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


LuceneTypes.h
Go to the documentation of this file.
1 // Copyright (c) 2009-2014 Alan Wright. All rights reserved.
3 // Distributable under the terms of either the Apache License (Version 2.0)
4 // or the GNU Lesser General Public License.
6 
7 #ifndef LUCENETYPES_H
8 #define LUCENETYPES_H
9 
10 #include "Lucene.h"
11 
12 #define DECLARE_SHARED_PTR(Type) \
13  class Type; \
14  typedef boost::shared_ptr<Type> Type##Ptr; \
15  typedef boost::weak_ptr<Type> Type##WeakPtr;
16 
17 namespace Lucene {
18 
19 // analysis
50 DECLARE_SHARED_PTR(StandardAnalyzerSavedStreams)
55 DECLARE_SHARED_PTR(StopAnalyzerSavedStreams)
68 
69 // document
83 
84 // index
100 DECLARE_SHARED_PTR(CoreReaders)
132 DECLARE_SHARED_PTR(FieldsReaderLocal)
135 DECLARE_SHARED_PTR(FindSegmentsModified)
136 DECLARE_SHARED_PTR(FindSegmentsOpen)
137 DECLARE_SHARED_PTR(FindSegmentsRead)
138 DECLARE_SHARED_PTR(FindSegmentsReopen)
177 DECLARE_SHARED_PTR(MergeThread)
185 DECLARE_SHARED_PTR(MyCommitPoint)
186 DECLARE_SHARED_PTR(MySegmentTermDocs)
195 DECLARE_SHARED_PTR(ParallelTermEnum)
196 DECLARE_SHARED_PTR(ParallelTermDocs)
197 DECLARE_SHARED_PTR(ParallelTermPositions)
216 DECLARE_SHARED_PTR(SegmentReaderRef)
244 DECLARE_SHARED_PTR(TermPositionsQueue)
266 
267 // query parser
275 
276 // search
283 DECLARE_SHARED_PTR(BooleanWeight)
291 DECLARE_SHARED_PTR(CachedDfSource)
299 DECLARE_SHARED_PTR(ConstantScoreAutoRewriteDefault)
300 DECLARE_SHARED_PTR(ConstantScoreBooleanQueryRewrite)
301 DECLARE_SHARED_PTR(ConstantScoreFilterRewrite)
303 DECLARE_SHARED_PTR(ConstantScorer)
304 DECLARE_SHARED_PTR(ConstantWeight)
311 DECLARE_SHARED_PTR(CustomWeight)
312 DECLARE_SHARED_PTR(CustomScorer)
313 DECLARE_SHARED_PTR(DefaultByteParser)
314 DECLARE_SHARED_PTR(DefaultCustomScoreProvider)
315 DECLARE_SHARED_PTR(DefaultDoubleParser)
316 DECLARE_SHARED_PTR(DefaultIntParser)
317 DECLARE_SHARED_PTR(DefaultLongParser)
321 DECLARE_SHARED_PTR(DisjunctionMaxWeight)
329 DECLARE_SHARED_PTR(EmptyDocIdSet)
330 DECLARE_SHARED_PTR(EmptyDocIdSetIterator)
335 DECLARE_SHARED_PTR(FieldCacheDocIdSet)
340 DECLARE_SHARED_PTR(FieldCacheRangeFilterByte)
341 DECLARE_SHARED_PTR(FieldCacheRangeFilterDouble)
342 DECLARE_SHARED_PTR(FieldCacheRangeFilterInt)
343 DECLARE_SHARED_PTR(FieldCacheRangeFilterLong)
344 DECLARE_SHARED_PTR(FieldCacheRangeFilterString)
347 DECLARE_SHARED_PTR(FieldCacheTermsFilterDocIdSet)
351 DECLARE_SHARED_PTR(FieldDocIdSetIteratorIncrement)
352 DECLARE_SHARED_PTR(FieldDocIdSetIteratorTermDocs)
359 DECLARE_SHARED_PTR(FilterCache)
360 DECLARE_SHARED_PTR(FilterCleaner)
364 DECLARE_SHARED_PTR(FilteredQueryWeight)
380 DECLARE_SHARED_PTR(MatchAllDocsWeight)
381 DECLARE_SHARED_PTR(MatchAllScorer)
384 DECLARE_SHARED_PTR(MultiComparatorsFieldValueHitQueue)
387 DECLARE_SHARED_PTR(MultiSearcherCallableNoSort)
388 DECLARE_SHARED_PTR(MultiSearcherCallableWithSort)
395 DECLARE_SHARED_PTR(NumericUtilsDoubleParser)
396 DECLARE_SHARED_PTR(NumericUtilsIntParser)
397 DECLARE_SHARED_PTR(NumericUtilsLongParser)
398 DECLARE_SHARED_PTR(OneComparatorFieldValueHitQueue)
408 DECLARE_SHARED_PTR(PayloadTermSpanScorer)
409 DECLARE_SHARED_PTR(PayloadTermWeight)
431 DECLARE_SHARED_PTR(ScoreTermQueue)
432 DECLARE_SHARED_PTR(ScoringBooleanQueryRewrite)
436 DECLARE_SHARED_PTR(SimilarityDisableCoord)
438 DECLARE_SHARED_PTR(SimilarityIDFExplanation)
470 DECLARE_SHARED_PTR(TimerThread)
478 DECLARE_SHARED_PTR(ValueSourceScorer)
479 DECLARE_SHARED_PTR(ValueSourceWeight)
483 
484 // store
499 DECLARE_SHARED_PTR(MMapIndexInput)
500 DECLARE_SHARED_PTR(NativeFSLock)
510 DECLARE_SHARED_PTR(SimpleFSIndexInput)
511 DECLARE_SHARED_PTR(SimpleFSIndexOutput)
512 DECLARE_SHARED_PTR(SimpleFSLock)
514 DECLARE_SHARED_PTR(SingleInstanceLock)
516 
517 // util
531 DECLARE_SHARED_PTR(HeapedScorerDoc)
548 DECLARE_SHARED_PTR(ReaderField)
561 }
562 
563 #endif
Definition: ByteBlockPool.h:54
A Filter that only accepts numeric values within a specified range. To use this, you must first index...
