Search in sources :

Example 6 with Column

use of com.datastax.oss.dsbulk.tests.simulacron.SimulacronUtils.Column in project dsbulk by datastax.

the class CSVEndToEndSimulacronIT method massive_load_errors.

/**
 * Test for DAT-593. Emulates 100 resources with 1000 records each, among which 100 bad records,
 * for a total of 10,000 failed records. Verifies that LogManager is capable of handling a high
 * number of bad records, without disrupting the main load workflow.
 */
@Test
void massive_load_errors() throws Exception {
    SimulacronUtils.primeTables(simulacron, new Keyspace("ks1", new Table("table1", new Column("pk", TEXT), new Column("cc", TEXT), new Column("v", TEXT))));
    MockConnector.setDelegate(new CSVConnector() {

        @Override
        public void configure(@NonNull Config settings, boolean read, boolean retainRecordSources) {
        }

        @Override
        public void init() {
        }

        @Override
        public int readConcurrency() {
            // to force runner to use maximum parallelism
            return Integer.MAX_VALUE;
        }

        @NonNull
        @Override
        public Publisher<Publisher<Record>> read() {
            List<Publisher<Record>> resources = new ArrayList<>();
            for (int i = 0; i < 100; i++) {
                AtomicInteger counter = new AtomicInteger();
                resources.add(Flux.generate((sink) -> {
                    int next = counter.getAndIncrement();
                    if (next == 1_000) {
                        sink.complete();
                    } else if (next % 10 == 0) {
                        sink.next(RecordUtils.error(new IllegalArgumentException("Record could not be read: " + next)));
                    } else {
                        sink.next(RecordUtils.indexedCSV("pk", String.valueOf(next), "cc", String.valueOf(next), "v", String.valueOf(next)));
                    }
                }));
            }
            return Flux.fromIterable(resources);
        }
    });
    String[] args = { "load", "-c", "mock", "--log.maxErrors", "10000", "--schema.keyspace", "ks1", "--schema.table", "table1" };
    ExitStatus status = new DataStaxBulkLoader(addCommonSettings(args)).run();
    assertStatus(status, STATUS_COMPLETED_WITH_ERRORS);
    assertThat(logs.getAllMessagesAsString()).contains("completed with 10000 errors").contains("Records: total: 100,000, successful: 90,000, failed: 10,000");
    validateExceptionsLog(10_000, "Record could not be read:", "connector-errors.log");
}
Also used : EndToEndUtils.primeIpByCountryTable(com.datastax.oss.dsbulk.runner.tests.EndToEndUtils.primeIpByCountryTable) Table(com.datastax.oss.dsbulk.tests.simulacron.SimulacronUtils.Table) Config(com.typesafe.config.Config) DataStaxBulkLoader(com.datastax.oss.dsbulk.runner.DataStaxBulkLoader) Publisher(org.reactivestreams.Publisher) ExitStatus(com.datastax.oss.dsbulk.runner.ExitStatus) Column(com.datastax.oss.dsbulk.tests.simulacron.SimulacronUtils.Column) AtomicInteger(java.util.concurrent.atomic.AtomicInteger) Keyspace(com.datastax.oss.dsbulk.tests.simulacron.SimulacronUtils.Keyspace) NonNull(edu.umd.cs.findbugs.annotations.NonNull) Record(com.datastax.oss.dsbulk.connectors.api.Record) Collections.emptyList(java.util.Collections.emptyList) List(java.util.List) ArrayList(java.util.ArrayList) CSVConnector(com.datastax.oss.dsbulk.connectors.csv.CSVConnector) Test(org.junit.jupiter.api.Test) ParameterizedTest(org.junit.jupiter.params.ParameterizedTest)

Example 7 with Column

use of com.datastax.oss.dsbulk.tests.simulacron.SimulacronUtils.Column in project dsbulk by datastax.

the class JsonEndToEndSimulacronIT method full_load_custom_features.

