Serialized Form
-
Package org.apache.tika.detect.microsoft
-
Class org.apache.tika.detect.microsoft.POIFSContainerDetector extends Object implements Serializable
- serialVersionUID:
- -3028021741663605293L
-
Serialized Fields
-
markLimit
int markLimit
-
-
-
Package org.apache.tika.detect.microsoft.ooxml
-
Class org.apache.tika.detect.microsoft.ooxml.OPCPackageDetector extends Object implements Serializable
-
-
Package org.apache.tika.parser.microsoft
-
Class org.apache.tika.parser.microsoft.AbstractOfficeParser extends Object implements Serializable
-
Serialized Fields
-
defaultOfficeParserConfig
OfficeParserConfig defaultOfficeParserConfig
-
-
-
Class org.apache.tika.parser.microsoft.EMFParser extends Object implements Serializable
-
Class org.apache.tika.parser.microsoft.JackcessParser extends Object implements Serializable
- serialVersionUID:
- -752276948656079347L
-
Serialized Fields
-
locale
Locale locale
-
-
Class org.apache.tika.parser.microsoft.MSOwnerFileParser extends Object implements Serializable
- serialVersionUID:
- -752276948656079347L
-
Class org.apache.tika.parser.microsoft.OfficeParser extends AbstractOfficeParser implements Serializable
- serialVersionUID:
- 7393462244028653479L
-
Class org.apache.tika.parser.microsoft.OfficeParserConfig extends Object implements Serializable
-
Serialized Fields
-
concatenatePhoneticRuns
boolean concatenatePhoneticRuns
-
dateOverrideFormat
String dateOverrideFormat
-
extractAllAlternativesFromMSG
boolean extractAllAlternativesFromMSG
-
extractExtendedMsgProperties
boolean extractExtendedMsgProperties
-
extractMacros
boolean extractMacros
-
includeDeletedContent
boolean includeDeletedContent
-
includeHeadersAndFooters
boolean includeHeadersAndFooters
-
includeMissingRows
boolean includeMissingRows
-
includeMoveFromContent
boolean includeMoveFromContent
-
includeShapeBasedContent
boolean includeShapeBasedContent
-
includeSlideMasterContent
boolean includeSlideMasterContent
-
includeSlideNotes
boolean includeSlideNotes
-
maxOverride
int maxOverride
-
useSAXDocxExtractor
boolean useSAXDocxExtractor
-
useSAXPptxExtractor
boolean useSAXPptxExtractor
-
writeSelectHeadersInBody
boolean writeSelectHeadersInBody
-
-
-
Class org.apache.tika.parser.microsoft.OldExcelParser extends Object implements Serializable
- serialVersionUID:
- 4611820730372823452L
-
Class org.apache.tika.parser.microsoft.TikaExcelGeneralFormat extends Format implements Serializable
- serialVersionUID:
- 1L
-
Serialized Fields
-
decimalFormat
DecimalFormat decimalFormat
-
decimalSymbols
DecimalFormatSymbols decimalSymbols
-
integerFormat
DecimalFormat integerFormat
-
scientificFormat
DecimalFormat scientificFormat
-
-
Class org.apache.tika.parser.microsoft.TNEFParser extends Object implements Serializable
- serialVersionUID:
- 4611820730372823452L
-
Class org.apache.tika.parser.microsoft.WMFParser extends Object implements Serializable
-
-
Package org.apache.tika.parser.microsoft.activemime
-
Class org.apache.tika.parser.microsoft.activemime.ActiveMimeParser extends Object implements Serializable
-
-
Package org.apache.tika.parser.microsoft.chm
-
Class org.apache.tika.parser.microsoft.chm.ChmItsfHeader extends Object implements Serializable
- serialVersionUID:
- 2215291838533213826L
-
Serialized Fields
-
currentPlace
int currentPlace
-
data_offset
long data_offset
-
dataRemained
int dataRemained
-
dir_len
long dir_len
-
dir_offset
long dir_offset
-
dir_uuid
byte[] dir_uuid
-
header_len
int header_len
-
lang_id
long lang_id
-
last_modified
long last_modified
-
signature
byte[] signature
-
stream_uuid
byte[] stream_uuid
-
unknown_000c
int unknown_000c
-
unknown_len
long unknown_len
-
unknown_offset
long unknown_offset
-
version
int version
-
-
Class org.apache.tika.parser.microsoft.chm.ChmItspHeader extends Object implements Serializable
- serialVersionUID:
