class PowerPointReader extends Serializable
Class to read and parse PowerPoint files.
Linear Supertypes
Ordering
- Alphabetic
- By Inheritance
Inherited
- PowerPointReader
- Serializable
- Serializable
- AnyRef
- Any
- Hide All
- Show All
Visibility
- Public
- All
Instance Constructors
-
new
PowerPointReader(storeContent: Boolean = false, inferTableStructure: Boolean = false, includeSlideNotes: Boolean = false)
- storeContent
Whether to include the raw file content in the output DataFrame as a separate 'content' column, alongside the structured output. The default value is false.
- inferTableStructure
Whether to generate an HTML table representation from structured table content. When enabled, a full
element is added alongside cell-level elements, based on row and column layout. The default value is false.
- includeSlideNotes
Whether to extract speaker notes from slides. When enabled, notes are included as narrative text elements. The default value is false. docPath: this is a path to a directory of Excel files or a path to an HTML file E.g. "path/power-point/files"
Example
val path = "./ppt-files/fake-power-point.pptx" val powerPointReader = new PowerPointReader() val pptDf = powerPointReader.ppt(path)
pptDf.show() +--------------------+--------------------+ | path| ppt| +--------------------+--------------------+ |file:/content/ppt...|[{Title, Adding a...| +--------------------+--------------------+ pptDf.printSchema() root |-- path: string (nullable = true) |-- ppt: array (nullable = true) | |-- element: struct (containsNull = true) | | |-- elementType: string (nullable = true) | | |-- content: string (nullable = true) | | |-- metadata: map (nullable = true) | | | |-- key: string | | | |-- value: string (valueContainsNull = true)For more examples please refer to this notebook.
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
-
final
def
asInstanceOf[T0]: T0
- Definition Classes
- Any
-
def
clone(): AnyRef
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws( ... ) @native()
-
final
def
eq(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
-
def
equals(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
-
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()
- def getOutputColumn: String
-
def
hashCode(): Int
- Definition Classes
- AnyRef → Any
- Annotations
- @native()
-
final
def
isInstanceOf[T0]: Boolean
- Definition Classes
- Any
-
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()
-
def
ppt(filePath: String): DataFrame
- filePath
this is a path to a directory of ppt files or a path to an ppt file E.g. "path/ppts/files"
- returns
Dataframe with parsed power point content.
- def pptToHTMLElement(content: Array[Byte]): Seq[HTMLElement]
- def setOutputColumn(value: String): PowerPointReader.this.type
-
final
def
synchronized[T0](arg0: ⇒ T0): T0
- Definition Classes
- AnyRef
- val titleFontSizeThreshold: Int
-
def
toString(): String
- Definition Classes
- AnyRef → Any
-
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()
Ungrouped