String fileName
String replicaId
ReplicaStoreState newvalue
String checksum
boolean changestorestate
boolean changechecksum
RemoteFile theRemoteFile
String precomputedChecksum
String baApplicationId
String originatingBatchMsgId
int noOfFilesProcessed
Collection<E> filesFailed
RemoteFile rf
List<E> exceptions
FileBatchJob job
String replicaId
List<E> args
String batchID
int noOfFilesProcessed
HashSet<E> filesFailed
RemoteFile resultFile
String terminateID
String arcfileName
RemoteFile remoteFile
String replicaId
String arcfile
long index
BitarchiveRecord record
long timestamp
String applicationId
String fileName
RemoteFile remoteFile
String replicaId
String checksum
String credentials
String arcfileName
RemoteFile theRemoteFile
String precomputedChecksum
RemoteFile theRemoteFile
String arcFilename
String theIncorrectChecksum
String replicaId
String credentials
RemoteFile removedFile
RemoteFile rf
String replicaId
RemoteFile remoteFile
String replicaId
String arcFilename
String checksum
String replicaId
boolean isReply
File file
boolean useChecksums
boolean fileDeletable
boolean multipleDownloads
long filesize
private void readObject(ObjectInputStream ois)
IOFailure
- if Java could not deserialize the object.private void writeObject(ObjectOutputStream oos)
IOFailure
- if Java could not serialize the object.String name
String ftpFileName
FTPConnectionManager connectionManager
File dataFile
String ftpServerName
int ftpServerPort
String ftpUserName
String ftpUserPassword
int ftpRetries
int ftpDataTimeout
String ftpServerName
int ftpServerPort
String ftpUserName
String ftpUserPassword
String ftpFileName
String checksum
FTPConnectionManager cm
Serializable serializable
String id
private void readObject(ObjectInputStream s)
private void writeObject(ObjectOutputStream s)
boolean failsOnCopy
String fileName
byte[] objectBuffer
long offset
long length
RemoteFile objectAsRemoteFile
boolean isStoredAsRemoteFile
boolean hasRemoteFileBeenDeleted
long LIMIT_FOR_SAVING_DATA_IN_OBJECT_BUFFER
int noOfRecordsProcessed
int noOfRecordsProcessed
String name
String name
private void readObject(ObjectInputStream s)
private void writeObject(ObjectOutputStream s) throws IOFailure
IOFailure
- If an exception is caught during writing of the object.Date since
Pattern filesToProcess
int noOfFilesProcessed
long batchJobTimeout
Set<E> filesFailed
List<E> exceptions
String fileName
long fileOffset
long outputOffset
Exception exception
boolean inInitialize
boolean inFinish
private void readObject(ObjectInputStream s)
private void readObject(ObjectInputStream in) throws IOException, ClassNotFoundException
IOException
- If there is an error reading from the stream, or the serialized object cannot be deserialized
due to errors in the serialized form.ClassNotFoundException
- If the class definition of the serialized object cannot be found.private void writeObject(ObjectOutputStream out) throws IOException
IOException
- In case there is an error from the underlying stream, or this object cannot be serialized.private void readObject(ObjectInputStream in) throws IOException, ClassNotFoundException
IOException
- If there is an error reading from the stream, or the serialized object cannot be deserialized
due to errors in the serialized form.ClassNotFoundException
- If the class definition of the serialized object cannot be found.private void writeObject(ObjectOutputStream out) throws IOException
IOException
- In case there is an error from the underlying stream, or this object cannot be serialized.ClassLoader multipleClassLoader
String jobClass
List<E> args
String testId
String name
String[] fields
boolean includeChecksum
String[] fields
boolean includeChecksum
String filtername
String[] fields
boolean includeChecksum
int noOfRecordsProcessed
org.dom4j.Document template
boolean verified
String template
Long forceMaxbytesPerDomain
Long forceMaxobjectsPerDomain
boolean verified
String ARCHIVER_BEAN_REFERENCE_PLACEHOLDER
String ARCHIVER_PROCESSOR_BEAN_PLACEHOLDER
boolean isActive
long template_id
Long jobID
Long origHarvestDefinitionID
JobStatus status
String channel
HarvestChannel
on which this job will be posted.boolean isSnapshot
long forceMaxObjectsPerDomain
long forceMaxBytesPerDomain
String orderXMLname
HeritrixTemplate orderXMLdoc
File[] settingsXMLfiles
Set<E> seedListSet
int harvestNum
String harvestErrors
String harvestErrorDetails
String uploadErrors
String uploadErrorDetails
Date actualStart
Date actualStop
Date submittedDate
Date creationDate
long edition
Long resubmittedAsJobWithID
Long continuationOF
Map<K,V> domainConfigurationMap
boolean configsChanged
boolean configurationSetsObjectLimit
boolean configurationSetsByteLimit
long minCountObjects
long maxCountObjects
long totalCountObjects
long forceMaxRunningTime
boolean underConstruction
Jobs loaded from the DAO are never under construction anymore.
