We Keep Coding

Permutations with constant prefix numbers

I have an array of integers where each value will have distinct meanings.The first value means the length of permutation, the second value represent the length of initial prefix and rest of integers are single integer that make up prefix of all permutations.
For e.g. if the array has elements {5,2,1,4}
where 5 is the number of elements in the permutation array.
and 2 is the length of the integer that will makeup the first 2 elements prefix in the array permutation. 1,4 are the prefix integers i.e. length 2 in 5 element permutation combination so missing elements are 2,3,5 where 1&4 being common prefix across all permutations as below
[14235][14253][14325][14352][14523][14532] where input array is {5,2,1,4}
How to achieve this?
I have below code to get the permutation of one missing elements 2,3 & 5 but I am not getting how to program the entire the solution
static void Main(string[] args)
{
int output;
int ip1;
ip1 = Convert.ToInt32(Console.ReadLine());
int ip2_size = 0;
ip2_size = Convert.ToInt32(Console.ReadLine());
int[] ip2 = new int[ip2_size];
int ip2_item;
for (int ip2_i = 0; ip2_i < ip2_size; ip2_i++)
{
ip2_item = Convert.ToInt32(Console.ReadLine());
ip2[ip2_i] = ip2_item;
}
output = correctResult(ip1, ip2);
Console.WriteLine(output);
}
static int correctResult(int n, int[] arr)
{
int permLength = 0;
int prefLength = 0;
int result = 0;
permLength = n;
prefLength = arr.Length;
int[] permArray = new int[permLength];
int len = 0;
var missingNum = Enumerable.Range(1,
permLength).Except(arr).ToArray<int>();
if (permLength < (missingNum.Length + len))
{
result = -1;
}
else
{
for (int i = 0; i < missingNum.Length; i++)
{
permArray[prefLength + i] = missingNum[i];
}
result = permute(missingNum, 0, missingNum.Length - 1);
}
return result;
}
static int permute(int[] arry, int i, int n)
{
int j;
if (i == n)
{
int s1, s2;
s1 = s2 = 0;
for (int a = 0; a < n - 1; a++)
{
for (int b = a + 1; b < n; b++)
{
if (arry[a] > arry[b])
{
s1++;
}
}
s2 = s2 + Math.Max(0, a + 1 - arry[a]);
}
int count = 0;
if (s1 == s2)
count++;
return count;
}
else
{
int count = 0;
for (j = i; j <= n; j++)
{
swap(ref arry[i], ref arry[j]);
count += permute(arry, i + 1, n);
swap(ref arry[i], ref arry[j]);
}
return count;
}
}
static void swap(ref int a, ref int b)
{
int tmp;
tmp = a;
a = b;
b = tmp;
}

Try solving this with immutable types, its easier to reason about them. If, after solving the problem, you have a performance goal you haven't met then you can start trying to optimize the code.
Consider the following approach with an immutable stack that keeps track of the current permutation:
static IEnumerable<IEnumerable<int>> GetPermutations(IList<int> input)
{
if (input == null)
throw new ArgumentNullException(nameof(input));
if (input.Count < 2)
throw new ArgumentException("Input does not have a valid format.");
var setSize = input[0];
var prefixSize = input[1];
if (prefixSize != input.Count - 2)
throw new ArgumentException("Input does not have a valid format.");
if (input.Skip(2).Any(i => i > setSize)) //we are assuming, per example, that valid range starts at 1.
throw new ArgumentException("Input does not have a valid format.");
//Ok, we've got a valid input, interesting stuff starts here.
var prefix = input.Skip(2).ToArray();
var initialSet = Enumerable.Range(1, setSize)
.Except(prefix)
.ToArray();
foreach (var p in getPermutations(ImmutableStack<int>.Empty, initialSet))
{
yield return prefix.Concat(p);
}
IEnumerable<IEnumerable<int>> getPermutations(ImmutableStack<int> permutation, IEnumerable<int> set)
{
if (permutation.Count == setSize - prefixSize)
{
yield return permutation;
}
else
{
foreach (var i in set)
{
foreach (var p in getPermutations(permutation.Push(i), set.Except(new[] { i })))
{
yield return p;
}
}
}
}
}
And that is it, solving your problem was about 10-12 lines of real code (not considering input validation). Note that I am using some c#7 features here, but its easily translatable to previous versions of the language. Also I'd like to underline the argument validation we are doing upfront; make sure you have a valid input before trying out anything.
For ImmutableStack<T> you can use the one in System.Collections.Immutable (you have to download the NuGet package) or implement your own, its simple:
private class ImmutableStack<T>: IEnumerable<T>
{
public static readonly ImmutableStack<T> Empty = new ImmutableStack<T>();
private readonly T head;
private readonly ImmutableStack<T> tail;
private ImmutableStack() { }
private ImmutableStack(T head, ImmutableStack<T> tail)
{
Debug.Assert(tail != null);
this.head = head;
this.tail = tail;
Count = tail.Count + 1;
}
public int Count { get; }
public T Peek() =>
this != Empty ? head : throw new InvalidOperationException("Empty stack.");
public ImmutableStack<T> Pop() =>
this != Empty ? tail : throw new InvalidOperationException("Empty stack.");
public ImmutableStack<T> Push(T item) => new ImmutableStack<T>(item, this);
public IEnumerator<T> GetEnumerator()
{
var current = this;
while (current != Empty)
{
yield return current.head;
current = current.tail;
}
}
IEnumerator IEnumerable.GetEnumerator() => GetEnumerator();
}
If you use the collections in System.Collections.Immutable, then you'll probably want to use some kind of immutable set for initalSet and set.

