解决这个问题的最佳方法（性能方面）是什么？我被推荐使用后缀树。这是最好的方法吗？
问问题
34928 次
7 回答
13
查看此链接：http: //introcs.cs.princeton.edu/java/42sort/LRS.java.html
/*************************************************************************
* Compilation: javac LRS.java
* Execution: java LRS < file.txt
* Dependencies: StdIn.java
*
* Reads a text corpus from stdin, replaces all consecutive blocks of
* whitespace with a single space, and then computes the longest
* repeated substring in that corpus. Suffix sorts the corpus using
* the system sort, then finds the longest repeated substring among
* consecutive suffixes in the sorted order.
*
* % java LRS < mobydick.txt
* ',- Such a funny, sporty, gamy, jesty, joky, hoky-poky lad, is the Ocean, oh! Th'
*
* % java LRS
* aaaaaaaaa
* 'aaaaaaaa'
*
* % java LRS
* abcdefg
* ''
*
*************************************************************************/
import java.util.Arrays;
public class LRS {
// return the longest common prefix of s and t
public static String lcp(String s, String t) {
int n = Math.min(s.length(), t.length());
for (int i = 0; i < n; i++) {
if (s.charAt(i) != t.charAt(i))
return s.substring(0, i);
}
return s.substring(0, n);
}
// return the longest repeated string in s
public static String lrs(String s) {
// form the N suffixes
int N = s.length();
String[] suffixes = new String[N];
for (int i = 0; i < N; i++) {
suffixes[i] = s.substring(i, N);
}
// sort them
Arrays.sort(suffixes);
// find longest repeated substring by comparing adjacent sorted suffixes
String lrs = "";
for (int i = 0; i < N - 1; i++) {
String x = lcp(suffixes[i], suffixes[i+1]);
if (x.length() > lrs.length())
lrs = x;
}
return lrs;
}
// read in text, replacing all consecutive whitespace with a single space
// then compute longest repeated substring
public static void main(String[] args) {
String s = StdIn.readAll();
s = s.replaceAll("\\s+", " ");
StdOut.println("'" + lrs(s) + "'");
}
}
于 2013-01-20T06:19:55.113 回答
6
也可以查看http://en.wikipedia.org/wiki/Suffix_array - 它们非常节省空间，并且有一些合理的可编程算法来生成它们，例如 Karkkainen 和 Sanders 的“简单线性工作后缀数组构造”
于 2012-04-27T18:09:21.050 回答
4
这是使用最简单的后缀树的最长重复子串的简单实现。后缀树以这种方式很容易实现。
#include <iostream>
#include <vector>
#include <unordered_map>
#include <string>
using namespace std;
class Node
{
public:
char ch;
unordered_map<char, Node*> children;
vector<int> indexes; //store the indexes of the substring from where it starts
Node(char c):ch(c){}
};
int maxLen = 0;
string maxStr = "";
void insertInSuffixTree(Node* root, string str, int index, string originalSuffix, int level=0)
{
root->indexes.push_back(index);
// it is repeated and length is greater than maxLen
// then store the substring
if(root->indexes.size() > 1 && maxLen < level)
{
maxLen = level;
maxStr = originalSuffix.substr(0, level);
}
if(str.empty()) return;
Node* child;
if(root->children.count(str[0]) == 0) {
child = new Node(str[0]);
root->children[str[0]] = child;
} else {
child = root->children[str[0]];
}
insertInSuffixTree(child, str.substr(1), index, originalSuffix, level+1);
}
int main()
{
string str = "banana"; //"abcabcaacb"; //"banana"; //"mississippi";
Node* root = new Node('@');
//insert all substring in suffix tree
for(int i=0; i<str.size(); i++){
string s = str.substr(i);
insertInSuffixTree(root, s, i, s);
}
cout << maxLen << "->" << maxStr << endl;
return 1;
}
/*
s = "mississippi", return "issi"
s = "banana", return "ana"
s = "abcabcaacb", return "abca"
s = "aababa", return "aba"
*/
于 2014-03-30T00:29:07.907 回答
2
LRS 问题是最好使用后缀树或后缀数组来解决的问题。两种方法都具有 O(n) 的最佳时间复杂度。
这是使用后缀数组的 LRS 问题的 O(nlog(n)) 解决方案。如果您有后缀数组的线性构造时间算法（这很难实现），我的解决方案可以改进为 O(n)。代码取自我的图书馆。如果您想了解有关后缀数组如何工作的更多信息，请务必查看我的教程
/**
* Finds the longest repeated substring(s) of a string.
