//If there is no '&' before set, the time cost will be tripled;
int ladderLength(unordered_set<string>& bList, unordered_set<string>& eList, unordered_set<string>& wordList, int len)
{
if(bList.empty())
return 0;
if(bList.size() > eList.size())
return ladderLength(eList, bList, wordList, len);
unordered_set<string> tmpList;
for(auto it=bList.begin(); it!=bList.end(); it++)
{
string cur = *it;
for(int i=0; i<cur.size(); i++)
{
char c0 = cur[i];
for(char c='a'; c<='z'; c++)
{
cur[i]=c;
if(eList.count(cur)) return len+1;
if(wordList.count(cur))
{
tmpList.insert(cur);
wordList.erase(cur);
}
}
cur[i] = c0;
}
}
return ladderLength(tmpList, eList, wordList, len+1);
}
bool helper(unordered_set<string>& word1, unordered_set<string>& word2, unordered_set<string>& dict){
if(word1.empty()) return 0;
if(word1.size() > word2.size()) return helper(word2, word1, dict);
for(auto v : word1) dict.erase(v);
for(auto v : word2) dict.erase(v);
++res;
bool reach = false;
unordered_set<string> word3;
for(auto it = word1.begin(); it != word1.end(); ++it){
string word = *it;
for(int i = 0; i < word.size(); ++i){
char letter = word[i];
for(int k = 0; k < 26; ++k){
word[i] = 'a'+k;
if(word2.count(word)){
reach = true;
return reach;
}
if(dict.count(word) && !reach){
word3.insert(word);
}
}
word[i] = letter;
}
}
return reach || helper(word2, word3, dict);
}
bool buildTree(unordered_set<string> &forward, unordered_set<string> &backward, unordered_set<string> &dict,
unordered_map<string, vector<string>> &tree, bool reversed){
if (forward.empty())
return false;
if (forward.size() > backward.size())
return buildTree(backward, forward, dict, tree, !reversed);
for (auto &word : forward)
dict.erase(word);
for (auto &word : backward)
dict.erase(word);
unordered_set<string> nextLevel;
bool done = false; // guarantee shortest ladder
for (auto &it : forward){ //traverse each word in the forward -> the current level of the tree;
string word = it;
for (auto &c : word){
char c0 = c; //store the original;
for (c = 'a'; c <= 'z'; ++c) //try each case;
if (c != c0){ //avoid futile checking;
//using count is an accelerating method;
if (backward.count(word)){ // count is O(1) while isChangedByOne is O(size(word)* size(backward))
done = true;
//keep the tree generation direction consistent;
!reversed ? tree[it].push_back(word) : tree[word].push_back(it);
}
else if (!done && dict.count(word)){
nextLevel.insert(word);
!reversed ? tree[it].push_back(word) : tree[word].push_back(it);
}
}
c = c0; //restore the word;
}
}
return done || buildTree(nextLevel, backward, dict, tree, reversed);
}
int ladderLengthHelper(unordered_set<string>& words1, unordered_set<string>& words2, unordered_set<string>& wordList, int level) {
if (words1.empty())
return 0;
if (words1.size() > words2.size())
return ladderLengthHelper(words2, words1, wordList, level);
unordered_set<string> words3; // the new layer
for (auto it = words1.begin(); it != words1.end(); ++it)
{
string word = *it;
for (auto ch = word.begin(); ch != word.end(); ++ch)
{
char tmp = *ch;
for (*ch = 'a'; *ch <= 'z'; ++(*ch))
{
if (*ch == tmp)
continue;
if (words2.find(word) != words2.end())
return level + 1;
if (wordList.find(word) != wordList.end())
{
wordList.erase(word);
words3.insert(word);
}
}
*ch = tmp;
}
}
return ladderLengthHelper(words2, words3, wordList, level + 1); // put words2 first
}
int ladderLength(string beginWord, string endWord, unordered_set<string>& wordList) {
if (beginWord.size() != endWord.size()) return 0;
if (beginWord.empty() || endWord.empty()) return 1;
if (wordList.size() == 0) return 0;
int distance = 1;
queue<string> queToPush, queToPop;
queToPop.push(beginWord);
while (wordList.size() > 0 && !queToPop.empty()) {
while (!queToPop.empty()) {
string str(queToPop.front());
