串的模式匹配 | KMP算法

• 当j增加1时，j的match值有两种情况
  

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

typedef int Position;
#define NotFound -1

void BuildMatch(char *pattern, int *match)
{   // 为pattern建立相应的match值
    Position i, j;
    int m = strlen(pattern);
    match[0] = -1;
    
    for (j=1; j<m; j++) {
        i = match[j-1];
        while ((i>=0) && (pattern[i+1]!=pattern[j]))
            i = match[i];  // i回退
        if (pattern[i+1] == pattern[j]) {
            match[j] = i+1;
        } else
            match[j] = -1;
    }
}

Position KMP(char *string, char *pattern)
{
    int n = strlen(string);
    int m = strlen(pattern);
    Position s, p, *match;
    if (n < m) return NotFound;
    match = (Position *)malloc(sizeof(Position) * m);
    BuildMatch(pattern, match);  // 为pattern建立相应的match值
    s = p = 0;
    while (s<n && p<m) {
        if (string[s] == pattern[p]) {
            s++; p++;
        }
        else if (p>0) p = match[p-1]+1;  // s与p匹配失败时，p回退到p-1的match值+1处
        else s++;  // 如果p=0时，说明pattern首字符就不能与s所指字符匹配，因此，s+1，指向下一个字符，重新匹配
    }
    // s指针一直往前走，没有回退，因此如果匹配成功，返回的下标应该是s-m
    return (p == m)? (s - m): NotFound;
}

int main()
{
    char string[] = "This is a simple example.";
    char pattern[] = "simple";
    Position p = KMP(string, pattern);
    if (p == NotFound) printf("Not Found.\n");
    else printf("%s\n", string+p);
    return 0;
}