Examples with TypeManager com.facebook.presto.common.type.TypeManager used on opensource projects

Example 11 with TypeManager

use of com.facebook.presto.common.type.TypeManager in project presto by prestodb.

the class HiveMetadata method createTemporaryTable.

@Override
public ConnectorTableHandle createTemporaryTable(ConnectorSession session, List<ColumnMetadata> columns, Optional<ConnectorPartitioningMetadata> partitioningMetadata) {
    String schemaName = getTemporaryTableSchema(session);
    HiveStorageFormat storageFormat = getTemporaryTableStorageFormat(session);
    Optional<HiveBucketProperty> bucketProperty = partitioningMetadata.map(partitioning -> {
        Set<String> allColumns = columns.stream().map(ColumnMetadata::getName).collect(toImmutableSet());
        if (!allColumns.containsAll(partitioning.getPartitionColumns())) {
            throw new PrestoException(INVALID_TABLE_PROPERTY, format("Bucketing columns %s not present in schema", Sets.difference(ImmutableSet.copyOf(partitioning.getPartitionColumns()), allColumns)));
        }
        HivePartitioningHandle partitioningHandle = (HivePartitioningHandle) partitioning.getPartitioningHandle();
        List<String> partitionColumns = partitioning.getPartitionColumns();
        BucketFunctionType bucketFunctionType = partitioningHandle.getBucketFunctionType();
        switch(bucketFunctionType) {
            case HIVE_COMPATIBLE:
                return new HiveBucketProperty(partitionColumns, partitioningHandle.getBucketCount(), ImmutableList.of(), HIVE_COMPATIBLE, Optional.empty());
            case PRESTO_NATIVE:
                Map<String, Type> columnNameToTypeMap = columns.stream().collect(toMap(ColumnMetadata::getName, ColumnMetadata::getType));
                return new HiveBucketProperty(partitionColumns, partitioningHandle.getBucketCount(), ImmutableList.of(), PRESTO_NATIVE, Optional.of(partitionColumns.stream().map(columnNameToTypeMap::get).collect(toImmutableList())));
            default:
                throw new IllegalArgumentException("Unsupported bucket function type " + bucketFunctionType);
        }
    });
    if (isUsePageFileForHiveUnsupportedType(session)) {
        if (!columns.stream().map(ColumnMetadata::getType).allMatch(HiveTypeTranslator::isSupportedHiveType)) {
            storageFormat = PAGEFILE;
        }
    }
    // PAGEFILE format doesn't require translation to hive type,
    // choose HIVE_BINARY as a default hive type to make it compatible with Hive connector
    Optional<HiveType> defaultHiveType = storageFormat == PAGEFILE ? Optional.of(HIVE_BINARY) : Optional.empty();
    List<HiveColumnHandle> columnHandles = getColumnHandles(// type to the boolean type that is binary compatible
    translateHiveUnsupportedTypesForTemporaryTable(columns, typeManager), ImmutableSet.of(), typeTranslator, defaultHiveType);
    validateColumns(storageFormat, columnHandles);
    HiveStorageFormat finalStorageFormat = storageFormat;
    String tableName = PRESTO_TEMPORARY_TABLE_NAME_PREFIX + finalStorageFormat.name() + "_" + session.getQueryId().replaceAll("-", "_") + "_" + randomUUID().toString().replaceAll("-", "_");
    Table table = Table.builder().setDatabaseName(schemaName).setTableName(tableName).setOwner(session.getUser()).setTableType(TEMPORARY_TABLE).setDataColumns(columnHandles.stream().map(handle -> new Column(handle.getName(), handle.getHiveType(), handle.getComment(), Optional.empty())).collect(toImmutableList())).withStorage(storage -> storage.setStorageFormat(fromHiveStorageFormat(finalStorageFormat)).setBucketProperty(bucketProperty).setLocation("")).build();
    List<String> partitionColumnNames = table.getPartitionColumns().stream().map(Column::getName).collect(toImmutableList());
    List<HiveColumnHandle> hiveColumnHandles = hiveColumnHandles(table);
    Map<String, Type> columnTypes = hiveColumnHandles.stream().filter(columnHandle -> !columnHandle.isHidden()).collect(toImmutableMap(HiveColumnHandle::getName, column -> column.getHiveType().getType(typeManager)));
    Map<String, Set<ColumnStatisticType>> columnStatisticTypes = hiveColumnHandles.stream().filter(columnHandle -> !partitionColumnNames.contains(columnHandle.getName())).filter(column -> !column.isHidden()).collect(toImmutableMap(HiveColumnHandle::getName, column -> ImmutableSet.copyOf(getSupportedColumnStatisticsForTemporaryTable(typeManager.getType(column.getTypeSignature())))));
    metastore.createTable(session, table, buildInitialPrivilegeSet(table.getOwner()), Optional.empty(), false, createEmptyPartitionStatistics(columnTypes, columnStatisticTypes));
    return new HiveTableHandle(schemaName, tableName);
}

