算法练习-KMP

字符串匹配算法(KMP)

构造前缀表

首先对子串构造前缀表

// 求每个前缀的最长公共前后缀
void prefix_table(char pattern[], int prefix[], int n)
{
	prefix[0] = 0;
	int len = 0, i = 1;

	while (i < n) {
		// 如果相等则公共前后缀长度加1
		if (pattern[len] == pattern[i]) {
			len++;
			prefix[i] = len; 
			i++;
		}
		else {
			if (len > 0) {
				len = prefix[--len];
			}
			else {
				// 没有公共前后缀
				prefix[i] = 0;
				++i;
			}
		}
	}
}

// 将前缀表往后移动一格
void move_prefix(int prefix[], int n)
{
	for (int i = n - 1; i > 0; --i) {
		prefix[i] = prefix[i - 1];
	}
	prefix[0] = -1;
}

根据前缀表进行字符串匹配

void kmp_search(
	const char* text, int m,
	const char* pattern, int n)
{
	int* prefix = (int*)malloc(sizeof(int) * n);
	prefix_table(pattern, prefix, n);
	move_prefix(prefix, n);
	// kmp search
	int i = 0, j = 0;
	for (; i < m;) {
		if (j == n - 1 && text[i] == pattern[j]) {
			printf("found \"%s\" at %d\n", pattern, i - j);
			j = prefix[j];
		}
		if (text[i] == pattern[j]) {
			i++; j++;
		}
		else {
			j = prefix[j];
			if (j == -1) {
				i++; j++;
			}
		}
	}
	free(prefix);
}

KMP算法测试

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

#define MAX_STR_LEN 256

int main(int argc, char** argv)
{
	int m, n;
	char text[MAX_STR_LEN];
	char pattern[MAX_STR_LEN];

	scanf("%s", text);
	scanf("%s", pattern);
	m = strlen(text);
	n = strlen(pattern);
		
	kmp_search(text, m, pattern, n);

	return 0;
}

程序运行结果

输入:
ABABABCABAABABABAB
ABABCABAA
输出:
found “ABABCABAA” at 2