Detect differences between two strings - c#

I have 2 strings
string a = "foo bar";
string b = "bar foo";
and I want to detect the changes from a to b. What characters do I have to change, to get from a to b?
I think there must be a iteration over each character and detect if it was added, removed or remained equal. So this is my exprected result
'f' Remove
'o' Remove
'o' Remove
' ' Remove
'b' Equal
'a' Equal
'r' Equal
' ' Add
'f' Add
'o' Add
'o' Add
class and enum for the result:
public enum Operation { Add,Equal,Remove };
public class Difference
{
public Operation op { get; set; }
public char c { get; set; }
}
Here is my solution but the "Remove" case is not clear to me how the code has to look like
public static List<Difference> CalculateDifferences(string left, string right)
{
int count = 0;
List<Difference> result = new List<Difference>();
foreach (char ch in left)
{
int index = right.IndexOf(ch, count);
if (index == count)
{
count++;
result.Add(new Difference() { c = ch, op = Operation.Equal });
}
else if (index > count)
{
string add = right.Substring(count, index - count);
result.AddRange(add.Select(x => new Difference() { c = x, op = Operation.Add }));
count += add.Length;
}
else
{
//Remove?
}
}
return result;
}
How does the code have to look like for removed characters?
Update - added a few more examples
example 1:
string a = "foobar";
string b = "fooar";
expected result:
'f' Equal
'o' Equal
'o' Equal
'b' Remove
'a' Equal
'r' Equal
example 2:
string a = "asdfghjk";
string b = "wsedrftr";
expected result:
'a' Remove
'w' Add
's' Equal
'e' Add
'd' Equal
'r' Add
'f' Equal
'g' Remove
'h' Remove
'j' Remove
'k' Remove
't' Add
'r' Add
Update:
Here is a comparison between Dmitry's and ingen's answer: https://dotnetfiddle.net/MJQDAO

You are looking for (minimum) edit distance / (minimum) edit sequence. You can find the theory of the process here:
https://web.stanford.edu/class/cs124/lec/med.pdf
Let's implement (simplest) Levenstein Distance / Sequence algorithm (for details see https://en.wikipedia.org/wiki/Levenshtein_distance). Let's start from helper classes (I've changed a bit your implementation of them):
public enum EditOperationKind : byte {
None, // Nothing to do
Add, // Add new character
Edit, // Edit character into character (including char into itself)
Remove, // Delete existing character
};
public struct EditOperation {
public EditOperation(char valueFrom, char valueTo, EditOperationKind operation) {
ValueFrom = valueFrom;
ValueTo = valueTo;
Operation = valueFrom == valueTo ? EditOperationKind.None : operation;
}
public char ValueFrom { get; }
public char ValueTo {get ;}
public EditOperationKind Operation { get; }
public override string ToString() {
switch (Operation) {
case EditOperationKind.None:
return $"'{ValueTo}' Equal";
case EditOperationKind.Add:
return $"'{ValueTo}' Add";
case EditOperationKind.Remove:
return $"'{ValueFrom}' Remove";
case EditOperationKind.Edit:
return $"'{ValueFrom}' to '{ValueTo}' Edit";
default:
return "???";
}
}
}
As far as I can see from the examples provided we don't have any edit operation, but add + remove; that's why I've put editCost = 2 when insertCost = 1, int removeCost = 1 (in case of tie: insert + remove vs. edit we put insert + remove).
Now we are ready to implement Levenstein algorithm:
public static EditOperation[] EditSequence(
string source, string target,
int insertCost = 1, int removeCost = 1, int editCost = 2) {
if (null == source)
throw new ArgumentNullException("source");
else if (null == target)
throw new ArgumentNullException("target");
// Forward: building score matrix
// Best operation (among insert, update, delete) to perform
EditOperationKind[][] M = Enumerable
.Range(0, source.Length + 1)
.Select(line => new EditOperationKind[target.Length + 1])
.ToArray();
// Minimum cost so far
int[][] D = Enumerable
.Range(0, source.Length + 1)
.Select(line => new int[target.Length + 1])
.ToArray();
// Edge: all removes
for (int i = 1; i <= source.Length; ++i) {
M[i][0] = EditOperationKind.Remove;
D[i][0] = removeCost * i;
}
// Edge: all inserts
for (int i = 1; i <= target.Length; ++i) {
M[0][i] = EditOperationKind.Add;
D[0][i] = insertCost * i;
}
// Having fit N - 1, K - 1 characters let's fit N, K
for (int i = 1; i <= source.Length; ++i)
for (int j = 1; j <= target.Length; ++j) {
// here we choose the operation with the least cost
int insert = D[i][j - 1] + insertCost;
int delete = D[i - 1][j] + removeCost;
int edit = D[i - 1][j - 1] + (source[i - 1] == target[j - 1] ? 0 : editCost);
int min = Math.Min(Math.Min(insert, delete), edit);
if (min == insert)
M[i][j] = EditOperationKind.Add;
else if (min == delete)
M[i][j] = EditOperationKind.Remove;
else if (min == edit)
M[i][j] = EditOperationKind.Edit;
D[i][j] = min;
}
// Backward: knowing scores (D) and actions (M) let's building edit sequence
List<EditOperation> result =
new List<EditOperation>(source.Length + target.Length);
for (int x = target.Length, y = source.Length; (x > 0) || (y > 0);) {
EditOperationKind op = M[y][x];
if (op == EditOperationKind.Add) {
x -= 1;
result.Add(new EditOperation('\0', target[x], op));
}
else if (op == EditOperationKind.Remove) {
y -= 1;
result.Add(new EditOperation(source[y], '\0', op));
}
else if (op == EditOperationKind.Edit) {
x -= 1;
y -= 1;
result.Add(new EditOperation(source[y], target[x], op));
}
else // Start of the matching (EditOperationKind.None)
break;
}
result.Reverse();
return result.ToArray();
}
Demo:
var sequence = EditSequence("asdfghjk", "wsedrftr");
Console.Write(string.Join(Environment.NewLine, sequence));
Outcome:
'a' Remove
'w' Add
's' Equal
'e' Add
'd' Equal
'r' Add
'f' Equal
'g' Remove
'h' Remove
'j' Remove
'k' Remove
't' Add
'r' Add

