Connect to External Systems

tableEnvironment
  .connect(...)
  .withFormat(...)
  .withSchema(...)
  .inAppendMode()
  .registerTableSource("MyTable")

table_environment \
    .connect(...) \
    .with_format(...) \
    .with_schema(...) \
    .in_append_mode() \
    .register_table_source("MyTable")

name: MyTable
type: source
update-mode: append
connector: ...
format: ...
schema: ...

tableEnvironment.sqlUpdate("CREATE TABLE MyTable (...) WITH (...)")

tableEnvironment
  // declare the external system to connect to
  .connect(
    new Kafka()
      .version("0.10")
      .topic("test-input")
      .startFromEarliest()
      .property("zookeeper.connect", "localhost:2181")
      .property("bootstrap.servers", "localhost:9092")
  )

  // declare a format for this system
  .withFormat(
    new Avro()
      .avroSchema(
        "{" +
        "  \"namespace\": \"org.myorganization\"," +
        "  \"type\": \"record\"," +
        "  \"name\": \"UserMessage\"," +
        "    \"fields\": [" +
        "      {\"name\": \"timestamp\", \"type\": \"string\"}," +
        "      {\"name\": \"user\", \"type\": \"long\"}," +
        "      {\"name\": \"message\", \"type\": [\"string\", \"null\"]}" +
        "    ]" +
        "}"
      )
  )

  // declare the schema of the table
  .withSchema(
    new Schema()
      .field("rowtime", Types.SQL_TIMESTAMP)
        .rowtime(new Rowtime()
          .timestampsFromField("timestamp")
          .watermarksPeriodicBounded(60000)
        )
      .field("user", Types.LONG)
      .field("message", Types.STRING)
  )

  // specify the update-mode for streaming tables
  .inAppendMode()

  // register as source, sink, or both and under a name
  .registerTableSource("MyUserTable");

table_environment \
    .connect(  # declare the external system to connect to
        Kafka()
        .version("0.10")
        .topic("test-input")
        .start_from_earliest()
        .property("zookeeper.connect", "localhost:2181")
        .property("bootstrap.servers", "localhost:9092")
    ) \
    .with_format(  # declare a format for this system
        Avro()
        .avro_schema(
            "{"
            "  \"namespace\": \"org.myorganization\","
            "  \"type\": \"record\","
            "  \"name\": \"UserMessage\","
            "    \"fields\": ["
            "      {\"name\": \"timestamp\", \"type\": \"string\"},"
            "      {\"name\": \"user\", \"type\": \"long\"},"
            "      {\"name\": \"message\", \"type\": [\"string\", \"null\"]}"
            "    ]"
            "}"
        )
    ) \
    .with_schema(  # declare the schema of the table
        Schema()
        .field("rowtime", DataTypes.TIMESTAMP())
        .rowtime(
            Rowtime()
            .timestamps_from_field("timestamp")
            .watermarks_periodic_bounded(60000)
        )
        .field("user", DataTypes.BIGINT())
        .field("message", DataTypes.STRING())
    ) \
    .in_append_mode() \
    .register_table_source("MyUserTable")  
    # specify the update-mode for streaming tables and
    # register as source, sink, or both and under a name

tables:
  - name: MyUserTable      # name the new table
    type: source           # declare if the table should be "source", "sink", or "both"
    update-mode: append    # specify the update-mode for streaming tables

    # declare the external system to connect to
    connector:
      type: kafka
      version: "0.10"
      topic: test-input
      startup-mode: earliest-offset
      properties:
        - key: zookeeper.connect
          value: localhost:2181
        - key: bootstrap.servers
          value: localhost:9092

    # declare a format for this system
    format:
      type: avro
      avro-schema: >
        {
          "namespace": "org.myorganization",
          "type": "record",
          "name": "UserMessage",
            "fields": [
              {"name": "ts", "type": "string"},
              {"name": "user", "type": "long"},
              {"name": "message", "type": ["string", "null"]}
            ]
        }

    # declare the schema of the table
    schema:
      - name: rowtime
        type: TIMESTAMP
        rowtime:
          timestamps:
            type: from-field
            from: ts
          watermarks:
            type: periodic-bounded
            delay: "60000"
      - name: user
        type: BIGINT
      - name: message
        type: VARCHAR

CREATE TABLE MyUserTable (
  `user` BIGINT,
  message VARCHAR,
  ts VARCHAR
) WITH (
  -- declare the external system to connect to
  'connector.type' = 'kafka',
  'connector.version' = '0.10',
  'connector.topic' = 'topic_name',
  'connector.startup-mode' = 'earliest-offset',
  'connector.properties.0.key' = 'zookeeper.connect',
  'connector.properties.0.value' = 'localhost:2181',
  'connector.properties.1.key' = 'bootstrap.servers',
  'connector.properties.1.value' = 'localhost:9092',
  'update-mode' = 'append',
  -- declare a format for this system
  'format.type' = 'avro',
  'format.avro-schema' = '{
                            "namespace": "org.myorganization",
                            "type": "record",
                            "name": "UserMessage",
                            "fields": [
                                {"name": "ts", "type": "string"},
                                {"name": "user", "type": "long"},
                                {"name": "message", "type": ["string", "null"]}
                            ]
                         }'
)

.withSchema(
  new Schema()
    .field("MyField1", Types.INT)     // required: specify the fields of the table (in this order)
    .field("MyField2", Types.STRING)
    .field("MyField3", Types.BOOLEAN)
)

.with_schema(
    Schema()
    .field("MyField1", DataTypes.INT())  # required: specify the fields of the table (in this order)
    .field("MyField2", DataTypes.STRING())
    .field("MyField3", DataTypes.BOOLEAN())
)

schema:
  - name: MyField1    # required: specify the fields of the table (in this order)
    type: INT
  - name: MyField2
    type: VARCHAR
  - name: MyField3
    type: BOOLEAN

.withSchema(
  new Schema()
    .field("MyField1", Types.SQL_TIMESTAMP)
      .proctime()      // optional: declares this field as a processing-time attribute
    .field("MyField2", Types.SQL_TIMESTAMP)
      .rowtime(...)    // optional: declares this field as a event-time attribute
    .field("MyField3", Types.BOOLEAN)
      .from("mf3")     // optional: original field in the input that is referenced/aliased by this field
)