You can rewrite your permute method (based on this answer):
private static IEnumerable<IEnumerable<T>> Permute<T>(List<T> prefix, List<T> suffix)
{
for (var i = 0; i < suffix.Count; ++i)
{
var newPrefix = new List<T>(prefix) {suffix[i]};
var newSuffix = new List<T>(suffix.Take(i).Concat(suffix.Skip(i + 1)));
if (newSuffix.Count == 0)
{
yield return newPrefix;
continue;
}
foreach (var permutation in Permute(newPrefix, newSuffix))
yield return permutation;
}
}
And use it like this:
public static void PrintAllPermutations()
{
var input = new[] {5, 2, 1, 4};
var prefix = input.Skip(2).Take(input[1]).ToList();
var suffx = Enumerable.Range(1, input[0]).Except(prefix).ToList();
foreach (var permutation in Permute(prefix, suffx))
Console.WriteLine(string.Join(", ", permutation));
}
Reult would be:
1, 4, 2, 3, 5
1, 4, 2, 5, 3
1, 4, 3, 2, 5
1, 4, 3, 5, 2
1, 4, 5, 2, 3
1, 4, 5, 3, 2

Find subset of numbers that add up to a given number

I have a problem I need to solve using C#. There is an array of decimal numbers (representing quantities of an item received by a warehouse at different times). This array is already sorted in the order in which the quantities were received. I need to be able to find the earliest combination of quantities that sum up to a specified total quantity.
So for example, say I have some quantities that came in chronologically as follows [13, 6, 9, 8, 23, 18, 4] and say my total quantity to match is 23. Then I should be able to get [13, 6, 4] as the matching subset although [6, 9, 8] and [23] are also matching but not the earliest.
What would be the best approach/algorithm for this?
I have so far come up with a rather naive approach using recursion.
public class MatchSubset
{
private decimal[] qty = null;
private decimal matchSum = 0;
public int operations = 0;
public int[] matchedIndices = null;
public int matchCount = 0;
private bool SumUp(int i, int n, decimal sum)
{
operations++;
matchedIndices[matchCount++] = i;
sum += qty[i];
if (sum == matchSum)
return true;
if (i >= n - 1)
{
matchCount--;
return false;
}
if (SumUp(i + 1, n, sum))
return true;
sum -= qty[i];
matchCount--;
return SumUp(i + 1, n, sum);
}
public bool Match(decimal[] qty, decimal matchSum)
{
this.qty = qty;
this.matchSum = matchSum;
matchCount = 0;
matchedIndices = new int[qty.Count()];
return SumUp(0, qty.Count(), 0);
}
}
static void Main(string[] args)
{
var match = new MatchSubset();
int maxQtys = 20;
Random rand = new Random(DateTime.Now.Millisecond);
decimal[] qty = new decimal[maxQtys];
for (int i = 0; i < maxQtys - 2; i++)
qty[i] = rand.Next(1, 500);
qty[maxQtys - 2] = 99910;
qty[maxQtys - 1] = 77910;
DateTime t1 = DateTime.Now;
if (match.Match(qty, 177820))
{
Console.WriteLine(DateTime.Now.Subtract(t1).TotalMilliseconds);
Console.WriteLine("Operations: " + match.operations);
for (int i = 0; i < match.matchCount; i++)
{
Console.WriteLine(match.matchedIndices[i]);
}
}
}
The matching subset can be as short as one element and as long as the original set (containing all elements). But to test the worst case scenario, in my test program I am using an arbitrarily long set of which only the last two match the given number.
I see that with 20 numbers in the set, it calls the recursive function over a million times with a max recursion depth of 20. If I run into a set of 30 or more numbers in production, I am fearing it will consume a very long time.
Is there a way to further optimize this? Also, looking at the downvotes, is this the wrong place for such questions?