I'll go out on a limb here and provide an algorithm that's not the most efficient, but is easy to reason about.
Let's cover some ground first:
1) Order matters
string before = "bar foo"
string after = "foo bar"
Even though "bar" and "foo" occur in both strings, "bar" will need to be removed and added again later. This also tells us it's the after string that gives us the order of chars we're interested in, we want "foo" first.
2) Order over count
Another way to look at it, is that some chars may never get their turn.
string before = "abracadabra"
string after = "bar bar"
Only the bold chars of "bar bar", get their say in "abracadabra". Even though we've got two b's in both strings, only the first one counts. By the time we get to the second b in "bar bar" the second b in "abracadabra" has already been passed, when we were looking for the first occurrence of 'r'.
3) Barriers
Barriers are the chars that exist in both strings, taking order and count into consideration. This already suggests a set might not be the most appropriate data structure, as we would lose count.
For an input
string before = "pinata"
string after = "accidental"
We get (pseudocode)
var barriers = { 'a', 't', 'a' }
"pinata"
"accidental"
Let's follow the execution flow:
'a' is the first barrier, it's also the first char of after so everything prepending the first 'a' in before can be removed. "pinata" -> "ata"
the second barrier is 't', it's not at the next position in our after string, so we can insert everything in between. "ata" -> "accidenta"
the third barrier 'a' is already at the next position, so we can move to the next barrier without doing any real work.
there are no more barriers, but our string length is still less than that of after, so there will be some post processing. "accidenta" -> "accidental"
Note 'i' and 'n' don't get to play, again, order over count.
Implementation
We've established that order and count matter, a Queue comes to mind.
static public List<Difference> CalculateDifferences(string before, string after)
{
List<Difference> result = new List<Difference>();
Queue<char> barriers = new Queue<char>();
#region Preprocessing
int index = 0;
for (int i = 0; i < after.Length; i++)
{
// Look for the first match starting at index
int match = before.IndexOf(after[i], index);
if (match != -1)
{
barriers.Enqueue(after[i]);
index = match + 1;
}
}
#endregion
#region Queue Processing
index = 0;
while (barriers.Any())
{
char barrier = barriers.Dequeue();
// Get the offset to the barrier in both strings,
// ignoring the part that's already been handled
int offsetBefore = before.IndexOf(barrier, index) - index;
int offsetAfter = after.IndexOf(barrier, index) - index;
// Remove prefix from 'before' string
if (offsetBefore > 0)
{
RemoveChars(before.Substring(index, offsetBefore), result);
before = before.Substring(offsetBefore);
}
// Insert prefix from 'after' string
if (offsetAfter > 0)
{
string substring = after.Substring(index, offsetAfter);
AddChars(substring, result);
before = before.Insert(index, substring);
index += substring.Length;
}
// Jump over the barrier
KeepChar(barrier, result);
index++;
}
#endregion
#region Post Queue processing
if (index < before.Length)
{
RemoveChars(before.Substring(index), result);
}
if (index < after.Length)
{
AddChars(after.Substring(index), result);
}
#endregion
return result;
}
static private void KeepChar(char barrier, List<Difference> result)
{
result.Add(new Difference()
{
c = barrier,
op = Operation.Equal
});
}
static private void AddChars(string substring, List<Difference> result)
{
result.AddRange(substring.Select(x => new Difference()
{
c = x,
op = Operation.Add
}));
}
static private void RemoveChars(string substring, List<Difference> result)
{
result.AddRange(substring.Select(x => new Difference()
{
c = x,
op = Operation.Remove
}));
}

I tested with 3 examples above, and it returns the expected result properly and perfectly.
int flag = 0;
int flag_2 = 0;
string a = "asdfghjk";
string b = "wsedrftr";
char[] array_a = a.ToCharArray();
char[] array_b = b.ToCharArray();
for (int i = 0,j = 0, n= 0; i < array_b.Count(); i++)
{
//Execute 1 time until reach first equal character
if(i == 0 && a.Contains(array_b[0]))
{
while (array_a[n] != array_b[0])
{
Console.WriteLine(String.Concat(array_a[n], " : Remove"));
n++;
}
Console.WriteLine(String.Concat(array_a[n], " : Equal"));
n++;
}
else if(i == 0 && !a.Contains(array_b[0]))
{
Console.WriteLine(String.Concat(array_a[n], " : Remove"));
n++;
Console.WriteLine(String.Concat(array_b[0], " : Add"));
}
else
{
if(n < array_a.Count())
{
if (array_a[n] == array_b[i])
{
Console.WriteLine(String.Concat(array_a[n], " : Equal"));
n++;
}
else
{
flag = 0;
for (int z = n; z < array_a.Count(); z++)
{
if (array_a[z] == array_b[i])
{
flag = 1;
break;
}
}
if (flag == 0)
{
flag_2 = 0;
for (int aa = i; aa < array_b.Count(); aa++)
{
for(int bb = n; bb < array_a.Count(); bb++)
{
if (array_b[aa] == array_a[bb])
{
flag_2 = 1;
break;
}
}
}
if(flag_2 == 1)
{
Console.WriteLine(String.Concat(array_b[i], " : Add"));
}
else
{
for (int z = n; z < array_a.Count(); z++)
{
Console.WriteLine(String.Concat(array_a[z], " : Remove"));
n++;
}
Console.WriteLine(String.Concat(array_b[i], " : Add"));
}
}
else
{
Console.WriteLine(String.Concat(array_a[n], " : Remove"));
i--;
n++;
}
}
}
else
{
Console.WriteLine(String.Concat(array_b[i], " : Add"));
}
}
}//end for
MessageBox.Show("Done");
//OUTPUT CONSOLE:
/*
a : Remove
w : Add
s : Equal
e : Add
d : Equal
r : Add
f : Equal
g : Remove
h : Remove
j : Remove
k : Remove
t : Add
r : Add
*/

