Lucene++ - a full-featured, c++ search engine
API Documentation


Loading...
Searching...
No Matches
Public Member Functions | Static Public Member Functions | Static Public Attributes | Protected Member Functions | Protected Attributes | Static Protected Attributes
Lucene::IndexWriter Class Reference

An IndexWriter creates and maintains an index. More...

#include <IndexWriter.h>

+ Inheritance diagram for Lucene::IndexWriter:

Public Member Functions

 IndexWriter (const DirectoryPtr &d, const AnalyzerPtr &a, bool create, int32_t mfl)
 
 IndexWriter (const DirectoryPtr &d, const AnalyzerPtr &a, int32_t mfl)
 
 IndexWriter (const DirectoryPtr &d, const AnalyzerPtr &a, const IndexDeletionPolicyPtr &deletionPolicy, int32_t mfl)
 
 IndexWriter (const DirectoryPtr &d, const AnalyzerPtr &a, bool create, const IndexDeletionPolicyPtr &deletionPolicy, int32_t mfl)
 
 IndexWriter (const DirectoryPtr &d, const AnalyzerPtr &a, const IndexDeletionPolicyPtr &deletionPolicy, int32_t mfl, const IndexCommitPtr &commit)
 
virtual ~IndexWriter ()
 
virtual String getClassName ()
 
boost::shared_ptr< IndexWritershared_from_this ()
 
virtual void initialize ()
 Called directly after instantiation to create objects that depend on this object being fully constructed.
 
virtual IndexReaderPtr getReader ()
 Returns a read-only reader, covering all committed as well as un-committed changes to the index. This provides "near real-time" searching, in that changes made during an IndexWriter session can be quickly made available for searching without closing the writer nor calling commit.
 
virtual IndexReaderPtr getReader (int32_t termInfosIndexDivisor)
 Like getReader, except you can specify which termInfosIndexDivisor should be used for any newly opened readers.
 
virtual int32_t numDeletedDocs (const SegmentInfoPtr &info)
 Obtain the number of deleted docs for a pooled reader. If the reader isn't being pooled, the segmentInfo's delCount is returned.
 
virtual void acquireWrite ()
 
virtual void releaseWrite ()
 
virtual void acquireRead ()
 
virtual void upgradeReadToWrite ()
 Allows one readLock to upgrade to a writeLock even if there are other readLocks as long as all other readLocks are also blocked in this method.
 
virtual void releaseRead ()
 
virtual bool isOpen (bool includePendingClose)
 
virtual void message (const String &message)
 
virtual bool getUseCompoundFile ()
 Get the current setting of whether newly flushed segments will use the compound file format. Note that this just returns the value previously set with setUseCompoundFile(bool), or the default value (true). You cannot use this to query the status of previously flushed segments.
 
virtual void setUseCompoundFile (bool value)
 Setting to turn on usage of a compound file. When on, multiple files for each segment are merged into a single file when a new segment is flushed.
 
virtual void setSimilarity (const SimilarityPtr &similarity)
 Set the Similarity implementation used by this IndexWriter.
 
virtual SimilarityPtr getSimilarity ()
 Return the Similarity implementation used by this IndexWriter. This defaults to the current value of Similarity#getDefault().
 
virtual void setTermIndexInterval (int32_t interval)
 Set the interval between indexed terms. Large values cause less memory to be used by IndexReader, but slow random-access to terms. Small values cause more memory to be used by an IndexReader, and speed random-access to terms.
 
virtual int32_t getTermIndexInterval ()
 Return the interval between indexed terms.
 
virtual void setMergePolicy (const MergePolicyPtr &mp)
 Set the merge policy used by this writer.
 
virtual MergePolicyPtr getMergePolicy ()
 Returns the current MergePolicy in use by this writer.
 
virtual void setMergeScheduler (const MergeSchedulerPtr &mergeScheduler)
 Set the merge scheduler used by this writer.
 
virtual MergeSchedulerPtr getMergeScheduler ()
 Returns the current MergePolicy in use by this writer.
 
virtual void setMaxMergeDocs (int32_t maxMergeDocs)
 Determines the largest segment (measured by document count) that may be merged with other segments. Small values (eg., less than 10,000) are best for interactive indexing, as this limits the length of pauses while indexing to a few seconds. Larger values are best for batched indexing and speedier searches.
 
virtual int32_t getMaxMergeDocs ()
 Returns the largest segment (measured by document count) that may be merged with other segments.
 
virtual void setMaxFieldLength (int32_t maxFieldLength)
 The maximum number of terms that will be indexed for a single field in a document. This limits the amount of memory required for indexing, so that collections with very large files will not crash the indexing process by running out of memory. This setting refers to the number of running terms, not to the number of different terms. Note: this silently truncates large documents, excluding from the index all terms that occur further in the document. If you know your source documents are large, be sure to set this value high enough to accommodate the expected size. If you set it to INT_MAX, then the only limit is your memory, but you should anticipate an std::bad_alloc. By default, no more than DEFAULT_MAX_FIELD_LENGTH terms will be indexed for a field.
 
virtual int32_t getMaxFieldLength ()
 Returns the maximum number of terms that will be indexed for a single field in a document.
 
virtual void setReaderTermsIndexDivisor (int32_t divisor)
 Sets the termsIndexDivisor passed to any readers that IndexWriter opens, for example when applying deletes or creating a near-real-time reader in IndexWriter#getReader. Default value is IndexReader#DEFAULT_TERMS_INDEX_DIVISOR.
 
virtual int32_t getReaderTermsIndexDivisor ()
 
virtual void setMaxBufferedDocs (int32_t maxBufferedDocs)
 Determines the minimal number of documents required before the buffered in-memory documents are flushed as a new Segment. Large values generally gives faster indexing.
 
virtual int32_t getMaxBufferedDocs ()
 Returns the number of buffered added documents that will trigger a flush if enabled.
 
virtual void setRAMBufferSizeMB (double mb)
 Determines the amount of RAM that may be used for buffering added documents and deletions before they are flushed to the Directory. Generally for faster indexing performance it's best to flush by RAM usage instead of document count and use as large a RAM buffer as you can.
 
virtual double getRAMBufferSizeMB ()
 Returns the value set by setRAMBufferSizeMB if enabled.
 
virtual void setMaxBufferedDeleteTerms (int32_t maxBufferedDeleteTerms)
 Determines the minimal number of delete terms required before the buffered in-memory delete terms are applied and flushed. If there are documents buffered in memory at the time, they are merged and a new segment is created.
 
virtual int32_t getMaxBufferedDeleteTerms ()
 Returns the number of buffered deleted terms that will trigger a flush if enabled.
 
virtual void setMergeFactor (int32_t mergeFactor)
 Determines how often segment indices are merged by addDocument(). With smaller values, less RAM is used while indexing, and searches on unoptimized indices are faster, but indexing speed is slower. With larger values, more RAM is used during indexing, and while searches on unoptimized indices are slower, indexing is faster. Thus larger values (> 10) are best for batch index creation, and smaller values (< 10) for indices that are interactively maintained.
 
virtual int32_t getMergeFactor ()
 Returns the number of segments that are merged at once and also controls the total number of segments allowed to accumulate in the index.
 
virtual void setInfoStream (const InfoStreamPtr &infoStream)
 If non-null, information about merges, deletes and a message when maxFieldLength is reached will be printed to this.
 
virtual InfoStreamPtr getInfoStream ()
 Returns the current infoStream in use by this writer.
 
virtual bool verbose ()
 Returns true if verbosing is enabled (i.e., infoStream != null).
 
virtual void setWriteLockTimeout (int64_t writeLockTimeout)
 Sets the maximum time to wait for a write lock (in milliseconds) for this instance of IndexWriter.
 
virtual int64_t getWriteLockTimeout ()
 Returns allowed timeout when acquiring the write lock.
 
virtual void close ()
 Commits all changes to an index and closes all associated files. Note that this may be a costly operation, so try to re-use a single writer instead of closing and opening a new one. See commit() for caveats about write caching done by some IO devices.
 
virtual void close (bool waitForMerges)
 Closes the index with or without waiting for currently running merges to finish. This is only meaningful when using a MergeScheduler that runs merges in background threads.
 
virtual DirectoryPtr getDirectory ()
 Returns the Directory used by this index.
 
virtual AnalyzerPtr getAnalyzer ()
 Returns the analyzer used by this index.
 
virtual int32_t maxDoc ()
 Returns total number of docs in this index, including docs not yet flushed (still in the RAM buffer), not counting deletions.
 
virtual int32_t numDocs ()
 Returns total number of docs in this index, including docs not yet flushed (still in the RAM buffer), and including deletions. NOTE: buffered deletions are not counted. If you really need these to be counted you should call commit() first.
 
virtual bool hasDeletions ()
 
virtual void addDocument (const DocumentPtr &doc)
 Adds a document to this index. If the document contains more than setMaxFieldLength(int32_t) terms for a given field, the remainder are discarded.
 
virtual void addDocument (const DocumentPtr &doc, const AnalyzerPtr &analyzer)
 Adds a document to this index, using the provided analyzer instead of the value of getAnalyzer(). If the document contains more than setMaxFieldLength(int32_t) terms for a given field, the remainder are discarded.
 
virtual void deleteDocuments (const TermPtr &term)
 Deletes the document(s) containing term.
 
virtual void deleteDocuments (Collection< TermPtr > terms)
 Deletes the document(s) containing any of the terms. All deletes are flushed at the same time.
 
virtual void deleteDocuments (const QueryPtr &query)
 Deletes the document(s) matching the provided query.
 
virtual void deleteDocuments (Collection< QueryPtr > queries)
 Deletes the document(s) matching any of the provided queries. All deletes are flushed at the same time.
 
virtual void updateDocument (const TermPtr &term, const DocumentPtr &doc)
 Updates a document by first deleting the document(s) containing term and then adding the new document. The delete and then add are atomic as seen by a reader on the same index (flush may happen only after the add).
 
virtual void updateDocument (const TermPtr &term, const DocumentPtr &doc, const AnalyzerPtr &analyzer)
 Updates a document by first deleting the document(s) containing term and then adding the new document. The delete and then add are atomic as seen by a reader on the same index (flush may happen only after the add).
 
virtual int32_t getSegmentCount ()
 
virtual int32_t getNumBufferedDocuments ()
 
virtual int32_t getDocCount (int32_t i)
 
virtual int32_t getFlushCount ()
 
virtual int32_t getFlushDeletesCount ()
 
virtual String newSegmentName ()
 
virtual void optimize ()
 Requests an "optimize" operation on an index, priming the index for the fastest available search. Traditionally this has meant merging all segments into a single segment as is done in the default merge policy, but individual merge policies may implement optimize in different ways.
 
virtual void optimize (int32_t maxNumSegments)
 Optimize the index down to <= maxNumSegments. If maxNumSegments==1 then this is the same as optimize().
 
virtual void optimize (bool doWait)
 Just like optimize(), except you can specify whether the call should block until the optimize completes. This is only meaningful with a MergeScheduler that is able to run merges in background threads.
 
virtual void optimize (int32_t maxNumSegments, bool doWait)
 Just like optimize(int32_t), except you can specify whether the call should block until the optimize completes. This is only meaningful with a MergeScheduler that is able to run merges in background threads.
 
