Serialized Form
-
Package org.apache.tika.batch
-
Exception Class org.apache.tika.batch.BatchNoRestartError
class BatchNoRestartError extends Error implements Serializable
-
-
Package org.apache.tika.client
-
Exception Class org.apache.tika.client.TikaClientException
class TikaClientException extends TikaException implements Serializable
-
-
Package org.apache.tika.config
-
Class org.apache.tika.config.Param
class Param extends Object implements Serializable -
Class org.apache.tika.config.TikaTaskTimeout
class TikaTaskTimeout extends Object implements Serializable-
Serialized Fields
-
timeoutMillis
long timeoutMillis
-
-
-
-
Package org.apache.tika.detect
-
Class org.apache.tika.detect.CompositeDetector
class CompositeDetector extends Object implements Serializable- serialVersionUID:
- 5980683158436430252L
-
Serialized Fields
-
detectors
List<Detector> detectors
-
registry
MediaTypeRegistry registry
-
-
Class org.apache.tika.detect.CompositeEncodingDetector
class CompositeEncodingDetector extends Object implements Serializable- serialVersionUID:
- 5980683158436430252L
-
Serialized Fields
-
detectors
List<EncodingDetector> detectors
-
-
Class org.apache.tika.detect.DefaultDetector
class DefaultDetector extends CompositeDetector implements Serializable- serialVersionUID:
- -8170114575326908027L
-
Class org.apache.tika.detect.DefaultEncodingDetector
class DefaultEncodingDetector extends CompositeEncodingDetector implements Serializable -
Class org.apache.tika.detect.DefaultProbDetector
class DefaultProbDetector extends CompositeDetector implements Serializable- serialVersionUID:
- -8836240060532323352L
-
Class org.apache.tika.detect.EmptyDetector
class EmptyDetector extends Object implements Serializable -
Class org.apache.tika.detect.FileCommandDetector
class FileCommandDetector extends Object implements Serializable -
Class org.apache.tika.detect.MagicDetector
class MagicDetector extends Object implements Serializable-
Serialized Fields
-
isRegex
boolean isRegex
True if pattern is a regular expression, false otherwise. -
isStringIgnoreCase
boolean isStringIgnoreCase
True if we're doing a case-insensitive string match, false otherwise. -
length
int length
Length of the comparison window. -
mask
byte[] mask
Bit mask that is applied to the source bytes before pattern matching. -
offsetRangeBegin
int offsetRangeBegin
First offset (inclusive) of the comparison window within the document input stream. Greater than or equal to zero. -
offsetRangeEnd
int offsetRangeEnd
Last offset (inclusive) of the comparison window within the document input stream. Greater than or equal to thefirst offset.Note that this is not the offset of the last byte read from the document stream. Instead, the last window of bytes to be compared starts at this offset.
-
pattern
byte[] pattern
The magic match pattern. If this byte pattern is equal to the possibly bit-masked bytes from the input stream, then the type detection succeeds and the configuredMagicDetector.typeis returned. -
patternLength
int patternLength
Length of the pattern, which in the case of regular expressions will not be the same as the comparison window length. -
type
MediaType type
The matching media type. Returned by theMagicDetector.detect(InputStream, Metadata)method if a match is found.
-
-
-
Class org.apache.tika.detect.MatroskaDetector
class MatroskaDetector extends Object implements Serializable- serialVersionUID:
- 1L
-
Class org.apache.tika.detect.NameDetector
class NameDetector extends Object implements Serializable -
Class org.apache.tika.detect.NNExampleModelDetector
class NNExampleModelDetector extends TrainedModelDetector implements Serializable- serialVersionUID:
- 1L
-
Class org.apache.tika.detect.NonDetectingEncodingDetector
class NonDetectingEncodingDetector extends Object implements Serializable-
Serialized Fields
-
charset
Charset charset
-
-
-
Class org.apache.tika.detect.OverrideDetector
class OverrideDetector extends Object implements Serializable -
Class org.apache.tika.detect.TextDetector
class TextDetector extends Object implements Serializable- serialVersionUID:
- 4774601079503507765L
-
Serialized Fields
-
bytesToTest
int bytesToTest
-
-
Class org.apache.tika.detect.TrainedModelDetector
class TrainedModelDetector extends Object implements Serializable- serialVersionUID:
- 1L
-
Serialized Fields
-
MODEL_MAP
Map<MediaType, TrainedModel> MODEL_MAP
-
-
Class org.apache.tika.detect.TypeDetector
class TypeDetector extends Object implements Serializable -
Class org.apache.tika.detect.ZeroSizeFileDetector
class ZeroSizeFileDetector extends Object implements Serializable
-
-
Package org.apache.tika.detect.magika
-
Class org.apache.tika.detect.magika.MagikaDetector
class MagikaDetector extends Object implements Serializable
-
-
Package org.apache.tika.detect.siegfried
-
Class org.apache.tika.detect.siegfried.SiegfriedDetector
class SiegfriedDetector extends Object implements Serializable
-
-
Package org.apache.tika.embedder
-
Class org.apache.tika.embedder.ExternalEmbedder