.with_schema(
    Schema()
    .field("MyField1", DataTypes.TIMESTAMP())
    .proctime()  # optional: declares this field as a processing-time attribute
    .field("MyField2", DataTypes.TIMESTAMP())
    .rowtime(...)  # optional: declares this field as a event-time attribute
    .field("MyField3", DataTypes.BOOLEAN())
    .from_origin_field("mf3")  # optional: original field in the input that is referenced/aliased by this field
)

schema:
  - name: MyField1
    type: TIMESTAMP
    proctime: true    # optional: boolean flag whether this field should be a processing-time attribute
  - name: MyField2
    type: TIMESTAMP
    rowtime: ...      # optional: wether this field should be a event-time attribute
  - name: MyField3
    type: BOOLEAN
    from: mf3         # optional: original field in the input that is referenced/aliased by this field

// Converts an existing LONG or SQL_TIMESTAMP field in the input into the rowtime attribute.
.rowtime(
  new Rowtime()
    .timestampsFromField("ts_field")    // required: original field name in the input
)

// Converts the assigned timestamps from a DataStream API record into the rowtime attribute
// and thus preserves the assigned timestamps from the source.
// This requires a source that assigns timestamps (e.g., Kafka 0.10+).
.rowtime(
  new Rowtime()
    .timestampsFromSource()
)

// Sets a custom timestamp extractor to be used for the rowtime attribute.
// The extractor must extend `org.apache.flink.table.sources.tsextractors.TimestampExtractor`.
.rowtime(
  new Rowtime()
    .timestampsFromExtractor(...)
)

# Converts an existing BIGINT or TIMESTAMP field in the input into the rowtime attribute.
.rowtime(
    Rowtime()
    .timestamps_from_field("ts_field")  # required: original field name in the input
)

# Converts the assigned timestamps into the rowtime attribute
# and thus preserves the assigned timestamps from the source.
# This requires a source that assigns timestamps (e.g., Kafka 0.10+).
.rowtime(
    Rowtime()
    .timestamps_from_source()
)

# Sets a custom timestamp extractor to be used for the rowtime attribute.
# The extractor must extend `org.apache.flink.table.sources.tsextractors.TimestampExtractor`.
# Due to python can not accept java object, so it requires a full-qualified class name of the extractor.
.rowtime(
    Rowtime()
    .timestamps_from_extractor(...)
)

# Converts an existing BIGINT or TIMESTAMP field in the input into the rowtime attribute.
rowtime:
  timestamps:
    type: from-field
    from: "ts_field"                 # required: original field name in the input

# Converts the assigned timestamps from a DataStream API record into the rowtime attribute
# and thus preserves the assigned timestamps from the source.
rowtime:
  timestamps:
    type: from-source

// Sets a watermark strategy for ascending rowtime attributes. Emits a watermark of the maximum
// observed timestamp so far minus 1. Rows that have a timestamp equal to the max timestamp
// are not late.
.rowtime(
  new Rowtime()
    .watermarksPeriodicAscending()
)

// Sets a built-in watermark strategy for rowtime attributes which are out-of-order by a bounded time interval.
// Emits watermarks which are the maximum observed timestamp minus the specified delay.
.rowtime(
  new Rowtime()
    .watermarksPeriodicBounded(2000)    // delay in milliseconds
)

// Sets a built-in watermark strategy which indicates the watermarks should be preserved from the
// underlying DataStream API and thus preserves the assigned watermarks from the source.
.rowtime(
  new Rowtime()
    .watermarksFromSource()
)

# Sets a watermark strategy for ascending rowtime attributes. Emits a watermark of the maximum
# observed timestamp so far minus 1. Rows that have a timestamp equal to the max timestamp
# are not late.
.rowtime(
    Rowtime()
    .watermarks_periodic_ascending()
)

# Sets a built-in watermark strategy for rowtime attributes which are out-of-order by a bounded time interval.
# Emits watermarks which are the maximum observed timestamp minus the specified delay.
.rowtime(
    Rowtime()
    .watermarks_periodic_bounded(2000)  # delay in milliseconds
)

# Sets a built-in watermark strategy which indicates the watermarks should be preserved from the
# underlying DataStream API and thus preserves the assigned watermarks from the source.
.rowtime(
    Rowtime()
    .watermarks_from_source()
)

# Sets a watermark strategy for ascending rowtime attributes. Emits a watermark of the maximum
# observed timestamp so far minus 1. Rows that have a timestamp equal to the max timestamp
# are not late.
rowtime:
  watermarks:
    type: periodic-ascending

# Sets a built-in watermark strategy for rowtime attributes which are out-of-order by a bounded time interval.
# Emits watermarks which are the maximum observed timestamp minus the specified delay.
rowtime:
  watermarks:
    type: periodic-bounded
    delay: ...                # required: delay in milliseconds

# Sets a built-in watermark strategy which indicates the watermarks should be preserved from the
# underlying DataStream API and thus preserves the assigned watermarks from the source.
rowtime:
  watermarks:
    type: from-source

.connect(...)
  .inAppendMode()    // otherwise: inUpsertMode() or inRetractMode()

.connect(...) \
    .in_append_mode()  # otherwise: in_upsert_mode() or in_retract_mode()

tables:
  - name: ...
    update-mode: append    # otherwise: "retract" or "upsert"

CREATE TABLE MyTable (
 ...
) WITH (
 'update-mode' = 'append'  -- otherwise: 'retract' or 'upsert'
)

.connect(
  new FileSystem()
    .path("file:///path/to/whatever")    // required: path to a file or directory
)

.connect(
    FileSystem()
    .path("file:///path/to/whatever")  # required: path to a file or directory
)

connector:
  type: filesystem
  path: "file:///path/to/whatever"    # required: path to a file or directory

CREATE TABLE MyUserTable (
  ...
) WITH (
  'connector.type' = 'filesystem',               -- required: specify to connector type
  'connector.path' = 'file:///path/to/whatever'  -- required: path to a file or directory
)

.connect(
  new Kafka()
    .version("0.11")    // required: valid connector versions are
                        //   "0.8", "0.9", "0.10", "0.11", and "universal"
    .topic("...")       // required: topic name from which the table is read

    // optional: connector specific properties
    .property("zookeeper.connect", "localhost:2181")
    .property("bootstrap.servers", "localhost:9092")
    .property("group.id", "testGroup")

    // optional: select a startup mode for Kafka offsets
    .startFromEarliest()
    .startFromLatest()
    .startFromSpecificOffsets(...)

