public class DocumentIndex extends Segment
Modifier and Type | Class and Description |
---|---|
static interface |
DocumentIndex.CallbackListener |
(package private) class |
DocumentIndex.Worker |
Segment.ReferenceReport, Segment.ReferenceReportCache
Modifier and Type | Field and Description |
---|---|
private DocumentIndex.CallbackListener |
callback |
private static AnchorURL |
poison |
private java.util.concurrent.BlockingQueue<AnchorURL> |
queue |
private int |
timezoneOffset |
private DocumentIndex.Worker[] |
worker |
(package private) static java.lang.ThreadGroup |
workerThreadGroup |
catchallHash, catchallString, catchallWord, citationIndexName, citationReferenceFactory, firstSeenIndex, firstseenIndexName, fulltext, lowcachedivisor, merger, targetFileSize, termIndex, termIndexName, urlCitationIndex, wCacheMaxAge, wCacheMaxChunk, wordOrder, wordReferenceFactory, writeBufferSize
Constructor and Description |
---|
DocumentIndex(java.io.File segmentPath,
java.io.File archivePath,
java.io.File collectionConfigurationPath,
java.io.File webgraphConfigurationPath,
DocumentIndex.CallbackListener callback,
int cachesize,
int timezoneOffset) |
Modifier and Type | Method and Description |
---|---|
private SolrInputDocument[] |
add(AnchorURL url,
int timezoneOffset) |
void |
addConcurrent(AnchorURL start)
add a file or a directory of files to the index If the given file is a path to a directory, the
complete sub-tree is indexed
|
void |
clearQueue() |
void |
close()
close the index.
|
int |
pending()
get the number of pending documents in the indexing queue
|
citationCount, citationSegmentCount, clear, clearCaches, connectCitation, connectedCitation, connectedRWI, connectRWI, disconnectCitation, disconnectRWI, firstSeen, fulltext, getFirstSeenTime, getLoadTime, getLocation, getReferenceReportCache, getWordCountGuess, putDocument, removeAllUrlReferences, removeAllUrlReferences, RWIBufferCount, RWICount, RWISegmentCount, setFirstSeenTime, storeDocument, storeRWI, storeRWI, termIndex, urlCitation, urlSelector
private static AnchorURL poison
private java.util.concurrent.BlockingQueue<AnchorURL> queue
private final DocumentIndex.Worker[] worker
private DocumentIndex.CallbackListener callback
private int timezoneOffset
static final java.lang.ThreadGroup workerThreadGroup
public DocumentIndex(java.io.File segmentPath, java.io.File archivePath, java.io.File collectionConfigurationPath, java.io.File webgraphConfigurationPath, DocumentIndex.CallbackListener callback, int cachesize, int timezoneOffset) throws java.io.IOException
java.io.IOException
public int pending()
public void clearQueue()
private SolrInputDocument[] add(AnchorURL url, int timezoneOffset) throws java.io.IOException
java.io.IOException
public void addConcurrent(AnchorURL start) throws java.io.IOException
start
- java.io.IOException