class ExternalEmbedder extends Object implements Serializable- serialVersionUID:
- -2828829275642475697L
-
Serialized Fields
-
command
String[] command
The external command to invoke.- See Also:
-
commandAppendOperator
String commandAppendOperator
-
commandAssignmentDelimeter
String commandAssignmentDelimeter
-
commandAssignmentOperator
String commandAssignmentOperator
-
metadataCommandArguments
Map<Property,
String[]> metadataCommandArguments Mapping of Tika metadata to command line parameters. -
quoteAssignmentValues
boolean quoteAssignmentValues
-
supportedEmbedTypes
Set<MediaType> supportedEmbedTypes
Media types supported by the external program. -
tmp
TemporaryResources tmp
-
-
-
Package org.apache.tika.eval.app.io
-
Exception Class org.apache.tika.eval.app.io.ExtractReaderException
class ExtractReaderException extends IOException implements Serializable-
Serialized Fields
-
type
ExtractReaderException.TYPE type
-
-
-
-
Package org.apache.tika.eval.core.metadata
-
Class org.apache.tika.eval.core.metadata.TikaEvalMetadataFilter
class TikaEvalMetadataFilter extends MetadataFilter implements Serializable
-
-
Package org.apache.tika.example
-
Class org.apache.tika.example.DirListParser
class DirListParser extends Object implements Serializable- serialVersionUID:
- 2717930544410610735L
-
Class org.apache.tika.example.EncryptedPrescriptionDetector
class EncryptedPrescriptionDetector extends Object implements Serializable- serialVersionUID:
- -1709652690773421147L
-
Class org.apache.tika.example.EncryptedPrescriptionParser
class EncryptedPrescriptionParser extends Object implements Serializable- serialVersionUID:
- -7816987249611278541L
-
Class org.apache.tika.example.LanguageDetectingParser
class LanguageDetectingParser extends DelegatingParser implements Serializable- serialVersionUID:
- 4291320409396502774L
-
Class org.apache.tika.example.PickBestTextEncodingParser
class PickBestTextEncodingParser extends AbstractMultipleParser implements Serializable- serialVersionUID:
- 730345169223211807L
-
Serialized Fields
-
charsetsToTry
String[] charsetsToTry
Deprecated.Which charsets we should try
-
-
Class org.apache.tika.example.PickBestTextEncodingParser.CharsetContentHandlerFactory
class CharsetContentHandlerFactory extends Object implements Serializable-
Serialized Fields
-
handler
ContentHandler handler
-
index
int index
-
-
-
Class org.apache.tika.example.PrescriptionParser
class PrescriptionParser extends org.apache.tika.parser.xml.XMLParser implements Serializable- serialVersionUID:
- 7690682277511967388L
-
-
Package org.apache.tika.exception
-
Exception Class org.apache.tika.exception.AccessPermissionException
class AccessPermissionException extends TikaException implements Serializable -
Exception Class org.apache.tika.exception.CorruptedFileException
class CorruptedFileException extends TikaException implements Serializable -
Exception Class org.apache.tika.exception.EncryptedDocumentException
class EncryptedDocumentException extends TikaException implements Serializable -
Exception Class org.apache.tika.exception.FileTooLongException
class FileTooLongException extends IOException implements Serializable -
Exception Class org.apache.tika.exception.RuntimeSAXException
class RuntimeSAXException extends RuntimeException implements Serializable -
Exception Class org.apache.tika.exception.TikaConfigException
class TikaConfigException extends TikaException implements Serializable -
Exception Class org.apache.tika.exception.TikaException
class TikaException extends Exception implements Serializable -
Exception Class org.apache.tika.exception.TikaMemoryLimitException
class TikaMemoryLimitException extends TikaException implements Serializable -
Exception Class org.apache.tika.exception.TikaTimeoutException
class TikaTimeoutException extends RuntimeException implements Serializable -
Exception Class org.apache.tika.exception.UnsupportedFormatException
class UnsupportedFormatException extends TikaException implements Serializable -
Exception Class org.apache.tika.exception.WriteLimitReachedException
class WriteLimitReachedException extends SAXException implements Serializable-
Serialized Fields
-
writeLimit
int writeLimit
-
-
-
Exception Class org.apache.tika.exception.ZeroByteFileException
class ZeroByteFileException extends TikaException implements Serializable
-
-
Package org.apache.tika.extractor
-
Class org.apache.tika.extractor.EmbeddedDocumentUtil
class EmbeddedDocumentUtil extends Object implements Serializable-
Serialized Fields
-
context
ParseContext context
-
detector
Detector detector
-
embeddedDocumentExtractor
EmbeddedDocumentExtractor embeddedDocumentExtractor
-
mimeTypes
MimeTypes mimeTypes
-
tikaConfig
TikaConfig tikaConfig
-
-
-
Class org.apache.tika.extractor.ParserContainerExtractor
class ParserContainerExtractor extends Object implements Serializable- serialVersionUID:
- 2261131045580861514L
-
Class org.apache.tika.extractor.ParsingEmbeddedDocumentExtractorFactory
