使用后缀数组和最长公共前缀尝试此代码。它还可以为您提供唯一子字符串的总数。该代码可能会在 Visual Studio 中产生堆栈溢出,但在 Eclipse C++ 中运行良好。那是因为它返回函数的向量。尚未针对极长的字符串对其进行测试。将这样做并报告。
// C++ program for building LCP array for given text
#include <bits/stdc++.h>
#include <vector>
#include <string>
using namespace std;
#define MAX 100000
int cum[MAX];
// Structure to store information of a suffix
struct suffix
{
int index; // To store original index
int rank[2]; // To store ranks and next rank pair
};
// A comparison function used by sort() to compare two suffixes
// Compares two pairs, returns 1 if first pair is smaller
int cmp(struct suffix a, struct suffix b)
{
return (a.rank[0] == b.rank[0])? (a.rank[1] < b.rank[1] ?1: 0):
(a.rank[0] < b.rank[0] ?1: 0);
}
// This is the main function that takes a string 'txt' of size n as an
// argument, builds and return the suffix array for the given string
vector<int> buildSuffixArray(string txt, int n)
{
// A structure to store suffixes and their indexes
struct suffix suffixes[n];
// Store suffixes and their indexes in an array of structures.
// The structure is needed to sort the suffixes alphabatically
// and maintain their old indexes while sorting
for (int i = 0; i < n; i++)
{
suffixes[i].index = i;
suffixes[i].rank[0] = txt[i] - 'a';
suffixes[i].rank[1] = ((i+1) < n)? (txt[i + 1] - 'a'): -1;
}
// Sort the suffixes using the comparison function
// defined above.
sort(suffixes, suffixes+n, cmp);
// At his point, all suffixes are sorted according to first
// 2 characters. Let us sort suffixes according to first 4
// characters, then first 8 and so on
int ind[n]; // This array is needed to get the index in suffixes[]
// from original index. This mapping is needed to get
// next suffix.
for (int k = 4; k < 2*n; k = k*2)
{
// Assigning rank and index values to first suffix
int rank = 0;
int prev_rank = suffixes[0].rank[0];
suffixes[0].rank[0] = rank;
ind[suffixes[0].index] = 0;
// Assigning rank to suffixes
for (int i = 1; i < n; i++)
{
// If first rank and next ranks are same as that of previous
// suffix in array, assign the same new rank to this suffix
if (suffixes[i].rank[0] == prev_rank &&
suffixes[i].rank[1] == suffixes[i-1].rank[1])
{
prev_rank = suffixes[i].rank[0];
suffixes[i].rank[0] = rank;
}
else // Otherwise increment rank and assign
{
prev_rank = suffixes[i].rank[0];
suffixes[i].rank[0] = ++rank;
}
ind[suffixes[i].index] = i;
}
// Assign next rank to every suffix
for (int i = 0; i < n; i++)
{
int nextindex = suffixes[i].index + k/2;
suffixes[i].rank[1] = (nextindex < n)?
suffixes[ind[nextindex]].rank[0]: -1;
}
// Sort the suffixes according to first k characters
sort(suffixes, suffixes+n, cmp);
}
// Store indexes of all sorted suffixes in the suffix array
vector<int>suffixArr;
for (int i = 0; i < n; i++)
suffixArr.push_back(suffixes[i].index);
// Return the suffix array
return suffixArr;
}
/* To construct and return LCP */
vector<int> kasai(string txt, vector<int> suffixArr)
{
int n = suffixArr.size();
// To store LCP array
vector<int> lcp(n, 0);
// An auxiliary array to store inverse of suffix array
// elements. For example if suffixArr[0] is 5, the
// invSuff[5] would store 0. This is used to get next
// suffix string from suffix array.
vector<int> invSuff(n, 0);
// Fill values in invSuff[]
for (int i=0; i < n; i++)
invSuff[suffixArr[i]] = i;
// Initialize length of previous LCP
int k = 0;
// Process all suffixes one by one starting from
// first suffix in txt[]
for (int i=0; i<n; i++)
{
/* If the current suffix is at n-1, then we don’t
have next substring to consider. So lcp is not
defined for this substring, we put zero. */
if (invSuff[i] == n-1)
{
k = 0;
continue;
}
/* j contains index of the next substring to
be considered to compare with the present
substring, i.e., next string in suffix array */
int j = suffixArr[invSuff[i]+1];
// Directly start matching from k'th index as
// at-least k-1 characters will match
while (i+k<n && j+k<n && txt[i+k]==txt[j+k])
k++;
lcp[invSuff[i]] = k; // lcp for the present suffix.
