So, I'm working on this project for Comp 272, Data Structures and Algorithms, and before anyone asks I have no one to help me. It's an online program through Athabasca University and for some unknown reason they didn't supply me with a tutor for this course, which is a first... So... Yeah. The question is as follows:
"(20 marks) Exercise 8.2. Illustrate what happens when the sequence 1, 5, 2, 4, 3 is added to an empty ScapegoatTree, and show where the credits described in the proof of Lemma 8.3 go, and how they are used during this sequence of additions."
This is my code, its complete and it compiles:
/*
Name: Westcott.
Assignment: 2, Question 3.
Date: 08-26-2022.
"(20 marks) Exercise 8.2. Illustrate what happens when the sequence 1, 5, 2, 4, 3 is added to an empty
ScapegoatTree, and show where the credits described in the proof of Lemma 8.3 go, and how they are used
during this sequence of additions."
*/
#include <iostream>
using namespace std;
class Node { // Originally I did this with Node as a subclass of sgTree but I found that this
public: // way was easier. This is actually my second attempt, from scratch, at doing this
int data; // problem. First version developed so many bugs I couldn't keep up with them.
Node* left;
Node* right;
Node* parent;
Node() : data(0), parent(NULL), left(NULL), right(NULL) {};
Node(int x) : data(x), parent(NULL), left(NULL), right(NULL) {};
~Node() {}; // Normally I would do a little more work on clean up but... Yea this problem didn't leave me much room.
Node* binarySearch(Node* root, int x); // The Node class only holds binarySearch in addition to its
// constructors/destructor, and of course the Node*'s left, right and parent.
};
class sgTree { // The sgTree keeps track of the root, n (the number of nodes in the tree), and q which is
public: // as Pat put it a 'high water mark'.
Node* root;
int n;
int q;
sgTree() : root(new Node()), n(1), q(1) {}
sgTree(int x) : root(new Node(x)), n(0), q(0) {}
~sgTree() {
delete root;
}
bool add(int x); // The add function is compounded, within it are findDepth and rebuild.
bool removeX(int x); // removeX works, but it didn't have a big part to play in this question,
int findDepth(Node* addedNode); // but I'll include it to maintain our sorted set interface.
void printTree(Node* u, int space) { // This was extra function I wrote to help me problem solve.
cout << "BINARY TREE DISPLAY" << endl; // this version only prints a title and then it calls printTreeSub on line 46.
cout << "________________________________________________\n\n" << endl;
printTreeSub(u, space);
cout << "________________________________________________\n\n" << endl;
}
int printTreeSub(Node* u, int space); // Function definition for this is on line 81.
int storeInArray(Node* ptr, Node* arr[], int i);// this is our function for storing all the elements of a tree in an array.
int size(Node* u); // this is size, defined on line 74.
void rebuild(Node* u); // And rebuild and buildBalanced are the stars of the show, defined on lines 262 and 282
Node* buildBalanced(Node** a, int i, int ns); // just above the main() funciton.
};
int log32(int q) { // As you can see there's two versions of this function.
int c = 0; // this is supposed to return the log of n to base 3/2.
while (q != 0) { // The version below I got from this website:
q = q / 2; // https://www.geeksforgeeks.org/scapegoat-tree-set-1-introduction-insertion/
c++; // It works fine but I prefer the one I wrote.
} // this is a much simpler function. It just divides q until its zero
return c; // and increments c on each division. Its not exact but it is based on what Pat said
} // in this lecture: https://www.youtube.com/watch?v=OGNUoDPVRCc&t=4852s
/*
static int const log32(int n)
{
double const log23 = 2.4663034623764317;
return (int)ceil(log23 * log(n));
}
*/
int sgTree::size(Node* u) {
if (u == NULL) {
return 0;
}
return 1 + size(u->left) + size(u->right); // Recursion in size();
}
int sgTree::printTreeSub(Node* u, int space) { // Here is my strange print function
if (u == NULL) return space; // I say strange because I'm not even 100% sure
space--; // how I got it to work. The order itself I worked out, but I built it
space -= printTreeSub(u->left, space); // and, originally, got a half decent tree, but then I just kept playing
if (u->right == NULL && u->left == NULL) { // around with increments, decrements, and returned values
cout << "\n\n\n" << u->data << "\n\n\n" << endl; // of space until it just sort of came together.
return 1; // Basically it prints the left most Node first and then prints every node
} // beneath that using recursion. I realized that by setting the for loop
for (int i = space; i >= 0; i--) { // on line 89 I could imitate different nodes having different heights in
cout << " "; // the tree. I figured that using n as an input I could take advantage of
} // the recursion to get an accurate tree. That much I understand.
cout << " " << u->data << "'s children are: "; // But it didn't work out quite how I wanted it to so I just kept playing
if (u->left != NULL) { // with space increments and decrements on different sides of the tree until
cout << u->left->data; // I got something pretty good.
}
else {
cout << "NULL";
}
if (u->right != NULL) {
cout << " and " << u->right->data;
}
else {
cout << " NULL";
}
cout << "\n\n" << endl;
space--;
space -= printTreeSub(u->right, space);
return 1;
}
int sgTree::storeInArray(Node* ptr, Node* a[], int i) { // This function took me a while to figure out.
if (ptr == NULL) { // The recursive insertions of values using i, when
return i; // i is defined by the very same recursion, makes this
} // a bit of a challenge to get your head around.
i = storeInArray(ptr->left, a, i); // Basically its just taking advantage on an inOrder
a[i] = ptr; // transversal to get the values stored into the array
i++; // in order from least to greatest.
return storeInArray(ptr->right, a, i);
}
Node* Node::binarySearch(Node* root, int x) { // I covered this in another question.
if (root->data == x) {
return root;
}
else if (x < root->data) {
if (root->left == NULL) {
return root;
}
return binarySearch(root->left, x);
}
else if (x > root->data) {
if (root->right == NULL) {
return root;
}
return binarySearch(root->right, x);
}
}
bool sgTree::add(int x) { // The add function itself isn't too difficult.
Node* addedNode = new Node(x); // We make a Node using our data, then we search for that Node
Node* parent = root->binarySearch(root, x); // in the tree. I amended binarySearch to return the parent
addedNode->parent = parent; // if it hits a NULL child, on lines 127 and 133.
if (x < parent->data) { // That way the new Node can just go into the returned parents child
parent->left = addedNode; // here is where we choose whether it enters the left or the right.
}
else if (x > parent->data) {
parent->right = addedNode;
}
int h = findDepth(addedNode); // We run findDepth() on the addedNode. I realize that this probably should
// have been a part of the binarySearch, it means we go down
if (h > log32(q)) { // the tree twice instead of once. I did look at changing binarySearch into searchAndDepth
// having binarySearch return an int for the height isn't a problem, but then that would
// mess up removeX and, I don't know. What's more important?
Node* w = addedNode->parent; // If this were going to be a database hosting millions of pieces of data I would give
while (3 * size(w) < 2 * size(w->parent)) { // that alot more consideration but, this is just an exercise after all so...
w = w->parent; // From there, we compare our height to the value output by log32(q) on line 152.