class ParsingEmbeddedDocumentExtractorFactory extends Object implements Serializable-
Serialized Fields
-
writeFileNameToContent
boolean writeFileNameToContent
-
-
-
Class org.apache.tika.extractor.RUnpackExtractorFactory
class RUnpackExtractorFactory extends Object implements Serializable-
Serialized Fields
-
embeddedBytesExcludeEmbeddedResourceTypes
Set<String> embeddedBytesExcludeEmbeddedResourceTypes
-
embeddedBytesExcludeMimeTypes
Set<String> embeddedBytesExcludeMimeTypes
-
embeddedBytesIncludeEmbeddedResourceTypes
Set<String> embeddedBytesIncludeEmbeddedResourceTypes
-
embeddedBytesIncludeMimeTypes
Set<String> embeddedBytesIncludeMimeTypes
-
maxEmbeddedBytesForExtraction
long maxEmbeddedBytesForExtraction
-
writeFileNameToContent
boolean writeFileNameToContent
-
-
-
-
Package org.apache.tika.fork
-
Class org.apache.tika.fork.ForkParser
class ForkParser extends Object implements Serializable- serialVersionUID:
- -4962742892274663950L
-
Serialized Fields
-
currentlyInUse
int currentlyInUse
-
java
List<String> java
Java command line -
loader
ClassLoader loader
-
maxFilesProcessedPerClient
int maxFilesProcessedPerClient
-
parser
Parser parser
-
parserFactoryFactory
ParserFactoryFactory parserFactoryFactory
-
pool
Queue<org.apache.tika.fork.ForkClient> pool
-
poolSize
int poolSize
Process pool size -
serverParseTimeoutMillis
long serverParseTimeoutMillis
-
serverPulseMillis
long serverPulseMillis
-
serverWaitTimeoutMillis
long serverWaitTimeoutMillis
-
tikaBin
Path tikaBin
-
-
Class org.apache.tika.fork.ParserFactoryFactory
class ParserFactoryFactory extends Object implements Serializable- serialVersionUID:
- 4710974869988895410L
-
-
Package org.apache.tika.fuzzing.exceptions
-
Exception Class org.apache.tika.fuzzing.exceptions.CantFuzzException
class CantFuzzException extends TikaException implements Serializable
-
-
Package org.apache.tika.gui
-
Class org.apache.tika.gui.TikaGUI
class TikaGUI extends JFrame implements Serializable- serialVersionUID:
- 5883906936187059495L
-
Serialized Fields
-
cards
JPanel cards
Container for the editor cards. -
chooser
JFileChooser chooser
File chooser. -
context
ParseContext context
Parsing context. -
html
JEditorPane html
Formatted XHTML output. -
imageParser
org.apache.tika.gui.TikaGUI.ImageSavingParser imageParser
Captures requested embedded images -
json
JEditorPane json
Raw JSON source. -
layout
CardLayout layout
The card layout for switching between different views. -
metadata
JEditorPane metadata
Document metadata. -
parser
Parser parser
Configured parser instance. -
text
JEditorPane text
Plain text output. -
textMain
JEditorPane textMain
Main content output. -
tikaConfig
TikaConfig tikaConfig
-
xml
JEditorPane xml
Raw XHTML source.
-
-
-
Package org.apache.tika.io
-
Exception Class org.apache.tika.io.EndianUtils.BufferUnderrunException
class BufferUnderrunException extends TikaException implements Serializable- serialVersionUID:
- 8358288231138076276L
-
-
Package org.apache.tika.langdetect.opennlp.metadatafilter
-
Class org.apache.tika.langdetect.opennlp.metadatafilter.OpenNLPMetadataFilter
class OpenNLPMetadataFilter extends MetadataFilter implements Serializable-
Serialized Fields
-
maxCharsForDetection
int maxCharsForDetection
-
-
-
-
Package org.apache.tika.langdetect.optimaize.metadatafilter
-
Class org.apache.tika.langdetect.optimaize.metadatafilter.OptimaizeMetadataFilter
class OptimaizeMetadataFilter extends MetadataFilter implements Serializable-
Serialized Fields
-
maxCharsForDetection
int maxCharsForDetection
-
-
-
-
Package org.apache.tika.metadata
-
Class org.apache.tika.metadata.Metadata
class Metadata extends Object implements Serializable- serialVersionUID:
- 5623926545693153182L
-
Serialized Fields
-
metadata
Map<String,
String[]> metadata A map of all metadata attributes. -
writeFilter
MetadataWriteFilter writeFilter
-
-
Exception Class org.apache.tika.metadata.PropertyTypeException
class PropertyTypeException extends IllegalArgumentException implements Serializable
-
-
Package org.apache.tika.metadata.filter
-
Class org.apache.tika.metadata.filter.CaptureGroupMetadataFilter
class CaptureGroupMetadataFilter extends MetadataFilter implements Serializable -
Class org.apache.tika.metadata.filter.ClearByAttachmentTypeMetadataFilter
class ClearByAttachmentTypeMetadataFilter extends MetadataFilter implements Serializable -
Class org.apache.tika.metadata.filter.ClearByMimeMetadataFilter
class ClearByMimeMetadataFilter extends MetadataFilter implements Serializable -
Class org.apache.tika.metadata.filter.CompositeMetadataFilter
class CompositeMetadataFilter extends MetadataFilter implements Serializable-
Serialized Fields
-
filters
List<MetadataFilter> filters
-
-
-
Class org.apache.tika.metadata.filter.DateNormalizingMetadataFilter
class DateNormalizingMetadataFilter extends MetadataFilter implements Serializable-
Serialized Fields
-
defaultTimeZone
TimeZone defaultTimeZone
-
-
-
Class org.apache.tika.metadata.filter.DefaultMetadataFilter
