KMP算法——病毒算法

 

 

#include<stdio.h>
#include<stdlib.h>
#include<string.h>
 
//状态码
#define OK 1
#define ERROR 0
#define TRUE 1
#define FALSE 0
#define EQ 0
#define GT 1
#define EQ 0 //相等 
#define GT 1 //大于
#define LT -1 //小于
 
#ifndef _STATUS_H_ //如果系统已经定义下列宏 就不在重复定义
	#define OVERFLOW -2 //堆栈上溢 超过所能表示的最大整数
	#define UNDERFLOW -3 //堆栈下溢 超过所能表示的最小负数
#endif
 
typedef int Status;
 
#define MAX_SIZE 1024
 
/*typedef struct{
	char ch[MAX_SIZE + 1]; //定长方式实现字符串 （浪费空间）
	int length;
}SString;*/
 
//使用指针实现
//串的堆式顺序存储结构（Beap）
typedef struct {
	char * ch; //如果是非空串 按照需要长度分配内存
	int length; //串的当前长度 length代替'\0'的作用
}HString;
 
void InitString_HeapString(HString * str){
	str->ch = NULL;
	str->length = 0;
}
 
void PrintHeapString(HString * str){
	if(str->length == 0 || !str->ch){
		printf("堆字符串为空！\n");
		return ;
	}
	for(int i = 0; i < str->length; i++){
		printf("%c",str->ch[i]);
	}
}
 
//为串赋值 值为字符串首地址chars
Status StrAssign_HeapString(HString * str, char * chars){
	int len = strlen(chars);
	if(!len){
		return ERROR;
	}
	InitString_HeapString(str);
	str->ch = (char *)malloc(len * sizeof(char));
	if(!str->ch){
		exit(OVERFLOW);
	}
	for(int i = 0; i < len; i++){
		str->ch[i] = chars[i];
	}
	str->length = len;
	return OK;
}

/*部分匹配函数的实现*/
void Get_Next(HString child, int * next){
    int i =0;
    int j =-1;
    next[0]= -1;   //不会用到
    while(i< child.length){
       if(j == -1 || child.ch[i] == child.ch[j]){
           ++i;
           ++j;
           next[i] = j;
       }else{
           j = next[j];
        }
    }
}

/*KMP匹配算法*/
int KMPCompare(HString parent, HString child, int pos){
    int next[255];
    Get_Next(child, next);
    int i =pos - 1;
    int j =0;     //j用于子串child中的起始位置
    while(i< parent.length && j < child.length){
       if(j == 0 || parent.ch[i] == child.ch[j]){
           ++i;
           ++j;
       }else{
           j = next[j];    //i不变，j后退
        }
    }
    if(j ==child.length){
       return (i + 1) - j;
    }
    return 0;
}

//检测病毒感染返回1表示感染 返回0表示未感染
int Virus_Check(HString parent , HString child)
{
	//char tempVirus[child.length * 2 + 1]; //预留一个位置给'\0' 这个位置注意不可以直接定义数组 来开辟空间 因为编译时 child.length未赋值导致 无法得到数组大小
	char * tempVirus = (char *)malloc((child.length * 2 + 1) * sizeof(char));
	for(int i = 0 ; i < child.length * 2 ; i++){
		tempVirus[i] = child.ch[i % child.length];
	}
	tempVirus[child.length * 2 ] = '\0';
	for(i = 0 ; i < child.length ; i++){
			char * virus = (char *)malloc((child.length + 1) * sizeof(char));
			for(int j = i ; j < i + child.length ; j++)
			{
				virus[j - i] = tempVirus[j];
			}
			virus[child.length] = '\0';

			//将virus转换为堆串比较
			HString virus_h;
			InitString_HeapString(&virus_h);
			StrAssign_HeapString(&virus_h , virus);
			if(KMPCompare(parent , virus_h , 1) != 0)
				return 1;
	}
	return 0;
}

void main(){
    /*使用KMP算法检测人类是否感染病毒*/
	//人类DNA
	char * person [] = {
		"bbaabbba","aaabbbba","abceaabb","abaabcea","cdabbbab",
			"cabbbbab","bcdedbda","bdedbcda","cdcdcdec","cdccdcce"
	};
	//病毒DNA
	char * virus [] = {
		"baa","bae","aabb","abcd","aacd",
			"abcde","acc","cde","cced","aace"
	};
	
	//保存DNA
	HString persons_h[10];
	HString virus_h [10];
	for(int i = 0 ; i < 10 ; i++)
	{
		InitString_HeapString(&persons_h[i]);
		InitString_HeapString(&virus_h[i]);
		StrAssign_HeapString(&persons_h[i],person[i]);
		StrAssign_HeapString(&virus_h[i],virus[i]);
	}
    
    //检测
	for(i = 0 ; i < 10 ; i++)
	{
		for(int j = 0 ; j < 10 ; j++)
		{
			if(Virus_Check(persons_h[i] , virus_h[j]))
				printf("检测样本DNA：%s\t匹配的病毒：%s\n", person[i] , virus[i]);
		}
	}

}