Search in sources :

Example 1 with DELTA_CANNOT_OPEN_SPLIT

use of com.facebook.presto.delta.DeltaErrorCode.DELTA_CANNOT_OPEN_SPLIT in project presto by prestodb.

the class DeltaPageSourceProvider method createParquetPageSource.

private static ConnectorPageSource createParquetPageSource(HdfsEnvironment hdfsEnvironment, String user, Configuration configuration, Path path, long start, long length, long fileSize, List<DeltaColumnHandle> columns, SchemaTableName tableName, DataSize maxReadBlockSize, boolean batchReaderEnabled, boolean verificationEnabled, TypeManager typeManager, TupleDomain<DeltaColumnHandle> effectivePredicate, FileFormatDataSourceStats stats, boolean columnIndexFilterEnabled) {
    AggregatedMemoryContext systemMemoryContext = newSimpleAggregatedMemoryContext();
    ParquetDataSource dataSource = null;
    try {
        FSDataInputStream inputStream = hdfsEnvironment.getFileSystem(user, path, configuration).open(path);
        dataSource = buildHdfsParquetDataSource(inputStream, path, stats);
        ParquetMetadata parquetMetadata = MetadataReader.readFooter(dataSource, fileSize).getParquetMetadata();
        FileMetaData fileMetaData = parquetMetadata.getFileMetaData();
        MessageType fileSchema = fileMetaData.getSchema();
        Optional<MessageType> message = columns.stream().filter(column -> column.getColumnType() == REGULAR || isPushedDownSubfield(column)).map(column -> getColumnType(typeManager.getType(column.getDataType()), fileSchema, column, tableName, path)).filter(Optional::isPresent).map(Optional::get).map(type -> new MessageType(fileSchema.getName(), type)).reduce(MessageType::union);
        MessageType requestedSchema = message.orElse(new MessageType(fileSchema.getName(), ImmutableList.of()));
        ImmutableList.Builder<BlockMetaData> footerBlocks = ImmutableList.builder();
        for (BlockMetaData block : parquetMetadata.getBlocks()) {
            long firstDataPage = block.getColumns().get(0).getFirstDataPageOffset();
            if (firstDataPage >= start && firstDataPage < start + length) {
                footerBlocks.add(block);
            }
        }
        Map<List<String>, RichColumnDescriptor> descriptorsByPath = getDescriptors(fileSchema, requestedSchema);
        TupleDomain<ColumnDescriptor> parquetTupleDomain = getParquetTupleDomain(descriptorsByPath, effectivePredicate);
        Predicate parquetPredicate = buildPredicate(requestedSchema, parquetTupleDomain, descriptorsByPath);
        final ParquetDataSource finalDataSource = dataSource;
        ImmutableList.Builder<BlockMetaData> blocks = ImmutableList.builder();
        List<ColumnIndexStore> blockIndexStores = new ArrayList<>();
        for (BlockMetaData block : footerBlocks.build()) {
            Optional<ColumnIndexStore> columnIndexStore = ColumnIndexFilterUtils.getColumnIndexStore(parquetPredicate, finalDataSource, block, descriptorsByPath, columnIndexFilterEnabled);
            if (predicateMatches(parquetPredicate, block, finalDataSource, descriptorsByPath, parquetTupleDomain, columnIndexStore, columnIndexFilterEnabled)) {
                blocks.add(block);
                blockIndexStores.add(columnIndexStore.orElse(null));
            }
        }
        MessageColumnIO messageColumnIO = getColumnIO(fileSchema, requestedSchema);
        ParquetReader parquetReader = new ParquetReader(messageColumnIO, blocks.build(), dataSource, systemMemoryContext, maxReadBlockSize, batchReaderEnabled, verificationEnabled, parquetPredicate, blockIndexStores, columnIndexFilterEnabled);
