class ReaderAssembler extends Transformer with DefaultParamsWritable with HasOutputAnnotatorType with HasOutputAnnotationCol with HasBinaryReaderProperties with HasTextReaderProperties with HasReaderContent

The ReaderAssembler annotator provides a unified interface for combining multiple Spark NLP readers (such as Reader2Doc, Reader2Table, and Reader2Image) into a single, configurable component. It automatically orchestrates the execution of different readers based on input type, configured priorities, and fallback strategies allowing you to handle diverse content formats without manually chaining multiple readers in your pipeline.

ReaderAssembler simplifies the process of building flexible pipelines capable of ingesting and processing documents, tables, and images in a consistent way. It handles reader selection, ordering, and fault-tolerance internally, ensuring that pipelines remain concise, robust, and easy to maintain.

Example

import com.johnsnowlabs.reader.ReaderAssembler
import com.johnsnowlabs.nlp.base.DocumentAssembler
import org.apache.spark.ml.Pipeline

val readerAssembler = new ReaderAssembler()
  .setContentType("text/html")
  .setContentPath(s"$htmlFilesDirectory/table-image.html")
  .setOutputCol("document")

val pipeline = new Pipeline()
  .setStages(Array(readerAssembler))

val pipelineModel = pipeline.fit(emptyDataSet)
val resultDf = pipelineModel.transform(emptyDataSet)

resultDf.show()
+--------+--------------------+--------------------+--------------------+---------+
|fileName|       document_text|      document_table|      document_image|exception|
+--------+--------------------+--------------------+--------------------+---------+
|    null|[{document, 0, 26...|[{document, 0, 50...|[{image, , 5, 5, ...|     null|
+--------+--------------------+--------------------+--------------------+---------+

This annotator is especially useful when working with heterogeneous input data — for example, when a dataset includes PDFs, spreadsheets, and images — allowing Spark NLP to automatically invoke the appropriate reader for each file type while preserving a unified schema in the output.

Linear Supertypes
HasReaderContent, HasTagsReaderProperties, HasXmlReaderProperties, HasHTMLReaderProperties, HasReaderProperties, HasTextReaderProperties, HasBinaryReaderProperties, HasPowerPointProperties, HasPdfReaderProperties, HasExcelReaderProperties, HasEmailReaderProperties, ParamsAndFeaturesWritable, HasFeatures, HasOutputAnnotationCol, HasOutputAnnotatorType, DefaultParamsWritable, MLWritable, Transformer, PipelineStage, Logging, Params, Serializable, Serializable, Identifiable, AnyRef, Any
Ordering
  1. Grouped
  2. Alphabetic
  3. By Inheritance
Inherited
  1. ReaderAssembler
  2. HasReaderContent
  3. HasTagsReaderProperties
  4. HasXmlReaderProperties
  5. HasHTMLReaderProperties
  6. HasReaderProperties
  7. HasTextReaderProperties
  8. HasBinaryReaderProperties
  9. HasPowerPointProperties
  10. HasPdfReaderProperties
  11. HasExcelReaderProperties
  12. HasEmailReaderProperties
  13. ParamsAndFeaturesWritable
  14. HasFeatures
  15. HasOutputAnnotationCol
  16. HasOutputAnnotatorType
  17. DefaultParamsWritable
  18. MLWritable
  19. Transformer
  20. PipelineStage
  21. Logging
  22. Params
  23. Serializable
  24. Serializable
  25. Identifiable
  26. AnyRef
  27. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Instance Constructors

  1. new ReaderAssembler()
  2. new ReaderAssembler(uid: String)

