LC: Concatenated Words - string

LC Question: https://leetcode.com/problems/concatenated-words/
var findAllConcatenatedWordsInADict = function(words) {
let m = new Map(), memo = new Map();
let res = [];
for (let i = 0; i < words.length; i++) {
m.set(words[i], 1);
}
for (let i = 0; i < words.length; i++) {
if (isConcat(words[i], m, memo)) res.push(words[i]);
}
return res;
};
function isConcat(word, m, memo) {
if (memo.has(word)) return memo.get(word);
for (let i = 1; i < word.length; i++) {
let prefix = word.slice(0, i);
let suffix = word.slice(i);
if (m.has(prefix) && (m.has(suffix) || isConcat(suffix, m, memo))) {
memo.set(word, true);
return true;
}
}
memo.set(word, false);
return false;
};
Still trying to wrap my head around the solution why do we call the isConcat function ONLY on the suffix that we generate from words[i] and not prefix?
Further, I have tried running various test cases ["cat","cats","dog","dogcatsdog","rat","ratcatdogcat"].
It seems like we do not call the isConcat function on the first suffix that is generated from word[0] ('at'). However, we do seem to call it on 'catsdog' as part of the "dogcatsdog" word so I'm not sure how the logic works as to how it chooses which suffixes to call on....

My mistake was misreading the code and assuming that the following conditions had to return true for a valid concatenated word:
Map has both prefix and suffix; OR
isConcat(suffix) returns true
In fact, prefix is already known to be in map (since map.has(prefix) must be true in order to reach the recursive call in the first place!). Thus, a concatenated word is only valid if the suffix is also an element of map or it's another concatenated word. map.has(suffix) tests if the suffix is in map, while isConcat(suffix, map, memo) tests whether the suffix is also a concatenated word.

Related

Check50 Errros: Not passing " handles most basic words properly" and "handles substrings properly" tests. Check50 also can't check for a memory error

I am working on Pset5 Speller. I've managed to get all my errors down to three, but I cannot figure out how to fix my program so that it handles most basic words and handles substrings. I have run debugger, but it doesn't really help. I have also run valgrind and it says that no memory leaks are possible. I think the problem maybe my check function or hash function, so I have changed them a few times but I still get the same check50 results. The sumbit50 link:
https://submit.cs50.io/check50/57b8af186bcdadea0b585f0785ef47a5cf317b99 says that check50 only ever finds 1 word in the dictionary and identifies all words as misspelled. I really am not quite sure what the problem is. Can someone help me please? Here are my checks and hash functions. Thank you!!!
// Hashes word to a number
unsigned int hash(const char *word)
{
// hash function created by Deliberate Think on Youtube
int hash_key = 0;
int n;
for (int i = 0; word[i] != '\0'; i++)
{
if (isalpha(word[i]))
{
n = word[i] - 'a' + 1;
}
else
{
n = 27;
}
hash_key = ((hash_key << 3) + n) % N;
}
return hash_key;
}
// Returns true if word is in dictionary else false
bool check(const char *word)
{
// create an array to store words, then copy words from table to compare
int n = strlen(word);
char wordcheck[LENGTH + 1];
strcpy(wordcheck, word);
for (int i = 0; i < n; i++)
{
wordcheck[i] = tolower(word[i]);
}
//hashes word, then accesses linked list at that value
int j = hash(wordcheck);
node *cursor = hashtable[j];
if (hashtable[j] != NULL)
{
//iterates through linked list: cursor pointer starts at head of list and while there is a value, it moves on to the next word in the list
while (cursor != NULL)
{
//if the word is found, return true
if (strcmp(cursor->word, wordcheck) == 0)
{
return true;
}
else
{
cursor = cursor->next;
}
}
}
return false;
}
bool load(const char *dictionary)
{
//opens dictionary file
FILE *inputfile = fopen(dictionary, "r");
if (inputfile == NULL)
{
return false;
}
//initializes new node pointer and reads words from new file while !EOF
char word[LENGTH + 1];
while (fscanf(inputfile, "%s", word) != EOF)
{
//actually creates and initializes new node( creates space in memory for node using malloc function) and copies word into node while keeping tracking of # of words
node *new_node = malloc(sizeof(node));
if (new_node == NULL)
{
unload();
return false;
}
else
{
strcpy(new_node->word, word);
}
//hashes words in node to determine which linked list to use
int j = hash(new_node->word);
//initializes node pointer to first bucket in hashtable
node *head = hashtable[j];
if (head == NULL)
{
//if there is no data in linked list, new_node becomes head of linked list
hashtable[j] = new_node;
}
else
{
//if data exists, node points to next word in list, then head of linked list points to node pointer
new_node->next = hashtable[j];
hashtable[j] = new_node;
}
wordcount++;
fclose(inputfile);
}
return true;
}
I solved it! I had to change the way the hash function was written inside of the load function and rewrite fclose(inputfile) to be outside of one of the curly braces. All errors gone!

