final case class Comet(env: String, tmpdir: String, datasets: String, metadata: String, metrics: Metrics, audit: Audit, archive: Boolean, sinkToFile: Boolean, lock: Lock, defaultWriteFormat: String, defaultRejectedWriteFormat: String, defaultAuditWriteFormat: String, csvOutput: Boolean, csvOutputExt: String, privacyOnly: Boolean, launcher: String, chewerPrefix: String, rowValidatorClass: String, treeValidatorClass: String, loadStrategyClass: String, analyze: Boolean, hive: Boolean, grouped: Boolean, mergeForceDistinct: Boolean, area: Area, airflow: Airflow, elasticsearch: Elasticsearch, hadoop: Map[String, String], connections: Map[String, Connection], jdbcEngines: Map[String, JdbcEngine], atlas: Atlas, privacy: Privacy, fileSystem: Option[String], metadataFileSystem: Option[String], internal: Option[Internal], udfs: Option[String], assertions: Assertions, kafka: KafkaConfig, sqlParameterPattern: String) extends Serializable with Product
- datasets
: Absolute path, datasets root folder beneath which each area is defined.
- metadata
: Absolute path, location where all types / domains and auto jobs are defined
- metrics
: Absolute path, location where all computed metrics are stored
- audit
: Absolute path, location where all log are stored
- archive
: Should we backup the ingested datasets ? true by default
- defaultWriteFormat
: Choose between parquet, orc ... Default is parquet
- defaultRejectedWriteFormat
: Writing format for rejected datasets, choose between parquet, orc ... Default is parquet
- defaultAuditWriteFormat
: Writing format for audit datasets, choose between parquet, orc ... Default is parquet
- launcher
: Cron Job Manager : simple (useful for testing) or airflow ? simple by default
- analyze
: Should we create basics Hive statistics on the generated dataset ? true by default
- hive
: Should we create a Hive Table ? true by default
- area
: see Area above
- airflow
: Airflow end point. Should be defined even if simple launccher is used instead of airflow.
- Alphabetic
- By Inheritance
- Comet
- Product
- Equals
- Serializable
- Serializable
- AnyRef
- Any
- Hide All
- Show All
- Public
- All
Instance Constructors
-
new
Comet(env: String, tmpdir: String, datasets: String, metadata: String, metrics: Metrics, audit: Audit, archive: Boolean, sinkToFile: Boolean, lock: Lock, defaultWriteFormat: String, defaultRejectedWriteFormat: String, defaultAuditWriteFormat: String, csvOutput: Boolean, csvOutputExt: String, privacyOnly: Boolean, launcher: String, chewerPrefix: String, rowValidatorClass: String, treeValidatorClass: String, loadStrategyClass: String, analyze: Boolean, hive: Boolean, grouped: Boolean, mergeForceDistinct: Boolean, area: Area, airflow: Airflow, elasticsearch: Elasticsearch, hadoop: Map[String, String], connections: Map[String, Connection], jdbcEngines: Map[String, JdbcEngine], atlas: Atlas, privacy: Privacy, fileSystem: Option[String], metadataFileSystem: Option[String], internal: Option[Internal], udfs: Option[String], assertions: Assertions, kafka: KafkaConfig, sqlParameterPattern: String)
- datasets
: Absolute path, datasets root folder beneath which each area is defined.
- metadata
: Absolute path, location where all types / domains and auto jobs are defined
- metrics
: Absolute path, location where all computed metrics are stored
- audit
: Absolute path, location where all log are stored
- archive
: Should we backup the ingested datasets ? true by default
- defaultWriteFormat
: Choose between parquet, orc ... Default is parquet
- defaultRejectedWriteFormat
: Writing format for rejected datasets, choose between parquet, orc ... Default is parquet
- defaultAuditWriteFormat
: Writing format for audit datasets, choose between parquet, orc ... Default is parquet
- launcher
: Cron Job Manager : simple (useful for testing) or airflow ? simple by default
- analyze
: Should we create basics Hive statistics on the generated dataset ? true by default
- hive
: Should we create a Hive Table ? true by default
- area
: see Area above
- airflow
: Airflow end point. Should be defined even if simple launccher is used instead of airflow.
Value Members
-
final
def
!=(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
-
final
def
##(): Int
- Definition Classes
- AnyRef → Any
-
final
def
==(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
- val airflow: Airflow
- val analyze: Boolean
- val archive: Boolean
- val area: Area
-
final
def
asInstanceOf[T0]: T0
- Definition Classes
- Any
- val assertions: Assertions
- val atlas: Atlas
- val audit: Audit
- val cacheStorageLevel: StorageLevel
- val chewerPrefix: String
-
def
clone(): AnyRef
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws( ... ) @native()
- val connections: Map[String, Connection]
- val csvOutput: Boolean
- val csvOutputExt: String
- val datasets: String
- val defaultAuditWriteFormat: String
- val defaultRejectedWriteFormat: String
- val defaultWriteFormat: String
- val elasticsearch: Elasticsearch
- val env: String
-
final
def
eq(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
- val fileSystem: Option[String]
-
def
finalize(): Unit
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws( classOf[java.lang.Throwable] )
-
final
def
getClass(): Class[_]
- Definition Classes
- AnyRef → Any
- Annotations
- @native()
- val grouped: Boolean
- val hadoop: Map[String, String]
- val hive: Boolean
- val internal: Option[Internal]
-
def
isElasticsearchSupported(): Boolean
- Annotations
- @JsonIgnore()
-
final
def
isInstanceOf[T0]: Boolean
- Definition Classes
- Any
- val jdbcEngines: Map[String, JdbcEngine]
- val kafka: KafkaConfig
- val launcher: String
- val loadStrategyClass: String
- val lock: Lock
- val mergeForceDistinct: Boolean
- val metadata: String
- val metadataFileSystem: Option[String]
- val metrics: Metrics
-
final
def
ne(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
-
final
def
notify(): Unit
- Definition Classes
- AnyRef
- Annotations
- @native()
-
final
def
notifyAll(): Unit
- Definition Classes
- AnyRef
- Annotations
- @native()
- val privacy: Privacy
- val privacyOnly: Boolean
- val rowValidatorClass: String
- val sinkToFile: Boolean
- val sqlParameterPattern: String
-
final
def
synchronized[T0](arg0: ⇒ T0): T0
- Definition Classes
- AnyRef
- val tmpdir: String
- val treeValidatorClass: String
- val udfs: Option[String]
-
final
def
wait(): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws( ... )
-
final
def
wait(arg0: Long, arg1: Int): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws( ... )
-
final
def
wait(arg0: Long): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws( ... ) @native()
-
def
writeReplace: AnyRef
- Attributes
- protected
- Annotations
- @throws( classOf[ObjectStreamException] )