Here might be another solution, full code and commented.
However the result of your first original example is inverted :
class Program
{
enum CharState
{
Add,
Equal,
Remove
}
struct CharResult
{
public char c;
public CharState state;
}
static void Main(string[] args)
{
string a = "asdfghjk";
string b = "wsedrftr";
while (true)
{
Console.WriteLine("Enter string a (enter to quit) :");
a = Console.ReadLine();
if (a == string.Empty)
break;
Console.WriteLine("Enter string b :");
b = Console.ReadLine();
List<CharResult> result = calculate(a, b);
DisplayResults(result);
}
Console.WriteLine("Press a key to exit");
Console.ReadLine();
}
static List<CharResult> calculate(string a, string b)
{
List<CharResult> res = new List<CharResult>();
int i = 0, j = 0;
char[] array_a = a.ToCharArray();
char[] array_b = b.ToCharArray();
while (i < array_a.Length && j < array_b.Length)
{
//For the current char in a, we check for the equal in b
int index = b.IndexOf(array_a[i], j);
if (index < 0) //not found, this char should be removed
{
res.Add(new CharResult() { c = array_a[i], state = CharState.Remove });
i++;
}
else
{
//we add all the chars between B's current index and the index
while (j < index)
{
res.Add(new CharResult() { c = array_b[j], state = CharState.Add });
j++;
}
//then we say the current is the same
res.Add(new CharResult() { c = array_a[i], state = CharState.Equal });
i++;
j++;
}
}
while (i < array_a.Length)
{
//b is now empty, we remove the remains
res.Add(new CharResult() { c = array_a[i], state = CharState.Remove });
i++;
}
while (j < array_b.Length)
{
//a has been treated, we add the remains
res.Add(new CharResult() { c = array_b[j], state = CharState.Add });
j++;
}
return res;
}
static void DisplayResults(List<CharResult> results)
{
foreach (CharResult r in results)
{
Console.WriteLine($"'{r.c}' - {r.state}");
}
}
}

If you want to have a precise comparison between two strings, you must read and understand Levenshtein Distance. by using this algorithm you can precisely calculate rate of similarity between two string and also you can backtrack the algorithm to get the chain of changing on the second string. this algorithm is a important metric for Natural Language Processing also.
there are some other benefits and it's need time to learn.
in this link there is a C# version of Levenshtein Distance :
https://www.dotnetperls.com/levenshtein

Related

How to find number of specific strings in a string in c#

There is a string: xxoxoxoxoxoxooxxxxox where x is a seat that is occupied and o is not, I have to find individual occupied seats, with both sides having an x.
I tried to look at
for (int i = 0; i < string.Length; i++) {
if(string[i]=='x' && string[i + 1]=='o' && string[i + 2] == 'x')
{
count++;
}
}
but i got error so I was wondering if theres a good way to do it.
As the question is pretty unclear, I am assuming that you are looking for a pattern xox and want to know the position of o.
you can run a for loop and get the index.
to get the count of such patterns. you can increment the count by 1.
string str = "xxoxoxoxoxoxooxxxxox";
for(int i = 0; i < str.Length - 2; i++)
{
if (str[i] == 'x' && str[i +1] == 'o' && str[i+ 2] == 'x')
{
Console.WriteLine(i + 1);
count++;
}
}
you can change the character value based on your requirement.
you can use regex.matches to find all matches ...
string s = "xxoxoxoxoxoxooxxxxox";
Regex rx = new Regex("xox");
foreach (Match match in rx.Matches(s))
{
Console.WriteLine("Match index: "+ match.Index);
}
RegEx approach which gives you all indices of individual occupied seats oxo https://dotnetfiddle.net/3jc1Vq
string input = "xxoxoxoxoxoxooxxxxox";
// ^ ^ ^ ^ ^ ^
int[] indices = Regex.Matches(input, "(?<=x)o(?=x)").Cast<Match>().Select(x => x.Index).ToArray();
// in case you only want the count
int count = Regex.Matches(input, "(?<=x)o(?=x)").Count();
I made a working example that makes use of ReadOnlySpan<T> and avoids RegEx and over allocation.
using System;
using System.Collections.Generic;
public class Program
{
public static void Main()
{
string seats = "xxoxoxoxoxoxooxxxxox";
var results = seats.ToCharArray().GetSingles('o');
foreach(var i in results)
{
Console.WriteLine(i);
}
}
}
public static class Ext
{
public static IReadOnlyList<int> GetSingles<T>(this T[] source, T search)
{
var results = new List<int>();
if(source.Length == 0)
{
return results;
}
if (source.Length == 1)
{
if (source[0].Equals(search))
{
results.Add(0);
}
return results;
}
if(source.Length >= 2)
{
if (source[0].Equals(search) && ! source[1].Equals(search))
{
results.Add(0);
}
if (source.Length == 2)
{
if (!source[0].Equals(search) && source[1].Equals(search))
{
results.Add(1);
}
return results;
}
}
ReadOnlySpan<T> window = new ReadOnlySpan<T>(source, 0, 3);
int i = 1;
for(; i < source.Length - 1; i++)
{
window = new ReadOnlySpan<T>(source, i - 1, 3);
if(!window[0].Equals(search) &&
window[1].Equals(search) &&
!window[2].Equals(search))
{
results.Add(i);
}
}
if(!window[1].Equals(search) && window[2].Equals(search))
{
results.Add(i + 1);
}
return results;
}
}
This outputs,
2
4
6
8
10
18
With the more challenging test data,
public class Program
{
public static void Main()
{
var tests = new string[]
{
"",
"o",
"x",
"oo",
"ox",
"xo",
"xx",
"oxx",
"oox",
"xox",
"xoo",
"xoxoxoxo",
"xoxoxoxoo",
"xoxoxox"
};
for(var i = 0; i < tests.Length; i++)
{
string seats = tests[i];
Console.WriteLine($"{i}:\"{seats}\"");
var results = seats.ToCharArray().GetSingles('o');
foreach(var r in results)
{
Console.WriteLine(r);
}
}
}
}
we get the correct output,
0:""
1:"o"
0
2:"x"
3:"oo"
4:"ox"
0
5:"xo"
1
6:"xx"
7:"oxx"
0
8:"oox"
9:"xox"
1
10:"xoo"
11:"xoxoxoxo"
1
3
5
8
12:"xoxoxoxoo"
1
3
5
13:"xoxoxox"
1
3
5

