();
                final String[] values = inputEval.values();
                for (int i = 0; i < currentSize; i++) {
                    if (values[i] == null) {
                        outputValues[i] = 1L;
                    } else {
                        outputValues[i] = 0L;
                    }
                }
                return new ExprEvalLongVector(outputValues, null);
            }

            @Override
            public ExpressionType getOutputType() {
                return ExpressionType.LONG;
            }
        };
    } else if (Types.is(type, ExprType.LONG)) {
        final ExprVectorProcessor<long[]> input = expr.buildVectorized(inspector);
        processor = new ExprVectorProcessor<long[]>() {

            @Override
            public ExprEvalVector<long[]> evalVector(Expr.VectorInputBinding bindings) {
                final ExprEvalVector<long[]> inputEval = input.evalVector(bindings);
                final int currentSize = bindings.getCurrentVectorSize();
                final boolean[] nulls = inputEval.getNullVector();
                if (nulls == null) {
                    Arrays.fill(outputValues, 0L);
                } else {
                    for (int i = 0; i < currentSize; i++) {
                        if (nulls[i]) {
                            outputValues[i] = 1L;
                        } else {
                            outputValues[i] = 0L;
                        }
                    }
                }
                return new ExprEvalLongVector(outputValues, null);
            }

            @Override
            public ExpressionType getOutputType() {
                return ExpressionType.LONG;
            }
        };
    } else if (Types.is(type, ExprType.DOUBLE)) {
        final ExprVectorProcessor<double[]> input = expr.buildVectorized(inspector);
        processor = new ExprVectorProcessor<long[]>() {

            @Override
            public ExprEvalVector<long[]> evalVector(Expr.VectorInputBinding bindings) {
                final ExprEvalVector<double[]> inputEval = input.evalVector(bindings);
                final int currentSize = bindings.getCurrentVectorSize();
                final boolean[] nulls = inputEval.getNullVector();
                if (nulls == null) {
                    Arrays.fill(outputValues, 0L);
                } else {
                    for (int i = 0; i < currentSize; i++) {
                        if (nulls[i]) {
                            outputValues[i] = 1L;
                        } else {
                            outputValues[i] = 0L;
                        }
                    }
                }
                return new ExprEvalLongVector(outputValues, null);
            }

            @Override
            public ExpressionType getOutputType() {
                return ExpressionType.LONG;
            }
        };
    }
    if (processor == null) {
        throw Exprs.cannotVectorize();
    }
    return (ExprVectorProcessor<T>) processor;
}