我正在尝试找到以下模式：
不知道可能出现的任何模式。
例如：
'ell', 'the b', 'y '。'the boy fell by the bell'。使用双重for循环，可能会强行强迫 非常 ：
ArrayList<String> patternsList = new ArrayList<>();
int length = string.length();
for (int i = 0; i < length; i++) {
int limit = (length - i) / 2;
for (int j = limit; j >= 1; j--) {
int candidateEndIndex = i + j;
String candidate = string.substring(i, candidateEndIndex);
if(candidate.length() <= 1) {
continue;
}
if (string.substring(candidateEndIndex).contains(candidate)) {
boolean notASubpattern = true;
for (String pattern : patternsList) {
if (pattern.contains(candidate)) {
notASubpattern = false;
break;
}
}
if (notASubpattern) {
patternsList.add(candidate);
}
}
}
}
然而，当搜索大量模式的大字符串时，这是非常慢的。
答案 0 :(得分：24)
您可以在线性时间内为字符串构建后缀树： https://en.wikipedia.org/wiki/Suffix_tree
您要查找的模式是与仅具有叶子元素的内部节点对应的字符串。
答案 1 :(得分：8)
您可以使用n-gram查找字符串中的模式。扫描字符串n-gram需要O（n）时间。当您使用n-gram找到子字符串时，将其放入哈希表中，并计算字符串中找到子字符串的次数。当您在字符串中搜索n-gram时，在哈希表中搜索大于1的计数，以查找字符串中的重复模式。
例如，在字符串中“男孩摔倒了铃铛，男孩摔倒了铃铛”，使用6克将发现子串“男孩摔倒了铃”。具有该子字符串的哈希表条目的计数为2，因为它在字符串中出现了两次。改变n-gram中的单词数量将有助于您发现字符串中的不同模式。
Dictionary<string, int>dict = new Dictionary<string, int>();
int count = 0;
int ngramcount = 6;
string substring = "";
// Add entries to the hash table
while (count < str.length) {
// copy the words into the substring
int i = 0;
substring = "";
while (ngramcount > 0 && count < str.length) {
substring[i] = str[count];
if (str[i] == ' ')
ngramcount--;
i++;
count++;
}
ngramcount = 6;
substring.Trim(); // get rid of the last blank in the substring
// Update the dictionary (hash table) with the substring
if (dict.Contains(substring)) { // substring is already in hash table so increment the count
int hashCount = dict[substring];
hashCount++;
dict[substring] = hashCount;
}
else
dict[substring] = 1;
}
// Find the most commonly occurrring pattern in the string
// by searching the hash table for the greatest count.
int maxCount = 0;
string mostCommonPattern = "";
foreach (KeyValuePair<string, int> pair in dict) {
if (pair.Value > maxCount) {
maxCount = pair.Value;
mostCommonPattern = pair.Key;
}
}
答案 2 :(得分：1)
我写这篇文章只是为了好玩。我希望我能正确理解这个问题，这个问题有效而且足够快;如果没有，请对我很轻松:)如果有人发现它有用，我可能会更多地优化它。
private static IEnumerable<string> getPatterns(string txt)
{
char[] arr = txt.ToArray();
BitArray ba = new BitArray(arr.Length);
for (int shingle = getMaxShingleSize(arr); shingle >= 2; shingle--)
{
char[] arr1 = new char[shingle];
int[] indexes = new int[shingle];
HashSet<int> hs = new HashSet<int>();
Dictionary<int, int[]> dic = new Dictionary<int, int[]>();
for (int i = 0, count = arr.Length - shingle; i <= count; i++)
{
for (int j = 0; j < shingle; j++)
{
int index = i + j;
arr1[j] = arr[index];
indexes[j] = index;
}
int h = getHashCode(arr1);
if (hs.Add(h))
{
int[] indexes1 = new int[indexes.Length];
Buffer.BlockCopy(indexes, 0, indexes1, 0, indexes.Length * sizeof(int));
dic.Add(h, indexes1);
}
else
{
bool exists = false;
foreach (int index in indexes)
if (ba.Get(index))
{
exists = true;
break;
}
if (!exists)
{
int[] indexes1 = dic[h];
if (indexes1 != null)
foreach (int index in indexes1)
if (ba.Get(index))
{
exists = true;
break;
}
}
if (!exists)
{
foreach (int index in indexes)
ba.Set(index, true);
int[] indexes1 = dic[h];
if (indexes1 != null)
foreach (int index in indexes1)
ba.Set(index, true);
dic[h] = null;
yield return new string(arr1);
}
}
}
}
}
private static int getMaxShingleSize(char[] arr)
{
for (int shingle = 2; shingle <= arr.Length / 2 + 1; shingle++)
{
char[] arr1 = new char[shingle];
HashSet<int> hs = new HashSet<int>();
bool noPattern = true;
for (int i = 0, count = arr.Length - shingle; i <= count; i++)
{
for (int j = 0; j < shingle; j++)
arr1[j] = arr[i + j];
int h = getHashCode(arr1);
if (!hs.Add(h))
{
noPattern = false;
break;
}
}
if (noPattern)