How to create a sequence of strings between "start" and "end" strings [duplicate]

I have a question about iterate through the Alphabet.
I would like to have a loop that begins with "a" and ends with "z". After that, the loop begins "aa" and count to "az". after that begins with "ba" up to "bz" and so on...
Anybody know some solution?
Thanks
EDIT: I forgot that I give a char "a" to the function then the function must return b. if u give "bnc" then the function must return "bnd"
First effort, with just a-z then aa-zz
public static IEnumerable<string> GetExcelColumns()
{
for (char c = 'a'; c <= 'z'; c++)
{
yield return c.ToString();
}
char[] chars = new char[2];
for (char high = 'a'; high <= 'z'; high++)
{
chars[0] = high;
for (char low = 'a'; low <= 'z'; low++)
{
chars[1] = low;
yield return new string(chars);
}
}
}
Note that this will stop at 'zz'. Of course, there's some ugly duplication here in terms of the loops. Fortunately, that's easy to fix - and it can be even more flexible, too:
Second attempt: more flexible alphabet
private const string Alphabet = "abcdefghijklmnopqrstuvwxyz";
public static IEnumerable<string> GetExcelColumns()
{
return GetExcelColumns(Alphabet);
}
public static IEnumerable<string> GetExcelColumns(string alphabet)
{
foreach(char c in alphabet)
{
yield return c.ToString();
}
char[] chars = new char[2];
foreach(char high in alphabet)
{
chars[0] = high;
foreach(char low in alphabet)
{
chars[1] = low;
yield return new string(chars);
}
}
}
Now if you want to generate just a, b, c, d, aa, ab, ac, ad, ba, ... you'd call GetExcelColumns("abcd").
Third attempt (revised further) - infinite sequence
public static IEnumerable<string> GetExcelColumns(string alphabet)
{
int length = 0;
char[] chars = null;
int[] indexes = null;
while (true)
{
int position = length-1;
// Try to increment the least significant
// value.
while (position >= 0)
{
indexes[position]++;
if (indexes[position] == alphabet.Length)
{
for (int i=position; i < length; i++)
{
indexes[i] = 0;
chars[i] = alphabet[0];
}
position--;
}
else
{
chars[position] = alphabet[indexes[position]];
break;
}
}
// If we got all the way to the start of the array,
// we need an extra value
if (position == -1)
{
length++;
chars = new char[length];
indexes = new int[length];
for (int i=0; i < length; i++)
{
chars[i] = alphabet[0];
}
}
yield return new string(chars);
}
}
It's possible that it would be cleaner code using recursion, but it wouldn't be as efficient.
Note that if you want to stop at a certain point, you can just use LINQ:
var query = GetExcelColumns().TakeWhile(x => x != "zzz");
"Restarting" the iterator
To restart the iterator from a given point, you could indeed use SkipWhile as suggested by thesoftwarejedi. That's fairly inefficient, of course. If you're able to keep any state between call, you can just keep the iterator (for either solution):
using (IEnumerator<string> iterator = GetExcelColumns())
{
iterator.MoveNext();
string firstAttempt = iterator.Current;
if (someCondition)
{
iterator.MoveNext();
string secondAttempt = iterator.Current;
// etc
}
}
Alternatively, you may well be able to structure your code to use a foreach anyway, just breaking out on the first value you can actually use.
Edit: Made it do exactly as the OP's latest edit wants
This is the simplest solution, and tested:
static void Main(string[] args)
{
Console.WriteLine(GetNextBase26("a"));
Console.WriteLine(GetNextBase26("bnc"));
}
private static string GetNextBase26(string a)
{
return Base26Sequence().SkipWhile(x => x != a).Skip(1).First();
}
private static IEnumerable<string> Base26Sequence()
{
long i = 0L;
while (true)
yield return Base26Encode(i++);
}
private static char[] base26Chars = "abcdefghijklmnopqrstuvwxyz".ToCharArray();
private static string Base26Encode(Int64 value)
{
string returnValue = null;
do
{
returnValue = base26Chars[value % 26] + returnValue;
value /= 26;
} while (value-- != 0);
return returnValue;
}
The following populates a list with the required strings:
List<string> result = new List<string>();
for (char ch = 'a'; ch <= 'z'; ch++){
result.Add (ch.ToString());
}
for (char i = 'a'; i <= 'z'; i++)
{
for (char j = 'a'; j <= 'z'; j++)
{
result.Add (i.ToString() + j.ToString());
}
}
I know there are plenty of answers here, and one's been accepted, but IMO they all make it harder than it needs to be. I think the following is simpler and cleaner:
static string NextColumn(string column){
char[] c = column.ToCharArray();
for(int i = c.Length - 1; i >= 0; i--){
if(char.ToUpper(c[i]++) < 'Z')
break;
c[i] -= (char)26;
if(i == 0)
return "A" + new string(c);
}
return new string(c);
}
Note that this doesn't do any input validation. If you don't trust your callers, you should add an IsNullOrEmpty check at the beginning, and a c[i] >= 'A' && c[i] <= 'Z' || c[i] >= 'a' && c[i] <= 'z' check at the top of the loop. Or just leave it be and let it be GIGO.
You may also find use for these companion functions:
static string GetColumnName(int index){
StringBuilder txt = new StringBuilder();
txt.Append((char)('A' + index % 26));
//txt.Append((char)('A' + --index % 26));
while((index /= 26) > 0)
txt.Insert(0, (char)('A' + --index % 26));
return txt.ToString();
}
static int GetColumnIndex(string name){
int rtn = 0;
foreach(char c in name)
rtn = rtn * 26 + (char.ToUpper(c) - '#');
return rtn - 1;
//return rtn;
}
These two functions are zero-based. That is, "A" = 0, "Z" = 25, "AA" = 26, etc. To make them one-based (like Excel's COM interface), remove the line above the commented line in each function, and uncomment those lines.
As with the NextColumn function, these functions don't validate their inputs. Both with give you garbage if that's what they get.
Here’s what I came up with.
/// <summary>
