c++ fstream + string 处理大数据

 //读取方式: 逐词读取, 词之间用空格区分(遇到空格认为本次读取结束)，输出之后进行下一次读取 
 //read data from the file, Word By Word 
 //when used in this manner, we'll get space-delimited bits of text from the file 
 //but all of the whitespace that separated words (including newlines) was lost. 
void ReadDataFromFileWBW()  
{  
    ifstream fin("data.txt");  
    string s;  
    cout << "*****start*******" << endl;  
 while( fin >> s )  
    {  
          cout << "Read from file: " << s << endl;  
    }  
    cout << "*****over*******" << endl;  
}  

 //读取方式: 逐行读取, 将行读入字符数组, 行之间用回车换行区分 
 //If we were interested in preserving whitespace, 
 //we could read the file in Line-By-Line using the I/O getline() function. 
void ReadDataFromFileLBLIntoCharArray()  
{  
    ifstream fin("data.txt",ios::in);// 默认的打开模式就是ios::in 
    ofstream fout("out.txt",ios::out);// 默认代开模式就是ios::out 
 const int LINE_LENGTH = 100;  
 char str[LINE_LENGTH];  
    fout << "****CharArray start******" << endl;  
    cout << "****CharArray start******" << endl;  
    fin.seekg(-20,ios::end);// -20表示从end向前移动20字节，汉字占两字节；20表示向后移动指针 
 while( fin.getline(str,LINE_LENGTH) )  
    {  
        fout << str << endl;  
        cout << "Read from file: " << str << "..." << endl;// ****str里面本身包含着换行的，原来是什么样子，现在保存的就是什么样子 
    }  
    fout << "*****over*******" << endl;  
    cout << "*****over*******" << endl;  
}  

 //读取方式: 逐行读取, 将行读入字符串, 行之间用回车换行区分 
 //If you want to avoid reading into character arrays, 
 //you can use the C++ string getline() function to read lines into strings 
void ReadDataFromFileLBLIntoString()  
{  
    ifstream fin("data.txt",ios::in);// 默认的打开模式就是ios::in 
    ofstream fout("out.txt",ios::app);// 追加到文件尾的方式打开 
    string s;  
    cout << "****start******" << endl;  
 while( getline(fin,s) )  
    {  
        fout << s << endl;// ofstream是默认，若文件不存在，则先建立此文件，并且再向文件写的过程中换行已经不存在了，这与cout控制台输出一样哦。。。 
        cout << "Read from file: " << s << endl;//****s同str里面本身已经没有了换行的，这和原来的getline()函数是一样的；数据原来是什么样子，现在保存的就是什么样子 
    }  
    fout << "*****over*******" << endl;  
    cout << "*****over*******" << endl;  
    fout.close();  
}  

#include <iostream> 
#include <fstream> 
#include <string> 
#include <cstdlib>// exit()函数 
using namespace std;  
 //输出空行 
void OutPutAnEmptyLine()  
{  
      cout<<"\n";  
}  
 //带错误检测的读取方式 
 //Simply evaluating an I/O object in a boolean context will return false 
 //if any errors have occurred 
void ReadDataWithErrChecking()  
{  
    string filename = "dataFUNNY.txt";  
    ifstream fin( filename.c_str());  
 if( !fin )  
    {  
          cout << "Error opening " << filename << " for input" << endl;  
          exit(-1);  
    }  
}  
int main()  
{  
      ReadDataFromFileWBW(); //逐词读入字符串 
      OutPutAnEmptyLine(); //输出空行 
      ReadDataFromFileLBLIntoCharArray(); //逐词读入字符数组 
      OutPutAnEmptyLine(); //输出空行 
      ReadDataFromFileLBLIntoString(); //逐词读入字符串 
      OutPutAnEmptyLine(); //输出空行 
      ReadDataWithErrChecking(); //带检测的读取 
 return 0;  
}  

#include <iostream>  
#include <fstream> 
#include <cassert> 
#include <ctime> 
#include <cstdio> 
using namespace std;</p><p>void test_read()  
{  
 const char* read_file = "D:\\zyp\\大数据实验<a target=_blank href="file://\\TOKEN_ENEX_201404_20W_yuansi.csv">\\TOKEN_ENEX_201404_20W_yuansi.csv</a>"; 
 const int BUF_SIZE = 1024 ;  
 char buf[BUF_SIZE];  
 //c++ style writing file 
  ifstream ifs(read_file,ios::binary);  
  assert(ifs);  
 time_t start, end;  
  start =  clock();  
 while(!ifs.eof())  
  {  
    ifs.read(buf,BUF_SIZE);  
  }  
  end = clock();  
  ifs.close();  
  cout<<"C++ style: "<<end - start <<" ms"<<endl;  
 //c style writing file 
 FILE* fp = fopen(read_file, "rb");  
  start =  clock();  
 int len = 0;  
 char *pline = NULL;  
 do 
  {  
 //len = fread(buf,1,BUF_SIZE,fp); 
      pline = fgets(buf,BUF_SIZE,fp);  
      cout << buf << endl;  
 //cout<<len<<endl; 
  }while(pline != NULL);  
  end = clock();  
  fclose(fp);  
  cout<<"C style: "<<end - start <<" ms"<<endl;  
  cin.get();  
}  
int main()  
{  
    test_read();  
 return 0;  
}</p>总之，/fread() 的效率 是 ifstream.read()的将近十倍！但是，fstream 对于处理数据而言，还是统一的应用STL的标准好；总之，语言仅仅是一门工具，本身没有优劣之分。fgets(char*,int,File*); getline(stream,string)，还是个人习惯的好。如今，还是建议应用面向对象的语言好一些，java 或者 c++，java更加强大一些，有自己的各种类库。c++没有的，链接JDBC的东东的