chinese-journal/rudict/rudict/noun.h

#ifndef NOUN_H_INCLUDED
#define NOUN_H_INCLUDED

#include <string>
#include <map>
#include <set>
#include <vector>
#include <fstream>

#include "boost/algorithm/string.hpp"

#include "grammarCase.h"

namespace NN
{

	struct NounRecord : public TranslationUnitSetMix
	{
		std::wstring nominativeForm;
		NounGender gender;

		bool haveSingleForm;
		bool haveMultipleForm;

		bool haveStandardMultipleForm;
		bool haveStandardMultipleFormWithMissingLastVowel;

		bool haveStandardMultipleFormEnding;
		bool haveAlternativeMultipleFormEnding;

		std::wstring specialMultipleForm;

		bool canBeAnimate;
		bool canBeInanimate;

		std::set<std::wstring> precalculatedNominativePluralSet;

		NounRecord();
		NounRecord(std::wstring line);

		bool operator<(const NounRecord& n) const
		{
			return nominativeForm < n.nominativeForm;
		}
	};

	enum NounDeclencion
	{
		FIRST_A_IFORM_INANIMATE = 0,
		FIRST_A_IFORM_ANIMATE,
		FIRST_A_UFORM_INANIMATE,
		FIRST_A_UFORM_ANIMATE,
		FIRST_YA_FORM_INANIMATE,
		FIRST_YA_FORM_ANIMATE,
		SECOND_MALE_IFORM_INANIMATE,
		SECOND_MALE_IFORM_ANIMATE,
		SECOND_MALE_UFORM_INANIMATE,
		SECOND_MALE_UFORM_ANIMATE,
		SECOND_MALE_SSFORM_INANIMATE,
		SECOND_MALE_SSFORM_ANIMATE,
		SECOND_I_SHORT_INANIMATE,
		SECOND_I_SHORT_ANIMATE,
		SECOND_NEUTRAL_E_FORM,
		SECOND_NEUTRAL_O_FORM,
		THIRD_FORM_INANIMATE,
		THIRD_FORM_ANIMATE,
	};

	extern std::vector<NounRecord> NounRecordArr;



	struct NounDeclencionCaseTableRecord
	{
		NounDeclencion nounDeclencion;
		std::vector<GrammaticalTableRecord> grammaticalCaseTable;
	};

	extern std::vector<NounDeclencionCaseTableRecord> nounDeclencionCaseTable;


	NounDeclencion WStringToNounDeclencion(std::wstring str);

	typedef std::tuple <
		NounDeclencion,
		NounCount,
		NounGrammaticalCase
	> NounTuple;

	typedef std::set<std::wstring> StringSet;

	struct NounEndingDivision
	{
		std::wstring base;
		std::wstring ending;

		enum DivisionCase
		{
			DC_COMMON = 0,
			DC_LOST_VOWEL_O,
			DC_LOST_VOWEL_E
		} divisionCase;

		bool operator<(const NounEndingDivision& other) const
		{
			if (base != other.base)
			{
				return base < other.base;
			}
			else
			{
				if (ending != other.ending)
				{
					return ending < other.ending;
				}
				else
				{
					return divisionCase < other.divisionCase;
				}
			}
		}
	};

	std::vector<std::wstring> GetAllNounEndingArr();


	std::set<std::wstring> getPluralForm(NounRecord nounRecord);

	bool NounIsInDictionary(std::wstring nounNominative);
	bool NounPluralFormIsInDictionary(std::wstring nounNominativePlural);


	NounRecord GetNounRecordFromDictionary(std::wstring nounNominative);
	NounRecord GetNounRecordFromDictionary_ByPluralForm(std::wstring nounNominativePlural);

	bool charIsMissingVowelSoftenerConsolant(wchar_t c);

	struct NounStruct
	{
		NounGrammaticalCase nounGrammaticalCase;
		NounCount nounCount;
		bool animated;
		NounRecord nounRecord;

		bool operator<(const NounStruct& other) const
		{
			if (nounGrammaticalCase != other.nounGrammaticalCase)
			{
				return nounGrammaticalCase < other.nounGrammaticalCase;
			}
			else
			{
				if (nounCount != other.nounCount)
				{
					return nounCount < other.nounCount;
				}
				else
				{
					if (animated != other.animated)
					{
						return animated < other.animated;
					}
					else
					{
						return nounRecord < other.nounRecord;
					}
				}
			}
		}
	};


	std::set<NounEndingDivision> getPossibleNounEndingDivisionSet(std::wstring noun);

	std::vector<NounTuple> GetPossibleNounTupleArr(std::wstring nounEnding);

	std::set<std::wstring> GetNounNoninative(std::wstring nounBase, NounDeclencion nounDeclencion, NounCount nounCount);
	std::wstring GetNounNoninativeSpecialPluralA(std::wstring nounBase, NounDeclencion nounDeclencion);

	wchar_t GetLastChar(const NounRecord& nounRecord);
	wchar_t GetPrevLastChar(const NounRecord& nounRecord);

	void SetupDeclentionMap();

	bool NounFitsDeclention(NounRecord nounRecord, NounTuple nounTuple);

	bool IsDeclencionSecondType(NounDeclencion nounDeclention);
	bool IsDeclencionAnimated(NounDeclencion nounDeclention);

	void FillDivisionCaseMaps();

	std::set<NounStruct> RecognizeNoun(std::wstring noun);

	NounDeclencion CalculateNounDeclention(NounRecord nounRecord);

	void CalculatePluralForm();

	void LoadFrequentWordSet();

	void LoadNounDeclencionCaseTable();


} //namespace NN

#endif //NOUN_H_INCLUDED