    // optional: output partitioning from Flink's partitions into Kafka's partitions
    .sinkPartitionerFixed()         // each Flink partition ends up in at-most one Kafka partition (default)
    .sinkPartitionerRoundRobin()    // a Flink partition is distributed to Kafka partitions round-robin
    .sinkPartitionerCustom(MyCustom.class)    // use a custom FlinkKafkaPartitioner subclass
)

.connect(
    Kafka()
    .version("0.11")  # required: valid connector versions are
                      # "0.8", "0.9", "0.10", "0.11", and "universal"
    .topic("...")     # required: topic name from which the table is read
    
    # optional: connector specific properties
    .property("zookeeper.connect", "localhost:2181")
    .property("bootstrap.servers", "localhost:9092")
    .property("group.id", "testGroup")

    # optional: select a startup mode for Kafka offsets
    .start_from_earliest()
    .start_from_latest()
    .start_from_specific_offsets(...)

    # optional: output partitioning from Flink's partitions into Kafka's partitions
    .sink_partitioner_fixed()        # each Flink partition ends up in at-most one Kafka partition (default)
    .sink_partitioner_round_robin()  # a Flink partition is distributed to Kafka partitions round-robin
    .sink_partitioner_custom("full.qualified.custom.class.name")  # use a custom FlinkKafkaPartitioner subclass
)

connector:
  type: kafka
  version: "0.11"     # required: valid connector versions are
                      #   "0.8", "0.9", "0.10", "0.11", and "universal"
  topic: ...          # required: topic name from which the table is read

  properties:         # optional: connector specific properties
    - key: zookeeper.connect
      value: localhost:2181
    - key: bootstrap.servers
      value: localhost:9092
    - key: group.id
      value: testGroup

  startup-mode: ...   # optional: valid modes are "earliest-offset", "latest-offset",
                      # "group-offsets", or "specific-offsets"
  specific-offsets:   # optional: used in case of startup mode with specific offsets
    - partition: 0
      offset: 42
    - partition: 1
      offset: 300

  sink-partitioner: ...    # optional: output partitioning from Flink's partitions into Kafka's partitions
                           # valid are "fixed" (each Flink partition ends up in at most one Kafka partition),
                           # "round-robin" (a Flink partition is distributed to Kafka partitions round-robin)
                           # "custom" (use a custom FlinkKafkaPartitioner subclass)
  sink-partitioner-class: org.mycompany.MyPartitioner  # optional: used in case of sink partitioner custom

CREATE TABLE MyUserTable (
  ...
) WITH (
  'connector.type' = 'kafka',       

  'connector.version' = '0.11',     -- required: valid connector versions are
                                    -- "0.8", "0.9", "0.10", "0.11", and "universal"

  'connector.topic' = 'topic_name', -- required: topic name from which the table is read

  'update-mode' = 'append',         -- required: update mode when used as table sink, 
                                    -- only support append mode now.

  'connector.properties.0.key' = 'zookeeper.connect', -- optional: connector specific properties
  'connector.properties.0.value' = 'localhost:2181',
  'connector.properties.1.key' = 'bootstrap.servers',
  'connector.properties.1.value' = 'localhost:9092',
  'connector.properties.2.key' = 'group.id',
  'connector.properties.2.value' = 'testGroup',
  'connector.startup-mode' = 'earliest-offset',    -- optional: valid modes are "earliest-offset", 
                                                   -- "latest-offset", "group-offsets", 
                                                   -- or "specific-offsets"

  -- optional: used in case of startup mode with specific offsets
  'connector.specific-offsets.0.partition' = '0',
  'connector.specific-offsets.0.offset' = '42',
  'connector.specific-offsets.1.partition' = '1',
  'connector.specific-offsets.1.offset' = '300',

  'connector.sink-partitioner' = '...',  -- optional: output partitioning from Flink's partitions 
                                         -- into Kafka's partitions valid are "fixed" 
                                         -- (each Flink partition ends up in at most one Kafka partition),
                                         -- "round-robin" (a Flink partition is distributed to 
                                         -- Kafka partitions round-robin)
                                         -- "custom" (use a custom FlinkKafkaPartitioner subclass)
  -- optional: used in case of sink partitioner custom
  'connector.sink-partitioner-class' = 'org.mycompany.MyPartitioner'
)

.connect(
  new Elasticsearch()
    .version("6")                      // required: valid connector versions are "6"
    .host("localhost", 9200, "http")   // required: one or more Elasticsearch hosts to connect to
    .index("MyUsers")                  // required: Elasticsearch index
    .documentType("user")              // required: Elasticsearch document type

    .keyDelimiter("$")        // optional: delimiter for composite keys ("_" by default)
                              //   e.g., "$" would result in IDs "KEY1$KEY2$KEY3"
    .keyNullLiteral("n/a")    // optional: representation for null fields in keys ("null" by default)

    // optional: failure handling strategy in case a request to Elasticsearch fails (fail by default)
    .failureHandlerFail()          // optional: throws an exception if a request fails and causes a job failure
    .failureHandlerIgnore()        //   or ignores failures and drops the request
    .failureHandlerRetryRejected() //   or re-adds requests that have failed due to queue capacity saturation
    .failureHandlerCustom(...)     //   or custom failure handling with a ActionRequestFailureHandler subclass

    // optional: configure how to buffer elements before sending them in bulk to the cluster for efficiency
    .disableFlushOnCheckpoint()    // optional: disables flushing on checkpoint (see notes below!)
    .bulkFlushMaxActions(42)       // optional: maximum number of actions to buffer for each bulk request
    .bulkFlushMaxSize("42 mb")     // optional: maximum size of buffered actions in bytes per bulk request
                                   //   (only MB granularity is supported)
    .bulkFlushInterval(60000L)     // optional: bulk flush interval (in milliseconds)

    .bulkFlushBackoffConstant()    // optional: use a constant backoff type
    .bulkFlushBackoffExponential() //   or use an exponential backoff type
    .bulkFlushBackoffMaxRetries(3) // optional: maximum number of retries
    .bulkFlushBackoffDelay(30000L) // optional: delay between each backoff attempt (in milliseconds)