Definition: NumericRangeFilter.h:24
The term text of a Token.
Definition: TermAttribute.h:15
The interface for search implementations.
Definition: Searchable.h:24
Load the First field and break. See FieldSelectorResult#LOAD_AND_BREAK.
Definition: LoadFirstFieldSelector.h:16
Implements LockFactory using File#createNewFile().
Definition: SimpleFSLockFactory.h:17
An IndexWriter creates and maintains an index.
Definition: IndexWriter.h:90
Read text from a character-input stream, buffering characters so as to provide for the efficient read...
Definition: BufferedReader.h:16
Definition: SegmentMerger.h:122
A MergeScheduler that simply does each merge sequentially, using the current thread.
Definition: SerialMergeScheduler.h:15
An abstract class that defines a way for Payload*Query instances to transform the cumulative effects ...
Definition: PayloadFunction.h:18
A straightforward implementation of FSDirectory using std::ofstream and std::ifstream.
Definition: SimpleFSDirectory.h:15
Definition: TermsHashConsumer.h:14
BooleanScorer uses a ~16k array to score windows of docs. So it scores docs 0-16k first...
Definition: BooleanScorer.h:30
Abstract class for enumerating terms.
Definition: TermEnum.h:18
Matches the union of its clauses.
Definition: SpanOrQuery.h:15
Used to buffer the top skip levels.
Definition: MultiLevelSkipListReader.h:88
The positionIncrement determines the position of this token relative to the previous Token in a Token...
Definition: PositionIncrementAttribute.h:32
Similar to NearSpansOrdered, but for the unordered case.
Definition: NearSpansUnordered.h:17
Scorer for conjunctions, sets of queries, all of which are required.
Definition: ConjunctionScorer.h:15
Definition: UnicodeUtils.h:84
Definition: FieldCacheImpl.h:51
This interface describes a character stream that maintains line and column number positions of the ch...
Definition: QueryParserCharStream.h:22
Filters LetterTokenizer with LowerCaseFilter and StopFilter.
Definition: StopAnalyzer.h:18
A Query that matches numeric values within a specified range. To use this, you must first index the n...
Definition: NumericRangeQuery.h:108
A range filter built on top of a cached single term field (in FieldCache).
Definition: FieldCacheRangeFilter.h:38
Declare what fields to load normally and what fields to load lazily.
Definition: SetBasedFieldSelector.h:15
Definition: FieldCacheImpl.h:94
Definition: DocFieldProcessorPerThread.h:63
A filter that replaces accented characters in the ISO Latin 1 character set (ISO-8859-1) by their una...
Definition: ISOLatin1AccentFilter.h:21
Definition: DirectoryReader.h:195
OneMerge provides the information necessary to perform an individual primitive merge operation...
Definition: MergePolicy.h:76
Obtains int field values from the FieldCache using getInts() and makes those values available as othe...
Definition: IntFieldSource.h:24
Utility class to support signaling notifications.
Definition: LuceneSignal.h:16
This class holds the state of an AttributeSource.
Definition: AttributeSource.h:168
Status from testing stored fields.
Definition: CheckIndex.h:275
A Collector implementation which wraps another Collector and makes sure only documents with scores > ...
Definition: PositiveScoresOnlyCollector.h:16
LowerCaseTokenizer performs the function of LetterTokenizer and LowerCaseFilter together. It divides text at non-letters and converts them to lower case. While it is functionally equivalent to the combination of LetterTokenizer and LowerCaseFilter, there is a performance advantage to doing the two tasks at once, hence this (redundant) implementation.
Definition: LowerCaseTokenizer.h:21
Tracks the reference count for a single index file.
Definition: IndexFileDeleter.h:130
Holds details for each commit point. This class is also passed to the deletion policy. Note: this class has a natural ordering that is inconsistent with equals.
Definition: IndexFileDeleter.h:149
Public for use by other weight implementations.
Definition: SpanWeight.h:15
Definition: TermsHashPerField.h:14
A FieldSelector based on a Map of field names to FieldSelectorResults.
Definition: MapFieldSelector.h:17
Basic tool and API to check the health of an index and write a new segments file that removes referen...
Definition: CheckIndex.h:20
Definition: BooleanScorer2.h:85
Base class for Attributes that can be added to a AttributeSource.
Definition: Attribute.h:18
Definition: FormatPostingsTermsConsumer.h:14
This class is very similar to SpanTermQuery except that it factors in the value of the payload locate...
Definition: PayloadTermQuery.h:21
File-based Directory implementation that uses mmap for reading, and SimpleFSIndexOutput for writing...
Definition: MMapDirectory.h:22
Definition: FormatPostingsFieldsWriter.h:14
Gathers all Fieldables for a document under the same name, updates FieldInfos, and calls per-field co...
Definition: DocFieldProcessorPerThread.h:19
A Token's lexical type. The Default value is "word".
Definition: TypeAttribute.h:15
This class accepts multiple added documents and directly writes a single segment file. It does this more efficiently than creating a single segment per document (with DocumentWriter) and doing standard merges on those segments.
Definition: DocumentsWriter.h:54
Definition: HitQueueBase.h:45
A Query that matches documents within an range of terms.
Definition: TermRangeQuery.h:21
A Token is an occurrence of a term from the text of a field. It consists of a term's text...
Definition: Token.h:76
Scoring functionality for phrase queries. A document is considered matching if it contains the phrase...
Definition: PhraseScorer.h:21
Wrapper to allow SpanQuery objects participate in composite single-field SpanQueries by 'lying' about...
Definition: FieldMaskingSpanQuery.h:52
Definition: FieldCacheImpl.h:138
Subclass of FilteredTermEnum for enumerating all terms that match the specified range parameters...
Definition: TermRangeTermEnum.h:18
Definition: FieldCacheImpl.h:105
This class implements a MergePolicy that tries to merge segments into levels of exponentially increas...
Definition: LogMergePolicy.h:24
Definition: DocFieldConsumersPerThread.h:14
Obtains the ordinal of the field value from the default Lucene FieldCache using getStringIndex().
