Simpliciy + KMP + BM 字符串搜索算法

Posted 2020-10-08 Archibald Witwicky

Simplicity

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

int simplicity(char *s, char *t, int pos);

int simplicity(char *s, char *t, int pos)
{
	int slen = strlen(s);
	int tlen = strlen(t);
	
	int i = pos;
	int j = 0;

	while(i < slen && j < tlen) {
		if(s[i] == t[j]) {
			i++;
			j++;
		} else {
			i = i - j + 1;
			j = 0;
		}
	}

	// subscripts start at 0 : j == len
	// subscripts start at 1 : j > len
	if(j == tlen) {
		return i - j;
	}

	return -1;
}

int main()
{
	int pos = 0;
	char *s = "goodgoogle";
	char *t = "goog";

	printf("{s:‘%s‘, t:‘%s‘, pos:‘%d‘, result(subsripts start at 0):‘%d‘}\n", s, t, pos, simplicity(s, t, pos));
	return 0;
}

 

 KMP

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

void get_nextSubscripts(char *t, int *next);
int kmp(char * s, char *t, int pos);

void get_nextSubscripts(char *t, int *next)
{
	int tlen = strlen(t);

	int i = 0; // suffix
	int j = -1; // prefix

	next[0] = -1;

	while(i <= tlen) {
		if(j == -1 || t[i] == t[j]) {
			i++;
			j++;

			if(t[i] == t[j]) {
				next[i] = next[j];
			} else {
				next[i] = j;
			}
		} else {
			j = next[j];
		}
	}
}

int kmp(char *s, char *t, int pos)
{
	int next[255];
	int slen = strlen(s);
	int tlen = strlen(t);

	int i = pos;
	int j = -1;

	get_nextSubscripts(t, next);

	while(i < slen && j < tlen) {
		if(j == -1 || s[i] == t[j]) {
			i++;
			j++;
		} else {
			j = next[j];	
		}
	}

	if(j == tlen) {
		return i - j;
	}

	return -1;
}

int main()
{
	int pos = 0;
	char *s = "goodgoogle";
	char *t = "goog";

	printf("{s:‘%s‘, t:‘%s‘, pos:‘%d‘, result(subsripts start at 0):‘%d‘}\n", s, t, pos, kmp(s, t, pos));

	return 0;
}

 

BM