    // optional: connection properties to be used during REST communication to Elasticsearch
    .connectionMaxRetryTimeout(3)  // optional: maximum timeout (in milliseconds) between retries
    .connectionPathPrefix("/v1")   // optional: prefix string to be added to every REST communication
)

.connect(
    Elasticsearch()
    .version("6")                      # required: valid connector versions are "6"
    .host("localhost", 9200, "http")   # required: one or more Elasticsearch hosts to connect to
    .index("MyUsers")                  # required: Elasticsearch index
    .document_type("user")             # required: Elasticsearch document type

    .key_delimiter("$")       # optional: delimiter for composite keys ("_" by default)
                              #   e.g., "$" would result in IDs "KEY1$KEY2$KEY3"
    .key_null_literal("n/a")  # optional: representation for null fields in keys ("null" by default)

    # optional: failure handling strategy in case a request to Elasticsearch fails (fail by default)
    .failure_handler_fail()             # optional: throws an exception if a request fails and causes a job failure
    .failure_handler_ignore()           #   or ignores failures and drops the request
    .failure_handler_retry_rejected()   #   or re-adds requests that have failed due to queue capacity saturation
    .failure_handler_custom(...)        #   or custom failure handling with a ActionRequestFailureHandler subclass

    # optional: configure how to buffer elements before sending them in bulk to the cluster for efficiency
    .disable_flush_on_checkpoint()      # optional: disables flushing on checkpoint (see notes below!)
    .bulk_flush_max_actions(42)         # optional: maximum number of actions to buffer for each bulk request
    .bulk_flush_max_size("42 mb")       # optional: maximum size of buffered actions in bytes per bulk request
                                        #   (only MB granularity is supported)
    .bulk_flush_interval(60000)         # optional: bulk flush interval (in milliseconds)

    .bulk_flush_backoff_constant()      # optional: use a constant backoff type
    .bulk_flush_backoff_exponential()   #   or use an exponential backoff type
    .bulk_flush_backoff_max_retries(3)  # optional: maximum number of retries
    .bulk_flush_backoff_delay(30000)    # optional: delay between each backoff attempt (in milliseconds)

    # optional: connection properties to be used during REST communication to Elasticsearch
    .connection_max_retry_timeout(3)    # optional: maximum timeout (in milliseconds) between retries
    .connection_path_prefix("/v1")      # optional: prefix string to be added to every REST communication
)

connector:
  type: elasticsearch
  version: 6                # required: valid connector versions are "6"
    hosts:                  # required: one or more Elasticsearch hosts to connect to
      - hostname: "localhost"
        port: 9200
        protocol: "http"
    index: "MyUsers"        # required: Elasticsearch index
    document-type: "user"   # required: Elasticsearch document type

    key-delimiter: "$"      # optional: delimiter for composite keys ("_" by default)
                            #   e.g., "$" would result in IDs "KEY1$KEY2$KEY3"
    key-null-literal: "n/a" # optional: representation for null fields in keys ("null" by default)

    # optional: failure handling strategy in case a request to Elasticsearch fails ("fail" by default)
    failure-handler: ...    # valid strategies are "fail" (throws an exception if a request fails and
                            #   thus causes a job failure), "ignore" (ignores failures and drops the request),
                            #   "retry-rejected" (re-adds requests that have failed due to queue capacity
                            #   saturation), or "custom" for failure handling with a
                            #   ActionRequestFailureHandler subclass

    # optional: configure how to buffer elements before sending them in bulk to the cluster for efficiency
    flush-on-checkpoint: true   # optional: disables flushing on checkpoint (see notes below!) ("true" by default)
    bulk-flush:
      max-actions: 42           # optional: maximum number of actions to buffer for each bulk request
      max-size: 42 mb           # optional: maximum size of buffered actions in bytes per bulk request
                                #   (only MB granularity is supported)
      interval: 60000           # optional: bulk flush interval (in milliseconds)
      back-off:                 # optional: backoff strategy ("disabled" by default)
        type: ...               #   valid strategies are "disabled", "constant", or "exponential"
        max-retries: 3          # optional: maximum number of retries
        delay: 30000            # optional: delay between each backoff attempt (in milliseconds)

    # optional: connection properties to be used during REST communication to Elasticsearch
    connection-max-retry-timeout: 3   # optional: maximum timeout (in milliseconds) between retries
    connection-path-prefix: "/v1"     # optional: prefix string to be added to every REST communication

CREATE TABLE MyUserTable (
  ...
) WITH (
  'connector.type' = 'elasticsearch', -- required: specify this table type is elasticsearch
  
  'connector.version' = '6',          -- required: valid connector versions are "6"
  
  'connector.hosts.0.hostname' = 'host_name',  -- required: one or more Elasticsearch hosts to connect to
  'connector.hosts.0.port' = '9092',
  'connector.hosts.0.protocol' = 'http',

  'connector.index' = 'MyUsers',       -- required: Elasticsearch index

  'connector.document-type' = 'user',  -- required: Elasticsearch document type

  'update-mode' = 'append',            -- optional: update mode when used as table sink.           

  'connector.key-delimiter' = '$',     -- optional: delimiter for composite keys ("_" by default)
                                       -- e.g., "$" would result in IDs "KEY1$KEY2$KEY3"

  'connector.key-null-literal' = 'n/a',  -- optional: representation for null fields in keys ("null" by default)

  'connector.failure-handler' = '...',   -- optional: failure handling strategy in case a request to 
                                         -- Elasticsearch fails ("fail" by default).
                                         -- valid strategies are 
                                         -- "fail" (throws an exception if a request fails and
                                         -- thus causes a job failure), 
                                         -- "ignore" (ignores failures and drops the request),
                                         -- "retry-rejected" (re-adds requests that have failed due 
                                         -- to queue capacity saturation), 
                                         -- or "custom" for failure handling with a
                                         -- ActionRequestFailureHandler subclass