/// Return an incremented alphabtical string
/// </summary>
/// <param name="letter">The string to be incremented</param>
/// <returns>the incremented string</returns>
public static string NextLetter(string letter)
{
const string alphabet = "ABCDEFGHIJKLMNOPQRSTUVWXYZ";
if (!string.IsNullOrEmpty(letter))
{
char lastLetterInString = letter[letter.Length - 1];
// if the last letter in the string is the last letter of the alphabet
if (alphabet.IndexOf(lastLetterInString) == alphabet.Length - 1)
{
//replace the last letter in the string with the first leter of the alphbat and get the next letter for the rest of the string
return NextLetter(letter.Substring(0, letter.Length - 1)) + alphabet[0];
}
else
{
// replace the last letter in the string with the proceeding letter of the alphabet
return letter.Remove(letter.Length-1).Insert(letter.Length-1, (alphabet[alphabet.IndexOf(letter[letter.Length-1])+1]).ToString() );
}
}
//return the first letter of the alphabet
return alphabet[0].ToString();
}
just curious , why not just
private string alphRecursive(int c) {
var alphabet = "abcdefghijklmnopqrstuvwxyz".ToCharArray();
if (c >= alphabet.Length) {
return alphRecursive(c/alphabet.Length) + alphabet[c%alphabet.Length];
} else {
return "" + alphabet[c%alphabet.Length];
}
}
This is like displaying an int, only using base 26 in stead of base 10. Try the following algorithm to find the nth entry of the array
q = n div 26;
r = n mod 26;
s = '';
while (q > 0 || r > 0) {
s = alphabet[r] + s;
q = q div 26;
r = q mod 26;
}
Of course, if you want the first n entries, this is not the most efficient solution. In this case, try something like daniel's solution.
I gave this a go and came up with this:
using System;
using System.Collections.Generic;
using System.Linq;
using System.Text;
namespace Alphabetty
{
class Program
{
const string alphabet = "abcdefghijklmnopqrstuvwxyz";
static int cursor = 0;
static int prefixCursor;
static string prefix = string.Empty;
static bool done = false;
static void Main(string[] args)
{
string s = string.Empty;
while (s != "Done")
{
s = GetNextString();
Console.WriteLine(s);
}
Console.ReadKey();
}
static string GetNextString()
{
if (done) return "Done";
char? nextLetter = GetNextLetter(ref cursor);
if (nextLetter == null)
{
char? nextPrefixLetter = GetNextLetter(ref prefixCursor);
if(nextPrefixLetter == null)
{
done = true;
return "Done";
}
prefix = nextPrefixLetter.Value.ToString();
nextLetter = GetNextLetter(ref cursor);
}
return prefix + nextLetter;
}
static char? GetNextLetter(ref int letterCursor)
{
if (letterCursor == alphabet.Length)
{
letterCursor = 0;
return null;
}
char c = alphabet[letterCursor];
letterCursor++;
return c;
}
}
}
Here is something I had cooked up that may be similar. I was experimenting with iteration counts in order to design a numbering schema that was as small as possible, yet gave me enough uniqueness.
I knew that each time a added an Alpha character, it would increase the possibilities 26x but I wasn't sure how many letters, numbers, or the pattern I wanted to use.
That lead me to the code below. Basically you pass it an AlphaNumber string, and every position that has a Letter, would eventually increment to "z\Z" and every position that had a Number, would eventually increment to "9".
So you can call it 1 of two ways..
//This would give you the next Itteration... (H3reIsaStup4dExamplf)
string myNextValue = IncrementAlphaNumericValue("H3reIsaStup4dExample")
//Or Loop it resulting eventually as "Z9zzZzzZzzz9zZzzzzzz"
string myNextValue = "H3reIsaStup4dExample"
while (myNextValue != null)
{
myNextValue = IncrementAlphaNumericValue(myNextValue)
//And of course do something with this like write it out
}
(For me, I was doing something like "1AA000")
public string IncrementAlphaNumericValue(string Value)
{
//We only allow Characters a-b, A-Z, 0-9
if (System.Text.RegularExpressions.Regex.IsMatch(Value, "^[a-zA-Z0-9]+$") == false)
{
throw new Exception("Invalid Character: Must be a-Z or 0-9");
}
//We work with each Character so it's best to convert the string to a char array for incrementing
char[] myCharacterArray = Value.ToCharArray();
//So what we do here is step backwards through the Characters and increment the first one we can.
for (Int32 myCharIndex = myCharacterArray.Length - 1; myCharIndex >= 0; myCharIndex--)
{
//Converts the Character to it's ASCII value
Int32 myCharValue = Convert.ToInt32(myCharacterArray[myCharIndex]);
//We only Increment this Character Position, if it is not already at it's Max value (Z = 90, z = 122, 57 = 9)
if (myCharValue != 57 && myCharValue != 90 && myCharValue != 122)
{
myCharacterArray[myCharIndex]++;
//Now that we have Incremented the Character, we "reset" all the values to the right of it
for (Int32 myResetIndex = myCharIndex + 1; myResetIndex < myCharacterArray.Length; myResetIndex++)
{
myCharValue = Convert.ToInt32(myCharacterArray[myResetIndex]);
if (myCharValue >= 65 && myCharValue <= 90)
{
myCharacterArray[myResetIndex] = 'A';
}
else if (myCharValue >= 97 && myCharValue <= 122)
{
myCharacterArray[myResetIndex] = 'a';
}
else if (myCharValue >= 48 && myCharValue <= 57)
{
myCharacterArray[myResetIndex] = '0';
}
}
//Now we just return an new Value
return new string(myCharacterArray);
}
}
//If we got through the Character Loop and were not able to increment anything, we retun a NULL.
return null;
}
Here's my attempt using recursion:
public static void PrintAlphabet(string alphabet, string prefix)
{
for (int i = 0; i < alphabet.Length; i++) {
Console.WriteLine(prefix + alphabet[i].ToString());
}
if (prefix.Length < alphabet.Length - 1) {
for (int i = 0; i < alphabet.Length; i++) {
PrintAlphabet(alphabet, prefix + alphabet[i]);
}
}
}
Then simply call PrintAlphabet("abcd", "");