// Deleting the starting character from the string.
if (k>0)
k--;
}
// return the constructed lcp array
return lcp;
}
// Utility function to print an array
void printArr(vector<int>arr, int n)
{
for (int i = 0; i < n; i++)
cout << arr[i] << " ";
cout << endl;
}
// Driver program
int main()
{
int t;
cin >> t;
//t = 1;
while (t > 0) {
//string str = "banana";
string str;
cin >> str; // >> k;
vector<int>suffixArr = buildSuffixArray(str, str.length());
int n = suffixArr.size();
cout << "Suffix Array : \n";
printArr(suffixArr, n);
vector<int>lcp = kasai(str, suffixArr);
cout << "\nLCP Array : \n";
printArr(lcp, n);
// cum will hold number of substrings if that'a what you want (total = cum[n-1]
cum[0] = n - suffixArr[0];
// vector <pair<int,int>> substrs[n];
int count = 1;
for (int i = 1; i <= n-suffixArr[0]; i++) {
//substrs[0].push_back({suffixArr[0],i});
string sub_str = str.substr(suffixArr[0],i);
cout << count << " " << sub_str << endl;
count++;
}
for(int i = 1;i < n;i++) {
cum[i] = cum[i-1] + (n - suffixArr[i] - lcp[i - 1]);
int end = n - suffixArr[i];
int begin = lcp[i-1] + 1;
int begin_suffix = suffixArr[i];
for (int j = begin, k = 1; j <= end; j++, k++) {
//substrs[i].push_back({begin_suffix, lcp[i-1] + k});
// cout << "i push " << i << " " << begin_suffix << " " << k << endl;
string sub_str = str.substr(begin_suffix, lcp[i-1] +k);
cout << count << " " << sub_str << endl;
count++;
}
}
/*int count = 1;
cout << endl;
for(int i = 0; i < n; i++){
for (auto it = substrs[i].begin(); it != substrs[i].end(); ++it ) {
string sub_str = str.substr(it->first, it->second);
cout << count << " " << sub_str << endl;
count++;
}
}*/
t--;
}
return 0;
}
还有一个更简单的算法:
#include <iostream>
#include <string.h>
#include <vector>
#include <string>
#include <algorithm>
#include <time.h>
using namespace std;
char txt[100000], *p[100000];
int m, n;
int cmp(const void *p, const void *q) {
int rc = memcmp(*(char **)p, *(char **)q, m);
return rc;
}
int main() {
std::cin >> txt;
int start_s = clock();
n = strlen(txt);
int k; int i;
int count = 1;
for (m = 1; m <= n; m++) {
for (k = 0; k+m <= n; k++)
p[k] = txt+k;
qsort(p, k, sizeof(p[0]), &cmp);
for (i = 0; i < k; i++) {
if (i != 0 && cmp(&p[i-1], &p[i]) == 0){
continue;
}
char cur_txt[100000];
memcpy(cur_txt, p[i],m);
cur_txt[m] = '\0';
std::cout << count << " " << cur_txt << std::endl;
count++;
}
}
cout << --count << endl;
int stop_s = clock();
float run_time = (stop_s - start_s) / double(CLOCKS_PER_SEC);
cout << endl << "distinct substrings \t\tExecution time = " << run_time << " seconds" << endl;
return 0;
}
不过,对于极长的字符串来说,这两种算法都太慢了。我针对长度超过 47,000 的字符串测试了算法,算法完成时间超过 20 分钟,第一个需要 1200 秒,第二个需要 1360 秒,这只是计算唯一子字符串而不输出到终端。因此,对于长度可能高达 1000 的字符串,您可能会得到一个可行的解决方案。两种解决方案确实计算了相同的唯一子字符串总数。我确实针对 2000 和 10,000 的字符串长度测试了这两种算法。第一个算法的时间:0.33 s 和 12 s;对于第二种算法,它是 0.535 秒和 20 秒。所以看起来一般第一个算法更快。