  -- optional: configure how to buffer elements before sending them in bulk to the cluster for efficiency
  'connector.flush-on-checkpoint' = 'true',   -- optional: disables flushing on checkpoint (see notes below!)
                                              -- ("true" by default)
  'connector.bulk-flush.max-actions' = '42',  -- optional: maximum number of actions to buffer 
                                              -- for each bulk request
  'connector.bulk-flush.max-size' = '42 mb',  -- optional: maximum size of buffered actions in bytes
                                              -- per bulk request
                                              -- (only MB granularity is supported)
  'connector.bulk-flush.interval' = '60000',  -- optional: bulk flush interval (in milliseconds)
  'connector.bulk-flush.back-off.type' = '...',       -- optional: backoff strategy ("disabled" by default)
                                                      -- valid strategies are "disabled", "constant",
                                                      -- or "exponential"
  'connector.bulk-flush.back-off.max-retries' = '3',  -- optional: maximum number of retries
  'connector.bulk-flush.back-off.delay' = '30000',    -- optional: delay between each backoff attempt
                                                      -- (in milliseconds)

  -- optional: connection properties to be used during REST communication to Elasticsearch
  'connector.connection-max-retry-timeout' = '3',     -- optional: maximum timeout (in milliseconds)
                                                      -- between retries
  'connector.connection-path-prefix' = '/v1'          -- optional: prefix string to be added to every
                                                      -- REST communication
)

connector:
  type: hbase
  version: "1.4.3"                 # required: currently only support "1.4.3"
  
  table-name: "hbase_table_name" # required: HBase table name
  
  zookeeper:
    quorum: "localhost:2181"     # required: HBase Zookeeper quorum configuration
    znode.parent: "/test"        # optional: the root dir in Zookeeper for HBase cluster.
                                 # The default value is "/hbase".
  
  write.buffer-flush:
    max-size: "10mb"             # optional: writing option, determines how many size in memory of buffered
                                 # rows to insert per round trip. This can help performance on writing to JDBC
                                 # database. The default value is "2mb".
    max-rows: 1000               # optional: writing option, determines how many rows to insert per round trip.
                                 # This can help performance on writing to JDBC database. No default value,
                                 # i.e. the default flushing is not depends on the number of buffered rows.
    interval: "2s"               # optional: writing option, sets a flush interval flushing buffered requesting
                                 # if the interval passes, in milliseconds. Default value is "0s", which means
                                 # no asynchronous flush thread will be scheduled.

CREATE TABLE MyUserTable (
  hbase_rowkey_name rowkey_type,
  hbase_column_family_name1 ROW<...>,
  hbase_column_family_name2 ROW<...>
) WITH (
  'connector.type' = 'hbase', -- required: specify this table type is hbase
  
  'connector.version' = '1.4.3',          -- required: valid connector versions are "1.4.3"
  
  'connector.table-name' = 'hbase_table_name',  -- required: hbase table name
  
  'connector.zookeeper.quorum' = 'localhost:2181', -- required: HBase Zookeeper quorum configuration
  'connector.zookeeper.znode.parent' = '/test',    -- optional: the root dir in Zookeeper for HBase cluster.
                                                   -- The default value is "/hbase".

  'connector.write.buffer-flush.max-size' = '10mb', -- optional: writing option, determines how many size in memory of buffered
                                                    -- rows to insert per round trip. This can help performance on writing to JDBC
                                                    -- database. The default value is "2mb".

  'connector.write.buffer-flush.max-rows' = '1000', -- optional: writing option, determines how many rows to insert per round trip.
                                                    -- This can help performance on writing to JDBC database. No default value,
                                                    -- i.e. the default flushing is not depends on the number of buffered rows.

  'connector.write.buffer-flush.interval' = '2s',   -- optional: writing option, sets a flush interval flushing buffered requesting
                                                    -- if the interval passes, in milliseconds. Default value is "0s", which means
                                                    -- no asynchronous flush thread will be scheduled.
)

connector:
  type: jdbc
  url: "jdbc:mysql://localhost:3306/flink-test"     # required: JDBC DB url
  table: "jdbc_table_name"        # required: jdbc table name
  driver: "com.mysql.jdbc.Driver" # optional: the class name of the JDBC driver to use to connect to this URL.
                                  # If not set, it will automatically be derived from the URL.

  username: "name"                # optional: jdbc user name and password
  password: "password"
  
  read: # scan options, optional, used when reading from table
    partition: # These options must all be specified if any of them is specified. In addition, partition.num must be specified. They
               # describe how to partition the table when reading in parallel from multiple tasks. partition.column must be a numeric,
               # date, or timestamp column from the table in question. Notice that lowerBound and upperBound are just used to decide
               # the partition stride, not for filtering the rows in table. So all rows in the table will be partitioned and returned.
               # This option applies only to reading.
      column: "column_name" # optional, name of the column used for partitioning the input.
      num: 50               # optional, the number of partitions.
      lower-bound: 500      # optional, the smallest value of the first partition.
      upper-bound: 1000     # optional, the largest value of the last partition.
    fetch-size: 100         # optional, Gives the reader a hint as to the number of rows that should be fetched
                            # from the database when reading per round trip. If the value specified is zero, then
                            # the hint is ignored. The default value is zero.
  
  lookup: # lookup options, optional, used in temporary join
    cache:
      max-rows: 5000 # optional, max number of rows of lookup cache, over this value, the oldest rows will
                     # be eliminated. "cache.max-rows" and "cache.ttl" options must all be specified if any
                     # of them is specified. Cache is not enabled as default.
      ttl: "10s"     # optional, the max time to live for each rows in lookup cache, over this time, the oldest rows
                     # will be expired. "cache.max-rows" and "cache.ttl" options must all be specified if any of
                     # them is specified. Cache is not enabled as default.
    max-retries: 3   # optional, max retry times if lookup database failed
  
  write: # sink options, optional, used when writing into table
      flush:
        max-rows: 5000 # optional, flush max size (includes all append, upsert and delete records), 
                       # over this number of records, will flush data. The default value is "5000".
        interval: "2s" # optional, flush interval mills, over this time, asynchronous threads will flush data.
                       # The default value is "0s", which means no asynchronous flush thread will be scheduled. 
      max-retries: 3   # optional, max retry times if writing records to database failed.

CREATE TABLE MyUserTable (
  ...
) WITH (
  'connector.type' = 'jdbc', -- required: specify this table type is jdbc
  
  'connector.url' = 'jdbc:mysql://localhost:3306/flink-test', -- required: JDBC DB url
  
  'connector.table' = 'jdbc_table_name',  -- required: jdbc table name
  
  'connector.driver' = 'com.mysql.jdbc.Driver', -- optional: the class name of the JDBC driver to use to connect to this URL. 
                                                -- If not set, it will automatically be derived from the URL.