Definition: OrdFieldSource.h:31
Provides support for converting longs to Strings, and back again. The strings are structured so that ...
Definition: NumberTools.h:26
A Collector implementation that collects the top-scoring hits, returning them as a TopDocs...
Definition: TopScoreDocCollector.h:21
Definition: NormsWriterPerThread.h:14
Definition: FreqProxTermsWriter.h:15
Base implementation class for buffered IndexOutput.
Definition: BufferedIndexOutput.h:15
Stores information about how to sort documents by terms in an individual field. Fields must be indexe...
Definition: SortField.h:16
A query that applies a filter to the results of another query.
Definition: FilteredQuery.h:20
A Directory instance that switches files between two other Directory instances.
Definition: FileSwitchDirectory.h:21
Describes the input token stream.
Definition: QueryParserToken.h:15
The most important method is parse(const String&).
Definition: QueryParser.h:70
This IndexDeletionPolicy implementation that keeps only the most recent commit and immediately remove...
Definition: KeepOnlyLastCommitDeletionPolicy.h:16
Class for accessing a compound stream. This class implements a directory, but is limited to only read...
Definition: CompoundFileReader.h:18
Describes the score computation for document and query, and can distinguish a match independent of a ...
Definition: ComplexExplanation.h:16
An "open" BitSet implementation that allows direct access to the array of words storing the bits...
Definition: OpenBitSet.h:19
Interface to parse ints from document fields.
Definition: FieldCache.h:220
Provides access to stored term vector of a document field. The vector consists of the name of the fie...
Definition: TermFreqVector.h:18
Definition: FieldCacheImpl.h:149
A WhitespaceTokenizer is a tokenizer that divides text at whitespace. Adjacent sequences of non-White...
Definition: WhitespaceTokenizer.h:16
Definition: InvertedDocEndConsumer.h:14
Definition: OpenBitSetDISI.h:14
A MergeSpecification instance provides the information necessary to perform multiple merges...
Definition: MergePolicy.h:119
Definition: ExactPhraseScorer.h:14
This is the base class for an in-memory posting list, keyed by a Token. TermsHash maintains a hash ta...
Definition: RawPostingList.h:19
Definition: NumericUtils.h:162
A query that wraps a filter and simply returns a constant score equal to the query boost for every do...
Definition: ConstantScoreQuery.h:18
A Spans that is formed from the ordered subspans of a SpanNearQuery where the subspans do not overlap...
Definition: NearSpansOrdered.h:31
MultiPhraseQuery is a generalized version of PhraseQuery, with an added method add(Term[]). To use this class, to search for the phrase "Microsoft app*" first use add(Term) on the term "Microsoft", then find all terms that have "app" as prefix using IndexReader.terms(Term), and use MultiPhraseQuery.add(Term[] terms) to add them to the query.
Definition: MultiPhraseQuery.h:18
A base class for ValueSource implementations that retrieve values for a single field from the FieldCa...
Definition: FieldCacheSource.h:28
Definition: SegmentTermPositionVector.h:14
CharReader is a Reader wrapper. It reads chars from Reader and outputs CharStream, defining an identify function correctOffset method that simply returns the provided offset.
Definition: CharReader.h:16
Encapsulates sort criteria for returned hits.
Definition: Sort.h:68
Abstract decorator class of a DocIdSetIterator implementation that provides on-demand filter/validati...
Definition: FilteredDocIdSetIterator.h:16
Definition: UTF8Stream.h:106
Abstract decorator class for a DocIdSet implementation that provides on-demand filtering/validation m...
Definition: FilteredDocIdSet.h:23
Abstract class for reading character streams.
Definition: Reader.h:15
Definition: DocFieldConsumer.h:14
A memory-resident Directory implementation. Locking implementation is by default the SingleInstanceLo...
Definition: RAMDirectory.h:17
Definition: StoredFieldsWriter.h:50
Callback for splitLongRange. You need to overwrite only one of the methods. NOTE: This is a very low-...
Definition: NumericUtils.h:148
Allows you to iterate over the TermPositions for multiple Terms as a single TermPositions.
Definition: MultipleTermPositions.h:16
An efficient implementation of QueryParserCharStream interface.
Definition: FastCharStream.h:18
A ScorerDocQueue maintains a partial ordering of its Scorers such that the least Scorer can always be...
Definition: ScorerDocQueue.h:16
This is the Porter stemming algorithm, coded up as thread-safe ANSI C by the author.
Definition: PorterStemmer.h:26
Base class for file system based locking implementation.
Definition: FSLockFactory.h:15
Wraps another filter's result and caches it. The purpose is to allow filters to simply filter...
Definition: CachingWrapperFilter.h:16
Container for a term at a position.
Definition: PositionBasedTermVectorMapper.h:49
Represents a single commit into an index as seen by the IndexDeletionPolicy or IndexReader.
Definition: IndexCommit.h:22
A Collector that sorts by SortField using FieldComparators.
Definition: TopFieldCollector.h:17
Definition: SegmentTermEnum.h:14
RAMFile buffer for DocWriters.
Definition: DocumentsWriter.h:381
Abstract base class for restricting which documents may be returned during searching.
Definition: Filter.h:15
Writes norms. Each thread X field accumulates the norms for the doc/fields it saw, then the flush method below merges all of these together into a single _X.nrm file.
Definition: NormsWriter.h:16
Implements the skip list reader for the default posting list format that stores positions and payload...
Definition: DefaultSkipListReader.h:15
Convenience class for holding TermVector information.
Definition: TermVectorEntry.h:15
Definition: TermsHashPerThread.h:14
Definition: FormatPostingsPositionsWriter.h:14
Definition: PhraseQueue.h:14
Returned from checkIndex() detailing the health and status of the index.
Definition: CheckIndex.h:108
Collects sorted results from Searchable's and collates them. The elements put into this queue must be...
Definition: FieldDocSortedHitQueue.h:16
Definition: DocFieldConsumerPerField.h:14
Convenience class for reading character files.
Definition: FileReader.h:15
Interface to parse longs from document fields.
Definition: FieldCache.h:232
A base class for all collectors that return a TopDocs output. This collector allows easy extension by...
