我想实现处理通配符的 Boyer Moore Horspool 算法的概括(匹配单词中的任何字母)。这意味着该模式h _ _ s e
将在此文本中出现两次:horsehouse
.
我需要帮助来实现这一点,我无法对算法有足够深入的了解来自己解决这个问题,一些提示?
int [] createBadCharacterTable(char [] needle) {
int [] badShift = new int [256];
for(int i = 0; i < 256; i++) {
badShift[i] = needle.length;
}
int last = needle.length - 1;
for(int i = 0; i < last; i++) {
badShift[(int) needle[i]] = last - i;
}
return badShift;
}
int boyerMooreHorsepool(String word, String text) {
char [] needle = word.toCharArray();
char [] haystack = text.toCharArray();
if(needle.length > haystack.length) {
return -1;
}
int [] badShift = createBadCharacterTable(needle);
int offset = 0;
int scan = 0;
int last = needle.length - 1;
int maxoffset = haystack.length - needle.length;
while(offset <= maxoffset) {
for(scan = last; (needle[scan] == haystack[scan+offset] || needle[scan] == (int) '_'); scan--) {
if(scan == 0) { //Match found
return offset;
}
}
offset += badShift[(int) haystack[offset + last]];
}
return -1;
}