  'connector.username' = 'name', -- optional: jdbc user name and password
  'connector.password' = 'password',
  
  -- scan options, optional, used when reading from table

  -- These options must all be specified if any of them is specified. In addition, partition.num must be specified. They
  -- describe how to partition the table when reading in parallel from multiple tasks. partition.column must be a numeric,
  -- date, or timestamp column from the table in question. Notice that lowerBound and upperBound are just used to decide
  -- the partition stride, not for filtering the rows in table. So all rows in the table will be partitioned and returned.
  -- This option applies only to reading.
  'connector.read.partition.column' = 'column_name', -- optional, name of the column used for partitioning the input.
  'connector.read.partition.num' = '50', -- optional, the number of partitions.
  'connector.read.partition.lower-bound' = '500', -- optional, the smallest value of the first partition.
  'connector.read.partition.upper-bound' = '1000', -- optional, the largest value of the last partition.
  
  'connector.read.fetch-size' = '100', -- optional, Gives the reader a hint as to the number of rows that should be fetched
                                       -- from the database when reading per round trip. If the value specified is zero, then
                                       -- the hint is ignored. The default value is zero.

  -- lookup options, optional, used in temporary join
  'connector.lookup.cache.max-rows' = '5000', -- optional, max number of rows of lookup cache, over this value, the oldest rows will
                                              -- be eliminated. "cache.max-rows" and "cache.ttl" options must all be specified if any
                                              -- of them is specified. Cache is not enabled as default.
  'connector.lookup.cache.ttl' = '10s', -- optional, the max time to live for each rows in lookup cache, over this time, the oldest rows
                                        -- will be expired. "cache.max-rows" and "cache.ttl" options must all be specified if any of
                                        -- them is specified. Cache is not enabled as default.
  'connector.lookup.max-retries' = '3', -- optional, max retry times if lookup database failed

  -- sink options, optional, used when writing into table
  'connector.write.flush.max-rows' = '5000', -- optional, flush max size (includes all append, upsert and delete records), 
                                             -- over this number of records, will flush data. The default value is "5000".
  'connector.write.flush.interval' = '2s', -- optional, flush interval mills, over this time, asynchronous threads will flush data.
                                           -- The default value is "0s", which means no asynchronous flush thread will be scheduled. 
  'connector.write.max-retries' = '3' -- optional, max retry times if writing records to database failed
)

.withFormat(
  new Csv()

    // required: define the schema either by using type information
    .schema(Type.ROW(...))

    // or use the table's schema
    .deriveSchema()

    .fieldDelimiter(';')         // optional: field delimiter character (',' by default)
    .lineDelimiter("\r\n")       // optional: line delimiter ("\n" by default;
                                 //   otherwise "\r" or "\r\n" are allowed)
    .quoteCharacter('\'')        // optional: quote character for enclosing field values ('"' by default)
    .allowComments()             // optional: ignores comment lines that start with '#' (disabled by default);
                                 //   if enabled, make sure to also ignore parse errors to allow empty rows
    .ignoreParseErrors()         // optional: skip fields and rows with parse errors instead of failing;
                                 //   fields are set to null in case of errors
    .arrayElementDelimiter("|")  // optional: the array element delimiter string for separating
                                 //   array and row element values (";" by default)
    .escapeCharacter('\\')       // optional: escape character for escaping values (disabled by default)
    .nullLiteral("n/a")          // optional: null literal string that is interpreted as a
                                 //   null value (disabled by default)
)

.with_format(
    Csv()

    # required: define the schema either by using type information
    .schema(DataTypes.ROW(...))

    # or use the table's schema
    .derive_schema()

    .field_delimiter(';')          # optional: field delimiter character (',' by default)
    .line_delimiter("\r\n")        # optional: line delimiter ("\n" by default;
                                   #   otherwise "\r" or "\r\n" are allowed)
    .quote_character('\'')         # optional: quote character for enclosing field values ('"' by default)
    .allow_comments()              # optional: ignores comment lines that start with '#' (disabled by default);
                                   #   if enabled, make sure to also ignore parse errors to allow empty rows
    .ignore_parse_errors()         # optional: skip fields and rows with parse errors instead of failing;
                                   #   fields are set to null in case of errors
    .array_element_delimiter("|")  # optional: the array element delimiter string for separating
                                   #   array and row element values (";" by default)
    .escape_character('\\')        # optional: escape character for escaping values (disabled by default)
    .null_literal("n/a")           # optional: null literal string that is interpreted as a
                                   #   null value (disabled by default)
)

format:
  type: csv

  # required: define the schema either by using type information
  schema: "ROW(lon FLOAT, rideTime TIMESTAMP)"

  # or use the table's schema
  derive-schema: true

  field-delimiter: ";"         # optional: field delimiter character (',' by default)
  line-delimiter: "\r\n"       # optional: line delimiter ("\n" by default; otherwise "\r" or "\r\n" are allowed)
  quote-character: "'"         # optional: quote character for enclosing field values ('"' by default)
  allow-comments: true         # optional: ignores comment lines that start with "#" (disabled by default);
                               #   if enabled, make sure to also ignore parse errors to allow empty rows
  ignore-parse-errors: true    # optional: skip fields and rows with parse errors instead of failing;
                               #   fields are set to null in case of errors
  array-element-delimiter: "|" # optional: the array element delimiter string for separating
                               #   array and row element values (";" by default)
  escape-character: "\\"       # optional: escape character for escaping values (disabled by default)
  null-literal: "n/a"          # optional: null literal string that is interpreted as a
                               #   null value (disabled by default)

CREATE TABLE MyUserTable (
  ...
) WITH (
  'format.type' = 'csv',                  -- required: specify the schema type

  'format.fields.0.name' = 'lon',         -- required: define the schema either by using type information
  'format.fields.0.type' = 'FLOAT',
  'format.fields.1.name' = 'rideTime',
  'format.fields.1.type' = 'TIMESTAMP',

  'format.derive-schema' = 'true',        -- or use the table's schema

  'format.field-delimiter' = ';',         -- optional: field delimiter character (',' by default)
  'format.line-delimiter' = '\r\n',       -- optional: line delimiter ("\n" by default; otherwise
                                          -- "\r" or "\r\n" are allowed)
  'format.quote-character' = '''',        -- optional: quote character for enclosing field values ('"' by default)
  'format.allow-comments' = true,         -- optional: ignores comment lines that start with "#" 
                                          -- (disabled by default);
                                          -- if enabled, make sure to also ignore parse errors to allow empty rows
  'format.ignore-parse-errors' = 'true',  -- optional: skip fields and rows with parse errors instead of failing;
                                          -- fields are set to null in case of errors
  'format.array-element-delimiter' = '|', -- optional: the array element delimiter string for separating
                                          -- array and row element values (";" by default)
  'format.escape-character' = '\\',       -- optional: escape character for escaping values (disabled by default)
  'format.null-literal' = 'n/a'           -- optional: null literal string that is interpreted as a
                                          -- null value (disabled by default)
)

.withFormat(
  new Json()
    .failOnMissingField(true)   // optional: flag whether to fail if a field is missing or not, false by default

    // required: define the schema either by using type information which parses numbers to corresponding types
    .schema(Type.ROW(...))