Definition: TopDocsCollector.h:21
An abstract Query that matches documents containing a subset of terms provided by a FilteredTermEnum ...
Definition: MultiTermQuery.h:31
Internal cache.
Definition: FieldCacheImpl.h:72
Provides support for converting dates to strings and vice-versa. The strings are structured so that l...
Definition: DateField.h:31
Used by DocumentsWriter to maintain per-thread state. We keep a separate Posting hash and other state...
Definition: DocumentsWriterThreadState.h:17
This is a DocFieldConsumer that inverts each field, separately, from a Document, and accepts a Invert...
Definition: DocInverterPerThread.h:17
Removes stop words from a token stream.
Definition: StopFilter.h:15
Definition: SegmentMergeQueue.h:14
This abstract class defines methods to iterate over a set of non-decreasing doc ids. Note that this class assumes it iterates on doc Ids, and therefore NO_MORE_DOCS is set to { NO_MORE_DOCS} in order to be used as a sentinel object. Implementations of this class are expected to consider INT_MAX as an invalid value.
Definition: DocIdSetIterator.h:17
Token Manager.
Definition: QueryParserTokenManager.h:15
Store a sorted collection of TermVectorEntrys. Collects all term information into a single...
Definition: SortedTermVectorMapper.h:22
Convenience class for reading strings.
Definition: StringReader.h:15
This class tracks the number and position / offset parameters of terms being added to the index...
Definition: FieldInvertState.h:16
Definition: TermVectorsTermsWriterPerField.h:14
Definition: SpanFilterResult.h:56
Utility class to handle a pool of threads.
Definition: ThreadPool.h:49
Public for extension only.
Definition: TermSpans.h:15
A Query that matches documents containing a particular sequence of terms. A PhraseQuery is built by Q...
Definition: PhraseQuery.h:18
This class can be used if the token attributes of a TokenStream are intended to be consumed more than...
Definition: CachingTokenFilter.h:19
Scoring API.
Definition: Similarity.h:427
Class to write byte streams into slices of shared byte[]. This is used by DocumentsWriter to hold the...
Definition: ByteSliceWriter.h:16
Definition: AllTermDocs.h:14
Abstract API that consumes terms, doc, freq, prox and payloads postings. Concrete implementations of ...
Definition: FormatPostingsFieldsConsumer.h:16
This is a helper class to generate prefix-encoded representations for numerical values and supplies c...
Definition: NumericUtils.h:37
A query that matches all documents.
Definition: MatchAllDocsQuery.h:15
See the description in BooleanScorer, comparing BooleanScorer & BooleanScorer2.
Definition: BooleanScorer2.h:20
Definition: BooleanScorer.h:63
Marker interface as super-interface to all parsers. It is used to specify a custom parser to SortFiel...
Definition: FieldCache.h:200
Definition: CharBlockPool.h:14
Implements LockFactory for a single in-process instance, meaning all locking will take place through ...
Definition: SingleInstanceLockFactory.h:20
A Query that matches documents containing terms with a specified prefix. A PrefixQuery is built by Qu...
Definition: PrefixQuery.h:18
Definition: FormatPostingsPositionsConsumer.h:14
A LetterTokenizer is a tokenizer that divides text at non-letters. That's to say, it defines tokens a...
Definition: LetterTokenizer.h:19
Definition: DirectoryReader.h:278
Remaps docIDs after a merge has completed, where the merged segments had at least one deletion...
Definition: MergeDocIDRemapper.h:17
A FilterIndexReader contains another IndexReader, which it uses as its basic source of data...
Definition: FilterIndexReader.h:21
Definition: InvertedDocEndConsumerPerThread.h:14
Filename filter that accept filenames and extensions only created by Lucene.
Definition: IndexFileNameFilter.h:15
Stores and iterate on sorted integers in compressed form in RAM.
Definition: SortedVIntList.h:22
A Filter that restricts search results to a range of term values in a given field.
Definition: TermRangeFilter.h:22
Removes words that are too long or too short from the stream.
Definition: LengthFilter.h:15
Definition: ReadOnlyDirectoryReader.h:14
Definition: FieldCacheImpl.h:127
Returns the maximum payload score seen, else 1 if there are no payloads on the doc.
Definition: MaxPayloadFunction.h:17
Default scoring implementation.
Definition: DefaultSimilarity.h:15
An IndexReader which reads indexes with multiple segments.
Definition: DirectoryReader.h:19
Definition: DocFieldConsumerPerThread.h:14
An interprocess mutex lock.
Definition: Lock.h:16
A filter that decides which AttributeSource states to store in the sink.
Definition: TeeSinkTokenFilter.h:120
Base class for enumerating all but deleted docs.
Definition: AbstractAllTermDocs.h:18
Subclass of FilteredTermEnum for enumerating all terms that match the specified prefix filter term...
Definition: PrefixTermEnum.h:18
CharStream adds correctOffset functionality over Reader. All Tokenizers accept a CharStream instead o...
Definition: CharStream.h:18
A query that generates the union of documents produced by its subqueries, and that scores each docume...
Definition: DisjunctionMaxQuery.h:27
Constrains search results to only match those which also match a provided query.
Definition: QueryWrapperFilter.h:20
Compares TermVectorEntrys first by frequency and then by the term (case-sensitive) ...
Definition: TermVectorEntryFreqSortedComparator.h:15
A Directory is a flat list of files. Files may be written once, when they are created. Once a file is created it may only be opened for read, or deleted. Random access is permitted both when reading and writing. Directory locking is implemented by an instance of LockFactory, and can be changed for each Directory instance using setLockFactory.
Definition: Directory.h:18
The abstract base class for queries.
Definition: Query.h:31
Synonymous with Field.
Definition: Fieldable.h:20
Definition: UTF8Stream.h:81
A Future represents the result of an asynchronous computation. Methods are provided to check if the c...
Definition: ThreadPool.h:25
Matches spans near the beginning of a field.
Definition: SpanFirstQuery.h:16
This is a LogMergePolicy that measures size of a segment as the total byte size of the segment's file...
Definition: LogByteSizeMergePolicy.h:16
An enumeration of span matches. Used to implement span searching. Each span represents a range of ter...