}
rebuild(w); // This expression 3 * size(w) < 2 * size(w->parent) is the formula on page 178 rewritten
//rebuild(root); // as a cross multiplication, clever. It keeps going up the tree until we find the scapegoat w.
// This is a much nicer result.
//See line 311.
} // Now, this is where my problems began. Pat says that this line should read: rebuild(w->parent);
n++; // but when I do that I get an error when w is the root. Because then w->parent is NULL. And in that case
q++; // line 258 throws an error because we're trying to set p equal to NULL's parent. It's not there.
return true; // So my work around was to just offset this by one and send rebuild(w). But that doesn't seem
} // to balance the tree just right. In fact, the best tree results when we replace w with root.
// and just rebalance the whole tree. But in any case, we increment n and q and lets pick this up on line 256.
int sgTree::findDepth(Node* addedNode) {
int d = 0;
while (addedNode != root) {
addedNode = addedNode->parent;
d++;
}
return d;
}
bool sgTree::removeX(int x) {
Node* u = root->binarySearch(root, x);
if (u->left == NULL && u->right == NULL) {
if (u == u->parent->left) {
u->parent->left = NULL;
}
if (u == u->parent->right) {
u->parent->right = NULL;
}
cout << u->data << " deleted" << endl;
n--;
delete u;
return true;
}
if (u->left != NULL && u->right == NULL) {
if (u->parent->left = u) {
u->parent->left = u->left;
}
else if (u->parent->right = u) {
u->parent->right = u->left;
}
cout << u->data << " deleted" << endl;
n--;
delete u;
return true;
}
if (u->left == NULL && u->right != NULL) {
if (u == u->parent->left) {
u->parent->left = u->right;
u->right->parent = u->parent;
}
else if (u == u->parent->right) {
u->parent->right = u->right;
u->right->parent = u->parent;
}
cout << u->data << " deleted" << endl;
n--;
delete u;
return true;
}
if (u->left != NULL && u->right != NULL) {
Node* X = u->right;
if (X->left == NULL) {
X->left = u->left;
if (u->parent != NULL) {
if (u->parent->right == u) {
u->parent->right == X;
}
else if (u->parent->left == u) {
u->parent->left = X;
}
}
else {
root = X;
}
X->parent = u->parent;
cout << u->data << " deleted" << endl;
n--;
delete u;
return true;
}
while (X->left != NULL) {
X = X->left;
}
X->parent->left = NULL;
X->left = u->left;
X->right = u->right;
if (u->parent != NULL) {
X->parent = u->parent;
}
cout << u->data << " deleted" << endl;
n--;
root = X;
delete u;
return true;
}
}
void sgTree::rebuild(Node* u) {
int ns = size(u); // Everything is pretty kosher here. Just get the number of nodes in the subtree.
Node* p = u->parent; // Originally I had n here instead of ns and... I don't want to talk about how long it took me to find that mistake...
/* It's funny because while writing the comments for this I'm like "Oh, hang on, if I just push the definition of p behind the if statement on line 262
and evaluate for whether or not u is NULL instead of p, that should solve all my problems! Yea, no, it doesn't. Because then for some reason it tries rebalancing
empty tree and... Yea I just have to stop myself from trying to fix this because everytime I do I get caught in an infinite loop of me chasing my tail in errors.
I think a solution could be found in buildBalanced, and I literally went through that function line by line, trying to comprehend a work around. I've included at
a photograph of that white board. Yea this is the code that Pat gave us... and its garbage. It doesn't work. Maybe its a C++ thing, I don't know... But I'm
getting frustrated again so I'm going to stop thinking about this part RIGHT HERE, and move on LOL*/
Node** a = new Node * [ns]; // a Node pointer-pointer array... again, another fine piece of code from the textbook. Sorry, trying to stay positive here.
storeInArray(u, a, 0); // See Line 112
if (p == NULL) { // Okay, once we have our array we use buildBalanced to rebuild the subtree with respect to which
root = buildBalanced(a, 0, ns); // child u is relative to its parent.
root->parent = NULL; // See line 281 for buildBalanced().
}
else if (p->right == u) {
p->right = buildBalanced(a, 0, ns);
p->right->parent = p;
}
else {
p->left = buildBalanced(a, 0, ns);
p->left->parent = p;
}
}
Node* sgTree::buildBalanced(Node** a, int i, int ns) { // This is without a doubt one of the hardest functions I've ever had
if (ns == 0) { // the displeasure of trying to understand... Trying to stay positive.
return NULL; // I've gone through it, in a line by line implementation of the array:
} // a[] = {1, 2, 3, 4, 5, 6, 7, 8, 9, 10} you can find that analysis in
int m = ns / 2; // the photo buildBalanced_Analysis.
a[i + m]->left = buildBalanced(a, i, m); // As confusing as it is, I have to admit that it is a beautiful function.
if (a[i + m]->left != NULL) { // It basically uses the two integers i and m to simultaneously
a[i + m]->left->parent = a[i + m]; // regulate the organization of the new tree and to specifically
} // grab the right value from the array when its needed.
a[i + m]->right = buildBalanced(a, i + m + 1, ns - m - 1); // but trying to map this out didn't help me to solve the issues I've been having.
if (a[i + m]->right != NULL) {
a[i + m]->right->parent = a[i + m];
}
return a[i + m];
}
int main() {
sgTree newTree(1);
int a[] = { 5, 2, 4, 3 };
for (int i = 0; i < (sizeof(a) / sizeof(a[0])); i++) {
newTree.add(a[i]);
}
newTree.printTree(newTree.root, newTree.n);
/*
This is a nice test, when paired with rebuild(root), that too me is the only thing that approaches redeeming this whole question.
sgTree newTreeB(1);
int b[] = { 2, 3, 4, 5, 6, 7, 8, 9, 10 };
for (int i = 0; i < (sizeof(b) / sizeof(b[0])); i++) {
newTreeB.add(b[i]);
}
newTreeB.printTree(newTreeB.root, newTreeB.n);
*/
}
Now the issue itself is not that hard to understand. My tree should look like this:
But instead, it looks like this, with 5 at the root and the values 1 and 4 as the leaves:
I'm confident that the problem lives somewhere around line 159 and in those first few calls to buildBalanced. The comments in the code itself elaborate more on the issue. I've spent days just pouring over this trying everything I can think of to make it work and... Yeah... I just can't figure it out.