finding the subsequence of strings in c# urjent

Alice has two strings, initial and goal. She can remove some number of characters from initial, which will give her a subsequence of that string. A string with no deletions is still considered a subsequence of itself. Given these two strings, can you find the minimum number of subsequences of initial that, when appended together, will form goal?
function minimumConcat(initial, goal) {
let result = 0;
let pattern = ''
let count1 = Array.apply(null, Array(26)).map(Number.prototype.valueOf, 0);
let count2 = Array.apply(null, Array(26)).map(Number.prototype.valueOf, 0);
initial.split('').forEach(c => {
pattern = pattern + c
});
pattern = "^[" + pattern + "]*$"
if (!RegExp(pattern).test(goal)) return -1
for (let i = 0; i < initial.length; i++) {
count1[initial.charCodeAt(i) - 97]++;
}
for (let i = 0; i < goal.length; i++) {
count2[goal.charCodeAt(i) - 97]++;
}
for (let i = 0; i < 26; i++) {
result += Math.abs(count1[i] - count2[i]);
}
return result;
}
var initial = readline();
var goal = readline();
print(minimumConcat(initial, goal));

Longest Substring without repeating characters issue with edge case

I was trying to solve this problem: Longest substring without repeating characters. The issue is, it's failing in couple test cases, I don't know how to fix it. I would need your help to see where I'm going wrong.
Question:
Given a string, find the length of the longest substring without
repeating characters.
Examples:
Given "abcabcbb", the answer is "abc", which the length is 3.
Given "bbbbb", the answer is "b", with the length of 1.
Given "pwwkew", the answer is "wke", with the length of 3. Note that
the answer must be a substring, "pwke" is a subsequence and not a
substring.
This is my code:
function longestSubString(arr){
let localSum=0,globalSum=0;
let set = new Set();
for(let i=0; i<arr.length; i++){
let current = arr[i];
//if the key is present in the store.
if(set.has(current)){
set.clear();
localSum = 1;
set.add(current);
} else {
localSum +=1;
set.add(current);
}
if(globalSum < localSum){
globalSum = localSum;
}
}
return globalSum;
}
Tests:
let test = "abcabc"; //returns 3 - correct
let test2 = "bbb"; //returns 1 - correct
let test5 = "dvdf"; //returns 2 - INCORRECT! it should return 3 (i.e for vdf) since I'm doing set.clear() I'm not able to store previous elements.
longestSubString(test5); //incorrect
Live:
https://repl.it/Jo5Z/10
Not fully tested!
function longestSubString(arr){
let localSum=0,globalSum=0;
let set = new Set();
for(let i=0; i<arr.length; i++){
let current = arr[i];
//if the key is present in the store.
if(set.has(current)){
let a = Array.from(set);
a.splice(0,a.indexOf(current)+1);
set = new Set(a);
set.add(current);
localSum = set.size;
} else {
localSum +=1;
set.add(current);
}
if(globalSum < localSum){
globalSum = localSum;
}
}
return globalSum;
}
The idea is that when you get duplicate, you should start from the charachter after the first duplicated character, in your case dvdf, when you reach the second d you should continue from vd not from d!
You have to consider that the substring might start from any character in the string. Erasing the set only when you're finding a duplicate makes you only consider a substring starting from characters that are equal to to the first character.
An O(logn*n^2) solution modifying yours just a bit:
function longestSubString(arr){
let globalSum=0;
for(let i=0; i<arr.length; i++){
let set = new Set();
let localSum=0;
for(let j=i; j<arr.lenght; j++){
let current = arr[j];
//if the key is present in the store.
if(set.has(current)){
break;
} else {
localSum +=1;
set.add(current);
}
}
if(globalSum < localSum){