Definition: Spans.h:17
Definition: QueryTermVector.h:14
Holds state for inverting all occurrences of a single field in the document. This class doesn't do an...
Definition: DocInverterPerField.h:17
A hit queue for sorting by hits by terms in more than one field. Uses FieldCache::DEFAULT for maintai...
Definition: FieldValueHitQueue.h:19
Definition: UTF8Stream.h:120
The TimeLimitingCollector is used to timeout search requests that take longer than the maximum allowe...
Definition: TimeLimitingCollector.h:17
Definition: InvertedDocConsumer.h:14
TermPositions provides an interface for enumerating the *> tuples for...
Definition: TermPositions.h:18
Definition: SegmentTermVector.h:14
Base implementation class for buffered IndexInput.
Definition: BufferedIndexInput.h:15
This class implements InvertedDocConsumer, which is passed each token produced by the analyzer on eac...
Definition: TermsHash.h:18
Subclass of FilteredTermEnum for enumerating all terms that match the specified wildcard filter term...
Definition: WildcardTermEnum.h:18
A FieldComparator compares hits so as to determine their sort order when collecting the top results w...
Definition: FieldComparator.h:42
Number of documents a delete term applies to.
Definition: BufferedDeletes.h:43
Definition: DirectoryReader.h:302
Documents are the unit of indexing and search.
Definition: Document.h:24
Convenience class for storing collate objects.
Definition: Collator.h:15
Provides a FieldComparator for custom field sorting.
Definition: FieldComparatorSource.h:15
Definition: AttributeSource.h:154
Definition: BooleanScorer2.h:125
Experimental class to get set of payloads for most standard Lucene queries. Operates like Highlighter...
Definition: PayloadSpanUtil.h:16
Common scoring functionality for different types of queries.
Definition: Scorer.h:22
Models the existing parallel array structure.
Definition: TermVectorsReader.h:118
The default cache implementation, storing all values in memory. A WeakHashMap is used for storage...
Definition: FieldCacheImpl.h:15
This analyzer is used to facilitate scenarios where different fields require different analysis techn...
Definition: PerFieldAnalyzerWrapper.h:29
Definition: PayloadNearQuery.h:63
Calculate the final score as the average score of all payloads seen.
Definition: AveragePayloadFunction.h:17
Definition: DocumentsWriter.h:356
Definition: TermVectorsTermsWriterPerThread.h:14
Definition: UTF8Stream.h:44
Base class for Directory implementations that store index files in the file system. There are currently three core subclasses:
Definition: FSDirectory.h:29
A Query that matches documents matching boolean combinations of other queries, eg. TermQuerys, PhraseQuerys or other BooleanQuerys.
Definition: BooleanQuery.h:18
Definition: PositionBasedTermVectorMapper.h:14
If getReader has been called (ie, this writer is in near real-time mode), then after a merge complete...
Definition: IndexWriter.h:1100
Definition: TermVectorsTermsWriter.h:54
Definition: SegmentMergeInfo.h:14
An abstract base class for search implementations. Implements the main search methods.
Definition: Searcher.h:18
Small Util class used to pass both an idf factor as well as an explanation for that factor...
Definition: Explanation.h:70
Definition: FieldInfo.h:14
Holds the status of each segment in the index. See segmentInfos.
Definition: CheckIndex.h:168
Subclass of FilteredTermEnum for enumerating a single term.
Definition: SingleTermEnum.h:18
The results of a SpanQueryFilter. Wraps the BitSet and the position information from the SpanQuery...
Definition: SpanFilterResult.h:15
Interface to parse bytes from document fields.
Definition: FieldCache.h:208
Abstract class that defines how the query is rewritten.
Definition: MultiTermQuery.h:122
Definition: BooleanScorer2.h:145
Optimized implementation of a vector of bits.
Definition: BitVector.h:15
File used as buffer in RAMDirectory.
Definition: RAMFile.h:15
An Analyzer builds TokenStreams, which analyze text. It thus represents a policy for extracting index...
Definition: Analyzer.h:19
A Payload is metadata that can be stored together with each occurrence of a term. This metadata is st...
Definition: Payload.h:21
A ScoreDoc which also contains information about how to sort the referenced document. In addition to the document number and score, this object contains an array of values for the document from the field(s) used to sort. For example, if the sort criteria was to sort by fields "a", "b" then "c", the fields object array will have three elements, corresponding respectively to the term values for the document in fields "a", "b" and "c". The class of each element in the array will be either Integer, Double or String depending on the type of values in the terms of each field.
Definition: FieldDoc.h:20
This abstract class reads skip lists with multiple levels.
Definition: MultiLevelSkipListReader.h:20
Implements parallel search over a set of Searchables.
Definition: ParallelMultiSearcher.h:18
Definition: SnapshotDeletionPolicy.h:14
Holds a map of String input to String output, to be used with MappingCharFilter.
Definition: NormalizeCharMap.h:15
Constrains search results to only match those which also match a provided query. Also provides positi...
Definition: SpanQueryFilter.h:20
Provides methods for sanity checking that entries in the FieldCache are not wasteful or inconsistent...
Definition: FieldCacheSanityChecker.h:28
This class is very similar to SpanNearQuery except that it factors in the value of the payloads locat...
Definition: PayloadNearQuery.h:25
Definition: DocConsumerPerThread.h:14
Public for extension only.
Definition: SpanScorer.h:15
For each Field, store a sorted collection of TermVectorEntrys This is not thread-safe.
Definition: FieldSortedTermVectorMapper.h:17
Definition: StoredFieldsWriterPerThread.h:14
Represents field values as different types. Normally created via a ValueSuorce for a particular field...
Definition: DocValues.h:22
Represents hits returned by Searcher#search(QueryPtr, FilterPtr, int32_t) and Searcher#search(QueryPt...
Definition: TopDocs.h:16
Taps into DocInverter, as an InvertedDocEndConsumer, which is called at the end of inverting each fie...
Definition: NormsWriterPerField.h:16
Base class for all Lucene classes.
Definition: LuceneObject.h:31
Simplistic CharFilter that applies the mappings contained in a NormalizeCharMap to the character stre...