Type Members

  1. type AnnotatorType = String
    Definition Classes
    HasOutputAnnotatorType

Value Members

  1. final def !=(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  2. final def ##(): Int
    Definition Classes
    AnyRef → Any
  3. final def $[T](param: Param[T]): T
    Attributes
    protected
    Definition Classes
    Params
  4. def $$[T](feature: StructFeature[T]): T
    Attributes
    protected
    Definition Classes
    HasFeatures
  5. def $$[K, V](feature: MapFeature[K, V]): Map[K, V]
    Attributes
    protected
    Definition Classes
    HasFeatures
  6. def $$[T](feature: SetFeature[T]): Set[T]
    Attributes
    protected
    Definition Classes
    HasFeatures
  7. def $$[T](feature: ArrayFeature[T]): Array[T]
    Attributes
    protected
    Definition Classes
    HasFeatures
  8. final def ==(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  9. val addAttachmentContent: Param[Boolean]
    Definition Classes
    HasEmailReaderProperties
  10. def afterAnnotate(dataset: DataFrame): DataFrame
  11. val appendCells: Param[Boolean]
    Definition Classes
    HasExcelReaderProperties
  12. final def asInstanceOf[T0]: T0
    Definition Classes
    Any
  13. def buildEmptyDataFrame(dataset: Dataset[_]): DataFrame
    Definition Classes
    HasReaderContent
  14. def buildErrorDataFrame(dataset: Dataset[_], filePath: String, badExt: String): DataFrame
    Definition Classes
    ReaderAssembler → HasReaderContent
  15. val cellSeparator: Param[String]
    Definition Classes
    HasExcelReaderProperties
  16. final def clear(param: Param[_]): ReaderAssembler.this.type
    Definition Classes
    Params
  17. def clone(): AnyRef
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  18. val contentPath: Param[String]
    Definition Classes
    HasReaderProperties
  19. val contentType: Param[String]
    Definition Classes
    HasReaderProperties
  20. def copy(extra: ParamMap): Transformer
    Definition Classes
    ReaderAssembler → Transformer → PipelineStage → Params
  21. def copyValues[T <: Params](to: T, extra: ParamMap): T
    Attributes
    protected
    Definition Classes
    Params
  22. val customPromptTemplate: Param[String]
  23. final def defaultCopy[T <: Params](extra: ParamMap): T
    Attributes
    protected
    Definition Classes
    Params
  24. final def eq(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  25. def equals(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  26. val excludeNonText: BooleanParam
  27. def explainParam(param: Param[_]): String
    Definition Classes
    Params
  28. def explainParams(): String
    Definition Classes
    Params
  29. val explodeDocs: BooleanParam
    Definition Classes
    HasReaderProperties
  30. final def extractParamMap(): ParamMap
    Definition Classes
    Params
  31. final def extractParamMap(extra: ParamMap): ParamMap
    Definition Classes
    Params
  32. val extractTagAttributes: StringArrayParam
    Definition Classes
    HasTextReaderProperties
  33. val features: ArrayBuffer[Feature[_, _, _]]
    Definition Classes
    HasFeatures
  34. def finalize(): Unit
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  35. val flattenOutput: BooleanParam
    Definition Classes
    HasReaderProperties
  36. def get[T](feature: StructFeature[T]): Option[T]
    Attributes
    protected
    Definition Classes
    HasFeatures
  37. def get[K, V](feature: MapFeature[K, V]): Option[Map[K, V]]
    Attributes
    protected
    Definition Classes
    HasFeatures
  38. def get[T](feature: SetFeature[T]): Option[Set[T]]
    Attributes
    protected
    Definition Classes
    HasFeatures
  39. def get[T](feature: ArrayFeature[T]): Option[Array[T]]
    Attributes
    protected
    Definition Classes
    HasFeatures
  40. final def get[T](param: Param[T]): Option[T]
    Definition Classes
    Params
  41. final def getClass(): Class[_]
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  42. def getContentType: String
    Definition Classes
    HasReaderContent
  43. final def getDefault[T](param: Param[T]): Option[T]
    Definition Classes
    Params
  44. val getFileName: UserDefinedFunction
    Definition Classes
    HasReaderContent
  45. def getHeadersAsJava: Map[String, String]
    Attributes
    protected
    Definition Classes
    HasHTMLReaderProperties
  46. final def getInputCol: String
    Definition Classes
    HasReaderProperties
  47. final def getOrDefault[T](param: Param[T]): T
    Definition Classes
    Params
  48. final def getOutputCol: String