    // or by using a JSON schema which parses to DECIMAL and TIMESTAMP
    .jsonSchema(
      "{" +
      "  type: 'object'," +
      "  properties: {" +
      "    lon: {" +
      "      type: 'number'" +
      "    }," +
      "    rideTime: {" +
      "      type: 'string'," +
      "      format: 'date-time'" +
      "    }" +
      "  }" +
      "}"
    )

    // or use the table's schema
    .deriveSchema()
)

.with_format(
    Json()
    .fail_on_missing_field(True)   # optional: flag whether to fail if a field is missing or not, False by default

    # required: define the schema either by using type information which parses numbers to corresponding types
    .schema(DataTypes.ROW(...))

    # or by using a JSON schema which parses to DECIMAL and TIMESTAMP
    .json_schema(
        "{"
        "  type: 'object',"
        "  properties: {"
        "    lon: {"
        "      type: 'number'"
        "    },"
        "    rideTime: {"
        "      type: 'string',"
        "      format: 'date-time'"
        "    }"
        "  }"
        "}"
    )

    # or use the table's schema
    .derive_schema()
)

format:
  type: json
  fail-on-missing-field: true   # optional: flag whether to fail if a field is missing or not, false by default

  # required: define the schema either by using a type string which parses numbers to corresponding types
  schema: "ROW(lon FLOAT, rideTime TIMESTAMP)"

  # or by using a JSON schema which parses to DECIMAL and TIMESTAMP
  json-schema: >
    {
      type: 'object',
      properties: {
        lon: {
          type: 'number'
        },
        rideTime: {
          type: 'string',
          format: 'date-time'
        }
      }
    }

  # or use the table's schema
  derive-schema: true

CREATE TABLE MyUserTable (
  ...
) WITH (
  'format.type' = 'json',                   -- required: specify the format type
  'format.fail-on-missing-field' = 'true'   -- optional: flag whether to fail if a field is missing or not, false by default

  'format.fields.0.name' = 'lon',           -- required: define the schema either by using a type string which parses numbers to corresponding types
  'format.fields.0.type' = 'FLOAT',
  'format.fields.1.name' = 'rideTime',
  'format.fields.1.type' = 'TIMESTAMP',

  'format.json-schema' =                    -- or by using a JSON schema which parses to DECIMAL and TIMESTAMP
    '{
      "type": "object",
      "properties": {
        "lon": {
          "type": "number"
        },
        "rideTime": {
          "type": "string",
          "format": "date-time"
        }
      }
    }',

  'format.derive-schema' = 'true'          -- or use the table's schema
)

.withFormat(
  new Avro()

    // required: define the schema either by using an Avro specific record class
    .recordClass(User.class)

    // or by using an Avro schema
    .avroSchema(
      "{" +
      "  \"type\": \"record\"," +
      "  \"name\": \"test\"," +
      "  \"fields\" : [" +
      "    {\"name\": \"a\", \"type\": \"long\"}," +
      "    {\"name\": \"b\", \"type\": \"string\"}" +
      "  ]" +
      "}"
    )
)

.with_format(
    Avro()

    # required: define the schema either by using an Avro specific record class
    .record_class("full.qualified.user.class.name")

    # or by using an Avro schema
    .avro_schema(
        "{"
        "  \"type\": \"record\","
        "  \"name\": \"test\","
        "  \"fields\" : ["
        "    {\"name\": \"a\", \"type\": \"long\"},"
        "    {\"name\": \"b\", \"type\": \"string\"}"
        "  ]"
        "}"
    )
)

format:
  type: avro

  # required: define the schema either by using an Avro specific record class
  record-class: "org.organization.types.User"

  # or by using an Avro schema
  avro-schema: >
    {
      "type": "record",
      "name": "test",
      "fields" : [
        {"name": "a", "type": "long"},
        {"name": "b", "type": "string"}
      ]
    }

CREATE TABLE MyUserTable (
  ...
) WITH (
  'format.type' = 'avro',                                 -- required: specify the schema type
  'format.record-class' = 'org.organization.types.User',  -- required: define the schema either by using an Avro specific record class

  'format.avro-schema' =                                  -- or by using an Avro schema
    '{
      "type": "record",
      "name": "test",
      "fields" : [
        {"name": "a", "type": "long"},
        {"name": "b", "type": "string"}
      ]
    }'
)

.withFormat(
  new OldCsv()
    .field("field1", Types.STRING)    // required: ordered format fields
    .field("field2", Types.TIMESTAMP)
    .fieldDelimiter(",")              // optional: string delimiter "," by default
    .lineDelimiter("\n")              // optional: string delimiter "\n" by default
    .quoteCharacter('"')              // optional: single character for string values, empty by default
    .commentPrefix('#')               // optional: string to indicate comments, empty by default
    .ignoreFirstLine()                // optional: ignore the first line, by default it is not skipped
    .ignoreParseErrors()              // optional: skip records with parse error instead of failing by default
)

