#pragma once
#include<iostream>
#include<string>
#include <unordered_map>
#include<fstream>
#include <boost/algorithm/string.hpp>
#include <mutex>
#include "ccjieba/Jieba.hpp"
#include "log.hpp"

namespace ns_util{
    class FileUtil{
        public:
            static bool ReadFile(const std::string &file_path,std::string *out)
            {
                //输入流
                std::ifstream in(file_path,std::ios::in/*表示读取*/);
                if(!in.is_open()){
                    std::cerr<<"open file "<<file_path<<" error"<<std::endl;
                    return false;
                }
                std::string line;
                while(std::getline(in,line)){
                    *out+=line;
                    //如何理解getline读取到文件结束呢？？
                    //getline的返回值是一个&，while(bool), 本质是因为重载了强制类型转化。
                    //就是返回特定的引用对象当中
                    //即while判断这个对象结果是否合理的时候，
                    //对象的内容重载了强制类型转化，变成了bool值。
                }
                in.close();
                return true;
            }
    };

    class StringUtil{
        public:
            static void Split(const std::string &target,std::vector<std::string> *out,const std::string &sep)
            { 
                //boost split
                boost::split(*out, target, boost::is_any_of(sep), boost::token_compress_on);
                //第一个参数就是切分的结果，第二个是数据源，第三个是分隔符，第四个是分隔符和分隔符之间是否需要压
                //缩（比如：aaa/3vv/3nn/3/3/3/3gggg/3）（boost::token_compress_on（默认是off）就是要不要
                //把中间的\3压缩为一个就是这个意思，如果不加，就会有很多空的数据）
            }
    };

    const char* const DICT_PATH = "./dict/jieba.dict.utf8";
    const char* const HMM_PATH = "./dict/hmm_model.utf8";
    const char* const USER_DICT_PATH = "./dict/user.dict.utf8";
    const char* const IDF_PATH = "./dict/idf.utf8";
    const char* const STOP_WORD_PATH = "./dict/stop_words.utf8";

    class JiebaUtil{
        private:
            //static cppjieba::Jieba jieba;
            cppjieba::Jieba jieba;
            std::unordered_map<std::string,bool> stop_words;
        private:
            JiebaUtil():jieba(DICT_PATH, HMM_PATH, USER_DICT_PATH, IDF_PATH, STOP_WORD_PATH)
            {}
            JiebaUtil(const JiebaUtil&) = delete;

            static JiebaUtil *instance;
        public:
            static JiebaUtil* get_instance()
            {
                static std::mutex mtx;
                if(nullptr == instance){
                    mtx.lock();
                    if(nullptr == instance){
                        instance = new JiebaUtil();
                        instance->InitJiebaUtil();
                    }
                    mtx.unlock();
                }

                return instance;
            }
            //把暂停词加载进来
            void InitJiebaUtil()
            {
                std::ifstream in(STOP_WORD_PATH);
                if(!in.is_open()){
                    LOG(FATAL, "load stop words file error");
                    return;
                }

                std::string line;
                while(std::getline(in, line)){
                    stop_words.insert({line, true});
                }

                in.close();
            }

            void CutStringHelper(const std::string &src, std::vector<std::string> *out)
            {
                jieba.CutForSearch(src, *out);
                for(auto iter = out->begin(); iter != out->end(); ){
                    auto it = stop_words.find(*iter);
                    if(it != stop_words.end()){
                        //说明当前的string 是暂停词，需要去掉
                        iter = out->erase(iter);
                    }
                    else{
                        iter++;
                    }
                }
            }
        public:
            static void CutString(const std::string &src,std::vector<std::string> *out)
            {
                ns_util::JiebaUtil::get_instance()->CutStringHelper(src, out);
                //jieba.CutForSearch(src,*out);
            }
    };
    JiebaUtil *JiebaUtil::instance = nullptr;
    //cppjieba::Jieba JiebaUtil::jieba(DICT_PATH, HMM_PATH, USER_DICT_PATH, IDF_PATH, STOP_WORD_PATH);//静态成员在类外定义
}