virtual void expungeDeletes (bool doWait)
 Just like expungeDeletes(), except you can specify whether the call should block until the operation completes. This is only meaningful with a MergeScheduler that is able to run merges in background threads.
 
virtual void expungeDeletes ()
 Expunges all deletes from the index. When an index has many document deletions (or updates to existing documents), it's best to either call optimize or expungeDeletes to remove all unused data in the index associated with the deleted documents. To see how many deletions you have pending in your index, call IndexReader#numDeletedDocs. This saves disk space and memory usage while searching. expungeDeletes should be somewhat faster than optimize since it does not insist on reducing the index to a single segment (though, this depends on the MergePolicy; see MergePolicy#findMergesToExpungeDeletes.). Note that this call does not first commit any buffered documents, so you must do so yourself if necessary. See also expungeDeletes(bool).
 
virtual void maybeMerge ()
 Asks the mergePolicy whether any merges are necessary now and if so, runs the requested merges and then iterate (test again if merges are needed) until no more merges are returned by the mergePolicy.
 
virtual OneMergePtr getNextMerge ()
 The MergeScheduler calls this method to retrieve the next merge requested by the MergePolicy.
 
virtual void rollback ()
 Close the IndexWriter without committing any changes that have occurred since the last commit (or since it was opened, if commit hasn't been called). This removes any temporary files that had been created, after which the state of the index will be the same as it was when commit() was last called or when this writer was first opened. This also clears a previous call to prepareCommit.
 
virtual void deleteAll ()
 Delete all documents in the index.
 
virtual void waitForMerges ()
 Wait for any currently outstanding merges to finish.
 
virtual void addIndexesNoOptimize (Collection< DirectoryPtr > dirs)
 Merges all segments from an array of indexes into this index.
 
virtual void addIndexes (Collection< IndexReaderPtr > readers)
 Merges the provided indexes into this index. After this completes, the index is optimized. The provided IndexReaders are not closed.
 
virtual void prepareCommit ()
 Prepare for commit.
 
virtual void prepareCommit (MapStringString commitUserData)
 Prepare for commit, specifying commitUserData Map (String -> String). This does the first phase of 2-phase commit. This method does all steps necessary to commit changes since this writer was opened: flushes pending added and deleted docs, syncs the index files, writes most of next segments_N file. After calling this you must call either commit() to finish the commit, or rollback() to revert the commit and undo all changes done since the writer was opened.
 
virtual void commit ()
 Commits all pending changes (added & deleted documents, optimizations, segment merges, added indexes, etc.) to the index, and syncs all referenced index files, such that a reader will see the changes and the index updates will survive an OS or machine crash or power loss. Note that this does not wait for any running background merges to finish. This may be a costly operation, so you should test the cost in your application and do it only when really necessary.
 
virtual void commit (MapStringString commitUserData)
 Commits all changes to the index, specifying a commitUserData Map (String -> String). This just calls prepareCommit(MapStringString) (if you didn't already call it) and then finishCommit.
 
virtual int64_t ramSizeInBytes ()
 Return the total size of all index files currently cached in memory. Useful for size management with flushRamDocs()
 
virtual int32_t numRamDocs ()
 Return the number of documents currently buffered in RAM.
 
virtual void merge (const OneMergePtr &merge)
 Merges the indicated segments, replacing them in the stack with a single segment.
 
virtual void mergeSuccess (const OneMergePtr &merge)
 Hook that's called when the specified merge is complete.
 
virtual bool registerMerge (const OneMergePtr &merge)
 Checks whether this merge involves any segments already participating in a merge. If not, this merge is "registered", meaning we record that its segments are now participating in a merge, and true is returned. Else (the merge conflicts) false is returned.
 
virtual void mergeInit (const OneMergePtr &merge)
 Does initial setup for a merge, which is fast but holds the synchronized lock on IndexWriter instance.
 
virtual void mergeFinish (const OneMergePtr &merge)
 Does finishing for a merge, which is fast but holds the synchronized lock on IndexWriter instance.
 
virtual void addMergeException (const OneMergePtr &merge)
 
virtual int32_t getBufferedDeleteTermsSize ()
 For test purposes.
 
virtual int32_t getNumBufferedDeleteTerms ()
 For test purposes.
 
virtual SegmentInfoPtr newestSegment ()
 Utility routines for tests.
 
virtual String segString ()
 
virtual void setMergedSegmentWarmer (const IndexReaderWarmerPtr &warmer)
 Set the merged segment warmer. See IndexReaderWarmer.
 
virtual IndexReaderWarmerPtr getMergedSegmentWarmer ()
 Returns the current merged segment warmer. See IndexReaderWarmer.
 
virtual bool testPoint (const String &name)
 Used only by assert for testing. Current points: startDoFlush startCommitMerge startStartCommit midStartCommit midStartCommit2 midStartCommitSuccess finishStartCommit startCommitMergeDeletes startMergeInit startApplyDeletes startMergeInit startMergeInit.
 
virtual bool nrtIsCurrent (const SegmentInfosPtr &infos)
 
virtual bool isClosed ()
 
- Public Member Functions inherited from Lucene::LuceneObject
virtual ~LuceneObject ()
 
virtual LuceneObjectPtr clone (const LuceneObjectPtr &other=LuceneObjectPtr())
 Return clone of this object.
 
virtual int32_t hashCode ()
 Return hash code for this object.
 
virtual bool equals (const LuceneObjectPtr &other)
 Return whether two objects are equal.
 
virtual int32_t compareTo (const LuceneObjectPtr &other)
 Compare two objects.
 
virtual String toString ()
 Returns a string representation of the object.
 
- Public Member Functions inherited from Lucene::LuceneSync
virtual ~LuceneSync ()
 
virtual SynchronizePtr getSync ()
 Return this object synchronize lock.
 
virtual LuceneSignalPtr getSignal ()
 Return this object signal.
 
virtual void lock (int32_t timeout=0)
 Lock this object using an optional timeout.
 
virtual void unlock ()
 Unlock this object.
 
virtual bool holdsLock ()
 Returns true if this object is currently locked by current thread.
 
virtual void wait (int32_t timeout=0)
 Wait for signal using an optional timeout.
 
virtual void notifyAll ()
 Notify all threads waiting for signal.
 

Static Public Member Functions

static String _getClassName ()
 
static int32_t MAX_TERM_LENGTH ()
 Absolute hard maximum length for a term. If a term arrives from the analyzer longer than this length, it is skipped and a message is printed to infoStream, if set (see setInfoStream).
 
static void setDefaultInfoStream (const InfoStreamPtr &infoStream)
 If non-null, this will be the default infoStream used by a newly instantiated IndexWriter.
 
static InfoStreamPtr getDefaultInfoStream ()
 Returns the current default infoStream for newly instantiated IndexWriters.
 
static void setDefaultWriteLockTimeout (int64_t writeLockTimeout)
 Sets the default (for any instance of IndexWriter) maximum time to wait for a write lock (in milliseconds).
 
static int64_t getDefaultWriteLockTimeout ()
 Returns default write lock timeout for newly instantiated IndexWriters.
 
static bool isLocked (const DirectoryPtr &directory)
 Returns true if the index in the named directory is currently locked.
 
static void unlock (const DirectoryPtr &directory)
 Forcibly unlocks the index in the named directory. Caution: this should only be used by failure recovery code, when it is known that no other process nor thread is in fact currently accessing this index.
 

Static Public Attributes

static int64_t WRITE_LOCK_TIMEOUT
 Default value for the write lock timeout (1,000).
 
static const String WRITE_LOCK_NAME
 
static const int32_t DISABLE_AUTO_FLUSH
 Value to denote a flush trigger is disabled.
 
static const int32_t DEFAULT_MAX_BUFFERED_DOCS
 Disabled by default (because IndexWriter flushes by RAM usage by default). Change using setMaxBufferedDocs(int32_t).
 
static const double DEFAULT_RAM_BUFFER_SIZE_MB
 Default value is 16 MB (which means flush when buffered docs consume 16 MB RAM). Change using setRAMBufferSizeMB.
 
static const int32_t DEFAULT_MAX_BUFFERED_DELETE_TERMS
 Disabled by default (because IndexWriter flushes by RAM usage by default). Change using setMaxBufferedDeleteTerms(int32_t).
 
static const int32_t DEFAULT_MAX_FIELD_LENGTH
 Default value is 10,000. Change using setMaxFieldLength(int32_t).
 
static const int32_t DEFAULT_TERM_INDEX_INTERVAL
 Default value is 128. Change using setTermIndexInterval(int32_t).
 
static const int32_t MaxFieldLengthUNLIMITED
 Sets the maximum field length to INT_MAX.
 
static const int32_t MaxFieldLengthLIMITED
 Sets the maximum field length to DEFAULT_MAX_FIELD_LENGTH.
 

Protected Member Functions

 IndexWriter (const DirectoryPtr &d, const AnalyzerPtr &a, bool create, const IndexDeletionPolicyPtr &deletionPolicy, int32_t mfl, const IndexingChainPtr &indexingChain, const IndexCommitPtr &commit)
 
virtual void ensureOpen (bool includePendingClose)
 
virtual void ensureOpen ()
 
virtual void setMessageID (const InfoStreamPtr &infoStream)
 
virtual LogMergePolicyPtr getLogMergePolicy ()
 Casts current mergePolicy to LogMergePolicy, and throws an exception if the mergePolicy is not a LogMergePolicy.
 
virtual void setRollbackSegmentInfos (const SegmentInfosPtr &infos)
 
virtual void pushMaxBufferedDocs ()
 If we are flushing by doc count (not by RAM usage), and using LogDocMergePolicy then push maxBufferedDocs down as its minMergeDocs, to keep backwards compatibility.
 
virtual void messageState ()
 
virtual bool shouldClose ()
 Returns true if this thread should attempt to close, or false if IndexWriter is now closed; else, waits until another thread finishes closing.
 
virtual void closeInternal (bool waitForMerges)
 
virtual bool flushDocStores ()
 Tells the docWriter to close its currently open shared doc stores (stored fields & vectors files). Return value specifies whether new doc store files are compound or not.
 
virtual bool optimizeMergesPending ()
 Returns true if any merges in pendingMerges or runningMerges are optimization merges.
 
virtual void maybeMerge (bool optimize)
 
virtual void maybeMerge (int32_t maxNumSegmentsOptimize, bool optimize)
 
virtual void updatePendingMerges (int32_t maxNumSegmentsOptimize, bool optimize)
 
virtual OneMergePtr getNextExternalMerge ()
 Like getNextMerge() except only returns a merge if it's external.
 
virtual void startTransaction (bool haveReadLock)
 Begin a transaction. During a transaction, any segment merges that happen (or ram segments flushed) will not write a new segments file and will not remove any files that were present at the start of the transaction. You must make a matched call to commitTransaction() or rollbackTransaction() to finish the transaction.
 
virtual void rollbackTransaction ()
 Rolls back the transaction and restores state to where we were at the start.
 
virtual void commitTransaction ()
 Commits the transaction. This will write the new segments file and remove and pending deletions we have accumulated during the transaction.
 