.with_format(
    OldCsv()
    .field("field1", DataTypes.STRING())    # required: ordered format fields
    .field("field2", DataTypes.TIMESTAMP())
    .field_delimiter(",")                   # optional: string delimiter "," by default
    .line_delimiter("\n")                   # optional: string delimiter "\n" by default
    .quote_character('"')                   # optional: single character for string values, empty by default
    .comment_prefix('#')                    # optional: string to indicate comments, empty by default
    .ignore_first_line()                    # optional: ignore the first line, by default it is not skipped
    .ignore_parse_errors()                  # optional: skip records with parse error instead of failing by default
)

format:
  type: csv
  fields:                    # required: ordered format fields
    - name: field1
      type: VARCHAR
    - name: field2
      type: TIMESTAMP
  field-delimiter: ","       # optional: string delimiter "," by default
  line-delimiter: "\n"       # optional: string delimiter "\n" by default
  quote-character: '"'       # optional: single character for string values, empty by default
  comment-prefix: '#'        # optional: string to indicate comments, empty by default
  ignore-first-line: false   # optional: boolean flag to ignore the first line, by default it is not skipped
  ignore-parse-errors: true  # optional: skip records with parse error instead of failing by default

CREATE TABLE MyUserTable (
  ...
) WITH (
  'format.type' = 'csv',                  -- required: specify the schema type

  'format.fields.0.name' = 'lon',         -- required: define the schema either by using type information
  'format.fields.0.type' = 'FLOAT',
  'format.fields.1.name' = 'rideTime',
  'format.fields.1.type' = 'TIMESTAMP',
  
  'format.field-delimiter' = ',',         -- optional: string delimiter "," by default
  'format.line-delimiter' = '\n',         -- optional: string delimiter "\n" by default
  'format.quote-character' = '"',         -- optional: single character for string values, empty by default
  'format.comment-prefix' = '#',          -- optional: string to indicate comments, empty by default
  'format.ignore-first-line' = 'false',   -- optional: boolean flag to ignore the first line, by default it is not skipped
  'format.ignore-parse-errors' = 'true'   -- optional: skip records with parse error instead of failing by default
)

// create Hadoop Configuration
Configuration config = new Configuration();

OrcTableSource orcTableSource = OrcTableSource.builder()
  // path to ORC file(s). NOTE: By default, directories are recursively scanned.
  .path("file:///path/to/data")
  // schema of ORC files
  .forOrcSchema("struct<name:string,addresses:array<struct<street:string,zip:smallint>>>")
  // Hadoop configuration
  .withConfiguration(config)
  // build OrcTableSource
  .build();

// create Hadoop Configuration
val config = new Configuration()

val orcTableSource = OrcTableSource.builder()
  // path to ORC file(s). NOTE: By default, directories are recursively scanned.
  .path("file:///path/to/data")
  // schema of ORC files
  .forOrcSchema("struct<name:string,addresses:array<struct<street:string,zip:smallint>>>")
  // Hadoop configuration
  .withConfiguration(config)
  // build OrcTableSource
  .build()

CsvTableSink sink = new CsvTableSink(
    path,                  // output path
    "|",                   // optional: delimit files by '|'
    1,                     // optional: write to a single file
    WriteMode.OVERWRITE);  // optional: override existing files

tableEnv.registerTableSink(
  "csvOutputTable",
  // specify table schema
  new String[]{"f0", "f1"},
  new TypeInformation[]{Types.STRING, Types.INT},
  sink);

Table table = ...
table.insertInto("csvOutputTable");

val sink: CsvTableSink = new CsvTableSink(
    path,                             // output path
    fieldDelim = "|",                 // optional: delimit files by '|'
    numFiles = 1,                     // optional: write to a single file
    writeMode = WriteMode.OVERWRITE)  // optional: override existing files

tableEnv.registerTableSink(
  "csvOutputTable",
  // specify table schema
  Array[String]("f0", "f1"),
  Array[TypeInformation[_]](Types.STRING, Types.INT),
  sink)

val table: Table = ???
table.insertInto("csvOutputTable")

field_names = ["f0", "f1"]
field_types = [DataTypes.STRING(), DataTypes.INT()]

sink = CsvTableSink(
    field_names,
    field_types,
    path,                 # output path
    "|",                  # optional: delimit files by '|'
    1,                    # optional: write to a single file
    WriteMode.OVERWRITE  # optional: override existing files
)

table_env.register_table_sink(
    "csvOutputTable",
    sink
)

table = ...
table.insert_into("csvOutputTable")

JDBCAppendTableSink sink = JDBCAppendTableSink.builder()
  .setDrivername("org.apache.derby.jdbc.EmbeddedDriver")
  .setDBUrl("jdbc:derby:memory:ebookshop")
  .setQuery("INSERT INTO books (id) VALUES (?)")
  .setParameterTypes(INT_TYPE_INFO)
  .build();

tableEnv.registerTableSink(
  "jdbcOutputTable",
  // specify table schema
  new String[]{"id"},
  new TypeInformation[]{Types.INT},
  sink);

Table table = ...
table.insertInto("jdbcOutputTable");

val sink: JDBCAppendTableSink = JDBCAppendTableSink.builder()
  .setDrivername("org.apache.derby.jdbc.EmbeddedDriver")
  .setDBUrl("jdbc:derby:memory:ebookshop")
  .setQuery("INSERT INTO books (id) VALUES (?)")
  .setParameterTypes(INT_TYPE_INFO)
  .build()

tableEnv.registerTableSink(
  "jdbcOutputTable",
  // specify table schema
  Array[String]("id"),
  Array[TypeInformation[_]](Types.INT),
  sink)

val table: Table = ???
table.insertInto("jdbcOutputTable")

ClusterBuilder builder = ... // configure Cassandra cluster connection

CassandraAppendTableSink sink = new CassandraAppendTableSink(
  builder,
  // the query must match the schema of the table
  "INSERT INTO flink.myTable (id, name, value) VALUES (?, ?, ?)");

tableEnv.registerTableSink(
  "cassandraOutputTable",
  // specify table schema
  new String[]{"id", "name", "value"},
  new TypeInformation[]{Types.INT, Types.STRING, Types.DOUBLE},
  sink);

Table table = ...
table.insertInto(cassandraOutputTable);

val builder: ClusterBuilder = ... // configure Cassandra cluster connection

val sink: CassandraAppendTableSink = new CassandraAppendTableSink(
  builder,
  // the query must match the schema of the table
  "INSERT INTO flink.myTable (id, name, value) VALUES (?, ?, ?)")

tableEnv.registerTableSink(
  "cassandraOutputTable",
  // specify table schema
  Array[String]("id", "name", "value"),
  Array[TypeInformation[_]](Types.INT, Types.STRING, Types.DOUBLE),
  sink)

val table: Table = ???
table.insertInto(cassandraOutputTable)