KMP算法代码笔记

 

 

C版本

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


void perfix_table(char pattern[], int prefix[], int n)
{
    prefix[0] = 0;
    int len = 0;
    int i = 1;
    while (i<n) {
        if (pattern[i] == pattern[len])
        {
            len++;
            prefix[i] = len;
            i++;
        }
        else
        {
            if (len>0) {
                len = prefix[len - 1];
            } else {
                prefix[i] = len;
                i++;
            }
        }
    }
    
}
void move_prefix_table(int prefix[],int n){
    int i;
    for (i=n-1; i>0; i--){
        prefix[i] = prefix[i-1];
    }
    prefix[0] = -1;
    
}
void kmp(char text[], char pattern[]) {
    int n = (int)strlen(pattern);
    int* prefix  = malloc(sizeof(int) * n);
    perfix_table(pattern, prefix, n);
    move_prefix_table(prefix, n);
    int m = (int)strlen(text);
    int i = 0;
    int j = 0;
    while (i < m) {
        if (j == n-1 && text[i] == pattern[j]) {
            printf("found pattern at %d\n", i-j);
            j = prefix[j];
        }
        if (text[i] == pattern[j]) {
            i++;
            j++;
        } else {
            j = prefix[j];
            if (j == -1) {
                i++;j++;
            }
        }
        
    }
}


int main ()
{
    char pattern[] = "ABCABCBAA";
    char text[] = "SABABCABABCAACCABCABCBAA";
    kmp(text, pattern);
    return 0;
}

java版本 https://www.zhihu.com/question/21923021

import java.util.ArrayList;
import java.util.Arrays;
import java.util.List;

public class KMPTest {

    public static void main(String[] args) {
        String text = "abababzabababa";
        String patten = "abababa";
        List<Integer> index = search(text, patten);
        System.out.println();
        index.forEach(integer -> System.out.print(integer + " "));
        System.out.println(text.substring(index.get(0), index.get(0) + patten.length()));
    }



    // 构造 pattern 的最大匹配数表
    static int[] calculateMaxMatchLengths(String pattern) {
        int[] maxMatchLengths = new int[pattern.length()];
        int maxLength = 0;
        for (int i = 1; i < pattern.length(); i++) {
            while (maxLength > 0 && pattern.charAt(maxLength) != pattern.charAt(i)) {
                maxLength = maxMatchLengths[maxLength - 1]; // ①
            }
            if (pattern.charAt(i) == pattern.charAt(maxLength)) {
                maxLength++; // ②
            }
            maxMatchLengths[i] = maxLength;
        }
        System.out.println(Arrays.toString(maxMatchLengths));
        return maxMatchLengths;
    }



    // 在 text 中寻找 pattern，返回所有匹配的位置开头
    static List<Integer> search(String text, String pattern) {
        List<Integer> positions = new ArrayList<>();
        int[] maxMatchLengths = calculateMaxMatchLengths(pattern);
        int count = 0;
        for (int i = 0; i < text.length(); i++) {
            while (count > 0 && pattern.charAt(count) != text.charAt(i)) {
                count = maxMatchLengths[count - 1];
            }
            if (pattern.charAt(count) == text.charAt(i)) {
                count++;
            }
            if (count == pattern.length()) {
                positions.add(i - pattern.length() + 1);
                count = maxMatchLengths[count - 1];
            }
        }
        return positions;
    }
}