Example 12 with TypeManager

use of com.facebook.presto.common.type.TypeManager in project presto by prestodb.

the class HivePageSourceProvider method createSelectivePageSource.

private static Optional<ConnectorPageSource> createSelectivePageSource(Set<HiveSelectivePageSourceFactory> selectivePageSourceFactories, Configuration configuration, ConnectorSession session, HiveSplit split, HiveTableLayoutHandle layout, List<HiveColumnHandle> columns, DateTimeZone hiveStorageTimeZone, TypeManager typeManager, LoadingCache<RowExpressionCacheKey, RowExpression> rowExpressionCache, SplitContext splitContext, Optional<EncryptionInformation> encryptionInformation) {
    Set<HiveColumnHandle> interimColumns = ImmutableSet.<HiveColumnHandle>builder().addAll(layout.getPredicateColumns().values()).addAll(split.getBucketConversion().map(BucketConversion::getBucketColumnHandles).orElse(ImmutableList.of())).build();
    Set<String> columnNames = columns.stream().map(HiveColumnHandle::getName).collect(toImmutableSet());
    List<HiveColumnHandle> allColumns = ImmutableList.<HiveColumnHandle>builder().addAll(columns).addAll(interimColumns.stream().filter(column -> !columnNames.contains(column.getName())).collect(toImmutableList())).build();
    Path path = new Path(split.getPath());
    List<ColumnMapping> columnMappings = ColumnMapping.buildColumnMappings(split.getPartitionKeys(), allColumns, ImmutableList.of(), split.getTableToPartitionMapping(), path, split.getTableBucketNumber(), split.getFileSize(), split.getFileModifiedTime());
    Optional<BucketAdaptation> bucketAdaptation = split.getBucketConversion().map(conversion -> toBucketAdaptation(conversion, columnMappings, split.getTableBucketNumber(), mapping -> mapping.getHiveColumnHandle().getHiveColumnIndex()));
    Map<Integer, String> prefilledValues = columnMappings.stream().filter(mapping -> mapping.getKind() == ColumnMappingKind.PREFILLED).collect(toImmutableMap(mapping -> mapping.getHiveColumnHandle().getHiveColumnIndex(), ColumnMapping::getPrefilledValue));
    Map<Integer, HiveCoercer> coercers = columnMappings.stream().filter(mapping -> mapping.getCoercionFrom().isPresent()).collect(toImmutableMap(mapping -> mapping.getHiveColumnHandle().getHiveColumnIndex(), mapping -> createCoercer(typeManager, mapping.getCoercionFrom().get(), mapping.getHiveColumnHandle().getHiveType())));
    List<Integer> outputColumns = columns.stream().map(HiveColumnHandle::getHiveColumnIndex).collect(toImmutableList());
    RowExpression optimizedRemainingPredicate = rowExpressionCache.getUnchecked(new RowExpressionCacheKey(layout.getRemainingPredicate(), session));
    if (shouldSkipBucket(layout, split, splitContext)) {
        return Optional.of(new HiveEmptySplitPageSource());
    }
    if (shouldSkipPartition(typeManager, layout, hiveStorageTimeZone, split, splitContext)) {
        return Optional.of(new HiveEmptySplitPageSource());
    }
    CacheQuota cacheQuota = generateCacheQuota(split);
    for (HiveSelectivePageSourceFactory pageSourceFactory : selectivePageSourceFactories) {
        Optional<? extends ConnectorPageSource> pageSource = pageSourceFactory.createPageSource(configuration, session, path, split.getStart(), split.getLength(), split.getFileSize(), split.getStorage(), toColumnHandles(columnMappings, true), prefilledValues, coercers, bucketAdaptation, outputColumns, splitContext.getDynamicFilterPredicate().map(filter -> filter.transform(handle -> new Subfield(((HiveColumnHandle) handle).getName())).intersect(layout.getDomainPredicate())).orElse(layout.getDomainPredicate()), optimizedRemainingPredicate, hiveStorageTimeZone, new HiveFileContext(splitContext.isCacheable(), cacheQuota, split.getExtraFileInfo().map(BinaryExtraHiveFileInfo::new), Optional.of(split.getFileSize()), split.getFileModifiedTime(), HiveSessionProperties.isVerboseRuntimeStatsEnabled(session)), encryptionInformation);
        if (pageSource.isPresent()) {
            return Optional.of(pageSource.get());
        }
    }
    return Optional.empty();
}