Definition: MappingCharFilter.h:16
This is a DocFieldConsumer that writes stored fields.
Definition: StoredFieldsWriter.h:15
An IndexReader which reads multiple indexes, appending their content.
Definition: MultiReader.h:15
Interface to parse doubles from document fields.
Definition: FieldCache.h:244
Base class for Locking implementation. Directory uses instances of this class to implement locking...
Definition: LockFactory.h:23
The TermVectorMapper can be used to map Term Vectors into your own structure instead of the parallel ...
Definition: TermVectorMapper.h:18
Definition: AbstractField.h:14
Simple DocIdSet and DocIdSetIterator backed by a BitSet.
Definition: DocIdBitSet.h:15
A simple class that stores Strings as char[]'s in a hash table. Note that this is not a general purpo...
Definition: CharArraySet.h:17
Describes the score computation for document and query.
Definition: Explanation.h:15
A memory-resident IndexOutput implementation.
Definition: RAMOutputStream.h:15
A Scorer for queries with a required part and an optional part. Delays skipTo() on the optional part ...
Definition: ReqOptSumScorer.h:16
Definition: FreqProxTermsWriterPerField.h:14
Simple utility class providing static methods to compress and decompress binary data for stored field...
Definition: CompressionTools.h:15
This is a DocFieldConsumer that inverts each field, separately, from a Document, and accepts a Invert...
Definition: DocInverter.h:16
Definition: AbstractAllTermDocs.h:12
Definition: SpanFilterResult.h:39
A grammar-based tokenizer.
Definition: StandardTokenizer.h:34
Definition: FieldCacheImpl.h:116
Abstract base class for output to a file in a Directory. A random-access output stream. Used for all Lucene index output operations.
Definition: IndexOutput.h:18
Consumes doc & freq, writing them using the current index file format.
Definition: FormatPostingsDocsWriter.h:15
A MergeScheduler that runs each merge using a separate thread, up until a maximum number of threads (...
Definition: ConcurrentMergeScheduler.h:19
Holds buffered deletes, by docID, term or query. We hold two instances of this class: one for the del...
Definition: BufferedDeletes.h:19
This stores a monotonically increasing set of pairs in a Directory. A TermInfos can be written once, in order.
Definition: TermInfosWriter.h:16
Definition: FieldCache.h:170
A memory-resident IndexInput implementation.
Definition: RAMInputStream.h:15
Abstract class for enumerating a subset of all terms.
Definition: FilteredTermEnum.h:18
Definition: ReadOnlySegmentReader.h:14
Definition: DocInverterPerThread.h:44
A Scorer which wraps another scorer and caches the score of the current document. Successive calls to...
Definition: ScoreCachingWrappingScorer.h:22
Base class for span-based queries.
Definition: SpanQuery.h:15
Definition: StandardTokenizerImpl.h:14
A TokenFilter is a TokenStream whose input is another TokenStream.
Definition: TokenFilter.h:18
A Filter that only accepts documents whose single term value in the specified field is contained in t...
Definition: FieldCacheTermsFilter.h:46
Definition: TermVectorsTermsWriter.h:16
This is just a "splitter" class: it lets you wrap two DocFieldConsumer instances as a single consumer...
Definition: DocFieldConsumers.h:16
Definition: TermBuffer.h:14
The FieldSelector allows one to make decisions about what Fields get loaded on a Document by IndexRea...
Definition: FieldSelector.h:16
Normalizes tokens extracted with StandardTokenizer.
Definition: StandardFilter.h:15
Holds all per thread, per field state.
Definition: DocFieldProcessorPerField.h:15
Implements the fuzzy search query. The similarity measurement is based on the Levenshtein (edit dista...
Definition: FuzzyQuery.h:19
Definition: FieldsWriter.h:14
Definition: DocumentsWriter.h:457
Used by DocumentsWriter to merge the postings from multiple ThreadStates when creating a segment...
Definition: FreqProxFieldMergeState.h:15
A clause in a BooleanQuery.
Definition: BooleanClause.h:15
#define DECLARE_SHARED_PTR(Type)
Definition: LuceneTypes.h:12
A Scorer for OR like queries, counterpart of ConjunctionScorer. This Scorer implements Scorer#skipTo(...
Definition: DisjunctionSumScorer.h:16
Definition: FieldCacheImpl.h:160
Definition: DocumentsWriter.h:469
Definition: FreqProxTermsWriter.h:41
A simple hash table of document scores within a range.
Definition: BooleanScorer.h:119
The SegmentMerger class combines two or more Segments, represented by an IndexReader (add...
Definition: SegmentMerger.h:20
Subclass of FilteredTermEnum for enumerating all terms that are similar to the specified filter term...
Definition: FuzzyTermEnum.h:18
Removes matches which overlap with another SpanQuery.
Definition: SpanNotQuery.h:15
An abstract base class for simple, character-oriented tokenizers.
Definition: CharTokenizer.h:15
Definition: DocFieldConsumers.h:50
A unique Identifier/Description for each item in the FieldCache. Can be useful for logging/debugging...
Definition: FieldCache.h:255
Definition: DocumentsWriter.h:497
Obtains double field values from the FieldCache using getDoubles() and makes those values available a...
Definition: DoubleFieldSource.h:25
Definition: FormatPostingsDocsConsumer.h:14
Definition: SegmentTermPositions.h:14
Collectors are primarily meant to be used to gather raw results from a search, and implement sorting ...
Definition: Collector.h:100
The IndexingChain must define the getChain(DocumentsWriter) method which returns the DocConsumer that...
Definition: DocumentsWriter.h:423
The start and end character offset of a Token.
Definition: PayloadAttribute.h:15
An Analyzer that uses WhitespaceTokenizer.
Definition: WhitespaceAnalyzer.h:15
Utility class to support streaming info messages.
Definition: InfoStream.h:16
Loader for text files that represent a list of stopwords.
Definition: WordlistLoader.h:15
Stream override to write messages to a std::cout.
Definition: InfoStream.h:44
Delegating scoring implementation. Useful in Query#getSimilarity(Searcher) implementations, to override only certain methods of a Searcher's Similarity implementation.
