Serialized Form

Package org.apache.tika.parser.ocr

Class org.apache.tika.parser.ocr.TesseractOCRConfig

class TesseractOCRConfig extends Object implements Serializable

serialVersionUID:

-4861942486845757891L

Serialized Fields

applyRotation

boolean applyRotation

colorspace

String colorspace

density

int density

depth

int depth

enableImagePreprocessing

boolean enableImagePreprocessing

filter

String filter

language

String language

maxFileSizeToOcr

long maxFileSizeToOcr

minFileSizeToOcr

long minFileSizeToOcr

otherTesseractConfig

Map<String,String> otherTesseractConfig

outputType

TesseractOCRConfig.OUTPUT_TYPE outputType

pageSegMode

String pageSegMode

pageSeparator

String pageSeparator

preserveInterwordSpacing

boolean preserveInterwordSpacing

resize

int resize

skipOcr

boolean skipOcr

timeoutSeconds

int timeoutSeconds

userConfigured

Set<String> userConfigured

Class org.apache.tika.parser.ocr.TesseractOCRParser

class TesseractOCRParser extends org.apache.tika.parser.AbstractExternalProcessParser implements Serializable

serialVersionUID:

-8167538283213097265L

Serialized Fields

defaultConfig

TesseractOCRConfig defaultConfig

hasImageMagick

boolean hasImageMagick

hasTesseract

boolean hasTesseract

imageMagickPath

String imageMagickPath

imagePreprocessor

org.apache.tika.parser.ocr.ImagePreprocessor imagePreprocessor

langs

Set<String> langs

preloadLangs

boolean preloadLangs

tessdataPath

String tessdataPath

tesseractPath

String tesseractPath