算法（C语言）-- KMP 算法

KMP 算法是对于暴力匹配算法的改进
 next 数组
 * 暴力在刚在的匹配的过程中，主串指针回溯了多次，才达到了匹配的状态
 * KMP算法，主串没有回溯，并且快速达到匹配状态。
 * KMP算法是一种高效的模式匹配算法，它牺牲了一定的空间保存 next 数组，提高了匹配效率
 * KMP算法可以更加智能的移动字符串，让字符串达到匹配状态

next 数组
 * 当该字符与主串发生不匹配之后，值对应索引的字符要移动到跟主串不匹配字符对齐。
 * 算法：公共前后缀 
 *      前面和后面是一样的
 * next值 = 公共前后缀 + 1
 * 找公共前后缀的目的是：为了找到前后能够匹配的状态

KMP算法的核心：减少主串指针的移动，并且快速找到前后匹配的状态，从而加快我们匹配的进程

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

typedef struct String
{
    char *data;
    int len;
} String;

String *initString()
{

    String *string = (String *)malloc(sizeof(String));
    if (string == NULL)
    {
        printf("malloc string error\n");
        exit(1);
    }
    string->data = NULL;
    string->len = 0;
    return string;
}

void stringAssign(String *string, char *data)
{
    if (string->data != NULL)
    {
        free(string->data);
        string->data = NULL;
    }
    int len = 0;
    char *temp = data;
    while (*temp) // 记录长度
    {
        len++;
        temp++;
    }
    if (len == 0)
    {
        string->data = NULL;
        string->len = 0;
    }
    else
    {
        temp = data; // 重新置位temp
        string->len = len;
        string->data = (char *)malloc(sizeof(char) * (len + 1)); // 给string->data 在堆上分配空间
        if (string->data == NULL)
        {
            printf("malloc string—>data error\n");
            exit(1);
        }
        for (int i = 0; i < len; i++)
        {
            string->data[i] = *temp;
            temp++;
        }
    }
}

void printString(String *string)
{
    for (int i = 0; i < string->len; i++)
    {
        if (i == 0)
        {
            printf("%c ", string->data[i]);
        }
        else
        {
            printf(" -> %c ", string->data[i]);
        }
    }
    printf("\n");
}

int *getNext(String *string)
{
    int *next = (int *)malloc(sizeof(int) * string->len);
    if (next == NULL)
    {
        printf("malloc next error!");
        exit(1);
    }
    int i = 0;  // 表示字符串的索引
    int j = -1; // next 的初始值
    next[i] = j;
    while (i < string->len - 1)
    {
        if (j == -1 || string->data[i] == string->data[j])
        {
            i++;
            j++;
            next[i] = j;
        }
        else
        {
            j = next[j];
        }
    }
    return next;
}

void KMPMatch(String *master, String *sub, int *next)
{
    int i = 0;
    int j = 0;
    while (i < master->len && j < sub->len)
    {
        if (j == -1 || master->data[i] == sub->data[j])
        {
            i++;
            j++;
        }
        else
        {
            j = next[j];
        }
    }
    if (j == sub->len)
    {
        printf("KMP 匹配成功!\n");
    }
    else
    {
        printf("KMP 匹配失败！\n");
    }
}

void printNext(int *next, int len)
{
    printf("next > ");
    for (int i = 0; i < len; i++)
    {
        if (i == 0)
        {
            printf("%d", next[i] + 1);
        }
        else
        {
            printf(" -> %d ", next[i] + 1);
        }
    }
    printf("\n");
}

int main()
{
    String *stringmaster = initString();
    stringAssign(stringmaster, "hello world");
    printString(stringmaster);
    printf("----------------------------------------------------------\n");
    int *next = getNext(stringmaster);
    printNext(next, stringmaster->len);
    printf("----------------------------------------------------------\n");
    String *stringsub = initString();
    stringAssign(stringsub, "llo");
    printString(stringsub);
    printf("----------------------------------------------------------\n");
    KMPMatch(stringmaster, stringsub, next);
    return 0;
}

执行结果：

superlan@GodFather:~/C_Language/data_structure$ ./a.out 
h  -> e  -> l  -> l  -> o  ->    -> w  -> o  -> r  -> l  -> d 
----------------------------------------------------------
next > 0 -> 1  -> 1  -> 1  -> 1  -> 1  -> 1  -> 1  -> 1  -> 1  -> 1 
----------------------------------------------------------
l  -> l  -> o 
----------------------------------------------------------
KMP 匹配成功!