class Reader2Table extends Reader2Doc

The Reader2Table annotator allows you to use the reading files more smoothly within existing Spark NLP workflows, enabling seamless reuse of your pipelines. Reader2Table can be used for extracting structured content from various document types using Spark NLP readers. It supports reading from many files types and returns parsed output as a structured Spark DataFrame.

Supported formats include plain text, HTML, Word (.doc/.docx), ODT (.odt), Excel (.xls/.xlsx), PowerPoint (.ppt/.pptx)

Example

import com.johnsnowlabs.reader.Reader2Table
import com. johnsnowlabs.nlp.base.DocumentAssembler
import org.apache.spark.ml.Pipeline

val reader2Table = new Reader2Table()
  .setContentType("application/csv")
  .setContentPath(s"$pdfDirectory/")

val pipeline = new Pipeline()
  .setStages(Array(reader2Table))

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

resultDf.show()
+----------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
|fileName        |document                                                                                                                                                                                    |
+----------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
|stanley-cups.csv|[{document, 0, 137, {"caption":"","header":[],"rows":[["Team","Location","Stanley Cups"],["Blues","STL","1"],["Flyers","PHI","2"],["Maple Leafs","TOR","13"]]}, {elementType -> Table}, []}]|
+----------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
Linear Supertypes
Reader2Doc, 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. Reader2Table
  2. Reader2Doc
  3. HasReaderContent
  4. HasTagsReaderProperties
  5. HasXmlReaderProperties
  6. HasHTMLReaderProperties
  7. HasReaderProperties
  8. HasTextReaderProperties
  9. HasBinaryReaderProperties
  10. HasPowerPointProperties
  11. HasPdfReaderProperties
  12. HasExcelReaderProperties
  13. HasEmailReaderProperties
  14. ParamsAndFeaturesWritable
  15. HasFeatures
  16. HasOutputAnnotationCol
  17. HasOutputAnnotatorType
  18. DefaultParamsWritable
  19. MLWritable
  20. Transformer
  21. PipelineStage
  22. Logging
  23. Params
  24. Serializable
  25. Serializable
  26. Identifiable
  27. AnyRef
  28. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Instance Constructors

  1. new Reader2Table()
  2. new Reader2Table(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
    Definition Classes
    Reader2Doc
  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[_], contentPath: String, ext: String): DataFrame
    Definition Classes
    HasReaderContent
  15. val cellSeparator: Param[String]
    Definition Classes
    HasExcelReaderProperties
  16. final def clear(param: Param[_]): Reader2Table.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
    Reader2Doc → Transformer → PipelineStage → Params
  21. def copyValues[T <: Params](to: T, extra: ParamMap): T
    Attributes
    protected
    Definition Classes
    Params
  22. final def defaultCopy[T <: Params](extra: ParamMap): T
    Attributes
    protected
    Definition Classes
    Params
  23. final def eq(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  24. def equals(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  25. val excludeNonText: BooleanParam
    Definition Classes
    Reader2Doc
  26. def explainParam(param: Param[_]): String
    Definition Classes
    Params
  27. def explainParams(): String
    Definition Classes
    Params
  28. val explodeDocs: BooleanParam
    Definition Classes
    HasReaderProperties
  29. final def extractParamMap(): ParamMap
    Definition Classes
    Params
  30. final def extractParamMap(extra: ParamMap): ParamMap
    Definition Classes
    Params
  31. val extractTagAttributes: StringArrayParam
    Definition Classes
    HasTextReaderProperties
  32. val features: ArrayBuffer[Feature[_, _, _]]
    Definition Classes
    HasFeatures
  33. def finalize(): Unit
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  34. val flattenOutput: BooleanParam
    Definition Classes
    HasReaderProperties
  35. def get[T](feature: StructFeature[T]): Option[T]
    Attributes
    protected
    Definition Classes
    HasFeatures
  36. def get[K, V](feature: MapFeature[K, V]): Option[Map[K, V]]
    Attributes
    protected
    Definition Classes
    HasFeatures
  37. def get[T](feature: SetFeature[T]): Option[Set[T]]
    Attributes
    protected
    Definition Classes
    HasFeatures
  38. def get[T](feature: ArrayFeature[T]): Option[Array[T]]
    Attributes
    protected
    Definition Classes
    HasFeatures
  39. final def get[T](param: Param[T]): Option[T]
    Definition Classes
    Params
  40. final def getClass(): Class[_]
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  41. def getContentType: String
    Definition Classes
    HasReaderContent
  42. final def getDefault[T](param: Param[T]): Option[T]
    Definition Classes
    Params
  43. val getFileName: UserDefinedFunction
    Definition Classes
    HasReaderContent
  44. final def getInputCol: String
    Definition Classes
    HasReaderProperties
  45. final def getOrDefault[T](param: Param[T]): T
    Definition Classes
    Params
  46. final def getOutputCol: String

