irmodel.h

来自「一个信息检索模型」· C头文件 代码 · 共 41 行

#include <iostream>
#include <string>
#include <fstream>

#include <vector>
#include <map>
#include <set>
using namespace std;

class IRModel
{
public:
	IRModel(){};
	~IRModel(){};

	typedef map<short, string> Sequence_Doc;          //<file sequence, file path>
	typedef vector<short> Locs;	         // lexicon sequence in the file
	typedef pair<short, Locs> TF_Locs;  
    typedef map<short, TF_Locs> Doc_locs; //<file sequence, locations>
	
	typedef vector<Doc_locs> IndexTermLocs;
	typedef pair<short,IndexTermLocs> IDF_IndexTerm;   //<DF, indexTerm>
	typedef map<string, IDF_IndexTerm> Index;

	typedef map<short, string>::value_type valT_Seq_Doc;
	typedef map<short, TF_Locs>::value_type ValT_Doc_locs;	
	typedef map<string,IDF_IndexTerm>::value_type ValT_Word_IndexTerm;
 
	string WordSegment(string fFileList);
	void EstablishIndex(string WSFileList);
	void index_line(string line, int wordSequence);
	void initStopWordSet();
	void deleteStopWords();
	void displayIndex();
	//int query_document_similarity(string query, short documentSequence);
private:
	Index invertedIndex;
	Sequence_Doc sequence_doc;
	set<string> stopWord_set; // 停用词集合
	static int docSequence;
};