Realtime Compute for Apache Flink:Hologres

VVR 11+

CREATE TEMPORARY TABLE test_message_src_binlog_table(
  id INTEGER,
  title VARCHAR,
  body VARCHAR
) WITH (
  'connector'='hologres',
  'dbname'='<yourDbname>',
  'tablename'='<yourTablename>',
  'username'='${secret_values.ak_id}',            -- We recommend using variables for AK/SK to prevent key leakage.
  'password'='${secret_values.ak_secret}',        
  'endpoint'='<yourEndpoint>',
  'source.binlog.change-log-mode'='ALL',  -- Read all changeLog types, including INSERT, DELETE, UPDATE_BEFORE, and UPDATE_AFTER.
  'retry-count'='10',                     -- Number of retries after a binlog read error.
  'retry-sleep-step-ms'='5000',           -- Incremental backoff time between retries. The first retry waits 5s, the second 10s, and so on.
  'source.binlog.batch-size'='512'        -- Number of rows to read from binlog in a batch.
);

VVR 8+

CREATE TEMPORARY TABLE test_message_src_binlog_table(
  id INTEGER,
  title VARCHAR,
  body VARCHAR
) WITH (
  'connector'='hologres',
  'dbname'='<yourDbname>',
  'tablename'='<yourTablename>',
  'username' = '${secret_values.ak_id}',       -- We recommend using variables for AK/SK to prevent key leakage.   
  'password' = '${secret_values.ak_secret}',
  'endpoint'='<yourEndpoint>',
  'binlog' = 'true',
  'cdcMode' = 'true',
  'sdkMode'='jdbc',
  'binlogMaxRetryTimes' = '10',     -- Number of retries after a binlog read error.
  'binlogRetryIntervalMs' = '500',  -- Retry interval after a binlog read error, in milliseconds.
  'binlogBatchReadSize' = '100'     -- Number of rows to read from binlog in a batch.
);

VVR 11+

CREATE TEMPORARY TABLE test_message_src_binlog_table(
  id INTEGER,
  title VARCHAR,
  body VARCHAR
) WITH (
  'connector'='hologres',
  'dbname'='<yourDbname>',
  'tablename'='<yourTablename>',
  'username' = '${secret_values.ak_id}',       -- We recommend using variables for AK/SK to prevent key leakage.   
  'password' = '${secret_values.ak_secret}',
  'endpoint'='<yourEndpoint>',
  'source.binlog.change-log-mode'='ALL_AS_APPEND_ONLY',  -- Treat all changelog types as INSERT.
  'retry-count'='10',                     -- Number of retries after a binlog read error.
  'retry-sleep-step-ms'='5000',           -- Incremental backoff time between retries. The first retry waits 5s, the second 10s, and so on.
  'source.binlog.batch-size'='512'        -- Number of rows to read from binlog in a batch.
);

VVR 8+

CREATE TEMPORARY TABLE test_message_src_binlog_table(
  hg_binlog_lsn BIGINT,
  hg_binlog_event_type BIGINT,
  hg_binlog_timestamp_us BIGINT,
  id INTEGER,
  title VARCHAR,
  body VARCHAR
) WITH (
  'connector'='hologres',
  'dbname'='<yourDbname>',
  'tablename'='<yourTablename>',
  'username' = '${secret_values.ak_id}',       -- We recommend using variables for AK/SK to prevent key leakage.   
  'password' = '${secret_values.ak_secret}',
  'endpoint'='<yourEndpoint>',
  'binlog' = 'true',
  'binlogMaxRetryTimes' = '10',     -- Number of retries after a binlog read error.
  'binlogRetryIntervalMs' = '500',  -- Retry interval after a binlog read error, in milliseconds.
  'binlogBatchReadSize' = '100'     -- Number of rows to read from binlog in a batch.
);

VVR 11+

Assume that Hologres contains the following DDL-defined partitioned table, with binary logging and dynamic partitioning enabled.

CREATE TABLE "test_message_src1" (
    id int,
    title text,
    body text,
    dt text,
    PRIMARY KEY (id, dt)
)
PARTITION BY LIST (dt) WITH (
    binlog_level = 'replica', 
    auto_partitioning_enable =  'true',   -- Enable dynamic partitioning.
    auto_partitioning_time_unit = 'DAY',  -- Partitions are created daily. Example partition names: test_message_src1_20250512, test_message_src1_20250513.
    auto_partitioning_num_precreate = '2' -- Pre-create two partitions.
);
-- For existing partitioned tables, you can also enable dynamic partitioning using ALTER TABLE.

