Examples with HiveVarcharObjectInspector org.apache.hadoop.hive.serde2.objectinspector.primitive.HiveVarcharObjectInspector used on opensource projects

Example 6 with HiveVarcharObjectInspector

use of org.apache.hadoop.hive.serde2.objectinspector.primitive.HiveVarcharObjectInspector in project hive by apache.

the class ObjectInspectorUtils method hashCode.

public static int hashCode(Object o, ObjectInspector objIns) {
    if (o == null) {
        return 0;
    }
    switch(objIns.getCategory()) {
        case PRIMITIVE:
            {
                PrimitiveObjectInspector poi = ((PrimitiveObjectInspector) objIns);
                switch(poi.getPrimitiveCategory()) {
                    case VOID:
                        return 0;
                    case BOOLEAN:
                        return ((BooleanObjectInspector) poi).get(o) ? 1 : 0;
                    case BYTE:
                        return ((ByteObjectInspector) poi).get(o);
                    case SHORT:
                        return ((ShortObjectInspector) poi).get(o);
                    case INT:
                        return ((IntObjectInspector) poi).get(o);
                    case LONG:
                        {
                            long a = ((LongObjectInspector) poi).get(o);
                            return (int) ((a >>> 32) ^ a);
                        }
                    case FLOAT:
                        return Float.floatToIntBits(((FloatObjectInspector) poi).get(o));
                    case DOUBLE:
                        {
                            // This hash function returns the same result as Double.hashCode()
                            // while DoubleWritable.hashCode returns a different result.
                            long a = Double.doubleToLongBits(((DoubleObjectInspector) poi).get(o));
                            return (int) ((a >>> 32) ^ a);
                        }
                    case STRING:
                        {
                            // This hash function returns the same result as String.hashCode() when
                            // all characters are ASCII, while Text.hashCode() always returns a
                            // different result.
                            Text t = ((StringObjectInspector) poi).getPrimitiveWritableObject(o);
                            int r = 0;
                            for (int i = 0; i < t.getLength(); i++) {
                                r = r * 31 + t.getBytes()[i];
                            }
                            return r;
                        }
                    case CHAR:
                        return ((HiveCharObjectInspector) poi).getPrimitiveWritableObject(o).hashCode();
                    case VARCHAR:
                        return ((HiveVarcharObjectInspector) poi).getPrimitiveWritableObject(o).hashCode();
                    case BINARY:
                        return ((BinaryObjectInspector) poi).getPrimitiveWritableObject(o).hashCode();
                    case DATE:
                        return ((DateObjectInspector) poi).getPrimitiveWritableObject(o).hashCode();
                    case TIMESTAMP:
                        TimestampWritable t = ((TimestampObjectInspector) poi).getPrimitiveWritableObject(o);
                        return t.hashCode();
                    case INTERVAL_YEAR_MONTH:
                        HiveIntervalYearMonthWritable intervalYearMonth = ((HiveIntervalYearMonthObjectInspector) poi).getPrimitiveWritableObject(o);
                        return intervalYearMonth.hashCode();
                    case INTERVAL_DAY_TIME:
                        HiveIntervalDayTimeWritable intervalDayTime = ((HiveIntervalDayTimeObjectInspector) poi).getPrimitiveWritableObject(o);
                        return intervalDayTime.hashCode();
                    case DECIMAL:
                        // compatible hash code.
                        return ((HiveDecimalObjectInspector) poi).getPrimitiveWritableObject(o).hashCode();
                    default:
                        {
                            throw new RuntimeException("Unknown type: " + poi.getPrimitiveCategory());
                        }
                }
            }
        case LIST:
            {
                int r = 0;
                ListObjectInspector listOI = (ListObjectInspector) objIns;
                ObjectInspector elemOI = listOI.getListElementObjectInspector();
                for (int ii = 0; ii < listOI.getListLength(o); ++ii) {
                    r = 31 * r + hashCode(listOI.getListElement(o, ii), elemOI);
                }
                return r;
            }
        case MAP:
            {
                int r = 0;
                MapObjectInspector mapOI = (MapObjectInspector) objIns;
                ObjectInspector keyOI = mapOI.getMapKeyObjectInspector();
                ObjectInspector valueOI = mapOI.getMapValueObjectInspector();
                Map<?, ?> map = mapOI.getMap(o);
                for (Map.Entry<?, ?> entry : map.entrySet()) {
                    r += hashCode(entry.getKey(), keyOI) ^ hashCode(entry.getValue(), valueOI);
                }
                return r;
            }
        case STRUCT:
            int r = 0;
            StructObjectInspector structOI = (StructObjectInspector) objIns;
            List<? extends StructField> fields = structOI.getAllStructFieldRefs();
            for (StructField field : fields) {
                r = 31 * r + hashCode(structOI.getStructFieldData(o, field), field.getFieldObjectInspector());
            }
            return r;
        case UNION:
            UnionObjectInspector uOI = (UnionObjectInspector) objIns;
            byte tag = uOI.getTag(o);
            return hashCode(uOI.getField(o), uOI.getObjectInspectors().get(tag));
        default:
            throw new RuntimeException("Unknown type: " + objIns.getTypeName());
    }
}