virtual void rollbackInternal ()
 
virtual void finishMerges (bool waitForMerges)
 
virtual void checkpoint ()
 Called whenever the SegmentInfos has been updated and the index files referenced exist (correctly) in the index directory.
 
virtual void finishAddIndexes ()
 
virtual void blockAddIndexes (bool includePendingClose)
 
virtual void resumeAddIndexes ()
 
virtual void resetMergeExceptions ()
 
virtual void noDupDirs (Collection< DirectoryPtr > dirs)
 
virtual bool hasExternalSegments ()
 
virtual void resolveExternalSegments ()
 If any of our segments are using a directory != ours then we have to either copy them over one by one, merge them (if merge policy has chosen to) or wait until currently running merges (in the background) complete. We don't return until the SegmentInfos has no more external segments. Currently this is only used by addIndexesNoOptimize().
 
virtual void doAfterFlush ()
 A hook for extending classes to execute operations after pending added and deleted documents have been flushed to the Directory but before the change is committed (new segments_N file written).
 
virtual void doBeforeFlush ()
 A hook for extending classes to execute operations before pending added and deleted documents are flushed to the Directory.
 
virtual void commit (int64_t sizeInBytes)
 
virtual void finishCommit ()
 
virtual void flush (bool triggerMerge, bool flushDocStores, bool flushDeletes)
 Flush all in-memory buffered updates (adds and deletes) to the Directory.
 
virtual bool doFlush (bool flushDocStores, bool flushDeletes)
 
virtual bool doFlushInternal (bool flushDocStores, bool flushDeletes)
 
virtual int32_t ensureContiguousMerge (const OneMergePtr &merge)
 
virtual void commitMergedDeletes (const OneMergePtr &merge, const SegmentReaderPtr &mergeReader)
 Carefully merges deletes for the segments we just merged. This is tricky because, although merging will clear all deletes (compacts the documents), new deletes may have been flushed to the segments since the merge was started. This method "carries over" such new deletes onto the newly merged segment, and saves the resulting deletes file (incrementing the delete generation for merge.info). If no deletes were flushed, no new deletes file is saved.
 
virtual bool commitMerge (const OneMergePtr &merge, const SegmentMergerPtr &merger, int32_t mergedDocCount, const SegmentReaderPtr &mergedReader)
 
virtual LuceneException handleMergeException (const LuceneException &exc, const OneMergePtr &merge)
 
virtual void _mergeInit (const OneMergePtr &merge)
 
virtual void setDiagnostics (const SegmentInfoPtr &info, const String &source)
 
virtual void setDiagnostics (const SegmentInfoPtr &info, const String &source, MapStringString details)
 
virtual void setMergeDocStoreIsCompoundFile (const OneMergePtr &merge)
 
virtual void closeMergeReaders (const OneMergePtr &merge, bool suppressExceptions)
 
virtual int32_t mergeMiddle (const OneMergePtr &merge)
 Does the actual (time-consuming) work of the merge, but without holding synchronized lock on IndexWriter instance.
 
virtual bool applyDeletes ()
 Apply buffered deletes to all segments.
 
virtual String segString (const SegmentInfosPtr &infos)
 
virtual bool startSync (const String &fileName, HashSet< String > pending)
 
virtual void finishSync (const String &fileName, bool success)
 
bool waitForAllSynced (HashSet< String > syncing)
 Blocks until all files in syncing are sync'd.
 
void doWait ()
 
virtual void startCommit (int64_t sizeInBytes, MapStringString commitUserData)
 Walk through all files referenced by the current segmentInfos and ask the Directory to sync each file, if it wasn't already. If that succeeds, then we prepare a new segments_N file but do not fully commit it.
 
virtual LuceneException handleOOM (const std::bad_alloc &oom, const String &location)
 
- Protected Member Functions inherited from Lucene::LuceneObject
 LuceneObject ()
 

Protected Attributes

int64_t writeLockTimeout
 
SynchronizePtr messageIDLock
 
int32_t messageID
 
bool hitOOM
 
DirectoryPtr directory
 
AnalyzerPtr analyzer
 
bool create
 
IndexDeletionPolicyPtr deletionPolicy
 
IndexingChainPtr indexingChain
 
IndexCommitPtr indexCommit
 
SimilarityPtr similarity
 
int64_t changeCount
 
int64_t lastCommitChangeCount
 
SegmentInfosPtr rollbackSegmentInfos
 
MapSegmentInfoInt rollbackSegments
 
SegmentInfosPtr localRollbackSegmentInfos
 
int32_t localFlushedDocCount
 
SegmentInfosPtr segmentInfos
 
DocumentsWriterPtr docWriter
 
IndexFileDeleterPtr deleter
 
SetSegmentInfo segmentsToOptimize
 
int32_t optimizeMaxNumSegments
 
LockPtr writeLock
 
int32_t termIndexInterval
 
bool closed
 
bool closing
 
SetSegmentInfo mergingSegments
 
MergePolicyPtr mergePolicy
 
MergeSchedulerPtr mergeScheduler
 
Collection< OneMergePtrpendingMerges
 
SetOneMerge runningMerges
 
Collection< OneMergePtrmergeExceptions
 
int64_t mergeGen
 
bool stopMerges
 
int32_t flushCount
 
int32_t flushDeletesCount
 
int32_t readCount
 Used to only allow one addIndexes to proceed at once.
 
int64_t writeThread
 
int32_t upgradeCount
 
int32_t readerTermsIndexDivisor
 
bool poolReaders
 
int32_t maxFieldLength
 The maximum number of terms that will be indexed for a single field in a document. This limits the amount of memory required for indexing, so that collections with very large files will not crash the indexing process by running out of memory. Note that this effectively truncates large documents, excluding from the index terms that occur further in the document. If you know your source documents are large, be sure to set this value high enough to accommodate the expected size. If you set it to INT_MAX, then the only limit is your memory, but you should anticipate an std::bad_alloc. By default, no more than 10,000 terms will be indexed for a field.
 
InfoStreamPtr infoStream
 
HashSet< String > synced
 
HashSet< String > syncing
 
IndexReaderWarmerPtr mergedSegmentWarmer
 
SynchronizePtr commitLock
 Used only by commit; lock order is commitLock -> IW.
 
INTERNAL : SegmentInfosPtr pendingCommit
 
int64_t pendingCommitChangeCount
 
ReaderPoolPtr readerPool
 
- Protected Attributes inherited from Lucene::LuceneSync
SynchronizePtr objectLock
 
LuceneSignalPtr objectSignal
 

Static Protected Attributes

static const int32_t MERGE_READ_BUFFER_SIZE
 The normal read buffer size defaults to 1024, but increasing this during merging seems to yield performance gains. However we don't want to increase it too much because there are quite a few BufferedIndexInputs created during merging.
 
static int32_t MESSAGE_ID
 
static InfoStreamPtr defaultInfoStream
 

Detailed Description

An IndexWriter creates and maintains an index.

The create argument to the ructor determines whether a new index is created, or whether an existing index is opened. Note that you can open an index with create=true even while readers are using the index. The old readers will continue to search the "point in time" snapshot they had opened, and won't see the newly created index until they re-open. There are also ructors with no create argument which will create a new index if there is not already an index at the provided path and otherwise open the existing index.

In either case, documents are added with addDocument and removed with deleteDocuments(TermPtr) or deleteDocuments(QueryPtr). A document can be updated with updateDocument (which just deletes and then adds the entire document). When finished adding, deleting and updating documents, close should be called.

These changes are buffered in memory and periodically flushed to the Directory (during the above method calls). A flush is triggered when there are enough buffered deletes (see setMaxBufferedDeleteTerms) or enough added documents since the last flush, whichever is sooner. For the added documents, flushing is triggered either by RAM usage of the documents (see setRAMBufferSizeMB) or the number of added documents. The default is to flush when RAM usage hits 16 MB. For best indexing speed you should flush by RAM usage with a large RAM buffer. Note that flushing just moves the internal buffered state in IndexWriter into the index, but these changes are not visible to IndexReader until either commit() or close is called. A flush may also trigger one or more segment merges which by default run with a background thread so as not to block the addDocument calls (see mergePolicy below for changing the MergeScheduler).

If an index will not have more documents added for a while and optimal search performance is desired, then either the full optimize method or partial optimize(int32_t) method should be called before the index is closed.

Opening an IndexWriter creates a lock file for the directory in use. Trying to open another IndexWriter on the same directory will lead to a LockObtainFailed exception. The LockObtainFailed exception is also thrown if an IndexReader on the same directory is used to delete documents from the index.

IndexWriter allows an optional IndexDeletionPolicy implementation to be specified. You can use this to control when prior commits are deleted from the index. The default policy is KeepOnlyLastCommitDeletionPolicy which removes all prior commits as soon as a new commit is done (this matches behavior before 2.2). Creating your own policy can allow you to explicitly keep previous "point in time" commits alive in the index for some time, to allow readers to refresh to the new commit without having the old commit deleted out from under them. This is necessary on file systems like NFS that do not support "delete on last close" semantics, which Lucene's "point in time" search normally relies on.

IndexWriter allows you to separately change the MergePolicy and the MergeScheduler. The MergePolicy is invoked whenever there are changes to the segments in the index. Its role is to select which merges to do, if any, and return a MergePolicy.MergeSpecification describing the merges. It also selects merges to do for optimize(). (The default is LogByteSizeMergePolicy. Then, the MergeScheduler is invoked with the requested merges and it decides when and how to run the merges. The default is ConcurrentMergeScheduler.

NOTE: if you hit an std::bad_alloc then IndexWriter will quietly record this fact and block all future segment commits. This is a defensive measure in case any internal state (buffered documents and deletions) were corrupted. Any subsequent calls to commit() will throw an IllegalState exception. The only course of action is to call close(), which internally will call rollback(), to undo any changes to the index since the last commit. You can also just call rollback() directly.

NOTE: IndexWriter instances are completely thread safe, meaning multiple threads can call any of its methods, concurrently. If your application requires external synchronization, you should not synchronize on the IndexWriter instance as this may cause deadlock; use your own (non-Lucene) objects instead.

Clarification: Check Points (and commits) IndexWriter writes new index files to the directory without writing a new segments_N file which references these new files. It also means that the state of the in memory SegmentInfos object is different than the most recent segments_N file written to the directory.

Each time the SegmentInfos is changed, and matches the (possibly modified) directory files, we have a new "check point". If the modified/new SegmentInfos is written to disk - as a new (generation of) segments_N file - this check point is also an IndexCommit.

A new checkpoint always replaces the previous checkpoint and becomes the new "front" of the index. This allows the IndexFileDeleter to delete files that are referenced only by stale checkpoints (files that were created since the last commit, but are no longer referenced by the "front" of the index). For this, IndexFileDeleter keeps track of the last non commit checkpoint.