class DefaultMetadataFilter extends CompositeMetadataFilter implements Serializable -
Class org.apache.tika.metadata.filter.ExcludeFieldMetadataFilter
class ExcludeFieldMetadataFilter extends MetadataFilter implements Serializable -
Class org.apache.tika.metadata.filter.FieldNameMappingFilter
class FieldNameMappingFilter extends MetadataFilter implements Serializable -
Class org.apache.tika.metadata.filter.GeoPointMetadataFilter
class GeoPointMetadataFilter extends MetadataFilter implements Serializable-
Serialized Fields
-
geoPointFieldName
String geoPointFieldName
-
-
-
Class org.apache.tika.metadata.filter.IncludeFieldMetadataFilter
class IncludeFieldMetadataFilter extends MetadataFilter implements Serializable -
Class org.apache.tika.metadata.filter.MetadataFilter
class MetadataFilter extends ConfigBase implements Serializable -
Class org.apache.tika.metadata.filter.NoOpFilter
class NoOpFilter extends MetadataFilter implements Serializable
-
-
Package org.apache.tika.metadata.listfilter
-
Class org.apache.tika.metadata.listfilter.CompositeMetadataListFilter
class CompositeMetadataListFilter extends MetadataListFilter implements Serializable-
Serialized Fields
-
filters
List<MetadataListFilter> filters
-
-
-
Class org.apache.tika.metadata.listfilter.MetadataListFilter
class MetadataListFilter extends ConfigBase implements Serializable -
Class org.apache.tika.metadata.listfilter.NoOpListFilter
class NoOpListFilter extends MetadataListFilter implements Serializable
-
-
Package org.apache.tika.metadata.writefilter
-
Class org.apache.tika.metadata.writefilter.StandardWriteFilter
class StandardWriteFilter extends Object implements Serializable-
Serialized Fields
-
estimatedSize
int estimatedSize
-
excludeFields
Set<String> excludeFields
-
fieldSizes
Map<String,
Integer> fieldSizes -
includeEmpty
boolean includeEmpty
-
includeFields
Set<String> includeFields
-
maxFieldSize
int maxFieldSize
-
maxKeySize
int maxKeySize
-
maxTotalEstimatedSize
int maxTotalEstimatedSize
-
maxValuesPerField
int maxValuesPerField
-
minimumMaxFieldSizeInAlwaysFields
int minimumMaxFieldSizeInAlwaysFields
-
-
-
-
Package org.apache.tika.mime
-
Class org.apache.tika.mime.MediaType
class MediaType extends Object implements Serializable- serialVersionUID:
- -3831000556189036392L
-
Serialized Fields
-
parameters
Map<String,
String> parameters Immutable sorted map of media type parameters. -
semicolon
int semicolon
Location of the first ";" character separating the type part ofMediaType.stringfrom possible parameters. Length ofMediaType.stringin case there are no parameters. -
slash
int slash
Location of the "/" character separating the type and the subtype tokens inMediaType.string. -
string
String string
Canonical string representation of this media type.
-
-
Class org.apache.tika.mime.MediaTypeRegistry
class MediaTypeRegistry extends Object implements Serializable- serialVersionUID:
- 4710974869988895410L
-
Serialized Fields
-
inheritance
Map<MediaType, MediaType> inheritance
Known type inheritance relationships. The mapping is from a media type to the closest supertype. -
registry
Map<MediaType, MediaType> registry
Registry of known media types, including type aliases. A canonical media type is handled as an identity mapping, while an alias is stored as a mapping from the alias to the corresponding canonical type.
-
-
Class org.apache.tika.mime.MimeType
class MimeType extends Object implements Serializable- serialVersionUID:
- 4357830439860729201L
-
Serialized Fields
-
acronym
String acronym
The MimeType acronym -
description
String description
Description of this media type. -
extensions
List<String> extensions
All known file extensions of this type, in order of preference (best first). -
isInterpreted
boolean isInterpreted
Whether this mime-type is used for server-side scripts, and thus cannot reliably be used for filename-based type detection -
links
List<URI> links
Documentation Links -
magics
List<org.apache.tika.mime.Magic> magics
The magics associated to this Mime-Type -
minLength
int minLength
The minimum length of data to provides for magic analyzis -
rootXML
List<org.apache.tika.mime.MimeType.RootXML> rootXML
The root-XML associated to this Mime-Type -
type
MediaType type
The normalized media type name. -
uti
String uti
The http://en.wikipedia.org/wiki/Uniform_Type_Identifier
-
-
Exception Class org.apache.tika.mime.MimeTypeException
class MimeTypeException extends TikaException implements Serializable -
Class org.apache.tika.mime.MimeTypes
class MimeTypes extends Object implements Serializable- serialVersionUID:
- -1350863170146349036L
-
Serialized Fields
-
htmlMimeType
MimeType htmlMimeType
html type, text/html -
magics
List<org.apache.tika.mime.Magic> magics
Sorted list of all registered magics -
patterns
org.apache.tika.mime.Patterns patterns
The patterns matcher -
registry
MediaTypeRegistry registry
Registered media types and their aliases. -
rootMimeType
MimeType rootMimeType
Root type, application/octet-stream. -
rootMimeTypeL
List<MimeType> rootMimeTypeL
-