I am trying to write a simple nonogram solver, in a kind of bruteforce way, but I am stuck on a relatively easy task. Let's say I have a row with clues [2,3] that has a length of 10
so the solutions are:
$$-$$$----
$$--$$$---
$$---$$$--
$$----$$$-
$$-----$$$
-$$----$$$
--$$---$$$
---$$--$$$
----$$-$$$
-$$---$$$-
--$$-$$$--
I want to find all the possible solutions for a row
I know that I have to consider each block separately, and each block will have an availible space of n-(sum of remaining blocks length + number of remaining blocks) but I do not know how to progress from here
Well, this question already have a good answer, so think of this one more as an advertisement of python's prowess.
def place(blocks,total):
if not blocks: return ["-"*total]
if blocks[0]>total: return []
starts = total-blocks[0] #starts = 2 means possible starting indexes are [0,1,2]
if len(blocks)==1: #this is special case
return [("-"*i+"$"*blocks[0]+"-"*(starts-i)) for i in range(starts+1)]
ans = []
for i in range(total-blocks[0]): #append current solutions
for sol in place(blocks[1:],starts-i-1): #with all possible other solutiona
ans.append("-"*i+"$"*blocks[0]+"-"+sol)
return ans
To test it:
for i in place([2,3,2],12):
print(i)
Which produces output like:
$$-$$$-$$---
$$-$$$--$$--
$$-$$$---$$-
$$-$$$----$$
$$--$$$-$$--
$$--$$$--$$-
$$--$$$---$$
$$---$$$-$$-
$$---$$$--$$
$$----$$$-$$
-$$-$$$-$$--
-$$-$$$--$$-
-$$-$$$---$$
-$$--$$$-$$-
-$$--$$$--$$
-$$---$$$-$$
--$$-$$$-$$-
--$$-$$$--$$
--$$--$$$-$$
---$$-$$$-$$
This is what i got:
#include <iostream>
#include <vector>
#include <string>
using namespace std;
typedef std::vector<bool> tRow;
void printRow(tRow row){
for (bool i : row){
std::cout << ((i) ? '$' : '-');
}
std::cout << std::endl;
}
int requiredCells(const std::vector<int> nums){
int sum = 0;
for (int i : nums){
sum += (i + 1); // The number + the at-least-one-cell gap at is right
}
return (sum == 0) ? 0 : sum - 1; // The right-most number don't need any gap
}
bool appendRow(tRow init, const std::vector<int> pendingNums, unsigned int rowSize, std::vector<tRow> &comb){
if (pendingNums.size() <= 0){
comb.push_back(init);
return false;
}
int cellsRequired = requiredCells(pendingNums);
if (cellsRequired > rowSize){
return false; // There are no combinations
}
tRow prefix;
int gapSize = 0;
std::vector<int> pNumsAux = pendingNums;
pNumsAux.erase(pNumsAux.begin());
unsigned int space = rowSize;
while ((gapSize + cellsRequired) <= rowSize){
space = rowSize;
space -= gapSize;
prefix.clear();
prefix = init;
for (int i = 0; i < gapSize; ++i){
prefix.push_back(false);
}
for (int i = 0; i < pendingNums[0]; ++i){
prefix.push_back(true);
space--;
}
if (space > 0){
prefix.push_back(false);
space--;
}
appendRow(prefix, pNumsAux, space, comb);
++gapSize;
}
return true;
}
std::vector<tRow> getCombinations(const std::vector<int> row, unsigned int rowSize) {
std::vector<tRow> comb;
tRow init;
appendRow(init, row, rowSize, comb);
return comb;
}
int main(){
std::vector<int> row = { 2, 3 };
auto ret = getCombinations(row, 10);
for (tRow r : ret){
while (r.size() < 10)
r.push_back(false);
printRow(r);
}
return 0;
}
And my output is:
$$-$$$----
$$--$$$---
$$---$$$--
$$----$$$--
$$-----$$$
-$$-$$$----
-$$--$$$--
-$$---$$$-
-$$----$$$-
--$$-$$$--
--$$--$$$-
--$$---$$$
---$$-$$$-
---$$--$$$
----$$-$$$
For sure, this must be absolutely improvable.
Note: i did't test it more than already written case
Hope it works for you
I have K objects (K is small, e.g. 2 or 5) and I need to iterate over them N times in random order where N may be large. I need to iterate in a foreach loop and for this I should provide an iterator.
So far I created a std::vector of my K objects copied accordingly, so the size of vector is N and now I use begin() and end() provided by that vector. I use std::shuffle() to randomize the vector and this takes up to 20% of running time. I think it would be better (and more elegant, anyways) to write a custom iterator that returns one of my object in random order without creating the helping vector of size N. But how to do this?
It is obvious that your iterator must:
Store pointer to original vector or array: m_pSource
Store the count of requests (to be able to stop): m_nOutputCount
Use random number generator (see random): m_generator
Some iterator must be treated as end iterator: m_nOutputCount == 0
I've made an example for type int:
#include <iostream>
#include <random>
class RandomIterator: public std::iterator<std::forward_iterator_tag, int>
{
public:
//Creates "end" iterator
RandomIterator() : m_pSource(nullptr), m_nOutputCount(0), m_nCurValue(0) {}
//Creates random "start" iterator
RandomIterator(const std::vector<int> &source, int nOutputCount) :
m_pSource(&source), m_nOutputCount(nOutputCount + 1),
m_distribution(0, source.size() - 1)
{
operator++(); //make new random value
}
int operator* () const
{
return m_nCurValue;
}
RandomIterator operator++()
{
if (m_nOutputCount == 0)
return *this;
--m_nOutputCount;
static std::default_random_engine generator;
static bool bWasGeneratorInitialized = false;
if (!bWasGeneratorInitialized)
{
std::random_device rd; //expensive calls
generator.seed(rd());
bWasGeneratorInitialized = true;
}
m_nCurValue = m_pSource->at(m_distribution(generator));
return *this;
}
RandomIterator operator++(int)
{ //postincrement
RandomIterator tmp = *this;
++*this;
return tmp;
}
int operator== (const RandomIterator& other) const
{
if (other.m_nOutputCount == 0)
return m_nOutputCount == 0; //"end" iterator
return m_pSource == other.m_pSource;
}
int operator!= (const RandomIterator& other) const
{
return !(*this == other);
}
private:
const std::vector<int> *m_pSource;
int m_nOutputCount;
int m_nCurValue;
std::uniform_int_distribution<std::vector<int>::size_type> m_distribution;
};
int main()
{
std::vector<int> arrTest{ 1, 2, 3, 4, 5 };
std::cout << "Original =";
for (auto it = arrTest.cbegin(); it != arrTest.cend(); ++it)
std::cout << " " << *it;
std::cout << std::endl;
RandomIterator rndEnd;
std::cout << "Random =";
for (RandomIterator it(arrTest, 15); it != rndEnd; ++it)
std::cout << " " << *it;
std::cout << std::endl;
}
The output is:
Original = 1 2 3 4 5
Random = 1 4 1 3 2 4 5 4 2 3 4 3 1 3 4
You can easily convert it into a template. And make it to accept any random access iterator.