Constructor & Destructor Documentation

◆ IndexWriter() [1/6]

Lucene::IndexWriter::IndexWriter ( const DirectoryPtr d,
const AnalyzerPtr a,
bool  create,
const IndexDeletionPolicyPtr deletionPolicy,
int32_t  mfl,
const IndexingChainPtr indexingChain,
const IndexCommitPtr commit 
)
protected

◆ IndexWriter() [2/6]

Lucene::IndexWriter::IndexWriter ( const DirectoryPtr d,
const AnalyzerPtr a,
bool  create,
int32_t  mfl 
)

◆ IndexWriter() [3/6]

Lucene::IndexWriter::IndexWriter ( const DirectoryPtr d,
const AnalyzerPtr a,
int32_t  mfl 
)

◆ IndexWriter() [4/6]

Lucene::IndexWriter::IndexWriter ( const DirectoryPtr d,
const AnalyzerPtr a,
const IndexDeletionPolicyPtr deletionPolicy,
int32_t  mfl 
)

◆ IndexWriter() [5/6]

Lucene::IndexWriter::IndexWriter ( const DirectoryPtr d,
const AnalyzerPtr a,
bool  create,
const IndexDeletionPolicyPtr deletionPolicy,
int32_t  mfl 
)

◆ IndexWriter() [6/6]

Lucene::IndexWriter::IndexWriter ( const DirectoryPtr d,
const AnalyzerPtr a,
const IndexDeletionPolicyPtr deletionPolicy,
int32_t  mfl,
const IndexCommitPtr commit 
)

◆ ~IndexWriter()

virtual Lucene::IndexWriter::~IndexWriter ( )
virtual

Member Function Documentation

◆ _getClassName()

static String Lucene::IndexWriter::_getClassName ( )
inlinestatic

◆ _mergeInit()

virtual void Lucene::IndexWriter::_mergeInit ( const OneMergePtr merge)
protectedvirtual

◆ acquireRead()

virtual void Lucene::IndexWriter::acquireRead ( )
virtual

◆ acquireWrite()

virtual void Lucene::IndexWriter::acquireWrite ( )
virtual

◆ addDocument() [1/2]

virtual void Lucene::IndexWriter::addDocument ( const DocumentPtr doc)
virtual

Adds a document to this index. If the document contains more than setMaxFieldLength(int32_t) terms for a given field, the remainder are discarded.

Note that if an Exception is hit (for example disk full) then the index will be consistent, but this document may not have been added. Furthermore, it's possible the index will have one segment in non-compound format even when using compound files (when a merge has partially succeeded).

This method periodically flushes pending documents to the Directory, and also periodically triggers segment merges in the index according to the MergePolicy in use.

Merges temporarily consume space in the directory. The amount of space required is up to 1X the size of all segments being merged, when no size of all segments being merged, when no 2X the size of all segments being merged when readers/searchers are open against the index (see optimize() for details). The sequence of primitive merge operations performed is governed by the merge policy.

Note that each term in the document can be no longer than 16383 characters, otherwise an IllegalArgument exception will be thrown.

NOTE: if this method hits an std::bad_alloc you should immediately close the writer.

◆ addDocument() [2/2]

virtual void Lucene::IndexWriter::addDocument ( const DocumentPtr doc,
const AnalyzerPtr analyzer 
)
virtual

Adds a document to this index, using the provided analyzer instead of the value of getAnalyzer(). If the document contains more than setMaxFieldLength(int32_t) terms for a given field, the remainder are discarded.

See addDocument(DocumentPtr) for details on index and IndexWriter state after an exception, and flushing/merging temporary free space requirements.

NOTE: if this method hits an std::bad_alloc you should immediately close the writer.

◆ addIndexes()

virtual void Lucene::IndexWriter::addIndexes ( Collection< IndexReaderPtr readers)
virtual

Merges the provided indexes into this index. After this completes, the index is optimized. The provided IndexReaders are not closed.

NOTE: while this is running, any attempts to add or delete documents (with another thread) will be paused until this method completes.

See addIndexesNoOptimize for details on transactional semantics, temporary free space required in the Directory, and non-CFS segments on an exception.

NOTE: if this method hits an std::bad_alloc you should immediately close the writer.

◆ addIndexesNoOptimize()

virtual void Lucene::IndexWriter::addIndexesNoOptimize ( Collection< DirectoryPtr dirs)
virtual

Merges all segments from an array of indexes into this index.

This may be used to parallelize batch indexing. A large document collection can be broken into sub-collections. Each sub-collection can be indexed in parallel, on a different thread, process or machine. The complete index can then be created by merging sub-collection indexes with this method.

NOTE: the index in each Directory must not be changed (opened by a writer) while this method is running. This method does not acquire a write lock in each input Directory, so it is up to the caller to enforce this.

NOTE: while this is running, any attempts to add or delete documents (with another thread) will be paused until this method completes.

This method is transactional in how exceptions are handled: it does not commit a new segments_N file until all indexes are added. This means if an exception occurs (for example disk full), then either no indexes will have been added or they all will have been.

Note that this requires temporary free space in the Directory up to 2X the sum of all input indexes (including the starting index). If readers/searchers are open against the starting index, then temporary free space required will be higher by the size of the starting index (see optimize() for details).

Once this completes, the final size of the index will be less than the sum of all input index sizes (including the starting index). It could be quite a bit smaller (if there were many pending deletes) or just slightly smaller.

This requires this index not be among those to be added.

NOTE: if this method hits an std::bad_alloc you should immediately close the writer.

◆ addMergeException()

virtual void Lucene::IndexWriter::addMergeException ( const OneMergePtr merge)
virtual

◆ applyDeletes()

virtual bool Lucene::IndexWriter::applyDeletes ( )
protectedvirtual

Apply buffered deletes to all segments.

◆ blockAddIndexes()

virtual void Lucene::IndexWriter::blockAddIndexes ( bool  includePendingClose)
protectedvirtual

◆ checkpoint()

virtual void Lucene::IndexWriter::checkpoint ( )
protectedvirtual

Called whenever the SegmentInfos has been updated and the index files referenced exist (correctly) in the index directory.

◆ close() [1/2]

virtual void Lucene::IndexWriter::close ( )
virtual

Commits all changes to an index and closes all associated files. Note that this may be a costly operation, so try to re-use a single writer instead of closing and opening a new one. See commit() for caveats about write caching done by some IO devices.

If an Exception is hit during close, eg due to disk full or some other reason, then both the on-disk index and the internal state of the IndexWriter instance will be consistent. However, the close will not be complete even though part of it (flushing buffered documents) may have succeeded, so the write lock will still be held.

If you can correct the underlying cause (eg free up some disk space) then you can call close() again.

NOTE: if this method hits an std::bad_alloc you should immediately close the writer, again.

◆ close() [2/2]

virtual void Lucene::IndexWriter::close ( bool  waitForMerges)
virtual

Closes the index with or without waiting for currently running merges to finish. This is only meaningful when using a MergeScheduler that runs merges in background threads.

NOTE: if this method hits an std::bad_alloc you should immediately close the writer, again.

NOTE: it is dangerous to always call close(false), especially when IndexWriter is not open for very long, because this can result in "merge starvation" whereby long merges will never have a chance to finish. This will cause too many segments in your index over time.

Parameters
waitForMergesif true, this call will block until all merges complete; else, it will ask all running merges to abort, wait until those merges have finished (which should be at most a few seconds), and then return.

◆ closeInternal()

virtual void Lucene::IndexWriter::closeInternal ( bool  waitForMerges)
protectedvirtual

◆ closeMergeReaders()

virtual void Lucene::IndexWriter::closeMergeReaders ( const OneMergePtr merge,
bool  suppressExceptions 
)
protectedvirtual

◆ commit() [1/3]

virtual void Lucene::IndexWriter::commit ( )
virtual

Commits all pending changes (added & deleted documents, optimizations, segment merges, added indexes, etc.) to the index, and syncs all referenced index files, such that a reader will see the changes and the index updates will survive an OS or machine crash or power loss. Note that this does not wait for any running background merges to finish. This may be a costly operation, so you should test the cost in your application and do it only when really necessary.

Note that this operation calls Directory.sync on the index files. That call should not return until the file contents & metadata are on stable storage. For FSDirectory, this calls the OS's fsync. But, beware: some hardware devices may in fact cache writes even during fsync, and return before the bits are actually on stable storage, to give the appearance of faster performance. If you have such a device, and it does not have a battery backup (for example) then on power loss it may still lose data. Lucene cannot guarantee consistency on such devices.

NOTE: if this method hits an std::bad_alloc you should immediately close the writer.

See also
prepareCommit
commit(MapStringString)

◆ commit() [2/3]

virtual void Lucene::IndexWriter::commit ( int64_t  sizeInBytes)
protectedvirtual

◆ commit() [3/3]

virtual void Lucene::IndexWriter::commit ( MapStringString  commitUserData)
virtual

Commits all changes to the index, specifying a commitUserData Map (String -> String). This just calls prepareCommit(MapStringString) (if you didn't already call it) and then finishCommit.

NOTE: if this method hits an std::bad_alloc you should immediately close the writer.

◆ commitMerge()

virtual bool Lucene::IndexWriter::commitMerge ( const OneMergePtr merge,
const SegmentMergerPtr merger,
int32_t  mergedDocCount,
const SegmentReaderPtr mergedReader 
)
protectedvirtual

◆ commitMergedDeletes()

virtual void Lucene::IndexWriter::commitMergedDeletes ( const OneMergePtr merge,
const SegmentReaderPtr mergeReader 
)
protectedvirtual

Carefully merges deletes for the segments we just merged. This is tricky because, although merging will clear all deletes (compacts the documents), new deletes may have been flushed to the segments since the merge was started. This method "carries over" such new deletes onto the newly merged segment, and saves the resulting deletes file (incrementing the delete generation for merge.info). If no deletes were flushed, no new deletes file is saved.

◆ commitTransaction()

virtual void Lucene::IndexWriter::commitTransaction ( )
protectedvirtual

Commits the transaction. This will write the new segments file and remove and pending deletions we have accumulated during the transaction.

◆ deleteAll()

virtual void Lucene::IndexWriter::deleteAll ( )
virtual

Delete all documents in the index.

This method will drop all buffered documents and will remove all segments from the index. This change will not be visible until a commit() has been called. This method can be rolled back using rollback().

NOTE: this method is much faster than using deleteDocuments().

NOTE: this method will forcefully abort all merges in progress. If other threads are running optimize() or any of the addIndexes methods, they will receive MergePolicy.MergeAbortedException

◆ deleteDocuments() [1/4]

virtual void Lucene::IndexWriter::deleteDocuments ( Collection< QueryPtr queries)
virtual

Deletes the document(s) matching any of the provided queries. All deletes are flushed at the same time.

NOTE: if this method hits an std::bad_alloc you should immediately close the writer.

Parameters
queriesarray of queries to identify the documents to be deleted

◆ deleteDocuments() [2/4]

virtual void Lucene::IndexWriter::deleteDocuments ( Collection< TermPtr terms)
virtual

Deletes the document(s) containing any of the terms. All deletes are flushed at the same time.

NOTE: if this method hits an std::bad_alloc you should immediately close the writer.

Parameters
termsarray of terms to identify the documents to be deleted

◆ deleteDocuments() [3/4]

virtual void Lucene::IndexWriter::deleteDocuments ( const QueryPtr query)
virtual

Deletes the document(s) matching the provided query.

NOTE: if this method hits an std::bad_alloc you should immediately close the writer.

Parameters
querythe query to identify the documents to be deleted

◆ deleteDocuments() [4/4]

virtual void Lucene::IndexWriter::deleteDocuments ( const TermPtr term)
virtual

Deletes the document(s) containing term.