    Gets annotation column name going to generate

    Gets annotation column name going to generate

    Definition Classes
    HasOutputAnnotationCol
  47. def getParam(paramName: String): Param[Any]
    Definition Classes
    Params
  48. val groupBrokenParagraphs: Param[Boolean]
    Definition Classes
    HasTextReaderProperties
  49. final def hasDefault[T](param: Param[T]): Boolean
    Definition Classes
    Params
  50. def hasParam(paramName: String): Boolean
    Definition Classes
    Params
  51. def hashCode(): Int
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  52. val headers: Param[Map[String, String]]
    Definition Classes
    HasHTMLReaderProperties
  53. val ignoreExceptions: BooleanParam
    Definition Classes
    HasReaderProperties
  54. val ignoreUrlErrors: BooleanParam
    Definition Classes
    HasHTMLReaderProperties
  55. val includePageBreaks: Param[Boolean]
    Definition Classes
    HasReaderProperties
  56. val includeSlideNotes: Param[Boolean]
    Definition Classes
    HasPowerPointProperties
  57. val includeTitleTag: Param[Boolean]
    Definition Classes
    HasHTMLReaderProperties
  58. val inferTableStructure: Param[Boolean]
    Definition Classes
    HasReaderProperties
  59. def initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  60. def initializeLogIfNecessary(isInterpreter: Boolean): Unit
    Attributes
    protected
    Definition Classes
    Logging
  61. final val inputCol: Param[String]
    Attributes
    protected
    Definition Classes
    HasReaderProperties
  62. final def isDefined(param: Param[_]): Boolean
    Definition Classes
    Params
  63. final def isInstanceOf[T0]: Boolean
    Definition Classes
    Any
  64. final def isSet(param: Param[_]): Boolean
    Definition Classes
    Params
  65. def isTraceEnabled(): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  66. val joinString: Param[String]
    Definition Classes
    Reader2Doc
  67. def listAllFilesRecursively(dir: File): Seq[File]
    Definition Classes
    HasReaderContent
  68. def log: Logger
    Attributes
    protected
    Definition Classes
    Logging
  69. def logDebug(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  70. def logDebug(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  71. def logError(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  72. def logError(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  73. def logInfo(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  74. def logInfo(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  75. def logName: String
    Attributes
    protected
    Definition Classes
    Logging
  76. def logTrace(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  77. def logTrace(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  78. def logWarning(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  79. def logWarning(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  80. val maxLineCount: Param[Int]
    Definition Classes
    HasTextReaderProperties
  81. final def ne(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  82. final def notify(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  83. final def notifyAll(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  84. def onWrite(path: String, spark: SparkSession): Unit
    Attributes
    protected
    Definition Classes
    ParamsAndFeaturesWritable
  85. val onlyLeafNodes: Param[Boolean]
    Definition Classes
    HasXmlReaderProperties
  86. val outputAnnotatorType: AnnotatorType
    Definition Classes
    Reader2Doc → HasOutputAnnotatorType
  87. val outputAsDocument: BooleanParam