I was unable to end up with something revolutionary, so the presented solution is just a different implementation of the same brute force algorithm, with 2 optimizations. The first optimization is using iterative implementation rather than recursive. I don't think it is significant because you are more likely to end up with out of time rather than out of stack space, but still it's a good one in general and not hard to implement. The most significant is the second one. The idea is, during the "forward" step, anytime the current sum becomes greater than the target sum, to be able to skip checking the next items that have greater or equal value to the current item. Usually that's accomplished by first sorting the input set, which is not applicable in your case. However, while thinking how to overcome that limitation, I realized that all I need is to have for each item the index of the first next item which value is less than the item value, so I can just jump to that index until I hit the end.
Now, although in the worst case both implementations perform the same way, i.e. may not end in a reasonable time, in many practical scenarios the optimized variant is able to produce result very quickly while the original still doesn't end in a reasonable time. You can check the difference by playing with maxQtys and maxQty parameters.
Here is the implementation described, with test code:
using System;
using System.Diagnostics;
using System.Linq;
namespace Tests
{
class Program
{
private static void Match(decimal[] inputQty, decimal matchSum, out int[] matchedIndices, out int matchCount, out int operations)
{
matchedIndices = new int[inputQty.Length];
matchCount = 0;
operations = 0;
var nextLessQtyPos = new int[inputQty.Length];
for (int i = inputQty.Length - 1; i >= 0; i--)
{
var currentQty = inputQty[i];
int nextPos = i + 1;
while (nextPos < inputQty.Length)
{
var nextQty = inputQty[nextPos];
int compare = nextQty.CompareTo(currentQty);
if (compare < 0) break;
nextPos = nextLessQtyPos[nextPos];
if (compare == 0) break;
}
nextLessQtyPos[i] = nextPos;
}
decimal currentSum = 0;
for (int nextPos = 0; ;)
{
if (nextPos < inputQty.Length)
{
// Forward
operations++;
var nextSum = currentSum + inputQty[nextPos];
int compare = nextSum.CompareTo(matchSum);
if (compare < 0)
{
matchedIndices[matchCount++] = nextPos;
currentSum = nextSum;
nextPos++;
}
else if (compare > 0)
{
nextPos = nextLessQtyPos[nextPos];
}
else
{
// Found
matchedIndices[matchCount++] = nextPos;
break;
}
}
else
{
// Backward
if (matchCount == 0) break;
var lastPos = matchedIndices[--matchCount];
currentSum -= inputQty[lastPos];
nextPos = lastPos + 1;
}
}
}
public class MatchSubset
{
private decimal[] qty = null;
private decimal matchSum = 0;
public int operations = 0;
public int[] matchedIndices = null;
public int matchCount = 0;
private bool SumUp(int i, int n, decimal sum)
{
operations++;
matchedIndices[matchCount++] = i;
sum += qty[i];
if (sum == matchSum)
return true;
if (i >= n - 1)
{
matchCount--;
return false;
}
if (SumUp(i + 1, n, sum))
return true;
sum -= qty[i];
matchCount--;
return SumUp(i + 1, n, sum);
}
public bool Match(decimal[] qty, decimal matchSum)
{
this.qty = qty;
this.matchSum = matchSum;
matchCount = 0;
matchedIndices = new int[qty.Count()];
return SumUp(0, qty.Count(), 0);
}
}
static void Main(string[] args)
{
int maxQtys = 3000;
decimal matchQty = 177820;
var qty = new decimal[maxQtys];
int maxQty = (int)(0.5m * matchQty);
var random = new Random();
for (int i = 0; i < maxQtys - 2; i++)
qty[i] = random.Next(1, maxQty);
qty[maxQtys - 2] = 99910;
qty[maxQtys - 1] = 77910;
Console.WriteLine("Source: {" + string.Join(", ", qty.Select(v => v.ToString())) + "}");
Console.WriteLine("Target: {" + matchQty + "}");
int[] matchedIndices;
int matchCount;
int operations;
var sw = new Stopwatch();
Console.Write("#1 processing...");
sw.Restart();
Match(qty, matchQty, out matchedIndices, out matchCount, out operations);
sw.Stop();
ShowResult(matchedIndices, matchCount, operations, sw.Elapsed);
Console.Write("#2 processing...");
var match = new MatchSubset();
sw.Restart();
match.Match(qty, matchQty);
sw.Stop();
ShowResult(match.matchedIndices, match.matchCount, match.operations, sw.Elapsed);
Console.Write("Done.");
Console.ReadLine();
}
static void ShowResult(int[] matchedIndices, int matchCount, int operations, TimeSpan time)
{
Console.WriteLine();
Console.WriteLine("Time: " + time);
Console.WriteLine("Operations: " + operations);
if (matchCount == 0)
Console.WriteLine("No Match.");
else
Console.WriteLine("Match: {" + string.Join(", ", Enumerable.Range(0, matchCount).Select(i => matchedIndices[i].ToString())) + "}");
}
}
}