Example 7 with HiveVarcharObjectInspector

use of org.apache.hadoop.hive.serde2.objectinspector.primitive.HiveVarcharObjectInspector in project hive by apache.

the class BinarySortableSerDe method serialize.

static void serialize(ByteStream.Output buffer, Object o, ObjectInspector oi, boolean invert, byte nullMarker, byte notNullMarker) throws SerDeException {
    // Is this field a null?
    if (o == null) {
        writeByte(buffer, nullMarker, invert);
        return;
    }
    // This field is not a null.
    writeByte(buffer, notNullMarker, invert);
    switch(oi.getCategory()) {
        case PRIMITIVE:
            {
                PrimitiveObjectInspector poi = (PrimitiveObjectInspector) oi;
                switch(poi.getPrimitiveCategory()) {
                    case VOID:
                        {
                            return;
                        }
                    case BOOLEAN:
                        {
                            boolean v = ((BooleanObjectInspector) poi).get(o);
                            writeByte(buffer, (byte) (v ? 2 : 1), invert);
                            return;
                        }
                    case BYTE:
                        {
                            ByteObjectInspector boi = (ByteObjectInspector) poi;
                            byte v = boi.get(o);
                            writeByte(buffer, (byte) (v ^ 0x80), invert);
                            return;
                        }
                    case SHORT:
                        {
                            ShortObjectInspector spoi = (ShortObjectInspector) poi;
                            short v = spoi.get(o);
                            serializeShort(buffer, v, invert);
                            return;
                        }
                    case INT:
                        {
                            IntObjectInspector ioi = (IntObjectInspector) poi;
                            int v = ioi.get(o);
                            serializeInt(buffer, v, invert);
                            return;
                        }
                    case LONG:
                        {
                            LongObjectInspector loi = (LongObjectInspector) poi;
                            long v = loi.get(o);
                            serializeLong(buffer, v, invert);
                            return;
                        }
                    case FLOAT:
                        {
                            FloatObjectInspector foi = (FloatObjectInspector) poi;
                            serializeFloat(buffer, foi.get(o), invert);
                            return;
                        }
                    case DOUBLE:
                        {
                            DoubleObjectInspector doi = (DoubleObjectInspector) poi;
                            serializeDouble(buffer, doi.get(o), invert);
                            return;
                        }
                    case STRING:
                        {
                            StringObjectInspector soi = (StringObjectInspector) poi;
                            Text t = soi.getPrimitiveWritableObject(o);
                            serializeBytes(buffer, t.getBytes(), t.getLength(), invert);
                            return;
                        }
                    case CHAR:
                        {
                            HiveCharObjectInspector hcoi = (HiveCharObjectInspector) poi;
                            HiveCharWritable hc = hcoi.getPrimitiveWritableObject(o);
                            // Trailing space should ignored for char comparisons.
                            // So write stripped values for this SerDe.
                            Text t = hc.getStrippedValue();
                            serializeBytes(buffer, t.getBytes(), t.getLength(), invert);
                            return;
                        }
                    case VARCHAR:
                        {
                            HiveVarcharObjectInspector hcoi = (HiveVarcharObjectInspector) poi;
                            HiveVarcharWritable hc = hcoi.getPrimitiveWritableObject(o);
                            // use varchar's text field directly
                            Text t = hc.getTextValue();
                            serializeBytes(buffer, t.getBytes(), t.getLength(), invert);
                            return;
                        }
                    case BINARY:
                        {
                            BinaryObjectInspector baoi = (BinaryObjectInspector) poi;
                            BytesWritable ba = baoi.getPrimitiveWritableObject(o);
                            byte[] toSer = new byte[ba.getLength()];
                            System.arraycopy(ba.getBytes(), 0, toSer, 0, ba.getLength());
                            serializeBytes(buffer, toSer, ba.getLength(), invert);
