Hash算法

Hash去除重复字符串：

#include <iostream>
#include <windows.h>
#include <random>
#include <time.h>
using namespace std;    

#define MAX 10000
#define MOD 9991

char * Hash[MAX][20];
int len[MAX];

int _hash(char *str){
	register int hash=0;
	while(int ch=(int)*str++){
		//hash=hash*31+ch;
		hash=hash<<7+hash<<1+hash+ch;
		hash%=MOD;
	}
	return hash%MOD;
}

void Test()//测试程序
{
	//freopen("C:\\in.txt","r",stdin);
	FILE *fp1=fopen("C:\\a.txt","r");
	FILE *fp2=fopen("C:\\b.txt","w");
	char str[20];
	memset(len,0,sizeof(len));
	while(~fscanf(fp1,"%s",str)){
		int pos=_hash(str);
		bool flag=false;
		for(int i=0;i<len[pos];i++){
			if(strcmp(str,Hash[pos][i])==0){
				flag=true;
				break;
			}
		}
		if(!flag){
			Hash[pos][len[pos]]=new char[20];
			int i=0;
			while(str[i]!=‘\0‘){
				Hash[pos][len[pos]][i]=str[i];
				i++;
			}
			Hash[pos][len[pos]++][i]=‘\0‘;
			fprintf(fp2,"%s ",str);
		}
	}
	fclose(fp1);
	fclose(fp2);
}
     
int main(void)    
{    
    LARGE_INTEGER BegainTime ;    
    LARGE_INTEGER EndTime ;    
    LARGE_INTEGER Frequency ;    
    QueryPerformanceFrequency(&Frequency);    
    QueryPerformanceCounter(&BegainTime) ;    
    
    //要测试的代码放在这里   
    Test();   
     
    QueryPerformanceCounter(&EndTime);   
    
    //输出运行时间（单位：s）   
    cout << "运行时间（单位：s）：" <<(double)( EndTime.QuadPart - BegainTime.QuadPart )/ Frequency.QuadPart <<endl;    
    
    //system("pause") ;    
    return 0 ;    
}

Hash算法

原文：http://blog.csdn.net/starcuan/article/details/19034185