C++ 搜索引擎通用工具模块：文件读取与中文分词实现

完整头文件实现

以下是整合后的 ns_util 命名空间代码，包含文件读取、字符串分割及分词功能，可直接引入项目使用。

#pragma once
#include<iostream>
#include<string>
#include<fstream>
#include<boost/algorithm/string.hpp>
#include"cppjieba/Jieba.hpp"

namespace ns_util{
    class FileUtil{
    public:
        static bool ReadFile(const std::string &file_path,std::string *out) {
            std::ifstream in(file_path,std::ios::in | std::ios::binary);
            if(!in.is_open()){
                std::cout<<"open file "<<file_path<<": error"<<std::endl;
                return false;
            }
            std::string line;
            while(std::getline(in,line)) *out+=line;
            in.close();
            return true;
        }
    };

    class StringUtil{
    public:
        // target 是要切分的目标，out 是结果容器，sep 是分隔符（\3）
        static void Split(const std::string& target,std::vector<std::string>* out,std::string sep) {
            boost::split(*out,target,boost::is_any_of(sep),boost::token_compress_on);
        }
    };

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

    class JiebaUsutl{
    private:
        static cppjieba::Jieba jieba;
    public:
        static void CutString(const std::string& src,std::vector<std::string>* out) {
            jieba.CutForSearch(src,*out);
        }
    };
    
    cppjieba::Jieba JiebaUsutl::jieba(DICT_PATH,HMM_PATH,USER_DICT_PATH,IDF_PATH,STOP_WORD_PATH);
};