Packages

c

com.johnsnowlabs.reader.util.pdf

PDFLayoutTextStripper

class PDFLayoutTextStripper extends PDFTextStripper

Java doc to be completed

Linear Supertypes
PDFTextStripper, LegacyPDFStreamEngine, PDFStreamEngine, AnyRef, Any
Ordering
  1. Alphabetic
  2. By Inheritance
Inherited
  1. PDFLayoutTextStripper
  2. PDFTextStripper
  3. LegacyPDFStreamEngine
  4. PDFStreamEngine
  5. AnyRef
  6. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Instance Constructors

  1. new PDFLayoutTextStripper()

Value Members

  1. final def !=(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  2. final def ##(): Int
    Definition Classes
    AnyRef → Any
  3. final def ==(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  4. final def addOperator(arg0: OperatorProcessor): Unit
    Definition Classes
    PDFStreamEngine
  5. def applyTextAdjustment(arg0: Float, arg1: Float): Unit
    Attributes
    protected[contentstream]
    Definition Classes
    PDFStreamEngine
    Annotations
    @throws( classOf[java.io.IOException] )
  6. final def asInstanceOf[T0]: T0
    Definition Classes
    Any
  7. def beginMarkedContentSequence(arg0: COSName, arg1: COSDictionary): Unit
    Definition Classes
    PDFStreamEngine
  8. def beginText(): Unit
    Definition Classes
    PDFStreamEngine
    Annotations
    @throws( classOf[java.io.IOException] )
  9. def clone(): AnyRef
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  10. def computeFontHeight(arg0: PDFont): Float
    Attributes
    protected[text]
    Definition Classes
    LegacyPDFStreamEngine
    Annotations
    @throws( classOf[java.io.IOException] )
  11. def decreaseLevel(): Unit
    Definition Classes
    PDFStreamEngine
  12. def endArticle(): Unit
    Attributes
    protected[text]
    Definition Classes
    PDFTextStripper
    Annotations
    @throws( classOf[java.io.IOException] )
  13. def endDocument(arg0: PDDocument): Unit
    Attributes
    protected[text]
    Definition Classes
    PDFTextStripper
    Annotations
    @throws( classOf[java.io.IOException] )
  14. def endMarkedContentSequence(): Unit
    Definition Classes
    PDFStreamEngine
  15. def endPage(arg0: PDPage): Unit
    Attributes
    protected[text]
    Definition Classes
    PDFTextStripper
    Annotations
    @throws( classOf[java.io.IOException] )
  16. def endText(): Unit
    Definition Classes
    PDFStreamEngine
    Annotations
    @throws( classOf[java.io.IOException] )
  17. final def eq(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  18. def equals(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  19. def finalize(): Unit
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  20. def getAddMoreFormatting(): Boolean
    Definition Classes
    PDFTextStripper
  21. def getAppearance(arg0: PDAnnotation): PDAppearanceStream
    Definition Classes
    PDFStreamEngine
  22. def getArticleEnd(): String
    Definition Classes
    PDFTextStripper
  23. def getArticleStart(): String
    Definition Classes
    PDFTextStripper
  24. def getAverageCharTolerance(): Float
    Definition Classes
    PDFTextStripper
  25. def getCharactersByArticle(): List[List[TextPosition]]
    Attributes
    protected[text]
    Definition Classes
    PDFTextStripper
  26. final def getClass(): Class[_]
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  27. def getCurrentPage(): PDPage
    Definition Classes
    PDFStreamEngine
  28. def getCurrentPageNo(): Int
    Attributes
    protected[text]
    Definition Classes
    PDFTextStripper
  29. def getDropThreshold(): Float
    Definition Classes
    PDFTextStripper
  30. def getEndBookmark(): PDOutlineItem
    Definition Classes
    PDFTextStripper