issues on using mode in C#

I'm having issues with my Mode and getting it to let me input more then 10 numbers!
Those are the two issues I am having with my code.
public static void Main(string[] args)
{
int[] myNums = new int[10];
int number = 0;
int count = 0;
Console.WriteLine("--Nmber Modifier--\n");
Console.WriteLine("Entering a number that is no between 1 and 10 will end your process");
do// limited to 10 HELP
{
number = Util.PromptForInt("Enter a number between 1 and 10 : ");
if ((number <= 10) && (number >= 1))
{
myNums[count] = number;
}
count++;
}
while ((number <= 10) && (number >= 1));
Array.Sort(myNums);
Console.WriteLine("Average number is : " + MeantAverage(myNums));
Console.WriteLine("Largest Number is : " + LargestNum(myNums));
Console.WriteLine("Smallest Number is : " + SmallestNum(myNums));
Console.WriteLine("Most common number is : " + Mode(myNums));
Console.ReadLine();
}
static double MeantAverage(int[] nums)
{
double dMeanAverage;
double dSum = 0;
var groups = nums.GroupBy(item => item);
foreach (var group in groups)
{
dSum = group.Key + dSum;
}
dMeanAverage = dSum / nums[nums.Length - 1];
return Math.Round(dMeanAverage, 2);
}
static int LargestNum(int[] nums)
{
int highestNum;
highestNum = nums[nums.Length - 1];
return highestNum;
}
static int SmallestNum(int[] nums)
{
int lowest = 0;
for (int b = 0; b < nums.Length; b++)
{
if (nums[b] > lowest)
{
lowest += nums[b];
return lowest;
}
} return lowest;
}
static int Mode(int[] nums)
{
// issues with mode
int modes = 0;
var modeGroup = nums.GroupBy(v => v);
int max = modeGroup.Max(g => g.Count());
modes = modeGroup.First(g => g.Count() == max).Key;
return modes;
}
}
}

You created an array of ten numbers:
int[] myNums = new int[10];
So while your loop doesn't restrict you to 10 numbers because you don't check against count, the system does because as soon as you try to access the 10th element (myNums[10]) you will get an IndexOutOfRangeException.
Since you don't catch it anywhere, its just going to terminate your program.
To solve your problem:
Check against count so you don't input too many numbers!
If you need a variable length collection, use a collection built for that like List<T> instead of an array. Arrays are fixed-length (mostly), and the way around that is a horrible misuse of the array semantic.

Modified code somewhat, intention is the same though.
You forgot to check against count in the while case
You will crash on '0' inputs (no safe guard against empty array)
Changed Mode to merge items and then sort descending
var myNums = new List<int>(10);
for(int i=0; i < 10; ++i)
{
int number = Utils.PromptForInt("Enter a number between 1 and 10 : ");
if(number > 10 || number < 1)
break;
myNums.Add(number);
}
if(myNums.Count < 1)
return; //no item input, do something
myNums.Sort();
Console.WriteLine("Average: {0}", myNums.Sum() / (double)myNums.Count);
Console.WriteLine("Largest: {0}", myNums[myNums.Count - 1]);
Console.WriteLine("Smallest: {0}", myNums[0]);
var result = myNums.GroupBy(n => n)
.Select(c => new { Key = c.Key, total = c.Count() })
.OrderByDescending( a => a.total);
Console.WriteLine("Most common: {0}, used {1} times", result.First().Key, result.First().total);

Finding all positions of substring in a larger string in C#

I have a large string I need to parse, and I need to find all the instances of extract"(me,i-have lots. of]punctuation, and store the index of each to a list.
So say this piece of string was in the beginning and middle of the larger string, both of them would be found, and their indexes would be added to the List. and the List would contain 0 and the other index whatever it would be.
I've been playing around, and the string.IndexOf does almost what I'm looking for, and I've written some code - but it's not working and I've been unable to figure out exactly what is wrong:
List<int> inst = new List<int>();
int index = 0;
while (index < source.LastIndexOf("extract\"(me,i-have lots. of]punctuation", 0) + 39)
{
int src = source.IndexOf("extract\"(me,i-have lots. of]punctuation", index);
inst.Add(src);
index = src + 40;
}
inst = The list
source = The large string
Any better ideas?

