Examples with TypeInfoUtils.getTypeInfoFromTypeString org.apache.hadoop.hive.serde2.typeinfo.TypeInfoUtils.getTypeInfoFromTypeString used on opensource projects

Example 6 with TypeInfoUtils.getTypeInfoFromTypeString

use of org.apache.hadoop.hive.serde2.typeinfo.TypeInfoUtils.getTypeInfoFromTypeString in project hive by apache.

the class DDLTask method alterTableAlterPart.

/**
   * Alter partition column type in a table
   *
   * @param db
   *          Database to rename the partition.
   * @param alterPartitionDesc
   *          change partition column type.
   * @return Returns 0 when execution succeeds and above 0 if it fails.
   * @throws HiveException
   */
private int alterTableAlterPart(Hive db, AlterTableAlterPartDesc alterPartitionDesc) throws HiveException {
    Table tbl = db.getTable(alterPartitionDesc.getTableName(), true);
    String tabName = alterPartitionDesc.getTableName();
    // This is checked by DDLSemanticAnalyzer
    assert (tbl.isPartitioned());
    List<FieldSchema> newPartitionKeys = new ArrayList<FieldSchema>();
    // with a non null value before trying to alter the partition column type.
    try {
        Set<Partition> partitions = db.getAllPartitionsOf(tbl);
        int colIndex = -1;
        for (FieldSchema col : tbl.getTTable().getPartitionKeys()) {
            colIndex++;
            if (col.getName().compareTo(alterPartitionDesc.getPartKeySpec().getName()) == 0) {
                break;
            }
        }
        if (colIndex == -1 || colIndex == tbl.getTTable().getPartitionKeys().size()) {
            throw new HiveException("Cannot find partition column " + alterPartitionDesc.getPartKeySpec().getName());
        }
        TypeInfo expectedType = TypeInfoUtils.getTypeInfoFromTypeString(alterPartitionDesc.getPartKeySpec().getType());
        ObjectInspector outputOI = TypeInfoUtils.getStandardWritableObjectInspectorFromTypeInfo(expectedType);
        Converter converter = ObjectInspectorConverters.getConverter(PrimitiveObjectInspectorFactory.javaStringObjectInspector, outputOI);
        // For all the existing partitions, check if the value can be type casted to a non-null object
        for (Partition part : partitions) {
            if (part.getName().equals(conf.getVar(HiveConf.ConfVars.DEFAULTPARTITIONNAME))) {
                continue;
            }
            try {
                String value = part.getValues().get(colIndex);
                Object convertedValue = converter.convert(value);
                if (convertedValue == null) {
                    throw new HiveException(" Converting from " + TypeInfoFactory.stringTypeInfo + " to " + expectedType + " for value : " + value + " resulted in NULL object");
                }
            } catch (Exception e) {
                throw new HiveException("Exception while converting " + TypeInfoFactory.stringTypeInfo + " to " + expectedType + " for value : " + part.getValues().get(colIndex));
            }
        }
    } catch (Exception e) {
        throw new HiveException("Exception while checking type conversion of existing partition values to " + alterPartitionDesc.getPartKeySpec() + " : " + e.getMessage());
    }
    for (FieldSchema col : tbl.getTTable().getPartitionKeys()) {
        if (col.getName().compareTo(alterPartitionDesc.getPartKeySpec().getName()) == 0) {
            newPartitionKeys.add(alterPartitionDesc.getPartKeySpec());
        } else {
            newPartitionKeys.add(col);
        }
    }
    tbl.getTTable().setPartitionKeys(newPartitionKeys);
    try {
        db.alterTable(tabName, tbl, null);
    } catch (InvalidOperationException e) {
        throw new HiveException(e, ErrorMsg.GENERIC_ERROR, "Unable to alter " + tabName);
    }
    work.getInputs().add(new ReadEntity(tbl));
    // We've already locked the table as the input, don't relock it as the output.
    addIfAbsentByName(new WriteEntity(tbl, WriteEntity.WriteType.DDL_NO_LOCK));
    return 0;
}

Example 7 with TypeInfoUtils.getTypeInfoFromTypeString

use of org.apache.hadoop.hive.serde2.typeinfo.TypeInfoUtils.getTypeInfoFromTypeString in project hive by apache.

the class MapJoinBytesTableContainer method createInternalOi.

private LazyBinaryStructObjectInspector createInternalOi(MapJoinObjectSerDeContext valCtx) throws SerDeException {
    // We are going to use LBSerDe to serialize values; create OI for retrieval.
    List<? extends StructField> fields = ((StructObjectInspector) valCtx.getSerDe().getObjectInspector()).getAllStructFieldRefs();
    List<String> colNames = new ArrayList<String>(fields.size());
    List<ObjectInspector> colOis = new ArrayList<ObjectInspector>(fields.size());
    for (int i = 0; i < fields.size(); ++i) {
        StructField field = fields.get(i);
        colNames.add(field.getFieldName());
        // It would be nice if OI could return typeInfo...
        TypeInfo typeInfo = TypeInfoUtils.getTypeInfoFromTypeString(field.getFieldObjectInspector().getTypeName());
        colOis.add(LazyBinaryUtils.getLazyBinaryObjectInspectorFromTypeInfo(typeInfo));
    }
    return LazyBinaryObjectInspectorFactory.getLazyBinaryStructObjectInspector(colNames, colOis);
}

