Config

final def !=(arg0: Any): Boolean

final def ##(): Int

final def ==(arg0: Any): Boolean

lazy val abstractParameters: AbstractParameters

final def asInstanceOf[T0]: T0

def clear(): Unit

def clone(): AnyRef

def compute(arg0: AnyRef, arg1: BiFunction[_ >: AnyRef, _ >: AnyRef, _ <: AnyRef]): AnyRef

def computeIfAbsent(arg0: AnyRef, arg1: Function[_ >: AnyRef, _ <: AnyRef]): AnyRef

def computeIfPresent(arg0: AnyRef, arg1: BiFunction[_ >: AnyRef, _ >: AnyRef, _ <: AnyRef]): AnyRef

val configPath: String

def contains(arg0: Any): Boolean

def containsKey(arg0: Any): Boolean

def containsValue(arg0: Any): Boolean

lazy val copyrightCheck: Boolean

lazy val datasetnameExtension: Option[String]

instead of a defined output dataset name, one can specify a name extension turncated at the end of the input dataset name (e.g.

lazy val dbPediaVersion: String

The version string of the DBpedia version being extracted

lazy val disambiguations: String

lazy val dumpDir: File

base-dir gives either an absolute path or a relative path to where all data is stored, normally wikidumps are downloaded here and extracted data is saved next to it, created folder structure is {{lang}}wiki/$date

def elements(): Enumeration[AnyRef]

def entrySet(): Set[Entry[AnyRef, AnyRef]]

final def eq(arg0: AnyRef): Boolean

def equals(arg0: Any): Boolean

lazy val extractorClasses: Map[Language, Seq[Class[_ <: Extractor[_]]]]

the extractor classes to be used when extracting the XML dumps

def finalize(): Unit

def forEach(arg0: BiConsumer[_ >: AnyRef, _ >: AnyRef]): Unit

lazy val formats: Map[String, Formatter]

def get(arg0: Any): AnyRef

def getArbitraryStringProperty(key: String): Option[String]

final def getClass(): Class[_]

def getDefaultExtractionRecorder[T](lang: Language, interval: Int = 100000, preamble: String = null, writer: Writer = null, datasets: ListBuffer[Dataset] = ListBuffer[Dataset](), monitor: ExtractionMonitor = null): ExtractionRecorder[T]

def getOrDefault(arg0: Any, arg1: AnyRef): AnyRef

def getProperty(arg0: String, arg1: String): String

def getProperty(arg0: String): String

def hashCode(): Int

lazy val inputDatasets: Seq[String]

An array of input dataset names (e.g.

lazy val inputSuffix: Option[String]

the suffix of the files representing the input dataset (usually a combination of RDF serialization extension and compression used - e.g.

def isDownloadComplete(lang: Language): Boolean

determines if 1.

def isEmpty(): Boolean

final def isInstanceOf[T0]: Boolean

def keySet(): Set[AnyRef]

def keys(): Enumeration[AnyRef]

lazy val languages: Array[Language]

An array of languages specified by the exact enumeration of language wiki codes (e.g.

def list(arg0: PrintWriter): Unit

def list(arg0: PrintStream): Unit

def load(arg0: InputStream): Unit

def load(arg0: Reader): Unit

def loadFromXML(arg0: InputStream): Unit

lazy val logDir: Option[File]

The directory where all log files will be stored

lazy val mappingsDir: File

Local mappings files, downloaded for speed and reproducibility Note: This is lazy to defer initialization until actually called (eg.

lazy val mediawikiConnection: MediaWikiConnection

def merge(arg0: AnyRef, arg1: AnyRef, arg2: BiFunction[_ >: AnyRef, _ >: AnyRef, _ <: AnyRef]): AnyRef

lazy val namespaces: Set[Namespace]

namespaces loaded defined by the languages in use (see languages)

final def ne(arg0: AnyRef): Boolean

lazy val nifParameters: NifParameters

final def notify(): Unit

final def notifyAll(): Unit

lazy val ontologyFile: File

Local ontology file, downloaded for speed and reproducibility Note: This is lazy to defer initialization until actually called (eg.

lazy val outputDataset: Option[String]

A dataset name for the output file generated (e.g.

lazy val outputSuffix: Option[String]

same as for inputSuffix (for the output dataset)

lazy val parallelProcesses: Int

Number of parallel processes allowed.

lazy val policies: Map[String, Array[Policy]]

def propertyNames(): Enumeration[_]

def put(arg0: AnyRef, arg1: AnyRef): AnyRef

def putAll(arg0: Map[_ <: AnyRef, _ <: AnyRef]): Unit

def putIfAbsent(arg0: AnyRef, arg1: AnyRef): AnyRef

def rehash(): Unit

def remove(arg0: Any, arg1: Any): Boolean

def remove(arg0: Any): AnyRef

def replace(arg0: AnyRef, arg1: AnyRef): AnyRef

def replace(arg0: AnyRef, arg1: AnyRef, arg2: AnyRef): Boolean

def replaceAll(arg0: BiFunction[_ >: AnyRef, _ >: AnyRef, _ <: AnyRef]): Unit

lazy val requireComplete: Boolean

before processing a given language, check if the download.complete file is present

lazy val retryFailedPages: Boolean

TODO experimental, ignore for now

val runJobsInParallel: Boolean

Normally extraction jobs are run sequentially (one language after the other), but for some jobs it makes sense to run these in parallel.

def setProperty(arg0: String, arg1: String): AnyRef

def size(): Int

lazy val slackCredentials: Try[SlackCredentials]

If set, extraction summaries are forwarded via the API of Slack, displaying messages on a dedicated channel.

lazy val source: Seq[String]

get all universal properties, check if there is an override in the provided config file

lazy val sparkLocalDir: String

lazy val sparkMaster: String

def store(arg0: OutputStream, arg1: String): Unit

def store(arg0: Writer, arg1: String): Unit

def storeToXML(arg0: OutputStream, arg1: String, arg2: String): Unit

def storeToXML(arg0: OutputStream, arg1: String): Unit

def stringPropertyNames(): Set[String]

final def synchronized[T0](arg0: ⇒ T0): T0

def throwMissingPropertyException(property: String, required: Boolean): Unit

def toString(): String

def values(): Collection[AnyRef]

final def wait(): Unit

final def wait(arg0: Long, arg1: Int): Unit

final def wait(arg0: Long): Unit

lazy val wikiName: String

lazy val wikidataMappingsFile: File

def save(arg0: OutputStream, arg1: String): Unit