-
accessChecker
AccessChecker accessChecker
-
averageCharTolerance
Float averageCharTolerance
-
catchIntermediateIOExceptions
boolean catchIntermediateIOExceptions
-
detectAngles
boolean detectAngles
-
dropThreshold
float dropThreshold
-
enableAutoSpace
boolean enableAutoSpace
-
extractAcroFormContent
boolean extractAcroFormContent
-
extractActions
boolean extractActions
-
extractAnnotationText
boolean extractAnnotationText
-
extractBookmarksText
boolean extractBookmarksText
-
extractFontNames
boolean extractFontNames
-
extractIncrementalUpdateInfo
boolean extractIncrementalUpdateInfo
-
extractInlineImageMetadataOnly
boolean extractInlineImageMetadataOnly
-
extractInlineImages
boolean extractInlineImages
-
extractMarkedContent
boolean extractMarkedContent
-
extractUniqueInlineImagesOnly
boolean extractUniqueInlineImagesOnly
-
ifXFAExtractOnlyXFA
boolean ifXFAExtractOnlyXFA
-
imageGraphicsEngineFactory
ImageGraphicsEngineFactory imageGraphicsEngineFactory
-
imageStrategy
PDFParserConfig.IMAGE_STRATEGY imageStrategy
Should the entire document be rendered?
-
maxIncrementalUpdates
int maxIncrementalUpdates
-
maxMainMemoryBytes
long maxMainMemoryBytes
-
ocrDPI
int ocrDPI
-
ocrImageFormatName
String ocrImageFormatName
-
ocrImageQuality
float ocrImageQuality
-
ocrImageType
org.apache.pdfbox.rendering.ImageType ocrImageType
-
ocrRenderingStrategy
PDFParserConfig.OCR_RENDERING_STRATEGY ocrRenderingStrategy
-
ocrStrategy
PDFParserConfig.OCR_STRATEGY ocrStrategy
-
ocrStrategyAuto
PDFParserConfig.OCRStrategyAuto ocrStrategyAuto
-
parseIncrementalUpdates
boolean parseIncrementalUpdates
-
renderer
org.apache.tika.renderer.Renderer renderer
-
setKCMS
boolean setKCMS
-
sortByPosition
boolean sortByPosition
-
spacingTolerance
Float spacingTolerance
-
suppressDuplicateOverlappingText
boolean suppressDuplicateOverlappingText
-
userConfigured
Set<String> userConfigured