NOTE: if this method hits an std::bad_alloc you should immediately close the writer.

Parameters
termthe term to identify the documents to be deleted

◆ doAfterFlush()

virtual void Lucene::IndexWriter::doAfterFlush ( )
protectedvirtual

A hook for extending classes to execute operations after pending added and deleted documents have been flushed to the Directory but before the change is committed (new segments_N file written).

◆ doBeforeFlush()

virtual void Lucene::IndexWriter::doBeforeFlush ( )
protectedvirtual

A hook for extending classes to execute operations before pending added and deleted documents are flushed to the Directory.

◆ doFlush()

virtual bool Lucene::IndexWriter::doFlush ( bool  flushDocStores,
bool  flushDeletes 
)
protectedvirtual

◆ doFlushInternal()

virtual bool Lucene::IndexWriter::doFlushInternal ( bool  flushDocStores,
bool  flushDeletes 
)
protectedvirtual

◆ doWait()

void Lucene::IndexWriter::doWait ( )
protected

◆ ensureContiguousMerge()

virtual int32_t Lucene::IndexWriter::ensureContiguousMerge ( const OneMergePtr merge)
protectedvirtual

◆ ensureOpen() [1/2]

virtual void Lucene::IndexWriter::ensureOpen ( )
protectedvirtual

◆ ensureOpen() [2/2]

virtual void Lucene::IndexWriter::ensureOpen ( bool  includePendingClose)
protectedvirtual

◆ expungeDeletes() [1/2]

virtual void Lucene::IndexWriter::expungeDeletes ( )
virtual

Expunges all deletes from the index. When an index has many document deletions (or updates to existing documents), it's best to either call optimize or expungeDeletes to remove all unused data in the index associated with the deleted documents. To see how many deletions you have pending in your index, call IndexReader#numDeletedDocs. This saves disk space and memory usage while searching. expungeDeletes should be somewhat faster than optimize since it does not insist on reducing the index to a single segment (though, this depends on the MergePolicy; see MergePolicy#findMergesToExpungeDeletes.). Note that this call does not first commit any buffered documents, so you must do so yourself if necessary. See also expungeDeletes(bool).

NOTE: if this method hits an std::bad_alloc you should immediately close the writer.

◆ expungeDeletes() [2/2]

virtual void Lucene::IndexWriter::expungeDeletes ( bool  doWait)
virtual

Just like expungeDeletes(), except you can specify whether the call should block until the operation completes. This is only meaningful with a MergeScheduler that is able to run merges in background threads.

NOTE: if this method hits an std::bad_alloc you should immediately close the writer.

◆ finishAddIndexes()

virtual void Lucene::IndexWriter::finishAddIndexes ( )
protectedvirtual

◆ finishCommit()

virtual void Lucene::IndexWriter::finishCommit ( )
protectedvirtual

◆ finishMerges()

virtual void Lucene::IndexWriter::finishMerges ( bool  waitForMerges)
protectedvirtual

◆ finishSync()

virtual void Lucene::IndexWriter::finishSync ( const String &  fileName,
bool  success 
)
protectedvirtual

◆ flush()

virtual void Lucene::IndexWriter::flush ( bool  triggerMerge,
bool  flushDocStores,
bool  flushDeletes 
)
protectedvirtual

Flush all in-memory buffered updates (adds and deletes) to the Directory.

Parameters
triggerMergeif true, we may merge segments (if deletes or docs were flushed) if necessary
flushDocStoresif false we are allowed to keep doc stores open to share with the next segment
flushDeleteswhether pending deletes should also be flushed

◆ flushDocStores()

virtual bool Lucene::IndexWriter::flushDocStores ( )
protectedvirtual

Tells the docWriter to close its currently open shared doc stores (stored fields & vectors files). Return value specifies whether new doc store files are compound or not.

◆ getAnalyzer()

virtual AnalyzerPtr Lucene::IndexWriter::getAnalyzer ( )
virtual

Returns the analyzer used by this index.

◆ getBufferedDeleteTermsSize()

virtual int32_t Lucene::IndexWriter::getBufferedDeleteTermsSize ( )
virtual

For test purposes.

◆ getClassName()

virtual String Lucene::IndexWriter::getClassName ( )
inlinevirtual

◆ getDefaultInfoStream()

static InfoStreamPtr Lucene::IndexWriter::getDefaultInfoStream ( )
static

Returns the current default infoStream for newly instantiated IndexWriters.

See also
setDefaultInfoStream

◆ getDefaultWriteLockTimeout()

static int64_t Lucene::IndexWriter::getDefaultWriteLockTimeout ( )
static

Returns default write lock timeout for newly instantiated IndexWriters.

See also
setDefaultWriteLockTimeout

◆ getDirectory()

virtual DirectoryPtr Lucene::IndexWriter::getDirectory ( )
virtual

Returns the Directory used by this index.

◆ getDocCount()

virtual int32_t Lucene::IndexWriter::getDocCount ( int32_t  i)
virtual

◆ getFlushCount()

virtual int32_t Lucene::IndexWriter::getFlushCount ( )
virtual

◆ getFlushDeletesCount()

virtual int32_t Lucene::IndexWriter::getFlushDeletesCount ( )
virtual

◆ getInfoStream()

virtual InfoStreamPtr Lucene::IndexWriter::getInfoStream ( )
virtual

Returns the current infoStream in use by this writer.

See also
setInfoStream

◆ getLogMergePolicy()

virtual LogMergePolicyPtr Lucene::IndexWriter::getLogMergePolicy ( )
protectedvirtual

Casts current mergePolicy to LogMergePolicy, and throws an exception if the mergePolicy is not a LogMergePolicy.

◆ getMaxBufferedDeleteTerms()

virtual int32_t Lucene::IndexWriter::getMaxBufferedDeleteTerms ( )
virtual

Returns the number of buffered deleted terms that will trigger a flush if enabled.

See also
setMaxBufferedDeleteTerms

◆ getMaxBufferedDocs()

virtual int32_t Lucene::IndexWriter::getMaxBufferedDocs ( )
virtual

Returns the number of buffered added documents that will trigger a flush if enabled.

See also
setMaxBufferedDocs

◆ getMaxFieldLength()

virtual int32_t Lucene::IndexWriter::getMaxFieldLength ( )
virtual

Returns the maximum number of terms that will be indexed for a single field in a document.

See also
setMaxFieldLength

◆ getMaxMergeDocs()

virtual int32_t Lucene::IndexWriter::getMaxMergeDocs ( )
virtual

Returns the largest segment (measured by document count) that may be merged with other segments.

Note that this method is a convenience method: it just calls mergePolicy.getMaxMergeDocs as long as mergePolicy is an instance of LogMergePolicy. Otherwise an IllegalArgument exception is thrown.

See also
setMaxMergeDocs

◆ getMergedSegmentWarmer()

virtual IndexReaderWarmerPtr Lucene::IndexWriter::getMergedSegmentWarmer ( )
virtual

Returns the current merged segment warmer. See IndexReaderWarmer.

◆ getMergeFactor()

virtual int32_t Lucene::IndexWriter::getMergeFactor ( )
virtual

Returns the number of segments that are merged at once and also controls the total number of segments allowed to accumulate in the index.

Note that this method is a convenience method: it just calls mergePolicy.getMergeFactor as long as mergePolicy is an instance of LogMergePolicy. Otherwise an IllegalArgument exception is thrown.

See also
setMergeFactor

◆ getMergePolicy()

virtual MergePolicyPtr Lucene::IndexWriter::getMergePolicy ( )
virtual

Returns the current MergePolicy in use by this writer.

See also
setMergePolicy

◆ getMergeScheduler()

virtual MergeSchedulerPtr Lucene::IndexWriter::getMergeScheduler ( )
virtual

Returns the current MergePolicy in use by this writer.

See also
setMergePolicy

◆ getNextExternalMerge()

virtual OneMergePtr Lucene::IndexWriter::getNextExternalMerge ( )
protectedvirtual

Like getNextMerge() except only returns a merge if it's external.

◆ getNextMerge()

virtual OneMergePtr Lucene::IndexWriter::getNextMerge ( )
virtual

The MergeScheduler calls this method to retrieve the next merge requested by the MergePolicy.

◆ getNumBufferedDeleteTerms()

virtual int32_t Lucene::IndexWriter::getNumBufferedDeleteTerms ( )
virtual

For test purposes.

◆ getNumBufferedDocuments()

virtual int32_t Lucene::IndexWriter::getNumBufferedDocuments ( )
virtual

◆ getRAMBufferSizeMB()

virtual double Lucene::IndexWriter::getRAMBufferSizeMB ( )
virtual

Returns the value set by setRAMBufferSizeMB if enabled.

◆ getReader() [1/2]

virtual IndexReaderPtr Lucene::IndexWriter::getReader ( )
virtual

Returns a read-only reader, covering all committed as well as un-committed changes to the index. This provides "near real-time" searching, in that changes made during an IndexWriter session can be quickly made available for searching without closing the writer nor calling commit.

Note that this is functionally equivalent to calling {commit} and then using IndexReader#open to open a new reader. But the turnaround time of this method should be faster since it avoids the potentially costly commit.

You must close the IndexReader returned by this method once you are done using it.

It's near real-time because there is no hard guarantee on how quickly you can get a new reader after making changes with IndexWriter. You'll have to experiment in your situation to determine if it's fast enough. As this is a new and experimental feature, please report back on your findings so we can learn, improve and iterate.

The resulting reader supports IndexReader#reopen, but that call will simply forward back to this method (though this may change in the future).

The very first time this method is called, this writer instance will make every effort to pool the readers that it opens for doing merges, applying deletes, etc. This means additional resources (RAM, file descriptors, CPU time) will be consumed.

For lower latency on reopening a reader, you should call setMergedSegmentWarmer to pre-warm a newly merged segment before it's committed to the index. This is important for minimizing index-to-search delay after a large merge.

If an addIndexes* call is running in another thread, then this reader will only search those segments from the foreign index that have been successfully copied over, so far.

NOTE: Once the writer is closed, any outstanding readers may continue to be used. However, if you attempt to reopen any of those readers, you'll hit an AlreadyClosed exception.

NOTE: This API is experimental and might change in incompatible ways in the next release.

Returns
IndexReader that covers entire index plus all changes made so far by this IndexWriter instance

◆ getReader() [2/2]

virtual IndexReaderPtr Lucene::IndexWriter::getReader ( int32_t  termInfosIndexDivisor)
virtual

Like getReader, except you can specify which termInfosIndexDivisor should be used for any newly opened readers.

Parameters
termInfosIndexDivisorSubsamples which indexed terms are loaded into RAM. This has the same effect as IndexWriter#setTermIndexInterval except that setting must be done at indexing time while this setting can be set per reader. When set to N, then one in every N*termIndexInterval terms in the index is loaded into memory. By setting this to a value > 1 you can reduce memory usage, at the expense of higher latency when loading a TermInfo. The default value is 1. Set this to -1 to skip loading the terms index entirely.