Here's an example extension method for it:
public static List<int> AllIndexesOf(this string str, string value) {
if (String.IsNullOrEmpty(value))
throw new ArgumentException("the string to find may not be empty", "value");
List<int> indexes = new List<int>();
for (int index = 0;; index += value.Length) {
index = str.IndexOf(value, index);
if (index == -1)
return indexes;
indexes.Add(index);
}
}
If you put this into a static class and import the namespace with using, it appears as a method on any string, and you can just do:
List<int> indexes = "fooStringfooBar".AllIndexesOf("foo");
For more information on extension methods, http://msdn.microsoft.com/en-us/library/bb383977.aspx
Also the same using an iterator:
public static IEnumerable<int> AllIndexesOf(this string str, string value) {
if (String.IsNullOrEmpty(value))
throw new ArgumentException("the string to find may not be empty", "value");
for (int index = 0;; index += value.Length) {
index = str.IndexOf(value, index);
if (index == -1)
break;
yield return index;
}
}

Why don't you use the built in RegEx class:
public static IEnumerable<int> GetAllIndexes(this string source, string matchString)
{
matchString = Regex.Escape(matchString);
foreach (Match match in Regex.Matches(source, matchString))
{
yield return match.Index;
}
}
If you do need to reuse the expression then compile it and cache it somewhere. Change the matchString param to a Regex matchExpression in another overload for the reuse case.

using LINQ
public static IEnumerable<int> IndexOfAll(this string sourceString, string subString)
{
return Regex.Matches(sourceString, subString).Cast<Match>().Select(m => m.Index);
}

Polished version + case ignoring support:
public static int[] AllIndexesOf(string str, string substr, bool ignoreCase = false)
{
if (string.IsNullOrWhiteSpace(str) ||
string.IsNullOrWhiteSpace(substr))
{
throw new ArgumentException("String or substring is not specified.");
}
var indexes = new List<int>();
int index = 0;
while ((index = str.IndexOf(substr, index, ignoreCase ? StringComparison.OrdinalIgnoreCase : StringComparison.Ordinal)) != -1)
{
indexes.Add(index++);
}
return indexes.ToArray();
}

It could be done in efficient time complexity using KMP algorithm in O(N + M) where N is the length of text and M is the length of the pattern.
This is the implementation and usage:
static class StringExtensions
{
public static IEnumerable<int> AllIndicesOf(this string text, string pattern)
{
if (string.IsNullOrEmpty(pattern))
{
throw new ArgumentNullException(nameof(pattern));
}
return Kmp(text, pattern);
}
private static IEnumerable<int> Kmp(string text, string pattern)
{
int M = pattern.Length;
int N = text.Length;
int[] lps = LongestPrefixSuffix(pattern);
int i = 0, j = 0;
while (i < N)
{
if (pattern[j] == text[i])
{
j++;
i++;
}
if (j == M)
{
yield return i - j;
j = lps[j - 1];
}
else if (i < N && pattern[j] != text[i])
{
if (j != 0)
{
j = lps[j - 1];
}
else
{
i++;
}
}
}
}
private static int[] LongestPrefixSuffix(string pattern)
{
int[] lps = new int[pattern.Length];
int length = 0;
int i = 1;
while (i < pattern.Length)
{
if (pattern[i] == pattern[length])
{
length++;
lps[i] = length;
i++;
}
else
{
if (length != 0)
{
length = lps[length - 1];
}
else
{
lps[i] = length;
i++;
}
}
}
return lps;
}
and this is an example of how to use it:
static void Main(string[] args)
{
string text = "this is a test";
string pattern = "is";
foreach (var index in text.AllIndicesOf(pattern))
{
Console.WriteLine(index); // 2 5
}
}

Without Regex, using string comparison type:
string search = "123aa456AA789bb9991AACAA";
string pattern = "AA";
Enumerable.Range(0, search.Length)
.Select(index => { return new { Index = index, Length = (index + pattern.Length) > search.Length ? search.Length - index : pattern.Length }; })
.Where(searchbit => searchbit.Length == pattern.Length && pattern.Equals(search.Substring(searchbit.Index, searchbit.Length),StringComparison.OrdinalIgnoreCase))
.Select(searchbit => searchbit.Index)
This returns {3,8,19,22}. Empty pattern would match all positions.
For multiple patterns:
string search = "123aa456AA789bb9991AACAA";
string[] patterns = new string[] { "aa", "99" };
patterns.SelectMany(pattern => Enumerable.Range(0, search.Length)
.Select(index => { return new { Index = index, Length = (index + pattern.Length) > search.Length ? search.Length - index : pattern.Length }; })
.Where(searchbit => searchbit.Length == pattern.Length && pattern.Equals(search.Substring(searchbit.Index, searchbit.Length), StringComparison.OrdinalIgnoreCase))
.Select(searchbit => searchbit.Index))
This returns {3, 8, 19, 22, 15, 16}