In Flink, use the following SQL statement to consume data from the partitioned table test_message_src1 in DYNAMIC mode.

CREATE TEMPORARY TABLE hologres_source
(
  id INTEGER,
  title VARCHAR,
  body VARCHAR,
  dt VARCHAR  -- The partition column of the Hologres partitioned table.
)
with (
  'connector' = 'hologres',
  'dbname' = '<yourDatabase>',
  'tablename' = 'test_message_src1',  -- The Hologres table with dynamic partitioning enabled.
  'username' = '<yourUserName>',
  'password' = '<yourPassword>',
  'endpoint' = '<yourEndpoint>',
  'source.binlog.partition-binlog-mode' = 'DYNAMIC', -- Dynamically monitor the latest partitions.
  'source.binlog.startup-mode' = 'initial'           -- First read all existing data, then start reading binlog incrementally.
);

VVR 8.0.11

Assume Hologres contains the following DDL-defined partitioned table, with binary logging and dynamic partitioning enabled.

CREATE TABLE "test_message_src1" (
    id int,
    title text,
    body text,
    dt text,
    PRIMARY KEY (id, dt)
)
PARTITION BY LIST (dt) WITH (
    binlog_level = 'replica', 
    auto_partitioning_enable =  'true',   -- Enable dynamic partitioning.
    auto_partitioning_time_unit = 'DAY',  -- Partitions are created daily. Example partition names: test_message_src1_20241027, test_message_src1_20241028.
    auto_partitioning_num_precreate = '2' -- Pre-create two partitions.
);

-- For existing partitioned tables, you can also enable dynamic partitioning using ALTER TABLE.

In Flink, use the following SQL statement to consume data from the partitioned table test_message_src1 in DYNAMIC mode.

CREATE TEMPORARY TABLE hologres_source
(
  id INTEGER,
  title VARCHAR,
  body VARCHAR,
  dt VARCHAR  -- The partition column of the Hologres partitioned table.
)
with (
  'connector' = 'hologres',
  'dbname' = '<yourDatabase>',
  'tablename' = 'test_message_src1',  -- The Hologres table with dynamic partitioning enabled.
  'username' = '<yourUserName>',
  'password' = '<yourPassword>',
  'endpoint' = '<yourEndpoint>',
  'binlog' = 'true',
  'partition-binlog.mode' = 'DYNAMIC',  -- Dynamically monitor the latest partitions.
  'binlogstartUpMode' = 'initial',      -- First read all existing data, then start reading binlog incrementally.
  'sdkMode' = 'jdbc_fixed'              -- Use this mode to avoid connection limit issues.
);

VVR 11+

Assume that Hologres contains the following partitioned table defined by Data Definition Language (DDL), and binary logging is enabled.

CREATE TABLE test_message_src2 (
    id int,
    title text,
    body text,
    color text,
    PRIMARY KEY (id, color)
)
PARTITION BY LIST (color) WITH (
    binlog_level = 'replica'
);
create table test_message_src2_red partition of test_message_src2 for values in ('red');
create table test_message_src2_blue partition of test_message_src2 for values in ('blue');
create table test_message_src2_green partition of test_message_src2 for values in ('green');
create table test_message_src2_black partition of test_message_src2 for values in ('black');

In Flink, use the following SQL statement to consume the partitioned table test_message_src2 in STATIC mode.

CREATE TEMPORARY TABLE hologres_source
(
  id INTEGER,
  title VARCHAR,
  body VARCHAR,
  color VARCHAR  -- The partition column of the Hologres partitioned table.
)
with (
  'connector' = 'hologres',
  'dbname' = '<yourDatabase>',
  'tablename' = 'test_message_src2',  -- The partitioned table.
  'username' = '<yourUserName>',
  'password' = '<yourPassword>',
  'endpoint' = '<yourEndpoint>',
  'source.binlog.partition-binlog-mode' = 'STATIC', -- Read a fixed set of partitions.
  'source.binlog.partition-values-to-read' = 'red,blue,green',  -- Read only the three specified partitions; the 'black' partition is not read. New partitions are also not read. If not set, all partitions of the parent table are read.
  'source.binlog.startup-mode' = 'initial'  -- First read all existing data, then start reading binlog incrementally.
);

VVR 8.0.11

Assume that the following DDL partitioned table exists in Hologres and has binary logging enabled.