queToPop.pop();
for (int i = 0; i < str.size(); i++) {
for (char j = 'a'; j <= 'z'; j++) {
if (j == str[i]) {
continue;
}
char temp = str[i];
str[i] = j;
if (str == endWord) return distance + 1;
if (wordList.count(str) > 0) {
queToPush.push(str);
wordList.erase(str);
}
str[i] = temp;
}
}
}
swap(queToPush, queToPop);
distance++;
}
return 0;
}
// 双向BFS搜索
// -------- ----------
// | | | |
// |words1 | <---------------> | words2 |
// | | | |
// --------- ----------
// 不断地从两端向中心搜索，直至搜索到中间单词temp在另一个词袋中
int searchwithDoubleBFS(unordered_set<string>& words1, unordered_set<string>& words2,
unordered_set<string>& dict, int level) {
if (words1.empty()) return 0;
if (words1.size() > words2.size())
return searchwithDoubleBFS(words2, words1, dict, level);
unordered_set<string> words3;
for (auto it = words1.begin(); it != words1.end(); ++it) {
string word = *it;
for (size_t i = 0; i < word.size(); ++i) {
int ch = word[i];
for (int k = 0; k < 26; ++k) {
int ch2 = 'a' + k;
if (ch2 != ch) {
string temp = word;
temp[i] = ch2;
if (words2.find(temp) != words2.end()) {
return level+1;
} else {
if (dict.find(temp) != dict.end()) {
dict.erase(temp);
words3.insert(temp);
}
}
}
}
}
}
return searchwithDoubleBFS(words3, words2, dict, level+1);
}
int ladderLength(string beginWord, string endWord, unordered_set<string>& wordList) {
vector<string> candidates;
if (valid_next(beginWord, endWord))
{
// Found it!
return 2;
}
for (auto w_iter: wordList)
{
if (valid_next(w_iter, beginWord))
{
candidates.push_back(w_iter);
}
}
if (candidates.empty()) return 0;
int min_length = wordList.size() + 1;
for (auto can_iter: candidates)
{
wordList.erase(can_iter);
int from_here = ladderLength(can_iter, endWord, wordList);
if (from_here != 0 && from_here < min_length)
{
min_length = from_here;
}
wordList.insert(can_iter);
}
return (min_length == wordList.size() + 1)? 0: min_length + 1;
}
// looking for connection from both ends
bool bfs(unordered_set<string> &forward, unordered_set<string> &backward, bool isForward,
unordered_set<string> &wordList, unordered_map<string, vector<string>> &transMap) {
if (forward.empty() || backward.empty())
{
return false;
}
// always do bfs with less nodes
if (forward.size() > backward.size())
{
return bfs(backward, forward, !isForward, wordList, transMap);
}
// remove added node in the wordList to avoid duplication
unordered_set<string>::iterator it;
for (it = forward.begin(); it != forward.end(); it++)
{
wordList.erase(*it);
}
for (it = backward.begin(); it != backward.end(); it++)
{
wordList.erase(*it);
}
unordered_set<string> nextlevel;
bool isConnected = false;
for (it = forward.begin(); it != forward.end(); it++)
{
string word = *it;
for (int i = 0; i < word.size(); i++)
{
for (char ch = 'a'; ch <= 'z'; ch++)
{
if (word[i] != ch)
{
// word is in forward list, str is in backward list
string str(word);
str[i] = ch;
if (backward.find(str) != backward.end())
{
isConnected = true;
connect(word, str, isForward, transMap);
}
else if (!isConnected && wordList.find(str) != wordList.end())
{
nextlevel.insert(str);
connect(word, str, isForward, transMap);
}
}
}
}
}
return isConnected || bfs(nextlevel, backward, isForward, wordList, transMap);
}
int ladderLength(string beginWord, string endWord, unordered_set<string>& wordList) {
// int min = wordList.size()+3;
// bool* visited = new bool[wordList.size()];
// for (int i = 0; i < wordList.size(); ++i) {
// visited[i] = false;
// }
// unordered_set<string>::iterator it;
//
// recusiveSearch(beginWord,endWord,wordList,visited,0,2,min);
// delete visited;
// return ((min == wordList.size()+3)?0:min);
int min = 2;
bool* visited = new bool[wordList.size()];
for (int i = 0; i < wordList.size(); ++i) {
visited[i] = false;
}
queue<string> searchQue;
string curr = beginWord;