*
* Time complexity: O(nlogn), bounded by suffix array construction
*
* @author William Fiset, william.alexandre.fiset@gmail.com
**/
import java.util.*;
public class LongestRepeatedSubstring {
// Example usage
public static void main(String[] args) {
String str = "ABC$BCA$CAB";
SuffixArray sa = new SuffixArray(str);
System.out.printf("LRS(s) of %s is/are: %s\n", str, sa.lrs());
str = "aaaaa";
sa = new SuffixArray(str);
System.out.printf("LRS(s) of %s is/are: %s\n", str, sa.lrs());
str = "abcde";
sa = new SuffixArray(str);
System.out.printf("LRS(s) of %s is/are: %s\n", str, sa.lrs());
}
}
class SuffixArray {
// ALPHABET_SZ is the default alphabet size, this may need to be much larger
int ALPHABET_SZ = 256, N;
int[] T, lcp, sa, sa2, rank, tmp, c;
public SuffixArray(String str) {
this(toIntArray(str));
}
private static int[] toIntArray(String s) {
int[] text = new int[s.length()];
for(int i=0;i<s.length();i++)text[i] = s.charAt(i);
return text;
}
// Designated constructor
public SuffixArray(int[] text) {
T = text;
N = text.length;
sa = new int[N];
sa2 = new int[N];
rank = new int[N];
c = new int[Math.max(ALPHABET_SZ, N)];
construct();
kasai();
}
private void construct() {
int i, p, r;
for (i=0; i<N; ++i) c[rank[i] = T[i]]++;
for (i=1; i<ALPHABET_SZ; ++i) c[i] += c[i-1];
for (i=N-1; i>=0; --i) sa[--c[T[i]]] = i;
for (p=1; p<N; p <<= 1) {
for (r=0, i=N-p; i<N; ++i) sa2[r++] = i;
for (i=0; i<N; ++i) if (sa[i] >= p) sa2[r++] = sa[i] - p;
Arrays.fill(c, 0, ALPHABET_SZ, 0);
for (i=0; i<N; ++i) c[rank[i]]++;
for (i=1; i<ALPHABET_SZ; ++i) c[i] += c[i-1];
for (i=N-1; i>=0; --i) sa[--c[rank[sa2[i]]]] = sa2[i];
for (sa2[sa[0]] = r = 0, i=1; i<N; ++i) {
if (!(rank[sa[i-1]] == rank[sa[i]] &&
sa[i-1]+p < N && sa[i]+p < N &&
rank[sa[i-1]+p] == rank[sa[i]+p])) r++;
sa2[sa[i]] = r;
} tmp = rank; rank = sa2; sa2 = tmp;
if (r == N-1) break; ALPHABET_SZ = r + 1;
}
}
// Use Kasai algorithm to build LCP array
private void kasai() {
lcp = new int[N];
int [] inv = new int[N];
for (int i = 0; i < N; i++) inv[sa[i]] = i;
for (int i = 0, len = 0; i < N; i++) {
if (inv[i] > 0) {
int k = sa[inv[i]-1];
while( (i + len < N) && (k + len < N) && T[i+len] == T[k+len] ) len++;
lcp[inv[i]-1] = len;
if (len > 0) len--;
}
}
}
// Finds the LRS(s) (Longest Repeated Substring) that occurs in a string.
// Traditionally we are only interested in substrings that appear at
// least twice, so this method returns an empty set if this is not the case.