textMimeType
MimeType textMimeType
Text type, text/plain. -
types
Map<MediaType, MimeType> types
All the registered MimeTypes indexed on their canonical names -
xmlMimeType
MimeType xmlMimeType
xml type, application/xml -
xmls
List<MimeType> xmls
Sorted list of all registered rootXML
-
-
Class org.apache.tika.mime.ProbabilisticMimeDetectionSelector
class ProbabilisticMimeDetectionSelector extends Object implements Serializable- serialVersionUID:
- 224589862960269260L
-
Serialized Fields
-
changeRate
float changeRate
-
extension_neg
float extension_neg
-
extension_trust
float extension_trust
-
magic_neg
float magic_neg
-
magic_trust
float magic_trust
-
meta_neg
float meta_neg
-
meta_trust
float meta_trust
-
mimeTypes
MimeTypes mimeTypes
-
priorExtensionFileType
float priorExtensionFileType
-
priorMagicFileType
float priorMagicFileType
-
priorMetaFileType
float priorMetaFileType
-
rootMediaType
MediaType rootMediaType
-
threshold
float threshold
-
-
-
Package org.apache.tika.parser
-
Class org.apache.tika.parser.AbstractEncodingDetectorParser
class AbstractEncodingDetectorParser extends Object implements Serializable-
Serialized Fields
-
encodingDetector
EncodingDetector encodingDetector
-
-
-
Class org.apache.tika.parser.AbstractExternalProcessParser
class AbstractExternalProcessParser extends Object implements Serializable- serialVersionUID:
- 7186985395903074255L
-
Class org.apache.tika.parser.AbstractParser
class AbstractParser extends Object implements Serializable- serialVersionUID:
- 7186985395903074255L
-
Class org.apache.tika.parser.AutoDetectParser
class AutoDetectParser extends CompositeParser implements Serializable- serialVersionUID:
- 6110455808615143122L
-
Serialized Fields
-
autoDetectParserConfig
AutoDetectParserConfig autoDetectParserConfig
Configuration used when initializing a SecureContentHandler and the TikaInputStream. -
detector
Detector detector
The type detector used by this parser to auto-detect the type of a document.
-
-
Class org.apache.tika.parser.AutoDetectParserConfig
class AutoDetectParserConfig extends ConfigBase implements Serializable-
Serialized Fields
-
contentHandlerDecoratorFactory
ContentHandlerDecoratorFactory contentHandlerDecoratorFactory
-
digesterFactory
DigestingParser.DigesterFactory digesterFactory
-
embeddedDocumentExtractorFactory
EmbeddedDocumentExtractorFactory embeddedDocumentExtractorFactory
-
maximumCompressionRatio
Long maximumCompressionRatio
SecureContentHandler -- Desired maximum compression ratio. -
maximumDepth
Integer maximumDepth
SecureContentHandler -- Desired maximum XML nesting level. -
maximumPackageEntryDepth
Integer maximumPackageEntryDepth
SecureContentHandler -- Desired maximum package entry nesting level. -
metadataWriteFilterFactory
MetadataWriteFilterFactory metadataWriteFilterFactory
-
outputThreshold
Long outputThreshold
SecureContentHandler -- Desired output threshold in characters. -
spoolToDisk
Long spoolToDisk
If this is not null and greater than -1, the AutoDetectParser will spool the stream to disk if the length of the stream is known ahead of time. -
throwOnZeroBytes
boolean throwOnZeroBytes
-
-
-
Class org.apache.tika.parser.CompositeParser
class CompositeParser extends Object implements Serializable- serialVersionUID:
- 2192845797749627824L
-
Serialized Fields
-
fallback
Parser fallback
The fallback parser, used when no better parser is available. -
parsers
List<Parser> parsers
List of component parsers. -
registry
MediaTypeRegistry registry
Media type registry.
-
-
Class org.apache.tika.parser.CryptoParser
class CryptoParser extends DelegatingParser implements Serializable- serialVersionUID:
- -3507995752666557731L
-
Class org.apache.tika.parser.DefaultParser
class DefaultParser extends CompositeParser implements Serializable- serialVersionUID:
- 3612324825403757520L
-
Class org.apache.tika.parser.DelegatingParser
class DelegatingParser extends Object implements Serializable -
Class org.apache.tika.parser.DigestingParser
class DigestingParser extends ParserDecorator implements Serializable-
Serialized Fields
-
digester
DigestingParser.Digester digester
-
embeddedStreamTranslator
EmbeddedStreamTranslator embeddedStreamTranslator
-
skipContainerDocument
boolean skipContainerDocument
-
-
-
Class org.apache.tika.parser.EmptyParser
class EmptyParser extends Object implements Serializable- serialVersionUID:
- -4218649699095732123L
-
Class org.apache.tika.parser.ErrorParser
class ErrorParser extends Object implements Serializable- serialVersionUID:
- 7727423956957641824L
-
Class org.apache.tika.parser.NetworkParser
class NetworkParser extends Object implements Serializable -
Class org.apache.tika.parser.ParseContext
class ParseContext extends Object implements Serializable- serialVersionUID:
- -5921436862145826534L
-
Class org.apache.tika.parser.ParserDecorator
class ParserDecorator extends Object implements Serializable- serialVersionUID:
- -3861669115439125268L
-
Serialized Fields
-
parser
Parser parser
The decorated parser instance.
