字符串匹配算法

字符串暴力匹配算法

算法步骤：用i指向原文本，j指向待匹配字符串。匹配时i,j下标递增，不匹配时待匹配字符串下标j置零，并使用待匹配字符串第0号元素循环匹配此时失配的文本字符直到匹配。

#include<stdio.h>
#include<stdlib.h>
#include<string.h>

void searchString(char* text,char* mystring){

	int i = 0;
	int j = 0;
	int mystring_len = strlen(mystring);
	int text_len = strlen(text);
	int len = text_len;
	/*printf("mystring_len is %d,text_len is %d\n",mystring_len,text_len);*/
	while(len > 0){

	if(text[i] == mystring[j]){

		i++;j++;len--;
		/*printf("i is %d,j is %d\n",i,j);*/
		if(j == mystring_len){

		printf("i = %d,mystring_len = %d,matched at %d\n",i,mystring_len,i-mystring_len);

	}

	}else if(text[i] != mystring[j] && i < text_len){

		j=0;
		while(mystring[0] != text[i]){
 			i++;len--;
		}

	}
	}

}





int main(){

	char* mystring = "ABABABCBACBA";
	char* text     = "ABAABAABASscscacsaABABABCBACBASCASFFSAFAFWDAABABABCBACBA";

	searchString(text,mystring);

	return 0;
}

i = 30,mystring_len = 12,matched at 18
i = 56,mystring_len = 12,matched at 44

效率分析：每次失配文本字符都需要和待匹配字符串首个字符元素进行对比，整体来看整个程序所有的文本字符都需要被比较一次，时间复杂度为O(n)，n为文本字符的长度。

KMP字符串匹配算法

#include<stdio.h>
#include<string.h>
#include<stdlib.h>

void prefix_table(char pattern[], int prefix[], int n){        //构建最大前后缀匹配表
	prefix[0] = 0;
	int len   = 0;              // The most match
	int i     = 1;
	while( i < n ) {
		if( pattern[i] == pattern[len] ){
			len++;
			prefix[i] = len;
			i++;
		} else {
			
			if(len > 0){

				len = prefix[len - 1];
		
			} else {

				prefix[i] = len;
				i++;

			}
			
		}
	}

}


void move_prefix_table(int prefix[], int n){  //移动前后缀最大匹配表
	
	int i;
	for (i = n; i > 0; i--){

		prefix[i] = prefix[i-1];

	}
	prefix[0] = -1;

}

void kmp_search(char text[],char pattern[]){  //kmp搜索函数

	int n = strlen(pattern);
	int m = strlen(text);
	int* prefix = malloc(sizeof(int) * n);
	prefix_table(pattern,prefix,n);
	move_prefix_table(prefix,n);

	int i = 0;
	int j = 0;

	while(i < m){
		if(j == n-1 && text[i] == pattern[j]){

			printf("Found pattern at %d\n",i-j+1);
			j = prefix[j];
		}
		if(text[i] == pattern[j]){

			i++;	j++;
		}else{
			j = prefix[j];
			if(j == -1){

				i++;	j++;
			}
		}


	}

}

int main(){
	
	char pattern[] = "ABABCABAA";
	char text[] = "ABABAABABCABAABABAC";

	kmp_search(text,pattern);
	/*
	int prefix[9];
	int n = 9;


	prefix_table(pattern,prefix,n);
	move_prefix_table(prefix,n);
	int i;
	for (i=0;i<n;i++){
		printf("%d\n",prefix[i]);
	}
	*/


	return 0;
}