boolean maxObjectsIsSetByQuotaEnforcer
String harvestnamePrefix
String harvestAudience
int repeats
String name
String comments
Date startDate
Frequency frequency
long edition
Long id
Date endDate
Long extendedFieldID
Long extendedFieldTypeID
String name
String formattingPattern
int datatype
boolean mandatory
int sequencenr
int maxlen
String defaultValue
String options
Long harvestId
boolean indexOK
String date
boolean removeW3xSubDomain
boolean addBeforeRemovingW3xSubDomain
boolean addW3SubDomain
boolean addBeforeAddingW3SubDomain
boolean allowSubDomainsRewrite
long jobID
long harvestID
String hostUrl
CrawlProgressMessage.CrawlStatus status
String progressStatisticsLegend
CrawlProgressMessage.CrawlServiceJobInfo.progressStatistics
property.CrawlProgressMessage.CrawlServiceInfo heritrixStatus
CrawlProgressMessage.CrawlServiceJobInfo jobStatus
int alertCount
boolean isCrawling
String currentJob
long discoveredFilesCount
long downloadedFilesCount
String frontierShortReport
long elapsedSeconds
long currentProcessedKBPerSec
long processedKBPerSec
double currentProcessedDocsPerSec
double processedDocsPerSec
int activeToeCount
String progressStatistics
String status
long jobID
JobStatus statusCode
HarvestReport harvestReport
String harvestErrors
String harvestErrorDetails
String uploadErrors
String uploadErrorDetails
long objectCount
long byteCount
StopReason stopReason
private void readObject(ObjectInputStream s) throws ClassNotFoundException, IOException
ClassNotFoundException
- In case the object read is of unknown class.IOException
- On I/O trouble reading the object.private void writeObject(ObjectOutputStream s) throws IOException
IOException
- On I/O trouble writing the object.Job submittedJob
HarvestDefinitionInfo origHarvestInfo
List<E> metadata
String filterId
InMemoryFrontierReport report
Long jobID
String harvestChannelName
boolean isValid
HarvestChannel
.boolean isSnapshot
HarvestChannel
handles snapshot or focused harvests. Meaningless if HarvesterRegistrationResponse.isValid
is false.long jobId
JobStatus jobStatus
long numberOfCURIsHandled
org.apache.commons.logging.Log log
long numberOfCURIsHandled
long numberOfLinksExtracted
String domainName
long currentSize
long precedence
https://webarchive.jira.com/wiki/display/Heritrix/Precedence+Feature+Notes
long totalEnqueues
long sessionBalance
double lastCost
double averageCost
String lastDequeueTime
String wakeTime
long totalSpend
long totalBudget
long errorCount
String lastPeekUri
String lastQueuedUri
com.sleepycat.je.Environment dbEnvironment
com.sleepycat.persist.EntityStore store
com.sleepycat.persist.PrimaryIndex<PK,E> linesIndex
com.sleepycat.persist.SecondaryIndex<SK,PK,E> linesByDomain
com.sleepycat.persist.SecondaryIndex<SK,PK,E> linesByCurrentSize
com.sleepycat.persist.SecondaryIndex<SK,PK,E> linesBySpentBudget
File storageDir
private void readObject(ObjectInputStream s) throws ClassNotFoundException, IOException
ClassNotFoundException
- If the class of the serialized object could not be foundIOException
- If an I/O error occurred while reading the serialized objectprivate void writeObject(ObjectOutputStream s) throws IOException
IOException
- If an I/O error occurred while writing to the outputstreamStopReason defaultStopReason
DomainStatsReport domainstatsReport
Map<K,V> domainStats
StopReason defaultStopReason
private void readObject(ObjectInputStream s)
private void writeObject(ObjectOutputStream s)
Set<E> requestedJobs
RequestType requestType
Set<E> foundJobs
List<E> resultFiles
if indexIsStoredInDirectory is false, this list must contain exactly one file (or not have been set yet).