Definition: SimilarityDelegator.h:16
Obtains the ordinal of the field value from the default Lucene FieldCache using getStringIndex() and ...
Definition: ReverseOrdFieldSource.h:31
Definition: InvertedDocConsumerPerField.h:14
A collection of SegmentInfo objects to be used as a base class for SegmentInfos.
Definition: SegmentInfoCollection.h:15
Definition: TermVectorsTermsWriter.h:80
Definition: TermVectorsReader.h:14
An iterator to iterate over set bits in an OpenBitSet. This is faster than nextSetBit() for iterating...
Definition: OpenBitSetIterator.h:17
Simple container for a collection of related CacheEntry objects that in conjunction with each other r...
Definition: FieldCacheSanityChecker.h:95
Definition: TermInfosReader.h:74
Writes bytes through to a primary IndexOutput, computing checksum. Note that you cannot use seek()...
Definition: ChecksumIndexOutput.h:17
Definition: HitQueue.h:14
Implements search over a single IndexReader.
Definition: IndexSearcher.h:23
IndexInput that knows how to read the byte slices written by Posting and PostingVector. We read the bytes in each slice until we hit the end of that slice at which point we read the forwarding address of the next slice and then jump to it.
Definition: ByteSliceReader.h:16
This is a LogMergePolicy that measures size of a segment as the number of documents (not taking delet...
Definition: LogDocMergePolicy.h:16
This stores a monotonically increasing set of pairs in a Directory. Pairs are accessed either by Term or by ordinal position the set.
Definition: TermInfosReader.h:17
Definition: AttributeSource.h:14
Definition: InvertedDocConsumerPerThread.h:14
Lucene thread container.
Definition: LuceneThread.h:23
Definition: FormatPostingsTermsWriter.h:14
A Query that matches documents containing a term. This may be combined with other terms with a Boolea...
Definition: TermQuery.h:16
Definition: SegmentWriteState.h:14
This class provides a Field that enables indexing of numeric values for efficient range filtering and...
Definition: NumericField.h:59
Creates a TokenAttributeFactory returning Token as instance for the basic attributes and for all othe...
Definition: Token.h:338
Utility class to support locking via a mutex.
Definition: Synchronize.h:16
Stream override to write messages to a file.
Definition: InfoStream.h:29
Definition: FieldValueHitQueue.h:56
Implementation of an IndexInput that reads from a portion of the compound file.
Definition: CompoundFileReader.h:83
A DocIdSet contains a set of doc ids. Implementing classes must only implement iterator to provide ac...
Definition: DocIdSet.h:16
The Scorer for DisjunctionMaxQuery. The union of all documents generated by the the subquery scorers ...
Definition: DisjunctionMaxScorer.h:18
Definition: BooleanScorer.h:138
Implement this class to plug into the TermsHash processor, which inverts & stores Tokens into a hash ...
Definition: TermsHashConsumerPerField.h:16
A Scorer for documents matching a Term.
Definition: TermScorer.h:15
Definition: TeeSinkTokenFilter.h:95
An InputStreamReader is a bridge from byte streams to character streams.
Definition: InputStreamReader.h:15
Token literal values and constants.
Definition: QueryParserConstants.h:15
A collection of SegmentInfo objects with methods for operating on those segments in relation to the f...
Definition: SegmentInfos.h:15
Implements search over a set of Searchables.
Definition: MultiSearcher.h:19
A Tokenizer is a TokenStream whose input is a Reader.
Definition: Tokenizer.h:20
Definition: UnicodeUtils.h:89
Definition: PayloadNearQuery.h:52
Matches spans containing a term.
Definition: SpanTermQuery.h:15
An instance of this subclass should be returned by CustomScoreQuery#getCustomScoreProvider, if you want to modify the custom score calculation of a CustomScoreQuery.
Definition: CustomScoreProvider.h:21
Emits the entire input as a single token.
Definition: KeywordTokenizer.h:15
Filters StandardTokenizer with StandardFilter, LowerCaseFilter and StopFilter, using a list of Englis...
Definition: StandardAnalyzer.h:23
Base utility class for implementing a CharFilter. You subclass this, and then record mappings by call...
Definition: BaseCharFilter.h:16
Consumer returns this on each doc. This holds any state that must be flushed synchronized "in docID o...
Definition: DocumentsWriter.h:402
This attribute can be used to pass different flags down the tokenizer chain, eg from one TokenFilter ...
Definition: FlagsAttribute.h:16
Implements the wildcard search query. Supported wildcards are *, which matches any character sequence...
Definition: WildcardQuery.h:21
Definition: IntBlockPool.h:14
Provides support for converting dates to strings and vice-versa. The strings are structured so that l...
Definition: DateTools.h:28
Policy for deletion of stale index commits. Implement this interface, and pass it to one of the Index...
Definition: IndexDeletionPolicy.h:27
A Filter that restricts search results to values that have a matching prefix in a given field...
Definition: PrefixFilter.h:15
An IndexReader which reads multiple, parallel indexes. Each index added must have the same number of ...
Definition: ParallelReader.h:26
Information about a segment such as it's name, directory, and files related to the segment...
Definition: SegmentInfo.h:16
IndexReader is an abstract class, providing an interface for accessing an index. Search of an index i...
Definition: IndexReader.h:39
This is a DocConsumer that gathers all fields under the same name, and calls per-field consumers to p...
Definition: DocFieldProcessor.h:17
This abstract class writes skip lists with multiple levels.
Definition: MultiLevelSkipListWriter.h:36
Implements LockFactory using native file lock.
Definition: NativeFSLockFactory.h:16
A MergePolicy determines the sequence of primitive merge operations to be used for overall merge and ...
Definition: MergePolicy.h:32
Expert: Returned by low-level search implementations.
Definition: ScoreDoc.h:16
TermDocs provides an interface for enumerating ; pairs for a term...
Definition: TermDocs.h:19
Definition: InvertedDocEndConsumerPerField.h:14
Represents hits returned by Searcher#search(QueryPtr, FilterPtr, int32_t, SortPtr).
Definition: TopFieldDocs.h:15
Subclasses of CharFilter can be chained to filter CharStream. They can be used as Reader with additio...