globalSum = localSum;
}
}
return globalSum;
}
There's also a O(n + d) (almost linear) solution, d being the number of characters in the alphabet. See http://www.geeksforgeeks.org/length-of-the-longest-substring-without-repeating-characters/.
There seem to be a lot of long answers here. The implementation I've thought of is simplified due to two observations:
Whenever you encounter a duplicate character, you need to start the next substring just after the previous occurrence of the current character.
Set() creates an array in insertion order when iterated.
function longestSubstring(str) {
let maxLength = 0
let current = new Set()
for (const character of str) {
if (current.has(character)) {
const substr = Array.from(current)
maxLength = Math.max(maxLength, substr.length)
current = new Set(substr.slice(substr.indexOf(character) + 1))
}
current.add(character)
}
return Math.max(maxLength, current.size)
}
const tests = [
"abcabc",
"bbb",
"pwwkew",
"geeksforgeeks",
"dvdf"
]
tests.map(longestSubstring).forEach(result => console.log(result))
A simple edit allows us to keep the first occurrence of the largest substring instead of the maximum length.
function longestSubstring(str) {
let maxSubstr = []
let current = new Set()
for (const character of str) {
if (current.has(character)) {
const substr = Array.from(current)
maxSubstr = maxSubstr.length < substr.length ? substr: maxSubstr
current = new Set(substr.slice(substr.indexOf(character) + 1))
}
current.add(character)
}
const substr = maxSubstr.length < current.size ? Array.from(current) : maxSubstr
return substr.join('')
}
const tests = [
"abcabc",
"bbb",
"pwwkew",
"geeksforgeeks",
"dvdf"
]
tests.map(longestSubstring).forEach(result => console.log(result))
As we can see, the last test yields vdf, as expected.
Below solution gets the length in O(n+d) time and also prints the longest non repeating character substring as well:
public void longestNonRepeatingLength(String a){
a="dvdf";
int visitedIndex[] = new int[256];
int curr_len = 0, max_len = 0, prev_ind = 0, start = 0, end = 1;
for(int i =0;i<256;i++)
visitedIndex[i] = -1;
visitedIndex[a.charAt(0)] = 0;
curr_len++;
int i = 0;
for( i=1;i<a.length();i++){
prev_ind = visitedIndex[a.charAt(i)];
if(prev_ind == -1 || i > prev_ind + curr_len)
curr_len++;
else{
if(curr_len>max_len){
start = prev_ind + 1;
end = i;
max_len = curr_len;
}
curr_len = i - prev_ind;
}
visitedIndex[a.charAt(i)] = i;
}
if(curr_len>max_len){
end = i-1;
max_len = curr_len;
}
for( i = start;i<=end;i++)
System.out.print(a.charAt(i));
System.out.println("");
System.out.println("Length = "+max_len);
}
As set contains the largest set of non-repeating characters of a String ending on index i, this means that when you encounter a previously seen character, rather than starting over with an empty set as your codes does now, you should just remove all characters from your set until that duplicate one.
Say for example your input is "abXcXdef". When the second "X" is encountered, you'll want to drop "a" and "b" from your set, leaving a set of ("c","X") as the longest set up to that point. Adding all other characters (as none are duplicates) you then end up with a max length of 5.
Something like this should work:
function longestSubString(arr) {
let globalSum = 0;
let set = new Set();
for (let i=0; i<arr.length; i++) {
let current = arr[i];
if (set.has(current)) {
while (true) {
let removeChar = arr[i - set.count];
if (removeChar != current)
set.remove(removeChar);
else
break;
}
} else {
set.add(current);
if (set.count > globalSum)
globalSum = set.count;
}
}
return globalSum;
}
As every character is added at most once and deleted at most once, this is an O(N) algorithm.