  31. def getEndPage(): Int
    Definition Classes
    PDFTextStripper
  32. def getGraphicsStackSize(): Int
    Definition Classes
    PDFStreamEngine
  33. def getGraphicsState(): PDGraphicsState
    Definition Classes
    PDFStreamEngine
  34. def getIndentThreshold(): Float
    Definition Classes
    PDFTextStripper
  35. def getInitialMatrix(): Matrix
    Definition Classes
    PDFStreamEngine
  36. def getLevel(): Int
    Definition Classes
    PDFStreamEngine
  37. def getLineSeparator(): String
    Definition Classes
    PDFTextStripper
  38. def getListItemPatterns(): List[Pattern]
    Attributes
    protected[text]
    Definition Classes
    PDFTextStripper
  39. def getOutput(): Writer
    Attributes
    protected[text]
    Definition Classes
    PDFTextStripper
  40. def getPageEnd(): String
    Definition Classes
    PDFTextStripper
  41. def getPageStart(): String
    Definition Classes
    PDFTextStripper
  42. def getParagraphEnd(): String
    Definition Classes
    PDFTextStripper
  43. def getParagraphStart(): String
    Definition Classes
    PDFTextStripper
  44. def getResources(): PDResources
    Definition Classes
    PDFStreamEngine
  45. def getSeparateByBeads(): Boolean
    Definition Classes
    PDFTextStripper
  46. def getSortByPosition(): Boolean
    Definition Classes
    PDFTextStripper
  47. def getSpacingTolerance(): Float
    Definition Classes
    PDFTextStripper
  48. def getStartBookmark(): PDOutlineItem
    Definition Classes
    PDFTextStripper
  49. def getStartPage(): Int
    Definition Classes
    PDFTextStripper
  50. def getSuppressDuplicateOverlappingText(): Boolean
    Definition Classes
    PDFTextStripper
  51. def getText(pmatrix: PageMatrix, pageWidth: Float, pageHeight: Float): String
  52. def getText(arg0: PDDocument): String
    Definition Classes
    PDFTextStripper
    Annotations
    @throws( classOf[java.io.IOException] )
  53. def getTextLineMatrix(): Matrix
    Definition Classes
    PDFStreamEngine
  54. def getTextMatrix(): Matrix
    Definition Classes
    PDFStreamEngine
  55. def getWordSeparator(): String
    Definition Classes
    PDFTextStripper
  56. def hashCode(): Int
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  57. def increaseLevel(): Unit
    Definition Classes
    PDFStreamEngine
  58. final def isInstanceOf[T0]: Boolean
    Definition Classes
    Any
  59. final def ne(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  60. final def notify(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  61. final def notifyAll(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  62. def operatorException(arg0: Operator, arg1: List[COSBase], arg2: IOException): Unit
    Attributes
    protected[contentstream]
    Definition Classes
    PDFStreamEngine
    Annotations
    @throws( classOf[java.io.IOException] )
  63. def processAnnotation(arg0: PDAnnotation, arg1: PDAppearanceStream): Unit
    Attributes
    protected[contentstream]
    Definition Classes
    PDFStreamEngine
    Annotations
    @throws( classOf[java.io.IOException] )
  64. def processChildStream(arg0: PDContentStream, arg1: PDPage): Unit
    Attributes
    protected[contentstream]
    Definition Classes
    PDFStreamEngine
    Annotations
    @throws( classOf[java.io.IOException] )
  65. def processOperator(arg0: Operator, arg1: List[COSBase]): Unit
    Attributes
    protected[contentstream]
    Definition Classes
    PDFStreamEngine
    Annotations
    @throws( classOf[java.io.IOException] )
  66. def processOperator(arg0: String, arg1: List[COSBase]): Unit
    Definition Classes
    PDFStreamEngine
    Annotations
    @throws( classOf[java.io.IOException] )
  67. def processPage(page: PDPage): Unit