    Whether to return all sentences joined into a single document

    Whether to return all sentences joined into a single document

    Definition Classes
    Reader2Doc
  88. final val outputCol: Param[String]
    Attributes
    protected
    Definition Classes
    HasOutputAnnotationCol
  89. val outputFormat: Param[String]
    Definition Classes
    HasHTMLReaderProperties
  90. val paragraphSplit: Param[String]
    Definition Classes
    HasTextReaderProperties
  91. lazy val params: Array[Param[_]]
    Definition Classes
    Params
  92. def partitionBuilder: Partition
    Attributes
    protected
    Definition Classes
    Reader2Doc
  93. def partitionContent(partition: Partition, contentPath: String, isText: Boolean, dataset: Dataset[_]): DataFrame
    Definition Classes
    HasReaderContent
  94. def partitionContentFromPath(partition: Partition, contentPath: String, isText: Boolean, dataset: Dataset[_]): DataFrame
    Definition Classes
    HasReaderContent
  95. def partitionMixedContent(dataset: Dataset[_], dirPath: String, partitionParams: Map[String, String]): DataFrame
    Definition Classes
    HasReaderContent
  96. def partitionToAnnotation: UserDefinedFunction
    Definition Classes
    Reader2Table → Reader2Doc
  97. final val readAsImage: BooleanParam
    Definition Classes
    HasPdfReaderProperties
  98. def retrieveFileName(path: String): String
    Definition Classes
    HasReaderContent
  99. def save(path: String): Unit
    Definition Classes
    MLWritable
    Annotations
    @Since( "1.6.0" ) @throws( ... )
  100. def set[T](feature: StructFeature[T], value: T): Reader2Table.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  101. def set[K, V](feature: MapFeature[K, V], value: Map[K, V]): Reader2Table.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  102. def set[T](feature: SetFeature[T], value: Set[T]): Reader2Table.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  103. def set[T](feature: ArrayFeature[T], value: Array[T]): Reader2Table.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  104. final def set(paramPair: ParamPair[_]): Reader2Table.this.type
    Attributes
    protected
    Definition Classes
    Params
  105. final def set(param: String, value: Any): Reader2Table.this.type
    Attributes
    protected
    Definition Classes
    Params
  106. final def set[T](param: Param[T], value: T): Reader2Table.this.type
    Definition Classes
    Params
  107. def setAddAttachmentContent(value: Boolean): Reader2Table.this.type
    Definition Classes
    HasEmailReaderProperties
  108. def setAppendCells(value: Boolean): Reader2Table.this.type
    Definition Classes
    HasExcelReaderProperties
  109. def setCellSeparator(value: String): Reader2Table.this.type
    Definition Classes
    HasExcelReaderProperties
  110. def setContentPath(value: String): Reader2Table.this.type
    Definition Classes
    HasReaderProperties
  111. def setContentType(value: String): Reader2Table.this.type
    Definition Classes
    HasReaderProperties
  112. def setDefault[T](feature: StructFeature[T], value: () ⇒ T): Reader2Table.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  113. def setDefault[K, V](feature: MapFeature[K, V], value: () ⇒ Map[K, V]): Reader2Table.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  114. def setDefault[T](feature: SetFeature[T], value: () ⇒ Set[T]): Reader2Table.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  115. def setDefault[T](feature: ArrayFeature[T], value: () ⇒ Array[T]): Reader2Table.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  116. final def setDefault(paramPairs: ParamPair[_]*): Reader2Table.this.type
    Attributes
    protected
    Definition Classes
    Params
  117. final def setDefault[T](param: Param[T], value: T): Reader2Table.this.type
    Attributes
    protected[org.apache.spark.ml]
    Definition Classes
    Params
  118. def setExcludeNonText(value: Boolean): Reader2Table.this.type

    Excludes rows that are not text data.

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

    Definition Classes
    Reader2Doc
  119. def setExplodeDocs(value: Boolean): Reader2Table.this.type
    Definition Classes
    HasReaderProperties
  120. def setExtractTagAttributes(attributes: Array[String]): Reader2Table.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
  121. def setFlattenOutput(value: Boolean): Reader2Table.this.type
    Definition Classes
    HasReaderProperties
  122. def setGroupBrokenParagraphs(value: Boolean): Reader2Table.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
  123. def setHeaders(value: Map[String, String]): Reader2Table.this.type
    Definition Classes
    HasHTMLReaderProperties
  124. def setHeadersPython(headers: Map[String, String]): Reader2Table.this.type
    Definition Classes
    HasHTMLReaderProperties
  125. def setIgnoreExceptions(value: Boolean): Reader2Table.this.type
    Definition Classes
    HasReaderProperties
  126. def setIgnoreUrlErrors(value: Boolean): Reader2Table.this.type
    Definition Classes
    HasHTMLReaderProperties
  127. def setIncludePageBreaks(value: Boolean): Reader2Table.this.type
    Definition Classes
    HasReaderProperties
  128. def setIncludeSlideNotes(value: Boolean): Reader2Table.this.type
    Definition Classes
    HasPowerPointProperties
  129. def setIncludeTitleTag(value: Boolean): Reader2Table.this.type
    Definition Classes
    HasHTMLReaderProperties
  130. def setInferTableStructure(value: Boolean): Reader2Table.this.type
    Definition Classes
    HasReaderProperties
  131. final def setInputCol(value: String): Reader2Table.this.type
    Definition Classes
    HasReaderProperties
  132. def setJoinString(value: String): Reader2Table.this.type