I just want to increment Dmitriy answer, because reading your question, it seems that you want that every time that you iterate your newly-created-and-shuffled collection the items should not repeat and Dmitryi´s answer does have repetition. So both iterators are useful.
template <typename T>
struct RandomIterator : public std::iterator<std::forward_iterator_tag, typename T::value_type>
{
RandomIterator() : Data(nullptr)
{
}
template <typename G>
RandomIterator(const T &source, G& g) : Data(&source)
{
Order = std::vector<int>(source.size());
std::iota(begin(Order), end(Order), 0);
std::shuffle(begin(Order), end(Order), g);
OrderIterator = begin(Order);
OrderIteratorEnd = end(Order);
}
const typename T::value_type& operator* () const noexcept
{
return (*Data)[*OrderIterator];
}
RandomIterator<T>& operator++() noexcept
{
++OrderIterator;
return *this;
}
int operator== (const RandomIterator<T>& other) const noexcept
{
if (Data == nullptr && other.Data == nullptr)
{
return 1;
}
else if ((OrderIterator == OrderIteratorEnd) && (other.Data == nullptr))
{
return 1;
}
return 0;
}
int operator!= (const RandomIterator<T>& other) const noexcept
{
return !(*this == other);
}
private:
const T *Data;
std::vector<int> Order;
std::vector<int>::iterator OrderIterator;
std::vector<int>::iterator OrderIteratorEnd;
};
template <typename T, typename G>
RandomIterator<T> random_begin(const T& v, G& g) noexcept
{
return RandomIterator<T>(v, g);
}
template <typename T>
RandomIterator<T> random_end(const T& v) noexcept
{
return RandomIterator<T>();
}
whole code at
http://coliru.stacked-crooked.com/a/df6ce482bbcbafcf or
https://github.com/xunilrj/sandbox/blob/master/sources/random_iterator/source/random_iterator.cpp
Implementing custom iterators can be very tricky so I tried to follow some tutorials, but please let me know if something have passed:
http://web.stanford.edu/class/cs107l/handouts/04-Custom-Iterators.pdf
https://codereview.stackexchange.com/questions/74609/custom-iterator-for-a-linked-list-class
Operator overloading
I think that the performance is satisfactory:
On the Coliru:
<size>:<time for 10 iterations>
1:0.000126582
10:3.5179e-05
100:0.000185914
1000:0.00160409
10000:0.0161338
100000:0.180089
1000000:2.28161
Off course it has the price to allocate a whole vector with the orders, that is the same size of the original vector.
An improvement would be to pre-allocate the Order vector if for some reason you have to random iterate very often and allow the iterator to use this pre-allocated vector, or some form of reset() in the iterator.
I was recently brushing up on some fundamentals and found merge sorting a linked list to be a pretty good challenge. If you have a good implementation then show it off here.
Wonder why it should be big challenge as it is stated here, here is a straightforward implementation in Java with out any "clever tricks".
//The main function
public static Node merge_sort(Node head)
{
if(head == null || head.next == null)
return head;
Node middle = getMiddle(head); //get the middle of the list
Node left_head = head;
Node right_head = middle.next;
middle.next = null; //split the list into two halfs
return merge(merge_sort(left_head), merge_sort(right_head)); //recurse on that
}
//Merge subroutine to merge two sorted lists
public static Node merge(Node a, Node b)
{
Node dummyHead = new Node();
for(Node current = dummyHead; a != null && b != null; current = current.next;)
{
if(a.data <= b.data)
{
current.next = a;
a = a.next;
}
else
{
current.next = b;
b = b.next;
}
}
dummyHead.next = (a == null) ? b : a;
return dummyHead.next;
}
//Finding the middle element of the list for splitting
public static Node getMiddle(Node head)
{
if(head == null)
return head;
Node slow = head, fast = head;
while(fast.next != null && fast.next.next != null)
{
slow = slow.next;
fast = fast.next.next;
}
return slow;
}
A simpler/clearer implementation might be the recursive implementation, from which the NLog(N) execution time is more clear.
typedef struct _aList {
struct _aList* next;
struct _aList* prev; // Optional.
// some data
} aList;
aList* merge_sort_list_recursive(aList *list,int (*compare)(aList *one,aList *two))
{
// Trivial case.
if (!list || !list->next)
return list;
aList *right = list,
*temp = list,
*last = list,
*result = 0,
*next = 0,
*tail = 0;
// Find halfway through the list (by running two pointers, one at twice the speed of the other).
while (temp && temp->next)
{
last = right;
right = right->next;
temp = temp->next->next;
}
// Break the list in two. (prev pointers are broken here, but we fix later)
last->next = 0;
// Recurse on the two smaller lists:
list = merge_sort_list_recursive(list, compare);
right = merge_sort_list_recursive(right, compare);
// Merge:
while (list || right)
{
// Take from empty lists, or compare:
if (!right) {
next = list;
list = list->next;
} else if (!list) {
next = right;
right = right->next;
} else if (compare(list, right) < 0) {
next = list;
list = list->next;
} else {
next = right;
right = right->next;
}
if (!result) {
result=next;
} else {
tail->next=next;
}
next->prev = tail; // Optional.
tail = next;
}
return result;
}
NB: This has a Log(N) storage requirement for the recursion. Performance should be roughly comparable with the other strategy I posted. There is a potential optimisation here by running the merge loop while (list && right), and simple appending the remaining list (since we don't really care about the end of the lists; knowing that they're merged suffices).
Heavily based on the EXCELLENT code from: http://www.chiark.greenend.org.uk/~sgtatham/algorithms/listsort.html
Trimmed slightly, and tidied:
typedef struct _aList {
struct _aList* next;
struct _aList* prev; // Optional.
// some data
} aList;
aList *merge_sort_list(aList *list,int (*compare)(aList *one,aList *two))
{
int listSize=1,numMerges,leftSize,rightSize;
aList *tail,*left,*right,*next;
if (!list || !list->next) return list; // Trivial case
do { // For each power of two<=list length
numMerges=0,left=list;tail=list=0; // Start at the start
while (left) { // Do this list_len/listSize times:
numMerges++,right=left,leftSize=0,rightSize=listSize;
// Cut list into two halves (but don't overrun)
while (right && leftSize<listSize) leftSize++,right=right->next;
// Run through the lists appending onto what we have so far.
while (leftSize>0 || (rightSize>0 && right)) {
// Left empty, take right OR Right empty, take left, OR compare.
if (!leftSize) {next=right;right=right->next;rightSize--;}
else if (!rightSize || !right) {next=left;left=left->next;leftSize--;}
else if (compare(left,right)<0) {next=left;left=left->next;leftSize--;}
else {next=right;right=right->next;rightSize--;}
// Update pointers to keep track of where we are:
if (tail) tail->next=next; else list=next;
// Sort prev pointer
next->prev=tail; // Optional.
tail=next;
}
// Right is now AFTER the list we just sorted, so start the next sort there.
left=right;
}
// Terminate the list, double the list-sort size.
tail->next=0,listSize<<=1;
} while (numMerges>1); // If we only did one merge, then we just sorted the whole list.
return list;
}
NB: This is O(NLog(N)) guaranteed, and uses O(1) resources (no recursion, no stack, nothing).
One interesting way is to maintain a stack, and only merge if the list on the stack has the same number of elements, and otherwise push the list, until you run out of elements in the incoming list, and then merge up the stack.
The simplest is from
Gonnet + Baeza Yates Handbook of Algorithms. You call it with the number of sorted elements you want, which recursively gets bisected until it reaches a request for a size one list which you then just peel off the front of the original list. These all get merged up into a full sized sorted list.