Example 13 with TypeManager

use of com.facebook.presto.common.type.TypeManager in project presto by prestodb.

the class HiveMaterializedViewUtils method getMaterializedDataPredicates.

public static MaterializedDataPredicates getMaterializedDataPredicates(SemiTransactionalHiveMetastore metastore, MetastoreContext metastoreContext, TypeManager typeManager, Table table, DateTimeZone timeZone) {
    List<Column> partitionColumns = table.getPartitionColumns();
    for (Column partitionColumn : partitionColumns) {
        HiveType hiveType = partitionColumn.getType();
        if (!hiveType.isSupportedType()) {
            throw new PrestoException(NOT_SUPPORTED, String.format("Unsupported Hive type %s found in partition keys of table %s.%s", hiveType, table.getDatabaseName(), table.getTableName()));
        }
    }
    List<HiveColumnHandle> partitionKeyColumnHandles = getPartitionKeyColumnHandles(table);
    Map<String, Type> partitionTypes = partitionKeyColumnHandles.stream().collect(toImmutableMap(HiveColumnHandle::getName, column -> typeManager.getType(column.getTypeSignature())));
    List<String> partitionNames = metastore.getPartitionNames(metastoreContext, table.getDatabaseName(), table.getTableName()).orElseThrow(() -> new TableNotFoundException(new SchemaTableName(table.getDatabaseName(), table.getTableName())));
    ImmutableList.Builder<TupleDomain<String>> partitionNamesAndValues = ImmutableList.builder();
    for (String partitionName : partitionNames) {
        ImmutableMap.Builder<String, NullableValue> partitionNameAndValuesMap = ImmutableMap.builder();
        Map<String, String> partitions = toPartitionNamesAndValues(partitionName);
        if (partitionColumns.size() != partitions.size()) {
            throw new PrestoException(HIVE_INVALID_METADATA, String.format("Expected %d partition key values, but got %d", partitionColumns.size(), partitions.size()));
        }
        partitionTypes.forEach((name, type) -> {
            String value = partitions.get(name);
            if (value == null) {
                throw new PrestoException(HIVE_INVALID_PARTITION_VALUE, String.format("partition key value cannot be null for field: %s", name));
            }
            partitionNameAndValuesMap.put(name, parsePartitionValue(name, value, type, timeZone));
        });
        TupleDomain<String> tupleDomain = TupleDomain.fromFixedValues(partitionNameAndValuesMap.build());
        partitionNamesAndValues.add(tupleDomain);
    }
    return new MaterializedDataPredicates(partitionNamesAndValues.build(), partitionColumns.stream().map(Column::getName).collect(toImmutableList()));
}

Example 14 with TypeManager

use of com.facebook.presto.common.type.TypeManager in project presto by prestodb.

the class RcFilePageSourceFactory method createPageSource.

