|
Public Member Functions |
| MemoryIndex () |
| MemoryIndex (lemur::api::DOCID_T docBase) |
| MemoryIndex (lemur::api::DOCID_T docBase, const std::vector< Index::FieldDescription > &fields) |
| ~MemoryIndex () |
void | close () |
lemur::api::DOCID_T | documentBase () |
lemur::api::DOCID_T | documentMaximum () |
| The documentMaximum is at least one greater than the largest documentID used in this index.
|
lemur::api::TERMID_T | term (const std::string &t) |
lemur::api::TERMID_T | term (const char *t) |
std::string | term (lemur::api::TERMID_T termID) |
int | field (const char *fieldName) |
int | field (const std::string &fieldName) |
std::string | field (int fieldID) |
int | documentLength (lemur::api::DOCID_T documentID) |
UINT64 | documentCount () |
UINT64 | documentCount (const std::string &term) |
UINT64 | uniqueTermCount () |
UINT64 | termCount (const std::string &term) |
UINT64 | termCount () |
UINT64 | fieldTermCount (const std::string &field) |
UINT64 | fieldTermCount (const std::string &field, const std::string &term) |
UINT64 | fieldDocumentCount (const std::string &field) |
UINT64 | fieldDocumentCount (const std::string &field, const std::string &term) |
DocListIterator * | docListIterator (lemur::api::TERMID_T termID) |
DocListIterator * | docListIterator (const std::string &term) |
DocListFileIterator * | docListFileIterator () |
DocExtentListIterator * | fieldListIterator (int fieldID) |
DocExtentListIterator * | fieldListIterator (const std::string &field) |
const TermList * | termList (lemur::api::DOCID_T documentID) |
TermListFileIterator * | termListFileIterator () |
VocabularyIterator * | vocabularyIterator () |
VocabularyIterator * | frequentVocabularyIterator () |
VocabularyIterator * | infrequentVocabularyIterator () |
DocumentDataIterator * | documentDataIterator () |
indri::thread::Lockable * | iteratorLock () |
indri::thread::Lockable * | statisticsLock () |
lemur::api::DOCID_T | addDocument (indri::api::ParsedDocument &document) |
size_t | memorySize () |
Private Member Functions |
void | _addOpenTags (indri::utility::greedy_vector< indri::parse::TagExtent * > &indexedTags, indri::utility::greedy_vector< indri::parse::TagExtent * > &openTags, indri::utility::greedy_vector< indri::parse::TagExtent * > &extents, unsigned int &extentIndex, unsigned int position) |
void | _removeClosedTags (indri::utility::greedy_vector< indri::parse::TagExtent * > &tags, unsigned int position) |
void | _writeFieldExtents (lemur::api::DOCID_T documentID, indri::utility::greedy_vector< indri::parse::TagExtent * > &indexedTags) |
void | _writeDocumentTermList (UINT64 &offset, int &byteLength, lemur::api::DOCID_T documentID, int documentLength, indri::index::TermList &locatedTerms) |
void | _writeDocumentStatistics (UINT64 offset, int byteLength, int indexedLength, int totalLength, int uniqueTerms) |
term_entry * | _lookupTerm (const char *term) |
void | _destroyTerms () |
int | _fieldID (const std::string &fieldName) |
int | _fieldID (const char *fieldName) |
Private Attributes |
indri::utility::RegionAllocator | _allocator |
indri::thread::ReadersWritersLock | _lock |
indri::thread::ReaderLockable | _readLock |
indri::thread::WriterLockable | _writeLock |
CorpusStatistics | _corpusStatistics |
lemur::api::DOCID_T | _baseDocumentID |
indri::index::TermList | _termList |
indri::utility::greedy_vector<
term_entry * > | _seenTerms |
indri::utility::HashTable<
const char *, term_entry * > | _stringToTerm |
std::vector< term_entry * > | _idToTerm |
indri::utility::HashTable<
const char *, int > | _fieldLookup |
std::vector< FieldStatistics > | _fieldData |
std::vector< indri::index::DocExtentListMemoryBuilder * > | _fieldLists |
std::vector< indri::index::DocumentData > | _documentData |
std::list< indri::utility::Buffer * > | _termLists |
UINT64 | _termListsBaseOffset |