    Gets annotation column name going to generate

    Gets annotation column name going to generate

    Definition Classes
    HasOutputAnnotationCol
  49. def getParam(paramName: String): Param[Any]
    Definition Classes
    Params
  50. val groupBrokenParagraphs: Param[Boolean]
    Definition Classes
    HasTextReaderProperties
  51. final def hasDefault[T](param: Param[T]): Boolean
    Definition Classes
    Params
  52. def hasParam(paramName: String): Boolean
    Definition Classes
    Params
  53. def hashCode(): Int
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  54. val headers: Param[Map[String, String]]
    Definition Classes
    HasHTMLReaderProperties
  55. val ignoreExceptions: BooleanParam
    Definition Classes
    HasReaderProperties
  56. val ignoreUrlErrors: BooleanParam
    Definition Classes
    HasHTMLReaderProperties
  57. val includePageBreaks: Param[Boolean]
    Definition Classes
    HasReaderProperties
  58. val includeSlideNotes: Param[Boolean]
    Definition Classes
    HasPowerPointProperties
  59. val includeTitleTag: Param[Boolean]
    Definition Classes
    HasHTMLReaderProperties
  60. val inferTableStructure: Param[Boolean]
    Definition Classes
    HasReaderProperties
  61. def initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  62. def initializeLogIfNecessary(isInterpreter: Boolean): Unit
    Attributes
    protected
    Definition Classes
    Logging
  63. final val inputCol: Param[String]
    Attributes
    protected
    Definition Classes
    HasReaderProperties
  64. final def isDefined(param: Param[_]): Boolean
    Definition Classes
    Params
  65. final def isInstanceOf[T0]: Boolean
    Definition Classes
    Any
  66. final def isSet(param: Param[_]): Boolean
    Definition Classes
    Params
  67. def isTraceEnabled(): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  68. def listAllFilesRecursively(spark: SparkSession, dirPath: String): Seq[String]

    Recursively lists all files under the given path as fully-qualified path strings.

    Recursively lists all files under the given path as fully-qualified path strings.

    Local paths are listed with java.io.File (preserving previous behavior), while distributed/remote schemes such as dbfs:, s3:, and hdfs: are listed through the Hadoop org.apache.hadoop.fs.FileSystem so that mixed-content reading works on Databricks and other cluster filesystems.

    Definition Classes
    HasReaderContent
  69. def listAllFilesRecursively(dir: File): Seq[File]
    Definition Classes
    HasReaderContent
  70. def log: Logger
    Attributes
    protected
    Definition Classes
    Logging
  71. def logDebug(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  72. def logDebug(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  73. def logError(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  74. def logError(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  75. def logInfo(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  76. def logInfo(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  77. def logName: String
    Attributes
    protected
    Definition Classes
    Logging
  78. def logTrace(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  79. def logTrace(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  80. def logWarning(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  81. def logWarning(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  82. val maxLineCount: Param[Int]
    Definition Classes
    HasTextReaderProperties
  83. final def ne(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  84. final def notify(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  85. final def notifyAll(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  86. def onWrite(path: String, spark: SparkSession): Unit
    Attributes
    protected
    Definition Classes
    ParamsAndFeaturesWritable
  87. val onlyLeafNodes: Param[Boolean]
    Definition Classes
    HasXmlReaderProperties
  88. val outputAnnotatorType: AnnotatorType
    Definition Classes
    ReaderAssembler → HasOutputAnnotatorType
  89. val outputAsDocument: BooleanParam