How to auto-increment number and letter to generate a string sequence wise in c#

I have to make a string which consists a string like - AAA0009, and once it reaches AAA0009, it will generate AA0010 to AAA0019 and so on.... till AAA9999 and when it will reach to AAA9999, it will give AAB0000 to AAB9999 and so on till ZZZ9999.
I want to use static class and static variables so that it can auto increment by itself on every hit.
I have tried some but not even close, so help me out thanks.
Thanks for being instructive I was trying as I Said already but anyways you already want to put negatives over there without even knowing the thing:
Code:
public class GenerateTicketNumber
{
private static int num1 = 0;
public static string ToBase36()
{
const string base36 = "0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ";
var sb = new StringBuilder(9);
do
{
sb.Insert(0, base36[(byte)(num1 % 36)]);
num1 /= 36;
} while (num1 != 0);
var paddedString = "#T" + sb.ToString().PadLeft(8, '0');
num1 = num1 + 1;
return paddedString;
}
}
above is the code. this will generate a sequence but not the way I want anyways will use it and thanks for help.
Though there's already an accepted answer, I would like to share this one.
P.S. I do not claim that this is the best approach, but in my previous work we made something similar using Azure Table Storage which is a no sql database (FYI) and it works.
1.) Create a table to store your running ticket number.
public class TicketNumber
{
public string Type { get; set; } // Maybe you want to have different types of ticket?
public string AlphaPrefix { get; set; }
public string NumericPrefix { get; set; }
public TicketNumber()
{
this.AlphaPrefix = "AAA";
this.NumericPrefix = "0001";
}
public void Increment()
{
int num = int.Parse(this.NumericPrefix);
if (num + 1 >= 9999)
{
num = 1;
int i = 2; // We are assuming that there are only 3 characters
bool isMax = this.AlphaPrefix == "ZZZ";
if (isMax)
{
this.AlphaPrefix = "AAA"; // reset
}
else
{
while (this.AlphaPrefix[i] == 'Z')
{
i--;
}
char iChar = this.AlphaPrefix[i];
StringBuilder sb = new StringBuilder(this.AlphaPrefix);
sb[i] = (char)(iChar + 1);
this.AlphaPrefix = sb.ToString();
}
}
else
{
num++;
}
this.NumericPrefix = num.ToString().PadLeft(4, '0');
}
public override string ToString()
{
return this.AlphaPrefix + this.NumericPrefix;
}
}
2.) Make sure you perform row-level locking and issue an error when it fails.
Here's an oracle syntax:
SELECT * FROM TICKETNUMBER WHERE TYPE = 'TYPE' FOR UPDATE NOWAIT;
This query locks the row and returns an error if the row is currently locked by another session.
We need this to make sure that even if you have millions of users generating a ticket number, it will not mess up the sequence.
Just make sure to save the new ticket number before you perform a COMMIT.
I forgot the MSSQL version of this but I recall using WITH (ROWLOCK) or something. Just google it.
3.) Working example:
static void Main()
{
TicketNumber ticketNumber = new TicketNumber();
ticketNumber.AlphaPrefix = "ZZZ";
ticketNumber.NumericPrefix = "9999";
for (int i = 0; i < 10; i++)
{
Console.WriteLine(ticketNumber);
ticketNumber.Increment();
}
Console.Read();
}
Output:
Looking at your code that you've provided, it seems that you're backing this with a number and just want to convert that to a more user-friendly text representation.
You could try something like this:
private static string ValueToId(int value)
{
var parts = new List<string>();
int numberPart = value % 10000;
parts.Add(numberPart.ToString("0000"));
value /= 10000;
for (int i = 0; i < 3 || value > 0; ++i)
{
parts.Add(((char)(65 + (value % 26))).ToString());
value /= 26;
}
return string.Join(string.Empty, parts.AsEnumerable().Reverse().ToArray());
}
It will take the first 4 characters and use them as is, and then for the remainder of the value if will convert it into characters A-Z.
So 9999 becomes AAA9999, 10000 becomes AAB0000, and 270000 becomes ABB0000.
If the number is big enough that it exceeds 3 characters, it will add more letters at the start.
Here's an example of how you could go about implementing it
void Main()
{
string template = #"AAAA00";
var templateChars = template.ToCharArray();
for (int i = 0; i < 100000; i++)
{
templateChars = IncrementCharArray(templateChars);
Console.WriteLine(string.Join("",templateChars ));
}
}
public static char Increment(char val)
{
if(val == '9') return 'A';
if(val == 'Z') return '0';
return ++val;
}
public static char[] IncrementCharArray(char[] val)
{
if (val.All(chr => chr == 'Z'))
{
var newArray = new char[val.Length + 1];
for (int i = 0; i < newArray.Length; i++)
{
newArray[i] = '0';
}
return newArray;
}
int length = val.Length;
while (length > -1)
{
char lastVal = val[--length];
val[length] = Increment(lastVal);
if ( val[length] != '0') break;
}
return val;
}