@Test
void full_load_custom_features() {
    SimulacronUtils.primeTables(simulacron, new SimulacronUtils.Keyspace("ks1", new Table("table1", new Column("key", INT), new Column("value", FLOAT))));
    String[] args = { "load", "-c", "json", "--connector.json.url", StringUtils.quoteJson(JsonUtils.JSON_RECORDS_WITH_COMMENTS), "--schema.query", "INSERT INTO ks1.table1 (key, value) VALUES (:key, :value)", "--connector.json.parserFeatures", "{ALLOW_COMMENTS = true}", "--connector.json.deserializationFeatures", "{USE_BIG_INTEGER_FOR_INTS = false, USE_BIG_DECIMAL_FOR_FLOATS = false}" };
    ExitStatus status = new DataStaxBulkLoader(addCommonSettings(args)).run();
    assertStatus(status, STATUS_OK);
    validateQueryCount(simulacron, 1, "INSERT INTO ks1.table1 (key, value) VALUES (:key, :value)", LOCAL_ONE);
}
Also used : ExitStatus(com.datastax.oss.dsbulk.runner.ExitStatus) EndToEndUtils.primeIpByCountryTable(com.datastax.oss.dsbulk.runner.tests.EndToEndUtils.primeIpByCountryTable) Table(com.datastax.oss.dsbulk.tests.simulacron.SimulacronUtils.Table) Column(com.datastax.oss.dsbulk.tests.simulacron.SimulacronUtils.Column) DataStaxBulkLoader(com.datastax.oss.dsbulk.runner.DataStaxBulkLoader) SimulacronUtils(com.datastax.oss.dsbulk.tests.simulacron.SimulacronUtils) Test(org.junit.jupiter.api.Test) ParameterizedTest(org.junit.jupiter.params.ParameterizedTest)

Example 8 with Column

use of com.datastax.oss.dsbulk.tests.simulacron.SimulacronUtils.Column in project dsbulk by datastax.

the class JsonEndToEndSimulacronIT method error_load_extra_field.

@Test
void error_load_extra_field() throws Exception {
    SimulacronUtils.primeTables(simulacron, new SimulacronUtils.Keyspace("ks1", new Table("table1", new Column("a", INT), new Column("b", TEXT))));
    String[] args = { "load", "-c", "json", "--log.maxErrors", "1", "--log.verbosity", "2", "--connector.json.url", StringUtils.quoteJson(getClass().getResource("/missing-extra.json")), "--schema.query", "INSERT INTO ks1.table1 (a, b) VALUES (:a, :b)", "--schema.mapping", "A = a, B = b", "--schema.allowExtraFields", "false" };
    ExitStatus status = new DataStaxBulkLoader(addCommonSettings(args)).run();
    assertStatus(status, STATUS_ABORTED_TOO_MANY_ERRORS);
    assertThat(logs.getAllMessagesAsString()).contains("aborted: Too many errors, the maximum allowed is 1").contains("Records: total: 3, successful: 1, failed: 2");
    validateNumberOfBadRecords(2);
    validateExceptionsLog(1, "Extraneous field C was found in record", "mapping-errors.log");
    validateExceptionsLog(1, "Extraneous field D was found in record", "mapping-errors.log");
}
Also used : ExitStatus(com.datastax.oss.dsbulk.runner.ExitStatus) EndToEndUtils.primeIpByCountryTable(com.datastax.oss.dsbulk.runner.tests.EndToEndUtils.primeIpByCountryTable) Table(com.datastax.oss.dsbulk.tests.simulacron.SimulacronUtils.Table) Column(com.datastax.oss.dsbulk.tests.simulacron.SimulacronUtils.Column) DataStaxBulkLoader(com.datastax.oss.dsbulk.runner.DataStaxBulkLoader) SimulacronUtils(com.datastax.oss.dsbulk.tests.simulacron.SimulacronUtils) Test(org.junit.jupiter.api.Test) ParameterizedTest(org.junit.jupiter.params.ParameterizedTest)

Example 9 with Column

use of com.datastax.oss.dsbulk.tests.simulacron.SimulacronUtils.Column in project dsbulk by datastax.

the class JsonEndToEndSimulacronIT method error_load_missing_field.