// @return an ordered set of longest repeated substrings
public TreeSet <String> lrs() {
int max_len = 0;
TreeSet <String> lrss = new TreeSet<>();
for (int i = 0; i < N; i++) {
if (lcp[i] > 0 && lcp[i] >= max_len) {
// We found a longer LRS
if ( lcp[i] > max_len )
lrss.clear();
// Append substring to the list and update max
max_len = lcp[i];
lrss.add( new String(T, sa[i], max_len) );
}
}
return lrss;
}
public void display() {
System.out.printf("-----i-----SA-----LCP---Suffix\n");
for(int i = 0; i < N; i++) {
int suffixLen = N - sa[i];
String suffix = new String(T, sa[i], suffixLen);
System.out.printf("% 7d % 7d % 7d %s\n", i, sa[i],lcp[i], suffix );
}
}
}
于 2017-08-30T02:53:04.913 回答
0
public class LongestSubString {
public static void main(String[] args) {
String s = findMaxRepeatedString("ssssssssssss this is a ddddddd word with iiiiiiiiiis and loads of these are ppppppppppppps");
System.out.println(s);
}
private static String findMaxRepeatedString(String s) {
Processor p = new Processor();
char[] c = s.toCharArray();
for (char ch : c) {
p.process(ch);
}
System.out.println(p.bigger());
return new String(new char[p.bigger().count]).replace('\0', p.bigger().letter);
}
static class CharSet {
int count;
Character letter;
boolean isLastPush;
boolean assign(char c) {
if (letter == null) {
count++;
letter = c;
isLastPush = true;
return true;
}
return false;
}
void reassign(char c) {
count = 1;
letter = c;
isLastPush = true;
}
boolean push(char c) {
if (isLastPush && letter == c) {
count++;
return true;
}
return false;
}
@Override
public String toString() {
return "CharSet [count=" + count + ", letter=" + letter + "]";
}
}
static class Processor {
Character previousLetter = null;
CharSet set1 = new CharSet();
CharSet set2 = new CharSet();
void process(char c) {
if ((set1.assign(c)) || set1.push(c)) {
set2.isLastPush = false;
} else if ((set2.assign(c)) || set2.push(c)) {
set1.isLastPush = false;
} else {
set1.isLastPush = set2.isLastPush = false;
smaller().reassign(c);
}
}
CharSet smaller() {
return set1.count < set2.count ? set1 : set2;
}
CharSet bigger() {
return set1.count < set2.count ? set2 : set1;
}
}
}
于 2016-12-01T22:57:44.267 回答
0
我有一个面试，我需要解决这个问题。这是我的解决方案：
public class FindLargestSubstring {
public static void main(String[] args) {
String test = "ATCGATCGA";
System.out.println(hasRepeatedSubString(test));
}
private static String hasRepeatedSubString(String string) {
Hashtable<String, Integer> hashtable = new Hashtable<>();
int length = string.length();
for (int subLength = length - 1; subLength > 1; subLength--) {
for (int i = 0; i <= length - subLength; i++) {
String sub = string.substring(i, subLength + i);
if (hashtable.containsKey(sub)) {
return sub;
} else {
hashtable.put(sub, subLength);
}
}
}
return "No repeated substring!";
}}
于 2018-04-15T02:00:26.607 回答
-1
影响性能的事情太多了，我们无法仅用您给我们的内容来回答这个问题。（操作系统、语言、内存问题、代码本身）
如果您只是在寻找算法效率的数学分析，您可能想要更改问题。
编辑
当我提到“内存问题”和“代码”时，我没有提供所有细节。您将要分析的字符串的长度是一个重要因素。此外，代码不能单独运行——它必须位于程序内部才能发挥作用。该程序的哪些特征会影响该算法的使用和性能？
基本上，在您有实际情况要测试之前，您无法进行性能调整。您可以对什么可能表现最好做出非常有根据的猜测，但是在您拥有真实数据和真实代码之前，您永远无法确定。
于 2012-04-27T17:25:08.587 回答