searchQue.push(beginWord);
unordered_set<string>::iterator it;
int layer = 1;
int layerRec = 1;
int visitCount = 0;
while (searchQue.size() != 0){
while (visitCount < layerRec) {
string word = searchQue.front();
searchQue.pop();
++visitCount;
if (isValidTrans(word, endWord)) {
return min;
}
for (int p = 0; p < (int)word.length(); p++) {
char letter = word[p];
for (int k = 0; k < 26; k++) {
word[p] = 'a' + k;
if (letter != word[p] && wordList.find(word) != wordList.end()) {
searchQue.push(word);
wordList.erase(word);
++layer;
}
}
word[p] = letter;
}
}
layerRec = layer;
++min;
}
return 0;
}
int ladderLength(string beginWord, string endWord, unordered_set<string>& wordList)
{
const int beginLen = beginWord.length();
const int endLen = endWord.length();
if (beginLen != endLen)
{
return 0;
}
if (beginLen == 0 || endLen == 0)
{
return 1;
}
if (wordList.size() == 0)
{
return 0;
}
int distance = 1;
queue<string> queToPush, queToPop;
queToPop.push(beginWord);
while (wordList.size() > 0 && !queToPop.empty())
{
while (!queToPop.empty())
{
string str(queToPop.front());
queToPop.pop();
for (int curInd = 0; curInd < beginLen; curInd++)
{
for (char curChar = 'a'; curChar <= 'z'; curChar++)
{
if (curChar == str[curInd])
{
continue;
}
char temp = str[curInd];
str[curInd] = curChar;
if (str == endWord)
{
return distance + 1;
}
if (wordList.count(str) > 0)
{
queToPush.push(str);
wordList.erase(str);
}
str[curInd] = temp;
}
}
}
swap(queToPush, queToPop);
distance++;
}
return 0;
}
void values(unordered_set<int> &s,int a,int b)
{
s.insert(a);
s.insert(b);
if(s.size()==1) return;
int n;
std::vector<int> src,dst;
std::vector<int>::iterator iti,itj;
std::unordered_set<int> v;
size_t lastsz=0;
while(true){
copy(s.begin(),s.end(),std::back_inserter(src));
for(iti=src.begin();iti!=src.end();++iti){
for(itj=src.begin();itj!=src.end();++itj){
n = *iti-*itj;
if(n>0)
v.insert(n);
}
}
/*
cout<<"差值[原始]:";
std::for_each(v.begin(),v.end(),[](int n){cout<<n<<'\t';});
cout<<endl;
*/
src.clear();
copy(v.begin(),v.end(),std::back_inserter(dst));
copy(s.begin(),s.end(),std::back_inserter(src));
std::sort(dst.begin(),dst.end());
std::sort(src.begin(),src.end());
//unordered_set difference
std::vector<int> tmp(a/(a-b)+1);
iti = std::set_difference(dst.begin(),dst.end(),src.begin(),src.end(),tmp.begin());
tmp.resize(iti-tmp.begin());
/*
cout<<"差值:";
std::for_each(tmp.begin(),tmp.end(),[](int n){cout<<n<<'\t';});
cout<<endl;
*/
if(tmp.empty()) break;
s.insert(*tmp.begin());
if(s.size()==lastsz) break;
lastsz = s.size();
//std::for_each(v.begin(),v.end(),[&s](int n){cout<<n<<'\t';s.insert(n);});
v.clear();
src.clear();
dst.clear();
}
}
void us_isect(unordered_set<int> &out,
const unordered_set<int> &in1,
const unordered_set<int> &in2)
{
out.clear();
if (in2.size() < in1.size()) {
us_isect(out, in2, in1);
return;
}
for (unordered_set<int>::const_iterator it = in1.begin(); it != in1.end(); ++it)
{
if (in2.find(*it) != in2.end())
out.insert(*it);
}
}
//这题很有意思，不知道从哪里下手
//BFS
//不能这么循环，因为会删光了
int ladderLength(string beginWord, string endWord, unordered_set<string>& wordList)
{
if(beginWord.size() != endWord.size()) return 0;
if(beginWord.empty() || endWord.empty()) return 0;
queue<string> path;
path.push(beginWord);
int level = 1;
wordList.erase(beginWord);
while(wordList.size() >= 0 && !path.empty()){
int len = path.size();
for(int count = 0; count<len; count++){
string curWord = path.front();
path.pop();
for(int i = 0; i<curWord.size(); i++){
string tmp = curWord;
for(char j = 'a'; j<='z'; j++){
if(tmp[i] == j) continue;
tmp[i] = j;
if(tmp == endWord) return level+1;
if(wordList.find(tmp) != wordList.end()) path.push(tmp);
wordList.erase(tmp);
}
}
}
level++;
}
return 0;
}
bool wordBreak(string s, unordered_set<string> &dict) {
