#pragma once

#include<mutex>
#include <iostream>
#include <string>
#include <vector>
#include <unordered_map>
#include <fstream>
#include "tool.hpp"
#include "log.hpp"
using namespace std;



namespace project_index
{
    typedef struct format
    {
        string title;
        string url;
        string content;
        uint64_t docid;//文档id

    }Format;
    
    typedef struct Inverted_zipper//倒排拉链
    {
        uint64_t docid;//文档id
        string keyword;//关键词
        int weight;//权重
        Inverted_zipper()
            :weight(0){}
    }Inverted_zipper;

    class index
    {
      private:
        vector<Format> Front_index;//正排索引 下标模拟文档id

        unordered_map<string,vector<Inverted_zipper>> inverted_index;//倒排 关键词与多个(一个)倒排拉链的对应

        static index * Index;
        static mutex mtx; 
        index(const index &)=delete;
        index& operator=(const index&)=delete;

        index()
        {}
      public:
        ~index()
        {}
   static index* GetIndex()
   {
     if(nullptr == Index)
     {
        mtx.lock();
        if(nullptr == Index){
            Index = new index();
        }
        mtx.unlock();
    }
        return Index;

   }
    //id获得文档内容
    Format* GetFront_index(uint64_t docid)
    {
        if(docid>=Front_index.size())
        {
            LOG(Warning,"docid>=Front_index.size");
            return nullptr;
        }

        return &Front_index[docid];
    }

    //关键词获得倒排拉链
    vector<Inverted_zipper>* Getinverted_index(const string &keyword)
    {
        auto it = inverted_index.find(keyword);
        if(it == inverted_index.end())
        {
            LOG(Warning,"keyword find Warning");
            return nullptr;
        }
        
        return &(it->second);
    }

    //建立索引 数据源:parser处理完的数据
    bool Establish_index(const string &raw)
    {
        ifstream in(raw,ios::in | ios::binary);
        if(!in.is_open())
        {
            LOG(Warning,"in.is_open Warning");
            return false;
        }

        string temp;
        int count =0;
        while(getline(in,temp))
        {
            Format* doc = Establish_Front_index(temp);//建立正排索引
            if(doc == nullptr)
            {
                LOG(Warning,"Establish_Front_index warning");
                continue;
            }
            /*if(doc->docid == 5008)
            {
                cout << "建立5008倒排索引" << endl;
            }*/
            bool flag = Establish_inverted_index(*doc);//建立倒排索引
            count++;
            LOG(Info,"当前已经建立索引的文档 :" + to_string(count));
        }
        return true;
    }   

    private:
        Format* Establish_Front_index(string &temp)
        {
            //切分temp
            vector<string> result;
            string sep = "\3";

            bool flag = project_tool::stringtool::Slice_strings(temp,&result,sep);
            if(!flag)
            {
                LOG(Warning,"Slice_strings WARNING");
                return nullptr;
            }
            //切分好后放到Format

            Format doc;
            if(result.size() != 3)
            {
                LOG(Warning,"Slice_strings WARNING");
                return nullptr;
            }
            doc.title = result[0];
            doc.content = result[1];
            doc.url = result[2];
            //doc.docid = result.size(); //id为vector下标
            doc.docid = Front_index.size();

            //结果插入正排索引
            Front_index.push_back(move(doc));//move性能优化
            return &Front_index.back();
        }

        bool Establish_inverted_index(Format &doc)//建立倒排
        {
            struct word_count
            {
              int title_count;
              int content_count;
              word_count():title_count(0),content_count(0){}
            };

            vector<string> title_result;
            project_tool::jiebatool::CutString(doc.title,&title_result);
  
            unordered_map<string,word_count> word_map;

            for(string &s:title_result)
            {
                boost::to_lower(s);
                word_map[s].title_count++;
            }
            vector<string> content_result;

            project_tool::jiebatool::CutString(doc.content,&content_result);
            for(string & s : content_result)
            {
                boost::to_lower(s);
                word_map[s].content_count++;
            }

const int title_corr = 10;

            for(auto &iter : word_map)
            {
                Inverted_zipper temp;

                temp.docid = doc.docid;
                temp.keyword = iter.first;
                temp.weight = title_corr * (iter.second.title_count)+ iter.second.content_count;
                vector<Inverted_zipper> &vector_temp = inverted_index[iter.first];

                vector_temp.push_back(move(temp));

            }

            return true;
        }

    

    };
    index * index::Index = nullptr;
    mutex index::mtx;
}