@Override
public Optional<? extends ConnectorPageSource> createPageSource(Configuration configuration, ConnectorSession session, Path path, long start, long length, long fileSize, Storage storage, SchemaTableName tableName, Map<String, String> tableParameters, List<HiveColumnHandle> columns, TupleDomain<HiveColumnHandle> effectivePredicate, DateTimeZone hiveStorageTimeZone, HiveFileContext hiveFileContext, Optional<EncryptionInformation> encryptionInformation) {
    if (!columns.isEmpty() && columns.stream().allMatch(hiveColumnHandle -> hiveColumnHandle.getColumnType() == AGGREGATED)) {
        throw new UnsupportedOperationException("Partial aggregation pushdown only supported for ORC/Parquet files. " + "Table " + tableName.toString() + " has file (" + path.toString() + ") of format " + storage.getStorageFormat().getOutputFormat() + ". Set session property hive.pushdown_partial_aggregations_into_scan=false and execute query again");
    }
    RcFileEncoding rcFileEncoding;
    if (LazyBinaryColumnarSerDe.class.getName().equals(storage.getStorageFormat().getSerDe())) {
        rcFileEncoding = new BinaryRcFileEncoding();
    } else if (ColumnarSerDe.class.getName().equals(storage.getStorageFormat().getSerDe())) {
        rcFileEncoding = createTextVectorEncoding(getHiveSchema(storage.getSerdeParameters(), tableParameters), hiveStorageTimeZone);
    } else {
        return Optional.empty();
    }
    if (fileSize == 0) {
        throw new PrestoException(HIVE_BAD_DATA, "RCFile is empty: " + path);
    }
    FSDataInputStream inputStream;
    try {
        inputStream = hdfsEnvironment.getFileSystem(session.getUser(), path, configuration).openFile(path, hiveFileContext);
    } catch (Exception e) {
        if (nullToEmpty(e.getMessage()).trim().equals("Filesystem closed") || e instanceof FileNotFoundException) {
            throw new PrestoException(HIVE_CANNOT_OPEN_SPLIT, e);
        }
        throw new PrestoException(HIVE_CANNOT_OPEN_SPLIT, splitError(e, path, start, length), e);
    }
    try {
        ImmutableMap.Builder<Integer, Type> readColumns = ImmutableMap.builder();
        for (HiveColumnHandle column : columns) {
            readColumns.put(column.getHiveColumnIndex(), column.getHiveType().getType(typeManager));
        }
        RcFileReader rcFileReader = new RcFileReader(new HdfsRcFileDataSource(path.toString(), inputStream, fileSize, stats), rcFileEncoding, readColumns.build(), new AircompressorCodecFactory(new HadoopCodecFactory(configuration.getClassLoader())), start, length, new DataSize(8, Unit.MEGABYTE));
        return Optional.of(new RcFilePageSource(rcFileReader, columns, typeManager));
    } catch (Throwable e) {
        try {
            inputStream.close();
        } catch (IOException ignored) {
        }
        if (e instanceof PrestoException) {
            throw (PrestoException) e;
        }
        String message = splitError(e, path, start, length);
        if (e instanceof RcFileCorruptionException) {
            throw new PrestoException(HIVE_BAD_DATA, message, e);
        }
        if (e.getClass().getSimpleName().equals("BlockMissingException")) {
            throw new PrestoException(HIVE_MISSING_DATA, message, e);
        }
        throw new PrestoException(HIVE_CANNOT_OPEN_SPLIT, message, e);
    }
}