if(dict.size()==0) return false;
int longestWord = 0;
for(string word : dict) {
longestWord = max(longestWord, (int)word.size());
}
vector<bool> dp(s.size()+1,false);
dp[0]=true;
for(int i=1; i<=s.size(); i++)
{
for(int j=i-1; j>=max(i-longestWord, 0); j--)
{
if(dp[j])
{
string word = s.substr(j,i-j);
if(dict.find(word)!= dict.end())
{
dp[i]=true;
break; //next i
}
}
}
}
return dp[s.size()];
}
vector<string> wordBreak(string s, unordered_set<string>& wordDict, int start)
{
vector<string> res;
if (s.length() == 0 || wordDict.size() == 0){
return res;
}
else{
vector<string> tmp;
unordered_set<string>::iterator it;;
string sub;
for (int i = start; i < s.length(); i++){
sub = s.substr(start, i + 1 - start);
it = wordDict.find(sub);
if (it != wordDict.end()){
if (i == s.length() - 1)
res.push_back(sub);
else{
tmp = wordBreak(s, wordDict, i + 1);
for (int j = 0; j < tmp.size(); j++){
res.push_back(sub + " " + tmp.at(j));
}
}
}
else if (i == s.length() - 1)
return res;
}
return res;
}
}
vector<vector<string> > findLadders(string start, string end, unordered_set<string> &dict) {
allstr.clear();
res.clear();
if (dict.size() == 0) return res;
if (start == end) {
vector<string> justone(1, start);
res.push_back(justone);
return res;
}
allstr.push_back(make_pair(start, 1));
allstr.push_back(make_pair(end, 0));
for (unordered_set<string>::iterator pos = dict.begin(); pos != dict.end(); ++ pos) {
if (*pos != start && *pos != end) {
allstr.push_back(make_pair(*pos, 0));
}
}
_makeLinks();
int step = _ladderLen();
stk.clear();
stk.push_back(1);
_DFS(step);
return res;
}
vector<string> wordBreak(string s, unordered_set<string> &dict) {
vector<string> ans;
int bitmap = 0;
min = INT_MAX;
max = -1;
if (s.size() == 0 || dict.size() == 0)
return ans;
for (unordered_set<string>::iterator iter = dict.begin();
iter != dict.end(); iter++) {
string d = *iter;
int size = d.size();
if (min > size)
min = size;
if (max < size)
max = size;
for (int i = 0; i < d.size(); i++)
bitmap |= 1<<(d[i]-'a');
}
bitmap = ~bitmap;
for (int i = 0; i < s.size(); i++) {
if ((1<<(s[i]-'a')) & bitmap)
return ans;
}
string tmp;
find_ans(ans, s, dict, tmp, 0);
return ans;
}
CharacterVector file(CharacterVector& x)
{
const char *const test_lines = x[0];
vector<pair<string, string> > res;
taggerseg.tag(test_lines, res);
//unsigned int it;
vector<string> m;
m.reserve(res.size()*2);
if(stopWords.size()>0){
for (vector<pair<string, string> >::iterator it = res.begin(); it != res.end(); it++)
{
if (stopWords.end() == stopWords.find((*it).first))
{
m.push_back((*it).first);
m.push_back((*it).second);
}
}
}else{
for (vector<pair<string, string> >::iterator it = res.begin(); it != res.end(); it++)
{
m.push_back((*it).first);
m.push_back((*it).second);
}
}
return wrap(m);
}
vector<QueenNode*> getPossibleChild(const unordered_set<int>& fullSet, const vector<int>& curSeq)
{
int n = (int)fullSet.size();
unordered_set<int> neighbor(fullSet);
for(size_t i = 0; i < curSeq.size(); i++){
removeItem(neighbor, curSeq[i]);
}
for(int iter = 1; iter <= (int)curSeq.size(); iter++ ){
int x = curSeq.size() - iter;
int y = curSeq[curSeq.size() - iter];
if(x + iter < n && y + iter < n){
removeItem(neighbor, y + iter);
}
if(x + iter < n && y - iter >= 0){
removeItem(neighbor, y - iter);
}
}
vector<QueenNode*> neighborList;
if(!neighbor.empty()){
for(unordered_set<int>::iterator it = neighbor.begin(); it != neighbor.end(); it++){
neighborList.push_back(new QueenNode(*it));
}
}
return neighborList;
}
bool wordBreak(string s, unordered_set<string> &dict) {
if (s.size() == 0){
return true;
}
if (dict.size() == 0){
return false;
}
bool* f = (bool*)malloc(sizeof(bool)*s.size());
for(int i = 0; i < s.size(); i++){
f[i] = false;
}
for(int i = 0; i < s.size(); i++){