[Note that the cool stack-based one in the first post is called the Online Mergesort and it gets the tiniest mention in an exercise in Knuth Vol 3]
Here's an alternative recursive version. This does not need to step along the list to split it: we supply a pointer to a head element (which is not part of the sort) and a length, and the recursive function returns a pointer to the end of the sorted list.
element* mergesort(element *head,long lengtho)
{
long count1=(lengtho/2), count2=(lengtho-count1);
element *next1,*next2,*tail1,*tail2,*tail;
if (lengtho<=1) return head->next; /* Trivial case. */
tail1 = mergesort(head,count1);
tail2 = mergesort(tail1,count2);
tail=head;
next1 = head->next;
next2 = tail1->next;
tail1->next = tail2->next; /* in case this ends up as the tail */
while (1) {
if(cmp(next1,next2)<=0) {
tail->next=next1; tail=next1;
if(--count1==0) { tail->next=next2; return tail2; }
next1=next1->next;
} else {
tail->next=next2; tail=next2;
if(--count2==0) { tail->next=next1; return tail1; }
next2=next2->next;
}
}
}
I'd been obsessing over optimizing clutter for this algorithm and below is what I've finally arrived at. Lot of other code on Internet and StackOverflow is horribly bad. There are people trying to get middle point of the list, doing recursion, having multiple loops for left over nodes, maintaining counts of ton of things - ALL of which is unnecessary. MergeSort naturally fits to linked list and algorithm can be beautiful and compact but it's not trivial to get to that state.
Below code maintains minimum number of variables and has minimum number of logical steps needed for the algorithm (i.e. without making code unmaintainable/unreadable) as far as I know. However I haven't tried to minimize LOC and kept as much white space as necessary to keep things readable. I've tested this code through fairly rigorous unit tests.
Note that this answer combines few techniques from other answer https://stackoverflow.com/a/3032462/207661. While the code is in C#, it should be trivial to convert in to C++, Java, etc.
SingleListNode<T> SortLinkedList<T>(SingleListNode<T> head) where T : IComparable<T>
{
int blockSize = 1, blockCount;
do
{
//Maintain two lists pointing to two blocks, left and right
SingleListNode<T> left = head, right = head, tail = null;
head = null; //Start a new list
blockCount = 0;
//Walk through entire list in blocks of size blockCount
while (left != null)
{
blockCount++;
//Advance right to start of next block, measure size of left list while doing so
int leftSize = 0, rightSize = blockSize;
for (;leftSize < blockSize && right != null; ++leftSize)
right = right.Next;
//Merge two list until their individual ends
bool leftEmpty = leftSize == 0, rightEmpty = rightSize == 0 || right == null;
while (!leftEmpty || !rightEmpty)
{
SingleListNode<T> smaller;
//Using <= instead of < gives us sort stability
if (rightEmpty || (!leftEmpty && left.Value.CompareTo(right.Value) <= 0))
{
smaller = left; left = left.Next; --leftSize;
leftEmpty = leftSize == 0;
}
else
{
smaller = right; right = right.Next; --rightSize;
rightEmpty = rightSize == 0 || right == null;
}
//Update new list
if (tail != null)
tail.Next = smaller;
else
head = smaller;
tail = smaller;
}
//right now points to next block for left
left = right;
}
//terminate new list, take care of case when input list is null
if (tail != null)
tail.Next = null;
//Lg n iterations
blockSize <<= 1;
} while (blockCount > 1);
return head;
}
Points of interest
There is no special handling for cases like null list of list of 1 etc required. These cases "just works".
Lot of "standard" algorithms texts have two loops to go over leftover elements to handle the case when one list is shorter than other. Above code eliminates need for it.
We make sure sort is stable
The inner while loop which is a hot spot evaluates 3 expressions per iteration on average which I think is minimum one can do.
Update: #ideasman42 has translated above code to C/C++ along with suggestions for fixing comments and bit more improvement. Above code is now up to date with these.
I decided to test the examples here, and also one more approach, originally written by Jonathan Cunningham in Pop-11. I coded all the approaches in C# and did a comparison with a range of different list sizes. I compared the Mono eglib approach by Raja R Harinath, the C# code by Shital Shah, the Java approach by Jayadev, the recursive and non-recursive versions by David Gamble, the first C code by Ed Wynn (this crashed with my sample dataset, I didn't debug), and Cunningham's version. Full code here: https://gist.github.com/314e572808f29adb0e41.git.
Mono eglib is based on a similar idea to Cunningham's and is of comparable speed, unless the list happens to be sorted already, in which case Cunningham's approach is much much faster (if its partially sorted, the eglib is slightly faster). The eglib code uses a fixed table to hold the merge sort recursion, whereas Cunningham's approach works by using increasing levels of recursion - so it starts out using no recursion, then 1-deep recursion, then 2-deep recursion and so on, according to how many steps are needed to do the sort. I find the Cunningham code a little easier to follow and there is no guessing involved in how big to make the recursion table, so it gets my vote. The other approaches I tried from this page were two or more times slower.
Here is the C# port of the Pop-11 sort:
/// <summary>
/// Sort a linked list in place. Returns the sorted list.
/// Originally by Jonathan Cunningham in Pop-11, May 1981.
/// Ported to C# by Jon Meyer.
/// </summary>
public class ListSorter<T> where T : IComparable<T> {
SingleListNode<T> workNode = new SingleListNode<T>(default(T));
SingleListNode<T> list;
/// <summary>
/// Sorts a linked list. Returns the sorted list.
/// </summary>
public SingleListNode<T> Sort(SingleListNode<T> head) {
if (head == null) throw new NullReferenceException("head");
list = head;
var run = GetRun(); // get first run
// As we progress, we increase the recursion depth.
var n = 1;
while (list != null) {
var run2 = GetSequence(n);
run = Merge(run, run2);
n++;
}
return run;
}
// Get the longest run of ordered elements from list.
// The run is returned, and list is updated to point to the
// first out-of-order element.
SingleListNode<T> GetRun() {
var run = list; // the return result is the original list
var prevNode = list;
var prevItem = list.Value;
list = list.Next; // advance to the next item
while (list != null) {
var comp = prevItem.CompareTo(list.Value);
if (comp > 0) {
// reached end of sequence
prevNode.Next = null;
break;
}
prevItem = list.Value;
prevNode = list;
list = list.Next;
}
return run;
}
// Generates a sequence of Merge and GetRun() operations.
// If n is 1, returns GetRun()
// If n is 2, returns Merge(GetRun(), GetRun())
// If n is 3, returns Merge(Merge(GetRun(), GetRun()),
// Merge(GetRun(), GetRun()))
// and so on.
SingleListNode<T> GetSequence(int n) {
if (n < 2) {
return GetRun();
} else {
n--;
var run1 = GetSequence(n);
if (list == null) return run1;
var run2 = GetSequence(n);
return Merge(run1, run2);
}
}
// Given two ordered lists this returns a list that is the
// result of merging the two lists in-place (modifying the pairs
// in list1 and list2).
SingleListNode<T> Merge(SingleListNode<T> list1, SingleListNode<T> list2) {
// we reuse a single work node to hold the result.