    page

    page to parse

    Definition Classes
    PDFLayoutTextStripper → PDFTextStripper → LegacyPDFStreamEngine → PDFStreamEngine
    Annotations
    @Override()
  68. def processPages(arg0: PDPageTree): Unit
    Attributes
    protected[text]
    Definition Classes
    PDFTextStripper
    Annotations
    @throws( classOf[java.io.IOException] )
  69. def processSoftMask(arg0: PDTransparencyGroup): Unit
    Attributes
    protected[contentstream]
    Definition Classes
    PDFStreamEngine
    Annotations
    @throws( classOf[java.io.IOException] )
  70. def processTextPosition(arg0: TextPosition): Unit
    Attributes
    protected[text]
    Definition Classes
    PDFTextStripper → LegacyPDFStreamEngine
  71. final def processTilingPattern(arg0: PDTilingPattern, arg1: PDColor, arg2: PDColorSpace, arg3: Matrix): Unit
    Attributes
    protected[contentstream]
    Definition Classes
    PDFStreamEngine
    Annotations
    @throws( classOf[java.io.IOException] )
  72. final def processTilingPattern(arg0: PDTilingPattern, arg1: PDColor, arg2: PDColorSpace): Unit
    Attributes
    protected[contentstream]
    Definition Classes
    PDFStreamEngine
    Annotations
    @throws( classOf[java.io.IOException] )
  73. def processTransparencyGroup(arg0: PDTransparencyGroup): Unit
    Attributes
    protected[contentstream]
    Definition Classes
    PDFStreamEngine
    Annotations
    @throws( classOf[java.io.IOException] )
  74. def processType3Stream(arg0: PDType3CharProc, arg1: Matrix): Unit
    Attributes
    protected[contentstream]
    Definition Classes
    PDFStreamEngine
    Annotations
    @throws( classOf[java.io.IOException] )
  75. final def restoreGraphicsStack(arg0: Deque[PDGraphicsState]): Unit
    Attributes
    protected[contentstream]
    Definition Classes
    PDFStreamEngine
  76. def restoreGraphicsState(): Unit
    Definition Classes
    PDFStreamEngine
  77. final def saveGraphicsStack(): Deque[PDGraphicsState]
    Attributes
    protected[contentstream]
    Definition Classes
    PDFStreamEngine
  78. def saveGraphicsState(): Unit
    Definition Classes
    PDFStreamEngine
  79. def setAddMoreFormatting(arg0: Boolean): Unit
    Definition Classes
    PDFTextStripper
  80. def setArticleEnd(arg0: String): Unit
    Definition Classes
    PDFTextStripper
  81. def setArticleStart(arg0: String): Unit
    Definition Classes
    PDFTextStripper
  82. def setAverageCharTolerance(arg0: Float): Unit
    Definition Classes
    PDFTextStripper
  83. def setCurrentPageWidth(currentPageWidth: Double): Unit
  84. def setDropThreshold(arg0: Float): Unit
    Definition Classes
    PDFTextStripper
  85. def setEndBookmark(arg0: PDOutlineItem): Unit
    Definition Classes
    PDFTextStripper
  86. def setEndPage(arg0: Int): Unit
    Definition Classes
    PDFTextStripper
  87. def setIndentThreshold(arg0: Float): Unit
    Definition Classes
    PDFTextStripper
  88. def setIsSort(sort: Boolean): Unit
  89. def setLineDashPattern(arg0: COSArray, arg1: Int): Unit
    Definition Classes
    PDFStreamEngine
  90. def setLineSeparator(arg0: String): Unit
    Definition Classes
    PDFTextStripper
  91. def setListItemPatterns(arg0: List[Pattern]): Unit
    Attributes
    protected[text]
    Definition Classes
    PDFTextStripper
  92. def setPageEnd(arg0: String): Unit
    Definition Classes
    PDFTextStripper
  93. def setPageStart(arg0: String): Unit
    Definition Classes
    PDFTextStripper
  94. def setParagraphEnd(arg0: String): Unit
    Definition Classes
    PDFTextStripper
  95. def setParagraphStart(arg0: String): Unit
    Definition Classes
    PDFTextStripper