-
-
Class org.apache.tika.parser.ParserPostProcessor
class ParserPostProcessor extends ParserDecorator implements Serializable -
Class org.apache.tika.parser.RecursiveParserWrapper
class RecursiveParserWrapper extends ParserDecorator implements Serializable- serialVersionUID:
- 9086536568120690938L
-
Serialized Fields
-
catchEmbeddedExceptions
boolean catchEmbeddedExceptions
-
inlineContent
boolean inlineContent
-
-
Class org.apache.tika.parser.RegexCaptureParser
class RegexCaptureParser extends Object implements Serializable -
Class org.apache.tika.parser.StatefulParser
class StatefulParser extends ParserDecorator implements Serializable
-
-
Package org.apache.tika.parser.ctakes
-
Class org.apache.tika.parser.ctakes.CTAKESConfig
class CTAKESConfig extends Object implements Serializable- serialVersionUID:
- -1599741171775528923L
-
Serialized Fields
-
aeDescriptorPath
String aeDescriptorPath
-
annotationProps
CTAKESAnnotationProperty[] annotationProps
-
metadata
String[] metadata
-
prettyPrint
boolean prettyPrint
-
separatorChar
char separatorChar
-
serialize
boolean serialize
-
serializerType
CTAKESSerializer serializerType
-
stream
OutputStream stream
-
text
boolean text
-
UMLSPass
String UMLSPass
-
UMLSUser
String UMLSUser
-
-
Class org.apache.tika.parser.ctakes.CTAKESParser
class CTAKESParser extends ParserDecorator implements Serializable- serialVersionUID:
- -2313482748027097961L
-
-
Package org.apache.tika.parser.envi
-
Class org.apache.tika.parser.envi.EnviHeaderParser
class EnviHeaderParser extends AbstractEncodingDetectorParser implements Serializable- serialVersionUID:
- -1479368523072408091L
-
-
Package org.apache.tika.parser.external
-
Class org.apache.tika.parser.external.CompositeExternalParser
class CompositeExternalParser extends CompositeParser implements Serializable- serialVersionUID:
- 6962436916649024024L
-
Class org.apache.tika.parser.external.ExternalParser
class ExternalParser extends Object implements Serializable- serialVersionUID:
- -1079128990650687037L
-
Serialized Fields
-
command
String[] command
The external command to invoke.- See Also:
-
ignoredLineConsumer
ExternalParser.LineConsumer ignoredLineConsumer
A consumer for ignored Lines -
metadataPatterns
Map<Pattern,
String> metadataPatterns Regular Expressions to run over STDOUT to extract Metadata. -
supportedTypes
Set<MediaType> supportedTypes
Media types supported by the external program. -
timeoutMs
long timeoutMs
-
-
-
Package org.apache.tika.parser.external2
-
Class org.apache.tika.parser.external2.ExternalParser
class ExternalParser extends Object implements Serializable
-
-
Package org.apache.tika.parser.gdal
-
Class org.apache.tika.parser.gdal.GDALParser
class GDALParser extends Object implements Serializable- serialVersionUID:
- -3869130527323941401L
-
Serialized Fields
-
command
String command
-
maxStdErr
int maxStdErr
-
maxStdOut
int maxStdOut
-
timeoutMs
long timeoutMs
-
-
-
Package org.apache.tika.parser.geo.topic
-
Class org.apache.tika.parser.geo.topic.GeoParser
class GeoParser extends Object implements Serializable- serialVersionUID:
- -2241391757440215491L
-
Serialized Fields
-
available
boolean available
-
defaultConfig
GeoParserConfig defaultConfig
-
gazetteerClient
GeoGazetteerClient gazetteerClient
-
initialized
boolean initialized
-
modelUrl
URL modelUrl
-
nameFinder
opennlp.tools.namefind.NameFinderME nameFinder
-
-
Class org.apache.tika.parser.geo.topic.GeoParserConfig
class GeoParserConfig extends Object implements Serializable- serialVersionUID:
- -3167692634278575818L
-
-
Package org.apache.tika.parser.geo.topic.gazetteer
-
Class org.apache.tika.parser.geo.topic.gazetteer.Location
class Location extends Object implements Serializable- serialVersionUID:
- -59485448766406004L
-
-
Package org.apache.tika.parser.geoinfo
-
Class org.apache.tika.parser.geoinfo.GeographicInformationParser
class GeographicInformationParser extends Object implements Serializable
-
-
Package org.apache.tika.parser.geopkg
-
Class org.apache.tika.parser.geopkg.GeoPkgParser
class GeoPkgParser extends SQLite3Parser implements Serializable- serialVersionUID:
- -752276948656079347L
-
-
Package org.apache.tika.parser.grib
-
Class org.apache.tika.parser.grib.GribParser
class GribParser extends Object implements Serializable- serialVersionUID:
- 7855458954474247655L
-
-
Package org.apache.tika.parser.hdf
-
Class org.apache.tika.parser.hdf.HDFParser
class HDFParser extends Object implements Serializable- serialVersionUID:
- 1091208208003437549L
-
-
Package org.apache.tika.parser.isatab
-
Class org.apache.tika.parser.isatab.ISArchiveParser
class ISArchiveParser extends Object implements Serializable- serialVersionUID:
- 3640809327541300229L
-
-
Package org.apache.tika.parser.journal
-
Class org.apache.tika.parser.journal.JournalParser
class JournalParser extends Object implements Serializable- serialVersionUID:
- 4664255544154296438L
-
-
Package org.apache.tika.parser.multiple
-
Class org.apache.tika.parser.multiple.AbstractMultipleParser
class AbstractMultipleParser extends Object implements Serializable- serialVersionUID:
- 5383668090329836559L
-
Serialized Fields
-
offeredTypes
Set<MediaType> offeredTypes
Computed list of Mime Types to offer, which is all those in common between the parsers. For explicit mimetypes only, use aParserDecorator -
parsers
Collection<? extends Parser> parsers
List of the multiple parsers to try. -
policy
AbstractMultipleParser.MetadataPolicy policy
How we should handle metadata clashes -
registry
MediaTypeRegistry registry
Media type registry.