I noticed that at least two proposed solutions don't handle overlapping search hits. I didn't check the one marked with the green checkmark. Here is one that handles overlapping search hits:
public static List<int> GetPositions(this string source, string searchString)
{
List<int> ret = new List<int>();
int len = searchString.Length;
int start = -1;
while (true)
{
start = source.IndexOf(searchString, start +1);
if (start == -1)
{
break;
}
else
{
ret.Add(start);
}
}
return ret;
}

public List<int> GetPositions(string source, string searchString)
{
List<int> ret = new List<int>();
int len = searchString.Length;
int start = -len;
while (true)
{
start = source.IndexOf(searchString, start + len);
if (start == -1)
{
break;
}
else
{
ret.Add(start);
}
}
return ret;
}
Call it like this:
List<int> list = GetPositions("bob is a chowder head bob bob sldfjl", "bob");
// list will contain 0, 22, 26

Hi nice answer by #Matti Virkkunen
public static List<int> AllIndexesOf(this string str, string value) {
if (String.IsNullOrEmpty(value))
throw new ArgumentException("the string to find may not be empty", "value");
List<int> indexes = new List<int>();
for (int index = 0;; index += value.Length) {
index = str.IndexOf(value, index);
if (index == -1)
return indexes;
indexes.Add(index);
index--;
}
}
But this covers tests cases like AOOAOOA
where substring
are AOOA and AOOA
Output 0 and 3

#csam is correct in theory, although his code will not complie and can be refractored to
public static IEnumerable<int> IndexOfAll(this string sourceString, string matchString)
{
matchString = Regex.Escape(matchString);
return from Match match in Regex.Matches(sourceString, matchString) select match.Index;
}

public static Dictionary<string, IEnumerable<int>> GetWordsPositions(this string input, string[] Susbtrings)
{
Dictionary<string, IEnumerable<int>> WordsPositions = new Dictionary<string, IEnumerable<int>>();
IEnumerable<int> IndexOfAll = null;
foreach (string st in Susbtrings)
{
IndexOfAll = Regex.Matches(input, st).Cast<Match>().Select(m => m.Index);
WordsPositions.Add(st, IndexOfAll);
}
return WordsPositions;
}

Based on the code I've used for finding multiple instances of a string within a larger string, your code would look like:
List<int> inst = new List<int>();
int index = 0;
while (index >=0)
{
index = source.IndexOf("extract\"(me,i-have lots. of]punctuation", index);
inst.Add(index);
index++;
}

I found this example and incorporated it into a function:
public static int solution1(int A, int B)
{
// Check if A and B are in [0...999,999,999]
if ( (A >= 0 && A <= 999999999) && (B >= 0 && B <= 999999999))
{
if (A == 0 && B == 0)
{
return 0;
}
// Make sure A < B
if (A < B)
{
// Convert A and B to strings
string a = A.ToString();
string b = B.ToString();
int index = 0;
// See if A is a substring of B
if (b.Contains(a))
{
// Find index where A is
if (b.IndexOf(a) != -1)
{
while ((index = b.IndexOf(a, index)) != -1)
{
Console.WriteLine(A + " found at position " + index);
index++;
}
Console.ReadLine();
return b.IndexOf(a);
}
else
return -1;
}
else
{
Console.WriteLine(A + " is not in " + B + ".");
Console.ReadLine();
return -1;
}
}
else
{
Console.WriteLine(A + " must be less than " + B + ".");
// Console.ReadLine();
return -1;
}
}
else
{
Console.WriteLine("A or B is out of range.");
//Console.ReadLine();
return -1;
}
}
static void Main(string[] args)
{
int A = 53, B = 1953786;
int C = 78, D = 195378678;
int E = 57, F = 153786;
solution1(A, B);
solution1(C, D);
solution1(E, F);
Console.WriteLine();
}
Returns:
53 found at position 2
78 found at position 4
78 found at position 7
57 is not in 153786

How is this alternative implementation?
public static class MyExtensions
{
public static int HowMany(this string str, char needle)
{
int counter = 0;
int nextIndex = 0;
for (; nextIndex != -1; )
{
nextIndex = str.IndexOf(needle, nextIndex);
if (nextIndex != -1)
{
counter++;
//step over to the next char
nextIndex++;
}
}
return counter;
}
}

you can use linq to select and enumerate all elements, then find by any string:
I've created a class:
class Pontos
{
//index on string
public int Pos { get; set; }
//caractere
public string Caractere { get; set; }
}
And use like this:
int count = 0;
var pontos = texto.Select(y => new Pontos { Pos = count++, Caractere = y.ToString() }).Where(x=>x.Caractere == ".").ToList();
then:
input string:
output list:
PS: SeForNumero is another field of my class, I need this for my own purposes, but is not necessary to this use.

Check for missing number in sequence

I have an List<int> which contains 1,2,4,7,9 for example.
I have a range from 0 to 10.
Is there a way to determine what numbers are missing in that sequence?
I thought LINQ might provide an option but I can't see one
In the real world my List could contain 100,000 items so performance is key

var list = new List<int>(new[] { 1, 2, 4, 7, 9 });
var result = Enumerable.Range(0, 10).Except(list);

Turn the range you want to check into a HashSet:
public IEnumerable<int> FindMissing(IEnumerable<int> values)
{
HashSet<int> myRange = new HashSet<int>(Enumerable.Range(0,10));
myRange.ExceptWith(values);
return myRange;
}
Will return the values that aren't in values.

