Implement strStr function in O(n + m) time.
strStr return the first index of the target string in a source string. The length of the target string is m and the length of the source string is n.
If target does not exist in source, just return -1.
Example
Given source = abcdef, target = bcd, return 1.
Rabin Karp Algorithm。用Hash方程的思想做。自己实现Hash function。
1.提前算好target的code。
2.开始读入source的每个字符,在for循环里计算所有长度为target.length()的子字符串的hashcode。
3.对比,如果code一样,要进一步对比是否substring的确一样以排除false positive.
细节:
1.第二步内比如从abc -> bcd,for循环每次都加了新的字符,d已经被加上去了,你只要轻松地排除窗口刚滑走的a*幂次即可。因为幂次固定是31*target.length(),可以提早把幂次算好。
2.对%BASE这个操作每次计算别忘了。
3.对两个各自对BASE取余过的数做减法后,可能会出来负数,这时候不好
我的实现:
public class Solution { /* * @param source: A source string * @param target: A target string * @return: An integer as index */ public int strStr2(String source, String target) { // write your code here if (source == null || target == null) { return -1; } if (target.length() == 0) { return 0; } int BASE = 100000; int length = target.length(); // 31^length, 31 is HASHBASE. int power = 1; for (int i = 0; i < length; i++) { power = (power * 31) % BASE; } int targetCode = 0; for (int i = 0; i < length; i++) { targetCode = (targetCode * 31 + target.charAt(i)) % BASE; } int sourceCode = 0; for (int i = 0; i < source.length(); i++) { sourceCode = (sourceCode * 31 + source.charAt(i)) % BASE; if (i >= length) { //注意这里。可能出现负数的地方不要直接再%,用if处理。 sourceCode = sourceCode - (source.charAt(i - length) * power) % BASE; if (sourceCode < 0) { sourceCode += BASE; } } if (i >= length - 1 && sourceCode == targetCode && source.substring(i - length + 1, i + 1).equals(target)) { return i - length + 1; } } return -1; } }
九章实现:
public class Solution { /** * @param source a source string * @param target a target string * @return an integer as index */ public int strStr2(String source, String target) { if(target == null) { return -1; } int m = target.length(); if(m == 0 && source != null) { return 0; } if(source == null) { return -1; } int n = source.length(); if(n == 0) { return -1; } // mod could be any big integer // just make sure mod * 33 wont exceed max value of int. int mod = Integer.MAX_VALUE / 33; int hash_target = 0; // 33 could be something else like 26 or whatever you want for (int i = 0; i < m; ++i) { hash_target = (hash_target * 33 + target.charAt(i) - 'a') % mod; if (hash_target < 0) { hash_target += mod; } } int m33 = 1; for (int i = 0; i < m - 1; ++i) { m33 = m33 * 33 % mod; } int value = 0; for (int i = 0; i < n; ++i) { if (i >= m) { value = (value - m33 * (source.charAt(i - m) - 'a')) % mod; } value = (value * 33 + source.charAt(i) - 'a') % mod; if (value < 0) { value += mod; } if (i >= m - 1 && value == hash_target) { // you have to double check by directly compare the string if (target.equals(source.substring(i - m + 1, i + 1))) { return i - m + 1; } } } return -1; } }