CREATE TABLE test_message_src2 (
    id int,
    title text,
    body text,
    color text,
    PRIMARY KEY (id, color)
)
PARTITION BY LIST (color) WITH (
    binlog_level = 'replica'
);
create table test_message_src2_red partition of test_message_src2 for values in ('red');
create table test_message_src2_blue partition of test_message_src2 for values in ('blue');
create table test_message_src2_green partition of test_message_src2 for values in ('green');
create table test_message_src2_black partition of test_message_src2 for values in ('black');

In Flink, use the following SQL statement to read data from the partitioned table test_message_src2 in STATIC mode.

CREATE TEMPORARY TABLE hologres_source
(
  id INTEGER,
  title VARCHAR,
  body VARCHAR,
  color VARCHAR  -- The partition column of the Hologres partitioned table.
)
with (
  'connector' = 'hologres',
  'dbname' = '<yourDatabase>',
  'tablename' = 'test_message_src2',  -- The partitioned table.
  'username' = '<yourUserName>',
  'password' = '<yourPassword>',
  'endpoint' = '<yourEndpoint>',
  'binlog' = 'true',
  'partition-binlog.mode' = 'STATIC', -- Read a fixed set of partitions.
  'partition-values-to-read' = 'red,blue,green',  -- Read only the three specified partitions; the 'black' partition is not read. New partitions are also not read. If not set, all partitions of the parent table are read.
  'binlogstartUpMode' = 'initial',  -- First read all existing data, then start reading binlog incrementally.
  'sdkMode' = 'jdbc_fixed' -- Use this mode to avoid connection limit issues.
);

VVR 11.3+

public class Sample {                                                                                                                                                                          
        public static void main(String[] args) throws Exception {
            final StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
            // Initialize the schema of the table to be read. It must match the columns of the Hologres table schema. You can define a subset of columns.
            TableSchema schema = TableSchema.builder()
                    .field("a", DataTypes.INT())
                    .field("b", DataTypes.STRING())
                    .field("c", DataTypes.TIMESTAMP())
                    .build();

            // Name of the table to read.
            String sourceTableName = "sourceTableName";

            // Hologres connector options.
            Configuration config = new Configuration();
            config.setString(HologresConfigs.ENDPOINT, "yourEndpoint");
            config.setString(HologresConfigs.USERNAME, "yourUserName");
            config.setString(HologresConfigs.PASSWORD, "yourPassword");
            config.setString(HologresConfigs.DATABASE, "yourDatabaseName");
            config.setString(HologresConfigs.TABLE, sourceTableName);
            config.set(HologresConfigs.BINLOG, true);
            config.set(HologresConfigs.BINLOG_CHANGE_LOG_MODE, BinlogChangeLogMode.ALL);
            // Build the HologresBinlogSource.
            HologresBinlogSource source = new HologresBinlogSource(
                    new HologresConnectionParam(config),
                    schema,
                    config,
                    StartupMode.INITIAL,
                    sourceTableName,
                    "",
                    Collections.emptyList(),
                    -1,
                    Collections.emptySet(),
                    Collections.emptyList()
            );
            env.fromSource(source, WatermarkStrategy.noWatermarks(), "Test source").print();
            env.execute();
        }
  }

VVR 8.0.11+

public class Sample {
    public static void main(String[] args) throws Exception {
        final StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        // Initialize the schema of the table to be read. It must match the columns of the Hologres table schema. You can define a subset of columns.
        TableSchema schema = TableSchema.builder()
                .field("a", DataTypes.INT())
                .field("b", DataTypes.STRING())
                .field("c", DataTypes.TIMESTAMP())
                .build();
        // Hologres connector options.
        Configuration config = new Configuration();
        config.setString(HologresConfigs.ENDPOINT, "yourEndpoint");
        config.setString(HologresConfigs.USERNAME, "yourUserName");
        config.setString(HologresConfigs.PASSWORD, "yourPassword");
        config.setString(HologresConfigs.DATABASE, "yourDatabaseName");
        config.setString(HologresConfigs.TABLE, "yourTableName");
        config.setString(HologresConfigs.SDK_MODE, "jdbc");
        config.setBoolean(HologresBinlogConfigs.OPTIONAL_BINLOG, true);
        config.setBoolean(HologresBinlogConfigs.BINLOG_CDC_MODE, true);
        // Build JDBCOptions.
        JDBCOptions jdbcOptions = JDBCUtils.getJDBCOptions(config);
        // Build the HologresBinlogSource.
        long startTimeMs = 0;
        HologresBinlogSource source = new HologresBinlogSource(
                new HologresConnectionParam(config),
                schema,
                config,
                jdbcOptions,
                startTimeMs,
                StartupMode.INITIAL,
                "",
                "",
                -1,
                Collections.emptySet(),
                new ArrayList<>()
        );
        env.fromSource(source, WatermarkStrategy.noWatermarks(), "Test source").print();
        env.execute();
    }
}