return shingle - 1;
}
return -1;
}
private static int getHashCode(char[] arr)
{
unchecked
{
int hash = (int)2166136261;
foreach (char c in arr)
hash = (hash * 16777619) ^ c.GetHashCode();
return hash;
}
}
修改
我之前的代码存在严重问题。这个更好：
private static IEnumerable<string> getPatterns(string txt)
{
Dictionary<int, int> dicIndexSize = new Dictionary<int, int>();
for (int shingle = 2, count0 = txt.Length / 2 + 1; shingle <= count0; shingle++)
{
Dictionary<string, int> dic = new Dictionary<string, int>();
bool patternExists = false;
for (int i = 0, count = txt.Length - shingle; i <= count; i++)
{
string sub = txt.Substring(i, shingle);
if (!dic.ContainsKey(sub))
dic.Add(sub, i);
else
{
patternExists = true;
int index0 = dic[sub];
if (index0 >= 0)
{
dicIndexSize[index0] = shingle;
dic[sub] = -1;
}
}
}
if (!patternExists)
break;
}
List<int> lst = dicIndexSize.Keys.ToList();
lst.Sort((a, b) => dicIndexSize[b].CompareTo(dicIndexSize[a]));
BitArray ba = new BitArray(txt.Length);
foreach (int i in lst)
{
bool ok = true;
int len = dicIndexSize[i];
for (int j = i, max = i + len; j < max; j++)
{
if (ok) ok = !ba.Get(j);
ba.Set(j, true);
}
if (ok)
yield return txt.Substring(i, len);
}
}
this book中的文字在我的电脑中耗时3.4秒。
答案 3 :(得分：0)
后缀数组是正确的想法，但是缺少一个非平凡的部分，即识别文献中称为“超最大重复”的内容。这是一个带有工作代码的GitHub仓库：https://github.com/eisenstatdavid/commonsub。后缀数组构造使用SAIS库，作为子模块出售。使用来自Efficient repeat finding via suffix arrays
(Becher–Deymonnaz–Heiber)中findsmaxr的伪代码的修正版本找到超极大重复。
static void FindRepeatedStrings(void) {
// findsmaxr from https://arxiv.org/pdf/1304.0528.pdf
printf("[");
bool needComma = false;
int up = -1;
for (int i = 1; i < Len; i++) {
if (LongCommPre[i - 1] < LongCommPre[i]) {
up = i;
continue;
}
if (LongCommPre[i - 1] == LongCommPre[i] || up < 0) continue;
for (int k = up - 1; k < i; k++) {
if (SufArr[k] == 0) continue;
unsigned char c = Buf[SufArr[k] - 1];
if (Set[c] == i) goto skip;
Set[c] = i;
}
if (needComma) {
printf("\n,");
}
printf("\"");
for (int j = 0; j < LongCommPre[up]; j++) {
unsigned char c = Buf[SufArr[up] + j];
if (iscntrl(c)) {
printf("\\u%.4x", c);
} else if (c == '\"' || c == '\\') {
printf("\\%c", c);
} else {
printf("%c", c);
}
}
printf("\"");
needComma = true;
skip:
up = -1;
}
printf("\n]\n");
}
以下是第一段文字的示例输出：
Davids-MBP:commonsub eisen$ ./repsub input
["\u000a"
," S"
," as "
," co"
," ide"
," in "
," li"
," n"
," p"
," the "
," us"
," ve"
," w"
,"\""
,"–"
,"("
,")"
,". "
,"0"
,"He"
,"Suffix array"
,"`"
,"a su"
,"at "
,"code"
,"com"
,"ct"
,"do"
,"e f"
,"ec"
,"ed "
,"ei"
,"ent"
,"ere's a "
,"find"
,"her"
,"https://"
,"ib"
,"ie"
,"ing "
,"ion "
,"is"
,"ith"
,"iv"
,"k"
,"mon"
,"na"
,"no"
,"nst"
,"ons"
,"or"
,"pdf"
,"ri"
,"s are "
,"se"
,"sing"
,"sub"
,"supermaximal repeats"
,"te"
,"ti"
,"tr"
,"ub "
,"uffix arrays"
,"via"
,"y, "
]
答案 4 :(得分：0)
我会使用Knuth–Morris–Pratt algorithm（线性时间复杂度 O（n））来查找子字符串。我会尝试找到最大的子串模式，从输入字符串中删除它，并尝试找到第二大的，依此类推。我会做这样的事情：
string pattern = input.substring(0,lenght/2);
string toMatchString = input.substring(pattern.length, input.lenght - 1);
List<string> matches = new List<string>();
while(pattern.lenght > 0)
{
int index = KMP(pattern, toMatchString);
if(index > 0)
{
matches.Add(pattern);
// remove the matched pattern occurences from the input string
// I would do something like this:
// 0 to pattern.lenght gets removed
// check for all occurences of pattern in toMatchString and remove them
// get the remaing shrinked input, reassign values for pattern & toMatchString
// keep looking for the next largest substring
}
else
{
pattern = input.substring(0, pattern.lenght - 1);
toMatchString = input.substring(pattern.length, input.lenght - 1);
}
}
KMP实现Knuth-Morris-Pratt算法。您可以在Github或Princeton找到它的Java实现，也可以自己编写。
PS：我没有用Java编写代码，我很快就尝试了即将结束的第一笔赏金。所以如果我错过了一些微不足道的事情或者发生了+/- 1错误，请不要给我这个棒。