- 1962394421998181341L
-
Serialized Fields
-
block_len
long block_len
-
blockidx_intvl
int blockidx_intvl
-
currentPlace
int currentPlace
-
dataRemained
int dataRemained
-
header_len
int header_len
-
index_depth
int index_depth
-
index_head
int index_head
-
index_root
int index_root
-
lang_id
long lang_id
-
num_blocks
long num_blocks
-
signature
byte[] signature
-
system_uuid
byte[] system_uuid
-
unknown_000c
int unknown_000c
-
unknown_0024
int unknown_0024
-
unknown_002c
int unknown_002c
-
unknown_0044
byte[] unknown_0044
-
version
int version
-
-
Class org.apache.tika.parser.microsoft.chm.ChmLzxcControlData extends Object implements Serializable
- serialVersionUID:
- -7897854774939631565L
-
Serialized Fields
-
currentPlace
int currentPlace
-
dataRemained
int dataRemained
-
resetInterval
long resetInterval
-
signature
byte[] signature
-
size
long size
-
unknown_18
long unknown_18
-
version
long version
-
windowSize
long windowSize
-
windowsPerReset
long windowsPerReset
-
-
Class org.apache.tika.parser.microsoft.chm.ChmLzxcResetTable extends Object implements Serializable
- serialVersionUID:
- -8209574429411707460L
-
Serialized Fields
-
block_address
long[] block_address
-
block_count
long block_count
-
block_len
long block_len
-
compressed_len
long compressed_len
-
currentPlace
int currentPlace
-
dataRemained
int dataRemained
-
table_offset
long table_offset
-
uncompressed_len
long uncompressed_len
-
unknown
long unknown
-
version
long version
-
-
Class org.apache.tika.parser.microsoft.chm.ChmParser extends Object implements Serializable
- serialVersionUID:
- 5938777307516469802L
-
Class org.apache.tika.parser.microsoft.chm.ChmParsingException extends org.apache.tika.exception.TikaException implements Serializable
- serialVersionUID:
- 6497936044733665210L
-
Class org.apache.tika.parser.microsoft.chm.ChmPmgiHeader extends Object implements Serializable
- serialVersionUID:
- -2092282339894303701L
-
Serialized Fields
-
currentPlace
int currentPlace
-
dataRemained
int dataRemained
-
free_space
long free_space
-
signature
byte[] signature
-
-
Class org.apache.tika.parser.microsoft.chm.ChmPmglHeader extends Object implements Serializable
- serialVersionUID:
- -6139486487475923593L
-
Serialized Fields
-
block_next
int block_next
-
block_prev
int block_prev
-
currentPlace
int currentPlace
-
dataRemained
int dataRemained
-
free_space
long free_space
-
signature
byte[] signature
-
unknown_0008
long unknown_0008
-
-
-
Package org.apache.tika.parser.microsoft.libpst
-
Class org.apache.tika.parser.microsoft.libpst.LibPstParser extends Object implements Serializable
-
Serialized Fields
-
defaultConfig
LibPstParserConfig defaultConfig
-
readPstPath
String readPstPath
-
-
-
Class org.apache.tika.parser.microsoft.libpst.LibPstParserConfig extends Object implements Serializable
-
Serialized Fields
-
includeDeleted
boolean includeDeleted
-
isDebug
boolean isDebug
In initial tests, setting this to true resulted in more emails being extracted. It did dramatically slow down processing time. :( -
maxEmails
int maxEmails
max emails to process. Will process everything if this value is < 0 -
processEmailAsMsg
boolean processEmailAsMsg
Should readpst also output msg files for processing. In an initial test, not as many attachments were extracted from msg files. Not yet clear if that is a POI limitation or a problem with libpst -
timeoutSeconds
long timeoutSeconds
-
-
-
-
Package org.apache.tika.parser.microsoft.onenote
-
Class org.apache.tika.parser.microsoft.onenote.OneNoteParser extends Object implements Serializable
- serialVersionUID:
- -5504243905998074168L
-
Serialized Fields
-
options
OneNoteTreeWalkerOptions options
-
-
Class org.apache.tika.parser.microsoft.onenote.OneNoteTreeWalkerOptions extends Object implements Serializable
-
Serialized Fields
-
crawlAllFileNodesFromRoot