  96. def setShouldSeparateByBeads(arg0: Boolean): Unit
    Definition Classes
    PDFTextStripper
  97. def setSortByPosition(arg0: Boolean): Unit
    Definition Classes
    PDFTextStripper
  98. def setSpacingTolerance(arg0: Float): Unit
    Definition Classes
    PDFTextStripper
  99. def setStartBookmark(arg0: PDOutlineItem): Unit
    Definition Classes
    PDFTextStripper
  100. def setStartPage(arg0: Int): Unit
    Definition Classes
    PDFTextStripper
  101. def setSuppressDuplicateOverlappingText(arg0: Boolean): Unit
    Definition Classes
    PDFTextStripper
  102. def setTextLineMatrix(arg0: Matrix): Unit
    Definition Classes
    PDFStreamEngine
  103. def setTextMatrix(arg0: Matrix): Unit
    Definition Classes
    PDFStreamEngine
  104. def setWordSeparator(arg0: String): Unit
    Definition Classes
    PDFTextStripper
  105. def showAnnotation(arg0: PDAnnotation): Unit
    Definition Classes
    PDFStreamEngine
    Annotations
    @throws( classOf[java.io.IOException] )
  106. def showFontGlyph(arg0: Matrix, arg1: PDFont, arg2: Int, arg3: Vector): Unit
    Attributes
    protected[contentstream]
    Definition Classes
    PDFStreamEngine
    Annotations
    @throws( classOf[java.io.IOException] )
  107. def showFontGlyph(arg0: Matrix, arg1: PDFont, arg2: Int, arg3: String, arg4: Vector): Unit
    Attributes
    protected[contentstream]
    Definition Classes
    PDFStreamEngine
    Annotations
    @throws( classOf[java.io.IOException] )
  108. def showForm(arg0: PDFormXObject): Unit
    Definition Classes
    PDFStreamEngine
    Annotations
    @throws( classOf[java.io.IOException] )
  109. def showGlyph(arg0: Matrix, arg1: PDFont, arg2: Int, arg3: String, arg4: Vector): Unit
    Attributes
    protected[text]
    Definition Classes
    LegacyPDFStreamEngine → PDFStreamEngine
    Annotations
    @throws( classOf[java.io.IOException] )
  110. def showGlyph(arg0: Matrix, arg1: PDFont, arg2: Int, arg3: Vector): Unit
    Attributes
    protected[contentstream]
    Definition Classes
    PDFStreamEngine
    Annotations
    @throws( classOf[java.io.IOException] )
  111. def showText(arg0: Array[Byte]): Unit
    Attributes
    protected[contentstream]
    Definition Classes
    PDFStreamEngine
    Annotations
    @throws( classOf[java.io.IOException] )
  112. def showTextString(arg0: Array[Byte]): Unit
    Definition Classes
    PDFStreamEngine
    Annotations
    @throws( classOf[java.io.IOException] )
  113. def showTextStrings(arg0: COSArray): Unit
    Definition Classes
    PDFStreamEngine
    Annotations
    @throws( classOf[java.io.IOException] )
  114. def showTransparencyGroup(arg0: PDTransparencyGroup): Unit
    Definition Classes
    PDFStreamEngine
    Annotations
    @throws( classOf[java.io.IOException] )
  115. def showType3Glyph(arg0: Matrix, arg1: PDType3Font, arg2: Int, arg3: Vector): Unit
    Attributes
    protected[contentstream]
    Definition Classes
    PDFStreamEngine
    Annotations
    @throws( classOf[java.io.IOException] )
  116. def showType3Glyph(arg0: Matrix, arg1: PDType3Font, arg2: Int, arg3: String, arg4: Vector): Unit
    Attributes
    protected[contentstream]
    Definition Classes
    PDFStreamEngine
    Annotations
    @throws( classOf[java.io.IOException] )
  117. def startArticle(arg0: Boolean): Unit
    Attributes
    protected[text]
    Definition Classes
    PDFTextStripper
    Annotations
    @throws( classOf[java.io.IOException] )
  118. def startArticle(): Unit
    Attributes
    protected[text]
    Definition Classes
    PDFTextStripper
    Annotations
    @throws( classOf[java.io.IOException] )
  119. def startDocument(arg0: PDDocument): Unit
    Attributes