// Simplifies the number of test cases in the code below.
var prevNode = workNode;
while (true) {
if (list1.Value.CompareTo(list2.Value) <= 0) {
// list1 goes first
prevNode.Next = list1;
prevNode = list1;
if ((list1 = list1.Next) == null) {
// reached end of list1 - join list2 to prevNode
prevNode.Next = list2;
break;
}
} else { // same but for list2
prevNode.Next = list2;
prevNode = list2;
if ((list2 = list2.Next) == null) {
prevNode.Next = list1;
break;
}
}
}
// the result is in the back of the workNode
return workNode.Next;
}
}
Here is my implementation of Knuth's "List merge sort" (Algorithm 5.2.4L from Vol.3 of TAOCP, 2nd ed.). I'll add some comments at the end, but here's a summary:
On random input, it runs a bit faster than Simon Tatham's code (see Dave Gamble's non-recursive answer, with a link) but a bit slower than Dave Gamble's recursive code. It's harder to understand than either. At least in my implementation, it requires each element to have TWO pointers to elements. (An alternative would be one pointer and a boolean flag.) So, it's probably not a useful approach. However, one distinctive point is that it runs very fast if the input has long stretches that are already sorted.
element *knuthsort(element *list)
{ /* This is my attempt at implementing Knuth's Algorithm 5.2.4L "List merge sort"
from Vol.3 of TAOCP, 2nd ed. */
element *p, *pnext, *q, *qnext, head1, head2, *s, *t;
if(!list) return NULL;
L1: /* This is the clever L1 from exercise 12, p.167, solution p.647. */
head1.next=list;
t=&head2;
for(p=list, pnext=p->next; pnext; p=pnext, pnext=p->next) {
if( cmp(p,pnext) > 0 ) { t->next=NULL; t->spare=pnext; t=p; }
}
t->next=NULL; t->spare=NULL; p->spare=NULL;
head2.next=head2.spare;
L2: /* begin a new pass: */
t=&head2;
q=t->next;
if(!q) return head1.next;
s=&head1;
p=s->next;
L3: /* compare: */
if( cmp(p,q) > 0 ) goto L6;
L4: /* add p onto the current end, s: */
if(s->next) s->next=p; else s->spare=p;
s=p;
if(p->next) { p=p->next; goto L3; }
else p=p->spare;
L5: /* complete the sublist by adding q and all its successors: */
s->next=q; s=t;
for(qnext=q->next; qnext; q=qnext, qnext=q->next);
t=q; q=q->spare;
goto L8;
L6: /* add q onto the current end, s: */
if(s->next) s->next=q; else s->spare=q;
s=q;
if(q->next) { q=q->next; goto L3; }
else q=q->spare;
L7: /* complete the sublist by adding p and all its successors: */
s->next=p;
s=t;
for(pnext=p->next; pnext; p=pnext, pnext=p->next);
t=p; p=p->spare;
L8: /* is this end of the pass? */
if(q) goto L3;
if(s->next) s->next=p; else s->spare=p;
t->next=NULL; t->spare=NULL;
goto L2;
}
There's a non-recursive linked-list mergesort in mono eglib.
The basic idea is that the control-loop for the various merges parallels the bitwise-increment of a binary integer. There are O(n) merges to "insert" n nodes into the merge tree, and the rank of those merges corresponds to the binary digit that gets incremented. Using this analogy, only O(log n) nodes of the merge-tree need to be materialized into a temporary holding array.
A tested, working C++ version of single linked list, based on the highest voted answer.
singlelinkedlist.h:
#pragma once
#include <stdexcept>
#include <iostream>
#include <initializer_list>
namespace ythlearn{
template<typename T>
class Linkedlist{
public:
class Node{
public:
Node* next;
T elem;
};
Node head;
int _size;
public:
Linkedlist(){
head.next = nullptr;
_size = 0;
}
Linkedlist(std::initializer_list<T> init_list){
head.next = nullptr;
_size = 0;
for(auto s = init_list.begin(); s!=init_list.end(); s++){
push_left(*s);
}
}
int size(){
return _size;
}
bool isEmpty(){
return size() == 0;
}
bool isSorted(){
Node* n_ptr = head.next;
while(n_ptr->next != nullptr){
if(n_ptr->elem > n_ptr->next->elem)
return false;
n_ptr = n_ptr->next;
}
return true;
}
Linkedlist& push_left(T elem){
Node* n = new Node;
n->elem = elem;
n->next = head.next;
head.next = n;
++_size;
return *this;
}
void print(){
Node* loopPtr = head.next;
while(loopPtr != nullptr){
std::cout << loopPtr->elem << " ";
loopPtr = loopPtr->next;
}
std::cout << std::endl;
}
void call_merge(){
head.next = merge_sort(head.next);
}
Node* merge_sort(Node* n){
if(n == nullptr || n->next == nullptr)
return n;
Node* middle = getMiddle(n);
Node* left_head = n;
Node* right_head = middle->next;
middle->next = nullptr;
return merge(merge_sort(left_head), merge_sort(right_head));
}
Node* getMiddle(Node* n){
if(n == nullptr)
return n;
Node* slow, *fast;
slow = fast = n;
while(fast->next != nullptr && fast->next->next != nullptr){
slow = slow->next;
fast = fast->next->next;
}
return slow;
}
Node* merge(Node* a, Node* b){
Node dummyHead;
Node* current = &dummyHead;
while(a != nullptr && b != nullptr){
if(a->elem < b->elem){
current->next = a;
a = a->next;
}else{
current->next = b;
b = b->next;
}
current = current->next;
}
current->next = (a == nullptr) ? b : a;
return dummyHead.next;
}
Linkedlist(const Linkedlist&) = delete;
Linkedlist& operator=(const Linkedlist&) const = delete;
~Linkedlist(){
Node* node_to_delete;
Node* ptr = head.next;
while(ptr != nullptr){
node_to_delete = ptr;
ptr = ptr->next;
delete node_to_delete;
}
}
};
}
main.cpp:
#include <iostream>
#include <cassert>
#include "singlelinkedlist.h"
using namespace std;
using namespace ythlearn;
int main(){
Linkedlist<int> l = {3,6,-5,222,495,-129,0};
l.print();
l.call_merge();
l.print();
assert(l.isSorted());
return 0;
}
Simplest Java Implementation:
Time Complexity: O(nLogn) n = number of nodes. Each iteration through the linked list doubles the size of the sorted smaller linked lists. For example, after the first iteration, the linked list will be sorted into two halves. After the second iteration, the linked list will be sorted into four halves. It will keep sorting up to the size of the linked list. This will take O(logn) doublings of the small linked lists' sizes to reach the original linked list size. The n in nlogn is there because each iteration of the linked list will take time proportional to the number of nodes in the originial linked list.