Example 15 with TypeManager

use of com.facebook.presto.common.type.TypeManager in project presto by prestodb.

the class HiveMetadata method finishInsertInternal.

private Optional<ConnectorOutputMetadata> finishInsertInternal(ConnectorSession session, ConnectorInsertTableHandle insertHandle, Collection<Slice> fragments, Collection<ComputedStatistics> computedStatistics) {
    HiveInsertTableHandle handle = (HiveInsertTableHandle) insertHandle;
    List<PartitionUpdate> partitionUpdates = getPartitionUpdates(session, fragments);
    HiveStorageFormat tableStorageFormat = handle.getTableStorageFormat();
    partitionUpdates = PartitionUpdate.mergePartitionUpdates(partitionUpdates);
    MetastoreContext metastoreContext = getMetastoreContext(session);
    Table table = metastore.getTable(metastoreContext, handle.getSchemaName(), handle.getTableName()).orElseThrow(() -> new TableNotFoundException(handle.getSchemaTableName()));
    if (!table.getStorage().getStorageFormat().getInputFormat().equals(tableStorageFormat.getInputFormat()) && isRespectTableFormat(session)) {
        throw new PrestoException(HIVE_CONCURRENT_MODIFICATION_DETECTED, "Table format changed during insert");
    }
    if (handle.getBucketProperty().isPresent() && isCreateEmptyBucketFiles(session)) {
        List<PartitionUpdate> partitionUpdatesForMissingBuckets = computePartitionUpdatesForMissingBuckets(session, handle, table, partitionUpdates);
        // replace partitionUpdates before creating the zero-row files so that those files will be cleaned up if we end up rollback
        partitionUpdates = PartitionUpdate.mergePartitionUpdates(concat(partitionUpdates, partitionUpdatesForMissingBuckets));
        HdfsContext hdfsContext = new HdfsContext(session, table.getDatabaseName(), table.getTableName(), table.getStorage().getLocation(), false);
        for (PartitionUpdate partitionUpdate : partitionUpdatesForMissingBuckets) {
            Optional<Partition> partition = table.getPartitionColumns().isEmpty() ? Optional.empty() : Optional.of(partitionObjectBuilder.buildPartitionObject(session, table, partitionUpdate, prestoVersion, handle.getEncryptionInformation().map(encryptionInfo -> encryptionInfo.getDwrfEncryptionMetadata().map(DwrfEncryptionMetadata::getExtraMetadata).orElseGet(ImmutableMap::of)).orElseGet(ImmutableMap::of)));
            zeroRowFileCreator.createFiles(session, hdfsContext, partitionUpdate.getWritePath(), getTargetFileNames(partitionUpdate.getFileWriteInfos()), getStorageFormat(partition, table), handle.getCompressionCodec(), getSchema(partition, table));
        }
    }
    List<String> partitionedBy = table.getPartitionColumns().stream().map(Column::getName).collect(toImmutableList());
    Map<String, Type> columnTypes = handle.getInputColumns().stream().collect(toImmutableMap(HiveColumnHandle::getName, column -> column.getHiveType().getType(typeManager)));
    Map<List<String>, ComputedStatistics> partitionComputedStatistics = createComputedStatisticsToPartitionMap(computedStatistics, partitionedBy, columnTypes);
    Set<String> existingPartitions = getExistingPartitionNames(session.getIdentity(), metastoreContext, handle.getSchemaName(), handle.getTableName(), partitionUpdates);
    for (PartitionUpdate partitionUpdate : partitionUpdates) {
        if (partitionUpdate.getName().isEmpty()) {
            if (handle.getEncryptionInformation().isPresent()) {
                throw new PrestoException(HIVE_UNSUPPORTED_ENCRYPTION_OPERATION, "Inserting into an existing table with encryption enabled is not supported yet");
            }
            // insert into unpartitioned table
            PartitionStatistics partitionStatistics = createPartitionStatistics(session, partitionUpdate.getStatistics(), columnTypes, getColumnStatistics(partitionComputedStatistics, ImmutableList.of()));
