Examples with ColumnarInts org.apache.druid.segment.data.ColumnarInts used on opensource projects

Example 1 with ColumnarInts

use of org.apache.druid.segment.data.ColumnarInts in project druid by druid-io.

the class DictionaryEncodedColumnPartSerde method getDeserializer.

@Override
public Deserializer getDeserializer() {
    return new Deserializer() {

        @Override
        public void read(ByteBuffer buffer, ColumnBuilder builder, ColumnConfig columnConfig) {
            final VERSION rVersion = VERSION.fromByte(buffer.get());
            final int rFlags;
            if (rVersion.compareTo(VERSION.COMPRESSED) >= 0) {
                rFlags = buffer.getInt();
            } else {
                rFlags = rVersion.equals(VERSION.UNCOMPRESSED_MULTI_VALUE) ? Feature.MULTI_VALUE.getMask() : NO_FLAGS;
            }
            final boolean hasMultipleValues = Feature.MULTI_VALUE.isSet(rFlags) || Feature.MULTI_VALUE_V3.isSet(rFlags);
            // Duplicate the first buffer since we are reading the dictionary twice.
            final GenericIndexed<String> rDictionary = GenericIndexed.read(buffer.duplicate(), GenericIndexed.STRING_STRATEGY, builder.getFileMapper());
            final GenericIndexed<ByteBuffer> rDictionaryUtf8 = GenericIndexed.read(buffer, GenericIndexed.BYTE_BUFFER_STRATEGY, builder.getFileMapper());
            builder.setType(ValueType.STRING);
            final WritableSupplier<ColumnarInts> rSingleValuedColumn;
            final WritableSupplier<ColumnarMultiInts> rMultiValuedColumn;
            if (hasMultipleValues) {
                rMultiValuedColumn = readMultiValuedColumn(rVersion, buffer, rFlags);
                rSingleValuedColumn = null;
            } else {
                rSingleValuedColumn = readSingleValuedColumn(rVersion, buffer);
                rMultiValuedColumn = null;
            }
            final String firstDictionaryEntry = rDictionary.get(0);
            DictionaryEncodedColumnSupplier dictionaryEncodedColumnSupplier = new DictionaryEncodedColumnSupplier(rDictionary, rDictionaryUtf8, rSingleValuedColumn, rMultiValuedColumn, columnConfig.columnCacheSizeBytes());
            builder.setHasMultipleValues(hasMultipleValues).setHasNulls(firstDictionaryEntry == null).setDictionaryEncodedColumnSupplier(dictionaryEncodedColumnSupplier);
            if (!Feature.NO_BITMAP_INDEX.isSet(rFlags)) {
                GenericIndexed<ImmutableBitmap> rBitmaps = GenericIndexed.read(buffer, bitmapSerdeFactory.getObjectStrategy(), builder.getFileMapper());
                builder.setBitmapIndex(new StringBitmapIndexColumnPartSupplier(bitmapSerdeFactory.getBitmapFactory(), rBitmaps, rDictionary));
            }
            if (buffer.hasRemaining()) {
                ImmutableRTree rSpatialIndex = new ImmutableRTreeObjectStrategy(bitmapSerdeFactory.getBitmapFactory()).fromByteBufferWithSize(buffer);
                builder.setSpatialIndex(new SpatialIndexColumnPartSupplier(rSpatialIndex));
            }
        }

        private WritableSupplier<ColumnarInts> readSingleValuedColumn(VERSION version, ByteBuffer buffer) {
            switch(version) {
                case UNCOMPRESSED_SINGLE_VALUE:
                case UNCOMPRESSED_WITH_FLAGS:
                    return VSizeColumnarInts.readFromByteBuffer(buffer);
                case COMPRESSED:
                    return CompressedVSizeColumnarIntsSupplier.fromByteBuffer(buffer, byteOrder);
                default:
                    throw new IAE("Unsupported single-value version[%s]", version);
            }
        }

        private WritableSupplier<ColumnarMultiInts> readMultiValuedColumn(VERSION version, ByteBuffer buffer, int flags) {
            switch(version) {
                case UNCOMPRESSED_MULTI_VALUE:
                    {
                        return VSizeColumnarMultiInts.readFromByteBuffer(buffer);
                    }
                case UNCOMPRESSED_WITH_FLAGS:
                    {
                        if (Feature.MULTI_VALUE.isSet(flags)) {
                            return VSizeColumnarMultiInts.readFromByteBuffer(buffer);
                        } else {
                            throw new IAE("Unrecognized multi-value flag[%d] for version[%s]", flags, version);
                        }
                    }
                case COMPRESSED:
                    {
                        if (Feature.MULTI_VALUE.isSet(flags)) {
                            return CompressedVSizeColumnarMultiIntsSupplier.fromByteBuffer(buffer, byteOrder);
                        } else if (Feature.MULTI_VALUE_V3.isSet(flags)) {
                            return V3CompressedVSizeColumnarMultiIntsSupplier.fromByteBuffer(buffer, byteOrder);
                        } else {
                            throw new IAE("Unrecognized multi-value flag[%d] for version[%s]", flags, version);
                        }
                    }
                default:
                    throw new IAE("Unsupported multi-value version[%s]", version);
            }
        }
    };
}

Example 2 with ColumnarInts

use of org.apache.druid.segment.data.ColumnarInts in project druid by druid-io.

the class CompressedVSizeColumnarMultiIntsBenchmark method setup.

@Setup
public void setup() throws IOException {
    Random rand = ThreadLocalRandom.current();
    List<int[]> rows = new ArrayList<>();
    final int bound = 1 << bytes;
    for (int i = 0; i < 0x100000; i++) {
        int count = rand.nextInt(valuesPerRowBound) + 1;
        int[] row = new int[rand.nextInt(count)];
        for (int j = 0; j < row.length; j++) {
            row[j] = rand.nextInt(bound);
        }
        rows.add(row);
    }
    final ByteBuffer bufferCompressed = serialize(CompressedVSizeColumnarMultiIntsSupplier.fromIterable(Iterables.transform(rows, (Function<int[], ColumnarInts>) input -> VSizeColumnarInts.fromArray(input, 20)), bound - 1, ByteOrder.nativeOrder(), CompressionStrategy.LZ4, Closer.create()));
    this.compressed = CompressedVSizeColumnarMultiIntsSupplier.fromByteBuffer(bufferCompressed, ByteOrder.nativeOrder()).get();
    final ByteBuffer bufferUncompressed = serialize(VSizeColumnarMultiInts.fromIterable(Iterables.transform(rows, input -> VSizeColumnarInts.fromArray(input, 20))));
    this.uncompressed = VSizeColumnarMultiInts.readFromByteBuffer(bufferUncompressed);
    filter = new BitSet();
    for (int i = 0; i < filteredRowCount; i++) {
        int rowToAccess = rand.nextInt(rows.size());
        // Skip already selected rows if any
        while (filter.get(rowToAccess)) {
            rowToAccess = (rowToAccess + 1) % rows.size();
        }
        filter.set(rowToAccess);
    }
}