74 lines
1.6 KiB
C++
74 lines
1.6 KiB
C++
#ifndef NOUN_H_INCLUDED
|
|
#define NOUN_H_INCLUDED
|
|
|
|
#include <string>
|
|
#include <map>
|
|
#include <set>
|
|
#include <vector>
|
|
#include <fstream>
|
|
#include <codecvt>
|
|
|
|
#include "boost/algorithm/string.hpp"
|
|
|
|
enum NounDeclencion
|
|
{
|
|
ND_1_HARD, // Ïàïà (ïàïû)
|
|
ND_1_SOFT, // Äîñêà (äîñêè)
|
|
ND_2_HARD_MALE, // Òðàêòîð (òðàêòîðû)
|
|
ND_2_SOFT_MALE, // Òîïîëü (òîïîëè)
|
|
ND_2_NEUTER_O, // Áðåâíî (áð¸âíà)
|
|
ND_2_NEUTER_E, // Ïîëå (ïîëÿ)
|
|
ND_3 // Ëîøàäü
|
|
};
|
|
|
|
enum NounGrammaticalCase
|
|
{
|
|
NGC_P1_NOMINATIVE,
|
|
NGC_P2_GENITIVE,
|
|
NGC_P3_DATIVE,
|
|
NGC_P4_ACCUSATIVE,
|
|
NGC_P5_INSTRUMENTAL,
|
|
NGC_P6_PREPOSITIONAL
|
|
};
|
|
|
|
enum NounNumber
|
|
{
|
|
NPF_SINGULAR,
|
|
NPF_PLURAL
|
|
};
|
|
|
|
typedef std::tuple<NounDeclencion, NounGrammaticalCase, NounNumber> NounTuple;
|
|
|
|
std::vector<std::wstring> GetAllNounEndingArr();
|
|
std::map<NounTuple, std::wstring> getNounEndingTable();
|
|
|
|
bool NounIsInDictionary(std::wstring nounNominative);
|
|
|
|
std::set<NounDeclencion> GetPossibleNounDeclencionSet(std::wstring nounNominative);
|
|
|
|
bool charIsConsolant(wchar_t c);
|
|
|
|
bool charIsVowel(wchar_t c);
|
|
|
|
|
|
struct NounStruct
|
|
{
|
|
NounTuple nounTuple;
|
|
std::wstring noun;
|
|
};
|
|
|
|
|
|
std::vector<std::pair<std::wstring, std::wstring>> getPossibleNounEndingDivisionArr(std::wstring noun);
|
|
|
|
std::vector<NounTuple> GetPossibleNounTupleArr(std::wstring nounEnding);
|
|
|
|
//std::vector<NounTuple> FilterNounTupleArrByNounDeclentionSet(std::vector<NounTuple> nounTupleArr, std::set<NounDeclencion> filter);
|
|
|
|
std::wstring RestoreNounByTuple(std::wstring nounBase, NounTuple nounTuple);
|
|
|
|
std::vector<NounStruct> RecognizeNoun(std::wstring noun);
|
|
|
|
void LoadFrequentWordSet();
|
|
|
|
#endif //NOUN_H_INCLUDED
|