class Node {
int data;
Node next;
Node(int d) {
data = d;
}
}
class LinkedList {
Node head;
public Node mergesort(Node head) {
if(head == null || head.next == null) return head;
Node middle = middle(head), middle_next = middle.next;
middle.next = null;
Node left = mergesort(head), right = mergesort(middle_next), node = merge(left, right);
return node;
}
public Node merge(Node first, Node second) {
Node node = null;
if (first == null) return second;
else if (second == null) return first;
else if (first.data <= second.data) {
node = first;
node.next = merge(first.next, second);
} else {
node = second;
node.next = merge(first, second.next);
}
return node;
}
public Node middle(Node head) {
if (head == null) return head;
Node second = head, first = head.next;
while(first != null) {
first = first.next;
if (first != null) {
second = second.next;
first = first.next;
}
}
return second;
}
}
Another example of a non-recursive merge sort for linked lists, where the functions are not part of a class. This example code and HP / Microsoft std::list::sort both use the same basic algorithm. A bottom up, non-recursive, merge sort that uses a small (26 to 32) array of pointers to the first nodes of a list, where array[i] is either 0 or points to a list of size 2 to the power i. On my system, Intel 2600K 3.4ghz, it can sort 4 million nodes with 32 bit unsigned integers as data in about 1 second.
typedef struct NODE_{
struct NODE_ * next;
uint32_t data;
}NODE;
NODE * MergeLists(NODE *, NODE *); /* prototype */
/* sort a list using array of pointers to list */
/* aList[i] == NULL or ptr to list with 2^i nodes */
#define NUMLISTS 32 /* number of lists */
NODE * SortList(NODE *pList)
{
NODE * aList[NUMLISTS]; /* array of lists */
NODE * pNode;
NODE * pNext;
int i;
if(pList == NULL) /* check for empty list */
return NULL;
for(i = 0; i < NUMLISTS; i++) /* init array */
aList[i] = NULL;
pNode = pList; /* merge nodes into array */
while(pNode != NULL){
pNext = pNode->next;
pNode->next = NULL;
for(i = 0; (i < NUMLISTS) && (aList[i] != NULL); i++){
pNode = MergeLists(aList[i], pNode);
aList[i] = NULL;
}
if(i == NUMLISTS) /* don't go beyond end of array */
i--;
aList[i] = pNode;
pNode = pNext;
}
pNode = NULL; /* merge array into one list */
for(i = 0; i < NUMLISTS; i++)
pNode = MergeLists(aList[i], pNode);
return pNode;
}
/* merge two already sorted lists */
/* compare uses pSrc2 < pSrc1 to follow the STL rule */
/* of only using < and not <= */
NODE * MergeLists(NODE *pSrc1, NODE *pSrc2)
{
NODE *pDst = NULL; /* destination head ptr */
NODE **ppDst = &pDst; /* ptr to head or prev->next */
if(pSrc1 == NULL)
return pSrc2;
if(pSrc2 == NULL)
return pSrc1;
while(1){
if(pSrc2->data < pSrc1->data){ /* if src2 < src1 */
*ppDst = pSrc2;
pSrc2 = *(ppDst = &(pSrc2->next));
if(pSrc2 == NULL){
*ppDst = pSrc1;
break;
}
} else { /* src1 <= src2 */
*ppDst = pSrc1;
pSrc1 = *(ppDst = &(pSrc1->next));
if(pSrc1 == NULL){
*ppDst = pSrc2;
break;
}
}
}
return pDst;
}
Visual Studio 2015 changed std::list::sort to be based on iterators instead of lists, and also changed to a top down merge sort, which requires the overhead of scanning. I initially assumed that the switch to top down was needed to work with the iterators, but when it was asked about again, I investigated this and determined that the switch to the slower top down method was not needed, and bottom up could be implemented using the same iterator based logic. The answer in this link explains this and provide a stand-alone example as well as a replacement for VS2019's std::list::sort() in the include file "list".
`std::list<>::sort()` - why the sudden switch to top-down strategy?
This is the entire Piece of code which shows how we can create linklist in java and sort it using Merge sort. I am creating node in MergeNode class and there is another class MergesortLinklist where there is divide and merge logic.
class MergeNode {
Object value;
MergeNode next;
MergeNode(Object val) {
value = val;
next = null;
}
MergeNode() {
value = null;
next = null;
}
public Object getValue() {
return value;
}
public void setValue(Object value) {
this.value = value;
}
public MergeNode getNext() {
return next;
}
public void setNext(MergeNode next) {
this.next = next;
}
#Override
public String toString() {
return "MergeNode [value=" + value + ", next=" + next + "]";
}
}
public class MergesortLinkList {
MergeNode head;
static int totalnode;
public MergeNode getHead() {
return head;
}
public void setHead(MergeNode head) {
this.head = head;
}
MergeNode add(int i) {
// TODO Auto-generated method stub
if (head == null) {
head = new MergeNode(i);
// System.out.println("head value is "+head);
return head;
}
MergeNode temp = head;
while (temp.next != null) {
temp = temp.next;
}
temp.next = new MergeNode(i);
return head;
}
MergeNode mergesort(MergeNode nl1) {
// TODO Auto-generated method stub
if (nl1.next == null) {
return nl1;
}
int counter = 0;
MergeNode temp = nl1;
while (temp != null) {
counter++;
temp = temp.next;
}
System.out.println("total nodes " + counter);
int middle = (counter - 1) / 2;
temp = nl1;
MergeNode left = nl1, right = nl1;
int leftindex = 0, rightindex = 0;
if (middle == leftindex) {
right = left.next;
}
while (leftindex < middle) {
leftindex++;
left = left.next;
right = left.next;
}
left.next = null;
left = nl1;
System.out.println(left.toString());
System.out.println(right.toString());
MergeNode p1 = mergesort(left);
MergeNode p2 = mergesort(right);
MergeNode node = merge(p1, p2);
return node;
}
MergeNode merge(MergeNode p1, MergeNode p2) {
// TODO Auto-generated method stub
MergeNode L = p1;
MergeNode R = p2;
int Lcount = 0, Rcount = 0;
MergeNode tempnode = null;
while (L != null && R != null) {
int val1 = (int) L.value;
int val2 = (int) R.value;
if (val1 > val2) {
if (tempnode == null) {
tempnode = new MergeNode(val2);
R = R.next;
} else {
MergeNode store = tempnode;
while (store.next != null) {
store = store.next;
}
store.next = new MergeNode(val2);
R = R.next;
}
} else {
if (tempnode == null) {
tempnode = new MergeNode(val1);
L = L.next;
} else {
MergeNode store = tempnode;
while (store.next != null) {
store = store.next;
}
store.next = new MergeNode(val1);
L = L.next;
}
}
}
MergeNode handle = tempnode;
while (L != null) {
while (handle.next != null) {
handle = handle.next;
}
handle.next = L;
L = null;
}
// Copy remaining elements of L[] if any
while (R != null) {
while (handle.next != null) {
handle = handle.next;
}
handle.next = R;
R = null;
}
System.out.println("----------------sorted value-----------");
System.out.println(tempnode.toString());
return tempnode;
}
public static void main(String[] args) {
MergesortLinkList objsort = new MergesortLinkList();
MergeNode n1 = objsort.add(9);
MergeNode n2 = objsort.add(7);
MergeNode n3 = objsort.add(6);
MergeNode n4 = objsort.add(87);
MergeNode n5 = objsort.add(16);
MergeNode n6 = objsort.add(81);
MergeNode n7 = objsort.add(21);
MergeNode n8 = objsort.add(16);
MergeNode n9 = objsort.add(99);
MergeNode n10 = objsort.add(31);
MergeNode val = objsort.mergesort(n1);
System.out.println("===============sorted values=====================");
while (val != null) {
System.out.println(" value is " + val.value);
val = val.next;
}
}
}
I don't see any C++ solutions posted here. So, here it goes. Hope it helps someone.
