IndexSet.h

Go to the documentation of this file.

//*-*- Mode: C++ -*-*/

//  DDC originally by Alexey Sokirko
//  Changes and modifications 2011-2018 by Bryan Jurish
//
//  This file is part of DDC.
// 
//  DDC is free software: you can redistribute it and/or modify
//  it under the terms of the GNU Lesser General Public License as published by
//  the Free Software Foundation, either version 3 of the License, or
//  (at your option) any later version.
// 
//  DDC is distributed in the hope that it will be useful,
//  but WITHOUT ANY WARRANTY; without even the implied warranty of
//  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
//  GNU Lesser General Public License for more details.
// 
//  You should have received a copy of the GNU Lesser General Public License
//  along with DDC.  If not, see <http://www.gnu.org/licenses/>.
//

#ifndef  IndexSet_h
#define  IndexSet_h

#include "../ConcordLib/IndexSetForLoadingStage.h"
#include "../ConcordLib/IndexSetForQueryingStage.h"
#include "../PCRE/pcre_rml.h"

struct COutputToken {
    string m_TokenStr;
    string m_InterpStr;
    BYTE m_Highlight;

    COutputToken() : m_Highlight(0) {};

    COutputToken(string WordStr, BYTE Highlight) : m_TokenStr(WordStr), m_Highlight(Highlight) {};

    bool operator==(const COutputToken &X) const {
        return m_TokenStr == X.m_TokenStr;
    };
};


class CStringIndexator;


class CStringIndexSet : public CIndexSetForLoadingStage, public CIndexSetForQueryingStage {
    ddcFileOrMMap m_StorageFile;


    bool ConvertLoadIndexToWorkingIndex();


    void CreateUnionTokenStorages(const vector<CStringIndexSet *> &IndexSets, const vector<size_t> &TokenCounts,
                                  const vector<vector<DWORD> > &xlateItemId);

    void OpenStorageFile();


    string GetName() const;

    bool ConvertTempStorageToPersistent();

public:

    string m_Name;

    string m_ShortName;

    template<class T>
    inline const char *GetIndexItemStr(const T &W) const {
        return m_StringBuffer.m_data + W.GetIndexItemOffset();
    };

    CStringIndexSet(const CStringIndexator *pParent);

    ~CStringIndexSet();

    string GetStorageFileName() const;

    void CloseStorageFile();

    void InitIndexSet(string Name, string ShortName, bool bCreateItemStorage, bool bCompress);

    void ReadFromTheDisk();

    bool DestroyIndexSet();

    bool WriteToFile(bool bAfterLoading);

    void UnionIndexSets(const vector<CStringIndexSet *> &IndexSets, const vector<size_t> &TokenCounts);

    void CreateSplitPartitions(vector<CStringIndexSet *> &Partitions, const vector<CTokenNo> &EndTokenNo) const;

    void EnsureSuffixIndex();

    bool GetTokensFromStorage(const size_t start_offset, const size_t end_offset, vector<COutputToken> &Tokens) const;

    DWORD GetTokenIndexId(CTokenNo TokenNo) const;

    ddcVecFile<CIndexItem>::const_iterator GetTypeIndexIdLowerBoundIter(const string &ValueStr) const;

    ddcVecFile<CIndexItem>::const_iterator GetTypeIndexIdUpperBoundIter(const string &ValueStr) const;

    DWORD GetTypeIndexIdLowerBound(const string &ValueStr) const;

    DWORD GetTypeIndexId(const string &ValueStr) const;

    bool GetContextBounds(CDDCFilterWithBounds &Filter, const string &LoValue, const string &HiValue) const;

    void FindOccurrences(const vector<DWORD> &IndexItems, const size_t PeriodNo, vector<CTokenNo> &occurrences,
                         CShortOccurCacheMap *pCaches, vector<int> &CacheIds) const;

    void
    FindChunkOccurrences(const vector<DWORD> &IndexItems, vector<CTokenNo> &occurrences, vector<DWORD> &ChunkLengths,
                         size_t PeriodNo, CShortOccurCacheMap *pCaches, vector<int> &CacheIds) const;

    void QueryTokenList(const string &WordForm, vector<DWORD> &MatchWords) const;

    void QueryTokenListWithRightTruncation(const string &Prefix, vector<DWORD> &MatchWords) const;

    void QueryTokenListWithLeftTruncation(const string &Suffix, vector<DWORD> &MatchWords) const;

    void QueryTokenListUsingRegExp(RML_RE &RegExp, vector<DWORD> &MatchWords, bool negated = false,
                                   bool ignore_diacritics = false) const;

    void QueryTokenListUniversal(vector<DWORD> &MatchWords) const;

    void DumpStorage(FILE *output) const;
};


#endif

/*--- emacs style variables ---
 * Local Variables:
 *  mode: C++
 *  c-file-style: "ellemtel"
 *  c-basic-offset: 4
 *  tab-width: 8
 *  indent-tabs-mode: nil
 * End:
 */