            metastore.finishInsertIntoExistingTable(session, handle.getSchemaName(), handle.getTableName(), partitionUpdate.getWritePath(), getTargetFileNames(partitionUpdate.getFileWriteInfos()), partitionStatistics);
        } else if (partitionUpdate.getUpdateMode() == APPEND) {
            if (handle.getEncryptionInformation().isPresent()) {
                throw new PrestoException(HIVE_UNSUPPORTED_ENCRYPTION_OPERATION, "Inserting into an existing partition with encryption enabled is not supported yet");
            }
            // insert into existing partition
            List<String> partitionValues = toPartitionValues(partitionUpdate.getName());
            PartitionStatistics partitionStatistics = createPartitionStatistics(session, partitionUpdate.getStatistics(), columnTypes, getColumnStatistics(partitionComputedStatistics, partitionValues));
            metastore.finishInsertIntoExistingPartition(session, handle.getSchemaName(), handle.getTableName(), handle.getLocationHandle().getTargetPath().toString(), partitionValues, partitionUpdate.getWritePath(), getTargetFileNames(partitionUpdate.getFileWriteInfos()), partitionStatistics);
        } else if (partitionUpdate.getUpdateMode() == NEW || partitionUpdate.getUpdateMode() == OVERWRITE) {
            Map<String, String> extraPartitionMetadata = handle.getEncryptionInformation().map(encryptionInfo -> encryptionInfo.getDwrfEncryptionMetadata().map(DwrfEncryptionMetadata::getExtraMetadata).orElseGet(ImmutableMap::of)).orElseGet(ImmutableMap::of);
            if (isPreferManifestsToListFiles(session) && isFileRenamingEnabled(session)) {
                // Store list of file names and sizes in partition metadata when prefer_manifests_to_list_files and file_renaming_enabled are set to true
                extraPartitionMetadata = updatePartitionMetadataWithFileNamesAndSizes(partitionUpdate, extraPartitionMetadata);
            }
            // Track the manifest blob size
            getManifestSizeInBytes(session, partitionUpdate, extraPartitionMetadata).ifPresent(hivePartitionStats::addManifestSizeInBytes);
            // insert into new partition or overwrite existing partition
            Partition partition = partitionObjectBuilder.buildPartitionObject(session, table, partitionUpdate, prestoVersion, extraPartitionMetadata);
            if (!partition.getStorage().getStorageFormat().getInputFormat().equals(handle.getPartitionStorageFormat().getInputFormat()) && isRespectTableFormat(session)) {
                throw new PrestoException(HIVE_CONCURRENT_MODIFICATION_DETECTED, "Partition format changed during insert");
            }
            if (existingPartitions.contains(partitionUpdate.getName())) {
                if (partitionUpdate.getUpdateMode() == OVERWRITE) {
                    metastore.dropPartition(session, handle.getSchemaName(), handle.getTableName(), handle.getLocationHandle().getTargetPath().toString(), partition.getValues());
                } else {
                    throw new PrestoException(HIVE_PARTITION_READ_ONLY, "Cannot insert into an existing partition of Hive table: " + partitionUpdate.getName());
                }
            }
            PartitionStatistics partitionStatistics = createPartitionStatistics(session, partitionUpdate.getStatistics(), columnTypes, getColumnStatistics(partitionComputedStatistics, partition.getValues()));
            metastore.addPartition(session, handle.getSchemaName(), handle.getTableName(), table.getStorage().getLocation(), false, partition, partitionUpdate.getWritePath(), partitionStatistics);
        } else {
            throw new IllegalArgumentException(format("Unsupported update mode: %s", partitionUpdate.getUpdateMode()));
        }
    }
    return Optional.of(new HiveWrittenPartitions(partitionUpdates.stream().map(PartitionUpdate::getName).map(name -> name.isEmpty() ? UNPARTITIONED_ID : name).collect(toList())));
}