boolean indexIsStoredInDirectory
boolean shouldReturnIndex
Long harvestId
RemoteFileSettings optionalConnectionSettings
org.archive.crawler.settings.StringList keywords
int pages
int resultsPerPage
org.archive.crawler.settings.StringList geoLocations
String language
boolean queueLinks
boolean queueUserStatus
boolean queueUserStatusLinks
boolean queueKeywordLinks
twitter4j.Twitter twitter
int tweetCount
int linkCount
com.antiaction.common.servlet.AutoIncrement resourceAutoInc
HostEntry hostEntry
String regexp
String domain
DeduplicateToCDXAdapter adapter
Pattern crawlLogUrlPattern
org.archive.wayback.resourcestore.indexer.ARCRecordToSearchResultAdapter aToSAdapter
org.archive.wayback.resourceindex.cdx.SearchResultToCDXLineAdapter srToCDXAdapter
org.archive.wayback.resourcestore.indexer.WARCRecordToSearchResultAdapter aToSAdapter
org.archive.wayback.resourceindex.cdx.SearchResultToCDXLineAdapter srToCDXAdapter
org.apache.lucene.search.IndexSearcher index
org.apache.lucene.index.IndexReader indexReader
String mimefilter
boolean blacklist
SimpleDateFormat sdfLastModified
SimpleDateFormat sdfIndexDate
long processedURLs
long unchangedURLs
boolean useSparseRangeFilter
org.apache.lucene.search.IndexSearcher index
org.apache.lucene.index.IndexReader indexReader
boolean lookupByURL
boolean equivalent
String mimefilter
boolean blacklist
boolean doTimestampAnalysis
boolean doETagAnalysis
boolean statsPerHost
boolean changeContentSize
boolean useOrigin
boolean useOriginFromIndex
boolean useSparseRangeFilter
is.hi.bok.deduplicator.Statistics stats
HashMap<K,V> perHostStats
boolean skipWriting
long crawlerStartTime
long crawlerEndTime
long crawlerPauseStarted
long crawlerTotalPausedTime
long lastLogPointTime
boolean shouldrun
org.archive.checkpointing.Checkpoint checkpoint
private void readObject(ObjectInputStream arg0) throws IOException, ClassNotFoundException
IOException
ClassNotFoundException
org.archive.crawler.framework.Checkpointer checkpointer
long maxBytes
long maxDocument
long maxTime
StringBuffer manifest
org.archive.crawler.framework.StatisticsTracking statistics
String attrDecideRules
org.archive.crawler.framework.Processor defaultNextProcessor
private void readObject(ObjectInputStream arg0) throws IOException, ClassNotFoundException
IOException
ClassNotFoundException
Logger logger
long totalBytesWritten
Copyright © 2005–2016 The Royal Danish Library, the Danish State and University Library, the National Library of France and the Austrian National Library.. All rights reserved.