class Solution {
public:
ListNode *merge(ListNode *left, ListNode *right){
ListNode *head = NULL, *temp = NULL;
// Find which one is the head node for the merged list
if(left->val <= right->val){
head = left, temp = left;
left = left->next;
}
else{
head = right, temp = right;
right = right->next;
}
while(left && right){
if(left->val <= right->val){
temp->next = left;
temp = left;
left = left->next;
}
else{
temp->next = right;
temp = right;
right = right->next;
}
}
// If some elements still left in the left or the right list
if(left)
temp->next = left;
if(right)
temp->next = right;
return head;
}
ListNode* sortList(ListNode* head){
if(!head || !head->next)
return head;
// Find the length of the list
int length = 0;
ListNode *temp = head;
while(temp){
length++;
temp = temp->next;
}
// Reset temp
temp = head;
// Store half of it in left and the other half in right
// Create two lists and sort them
ListNode *left = temp, *prev = NULL;
int i = 0, mid = length / 2;
// Left list
while(i < mid){
prev = temp;
temp = temp->next;
i++;
}
// The end of the left list should point to NULL
if(prev)
prev->next = NULL;
// Right list
ListNode *right = temp;
// Sort left list
ListNode *sortedLeft = sortList(left);
// Sort right list
ListNode *sortedRight = sortList(right);
// Merge them
ListNode *sortedList = merge(sortedLeft, sortedRight);
return sortedList;
}
};
Here is the Java Implementation of Merge Sort on Linked List:
Time Complexity: O(n.logn)
Space Complexity: O(1) - Merge sort implementation on Linked List avoids the O(n) auxiliary storage cost normally associated with the
algorithm
class Solution
{
public ListNode mergeSortList(ListNode head)
{
if(head == null || head.next == null)
return head;
ListNode mid = getMid(head), second_head = mid.next; mid.next = null;
return merge(mergeSortList(head), mergeSortList(second_head));
}
private ListNode merge(ListNode head1, ListNode head2)
{
ListNode result = new ListNode(0), current = result;
while(head1 != null && head2 != null)
{
if(head1.val < head2.val)
{
current.next = head1;
head1 = head1.next;
}
else
{
current.next = head2;
head2 = head2.next;
}
current = current.next;
}
if(head1 != null) current.next = head1;
if(head2 != null) current.next = head2;
return result.next;
}
private ListNode getMid(ListNode head)
{
ListNode slow = head, fast = head.next;
while(fast != null && fast.next != null)
{
slow = slow.next;
fast = fast.next.next;
}
return slow;
}
}
Hey I know that this is a bit late an answer but got a fast simple one.
The code is in F# but will goes in any language. Since this is an uncommen language of the ML family, I'll give some point to enhance the readability.
F# are nesting done by tabulating. the last line of code in a function (nested part) are the return value. (x, y) is a tuple, x::xs is a list of the head x and tail xs (where xs can be empty), |> take the result of last line an pipe it as argument to the expression right of it (readability enhancing) and last (fun args -> some expression) are a lambda function.
// split the list into a singleton list
let split list = List.map (fun x -> [x]) lst
// takes to list and merge them into a sorted list
let sort lst1 lst2 =
// nested function to hide accumulator
let rec s acc pair =
match pair with
// empty list case, return the sorted list
| [], [] -> List.rev acc
| xs, [] | [], xs ->
// one empty list case,
// append the rest of xs onto acc and return the sorted list
List.fold (fun ys y -> y :: ys) acc xs
|> List.rev
// general case
| x::xs, y::ys ->
match x < y with
| true -> // cons x onto the accumulator
s (x::acc) (xs,y::ys)
| _ ->
// cons y onto the accumulator
s (y::acc) (x::xs,ys)
s [] (lst1, lst2)
let msort lst =
let rec merge acc lst =
match lst with
| [] ->
match acc with
| [] -> [] // empty list case
| _ -> merge [] acc
| x :: [] -> // single list case (x is a list)
match acc with
| [] -> x // since acc are empty there are only x left, hence x are the sorted list.
| _ -> merge [] (x::acc) // still need merging.
| x1 :: x2 :: xs ->
// merge the lists x1 and x2 and add them to the acummulator. recursiv call
merge (sort x1 x2 :: acc) xs
// return part
split list // expand to singleton list list
|> merge [] // merge and sort recursively.
It is important to notice that this is fully tail recursive so no possibility of stack overflow, and by first expanding the list to a singleton list list in one go we, lower the constant factor on the worst cost. Since merge are working on list of list, we can recursively merge and sort the inner list until we get to the fix point where all inner list are sorted into one list and then we return that list, hence collapsing from a list list to a list again.
Here is the solution using Swift Programming Language.
//Main MergeSort Function
func mergeSort(head: Node?) -> Node? {
guard let head = head else { return nil }
guard let _ = head.next else { return head }
let middle = getMiddle(head: head)
let left = head
let right = middle.next
middle.next = nil
return merge(left: mergeSort(head: left), right: mergeSort(head: right))
}
//Merge Function
func merge(left: Node?, right: Node?) -> Node? {
guard let left = left, let right = right else { return nil}
let dummyHead: Node = Node(value: 0)
var current: Node? = dummyHead
var currentLeft: Node? = left
var currentRight: Node? = right
while currentLeft != nil && currentRight != nil {
if currentLeft!.value < currentRight!.value {
current?.next = currentLeft
currentLeft = currentLeft!.next
} else {
current?.next = currentRight
currentRight = currentRight!.next
}
current = current?.next
}
if currentLeft != nil {
current?.next = currentLeft
}
if currentRight != nil {
current?.next = currentRight
}
return dummyHead.next!
}
And here are the Node Class & getMiddle Method
class Node {
//Node Class which takes Integers as value
var value: Int
var next: Node?
init(value: Int) {
self.value = value
}
}
func getMiddle(head: Node) -> Node {
guard let nextNode = head.next else { return head }
var slow: Node = head
var fast: Node? = head
while fast?.next?.next != nil {
slow = slow.next!
fast = fast!.next?.next
}
return slow
}
public int[] msort(int[] a) {
if (a.Length > 1) {
int min = a.Length / 2;
int max = min;
int[] b = new int[min];
int[] c = new int[max]; // dividing main array into two half arrays
for (int i = 0; i < min; i++) {
b[i] = a[i];
}
for (int i = min; i < min + max; i++) {
c[i - min] = a[i];
}
b = msort(b);
c = msort(c);
int x = 0;
int y = 0;
int z = 0;
while (b.Length != y && c.Length != z) {
if (b[y] < c[z]) {
a[x] = b[y];
//r--
x++;
y++;
} else {
a[x] = c[z];
x++;
z++;
}
}
while (b.Length != y) {
a[x] = b[y];
x++;
y++;
}
while (c.Length != z) {
a[x] = c[z];
x++;
z++;
}
}
return a;
}