-
-
Class org.apache.tika.parser.multiple.FallbackParser
class FallbackParser extends AbstractMultipleParser implements Serializable- serialVersionUID:
- 5844409020977206167L
-
Class org.apache.tika.parser.multiple.SupplementingParser
class SupplementingParser extends AbstractMultipleParser implements Serializable- serialVersionUID:
- 313179254565350994L
-
-
Package org.apache.tika.parser.ner
-
Class org.apache.tika.parser.ner.NamedEntityParser
class NamedEntityParser extends Object implements Serializable-
Serialized Fields
-
available
boolean available
-
initialized
boolean initialized
-
nerChain
List<NERecogniser> nerChain
-
secondaryParser
Tika secondaryParser
-
-
-
-
Package org.apache.tika.parser.netcdf
-
Class org.apache.tika.parser.netcdf.NetCDFParser
class NetCDFParser extends Object implements Serializable- serialVersionUID:
- -5940938274907708665L
-
-
Package org.apache.tika.parser.pot
-
Class org.apache.tika.parser.pot.PooledTimeSeriesParser
class PooledTimeSeriesParser extends Object implements Serializable- serialVersionUID:
- -2855917932512164988L
-
-
Package org.apache.tika.parser.recognition
-
Class org.apache.tika.parser.recognition.AgeRecogniser
class AgeRecogniser extends Object implements Serializable- serialVersionUID:
- 1108439049093046832L
-
Serialized Fields
-
config
AgeRecogniserConfig config
-
secondaryParser
Tika secondaryParser
-
-
Class org.apache.tika.parser.recognition.ObjectRecognitionParser
class ObjectRecognitionParser extends Object implements Serializable-
Serialized Fields
-
recogniser
ObjectRecogniser recogniser
-
-
-
-
Package org.apache.tika.parser.recognition.tf
-
Class org.apache.tika.parser.recognition.tf.TensorflowImageRecParser
class TensorflowImageRecParser extends ExternalParser implements Serializable
-
-
Package org.apache.tika.parser.sentiment
-
Class org.apache.tika.parser.sentiment.SentimentAnalysisParser
class SentimentAnalysisParser extends Object implements Serializable-
Serialized Fields
-
classifier
opennlp.tools.sentiment.SentimentME classifier
-
modelPath
String modelPath
Path to model path. Default is "https://raw.githubusercontent.com/USCDataScience/SentimentAnalysisParser/master/sentiment-models/src/main/resources/edu/usc/irds/sentiment/en-netflix-sentiment.bin"
The path could be one of the following:- a HTTP or HTTPS URL (Not recommended for production use since no caching is implemented)
- an absolute or relative path on local file system (recommended for production use in standalone mode)
- a relative path known to class loader (Especially useful in distributed environments, recommended for advanced users
-
-
-
-
Package org.apache.tika.parser.sqlite3
-
Class org.apache.tika.parser.sqlite3.SQLite3DBParser
class SQLite3DBParser extends org.apache.tika.parser.jdbc.AbstractDBParser implements Serializable-
Serialized Fields
-
tmpFile
Path tmpFile
-
-
-
Class org.apache.tika.parser.sqlite3.SQLite3Parser
class SQLite3Parser extends Object implements Serializable- serialVersionUID:
- -752276948656079347L
-
-
Package org.apache.tika.parser.transcribe.aws
-
Class org.apache.tika.parser.transcribe.aws.AmazonTranscribe
class AmazonTranscribe extends Object implements Serializable-
Serialized Fields
-
amazonS3
software.amazon.awssdk.services.s3.S3Client amazonS3
-
amazonTranscribeAsync
software.amazon.awssdk.services.transcribe.TranscribeAsyncClient amazonTranscribeAsync
-
bucketName
String bucketName
-
clientId
String clientId
-
clientSecret
String clientSecret
-
credsProvider
software.amazon.awssdk.auth.credentials.StaticCredentialsProvider credsProvider
-
isAvailable
boolean isAvailable
-
region
String region
-
-
-
-
Package org.apache.tika.pipes
-
Exception Class org.apache.tika.pipes.FailedToStartClientException
class FailedToStartClientException extends RuntimeException implements Serializable -
Class org.apache.tika.pipes.FetchEmitTuple
class FetchEmitTuple extends Object implements Serializable-
Serialized Fields
-
embeddedDocumentBytesConfig
EmbeddedDocumentBytesConfig embeddedDocumentBytesConfig
-
emitKey
EmitKey emitKey
-
fetchKey
FetchKey fetchKey
-
id
String id
-
metadata
Metadata metadata
-
onParseException
FetchEmitTuple.ON_PARSE_EXCEPTION onParseException
-
parseContext
ParseContext parseContext
-
-
-
Class org.apache.tika.pipes.HandlerConfig
class HandlerConfig extends Object implements Serializable- serialVersionUID:
- -3861669115439125268L
-
Serialized Fields
-
maxEmbeddedResources
int maxEmbeddedResources
-
parseMode
HandlerConfig.PARSE_MODE parseMode
-
throwOnWriteLimitReached
boolean throwOnWriteLimitReached
-
type
BasicContentHandlerFactory.HANDLER_TYPE type