                            return;
                        }
                    case DATE:
                        {
                            DateObjectInspector doi = (DateObjectInspector) poi;
                            int v = doi.getPrimitiveWritableObject(o).getDays();
                            serializeInt(buffer, v, invert);
                            return;
                        }
                    case TIMESTAMP:
                        {
                            TimestampObjectInspector toi = (TimestampObjectInspector) poi;
                            TimestampWritable t = toi.getPrimitiveWritableObject(o);
                            serializeTimestampWritable(buffer, t, invert);
                            return;
                        }
                    case INTERVAL_YEAR_MONTH:
                        {
                            HiveIntervalYearMonthObjectInspector ioi = (HiveIntervalYearMonthObjectInspector) poi;
                            HiveIntervalYearMonth intervalYearMonth = ioi.getPrimitiveJavaObject(o);
                            serializeHiveIntervalYearMonth(buffer, intervalYearMonth, invert);
                            return;
                        }
                    case INTERVAL_DAY_TIME:
                        {
                            HiveIntervalDayTimeObjectInspector ioi = (HiveIntervalDayTimeObjectInspector) poi;
                            HiveIntervalDayTime intervalDayTime = ioi.getPrimitiveJavaObject(o);
                            serializeHiveIntervalDayTime(buffer, intervalDayTime, invert);
                            return;
                        }
                    case DECIMAL:
                        {
                            HiveDecimalObjectInspector boi = (HiveDecimalObjectInspector) poi;
                            HiveDecimal dec = boi.getPrimitiveJavaObject(o);
                            serializeHiveDecimal(buffer, dec, invert);
                            return;
                        }
                    default:
                        {
                            throw new RuntimeException("Unrecognized type: " + poi.getPrimitiveCategory());
                        }
                }
            }
        case LIST:
            {
                ListObjectInspector loi = (ListObjectInspector) oi;
                ObjectInspector eoi = loi.getListElementObjectInspector();
                // \1 followed by each element
                int size = loi.getListLength(o);
                for (int eid = 0; eid < size; eid++) {
                    writeByte(buffer, (byte) 1, invert);
                    serialize(buffer, loi.getListElement(o, eid), eoi, invert, nullMarker, notNullMarker);
                }
                // and \0 to terminate
                writeByte(buffer, (byte) 0, invert);
                return;
            }
        case MAP:
            {
                MapObjectInspector moi = (MapObjectInspector) oi;
                ObjectInspector koi = moi.getMapKeyObjectInspector();
                ObjectInspector voi = moi.getMapValueObjectInspector();
                // \1 followed by each key and then each value
                Map<?, ?> map = moi.getMap(o);
                for (Map.Entry<?, ?> entry : map.entrySet()) {
                    writeByte(buffer, (byte) 1, invert);
                    serialize(buffer, entry.getKey(), koi, invert, nullMarker, notNullMarker);
                    serialize(buffer, entry.getValue(), voi, invert, nullMarker, notNullMarker);
                }
                // and \0 to terminate
                writeByte(buffer, (byte) 0, invert);
                return;
            }
        case STRUCT:
            {
                StructObjectInspector soi = (StructObjectInspector) oi;
                List<? extends StructField> fields = soi.getAllStructFieldRefs();
                for (int i = 0; i < fields.size(); i++) {
                    serialize(buffer, soi.getStructFieldData(o, fields.get(i)), fields.get(i).getFieldObjectInspector(), invert, nullMarker, notNullMarker);
                }
                return;
            }
        case UNION:
            {
                UnionObjectInspector uoi = (UnionObjectInspector) oi;
                byte tag = uoi.getTag(o);
                writeByte(buffer, tag, invert);
                serialize(buffer, uoi.getField(o), uoi.getObjectInspectors().get(tag), invert, nullMarker, notNullMarker);
                return;
            }
        default:
            {
                throw new RuntimeException("Unrecognized type: " + oi.getCategory());
            }
    }
}

Example 8 with HiveVarcharObjectInspector

use of org.apache.hadoop.hive.serde2.objectinspector.primitive.HiveVarcharObjectInspector in project hive by apache.

the class DataWritableWriter method createWriter.