    If outputAsDocument is true, specifies the string used to join elements into a single

    If outputAsDocument is true, specifies the string used to join elements into a single

    Definition Classes
    Reader2Doc
  133. def setMaxLineCount(value: Int): Reader2Table.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
  134. def setOnlyLeafNodes(value: Boolean): Reader2Table.this.type
    Definition Classes
    HasXmlReaderProperties
  135. def setOutputAsDocument(value: Boolean): Reader2Table.this.type

    Whether to return all sentences joined into a single document

    Whether to return all sentences joined into a single document

    Definition Classes
    Reader2Doc
  136. final def setOutputCol(value: String): Reader2Table.this.type

    Overrides annotation column name when transforming

    Overrides annotation column name when transforming

    Definition Classes
    HasOutputAnnotationCol
  137. def setOutputFormat(value: String): Reader2Table.this.type
    Definition Classes
    HasHTMLReaderProperties
  138. def setParagraphSplit(value: String): Reader2Table.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
  139. def setShortLineWordThreshold(value: Int): Reader2Table.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
  140. def setStoreContent(value: Boolean): Reader2Table.this.type
    Definition Classes
    HasReaderProperties
  141. def setThreshold(value: Double): Reader2Table.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
  142. def setTimeout(value: Int): Reader2Table.this.type
    Definition Classes
    HasHTMLReaderProperties
  143. def setTitleFontSize(value: Int): Reader2Table.this.type
    Definition Classes
    HasReaderProperties
  144. def setTitleLengthSize(value: Int): Reader2Table.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
  145. def setTitleThreshold(value: Double): Reader2Table.this.type
    Definition Classes
    HasPdfReaderProperties
  146. def setXmlKeepTags(value: Boolean): Reader2Table.this.type
    Definition Classes
    HasXmlReaderProperties
  147. val shortLineWordThreshold: Param[Int]
    Definition Classes
    HasTextReaderProperties
  148. val storeContent: Param[Boolean]
    Definition Classes
    HasReaderProperties
  149. val supportedTypes: Map[String, (String, Boolean)]
    Definition Classes
    HasReaderContent
  150. final def synchronized[T0](arg0: ⇒ T0): T0
    Definition Classes
    AnyRef
  151. val threshold: Param[Double]
    Definition Classes
    HasTextReaderProperties
  152. val timeout: Param[Int]
    Definition Classes
    HasHTMLReaderProperties
  153. val titleFontSize: Param[Int]
    Definition Classes
    HasReaderProperties
  154. val titleLengthSize: Param[Int]
    Definition Classes
    HasTextReaderProperties
  155. val titleThreshold: Param[Double]
    Definition Classes
    HasPdfReaderProperties
  156. def toString(): String
    Definition Classes
    Identifiable → AnyRef → Any
  157. def transform(dataset: Dataset[_]): DataFrame
    Definition Classes
    Reader2Table → Reader2Doc → Transformer
  158. def transform(dataset: Dataset[_], paramMap: ParamMap): DataFrame
    Definition Classes
    Transformer
    Annotations
    @Since( "2.0.0" )
  159. def transform(dataset: Dataset[_], firstParamPair: ParamPair[_], otherParamPairs: ParamPair[_]*): DataFrame
    Definition Classes
    Transformer
    Annotations
    @Since( "2.0.0" ) @varargs()
  160. def transformSchema(schema: StructType): StructType
    Definition Classes
    Reader2Doc → PipelineStage
  161. def transformSchema(schema: StructType, logging: Boolean): StructType
    Attributes
    protected
    Definition Classes
    PipelineStage
    Annotations
    @DeveloperApi()
  162. val uid: String
    Definition Classes
    Reader2Table → Reader2Doc → Identifiable
  163. def validateRequiredParameters(): Unit
    Definition Classes
    Reader2Table → Reader2Doc
  164. final def wait(): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  165. final def wait(arg0: Long, arg1: Int): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  166. final def wait(arg0: Long): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  167. def write: MLWriter
    Definition Classes
    ParamsAndFeaturesWritable → DefaultParamsWritable → MLWritable
  168. val xmlKeepTags: Param[Boolean]
    Definition Classes
    HasXmlReaderProperties

Inherited from Reader2Doc

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