AS3 String splitting keeping tags

I have variable strings that can contain tags, e.g.:
"<b>Water</b>=H<sub>2</sub>O"
What i want is an array that should look like:
Array[0] <b>Water</b>
Array[1] =H
Array[2] <sub>2</sub>
Array[3] O
How can i do this?
Thanks!
Give this a go, it uses a common regex to find html tags to get it separated and then indexOf and substring to assemble it back together.
function splitWithTags(str:String):Array {
var tags:Array = str.match(/(<(.|\n)*?>)/g);
var c:int = tags.length;
if(c%2 != 0) c--; // if it's odd, decrement to make even so loop works, last tag will be ignored.
if(c<2) return [str]; // not enough tags so return full string
var out:Array = [];
var end:int = 0;
var pos1:int, pos2:int;
for(var i:int = 0; i<c; i+=2) {
// find position of 2 tags.
pos1 = str.indexOf(tags[i]);
pos2 = str.indexOf(tags[i+1]);
if(pos1 >= end+1) { // there's some stuff not between tags to add
out.push(str.substring(end, pos1));
}
end = pos2+tags[i+1].length
out.push(str.substring(pos1, end));
}
if(end < str.length) { // there is substr at end
out.push(str.substring(end, str.length));
}
return out;
}

How to remove duplicates from a string except it's first occurence

I've been given the following exercise but can't seem to get it working.
//Remove duplicate characters in a
// given string keeping only the first occurrences.
// For example, if the input is ‘tree traversal’
// the output will be "tre avsl".
// ---------------------
var params = 'tree traversal word';
var removeDuplicates = function (string) {
return string;
};
// This function runs the application
// ---------------------
var run = function() {
// We execute the function returned here,
// passing params as arguments
return removeDuplicates;
};
What I've done -
var removeDuplicates = function (string) {
var word ='';
for(var i=0; i < string.length; i++){
if(string[i] == " "){
word += string[i] + " ";
}
else if(string.lastIndexOf(string[i]) == string.indexOf(string[i]))
{
word += string[i];
}
}
return word;
};
I'm not allowed to use replaceAll and when I create an inner for loop it doesn't work.
<script>
function removeDuplicates(string)
{
var result = [];
var i = null;
var length = string.length;
for (i = 0; i < length; i += 1)
{
var current = string.charAt(i);
if (result.indexOf(current) === -1)
{
result.push(current);
}
}
return result.join("");
}
function removeDuplicatesRegex(string)
{
return string.replace(/(.)(?=\1)/g, "");
}
var str = "tree traversal";
alert(removeDuplicates(str));
</script>
First of all, the run function should be returning removeDuplicates(params), right?
You're on the right lines, but need to think about this condition again:
else if(string.lastIndexOf(string[i]) == string.indexOf(string[i]))
With i = 0 and taking 'tree traversal word' as the example, lastIndexOf() is going to be returning 5 (the index of the 2nd 't'), whereas indexOf() will be returning 0.
Obviously this isn't what you want, because 't' hasn't yet been appended to word yet (but it is a repeated character, which is what your condition does actually test for).
Because you're gradually building up word, think about testing to see if the character string[i] exists in word already for each iteration of your for loop. If it doesn't, append it.
(maybe this will come in handy: http://www.w3schools.com/jsref/jsref_search.asp)
Good luck!

Resources