声明
BF的话主要是为了体现出KMP的高效之处，当然比BF更高效的还有BM，这里的话就不一一过多解释
BF算法
#include<iostream>
using namespace std;
//返回子串t在主串t中第pos个字符之后的位置；若不存在，函数返回0
//t非空，1≤pos≤s.size()
int Index(string s, string t, int pos=0) //默认为0，默认从第一个元素开始查找
{
int i = pos; //主串t当前下表
int j = 0; //子串t当前下表
while (i<s.size() && j<t.size()) //i小于s长度，j小于t长度，循环继续
{
if (s[i] == t[j])
{
i++;
j++;
}
else //指针退回，重新开始匹配
{
i = i - j + 1; //i退回到上一次匹配首位的下一位
j = 0; //j退回到子串t的首位
}
}
if (j >= t.size())
return i - t.size() + 1; //i - t.size()表示从s[4]开始重复，+1表示该元素为第5个元素
else
return 0;
}
int main()
{
string s = "goodgoogle";
string t = "google";
cout << Index(s, t)<<endl;
return 0;
}
KMP算法
原版
#define _CRT_SECURE_NO_WARNINGS
#include<stdio.h>
#include<string.h>
#include<Windows.h>
#define BUF_SIZE 256
typedef struct seqstring {
char string[100];
int length;
}seqstring;
void getnext(seqstring p, int next[]) {
int i, j;
i = 0;//指向字符串每个字符的下标
j = -1;
next[i] = j;//next[0]放上-1
while (i < p.length) {
//没有到达结尾的话
if (j == -1 || p.string[i] == p.string[j]) {
//如果是第一个字符或遇到相同的字符
next[++i] = ++j;
}
else {
j = next[j];
}
}
for (i = 0;i < p.length;i++) {
//输出next[]值
printf("%d ", next[i]);
}
}
int kmp(seqstring t, seqstring p, int next[]) {
int i, j;
i = j = 0;
while (i < t.length && j < p.length) {
if (j == -1 || t.string[i] == p.string[j]) {
i++;j++;
}
else {
j = next[j];
}
}
if (j == p.length) return i - p.length;
else return -1;
}
int main() {
seqstring t, p;
int next[50];
DWORD nIn;
char buffer[BUF_SIZE] = "";
HANDLE handle = CreateFile("test.txt",
GENERIC_READ,
FILE_SHARE_READ,
NULL,
OPEN_EXISTING,
FILE_ATTRIBUTE_NORMAL,
NULL);
if (handle == INVALID_HANDLE_VALUE) {
printf("%d", GetLastError());
return -1;
}
ReadFile(handle, buffer, BUF_SIZE, &nIn, NULL) ;
strcpy(t.string, buffer);
printf("%s\n", t.string);
t.length = strlen(t.string);
printf("please input string p:");
scanf("%s", p.string);
printf("%s\n", p.string);
p.length = strlen(p.string);
printf("next:");
getnext(p, next);
printf("\n%d\n", kmp(t, p, next));
}
改进版（符合题意版）
#define _CRT_SECURE_NO_WARNINGS
#include<stdio.h>
#include<string.h>
#include<Windows.h>
#include <iostream>
using namespace std;
#define BUF_SIZE 256
int counts = 0;
int direction[200] = {
0};
typedef struct seqstring {
char string[100];
int length;
}seqstring;
void getnext(seqstring p, int next[]) {
int i, j;
i = 0;//指向字符串每个字符的下标
j = -1;
next[i] = j;//next[0]放上-1
while (i < p.length) {
//没有到达结尾的话
if (j == -1 || p.string[i] == p.string[j]) {
//如果是第一个字符或遇到相同的字符
next[++i] = ++j;
}
else {
j = next[j];
}
}
for (i = 0; i < p.length; i++) {
//输出next[]值
//printf("%d ", next[i]);
}
}
int kmp(seqstring t, seqstring p, int next[]) {
int i, j;
i = j = 0;
while (true) {
if (j == -1 || t.string[i] == p.string[j]) {
i++; j++;
}
else {
j = next[j];
}
if (!(i < t.length && j < p.length)) {
if (j == p.length) {
direction[counts] = i - p.length;
counts++;
j = 0;
}
if (i == t.length) {
return 0;
}
}
}
if (j == p.length)
{
return i - p.length;
}
else
{
return -1;
}
}
int main() {
seqstring t, p;
int next[50];
DWORD nIn;
char buffer[BUF_SIZE] = "";
HANDLE handle = CreateFile("test.txt",
GENERIC_READ,
FILE_SHARE_READ,
NULL,
OPEN_EXISTING,
FILE_ATTRIBUTE_NORMAL,
NULL);
if (handle == INVALID_HANDLE_VALUE) {
printf("%d", GetLastError());
return -1;
}
ReadFile(handle, buffer, BUF_SIZE, &nIn, NULL);
strcpy(t.string, buffer);
printf("%s\n", t.string);
t.length = strlen(t.string);
printf("please input string p:");
scanf("%s", p.string);
printf("%s\n", p.string);
p.length = strlen(p.string);
//printf("next:");
getnext(p, next);
kmp(t, p, next);
printf("\n%d\n", counts);
printf("单词出现的位置如下：\n");
for (int i = 0; i < counts; i++) {
cout << direction[i]<<" ";
}
}
查找结果：