        ImmutableList.Builder<String> namesBuilder = ImmutableList.builder();
        ImmutableList.Builder<Type> typesBuilder = ImmutableList.builder();
        ImmutableList.Builder<Optional<Field>> fieldsBuilder = ImmutableList.builder();
        for (DeltaColumnHandle column : columns) {
            checkArgument(column.getColumnType() == REGULAR || column.getColumnType() == SUBFIELD, "column type must be regular or subfield column");
            String name = column.getName();
            Type type = typeManager.getType(column.getDataType());
            namesBuilder.add(name);
            typesBuilder.add(type);
            if (isPushedDownSubfield(column)) {
                Subfield pushedDownSubfield = getPushedDownSubfield(column);
                List<String> nestedColumnPath = nestedColumnPath(pushedDownSubfield);
                Optional<ColumnIO> columnIO = findNestedColumnIO(lookupColumnByName(messageColumnIO, pushedDownSubfield.getRootName()), nestedColumnPath);
                if (columnIO.isPresent()) {
                    fieldsBuilder.add(constructField(type, columnIO.get()));
                } else {
                    fieldsBuilder.add(Optional.empty());
                }
            } else if (getParquetType(type, fileSchema, column, tableName, path).isPresent()) {
                fieldsBuilder.add(constructField(type, lookupColumnByName(messageColumnIO, name)));
            } else {
                fieldsBuilder.add(Optional.empty());
            }
        }
        return new ParquetPageSource(parquetReader, typesBuilder.build(), fieldsBuilder.build(), namesBuilder.build(), new RuntimeStats());
    } catch (Exception exception) {
        try {
            if (dataSource != null) {
                dataSource.close();
            }
        } catch (IOException ignored) {
        }
        if (exception instanceof PrestoException) {
            throw (PrestoException) exception;
        }
        if (exception instanceof ParquetCorruptionException) {
            throw new PrestoException(DELTA_BAD_DATA, exception);
        }
        if (exception instanceof AccessControlException) {
            throw new PrestoException(PERMISSION_DENIED, exception.getMessage(), exception);
        }
        if (nullToEmpty(exception.getMessage()).trim().equals("Filesystem closed") || exception instanceof FileNotFoundException) {
            throw new PrestoException(DELTA_CANNOT_OPEN_SPLIT, exception);
        }
        String message = format("Error opening Hive split %s (offset=%s, length=%s): %s", path, start, length, exception.getMessage());
        if (exception.getClass().getSimpleName().equals("BlockMissingException")) {
            throw new PrestoException(DELTA_MISSING_DATA, message, exception);
        }
        throw new PrestoException(DELTA_CANNOT_OPEN_SPLIT, message, exception);
    }
}
Also used : ColumnIOConverter.constructField(org.apache.parquet.io.ColumnIOConverter.constructField) HdfsEnvironment(com.facebook.presto.hive.HdfsEnvironment) RichColumnDescriptor(com.facebook.presto.parquet.RichColumnDescriptor) DeltaColumnHandle.getPushedDownSubfield(com.facebook.presto.delta.DeltaColumnHandle.getPushedDownSubfield) ConnectorTransactionHandle(com.facebook.presto.spi.connector.ConnectorTransactionHandle) ParquetCorruptionException(com.facebook.presto.parquet.ParquetCorruptionException) ParquetTypeUtils.lookupColumnByName