f[i] = dict.count(s.substr(0,i+1));
if (f[i]){
continue;
}
for (int j = 0; j < i; ++j){
if (f[j] && dict.count(s.substr(j+1,i-j))){
f[i] = true;
break;
}
}
}
return f[s.size() - 1];
}
int minLength(string &start, string &end, unordered_set<string> &dict){
int n = dict.size();
if(n == 0)
return 0;
int len = dict.begin()->size();
queue<string> q;
q.push(start);
map<string, int> vis;
map<string, string> pre;
vis[start] = 0;
while(!q.empty()){
string u = q.front();
q.pop();
for(int i = 0; i < len; i++){
string v = u;
char oldc = u[i];
for(char c = 'a'; c <= 'z'; c++){
if(c == oldc)
continue;
v[i] = c;
if(v == end){
return vis[u] + 1;
}
if(dict.find(v) == dict.end())
continue;
if(vis.find(v) == vis.end()){
vis[v] = vis[u] + 1;
q.push(v);
}
}
}
}
return 0;
}
void findNeighborPoints(vtkDataSet* data, vtkIdType ptId, unordered_set<vtkIdType>& nbrs, vtkIdList* cellIds, vtkIdTypeArray* neighbors = NULL) {
nbrs.clear();
cellIds->Reset();
data->GetPointCells(ptId, cellIds);
for (size_t k = 0; k < cellIds->GetNumberOfIds(); k++) {
vtkCell* cell = data->GetCell(cellIds->GetId(k));
for (size_t l = 0; l < cell->GetNumberOfEdges(); l++) {
vtkCell* edge = cell->GetEdge(l);
vtkIdType s = edge->GetPointId(0);
vtkIdType e = edge->GetPointId(1);
vtkIdType n = -1;
if (s == ptId) {
n = e;
} else if (e == ptId) {
n = s;
}
if (n > -1) {
if (nbrs.find(n) == nbrs.end()) {
nbrs.insert(n);
if (neighbors != NULL) {
neighbors->SetComponent(ptId, nbrs.size() - 1, n);
}
}
}
}
}
}
vector<string> wordBreak(string s, unordered_set<string> &dict) {
// IMPORTANT: Please reset any member data you declared, as
// the same Solution instance will be reused for each test case.
vector<string> sentences;
if (s != "" && dict.size() && this->is_valid(s, dict))
this->find_sentences("", s, dict, sentences);
return sentences;
}
void print_clusters(){
int i = 0;
unordered_set<unordered_set<point*>*>::iterator iter;
for(iter = clusters.begin(); iter != clusters.end(); iter++){
printf("i: %d\n", i);
i++;
unordered_set<point*>* c = *iter;
printf("cluster: %d\n", c->size());
unordered_set<point*>::iterator it;
for(it = c->begin(); it != c->end(); it++){
print_point(*it);
}
}
printf("cluster size: %d\n", clusters.size());
printf("noise: %d\n", noiseCluster->size());
printf("total: %d\n", clusters.size());
}
// constructor 1:
// takes in kmer sets - kmers and potential edges (read edges)
KBF2(const int k, unordered_set<kmer_t> & kmer_set, unordered_set<kmer_t> & edge_set, const unsigned extend_len = 1, const size_t size_factor = 10) : BaseBloomFilter(k, kmer_set.size(), size_factor), extend_len(extend_len){
populate(kmer_set);
getEdges(edge_set);
cerr << "Edges: " << edge_kmers.size() << endl;
extended_check = 0;
edge_check = 0;
edge_pass = 0;
}
vector<string> wordBreak(string s, unordered_set<string> &dict)
{
vector<string> res;
if (dict.size() == 0 || s.size() == 0)
return res;
helper(s, dict, 0, "", res);
return res;
}
vector<string> wordBreak(string s, unordered_set<string>& wordDict) {
vector<string> res;
if (s.length() == 0 || wordDict.size() == 0) //非合法输入
return res;
if (!IswordBreak(s, wordDict)) //先判断是否可分解，其实这步可
return res;
return __wordBreak(s, wordDict); //分解
}
void _loadSpecialSymbols()
{
size_t size = sizeof(SPECIAL_SYMBOL)/sizeof(*SPECIAL_SYMBOL);
for(size_t i = 0; i < size; i ++)
{
_specialSymbols.insert(SPECIAL_SYMBOL[i]);
}
assert(_specialSymbols.size());
}
// constructor actions
void constructKBF(unordered_set<kmer_t> & kmer_set, unordered_set<kmer_t> & edge_set){
populate(kmer_set);
getEdges(edge_set);
cerr << "Edges: " << edge_kmers.size() << endl;
sparse_check = 0;
extended_check = 0;
edge_check = 0;
edge_pass = 0;
}
void print(unordered_set<string> set)
{
cout << "\nSet: \n";
int len = set.size();
for (string s : set)
{
cout << s << "\n";
}
}