Using Unity i have tested two solutions on set of million integers. Looks like using Dictionary and two "for" loops gives better result than Enumerable.Except
FindMissing1 Total time: 0.1420 (Enumerable.Except)
FindMissing2 Total time: 0.0621 (Dictionary and two for loops)
public static class ArrayExtension
{
public static T[] FindMissing1<T>(T[] range, T[] values)
{
List<T> result = Enumerable.Except<T>(range, values).ToList<T>();
return result.ToArray<T>();
}
public static T[] FindMissing2<T>(T[] range, T[] values)
{
List<T> result = new List<T>();
Dictionary<T, T> hash = new Dictionary<T, T>(values.Length);
for (int i = 0; i < values.Length; i++)
hash.Add(values[i], values[i]);
for (int i = 0; i < range.Length; i++)
{
if (!hash.ContainsKey(range[i]))
result.Add(range[i]);
}
return result.ToArray<T>();
}
}
public class ArrayManipulationTest : MonoBehaviour
{
void Start()
{
int rangeLength = 1000000;
int[] range = Enumerable.Range(0, rangeLength).ToArray();
int[] values = new int[rangeLength / 5];
int[] missing;
float start;
float duration;
for (int i = 0; i < rangeLength / 5; i ++)
values[i] = i * 5;
start = Time.realtimeSinceStartup;
missing = ArrayExtension.FindMissing1<int>(range, values);
duration = Time.realtimeSinceStartup - start;
Debug.Log($"FindMissing1 Total time: {duration:0.0000}");
start = Time.realtimeSinceStartup;
missing = ArrayExtension.FindMissing2<int>(range, values);
duration = Time.realtimeSinceStartup - start;
Debug.Log($"FindMissing2 Total time: {duration:0.0000}");
}
}

List<int> selectedNumbers = new List<int>(){8, 5, 3, 12, 2};
int firstNumber = selectedNumbers.OrderBy(i => i).First();
int lastNumber = selectedNumbers.OrderBy(i => i).Last();
List<int> allNumbers = Enumerable.Range(firstNumber, lastNumber - firstNumber + 1).ToList();
List<int> missingNumbers = allNumbers.Except(selectedNumbers).ToList();
foreach (int i in missingNumbers)
{
Response.Write(i);
}

LINQ's Except method would be the most readable. Whether it performs adequately for you or not would be a matter for testing.
E.g.
range.Except(listOfValues);
Edit
Here's the program I used for my mini-benchmark, for others to plug away with:
static void Main()
{
var a = Enumerable.Range(0, 1000000);
var b = new List<int>();
for (int i = 0; i < 1000000; i += 10)
{
b.Add(i);
}
Stopwatch sw = new Stopwatch();
sw.Start();
var c = a.Except(b).ToList();
sw.Stop();
Console.WriteLine("Milliseconds {0}", sw.ElapsedMilliseconds );
sw.Reset();
Console.ReadLine();
}

An alternative method which works in general for any two IEnunumerable<T> where T :IComparable. If the IEnumerables are both sorted, this works in O(1) memory (i.e. there is no creating another ICollection and subtracting, etc.) and in O(n) time.
The use of IEnumerable<IComparable> and GetEnumerator makes this a little less readable, but far more general.
Implementation
/// <summary>
/// <para>For two sorted IEnumerable<T> (superset and subset),</para>
/// <para>returns the values in superset which are not in subset.</para>
/// </summary>
public static IEnumerable<T> CompareSortedEnumerables<T>(IEnumerable<T> superset, IEnumerable<T> subset)
where T : IComparable
{
IEnumerator<T> supersetEnumerator = superset.GetEnumerator();
IEnumerator<T> subsetEnumerator = subset.GetEnumerator();
bool itemsRemainingInSubset = subsetEnumerator.MoveNext();
// handle the case when the first item in subset is less than the first item in superset
T firstInSuperset = superset.First();
while ( itemsRemainingInSubset && supersetEnumerator.Current.CompareTo(subsetEnumerator.Current) >= 0 )
itemsRemainingInSubset = subsetEnumerator.MoveNext();
while ( supersetEnumerator.MoveNext() )
{
int comparison = supersetEnumerator.Current.CompareTo(subsetEnumerator.Current);
if ( !itemsRemainingInSubset || comparison < 0 )
{
yield return supersetEnumerator.Current;
}
else if ( comparison >= 0 )
{
while ( itemsRemainingInSubset && supersetEnumerator.Current.CompareTo(subsetEnumerator.Current) >= 0 )
itemsRemainingInSubset = subsetEnumerator.MoveNext();
}
}
}
Usage
var values = Enumerable.Range(0, 11);
var list = new List<int> { 1, 2, 4, 7, 9 };
var notIncluded = CompareSortedEnumerables(values, list);