Example 8 with TypeInfoUtils.getTypeInfoFromTypeString

use of org.apache.hadoop.hive.serde2.typeinfo.TypeInfoUtils.getTypeInfoFromTypeString in project hive by apache.

the class VectorSerializeRow method init.

public void init(List<String> typeNames, int[] columnMap) throws HiveException {
    final int size = typeNames.size();
    categories = new Category[size];
    primitiveCategories = new PrimitiveCategory[size];
    outputColumnNums = Arrays.copyOf(columnMap, size);
    TypeInfo typeInfo;
    for (int i = 0; i < size; i++) {
        typeInfo = TypeInfoUtils.getTypeInfoFromTypeString(typeNames.get(i));
        categories[i] = typeInfo.getCategory();
        if (categories[i] == Category.PRIMITIVE) {
            primitiveCategories[i] = ((PrimitiveTypeInfo) typeInfo).getPrimitiveCategory();
        }
    }
}

Example 9 with TypeInfoUtils.getTypeInfoFromTypeString

use of org.apache.hadoop.hive.serde2.typeinfo.TypeInfoUtils.getTypeInfoFromTypeString in project hive by apache.

the class VectorizationContext method getInExpression.

/**
   * Create a filter or boolean-valued expression for column IN ( <list-of-constants> )
   */
private VectorExpression getInExpression(List<ExprNodeDesc> childExpr, VectorExpressionDescriptor.Mode mode, TypeInfo returnType) throws HiveException {
    ExprNodeDesc colExpr = childExpr.get(0);
    List<ExprNodeDesc> inChildren = childExpr.subList(1, childExpr.size());
    String colType = colExpr.getTypeString();
    colType = VectorizationContext.mapTypeNameSynonyms(colType);
    TypeInfo colTypeInfo = TypeInfoUtils.getTypeInfoFromTypeString(colType);
    Category category = colTypeInfo.getCategory();
    if (category == Category.STRUCT) {
        return getStructInExpression(childExpr, colExpr, colTypeInfo, inChildren, mode, returnType);
    } else if (category != Category.PRIMITIVE) {
        return null;
    }
    // prepare arguments for createVectorExpression
    List<ExprNodeDesc> childrenForInList = evaluateCastOnConstants(inChildren);
    /* This method assumes that the IN list has no NULL entries. That is enforced elsewhere,
     * in the Vectorizer class. If NULL is passed in as a list entry, behavior is not defined.
     * If in the future, NULL values are allowed in the IN list, be sure to handle 3-valued
     * logic correctly. E.g. NOT (col IN (null)) should be considered UNKNOWN, so that would
     * become FALSE in the WHERE clause, and cause the row in question to be filtered out.
     * See the discussion in Jira HIVE-5583.
     */
    VectorExpression expr = null;
    // Validate the IN items are only constants.
    for (ExprNodeDesc inListChild : childrenForInList) {
        if (!(inListChild instanceof ExprNodeConstantDesc)) {
            throw new HiveException("Vectorizing IN expression only supported for constant values");
        }
    }
    // determine class
    Class<?> cl = null;
    //       non-vectorized validates that explicitly during UDF init.
    if (isIntFamily(colType)) {
        cl = (mode == VectorExpressionDescriptor.Mode.FILTER ? FilterLongColumnInList.class : LongColumnInList.class);
        long[] inVals = new long[childrenForInList.size()];
        for (int i = 0; i != inVals.length; i++) {
            inVals[i] = getIntFamilyScalarAsLong((ExprNodeConstantDesc) childrenForInList.get(i));
        }
        expr = createVectorExpression(cl, childExpr.subList(0, 1), VectorExpressionDescriptor.Mode.PROJECTION, returnType);
        ((ILongInExpr) expr).setInListValues(inVals);
    } else if (isTimestampFamily(colType)) {
        cl = (mode == VectorExpressionDescriptor.Mode.FILTER ? FilterTimestampColumnInList.class : TimestampColumnInList.class);
        Timestamp[] inVals = new Timestamp[childrenForInList.size()];
        for (int i = 0; i != inVals.length; i++) {
            inVals[i] = getTimestampScalar(childrenForInList.get(i));
        }
        expr = createVectorExpression(cl, childExpr.subList(0, 1), VectorExpressionDescriptor.Mode.PROJECTION, returnType);
        ((ITimestampInExpr) expr).setInListValues(inVals);
    } else if (isStringFamily(colType)) {
        cl = (mode == VectorExpressionDescriptor.Mode.FILTER ? FilterStringColumnInList.class : StringColumnInList.class);
        byte[][] inVals = new byte[childrenForInList.size()][];
        for (int i = 0; i != inVals.length; i++) {
            inVals[i] = getStringScalarAsByteArray((ExprNodeConstantDesc) childrenForInList.get(i));
        }
        expr = createVectorExpression(cl, childExpr.subList(0, 1), VectorExpressionDescriptor.Mode.PROJECTION, returnType);
        ((IStringInExpr) expr).setInListValues(inVals);
    } else if (isFloatFamily(colType)) {
        cl = (mode == VectorExpressionDescriptor.Mode.FILTER ? FilterDoubleColumnInList.class : DoubleColumnInList.class);
        double[] inValsD = new double[childrenForInList.size()];
        for (int i = 0; i != inValsD.length; i++) {
            inValsD[i] = getNumericScalarAsDouble(childrenForInList.get(i));
        }
        expr = createVectorExpression(cl, childExpr.subList(0, 1), VectorExpressionDescriptor.Mode.PROJECTION, returnType);
        ((IDoubleInExpr) expr).setInListValues(inValsD);
    } else if (isDecimalFamily(colType)) {
        cl = (mode == VectorExpressionDescriptor.Mode.FILTER ? FilterDecimalColumnInList.class : DecimalColumnInList.class);
        HiveDecimal[] inValsD = new HiveDecimal[childrenForInList.size()];
        for (int i = 0; i != inValsD.length; i++) {
            inValsD[i] = (HiveDecimal) getVectorTypeScalarValue((ExprNodeConstantDesc) childrenForInList.get(i));
        }
        expr = createVectorExpression(cl, childExpr.subList(0, 1), VectorExpressionDescriptor.Mode.PROJECTION, returnType);
        ((IDecimalInExpr) expr).setInListValues(inValsD);
    } else if (isDateFamily(colType)) {
        cl = (mode == VectorExpressionDescriptor.Mode.FILTER ? FilterLongColumnInList.class : LongColumnInList.class);
        long[] inVals = new long[childrenForInList.size()];
        for (int i = 0; i != inVals.length; i++) {
            inVals[i] = (Long) getVectorTypeScalarValue((ExprNodeConstantDesc) childrenForInList.get(i));
        }
        expr = createVectorExpression(cl, childExpr.subList(0, 1), VectorExpressionDescriptor.Mode.PROJECTION, returnType);
        ((ILongInExpr) expr).setInListValues(inVals);
    }
    // execution to fall back to row mode.
    return expr;
}

