KMP
参考:https://baijiahao.baidu.com/s?id=1659735837100760934&wfr=spider&for=pc
// KMP
public static int kmp(String str, String pattern) {
// 预处理,生成next数组
int[] next = getNexts(pattern);
int j = 0;
// 主循环,遍历主串字符
for (int i = 0; i < str.length(); i++) {
while (j > 0 && str.charAt(i) != pattern.charAt(j)) {
//遇到坏字符时,查询next数组并改变模式串的起点
j = next[j];
}
if (str.charAt(i) == pattern.charAt(j)) {
j++;
}
if (j == pattern.length()) {
//匹配成功,返回下标
return i - pattern.length() + 1;
}
}
return -1;
}
// 生成Next数组
private static int[] getNexts(String pattern) {
int[] next = new int[pattern.length()];
int j = 0;
for (int i = 2; i < pattern.length(); i++) {
while (j != 0 && pattern.charAt(j) != pattern.charAt(i - 1)) {
//从next[i+1]的求解回溯到next[j]
j = next[j];
}
if (pattern.charAt(j) == pattern.charAt(i - 1)) {
j++;
}
next[i] = j;
}
return next;
}
String str = “ATGTGAGCTGGTGTGTGCFAA”;
String pattern = “GTGTGCF”;
int index = stringMatch.kmp(str, pattern);
System.out.println(“首次出现位置:” + index);
首次出现位置:12
BM
参考:https://blog.csdn.net/baidu_39502694/article/details/106475463
// BM算法匹配字符串,匹配成功返回P在S中的首字符下标,匹配失败返回-1
public int bmMatch(String source, String pattern) {
char[] src = source.toCharArray();
char[] ptn = pattern.toCharArray();
int sLen = src.length;
int pLen = ptn.length;
if (pLen == 0) {
return 0;
}
if (sLen < pLen) {
return -1;
}
int[] BC = buildBadCharacter(ptn);
int[] GS = buildGoodSuffix(ptn);
for (int i = pLen - 1; i < sLen; ) {
int j = pLen - 1;
for (; src[i] == ptn[j]; i--, j--) {
if (j == 0) {
return i;
}
}
// 每次后移“坏字符规则”和“好后缀规则”两者的较大值
// 注意此时i(坏字符)已经向前移动,所以并非真正意义上的规则
i += Math.max(BC[src[i]], GS[pLen - 1 - j]);
}
return -1;
}
// 坏字符规则表
public static int[] buildBadCharacter(char[] pattern) {
int pLen = pattern.length;
final int CHARACTER_SIZE = 256;
int[] BC = new int[CHARACTER_SIZE];
Arrays.fill(BC, pLen);
for (int i = 0; i < pLen - 1; i++) {
int ascii = pattern[i];
BC[ascii] = pLen - 1 - i;
}
return BC;
}
// 非真正意义上的好字符规则表,后移位数还加上了当前好后缀的最大长度
private static int[] buildGoodSuffix(char[] pattern) {
int pLen = pattern.length;
int[] GS = new int[pLen]; // 记录好后缀出现时后移位数
int lastPrefixPos = pLen; // 好后缀的首字符位置
for (int i = pLen - 1; i >= 0; i--) {
// i+1是主串begin(含)之后的子串是否匹配模式串的前缀
if (isPrefix(pattern, i + 1)) {
lastPrefixPos = i + 1;
}
GS[pLen - 1 - i] = lastPrefixPos + pLen - 1 - i;
}
// 上面在比较好后缀时,是从模式串的首字符开始的,但实际上好后缀可能出现在模式串中间。
// 比如模式串EXAMPXA,假设主串指针在比较P时发现是坏字符,那么XA就是好后缀,
// 虽然它的首字符X与模式串的首字符E并不相等。此时suffixLen=2表示将主串指针后移至模式串末尾,
// pLen-1-i=4表示真正的好字符规则,同样主串指针后移,使得模式串前面的XA对齐主串的XA
for (int i = 0; i < pLen - 1; i++) {
int suffixLen = suffixLength(pattern, i);
GS[suffixLen] = pLen - 1 - i + suffixLen;
}
return GS;
}
// 判断是否是好后缀,即模式串begin(含)之后的子串是否匹配模式串的前缀
private static boolean isPrefix(char[] pattern, int begin) {
for (int i = begin, j = 0; i < pattern.length; i++, j++) {
if (pattern[i] != pattern[j]) {
return false;
}
}
return true;
}
// 返回模式串中以pattern[begin](含)结尾的后缀子串的最大长度
private static int suffixLength(char[] pattern, int begin) {
int suffixLen = 0;
int i = begin;
int j = pattern.length - 1;
while (i >= 0 && pattern[i] == pattern[j]) {
suffixLen++;
i--;
j--;
}
return suffixLen;
}
StringMatch stringMatch = new StringMatch();
int i = stringMatch.bmMatch(“HERE IS A SIMPLE EXAMPLE”, “EXAMPLE”);
System.out.println(“结果:”+i);
结果:17