    protected[text]
    Definition Classes
    PDFTextStripper
    Annotations
    @throws( classOf[java.io.IOException] )
  120. def startPage(arg0: PDPage): Unit
    Attributes
    protected[text]
    Definition Classes
    PDFTextStripper
    Annotations
    @throws( classOf[java.io.IOException] )
  121. final def synchronized[T0](arg0: ⇒ T0): T0
    Definition Classes
    AnyRef
  122. def toString(): String
    Definition Classes
    AnyRef → Any
  123. def transformWidth(arg0: Float): Float
    Attributes
    protected[contentstream]
    Definition Classes
    PDFStreamEngine
  124. def transformedPoint(arg0: Float, arg1: Float): Float
    Definition Classes
    PDFStreamEngine
  125. def unsupportedOperator(arg0: Operator, arg1: List[COSBase]): Unit
    Attributes
    protected[contentstream]
    Definition Classes
    PDFStreamEngine
    Annotations
    @throws( classOf[java.io.IOException] )
  126. final def wait(): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  127. final def wait(arg0: Long, arg1: Int): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  128. final def wait(arg0: Long): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  129. def writeCharacters(arg0: TextPosition): Unit
    Attributes
    protected[text]
    Definition Classes
    PDFTextStripper
    Annotations
    @throws( classOf[java.io.IOException] )
  130. def writeLineSeparator(): Unit
    Attributes
    protected[text]
    Definition Classes
    PDFTextStripper
    Annotations
    @throws( classOf[java.io.IOException] )
  131. def writePage(): Unit
    Attributes
    protected[pdf]
    Definition Classes
    PDFLayoutTextStripper → PDFTextStripper
    Annotations
    @Override()
  132. def writePageEnd(): Unit
    Attributes
    protected[text]
    Definition Classes
    PDFTextStripper
    Annotations
    @throws( classOf[java.io.IOException] )
  133. def writePageStart(): Unit
    Attributes
    protected[text]
    Definition Classes
    PDFTextStripper
    Annotations
    @throws( classOf[java.io.IOException] )
  134. def writeParagraphEnd(): Unit
    Attributes
    protected[text]
    Definition Classes
    PDFTextStripper
    Annotations
    @throws( classOf[java.io.IOException] )
  135. def writeParagraphSeparator(): Unit
    Attributes
    protected[text]
    Definition Classes
    PDFTextStripper
    Annotations
    @throws( classOf[java.io.IOException] )
  136. def writeParagraphStart(): Unit
    Attributes
    protected[text]
    Definition Classes
    PDFTextStripper
    Annotations
    @throws( classOf[java.io.IOException] )
  137. def writeString(arg0: String): Unit
    Attributes
    protected[text]
    Definition Classes
    PDFTextStripper
    Annotations
    @throws( classOf[java.io.IOException] )
  138. def writeString(arg0: String, arg1: List[TextPosition]): Unit
    Attributes
    protected[text]
    Definition Classes
    PDFTextStripper
    Annotations
    @throws( classOf[java.io.IOException] )
  139. def writeText(arg0: PDDocument, arg1: Writer): Unit
    Definition Classes
    PDFTextStripper
    Annotations
    @throws( classOf[java.io.IOException] )
  140. def writeWordSeparator(): Unit
    Attributes
    protected[text]
    Definition Classes
    PDFTextStripper
    Annotations
    @throws( classOf[java.io.IOException] )

Deprecated Value Members

  1. def registerOperatorProcessor(arg0: String, arg1: OperatorProcessor): Unit
    Definition Classes
    PDFStreamEngine
    Annotations
    @Deprecated
    Deprecated

Inherited from PDFTextStripper

Inherited from LegacyPDFStreamEngine

Inherited from PDFStreamEngine

Inherited from AnyRef

Inherited from Any

Ungrouped