/**
   * Creates a writer for the specific object inspector. The returned writer will be used
   * to call Parquet API for the specific data type.
   * @param inspector The object inspector used to get the correct value type.
   * @param type Type that contains information about the type schema.
   * @return A ParquetWriter object used to call the Parquet API fo the specific data type.
   */
private DataWriter createWriter(ObjectInspector inspector, Type type) {
    if (type.isPrimitive()) {
        checkInspectorCategory(inspector, ObjectInspector.Category.PRIMITIVE);
        PrimitiveObjectInspector primitiveInspector = (PrimitiveObjectInspector) inspector;
        switch(primitiveInspector.getPrimitiveCategory()) {
            case BOOLEAN:
                return new BooleanDataWriter((BooleanObjectInspector) inspector);
            case BYTE:
                return new ByteDataWriter((ByteObjectInspector) inspector);
            case SHORT:
                return new ShortDataWriter((ShortObjectInspector) inspector);
            case INT:
                return new IntDataWriter((IntObjectInspector) inspector);
            case LONG:
                return new LongDataWriter((LongObjectInspector) inspector);
            case FLOAT:
                return new FloatDataWriter((FloatObjectInspector) inspector);
            case DOUBLE:
                return new DoubleDataWriter((DoubleObjectInspector) inspector);
            case STRING:
                return new StringDataWriter((StringObjectInspector) inspector);
            case CHAR:
                return new CharDataWriter((HiveCharObjectInspector) inspector);
            case VARCHAR:
                return new VarcharDataWriter((HiveVarcharObjectInspector) inspector);
            case BINARY:
                return new BinaryDataWriter((BinaryObjectInspector) inspector);
            case TIMESTAMP:
                return new TimestampDataWriter((TimestampObjectInspector) inspector);
            case DECIMAL:
                return new DecimalDataWriter((HiveDecimalObjectInspector) inspector);
            case DATE:
                return new DateDataWriter((DateObjectInspector) inspector);
            default:
                throw new IllegalArgumentException("Unsupported primitive data type: " + primitiveInspector.getPrimitiveCategory());
        }
    } else {
        GroupType groupType = type.asGroupType();
        OriginalType originalType = type.getOriginalType();
        if (originalType != null && originalType.equals(OriginalType.LIST)) {
            checkInspectorCategory(inspector, ObjectInspector.Category.LIST);
            return new ListDataWriter((ListObjectInspector) inspector, groupType);
        } else if (originalType != null && originalType.equals(OriginalType.MAP)) {
            checkInspectorCategory(inspector, ObjectInspector.Category.MAP);
            return new MapDataWriter((MapObjectInspector) inspector, groupType);
        } else {
            checkInspectorCategory(inspector, ObjectInspector.Category.STRUCT);
            return new StructDataWriter((StructObjectInspector) inspector, groupType);
        }
    }
}

Example 9 with HiveVarcharObjectInspector

use of org.apache.hadoop.hive.serde2.objectinspector.primitive.HiveVarcharObjectInspector in project hive by apache.

the class StatsUtils method getAvgColLenOf.

/**
   * Get the raw data size of variable length data types
   * @param conf
   *          - hive conf
   * @param oi
   *          - object inspector
   * @param colType
   *          - column type
   * @return raw data size
   */
public static long getAvgColLenOf(HiveConf conf, ObjectInspector oi, String colType) {
    long configVarLen = HiveConf.getIntVar(conf, HiveConf.ConfVars.HIVE_STATS_MAX_VARIABLE_LENGTH);
    String colTypeLowCase = colType.toLowerCase();
    if (colTypeLowCase.equals(serdeConstants.STRING_TYPE_NAME)) {
        // constant string projection Ex: select "hello" from table
        if (oi instanceof ConstantObjectInspector) {
            ConstantObjectInspector coi = (ConstantObjectInspector) oi;
            // if writable constant is null then return size 0
            Object constantValue = coi.getWritableConstantValue();
            return constantValue == null ? 0 : constantValue.toString().length();
        } else if (oi instanceof StringObjectInspector) {
            // return the variable length from config
            return configVarLen;
        }
    } else if (colTypeLowCase.startsWith(serdeConstants.VARCHAR_TYPE_NAME)) {
        // constant varchar projection
        if (oi instanceof ConstantObjectInspector) {
            ConstantObjectInspector coi = (ConstantObjectInspector) oi;
            // if writable constant is null then return size 0
            Object constantValue = coi.getWritableConstantValue();
            return constantValue == null ? 0 : constantValue.toString().length();
        } else if (oi instanceof HiveVarcharObjectInspector) {
            VarcharTypeInfo type = (VarcharTypeInfo) ((HiveVarcharObjectInspector) oi).getTypeInfo();
            return type.getLength();
        }
    } else if (colTypeLowCase.startsWith(serdeConstants.CHAR_TYPE_NAME)) {
        // constant char projection
        if (oi instanceof ConstantObjectInspector) {
            ConstantObjectInspector coi = (ConstantObjectInspector) oi;
            // if writable constant is null then return size 0
            Object constantValue = coi.getWritableConstantValue();
            return constantValue == null ? 0 : constantValue.toString().length();
        } else if (oi instanceof HiveCharObjectInspector) {
            CharTypeInfo type = (CharTypeInfo) ((HiveCharObjectInspector) oi).getTypeInfo();
            return type.getLength();
        }
    } else if (colTypeLowCase.equals(serdeConstants.BINARY_TYPE_NAME)) {
        // constant byte arrays
        if (oi instanceof ConstantObjectInspector) {
            ConstantObjectInspector coi = (ConstantObjectInspector) oi;
            // if writable constant is null then return size 0
            BytesWritable constantValue = (BytesWritable) coi.getWritableConstantValue();
            return constantValue == null ? 0 : constantValue.getLength();
        } else if (oi instanceof BinaryObjectInspector) {
            // return the variable length from config
            return configVarLen;
        }
    } else {
        // complex types (map, list, struct, union)
        return getSizeOfComplexTypes(conf, oi);
    }
    throw new IllegalArgumentException("Size requested for unknown type: " + colType + " OI: " + oi.getTypeName());
}