    Whether to return all sentences joined into a single document

  90. final val outputCol: Param[String]
    Attributes
    protected
    Definition Classes
    HasOutputAnnotationCol
  91. val outputFormat: Param[String]
    Definition Classes
    HasHTMLReaderProperties
  92. val paragraphSplit: Param[String]
    Definition Classes
    HasTextReaderProperties
  93. lazy val params: Array[Param[_]]
    Definition Classes
    Params
  94. def partitionContent(partition: Partition, contentPath: String, isText: Boolean, dataset: Dataset[_]): DataFrame
    Definition Classes
    HasReaderContent
  95. def partitionContentFromPath(partition: Partition, contentPath: String, isText: Boolean, dataset: Dataset[_]): DataFrame
    Definition Classes
    HasReaderContent
  96. def partitionMixedContent(dataset: Dataset[_], dirPath: String, partitionParams: Map[String, String]): DataFrame
    Definition Classes
    HasReaderContent
  97. val promptTemplate: Param[String]
  98. final val readAsImage: BooleanParam
    Definition Classes
    HasPdfReaderProperties
  99. def retrieveFileName(path: String): String
    Definition Classes
    HasReaderContent
  100. def save(path: String): Unit
    Definition Classes
    MLWritable
    Annotations
    @Since( "1.6.0" ) @throws( ... )
  101. def set[T](feature: StructFeature[T], value: T): ReaderAssembler.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  102. def set[K, V](feature: MapFeature[K, V], value: Map[K, V]): ReaderAssembler.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  103. def set[T](feature: SetFeature[T], value: Set[T]): ReaderAssembler.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  104. def set[T](feature: ArrayFeature[T], value: Array[T]): ReaderAssembler.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  105. final def set(paramPair: ParamPair[_]): ReaderAssembler.this.type
    Attributes
    protected
    Definition Classes
    Params
  106. final def set(param: String, value: Any): ReaderAssembler.this.type
    Attributes
    protected
    Definition Classes
    Params
  107. final def set[T](param: Param[T], value: T): ReaderAssembler.this.type
    Definition Classes
    Params
  108. def setAddAttachmentContent(value: Boolean): ReaderAssembler.this.type
    Definition Classes
    HasEmailReaderProperties
  109. def setAppendCells(value: Boolean): ReaderAssembler.this.type
    Definition Classes
    HasExcelReaderProperties
  110. def setCellSeparator(value: String): ReaderAssembler.this.type
    Definition Classes
    HasExcelReaderProperties
  111. def setContentPath(value: String): ReaderAssembler.this.type
    Definition Classes
    HasReaderProperties
  112. def setContentType(value: String): ReaderAssembler.this.type
    Definition Classes
    HasReaderProperties
  113. def setCustomPromptTemplate(value: String): ReaderAssembler.this.type
  114. def setDefault[T](feature: StructFeature[T], value: () ⇒ T): ReaderAssembler.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  115. def setDefault[K, V](feature: MapFeature[K, V], value: () ⇒ Map[K, V]): ReaderAssembler.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  116. def setDefault[T](feature: SetFeature[T], value: () ⇒ Set[T]): ReaderAssembler.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  117. def setDefault[T](feature: ArrayFeature[T], value: () ⇒ Array[T]): ReaderAssembler.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  118. final def setDefault(paramPairs: ParamPair[_]*): ReaderAssembler.this.type
    Attributes
    protected
    Definition Classes
    Params
  119. final def setDefault[T](param: Param[T], value: T): ReaderAssembler.this.type
    Attributes
    protected[org.apache.spark.ml]
    Definition Classes
    Params
  120. def setExcludeNonText(value: Boolean): ReaderAssembler.this.type

    Excludes rows that are not text data.

    Excludes rows that are not text data. e.g. tables

  121. def setExplodeDocs(value: Boolean): ReaderAssembler.this.type
    Definition Classes
    HasReaderProperties
  122. def setExtractTagAttributes(attributes: Array[String]): ReaderAssembler.this.type

    Specify which tag attributes should have their values extracted as text when parsing tag-based formats (e.g., HTML or XML).

    Specify which tag attributes should have their values extracted as text when parsing tag-based formats (e.g., HTML or XML).

    attributes

    array of attribute names to extract

    returns

    this instance with the updated extractTagAttributes parameter

    Definition Classes
    HasTextReaderProperties
  123. def setFlattenOutput(value: Boolean): ReaderAssembler.this.type
    Definition Classes
    HasReaderProperties
  124. def setGroupBrokenParagraphs(value: Boolean): ReaderAssembler.this.type

    Enable or disable merging of fragmented lines into coherent paragraphs when parsing text.