boolean crawlAllFileNodesFromRoot
-
onlyLatestRevision
boolean onlyLatestRevision
-
utf16PropertiesToPrint
Set<OneNotePropertyEnum> utf16PropertiesToPrint
-
-
-
-
Package org.apache.tika.parser.microsoft.onenote.fsshttpb.exception
-
Class org.apache.tika.parser.microsoft.onenote.fsshttpb.exception.DataElementParseErrorException extends RuntimeException implements Serializable
-
Serialized Fields
-
index
int index
-
-
-
-
Package org.apache.tika.parser.microsoft.onenote.fsshttpb.streamobj
-
Class org.apache.tika.parser.microsoft.onenote.fsshttpb.streamobj.StreamObjectParseErrorException extends RuntimeException implements Serializable
-
Serialized Fields
-
index
int index
-
streamObjectTypeName
String streamObjectTypeName
-
-
-
-
Package org.apache.tika.parser.microsoft.onenote.fsshttpb.unsigned
-
Class org.apache.tika.parser.microsoft.onenote.fsshttpb.unsigned.UByte extends UNumber implements Serializable
- serialVersionUID:
- -6821055240959745390L
-
Serialization Methods
-
readResolve
private Object readResolve() throws ObjectStreamException
Replace version read through deserialization with cached version. Note that this does not use theUByte.valueOfUnchecked(short)as we have no guarantee that the value from the stream is valid.- Throws:
ObjectStreamException
-
-
Serialized Fields
-
value
short value
The value modelling the content of thisunsigned byte
-
-
Class org.apache.tika.parser.microsoft.onenote.fsshttpb.unsigned.UInteger extends UNumber implements Serializable
- serialVersionUID:
- -6821055240959745390L
-
Serialization Methods
-
readResolve
private Object readResolve() throws ObjectStreamException
Replace version read through deserialization with cached version.- Throws:
ObjectStreamException
-
-
Serialized Fields
-
value
long value
The value modelling the content of thisunsigned int
-
-
Class org.apache.tika.parser.microsoft.onenote.fsshttpb.unsigned.ULong extends UNumber implements Serializable
- serialVersionUID:
- -6821055240959745390L
-
Serialized Fields
-
value
long value
The value modelling the content of thisunsigned long
-
-
Class org.apache.tika.parser.microsoft.onenote.fsshttpb.unsigned.UNumber extends Number implements Serializable
- serialVersionUID:
- -7666221938815339843L
-
Class org.apache.tika.parser.microsoft.onenote.fsshttpb.unsigned.UShort extends UNumber implements Serializable
- serialVersionUID:
- -6821055240959745390L
-
Serialized Fields
-
value
int value
The value modelling the content of thisunsigned short
-
-
-
Package org.apache.tika.parser.microsoft.ooxml
-
Class org.apache.tika.parser.microsoft.ooxml.OOXMLParser extends AbstractOfficeParser implements Serializable
- serialVersionUID:
- 6535995710857776481L
-
-
Package org.apache.tika.parser.microsoft.ooxml.xwpf.ml2006
-
Class org.apache.tika.parser.microsoft.ooxml.xwpf.ml2006.Word2006MLParser extends AbstractOfficeParser implements Serializable
-
-
Package org.apache.tika.parser.microsoft.pst
-
Class org.apache.tika.parser.microsoft.pst.OutlookPSTParser extends Object implements Serializable
- serialVersionUID:
- 620998217748364063L
-
Class org.apache.tika.parser.microsoft.pst.PSTMailItemParser extends Object implements Serializable
-
-
Package org.apache.tika.parser.microsoft.rtf
-
Class org.apache.tika.parser.microsoft.rtf.RTFParser extends Object implements Serializable
- serialVersionUID:
- -4165069489372320313L
-
Serialized Fields
-
ignoreListMarkup
boolean ignoreListMarkup
-
memoryLimitInKb
int memoryLimitInKb
-
-
-
Package org.apache.tika.parser.microsoft.xml
-
Class org.apache.tika.parser.microsoft.xml.AbstractXML2003Parser extends Object implements Serializable
-
Class org.apache.tika.parser.microsoft.xml.SpreadsheetMLParser extends AbstractXML2003Parser implements Serializable
-
Class org.apache.tika.parser.microsoft.xml.WordMLParser extends AbstractXML2003Parser implements Serializable
-