◆ getReaderTermsIndexDivisor()

virtual int32_t Lucene::IndexWriter::getReaderTermsIndexDivisor ( )
virtual

◆ getSegmentCount()

virtual int32_t Lucene::IndexWriter::getSegmentCount ( )
virtual

◆ getSimilarity()

virtual SimilarityPtr Lucene::IndexWriter::getSimilarity ( )
virtual

Return the Similarity implementation used by this IndexWriter. This defaults to the current value of Similarity#getDefault().

◆ getTermIndexInterval()

virtual int32_t Lucene::IndexWriter::getTermIndexInterval ( )
virtual

Return the interval between indexed terms.

See also
setTermIndexInterval(int32_t)

◆ getUseCompoundFile()

virtual bool Lucene::IndexWriter::getUseCompoundFile ( )
virtual

Get the current setting of whether newly flushed segments will use the compound file format. Note that this just returns the value previously set with setUseCompoundFile(bool), or the default value (true). You cannot use this to query the status of previously flushed segments.

Note that this method is a convenience method: it just calls mergePolicy.getUseCompoundFile as long as mergePolicy is an instance of LogMergePolicy. Otherwise an IllegalArgument exception is thrown.

See also
setUseCompoundFile(bool)

◆ getWriteLockTimeout()

virtual int64_t Lucene::IndexWriter::getWriteLockTimeout ( )
virtual

Returns allowed timeout when acquiring the write lock.

See also
setWriteLockTimeout

◆ handleMergeException()

virtual LuceneException Lucene::IndexWriter::handleMergeException ( const LuceneException exc,
const OneMergePtr merge 
)
protectedvirtual

◆ handleOOM()

virtual LuceneException Lucene::IndexWriter::handleOOM ( const std::bad_alloc &  oom,
const String &  location 
)
protectedvirtual

◆ hasDeletions()

virtual bool Lucene::IndexWriter::hasDeletions ( )
virtual

◆ hasExternalSegments()

virtual bool Lucene::IndexWriter::hasExternalSegments ( )
protectedvirtual

◆ initialize()

virtual void Lucene::IndexWriter::initialize ( )
virtual

Called directly after instantiation to create objects that depend on this object being fully constructed.

Reimplemented from Lucene::LuceneObject.

◆ isClosed()

virtual bool Lucene::IndexWriter::isClosed ( )
virtual

◆ isLocked()

static bool Lucene::IndexWriter::isLocked ( const DirectoryPtr directory)
static

Returns true if the index in the named directory is currently locked.

Parameters
directorythe directory to check for a lock

◆ isOpen()

virtual bool Lucene::IndexWriter::isOpen ( bool  includePendingClose)
virtual

◆ MAX_TERM_LENGTH()

static int32_t Lucene::IndexWriter::MAX_TERM_LENGTH ( )
static

Absolute hard maximum length for a term. If a term arrives from the analyzer longer than this length, it is skipped and a message is printed to infoStream, if set (see setInfoStream).

◆ maxDoc()

virtual int32_t Lucene::IndexWriter::maxDoc ( )
virtual

Returns total number of docs in this index, including docs not yet flushed (still in the RAM buffer), not counting deletions.

See also
numDocs

◆ maybeMerge() [1/3]

virtual void Lucene::IndexWriter::maybeMerge ( )
virtual

Asks the mergePolicy whether any merges are necessary now and if so, runs the requested merges and then iterate (test again if merges are needed) until no more merges are returned by the mergePolicy.

Explicit calls to maybeMerge() are usually not necessary. The most common case is when merge policy parameters have changed.

NOTE: if this method hits an std::bad_alloc you should immediately close the writer.

◆ maybeMerge() [2/3]

virtual void Lucene::IndexWriter::maybeMerge ( bool  optimize)
protectedvirtual

◆ maybeMerge() [3/3]

virtual void Lucene::IndexWriter::maybeMerge ( int32_t  maxNumSegmentsOptimize,
bool  optimize 
)
protectedvirtual

◆ merge()

virtual void Lucene::IndexWriter::merge ( const OneMergePtr merge)
virtual

Merges the indicated segments, replacing them in the stack with a single segment.

◆ mergeFinish()

virtual void Lucene::IndexWriter::mergeFinish ( const OneMergePtr merge)
virtual

Does finishing for a merge, which is fast but holds the synchronized lock on IndexWriter instance.

◆ mergeInit()

virtual void Lucene::IndexWriter::mergeInit ( const OneMergePtr merge)
virtual

Does initial setup for a merge, which is fast but holds the synchronized lock on IndexWriter instance.

◆ mergeMiddle()

virtual int32_t Lucene::IndexWriter::mergeMiddle ( const OneMergePtr merge)
protectedvirtual

Does the actual (time-consuming) work of the merge, but without holding synchronized lock on IndexWriter instance.

◆ mergeSuccess()

virtual void Lucene::IndexWriter::mergeSuccess ( const OneMergePtr merge)
virtual

Hook that's called when the specified merge is complete.

◆ message()

virtual void Lucene::IndexWriter::message ( const String &  message)
virtual

◆ messageState()

virtual void Lucene::IndexWriter::messageState ( )
protectedvirtual

◆ newestSegment()

virtual SegmentInfoPtr Lucene::IndexWriter::newestSegment ( )
virtual

Utility routines for tests.

◆ newSegmentName()

virtual String Lucene::IndexWriter::newSegmentName ( )
virtual

◆ noDupDirs()

virtual void Lucene::IndexWriter::noDupDirs ( Collection< DirectoryPtr dirs)
protectedvirtual

◆ nrtIsCurrent()

virtual bool Lucene::IndexWriter::nrtIsCurrent ( const SegmentInfosPtr infos)
virtual

◆ numDeletedDocs()

virtual int32_t Lucene::IndexWriter::numDeletedDocs ( const SegmentInfoPtr info)
virtual

Obtain the number of deleted docs for a pooled reader. If the reader isn't being pooled, the segmentInfo's delCount is returned.

◆ numDocs()

virtual int32_t Lucene::IndexWriter::numDocs ( )
virtual

Returns total number of docs in this index, including docs not yet flushed (still in the RAM buffer), and including deletions. NOTE: buffered deletions are not counted. If you really need these to be counted you should call commit() first.

◆ numRamDocs()

virtual int32_t Lucene::IndexWriter::numRamDocs ( )
virtual

Return the number of documents currently buffered in RAM.

◆ optimize() [1/4]

virtual void Lucene::IndexWriter::optimize ( )
virtual

Requests an "optimize" operation on an index, priming the index for the fastest available search. Traditionally this has meant merging all segments into a single segment as is done in the default merge policy, but individual merge policies may implement optimize in different ways.

It is recommended that this method be called upon completion of indexing. In environments with frequent updates, optimize is best done during low volume times, if at all.

Note that optimize requires 2X the index size free space in your Directory (3X if you're using compound file format). For example, if your index size is 10 MB then you need 20 MB free for optimize to complete (30 MB if you're using compound file format).

If some but not all readers re-open while an optimize is underway, this will cause > 2X temporary space to be consumed as those new readers will then hold open the partially optimized segments at that time. It is best not to re-open readers while optimize is running.

The actual temporary usage could be much less than these figures (it depends on many factors).

In general, once the optimize completes, the total size of the index will be less than the size of the starting index. It could be quite a bit smaller (if there were many pending deletes) or just slightly smaller.

If an Exception is hit during optimize(), for example due to disk full, the index will not be corrupt and no documents will have been lost. However, it may have been partially optimized (some segments were merged but not all), and it's possible that one of the segments in the index will be in non-compound format even when using compound file format. This will occur when the exception is hit during conversion of the segment into compound format.

This call will optimize those segments present in the index when the call started. If other threads are still adding documents and flushing segments, those newly created segments will not be optimized unless you call optimize again.

NOTE: if this method hits an std::bad_alloc you should immediately close the writer.

See also
LogMergePolicy::findMergesForOptimize

◆ optimize() [2/4]

virtual void Lucene::IndexWriter::optimize ( bool  doWait)
virtual

Just like optimize(), except you can specify whether the call should block until the optimize completes. This is only meaningful with a MergeScheduler that is able to run merges in background threads.

NOTE: if this method hits an std::bad_alloc you should immediately close the writer.

◆ optimize() [3/4]

virtual void Lucene::IndexWriter::optimize ( int32_t  maxNumSegments)
virtual

Optimize the index down to <= maxNumSegments. If maxNumSegments==1 then this is the same as optimize().

NOTE: if this method hits an std::bad_alloc you should immediately close the writer.

Parameters
maxNumSegmentsmaximum number of segments left in the index after optimization finishes

◆ optimize() [4/4]

virtual void Lucene::IndexWriter::optimize ( int32_t  maxNumSegments,
bool  doWait 
)
virtual

Just like optimize(int32_t), except you can specify whether the call should block until the optimize completes. This is only meaningful with a MergeScheduler that is able to run merges in background threads.

NOTE: if this method hits an std::bad_alloc you should immediately close the writer.

◆ optimizeMergesPending()

virtual bool Lucene::IndexWriter::optimizeMergesPending ( )
protectedvirtual

Returns true if any merges in pendingMerges or runningMerges are optimization merges.

◆ prepareCommit() [1/2]

virtual void Lucene::IndexWriter::prepareCommit ( )
virtual

Prepare for commit.

NOTE: if this method hits an std::bad_alloc you should immediately close the writer.

See also
prepareCommit(MapStringString)

◆ prepareCommit() [2/2]

virtual void Lucene::IndexWriter::prepareCommit ( MapStringString  commitUserData)
virtual

Prepare for commit, specifying commitUserData Map (String -> String). This does the first phase of 2-phase commit. This method does all steps necessary to commit changes since this writer was opened: flushes pending added and deleted docs, syncs the index files, writes most of next segments_N file. After calling this you must call either commit() to finish the commit, or rollback() to revert the commit and undo all changes done since the writer was opened.

You can also just call commit(Map) directly without prepareCommit first in which case that method will internally call prepareCommit.

NOTE: if this method hits an std::bad_alloc you should immediately close the writer.

Parameters
commitUserDataOpaque Map (String->String) that's recorded into the segments file in the index, and retrievable by IndexReader#getCommitUserData. Note that when IndexWriter commits itself during close, the commitUserData is unchanged (just carried over from the prior commit). If this is null then the previous commitUserData is kept. Also, the commitUserData

◆ pushMaxBufferedDocs()

virtual void Lucene::IndexWriter::pushMaxBufferedDocs ( )
protectedvirtual

If we are flushing by doc count (not by RAM usage), and using LogDocMergePolicy then push maxBufferedDocs down as its minMergeDocs, to keep backwards compatibility.

◆ ramSizeInBytes()

virtual int64_t Lucene::IndexWriter::ramSizeInBytes ( )
virtual

Return the total size of all index files currently cached in memory. Useful for size management with flushRamDocs()

◆ registerMerge()

virtual bool Lucene::IndexWriter::registerMerge ( const OneMergePtr merge)
virtual

Checks whether this merge involves any segments already participating in a merge. If not, this merge is "registered", meaning we record that its segments are now participating in a merge, and true is returned. Else (the merge conflicts) false is returned.