VVR 8.0.7+

public class Sample {
    public static void main(String[] args) throws Exception {
        final StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        // Initialize the schema of the table to be read. It must match the columns of the Hologres table schema. You can define a subset of columns.
        TableSchema schema = TableSchema.builder()
                .field("a", DataTypes.INT())
                .field("b", DataTypes.STRING())
                .field("c", DataTypes.TIMESTAMP())
                .build();
        // Hologres connector options.
        Configuration config = new Configuration();
        config.setString(HologresConfigs.ENDPOINT, "yourEndpoint");
        config.setString(HologresConfigs.USERNAME, "yourUserName");
        config.setString(HologresConfigs.PASSWORD, "yourPassword");
        config.setString(HologresConfigs.DATABASE, "yourDatabaseName");
        config.setString(HologresConfigs.TABLE, "yourTableName");
        config.setString(HologresConfigs.SDK_MODE, "jdbc");
        config.setBoolean(HologresBinlogConfigs.OPTIONAL_BINLOG, true);
        config.setBoolean(HologresBinlogConfigs.BINLOG_CDC_MODE, true);
        // Build JDBCOptions.
        JDBCOptions jdbcOptions = JDBCUtils.getJDBCOptions(config);
        // Build the HologresBinlogSource.
        long startTimeMs = 0;
        HologresBinlogSource source = new HologresBinlogSource(
                new HologresConnectionParam(config),
                schema,
                config,
                jdbcOptions,
                startTimeMs,
                StartupMode.INITIAL,
                "",
                "",
                -1,
                Collections.emptySet()
        );
        env.fromSource(source, WatermarkStrategy.noWatermarks(), "Test source").print();
        env.execute();
    }
}

VVR 6.0.7+

public class Sample {
    public static void main(String[] args) throws Exception {
        final StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        // Initialize the schema of the table to be read. It must match the columns of the Hologres table schema. You can define a subset of columns.
        TableSchema schema = TableSchema.builder()
                .field("a", DataTypes.INT())
                .build();
         // Hologres connector options.
        Configuration config = new Configuration();
        config.setString(HologresConfigs.ENDPOINT, "yourEndpoint");
        config.setString(HologresConfigs.USERNAME, "yourUserName");
        config.setString(HologresConfigs.PASSWORD, "yourPassword");
        config.setString(HologresConfigs.DATABASE, "yourDatabaseName");
        config.setString(HologresConfigs.TABLE, "yourTableName");
        config.setString(HologresConfigs.SDK_MODE, "jdbc");
        config.setBoolean(HologresBinlogConfigs.OPTIONAL_BINLOG, true);
        config.setBoolean(HologresBinlogConfigs.BINLOG_CDC_MODE, true);
        // Build JDBCOptions.
        JDBCOptions jdbcOptions = JDBCUtils.getJDBCOptions(config);
        // Set or create the default slot name.
        config.setString(HologresBinlogConfigs.JDBC_BINLOG_SLOT_NAME, HoloBinlogUtil.getOrCreateDefaultSlotForJDBCBinlog(jdbcOptions));

        boolean cdcMode = config.get(HologresBinlogConfigs.BINLOG_CDC_MODE) && config.get(HologresBinlogConfigs.OPTIONAL_BINLOG);
        // Build the JDBCBinlogRecordConverter.
        JDBCBinlogRecordConverter recordConverter = new JDBCBinlogRecordConverter(
                jdbcOptions.getTable(),
                schema,
                new HologresConnectionParam(config),
                cdcMode,
                Collections.emptySet());
        
        // Build the HologresBinlogSource.
        long startTimeMs = 0;
        HologresJDBCBinlogSource source = new HologresJDBCBinlogSource(
                new HologresConnectionParam(config),
                schema,
                config,
                jdbcOptions,
                startTimeMs,
                StartupMode.TIMESTAMP,
                recordConverter,
                "",
                -1);
        env.fromSource(source, WatermarkStrategy.noWatermarks(), "Test source").print();
        env.execute();
    }
}