(com.facebook.presto.parquet.ParquetTypeUtils.lookupColumnByName) Preconditions.checkArgument(com.google.common.base.Preconditions.checkArgument) SchemaTableName(com.facebook.presto.spi.SchemaTableName) Collectors.toMap(java.util.stream.Collectors.toMap) SplitContext(com.facebook.presto.spi.SplitContext) ParquetTypeUtils.getDescriptors(com.facebook.presto.parquet.ParquetTypeUtils.getDescriptors) Configuration(org.apache.hadoop.conf.Configuration) Map(java.util.Map) Path(org.apache.hadoop.fs.Path) DeltaColumnHandle.isPushedDownSubfield(com.facebook.presto.delta.DeltaColumnHandle.isPushedDownSubfield) RuntimeStats(com.facebook.presto.common.RuntimeStats) FileFormatDataSourceStats(com.facebook.presto.hive.FileFormatDataSourceStats) HdfsContext(com.facebook.presto.hive.HdfsContext) ConnectorPageSourceProvider(com.facebook.presto.spi.connector.ConnectorPageSourceProvider) FSDataInputStream(org.apache.hadoop.fs.FSDataInputStream) ParquetDataSource(com.facebook.presto.parquet.ParquetDataSource) SUBFIELD(com.facebook.presto.delta.DeltaColumnHandle.ColumnType.SUBFIELD) GroupType(org.apache.parquet.schema.GroupType) ImmutableMap(com.google.common.collect.ImmutableMap) DELTA_MISSING_DATA(com.facebook.presto.delta.DeltaErrorCode.DELTA_MISSING_DATA) ColumnIndexStore(org.apache.parquet.internal.filter2.columnindex.ColumnIndexStore) Collectors(java.util.stream.Collectors) ColumnIOConverter.findNestedColumnIO(org.apache.parquet.io.ColumnIOConverter.findNestedColumnIO) FileNotFoundException(java.io.FileNotFoundException) String.format(java.lang.String.format) ColumnIndexFilterUtils(com.facebook.presto.parquet.reader.ColumnIndexFilterUtils) ConnectorSession(com.facebook.presto.spi.ConnectorSession) MessageType(org.apache.parquet.schema.MessageType) DataSize(io.airlift.units.DataSize) List(java.util.List) DELTA_CANNOT_OPEN_SPLIT(com.facebook.presto.delta.DeltaErrorCode.DELTA_CANNOT_OPEN_SPLIT) ColumnDescriptor(org.apache.parquet.column.ColumnDescriptor) ParquetTypeUtils.columnPathFromSubfield(com.facebook.presto.parquet.ParquetTypeUtils.columnPathFromSubfield) BlockMetaData(org.apache.parquet.hadoop.metadata.BlockMetaData) ColumnIO(org.apache.parquet.io.ColumnIO) Optional(java.util.Optional) DELTA_PARQUET_SCHEMA_MISMATCH(com.facebook.presto.delta.DeltaErrorCode.DELTA_PARQUET_SCHEMA_MISMATCH) ParquetPageSource(com.facebook.presto.hive.parquet.ParquetPageSource) REGULAR(com.facebook.presto.delta.DeltaColumnHandle.ColumnType.REGULAR) HdfsParquetDataSource.buildHdfsParquetDataSource(com.facebook.presto.hive.parquet.HdfsParquetDataSource.buildHdfsParquetDataSource) DeltaSessionProperties.getParquetMaxReadBlockSize(com.facebook.presto.delta.DeltaSessionProperties.getParquetMaxReadBlockSize) MessageColumnIO(org.apache.parquet.io.MessageColumnIO) MetadataReader(com.facebook.presto.parquet.cache.MetadataReader) PARTITION(com.facebook.presto.delta.DeltaColumnHandle.ColumnType.PARTITION) Strings.nullToEmpty(com.google.common.base.Strings.nullToEmpty) Utils(com.facebook.presto.common.Utils) ConnectorTableLayoutHandle(com.facebook.presto.spi.ConnectorTableLayoutHandle) PredicateUtils.predicateMatches(com.facebook.presto.parquet.predicate.PredicateUtils.predicateMatches) PrestoException(com.facebook.presto.spi.PrestoException) DeltaSessionProperties.isParquetBatchReaderVerificationEnabled(com.facebook.presto.delta.DeltaSessionProperties.isParquetBatchReaderVerificationEnabled) ArrayList(java.util.ArrayList) ParquetTypeUtils.getSubfieldType(com.facebook.presto.parquet.ParquetTypeUtils.getSubfieldType) Inject(javax.inject.Inject) ParquetTypeUtils.getParquetTypeByName(com.facebook.presto.parquet.ParquetTypeUtils.getParquetTypeByName) Subfield(com.facebook.presto.common.Subfield) ImmutableList(com.google.common.collect.ImmutableList) TypeManager(com.facebook.presto.common.type.TypeManager) Objects.requireNonNull(java.util.Objects.requireNonNull) Predicate(com.facebook.presto.parquet.predicate.Predicate) ParquetPageSourceFactory.checkSchemaMatch(com.facebook.presto.hive.parquet.ParquetPageSourceFactory.checkSchemaMatch) DELTA_BAD_DATA(com.facebook.presto.delta.DeltaErrorCode.DELTA_BAD_DATA) AggregatedMemoryContext.newSimpleAggregatedMemoryContext(com.facebook.presto.memory.context.AggregatedMemoryContext.newSimpleAggregatedMemoryContext) PredicateUtils.buildPredicate(com.facebook.presto.parquet.predicate.PredicateUtils.buildPredicate) Type(com.facebook.presto.common.type.Type) ParquetTypeUtils.getColumnIO(com.facebook.presto.parquet.ParquetTypeUtils.getColumnIO) IOException(java.io.IOException) ParquetTypeUtils.nestedColumnPath(com.facebook.presto.parquet.ParquetTypeUtils.nestedColumnPath) DeltaSessionProperties.isParquetBatchReadsEnabled(com.facebook.presto.delta.DeltaSessionProperties.isParquetBatchReadsEnabled) Domain(com.facebook.presto.common.predicate.Domain) TupleDomain(com.facebook.presto.common.predicate.TupleDomain) AggregatedMemoryContext(com.facebook.presto.memory.context.AggregatedMemoryContext) ParquetReader(com.facebook.presto.parquet.reader.ParquetReader) PERMISSION_DENIED(com.facebook.presto.spi.StandardErrorCode.PERMISSION_DENIED) Field(com.facebook.presto.parquet.Field) ConnectorSplit(com.facebook.presto.spi.ConnectorSplit) ConnectorPageSource(com.facebook.presto.spi.ConnectorPageSource) DeltaTypeUtils.convertPartitionValue(com.facebook.presto.delta.DeltaTypeUtils.convertPartitionValue) ColumnHandle(com.facebook.presto.spi.ColumnHandle) AccessControlException(org.apache.hadoop.security.AccessControlException) FileMetaData(org.apache.parquet.hadoop.metadata.FileMetaData) ParquetMetadata(org.apache.parquet.hadoop.metadata.ParquetMetadata) Block(com.facebook.presto.common.block.Block) BlockMetaData(org.apache.parquet.hadoop.metadata.BlockMetaData) ParquetMetadata(org.apache.parquet.hadoop.metadata.ParquetMetadata) ImmutableList(com.google.common.collect.ImmutableList) RichColumnDescriptor(com.facebook.presto.parquet.RichColumnDescriptor) RuntimeStats(com.facebook.presto.common.RuntimeStats) ArrayList(java.util.ArrayList) FileNotFoundException(java.io.FileNotFoundException) PrestoException(com.facebook.presto.spi.PrestoException) MessageColumnIO(org.apache.parquet.io.MessageColumnIO) Predicate(com.facebook.presto.parquet.predicate.Predicate) PredicateUtils.buildPredicate(com.facebook.presto.parquet.predicate.PredicateUtils.buildPredicate) ParquetCorruptionException(com.facebook.presto.parquet.ParquetCorruptionException) ColumnIndexStore(org.apache.parquet.internal.filter2.columnindex.ColumnIndexStore) List(java.util.List) ArrayList(java.util.ArrayList) ImmutableList(com.google.common.collect.ImmutableList) FileMetaData(org.apache.parquet.hadoop.metadata.FileMetaData) MessageType(org.apache.parquet.schema.MessageType) DeltaColumnHandle.getPushedDownSubfield(com.facebook.presto.delta.DeltaColumnHandle.getPushedDownSubfield) DeltaColumnHandle.isPushedDownSubfield(com.facebook.presto.delta.DeltaColumnHandle.isPushedDownSubfield) ParquetTypeUtils.columnPathFromSubfield(com.facebook.presto.parquet.ParquetTypeUtils.columnPathFromSubfield) Subfield(com.facebook.presto.common.Subfield) ParquetDataSource(com.facebook.presto.parquet.ParquetDataSource) HdfsParquetDataSource.buildHdfsParquetDataSource(com.facebook.presto.hive.parquet.HdfsParquetDataSource.buildHdfsParquetDataSource) Optional(java.util.Optional) RichColumnDescriptor(com.facebook.presto.parquet.RichColumnDescriptor) ColumnDescriptor(org.apache.parquet.column.ColumnDescriptor) ParquetReader(com.facebook.presto.parquet.reader.ParquetReader) AccessControlException(org.apache.hadoop.security.AccessControlException) ParquetPageSource(com.facebook.presto.hive.parquet.ParquetPageSource) IOException(java.io.IOException) AggregatedMemoryContext.newSimpleAggregatedMemoryContext(com.facebook.presto.memory.context.AggregatedMemoryContext.newSimpleAggregatedMemoryContext) AggregatedMemoryContext(com.facebook.presto.memory.context.AggregatedMemoryContext) ColumnIOConverter.findNestedColumnIO(org.apache.parquet.io.ColumnIOConverter.findNestedColumnIO) ColumnIO(org.apache.parquet.io.ColumnIO) MessageColumnIO(org.apache.parquet.io.MessageColumnIO) ParquetTypeUtils.getColumnIO(com.facebook.presto.parquet.ParquetTypeUtils.getColumnIO) ParquetCorruptionException(com.facebook.presto.parquet.ParquetCorruptionException) FileNotFoundException(java.io.FileNotFoundException) PrestoException(com.facebook.presto.spi.PrestoException) IOException(java.io.IOException) AccessControlException(org.apache.hadoop.security.AccessControlException) GroupType(org.apache.parquet.schema.GroupType) MessageType(org.apache.parquet.schema.MessageType) ParquetTypeUtils.getSubfieldType(com.facebook.presto.parquet.ParquetTypeUtils.getSubfieldType) Type(com.facebook.presto.common.type.Type) FSDataInputStream(org.apache.hadoop.fs.FSDataInputStream)

Aggregations

RuntimeStats (com.facebook.presto.common.RuntimeStats)1 Subfield (com.facebook.presto.common.Subfield)1 Utils (com.facebook.presto.common.Utils)1 Block (com.facebook.presto.common.block.Block)1 Domain (com.facebook.presto.common.predicate.Domain)1 TupleDomain (com.facebook.presto.common.predicate.TupleDomain)1 Type (com.facebook.presto.common.type.Type)1 TypeManager (com.facebook.presto.common.type.TypeManager)1 PARTITION (com.facebook.presto.delta.DeltaColumnHandle.ColumnType.PARTITION)1 REGULAR (com.facebook.presto.delta.DeltaColumnHandle.ColumnType.REGULAR)1 SUBFIELD (com.facebook.presto.delta.DeltaColumnHandle.ColumnType.SUBFIELD)1 DeltaColumnHandle.getPushedDownSubfield (com.facebook.presto.delta.DeltaColumnHandle.getPushedDownSubfield)1 DeltaColumnHandle.isPushedDownSubfield (com.facebook.presto.delta.DeltaColumnHandle.isPushedDownSubfield)1 DELTA_BAD_DATA (com.facebook.presto.delta.DeltaErrorCode.DELTA_BAD_DATA)1 DELTA_CANNOT_OPEN_SPLIT (com.facebook.presto.delta.DeltaErrorCode.DELTA_CANNOT_OPEN_SPLIT)1 DELTA_MISSING_DATA (com.facebook.presto.delta.DeltaErrorCode.DELTA_MISSING_DATA)1 DELTA_PARQUET_SCHEMA_MISMATCH (com.facebook.presto.delta.DeltaErrorCode.DELTA_PARQUET_SCHEMA_MISMATCH)1 DeltaSessionProperties.getParquetMaxReadBlockSize (com.facebook.presto.delta.DeltaSessionProperties.getParquetMaxReadBlockSize)1 DeltaSessionProperties.isParquetBatchReaderVerificationEnabled (com.facebook.presto.delta.DeltaSessionProperties.isParquetBatchReaderVerificationEnabled)1 DeltaSessionProperties.isParquetBatchReadsEnabled (com.facebook.presto.delta.DeltaSessionProperties.isParquetBatchReadsEnabled)1