C# foreach with string - ignore last character

I have a methode who add numbers together parsed from a string.
If user type : "52+7+1", it will result in (60)
"52++2+3", "52+c+2", "+52+2", "52+2++", ... won't work.
My code works almost perfectly, expect... it ignores the last character. It works when, in the code I add "+0" to the string but of course it brokes the condition who prevent the user to type "+" as a last character.
public int addFromString(string str)
{
bool valid_str = true;
bool current_char_numeric = false;
string unparsedNumber = "";
int parsedNumber = 0;
List<int> parsedNumbers = new List<int>();
if (string.IsNullOrEmpty(chaine))
chaine_valide = false;
else
{
if (!int.TryParse(str[0].ToString(), out parsedNumber))
valid_str = false;
if (!int.TryParse(str[str.Length - 1].ToString(), out parsedNumber))
valid_str = false;
}
foreach (char c in str)
{
current_char_numeric = int.TryParse(c.ToString(), out parsedNumber);
if (current_char_numeric)
unparsedNumber += c;
else if(c == '+')
{
int.TryParse(unparsedNumber, out parsedNumber);
parsedNumbers.Add(parsedNumber);
if (str.IndexOf(c) < str.Length && str.ElementAt(str.IndexOf(c) + 1) == '+')
valid_str = false;
//Just in case :
unparsedNumber = "";
current_char_numeric = int.TryParse(c.ToString(), out parsedNumber);
}
else valid_str = false;
}
int result = 0;
if(valid_str) { foreach(int n in parsedNumbers) { result += n; } }
return result;
}
So if I type : "52+2" I get 52
If I type : "52+2+6" I get 54
It misses the last value because you only add numbers if you find a +. So for the last unparsedNumber you never enter the else if (c == '+') block.
Let me suggest an more compact solution:
public int addFromString(string str)
{
string trimmed = str.Trim();
if (str.StartsWith("+") || str.EndsWith("+")) return 0; // invalid -> return immediatly
// split string at "+" and trim parts
string[] numbers = str.Split('+').Select(s => s.Trim()).ToArray();
int result = 0;
foreach(string number in numbers)
{
int n;
if (!int.TryParse(number, out n)) return 0; // invalid -> return
result += n;
}
return result;
}
You only add a number to the numbers collection when you encounter a +.
What about the last number? There's no '+' after that.
You should add unparsedNumber to parsedNumbers for the last number too.
You can do a more elegant version:
public int addFromString(string str)
{
int parsedNumber = 0;
int result = 0;
if (string.IsNullOrEmpty(chaine))
{
return result;
}
else
{
if (!int.TryParse(str[0].ToString(), out parsedNumber)
|| !int.TryParse(str[str.Length - 1].ToString(), out parsedNumber))
{
return result;
}
}
try
{
result = str.Split(new char[] { '+' }).Select(s => Convert.ToInt32(s)).Sum();
}
finally
{
return result;
}
}
It seems that all you want is Split:
string source = "52+7+1";
int sum = 0; // initial sum is 0
bool chaine_valide = true; // the chain is valid (we don't have any counter examples)
// Split on terms: 52, 7, 1
foreach (string term in source.Split('+')) {
int value;
// No need in Trim() etc. - TryParse is smart enough
if (int.TryParse(term, out value))
sum += value; // valid term: add it up
else {
chaine_valide = false; // counter example: term is not a valid integer
break;
}
}
...
Console.Write(chaine_valide ? sum.ToString() : "Invalid formula");
In case of C# 7.0 you can (with a help of out var) simplify the code into
int sum = 0; // initial sum is 0
bool chaine_valide = true; // the chain is valid (we don't have any counter examples)
// Split on terms: 52, 7, 1
foreach (string term in source.Split('+'))
if (int.TryParse(term, out var value))
sum += value; // valid term: add it up
else {
chaine_valide = false; // counter example: term is not a valid integer
break;
}

