Examples with RcFileCorruptionException com.facebook.presto.rcfile.RcFileCorruptionException used on opensource projects

Example 1 with RcFileCorruptionException

use of com.facebook.presto.rcfile.RcFileCorruptionException 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 2 with RcFileCorruptionException

use of com.facebook.presto.rcfile.RcFileCorruptionException in project presto by prestodb.

the class RcFilePageSource method getNextPage.

@Override
public Page getNextPage() {
    try {
        // advance in the current batch
        pageId++;
        // if the batch has been consumed, read the next batch
        int currentPageSize = rcFileReader.advance();
        if (currentPageSize < 0) {
            close();
            return null;
        }
        completedPositions += currentPageSize;
        Block[] blocks = new Block[hiveColumnIndexes.length];
        for (int fieldId = 0; fieldId < blocks.length; fieldId++) {
            if (constantBlocks[fieldId] != null) {
                blocks[fieldId] = new RunLengthEncodedBlock(constantBlocks[fieldId], currentPageSize);
            } else {
                blocks[fieldId] = createBlock(currentPageSize, fieldId);
            }
        }
        return new Page(currentPageSize, blocks);
    } catch (PrestoException e) {
        closeWithSuppression(e);
        throw e;
    } catch (RcFileCorruptionException e) {
        closeWithSuppression(e);
        throw new PrestoException(HIVE_BAD_DATA, format("Corrupted RC file: %s", rcFileReader.getId()), e);
    } catch (IOException | RuntimeException e) {
        closeWithSuppression(e);
        throw new PrestoException(HIVE_CURSOR_ERROR, format("Failed to read RC file: %s", rcFileReader.getId()), e);
    }
}