6.编写正排索引切分字符串|倒排索引原理|引入jieba到项目(C++)

编写正排索引

继续编写incde.hpp

#pragma once

#include <iostream>
#include <string>
#include <vector>
#include <fstream>
#include <unordered_map>
#include "util.hpp"

namespace ns_index{

	struct DocInfo{
		std::string title;   //文档标题
		std::string content; //文档对应的去标签之后的内容
		std::string url;     //官网文档url
		uint64_t dic_id;     //文档的ID
	}

	struct InvertedElem{
		uint64_t doc_id;
		std::string word;
		int weight;
	}

	//倒排拉链
	typedef std::vector<InvertedElem> InvertedList;

	class Index{
		private:
			//正排索引的数据结构用数组，数组的下标天然是文档的ID
			std::vector<DocInfo> forward_index; //正排索引
			//倒排索引一定是一个关键字和一组(个)InvertedElem对应[关键字和倒排拉链的映射关系]
			std::unordered_map<std::string, InvertedList> inverted_index;
		public:
			Index(){}
			~Index(){}
		public:
			//根据doc_id找到文档内容
			DocInfo *GetForwardIdex(uint64_t doc_id)
			{
				if(doc_id >= forward_index.size()){
						std::cerr << "doc_id out range, error" << std::endl;
						return nullptr;
				}
				return &forward_index[doc_id];
			}

			//根据关键字string获得倒排拉链
			InvertedList *GetInvertedList(const std::string &word)
			{
				auto iter = inverted_index.find(word);
				if(iter == inverted_index.end()){
						std::cerr << word << " have no InvertedList" << std::endl;
						return nullptr;
				}

				return &(iter->second);
			}
			//根据去标签，格式化之后的文档，构建正排和倒排索引
			//data/raw_html/raw.txt
			bool BuildIndex(const std::string &input) //parse处理完毕的数据交给我
			{
				std::ifstream in(input, std::ios::in | std::ios::binary);
				if(!in.is_open()){
					std::cerr << "sorry, " << input << " open error" << std::endl;
					return false;
				}

				std::string line;
				while(std::getline(in, line)){
					DocInfo * doc = BuildForwardIndex(line);
					if(nullptr == doc){
							std::cerr << "build " << line << " error" << std::endl; //for debug
							continue;
					}

					BuildInvertedIndex(*doc);
				}
				return true;
			}
		private:
			DocInfo *BuildForwardIndex(const std