-
writeLimit
int writeLimit
-
-
Exception Class org.apache.tika.pipes.PipesException
class PipesException extends Exception implements Serializable
-
-
Package org.apache.tika.pipes.async
-
Exception Class org.apache.tika.pipes.async.OfferLargerThanQueueSize
class OfferLargerThanQueueSize extends IllegalArgumentException implements Serializable-
Serialized Fields
-
queueSize
int queueSize
-
sizeOffered
int sizeOffered
-
-
-
-
Package org.apache.tika.pipes.emitter
-
Class org.apache.tika.pipes.emitter.EmitData
class EmitData extends Object implements Serializable- serialVersionUID:
- -3861669115439125268L
-
Serialized Fields
-
containerStackTrace
String containerStackTrace
-
emitKey
EmitKey emitKey
-
metadataList
List<Metadata> metadataList
-
parseContext
ParseContext parseContext
-
-
Class org.apache.tika.pipes.emitter.EmitKey
class EmitKey extends Object implements Serializable- serialVersionUID:
- -3861669115439125268L
-
Exception Class org.apache.tika.pipes.emitter.TikaEmitterException
class TikaEmitterException extends TikaException implements Serializable
-
-
Package org.apache.tika.pipes.extractor
-
Class org.apache.tika.pipes.extractor.EmbeddedDocumentBytesConfig
class EmbeddedDocumentBytesConfig extends Object implements Serializable- serialVersionUID:
- -3861669115439125268L
-
Serialized Fields
-
embeddedIdPrefix
String embeddedIdPrefix
-
emitKeyBase
String emitKeyBase
-
emitter
String emitter
-
extractEmbeddedDocumentBytes
boolean extractEmbeddedDocumentBytes
-
includeOriginal
boolean includeOriginal
-
suffixStrategy
EmbeddedDocumentBytesConfig.SUFFIX_STRATEGY suffixStrategy
-
zeroPadName
int zeroPadName
-
-
-
Package org.apache.tika.pipes.fetcher
-
Exception Class org.apache.tika.pipes.fetcher.FetcherStringException
class FetcherStringException extends TikaException implements Serializable -
Class org.apache.tika.pipes.fetcher.FetchKey
class FetchKey extends Object implements Serializable- serialVersionUID:
- -3861669115439125268L
-
-
Package org.apache.tika.renderer
-
Class org.apache.tika.renderer.CompositeRenderer
class CompositeRenderer extends Object implements Serializable
-
-
Package org.apache.tika.sax
-
Class org.apache.tika.sax.AbstractRecursiveParserWrapperHandler
class AbstractRecursiveParserWrapperHandler extends DefaultHandler implements Serializable-
Serialized Fields
-
contentHandlerFactory
ContentHandlerFactory contentHandlerFactory
-
embeddedDepth
int embeddedDepth
-
embeddedResources
int embeddedResources
-
maxEmbeddedResources
int maxEmbeddedResources
-
-
-
Class org.apache.tika.sax.BasicContentHandlerFactory
class BasicContentHandlerFactory extends Object implements Serializable-
Serialized Fields
-
parseContext
ParseContext parseContext
-
throwOnWriteLimitReached
boolean throwOnWriteLimitReached
-
type
BasicContentHandlerFactory.HANDLER_TYPE type
-
writeLimit
int writeLimit
-
-
-
Class org.apache.tika.sax.RecursiveParserWrapperHandler
class RecursiveParserWrapperHandler extends AbstractRecursiveParserWrapperHandler implements Serializable-
Serialized Fields
-
metadataFilter
MetadataFilter metadataFilter
-
metadataList
List<Metadata> metadataList
-
-
-
Exception Class org.apache.tika.sax.StoppingEarlyException
class StoppingEarlyException extends SAXException implements Serializable -
Exception Class org.apache.tika.sax.TaggedSAXException
class TaggedSAXException extends SAXException implements Serializable-
Serialized Fields
-
tag
Object tag
The object reference used to tag the exception.
-
-
-
-
Package org.apache.tika.serialization
-
Exception Class org.apache.tika.serialization.TikaSerializationException
class TikaSerializationException extends TikaException implements Serializable
-
-
Package org.apache.tika.server.client
-
Exception Class org.apache.tika.server.client.TikaClientConfigException
class TikaClientConfigException extends TikaException implements Serializable
-
-
Package org.apache.tika.server.core
-
Exception Class org.apache.tika.server.core.TikaServerParseException
class TikaServerParseException extends jakarta.ws.rs.WebApplicationException implements Serializable
-
-
Package org.apache.tika.utils
-
Class org.apache.tika.utils.XMLReaderUtils
class XMLReaderUtils extends Object implements Serializable- serialVersionUID:
- 6110455808615143122L
-
-
Package org.apache.tika.xmp
-
Class org.apache.tika.xmp.XMPMetadata
class XMPMetadata extends Metadata implements Serializable-
Serialization Methods
-
readObject
- Throws:
ClassNotFoundExceptionIOException
-
writeObject
- Throws:
IOException
-
-
Serialized Fields
-
xmpData
com.adobe.internal.xmp.XMPMeta xmpData
The XMP data
-
-
-