Definition: CharFilter.h:17
Count a scorer as a single match.
Definition: BooleanScorer2.h:105
Query that sets document score as a programmatic function of several (sub) scores: ...
Definition: CustomScoreQuery.h:21
Normalizes token text to lower case.
Definition: LowerCaseFilter.h:15
Definition: TermVectorsWriter.h:14
Definition: UTF8Stream.h:67
A rewrite method that tries to pick the best constant-score rewrite method based on term and document...
Definition: MultiTermQuery.h:135
Abstract base class providing a mechanism to restrict searches to a subset of an index and also maint...
Definition: SpanFilter.h:21
Abstract base class for input from a file in a Directory. A random-access input stream. Used for all Lucene index input operations.
Definition: IndexInput.h:17
Class that Posting and PostingVector use to write byte streams into shared fixed-size byte[] arrays...
Definition: ByteBlockPool.h:23
Position of a term in a document that takes into account the term offset within the phrase...
Definition: PhrasePositions.h:15
Source of values for basic function queries.
Definition: ValueSource.h:21
This TokenFilter provides the ability to set aside attribute states that have already been analyzed...
Definition: TeeSinkTokenFilter.h:62
Writes bytes through to a primary IndexInput, computing checksum as it goes. Note that you cannot use...
Definition: ChecksumIndexInput.h:17
An Analyzer that filters LetterTokenizer with LowerCaseFilter.
Definition: SimpleAnalyzer.h:15
Definition: FreqProxTermsWriterPerThread.h:14
Definition: DirectoryReader.h:225
Obtains byte field values from the FieldCache using getBytes() and makes those values available as ot...
Definition: ByteFieldSource.h:24
Utility class to generate a stream of pseudorandom numbers.
Definition: Random.h:15
This is the current indexing chain: DocConsumer / DocConsumerPerThread –> code: DocFieldProcessor / ...
Definition: DocumentsWriter.h:447
Maintains caches of term values.
Definition: FieldCache.h:17
A Scorer for queries with a required subscorer and an excluding (prohibited) sub DocIdSetIterator. This Scorer implements Scorer#skipTo(int32_t), and it uses the skipTo() on the given scorers.
Definition: ReqExclScorer.h:16
Combines multiple files into a single compound file. The file format: VInt fileCount {Directory} file...
Definition: CompoundFileWriter.h:27
Wraps another SpanFilter's result and caches it. The purpose is to allow filters to simply filter...
Definition: CachingSpanFilter.h:17
Access to the Fieldable Info file that describes document fields and whether or not they are indexed...
Definition: FieldInfos.h:18
The TermVectorOffsetInfo class holds information pertaining to a Term in a TermPositionVector's offse...
Definition: TermVectorOffsetInfo.h:17
A QueryParser which constructs queries to search multiple fields.
Definition: MultiFieldQueryParser.h:16
A Query that sets the scores of document to the values obtained from a ValueSource.
Definition: ValueSourceQuery.h:22
Definition: TermsHashConsumerPerThread.h:14
Transforms the token stream as per the Porter stemming algorithm. Note: the input to the stemming fil...
Definition: PorterStemFilter.h:31
Definition: DocFieldConsumersPerField.h:14
This class converts alphabetic, numeric, and symbolic Unicode characters which are not in the first 1...
Definition: ASCIIFoldingFilter.h:42
A query that scores each document as the value of the numeric input field.
Definition: FieldScoreQuery.h:43
Extends TermFreqVector to provide additional information about positions in which each of the terms i...
Definition: TermPositionVector.h:16
Definition: BooleanScorer.h:103
Definition: HitQueueBase.h:14
Filter caching singleton. It can be used to save filters locally for reuse. Also could be used as a p...
Definition: FilterManager.h:20
Matches spans which are near one another. One can specify slop, the maximum number of intervening unm...
Definition: SpanNearQuery.h:16
Definition: BitSet.h:15
Definition: SegmentTermDocs.h:14
Calculate query weights and build query scorers.
Definition: Weight.h:30
Definition: BooleanScorer.h:85
A Term represents a word from text. This is the unit of search. It is composed of two elements...
Definition: Term.h:20
Status from testing stored fields.
Definition: CheckIndex.h:294
Definition: SegmentReader.h:15
IndexWriter uses an instance implementing this interface to execute the merges selected by a MergePol...
Definition: MergeScheduler.h:16
This class provides a TokenStream for indexing numeric values that can be used by NumericRangeQuery o...
Definition: NumericTokenStream.h:52
Calculates the minimum payload seen.
Definition: MinPayloadFunction.h:15
Status from testing term index.
Definition: CheckIndex.h:253
Definition: SloppyPhraseScorer.h:14
Status from testing field norms.
Definition: CheckIndex.h:237
This class keeps track of each SegmentInfos instance that is still "live", either because it correspo...
Definition: IndexFileDeleter.h:34
A wrapper for MultiTermQuery, that exposes its functionality as a Filter.
Definition: MultiTermQueryWrapperFilter.h:22
A TermInfo is the record of information stored for a term.
Definition: TermInfo.h:15
Tokenizes the entire stream as a single token. This is useful for data like zip codes, ids, and some product names.
Definition: KeywordAnalyzer.h:16
A TokenStream enumerates the sequence of tokens, either from Fields of a Document or from query text...
Definition: TokenStream.h:44
Definition: DocConsumer.h:14
Class responsible for access to stored document fields. It uses .fdt and ...
Definition: FieldsReader.h:16
Implements the skip list writer for the default posting list format that stores positions and payload...
Definition: DefaultSkipListWriter.h:15
Stores term text values and document ordering data.
Definition: FieldCache.h:180
Definition: Field.h:14
An AttributeSource contains a list of different Attributes, and methods to add and get them...
Definition: AttributeSource.h:43
Used by DocumentsWriter to implemented a StringReader that can be reset to a new string; we use this ...
Definition: ReusableStringReader.h:16
The start and end character offset of a Token.
Definition: OffsetAttribute.h:15
Use this LockFactory to disable locking entirely. Only one instance of this lock is created...
Definition: NoLockFactory.h:18

clucene.sourceforge.net