Examples with PartitionReader org.apache.flink.connector.file.table.PartitionReader used on opensource projects

Example 1 with PartitionReader

use of org.apache.flink.connector.file.table.PartitionReader in project flink by apache.

the class HiveLookupTableSource method getLookupFunction.

private TableFunction<RowData> getLookupFunction(int[] keys) {
    final String defaultPartitionName = JobConfUtils.getDefaultPartitionName(jobConf);
    PartitionFetcher.Context<HiveTablePartition> fetcherContext = new HiveTablePartitionFetcherContext(tablePath, hiveShim, new JobConfWrapper(jobConf), catalogTable.getPartitionKeys(), getProducedTableSchema().getFieldDataTypes(), getProducedTableSchema().getFieldNames(), configuration, defaultPartitionName);
    final PartitionFetcher<HiveTablePartition> partitionFetcher;
    // avoid lambda capture
    final ObjectPath tableFullPath = tablePath;
    if (catalogTable.getPartitionKeys().isEmpty()) {
        // non-partitioned table, the fetcher fetches the partition which represents the given
        // table.
        partitionFetcher = context -> {
            List<HiveTablePartition> partValueList = new ArrayList<>();
            partValueList.add(context.getPartition(new ArrayList<>()).orElseThrow(() -> new IllegalArgumentException(String.format("Fetch partition fail for hive table %s.", tableFullPath))));
            return partValueList;
        };
    } else if (isStreamingSource()) {
        // streaming-read partitioned table, the fetcher fetches the latest partition of the
        // given table.
        partitionFetcher = context -> {
            List<HiveTablePartition> partValueList = new ArrayList<>();
            List<PartitionFetcher.Context.ComparablePartitionValue> comparablePartitionValues = context.getComparablePartitionValueList();
            // fetch latest partitions for partitioned table
            if (comparablePartitionValues.size() > 0) {
                // sort in desc order
                comparablePartitionValues.sort((o1, o2) -> o2.getComparator().compareTo(o1.getComparator()));
                PartitionFetcher.Context.ComparablePartitionValue maxPartition = comparablePartitionValues.get(0);
                partValueList.add(context.getPartition((List<String>) maxPartition.getPartitionValue()).orElseThrow(() -> new IllegalArgumentException(String.format("Fetch partition fail for hive table %s.", tableFullPath))));
            } else {
                throw new IllegalArgumentException(String.format("At least one partition is required when set '%s' to 'latest' in temporal join," + " but actual partition number is '%s' for hive table %s", STREAMING_SOURCE_PARTITION_INCLUDE.key(), comparablePartitionValues.size(), tableFullPath));
            }
            return partValueList;
        };
    } else {
        // bounded-read partitioned table, the fetcher fetches all partitions of the given
        // filesystem table.
        partitionFetcher = context -> {
            List<HiveTablePartition> partValueList = new ArrayList<>();
            List<PartitionFetcher.Context.ComparablePartitionValue> comparablePartitionValues = context.getComparablePartitionValueList();
            for (PartitionFetcher.Context.ComparablePartitionValue comparablePartitionValue : comparablePartitionValues) {
                partValueList.add(context.getPartition((List<String>) comparablePartitionValue.getPartitionValue()).orElseThrow(() -> new IllegalArgumentException(String.format("Fetch partition fail for hive table %s.", tableFullPath))));
            }
            return partValueList;
        };
    }
    PartitionReader<HiveTablePartition, RowData> partitionReader = new HiveInputFormatPartitionReader(flinkConf, jobConf, hiveVersion, tablePath, getProducedTableSchema().getFieldDataTypes(), getProducedTableSchema().getFieldNames(), catalogTable.getPartitionKeys(), projectedFields, flinkConf.get(HiveOptions.TABLE_EXEC_HIVE_FALLBACK_MAPRED_READER));
    return new FileSystemLookupFunction<>(partitionFetcher, fetcherContext, partitionReader, (RowType) getProducedTableSchema().toRowDataType().getLogicalType(), keys, hiveTableReloadInterval);
}

Example 2 with PartitionReader

use of org.apache.flink.connector.file.table.PartitionReader in project flink by apache.

the class HiveLookupJoinITCase method testPartitionFetcherAndReader.

@Test
public void testPartitionFetcherAndReader() throws Exception {
    // constructs test data using dynamic partition
    TableEnvironment batchEnv = HiveTestUtils.createTableEnvInBatchMode(SqlDialect.HIVE);
    batchEnv.registerCatalog(hiveCatalog.getName(), hiveCatalog);
    batchEnv.useCatalog(hiveCatalog.getName());
    batchEnv.executeSql("insert overwrite partition_table values " + "(1,'a',08,2019,'08','01')," + "(1,'a',10,2020,'08','31')," + "(2,'a',21,2020,'08','31')," + "(2,'b',22,2020,'08','31')," + "(3,'c',33,2020,'09','31')").await();
    FileSystemLookupFunction<HiveTablePartition> lookupFunction = getLookupFunction("partition_table");
    lookupFunction.open(null);
    PartitionFetcher<HiveTablePartition> fetcher = lookupFunction.getPartitionFetcher();
    PartitionFetcher.Context<HiveTablePartition> context = lookupFunction.getFetcherContext();
    List<HiveTablePartition> partitions = fetcher.fetch(context);
    // fetch latest partition by partition-name
    assertEquals(1, partitions.size());
    PartitionReader<HiveTablePartition, RowData> reader = lookupFunction.getPartitionReader();
    reader.open(partitions);
    List<RowData> res = new ArrayList<>();
    ObjectIdentifier tableIdentifier = ObjectIdentifier.of(hiveCatalog.getName(), "default", "partition_table");
    CatalogTable catalogTable = (CatalogTable) hiveCatalog.getTable(tableIdentifier.toObjectPath());
    GenericRowData reuse = new GenericRowData(catalogTable.getSchema().getFieldCount());
    TypeSerializer<RowData> serializer = InternalSerializers.create(catalogTable.getSchema().toRowDataType().getLogicalType());
    RowData row;
    while ((row = reader.read(reuse)) != null) {
        res.add(serializer.copy(row));
    }
    res.sort(Comparator.comparingInt(o -> o.getInt(0)));
    assertEquals("[+I(3,c,33,2020,09,31)]", res.toString());
}