    Enable or disable merging of fragmented lines into coherent paragraphs when parsing text. When enabled, heuristics based on line length and structure are used to group lines.

    value

    true to group broken paragraphs, false to preserve original line breaks

    returns

    this instance with the updated groupBrokenParagraphs parameter

    Definition Classes
    HasTextReaderProperties
  125. def setHeaders(value: Map[String, String]): ReaderAssembler.this.type
    Definition Classes
    HasHTMLReaderProperties
  126. def setHeadersPython(headers: Map[String, String]): ReaderAssembler.this.type
    Definition Classes
    HasHTMLReaderProperties
  127. def setIgnoreExceptions(value: Boolean): ReaderAssembler.this.type
    Definition Classes
    HasReaderProperties
  128. def setIgnoreUrlErrors(value: Boolean): ReaderAssembler.this.type
    Definition Classes
    HasHTMLReaderProperties
  129. def setIncludePageBreaks(value: Boolean): ReaderAssembler.this.type
    Definition Classes
    HasReaderProperties
  130. def setIncludeSlideNotes(value: Boolean): ReaderAssembler.this.type
    Definition Classes
    HasPowerPointProperties
  131. def setIncludeTitleTag(value: Boolean): ReaderAssembler.this.type
    Definition Classes
    HasHTMLReaderProperties
  132. def setInferTableStructure(value: Boolean): ReaderAssembler.this.type
    Definition Classes
    HasReaderProperties
  133. final def setInputCol(value: String): ReaderAssembler.this.type
    Definition Classes
    HasReaderProperties
  134. def setMaxLineCount(value: Int): ReaderAssembler.this.type

    Set the maximum number of lines to evaluate when estimating paragraph layout characteristics.

    Set the maximum number of lines to evaluate when estimating paragraph layout characteristics. This limits the amount of text inspected for layout heuristics.

    value

    maximum number of lines to inspect

    returns

    this instance with the updated maxLineCount parameter

    Definition Classes
    HasTextReaderProperties
  135. def setOnlyLeafNodes(value: Boolean): ReaderAssembler.this.type
    Definition Classes
    HasXmlReaderProperties
  136. def setOutputAsDocument(value: Boolean): ReaderAssembler.this.type

    Whether to return all sentences joined into a single document

  137. final def setOutputCol(value: String): ReaderAssembler.this.type

    Overrides annotation column name when transforming

    Overrides annotation column name when transforming

    Definition Classes
    HasOutputAnnotationCol
  138. def setOutputFormat(value: String): ReaderAssembler.this.type
    Definition Classes
    HasHTMLReaderProperties
  139. def setParagraphSplit(value: String): ReaderAssembler.this.type

    Set the regular expression used to detect paragraph boundaries when grouping broken paragraphs.

    Set the regular expression used to detect paragraph boundaries when grouping broken paragraphs.

    value

    regex pattern string to detect paragraph boundaries

    returns

    this instance with the updated paragraphSplit parameter

    Definition Classes
    HasTextReaderProperties
  140. def setPromptTemplate(value: String): ReaderAssembler.this.type
  141. def setShortLineWordThreshold(value: Int): ReaderAssembler.this.type

    Set the maximum number of words for a line to be considered "short" when grouping broken paragraphs.

    Set the maximum number of words for a line to be considered "short" when grouping broken paragraphs. Short lines often indicate line-wrapping within a paragraph rather than a real paragraph break.

    value

    maximum word count for a line to be considered short

    returns

    this instance with the updated shortLineWordThreshold parameter

    Definition Classes
    HasTextReaderProperties
  142. def setStoreContent(value: Boolean): ReaderAssembler.this.type
    Definition Classes
    HasReaderProperties
  143. def setThreshold(value: Double): ReaderAssembler.this.type

    Set the threshold ratio of empty lines used to decide between new line-based or broken-paragraph grouping.

    Set the threshold ratio of empty lines used to decide between new line-based or broken-paragraph grouping. Lower values make it easier to choose broken-paragraph grouping.

    value

    ratio between 0.0 and 1.0 representing the empty-line threshold

    returns

    this instance with the updated threshold parameter

    Definition Classes
    HasTextReaderProperties
  144. def setTimeout(value: Int): ReaderAssembler.this.type
    Definition Classes
    HasHTMLReaderProperties
  145. def setTitleFontSize(value: Int): ReaderAssembler.this.type
    Definition Classes
    HasReaderProperties
  146. def setTitleLengthSize(value: Int): ReaderAssembler.this.type

    Set the maximum character length used to determine if a text block qualifies as a title during parsing.