◆ releaseRead()

virtual void Lucene::IndexWriter::releaseRead ( )
virtual

◆ releaseWrite()

virtual void Lucene::IndexWriter::releaseWrite ( )
virtual

◆ resetMergeExceptions()

virtual void Lucene::IndexWriter::resetMergeExceptions ( )
protectedvirtual

◆ resolveExternalSegments()

virtual void Lucene::IndexWriter::resolveExternalSegments ( )
protectedvirtual

If any of our segments are using a directory != ours then we have to either copy them over one by one, merge them (if merge policy has chosen to) or wait until currently running merges (in the background) complete. We don't return until the SegmentInfos has no more external segments. Currently this is only used by addIndexesNoOptimize().

◆ resumeAddIndexes()

virtual void Lucene::IndexWriter::resumeAddIndexes ( )
protectedvirtual

◆ rollback()

virtual void Lucene::IndexWriter::rollback ( )
virtual

Close the IndexWriter without committing any changes that have occurred since the last commit (or since it was opened, if commit hasn't been called). This removes any temporary files that had been created, after which the state of the index will be the same as it was when commit() was last called or when this writer was first opened. This also clears a previous call to prepareCommit.

◆ rollbackInternal()

virtual void Lucene::IndexWriter::rollbackInternal ( )
protectedvirtual

◆ rollbackTransaction()

virtual void Lucene::IndexWriter::rollbackTransaction ( )
protectedvirtual

Rolls back the transaction and restores state to where we were at the start.

◆ segString() [1/2]

virtual String Lucene::IndexWriter::segString ( )
virtual

◆ segString() [2/2]

virtual String Lucene::IndexWriter::segString ( const SegmentInfosPtr infos)
protectedvirtual

◆ setDefaultInfoStream()

static void Lucene::IndexWriter::setDefaultInfoStream ( const InfoStreamPtr infoStream)
static

If non-null, this will be the default infoStream used by a newly instantiated IndexWriter.

See also
setInfoStream

◆ setDefaultWriteLockTimeout()

static void Lucene::IndexWriter::setDefaultWriteLockTimeout ( int64_t  writeLockTimeout)
static

Sets the default (for any instance of IndexWriter) maximum time to wait for a write lock (in milliseconds).

◆ setDiagnostics() [1/2]

virtual void Lucene::IndexWriter::setDiagnostics ( const SegmentInfoPtr info,
const String &  source 
)
protectedvirtual

◆ setDiagnostics() [2/2]

virtual void Lucene::IndexWriter::setDiagnostics ( const SegmentInfoPtr info,
const String &  source,
MapStringString  details 
)
protectedvirtual

◆ setInfoStream()

virtual void Lucene::IndexWriter::setInfoStream ( const InfoStreamPtr infoStream)
virtual

If non-null, information about merges, deletes and a message when maxFieldLength is reached will be printed to this.

◆ setMaxBufferedDeleteTerms()

virtual void Lucene::IndexWriter::setMaxBufferedDeleteTerms ( int32_t  maxBufferedDeleteTerms)
virtual

Determines the minimal number of delete terms required before the buffered in-memory delete terms are applied and flushed. If there are documents buffered in memory at the time, they are merged and a new segment is created.

Disabled by default (writer flushes by RAM usage).

See also
setRAMBufferSizeMB

◆ setMaxBufferedDocs()

virtual void Lucene::IndexWriter::setMaxBufferedDocs ( int32_t  maxBufferedDocs)
virtual

Determines the minimal number of documents required before the buffered in-memory documents are flushed as a new Segment. Large values generally gives faster indexing.

When this is set, the writer will flush every maxBufferedDocs added documents. Pass in DISABLE_AUTO_FLUSH to prevent triggering a flush due to number of buffered documents. Note that if flushing by RAM usage is also enabled, then the flush will be triggered by whichever comes first.

Disabled by default (writer flushes by RAM usage).

See also
setRAMBufferSizeMB

◆ setMaxFieldLength()

virtual void Lucene::IndexWriter::setMaxFieldLength ( int32_t  maxFieldLength)
virtual

The maximum number of terms that will be indexed for a single field in a document. This limits the amount of memory required for indexing, so that collections with very large files will not crash the indexing process by running out of memory. This setting refers to the number of running terms, not to the number of different terms. Note: this silently truncates large documents, excluding from the index all terms that occur further in the document. If you know your source documents are large, be sure to set this value high enough to accommodate the expected size. If you set it to INT_MAX, then the only limit is your memory, but you should anticipate an std::bad_alloc. By default, no more than DEFAULT_MAX_FIELD_LENGTH terms will be indexed for a field.

◆ setMaxMergeDocs()

virtual void Lucene::IndexWriter::setMaxMergeDocs ( int32_t  maxMergeDocs)
virtual

Determines the largest segment (measured by document count) that may be merged with other segments. Small values (eg., less than 10,000) are best for interactive indexing, as this limits the length of pauses while indexing to a few seconds. Larger values are best for batched indexing and speedier searches.

The default value is INT_MAX.

Note that this method is a convenience method: it just calls mergePolicy.setMaxMergeDocs as long as mergePolicy is an instance of LogMergePolicy. Otherwise an IllegalArgument exception is thrown.

The default merge policy (LogByteSizeMergePolicy) also allows you to set this limit by net size (in MB) of the segment, using LogByteSizeMergePolicy#setMaxMergeMB.

◆ setMergeDocStoreIsCompoundFile()

virtual void Lucene::IndexWriter::setMergeDocStoreIsCompoundFile ( const OneMergePtr merge)
protectedvirtual

◆ setMergedSegmentWarmer()

virtual void Lucene::IndexWriter::setMergedSegmentWarmer ( const IndexReaderWarmerPtr warmer)
virtual

Set the merged segment warmer. See IndexReaderWarmer.

◆ setMergeFactor()

virtual void Lucene::IndexWriter::setMergeFactor ( int32_t  mergeFactor)
virtual

Determines how often segment indices are merged by addDocument(). With smaller values, less RAM is used while indexing, and searches on unoptimized indices are faster, but indexing speed is slower. With larger values, more RAM is used during indexing, and while searches on unoptimized indices are slower, indexing is faster. Thus larger values (> 10) are best for batch index creation, and smaller values (< 10) for indices that are interactively maintained.

Note that this method is a convenience method: it just calls mergePolicy.setMergeFactor as long as mergePolicy is an instance of LogMergePolicy. Otherwise an IllegalArgument exception is thrown. This must never be less than 2. The default value is 10.

◆ setMergePolicy()

virtual void Lucene::IndexWriter::setMergePolicy ( const MergePolicyPtr mp)
virtual

Set the merge policy used by this writer.

◆ setMergeScheduler()

virtual void Lucene::IndexWriter::setMergeScheduler ( const MergeSchedulerPtr mergeScheduler)
virtual

Set the merge scheduler used by this writer.

◆ setMessageID()

virtual void Lucene::IndexWriter::setMessageID ( const InfoStreamPtr infoStream)
protectedvirtual

◆ setRAMBufferSizeMB()

virtual void Lucene::IndexWriter::setRAMBufferSizeMB ( double  mb)
virtual

Determines the amount of RAM that may be used for buffering added documents and deletions before they are flushed to the Directory. Generally for faster indexing performance it's best to flush by RAM usage instead of document count and use as large a RAM buffer as you can.

When this is set, the writer will flush whenever buffered documents and deletions use this much RAM. Pass in DISABLE_AUTO_FLUSH to prevent triggering a flush due to RAM usage. Note that if flushing by document count is also enabled, then the flush will be triggered by whichever comes first.

Note: the account of RAM usage for pending deletions is only approximate. Specifically, if you delete by Query, Lucene currently has no way to measure the RAM usage if individual Queries so the accounting will under-estimate and you should compensate by either calling commit() periodically yourself, or by using setMaxBufferedDeleteTerms to flush by count instead of RAM usage (each buffered delete Query counts as one).

Note: because IndexWriter uses int32_t when managing its internal storage, the absolute maximum value for this setting is somewhat less than 2048 MB. The precise limit depends on various factors, such as how large your documents are, how many fields have norms, etc., so it's best to set this value comfortably under 2048.

The default value is DEFAULT_RAM_BUFFER_SIZE_MB.

◆ setReaderTermsIndexDivisor()

virtual void Lucene::IndexWriter::setReaderTermsIndexDivisor ( int32_t  divisor)
virtual

Sets the termsIndexDivisor passed to any readers that IndexWriter opens, for example when applying deletes or creating a near-real-time reader in IndexWriter#getReader. Default value is IndexReader#DEFAULT_TERMS_INDEX_DIVISOR.

◆ setRollbackSegmentInfos()

virtual void Lucene::IndexWriter::setRollbackSegmentInfos ( const SegmentInfosPtr infos)
protectedvirtual

◆ setSimilarity()

virtual void Lucene::IndexWriter::setSimilarity ( const SimilarityPtr similarity)
virtual

Set the Similarity implementation used by this IndexWriter.

◆ setTermIndexInterval()

virtual void Lucene::IndexWriter::setTermIndexInterval ( int32_t  interval)
virtual

Set the interval between indexed terms. Large values cause less memory to be used by IndexReader, but slow random-access to terms. Small values cause more memory to be used by an IndexReader, and speed random-access to terms.

This parameter determines the amount of computation required per query term, regardless of the number of documents that contain that term. In particular, it is the maximum number of other terms that must be scanned before a term is located and its frequency and position information may be processed. In a large index with user-entered query terms, query processing time is likely to be dominated not by term lookup but rather by the processing of frequency and positional data. In a small index or when many uncommon query terms are generated (eg., by wildcard queries) term lookup may become a dominant cost.

In particular, numUniqueTerms/interval terms are read into memory by an IndexReader, and on average, interval/2 terms must be scanned for each random term access.

See also
DEFAULT_TERM_INDEX_INTERVAL

◆ setUseCompoundFile()

virtual void Lucene::IndexWriter::setUseCompoundFile ( bool  value)
virtual

Setting to turn on usage of a compound file. When on, multiple files for each segment are merged into a single file when a new segment is flushed.

Note that this method is a convenience method: it just calls mergePolicy.setUseCompoundFile as long as mergePolicy is an instance of LogMergePolicy. Otherwise an IllegalArgument exception is thrown.

◆ setWriteLockTimeout()

virtual void Lucene::IndexWriter::setWriteLockTimeout ( int64_t  writeLockTimeout)
virtual

Sets the maximum time to wait for a write lock (in milliseconds) for this instance of IndexWriter.

See also
setDefaultWriteLockTimeout to change the default value for all instances of IndexWriter.

◆ shared_from_this()

boost::shared_ptr< IndexWriter > Lucene::IndexWriter::shared_from_this ( )
inline

◆ shouldClose()

virtual bool Lucene::IndexWriter::shouldClose ( )
protectedvirtual

Returns true if this thread should attempt to close, or false if IndexWriter is now closed; else, waits until another thread finishes closing.

◆ startCommit()

virtual void Lucene::IndexWriter::startCommit ( int64_t  sizeInBytes,
MapStringString  commitUserData 
)
protectedvirtual

Walk through all files referenced by the current segmentInfos and ask the Directory to sync each file, if it wasn't already. If that succeeds, then we prepare a new segments_N file but do not fully commit it.

