Examples with SparkTable org.apache.iceberg.spark.source.SparkTable used on opensource projects

Example 11 with SparkTable

use of org.apache.iceberg.spark.source.SparkTable in project iceberg by apache.

the class TestRemoveOrphanFilesAction3 method testSparkCatalogNamedHiveTable.

@Test
public void testSparkCatalogNamedHiveTable() throws Exception {
    spark.conf().set("spark.sql.catalog.hive", "org.apache.iceberg.spark.SparkCatalog");
    spark.conf().set("spark.sql.catalog.hive.type", "hadoop");
    spark.conf().set("spark.sql.catalog.hive.warehouse", tableLocation);
    SparkCatalog cat = (SparkCatalog) spark.sessionState().catalogManager().catalog("hive");
    String[] database = { "default" };
    Identifier id = Identifier.of(database, "table");
    Map<String, String> options = Maps.newHashMap();
    Transform[] transforms = {};
    cat.createTable(id, SparkSchemaUtil.convert(SCHEMA), transforms, options);
    SparkTable table = cat.loadTable(id);
    spark.sql("INSERT INTO hive.default.table VALUES (1,1,1)");
    String location = table.table().location().replaceFirst("file:", "");
    new File(location + "/data/trashfile").createNewFile();
    DeleteOrphanFiles.Result results = SparkActions.get().deleteOrphanFiles(table.table()).olderThan(System.currentTimeMillis() + 1000).execute();
    Assert.assertTrue("trash file should be removed", StreamSupport.stream(results.orphanFileLocations().spliterator(), false).anyMatch(file -> file.contains("file:" + location + "/data/trashfile")));
}

Example 12 with SparkTable

use of org.apache.iceberg.spark.source.SparkTable in project iceberg by apache.

the class TestRemoveOrphanFilesAction3 method testSparkSessionCatalogHiveTable.

@Test
public void testSparkSessionCatalogHiveTable() throws Exception {
    spark.conf().set("spark.sql.catalog.spark_catalog", "org.apache.iceberg.spark.SparkSessionCatalog");
    spark.conf().set("spark.sql.catalog.spark_catalog.type", "hive");
    SparkSessionCatalog cat = (SparkSessionCatalog) spark.sessionState().catalogManager().v2SessionCatalog();
    String[] database = { "default" };
    Identifier id = Identifier.of(database, "sessioncattest");
    Map<String, String> options = Maps.newHashMap();
    Transform[] transforms = {};
    cat.dropTable(id);
    cat.createTable(id, SparkSchemaUtil.convert(SCHEMA), transforms, options);
    SparkTable table = (SparkTable) cat.loadTable(id);
    spark.sql("INSERT INTO default.sessioncattest VALUES (1,1,1)");
    String location = table.table().location().replaceFirst("file:", "");
    new File(location + "/data/trashfile").createNewFile();
    DeleteOrphanFiles.Result results = SparkActions.get().deleteOrphanFiles(table.table()).olderThan(System.currentTimeMillis() + 1000).execute();
    Assert.assertTrue("trash file should be removed", StreamSupport.stream(results.orphanFileLocations().spliterator(), false).anyMatch(file -> file.contains("file:" + location + "/data/trashfile")));
}

Example 13 with SparkTable

use of org.apache.iceberg.spark.source.SparkTable in project OpenLineage by OpenLineage.

the class IcebergHandler method getDatasetVersion.

@SneakyThrows
public Optional<String> getDatasetVersion(TableCatalog tableCatalog, Identifier identifier, Map<String, String> properties) {
    SparkCatalog sparkCatalog = (SparkCatalog) tableCatalog;
    SparkTable table;
    try {
        table = sparkCatalog.loadTable(identifier);
    } catch (NoSuchTableException ex) {
        return Optional.empty();
    }
    if (table.table() != null && table.table().currentSnapshot() != null) {
        return Optional.of(Long.toString(table.table().currentSnapshot().snapshotId()));
    }
    return Optional.empty();
}

Example 14 with SparkTable

use of org.apache.iceberg.spark.source.SparkTable in project iceberg by apache.

the class TestAlterTablePartitionFields method sparkTable.

private SparkTable sparkTable() throws Exception {
    validationCatalog.loadTable(tableIdent).refresh();
    CatalogManager catalogManager = spark.sessionState().catalogManager();
    TableCatalog catalog = (TableCatalog) catalogManager.catalog(catalogName);
    Identifier identifier = Identifier.of(tableIdent.namespace().levels(), tableIdent.name());
    return (SparkTable) catalog.loadTable(identifier);
}

Example 15 with SparkTable

use of org.apache.iceberg.spark.source.SparkTable in project iceberg by apache.

the class Spark3Util method loadIcebergTable.

/**
 * Returns an Iceberg Table by its name from a Spark V2 Catalog. If cache is enabled in {@link SparkCatalog},
 * the {@link TableOperations} of the table may be stale, please refresh the table to get the latest one.
 *
 * @param spark SparkSession used for looking up catalog references and tables
 * @param name  The multipart identifier of the Iceberg table
 * @return an Iceberg table
 */
public static org.apache.iceberg.Table loadIcebergTable(SparkSession spark, String name) throws ParseException, NoSuchTableException {
    CatalogAndIdentifier catalogAndIdentifier = catalogAndIdentifier(spark, name);
    TableCatalog catalog = asTableCatalog(catalogAndIdentifier.catalog);
    Table sparkTable = catalog.loadTable(catalogAndIdentifier.identifier);
    return toIcebergTable(sparkTable);
}