    Set the maximum character length used to determine if a text block qualifies as a title during parsing.

    value

    maximum number of characters to treat a block as a title

    returns

    this instance with the updated titleLengthSize parameter

    Definition Classes
    HasTextReaderProperties
  147. def setTitleThreshold(value: Double): ReaderAssembler.this.type
    Definition Classes
    HasPdfReaderProperties
  148. def setUseEncodedImageBytes(value: Boolean): ReaderAssembler.this.type
  149. def setUserMessage(value: String): ReaderAssembler.this.type
  150. def setXmlKeepTags(value: Boolean): ReaderAssembler.this.type
    Definition Classes
    HasXmlReaderProperties
  151. val shortLineWordThreshold: Param[Int]
    Definition Classes
    HasTextReaderProperties
  152. val storeContent: Param[Boolean]
    Definition Classes
    HasReaderProperties
  153. val supportedTypes: Map[String, (String, Boolean)]
    Definition Classes
    ReaderAssembler → HasReaderContent
  154. final def synchronized[T0](arg0: ⇒ T0): T0
    Definition Classes
    AnyRef
  155. val threshold: Param[Double]
    Definition Classes
    HasTextReaderProperties
  156. val timeout: Param[Int]
    Definition Classes
    HasHTMLReaderProperties
  157. val titleFontSize: Param[Int]
    Definition Classes
    HasReaderProperties
  158. val titleLengthSize: Param[Int]
    Definition Classes
    HasTextReaderProperties
  159. val titleThreshold: Param[Double]
    Definition Classes
    HasPdfReaderProperties
  160. def toString(): String
    Definition Classes
    Identifiable → AnyRef → Any
  161. def transform(dataset: Dataset[_]): DataFrame
    Definition Classes
    ReaderAssembler → Transformer
  162. def transform(dataset: Dataset[_], paramMap: ParamMap): DataFrame
    Definition Classes
    Transformer
    Annotations
    @Since( "2.0.0" )
  163. def transform(dataset: Dataset[_], firstParamPair: ParamPair[_], otherParamPairs: ParamPair[_]*): DataFrame
    Definition Classes
    Transformer
    Annotations
    @Since( "2.0.0" ) @varargs()
  164. def transformSchema(schema: StructType): StructType
    Definition Classes
    ReaderAssembler → PipelineStage
  165. def transformSchema(schema: StructType, logging: Boolean): StructType
    Attributes
    protected
    Definition Classes
    PipelineStage
    Annotations
    @DeveloperApi()
  166. val uid: String
    Definition Classes
    ReaderAssembler → Identifiable
  167. val useEncodedImageBytes: Param[Boolean]
  168. val userMessage: Param[String]
  169. def validateRequiredParameters(): Unit
    Attributes
    protected
  170. final def wait(): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  171. final def wait(arg0: Long, arg1: Int): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  172. final def wait(arg0: Long): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  173. def write: MLWriter
    Definition Classes
    ParamsAndFeaturesWritable → DefaultParamsWritable → MLWritable
  174. val xmlKeepTags: Param[Boolean]
    Definition Classes
    HasXmlReaderProperties

Inherited from HasReaderContent

Inherited from HasTagsReaderProperties

Inherited from HasXmlReaderProperties

Inherited from HasHTMLReaderProperties

Inherited from HasReaderProperties

Inherited from HasTextReaderProperties

Inherited from HasBinaryReaderProperties

Inherited from HasPowerPointProperties

Inherited from HasPdfReaderProperties

Inherited from HasExcelReaderProperties

Inherited from HasEmailReaderProperties

Inherited from ParamsAndFeaturesWritable

Inherited from HasFeatures

Inherited from HasOutputAnnotationCol

Inherited from HasOutputAnnotatorType

Inherited from DefaultParamsWritable

Inherited from MLWritable

Inherited from Transformer

Inherited from PipelineStage

Inherited from Logging

Inherited from Params

Inherited from Serializable

Inherited from Serializable

Inherited from Identifiable

Inherited from AnyRef

Inherited from Any

param

Ungrouped