@Test
void error_load_missing_field() throws Exception {
    SimulacronUtils.primeTables(simulacron, new SimulacronUtils.Keyspace("ks1", new Table("table1", new Column("a", INT), new Column("b", TEXT), new Column("c", BOOLEAN), new Column("d", INT))));
    String[] args = { "load", "-c", "json", "--log.maxErrors", "2", "--log.verbosity", "2", "--connector.json.url", StringUtils.quoteJson(getClass().getResource("/missing-extra.json")), "--schema.query", "INSERT INTO ks1.table1 (a, b, c, d) VALUES (:a, :b, :c, :d)", "--schema.mapping", "A = a, B = b, C = c, D = d", "--schema.allowMissingFields", "false" };
    ExitStatus status = new DataStaxBulkLoader(addCommonSettings(args)).run();
    assertStatus(status, STATUS_ABORTED_TOO_MANY_ERRORS);
    assertThat(logs.getAllMessagesAsString()).contains("aborted: Too many errors, the maximum allowed is 2").contains("Records: total: 3, successful: 0, failed: 3");
    validateNumberOfBadRecords(3);
    validateExceptionsLog(2, "Required field C (mapped to column c) was missing from record", "mapping-errors.log");
    validateExceptionsLog(1, "Required field D (mapped to column d) was missing from record", "mapping-errors.log");
}
Also used : ExitStatus(com.datastax.oss.dsbulk.runner.ExitStatus) EndToEndUtils.primeIpByCountryTable(com.datastax.oss.dsbulk.runner.tests.EndToEndUtils.primeIpByCountryTable) Table(com.datastax.oss.dsbulk.tests.simulacron.SimulacronUtils.Table) Column(com.datastax.oss.dsbulk.tests.simulacron.SimulacronUtils.Column) DataStaxBulkLoader(com.datastax.oss.dsbulk.runner.DataStaxBulkLoader) SimulacronUtils(com.datastax.oss.dsbulk.tests.simulacron.SimulacronUtils) Test(org.junit.jupiter.api.Test) ParameterizedTest(org.junit.jupiter.params.ParameterizedTest)

Aggregations

DataStaxBulkLoader (com.datastax.oss.dsbulk.runner.DataStaxBulkLoader)9 ExitStatus (com.datastax.oss.dsbulk.runner.ExitStatus)9 Column (com.datastax.oss.dsbulk.tests.simulacron.SimulacronUtils.Column)9 Table (com.datastax.oss.dsbulk.tests.simulacron.SimulacronUtils.Table)9 EndToEndUtils.primeIpByCountryTable (com.datastax.oss.dsbulk.runner.tests.EndToEndUtils.primeIpByCountryTable)8 Test (org.junit.jupiter.api.Test)8 ParameterizedTest (org.junit.jupiter.params.ParameterizedTest)8 SimulacronUtils (com.datastax.oss.dsbulk.tests.simulacron.SimulacronUtils)5 Keyspace (com.datastax.oss.dsbulk.tests.simulacron.SimulacronUtils.Keyspace)5 Record (com.datastax.oss.dsbulk.connectors.api.Record)2 NonNull (edu.umd.cs.findbugs.annotations.NonNull)2 ArrayList (java.util.ArrayList)2 LinkedHashMap (java.util.LinkedHashMap)2 AtomicInteger (java.util.concurrent.atomic.AtomicInteger)2 Session (com.datastax.oss.driver.api.core.session.Session)1 TEXT (com.datastax.oss.driver.api.core.type.DataTypes.TEXT)1 GenericType (com.datastax.oss.driver.api.core.type.reflect.GenericType)1 Resources (com.datastax.oss.driver.shaded.guava.common.io.Resources)1 CommonConnectorFeature (com.datastax.oss.dsbulk.connectors.api.CommonConnectorFeature)1 Connector (com.datastax.oss.dsbulk.connectors.api.Connector)1