◆ startSync()

virtual bool Lucene::IndexWriter::startSync ( const String &  fileName,
HashSet< String >  pending 
)
protectedvirtual

◆ startTransaction()

virtual void Lucene::IndexWriter::startTransaction ( bool  haveReadLock)
protectedvirtual

Begin a transaction. During a transaction, any segment merges that happen (or ram segments flushed) will not write a new segments file and will not remove any files that were present at the start of the transaction. You must make a matched call to commitTransaction() or rollbackTransaction() to finish the transaction.

Note that buffered documents and delete terms are not handled within the transactions, so they must be flushed before the transaction is started.

◆ testPoint()

virtual bool Lucene::IndexWriter::testPoint ( const String &  name)
virtual

Used only by assert for testing. Current points: startDoFlush startCommitMerge startStartCommit midStartCommit midStartCommit2 midStartCommitSuccess finishStartCommit startCommitMergeDeletes startMergeInit startApplyDeletes startMergeInit startMergeInit.

◆ unlock()

static void Lucene::IndexWriter::unlock ( const DirectoryPtr directory)
static

Forcibly unlocks the index in the named directory. Caution: this should only be used by failure recovery code, when it is known that no other process nor thread is in fact currently accessing this index.

◆ updateDocument() [1/2]

virtual void Lucene::IndexWriter::updateDocument ( const TermPtr term,
const DocumentPtr doc 
)
virtual

Updates a document by first deleting the document(s) containing term and then adding the new document. The delete and then add are atomic as seen by a reader on the same index (flush may happen only after the add).

NOTE: if this method hits an std::bad_alloc you should immediately close the writer.

Parameters
termthe term to identify the document(s) to be deleted
docthe document to be added

◆ updateDocument() [2/2]

virtual void Lucene::IndexWriter::updateDocument ( const TermPtr term,
const DocumentPtr doc,
const AnalyzerPtr analyzer 
)
virtual

Updates a document by first deleting the document(s) containing term and then adding the new document. The delete and then add are atomic as seen by a reader on the same index (flush may happen only after the add).

NOTE: if this method hits an std::bad_alloc you should immediately close the writer.

Parameters
termthe term to identify the document(s) to be deleted
docthe document to be added
analyzerthe analyzer to use when analyzing the document

◆ updatePendingMerges()

virtual void Lucene::IndexWriter::updatePendingMerges ( int32_t  maxNumSegmentsOptimize,
bool  optimize 
)
protectedvirtual

◆ upgradeReadToWrite()

virtual void Lucene::IndexWriter::upgradeReadToWrite ( )
virtual

Allows one readLock to upgrade to a writeLock even if there are other readLocks as long as all other readLocks are also blocked in this method.

◆ verbose()

virtual bool Lucene::IndexWriter::verbose ( )
virtual

Returns true if verbosing is enabled (i.e., infoStream != null).

◆ waitForAllSynced()

bool Lucene::IndexWriter::waitForAllSynced ( HashSet< String >  syncing)
protected

Blocks until all files in syncing are sync'd.

◆ waitForMerges()

virtual void Lucene::IndexWriter::waitForMerges ( )
virtual

Wait for any currently outstanding merges to finish.

It is guaranteed that any merges started prior to calling this method will have completed once this method completes.

Field Documentation

◆ __pad0__

INTERNAL Lucene::IndexWriter::__pad0__
protected

◆ analyzer

AnalyzerPtr Lucene::IndexWriter::analyzer
protected

◆ changeCount

int64_t Lucene::IndexWriter::changeCount
protected

◆ closed

bool Lucene::IndexWriter::closed
protected

◆ closing

bool Lucene::IndexWriter::closing
protected

◆ commitLock

SynchronizePtr Lucene::IndexWriter::commitLock
protected

Used only by commit; lock order is commitLock -> IW.

◆ create

bool Lucene::IndexWriter::create
protected

◆ DEFAULT_MAX_BUFFERED_DELETE_TERMS

const int32_t Lucene::IndexWriter::DEFAULT_MAX_BUFFERED_DELETE_TERMS
static

Disabled by default (because IndexWriter flushes by RAM usage by default). Change using setMaxBufferedDeleteTerms(int32_t).

◆ DEFAULT_MAX_BUFFERED_DOCS

const int32_t Lucene::IndexWriter::DEFAULT_MAX_BUFFERED_DOCS
static

Disabled by default (because IndexWriter flushes by RAM usage by default). Change using setMaxBufferedDocs(int32_t).

◆ DEFAULT_MAX_FIELD_LENGTH

const int32_t Lucene::IndexWriter::DEFAULT_MAX_FIELD_LENGTH
static

Default value is 10,000. Change using setMaxFieldLength(int32_t).

◆ DEFAULT_RAM_BUFFER_SIZE_MB

const double Lucene::IndexWriter::DEFAULT_RAM_BUFFER_SIZE_MB
static

Default value is 16 MB (which means flush when buffered docs consume 16 MB RAM). Change using setRAMBufferSizeMB.

◆ DEFAULT_TERM_INDEX_INTERVAL

const int32_t Lucene::IndexWriter::DEFAULT_TERM_INDEX_INTERVAL
static

Default value is 128. Change using setTermIndexInterval(int32_t).

◆ defaultInfoStream

InfoStreamPtr Lucene::IndexWriter::defaultInfoStream
staticprotected

◆ deleter

IndexFileDeleterPtr Lucene::IndexWriter::deleter
protected

◆ deletionPolicy

IndexDeletionPolicyPtr Lucene::IndexWriter::deletionPolicy
protected

◆ directory

DirectoryPtr Lucene::IndexWriter::directory
protected

◆ DISABLE_AUTO_FLUSH

const int32_t Lucene::IndexWriter::DISABLE_AUTO_FLUSH
static

Value to denote a flush trigger is disabled.

◆ docWriter

DocumentsWriterPtr Lucene::IndexWriter::docWriter
protected

◆ flushCount

int32_t Lucene::IndexWriter::flushCount
protected

◆ flushDeletesCount

int32_t Lucene::IndexWriter::flushDeletesCount
protected

◆ hitOOM

bool Lucene::IndexWriter::hitOOM
protected

◆ indexCommit

IndexCommitPtr Lucene::IndexWriter::indexCommit
protected

◆ indexingChain

IndexingChainPtr Lucene::IndexWriter::indexingChain
protected

◆ infoStream

InfoStreamPtr Lucene::IndexWriter::infoStream
protected

◆ lastCommitChangeCount

int64_t Lucene::IndexWriter::lastCommitChangeCount
protected

◆ localFlushedDocCount

int32_t Lucene::IndexWriter::localFlushedDocCount
protected

◆ localRollbackSegmentInfos

SegmentInfosPtr Lucene::IndexWriter::localRollbackSegmentInfos
protected

◆ maxFieldLength

int32_t Lucene::IndexWriter::maxFieldLength
protected

The maximum number of terms that will be indexed for a single field in a document. This limits the amount of memory required for indexing, so that collections with very large files will not crash the indexing process by running out of memory. Note that this effectively truncates large documents, excluding from the index terms that occur further in the document. If you know your source documents are large, be sure to set this value high enough to accommodate the expected size. If you set it to INT_MAX, then the only limit is your memory, but you should anticipate an std::bad_alloc. By default, no more than 10,000 terms will be indexed for a field.

See also
setMaxFieldLength(int32_t)

◆ MaxFieldLengthLIMITED

const int32_t Lucene::IndexWriter::MaxFieldLengthLIMITED
static

Sets the maximum field length to DEFAULT_MAX_FIELD_LENGTH.

◆ MaxFieldLengthUNLIMITED

const int32_t Lucene::IndexWriter::MaxFieldLengthUNLIMITED
static

Sets the maximum field length to INT_MAX.

◆ MERGE_READ_BUFFER_SIZE

const int32_t Lucene::IndexWriter::MERGE_READ_BUFFER_SIZE
staticprotected

The normal read buffer size defaults to 1024, but increasing this during merging seems to yield performance gains. However we don't want to increase it too much because there are quite a few BufferedIndexInputs created during merging.

◆ mergedSegmentWarmer

IndexReaderWarmerPtr Lucene::IndexWriter::mergedSegmentWarmer
protected

◆ mergeExceptions

Collection<OneMergePtr> Lucene::IndexWriter::mergeExceptions
protected

◆ mergeGen

int64_t Lucene::IndexWriter::mergeGen
protected

◆ mergePolicy

MergePolicyPtr Lucene::IndexWriter::mergePolicy
protected

◆ mergeScheduler

MergeSchedulerPtr Lucene::IndexWriter::mergeScheduler
protected

◆ mergingSegments

SetSegmentInfo Lucene::IndexWriter::mergingSegments
protected

◆ MESSAGE_ID

int32_t Lucene::IndexWriter::MESSAGE_ID
staticprotected

◆ messageID

int32_t Lucene::IndexWriter::messageID
protected

◆ messageIDLock

SynchronizePtr Lucene::IndexWriter::messageIDLock
protected

◆ optimizeMaxNumSegments

int32_t Lucene::IndexWriter::optimizeMaxNumSegments
protected

◆ pendingCommitChangeCount

int64_t Lucene::IndexWriter::pendingCommitChangeCount
protected

◆ pendingMerges

Collection<OneMergePtr> Lucene::IndexWriter::pendingMerges
protected

◆ poolReaders

bool Lucene::IndexWriter::poolReaders
protected

◆ readCount

int32_t Lucene::IndexWriter::readCount
protected

Used to only allow one addIndexes to proceed at once.

◆ readerPool

ReaderPoolPtr Lucene::IndexWriter::readerPool
protected

◆ readerTermsIndexDivisor

int32_t Lucene::IndexWriter::readerTermsIndexDivisor
protected

◆ rollbackSegmentInfos

SegmentInfosPtr Lucene::IndexWriter::rollbackSegmentInfos
protected

◆ rollbackSegments

MapSegmentInfoInt Lucene::IndexWriter::rollbackSegments
protected

◆ runningMerges

SetOneMerge Lucene::IndexWriter::runningMerges
protected

◆ segmentInfos

SegmentInfosPtr Lucene::IndexWriter::segmentInfos
protected

◆ segmentsToOptimize

SetSegmentInfo Lucene::IndexWriter::segmentsToOptimize
protected

◆ similarity

SimilarityPtr Lucene::IndexWriter::similarity
protected

◆ stopMerges

bool Lucene::IndexWriter::stopMerges
protected

◆ synced

HashSet<String> Lucene::IndexWriter::synced
protected

◆ syncing

HashSet<String> Lucene::IndexWriter::syncing
protected

◆ termIndexInterval

int32_t Lucene::IndexWriter::termIndexInterval
protected

◆ upgradeCount

int32_t Lucene::IndexWriter::upgradeCount
protected

◆ WRITE_LOCK_NAME

const String Lucene::IndexWriter::WRITE_LOCK_NAME
static

◆ WRITE_LOCK_TIMEOUT

int64_t Lucene::IndexWriter::WRITE_LOCK_TIMEOUT
static

Default value for the write lock timeout (1,000).

See also
setDefaultWriteLockTimeout

◆ writeLock

LockPtr Lucene::IndexWriter::writeLock
protected

◆ writeLockTimeout

int64_t Lucene::IndexWriter::writeLockTimeout
protected

◆ writeThread

int64_t Lucene::IndexWriter::writeThread
protected

The documentation for this class was generated from the following file:

clucene.sourceforge.net