Example 10 with HiveVarcharObjectInspector

use of org.apache.hadoop.hive.serde2.objectinspector.primitive.HiveVarcharObjectInspector in project presto by prestodb.

the class SerDeUtils method serializePrimitive.

private static void serializePrimitive(Type type, BlockBuilder builder, Object object, PrimitiveObjectInspector inspector) {
    requireNonNull(builder, "parent builder is null");
    if (object == null) {
        builder.appendNull();
        return;
    }
    switch(inspector.getPrimitiveCategory()) {
        case BOOLEAN:
            BooleanType.BOOLEAN.writeBoolean(builder, ((BooleanObjectInspector) inspector).get(object));
            return;
        case BYTE:
            TinyintType.TINYINT.writeLong(builder, ((ByteObjectInspector) inspector).get(object));
            return;
        case SHORT:
            SmallintType.SMALLINT.writeLong(builder, ((ShortObjectInspector) inspector).get(object));
            return;
        case INT:
            IntegerType.INTEGER.writeLong(builder, ((IntObjectInspector) inspector).get(object));
            return;
        case LONG:
            BigintType.BIGINT.writeLong(builder, ((LongObjectInspector) inspector).get(object));
            return;
        case FLOAT:
            RealType.REAL.writeLong(builder, floatToRawIntBits(((FloatObjectInspector) inspector).get(object)));
            return;
        case DOUBLE:
            DoubleType.DOUBLE.writeDouble(builder, ((DoubleObjectInspector) inspector).get(object));
            return;
        case STRING:
            type.writeSlice(builder, Slices.utf8Slice(((StringObjectInspector) inspector).getPrimitiveJavaObject(object)));
            return;
        case VARCHAR:
            type.writeSlice(builder, Slices.utf8Slice(((HiveVarcharObjectInspector) inspector).getPrimitiveJavaObject(object).getValue()));
            return;
        case CHAR:
            CharType charType = (CharType) type;
            HiveChar hiveChar = ((HiveCharObjectInspector) inspector).getPrimitiveJavaObject(object);
            type.writeSlice(builder, trimSpacesAndTruncateToLength(Slices.utf8Slice(hiveChar.getValue()), charType.getLength()));
            return;
        case DATE:
            DateType.DATE.writeLong(builder, formatDateAsLong(object, (DateObjectInspector) inspector));
            return;
        case TIMESTAMP:
            TimestampType.TIMESTAMP.writeLong(builder, formatTimestampAsLong(object, (TimestampObjectInspector) inspector));
            return;
        case BINARY:
            VARBINARY.writeSlice(builder, Slices.wrappedBuffer(((BinaryObjectInspector) inspector).getPrimitiveJavaObject(object)));
            return;
        case DECIMAL:
            DecimalType decimalType = (DecimalType) type;
            HiveDecimalWritable hiveDecimal = ((HiveDecimalObjectInspector) inspector).getPrimitiveWritableObject(object);
            if (decimalType.isShort()) {
                decimalType.writeLong(builder, DecimalUtils.getShortDecimalValue(hiveDecimal, decimalType.getScale()));
            } else {
                decimalType.writeSlice(builder, DecimalUtils.getLongDecimalValue(hiveDecimal, decimalType.getScale()));
            }
            return;
    }
    throw new RuntimeException("Unknown primitive type: " + inspector.getPrimitiveCategory());
}