Example 10 with TypeInfoUtils.getTypeInfoFromTypeString

use of org.apache.hadoop.hive.serde2.typeinfo.TypeInfoUtils.getTypeInfoFromTypeString in project hive by apache.

the class VectorColumnSetInfo method addKey.

protected void addKey(String outputType) throws HiveException {
    indexLookup[addIndex] = new KeyLookupHelper();
    String typeName = VectorizationContext.mapTypeNameSynonyms(outputType);
    TypeInfo typeInfo = TypeInfoUtils.getTypeInfoFromTypeString(typeName);
    Type columnVectorType = VectorizationContext.getColumnVectorTypeFromTypeInfo(typeInfo);
    switch(columnVectorType) {
        case LONG:
            longIndices[longIndicesIndex] = addIndex;
            indexLookup[addIndex].setLong(longIndicesIndex);
            ++longIndicesIndex;
            break;
        case DOUBLE:
            doubleIndices[doubleIndicesIndex] = addIndex;
            indexLookup[addIndex].setDouble(doubleIndicesIndex);
            ++doubleIndicesIndex;
            break;
        case BYTES:
            stringIndices[stringIndicesIndex] = addIndex;
            indexLookup[addIndex].setString(stringIndicesIndex);
            ++stringIndicesIndex;
            break;
        case DECIMAL:
            decimalIndices[decimalIndicesIndex] = addIndex;
            indexLookup[addIndex].setDecimal(decimalIndicesIndex);
            ++decimalIndicesIndex;
            break;
        case TIMESTAMP:
            timestampIndices[timestampIndicesIndex] = addIndex;
            indexLookup[addIndex].setTimestamp(timestampIndicesIndex);
            ++timestampIndicesIndex;
            break;
        case INTERVAL_DAY_TIME:
            intervalDayTimeIndices[intervalDayTimeIndicesIndex] = addIndex;
            indexLookup[addIndex].setIntervalDayTime(intervalDayTimeIndicesIndex);
            ++intervalDayTimeIndicesIndex;
            break;
        default:
            throw new HiveException("Unexpected column vector type " + columnVectorType);
    }
    addIndex++;
}