If the range is predictable I suggest the following solution:
public static void Main()
{
//set up the expected range
var expectedRange = Enumerable.Range(0, 10);
//set up the current list
var currentList = new List<int> {1, 2, 4, 7, 9};
//get the missing items
var missingItems = expectedRange.Except(currentList);
//print the missing items
foreach (int missingItem in missingItems)
{
Console.WriteLine(missingItem);
}
Console.ReadLine();
}
Regards,
y00daa

This does not use LINQ but it works in linear time.
I assume that input list is sorted.
This takes O(list.Count).
private static IEnumerable<int> get_miss(List<int> list,int length)
{
var miss = new List<int>();
int i =0;
for ( i = 0; i < list.Count - 1; i++)
{
foreach (var item in
Enumerable.Range(list[i] + 1, list[i + 1] - list[i] - 1))
{
yield return item;
}
}
foreach (var item in Enumerable.Range(list[i]+1,length-list[i]))
{
yield return item;
}
}
This should take O(n) where n is length of full range.
static void Main()
{
List<int> identifiers = new List<int>() { 1, 2, 4, 7, 9 };
Stopwatch sw = new Stopwatch();
sw.Start();
List<int> miss = GetMiss(identifiers,150000);
sw.Stop();
Console.WriteLine("{0}",sw.ElapsedMilliseconds);
}
private static List<int> GetMiss(List<int> identifiers,int length)
{
List<int> miss = new List<int>();
int j = 0;
for (int i = 0; i < length; i++)
{
if (i < identifiers[j])
miss.Add(i);
else if (i == identifiers[j])
j++;
if (j == identifiers.Count)
{
miss.AddRange(Enumerable.Range(i + 1, length - i));
break;
}
}
return miss;
}

Ok, really, create a new list which parallels the initial list and run the method Except over it...
I have created a fully linq answer using the Aggregate method instead to find the missings:
var list = new List<int>(new[] { 1, 2, 4, 7, 9 }); // Assumes list is ordered at this point
list.Insert(0, 0); // No error checking, just put in the lowest and highest possibles.
list.Add(10); // For real world processing, put in check and if not represented then add it/them.
var missing = new List<int>(); // Hold any missing values found.
list.Aggregate ((seed, aggr) => // Seed is the previous #, aggr is the current number.
{
var diff = (aggr - seed) -1; // A difference between them indicates missing.
if (diff > 0) // Missing found...put in the missing range.
missing.AddRange(Enumerable.Range((aggr - diff), diff));
return aggr;
});
The missing list has this after the above code has been executed:
3, 5, 6, 8

for a List L a general solution (works in all programming languages) would be simply
L.Count()*(L.Count()+1)/2 - L.Sum();
which returns the expected sum of series minus the actual series.
for a List of size n the missing number is:
n(n+1)/2 - (sum of list numbers)

this method here returns the number of missing elements ,sort the set , add all elements from range 0 to range max , then remove the original elements , then you will have the missing set
int makeArrayConsecutive(int[] statues)
{
Array.Sort(statues);
HashSet<int> set = new HashSet<int>();
for(int i = statues[0]; i< statues[statues.Length -1]; i++)
{
set.Add(i);
}
for (int i = 0; i < statues.Length; i++)
{
set.Remove(statues[i]);
}
var x = set.Count;
return x;
// return set ; // use this if you need the actual elements + change the method return type
}

Create an array of num items
const int numItems = 1000;
bool found[numItems] = new bool[numItems];
List<int> list;
PopulateList(list);
list.ForEach( i => found[i] = true );
// now iterate found for the numbers found
for(int count = 0; i < numItems; ++numItems){
Console.WriteList("Item {0} is {1}", count, found[count] ? "there" : "not there");
}

This method does not use LINQ and works in general for any two IEnunumerable<T> where T :IComparable
public static IEnumerable<T> FindMissing<T>(IEnumerable<T> superset, IEnumerable<T> subset) where T : IComparable
{
bool include = true;
foreach (var i in superset)
{
foreach (var j in subset)
{
include = i.CompareTo(j) == 0;
if (include)
break;
}
if (!include)
yield return i;
}
}

int sum = 0,missingNumber;
int[] arr = { 1,2,3,4,5,6,7,8,9};
for (int i = 0; i < arr.Length; i++)
{
sum += arr[i];
}
Console.WriteLine("The sum from 1 to 10 is 55");
Console.WriteLine("Sum is :" +sum);
missingNumber = 55 - sum;
Console.WriteLine("Missing Number is :-"+missingNumber);
Console.ReadLine();