Program to find minimum number in string

I have a c# class like so
internal class QueuedMinimumNumberFinder : ConcurrentQueue<int>
{
private readonly string _minString;
public QueuedMinimumNumberFinder(string number, int takeOutAmount)
{
if (number.Length < takeOutAmount)
{
throw new Exception("Error *");
}
var queueIndex = 0;
var queueAmount = number.Length - takeOutAmount;
var numQueue = new ConcurrentQueue<int>(number.ToCharArray().Where(m => (int) Char.GetNumericValue(m) != 0).Select(m=>(int)Char.GetNumericValue(m)).OrderBy(m=>m));
var zeroes = number.Length - numQueue.Count;
while (queueIndex < queueAmount)
{
int next;
if (queueIndex == 0)
{
numQueue.TryDequeue(out next);
Enqueue(next);
} else
{
if (zeroes > 0)
{
Enqueue(0);
zeroes--;
} else
{
numQueue.TryDequeue(out next);
Enqueue(next);
}
}
queueIndex++;
}
var builder = new StringBuilder();
while (Count > 0)
{
int next = 0;
TryDequeue(out next);
builder.Append(next.ToString());
}
_minString = builder.ToString();
}
public override string ToString() { return _minString; }
}
The point of the program is to find the minimum possible integer that can be made by taking out any x amount of characters from a string(example 100023 is string, if you take out any 3 letters, the minimum int created would be 100). My question is, is this the correct way to do this? Is there a better data structure that can be used for this problem?
First Edit:
Here's how it looks now
internal class QueuedMinimumNumberFinder
{
private readonly string _minString;
public QueuedMinimumNumberFinder(string number, int takeOutAmount)
{
var queue = new Queue<int>();
if (number.Length < takeOutAmount)
{
throw new Exception("Error *");
}
var queueIndex = 0;
var queueAmount = number.Length - takeOutAmount;
var numQueue = new List<int>(number.Where(m=>(int)Char.GetNumericValue(m)!=0).Select(m=>(int)Char.GetNumericValue(m))).ToList();
var zeroes = number.Length - numQueue.Count;
while (queueIndex < queueAmount)
{
if (queueIndex == 0)
{
var nextMin = numQueue.Min();
numQueue.Remove(nextMin);
queue.Enqueue(nextMin);
} else
{
if (zeroes > 1)
{
queue.Enqueue(0);
zeroes--;
} else
{
var nextMin = numQueue.Min();
numQueue.Remove(nextMin);
queue.Enqueue(nextMin);
}
}
queueIndex++;
}
var builder = new StringBuilder();
while (queue.Count > 0)
{
builder.Append(queue.Dequeue().ToString());
}
_minString = builder.ToString();
}
public override string ToString() { return _minString; }
}
A pretty simple and efficient implementation can be made, once you realize that your input string digits map to the domain of only 10 possible values: '0' .. '9'.
This can be encoded as the number of occurrences of a specific digit in your input string using a simple array of 10 integers: var digit_count = new int[10];
#MasterGillBates describes this idea in his answer.
You can then regard this array as your priority queue from which you can dequeue the characters you need by iteratively removing the lowest available character (decreasing its occurrence count in the array).
The code sample below provides an example implementation for this idea.
public static class MinNumberSolver
{
public static string GetMinString(string number, int takeOutAmount)
{
// "Add" the string by simply counting digit occurrance frequency.
var digit_count = new int[10];
foreach (var c in number)
if (char.IsDigit(c))
digit_count[c - '0']++;
// Now remove them one by one in lowest to highest order.
// For the first character we skip any potential leading 0s
var selected = new char[takeOutAmount];
var start_index = 1;
selected[0] = TakeLowest(digit_count, ref start_index);
// For the rest we start in digit order at '0' first.
start_index = 0;
for (var i = 0; i < takeOutAmount - 1; i++)
selected[1 + i] = TakeLowest(digit_count, ref start_index);
// And return the result.
return new string(selected);
}
private static char TakeLowest(int[] digit_count, ref int start_index)
{
for (var i = start_index; i < digit_count.Length; i++)
{
if (digit_count[i] > 0)
{
start_index = ((--digit_count[i] > 0) ? i : i + 1);
return (char)('0' + i);
}
}
throw new InvalidDataException("Input string does not have sufficient digits");
}
}
Just keep a count of how many times each digit appears. An array of size 10 will do. Count[i] gives the count of digit i.
Then pick the smallest non-zero i first, then pick the smallest etc and form your number.
Here's my solution using LINQ:
public string MinimumNumberFinder(string number, int takeOutAmount)
{
var ordered = number.OrderBy(n => n);
var nonZero = ordered.SkipWhile(n => n == '0');
var zero = ordered.TakeWhile(n => n == '0');
var result = nonZero.Take(1)
.Concat(zero)
.Concat(nonZero.Skip(1))
.Take(number.Length - takeOutAmount);
return new string(result.ToArray());
}
You could place every integer into a list and find all possible sequences of these values. From the list of sequences, you could sort through taking only the sets which have the number of integers you want. From there, you can write a quick function which parses a sequence into an integer. Next, you could store all of your parsed sequences into an array or an other data structure and sort based on value, which will allow you to select the minimum number from the data structure. There may be simpler ways to do this, but this will definitely work and gives you options as far as how many digits you want your number to have.
If I'm understanding this correctly, why don't you just pick out your numbers starting with the smallest number greater than zero. Then pick out all zeroes, then any remaining number if all the zeroes are picked up. This is all depending on the length of your ending result
In your example you have a 6 digit number and you want to pick out 3 digits. This means you'll only have 3 digits left. If it was a 10 digit number, then you would end up with a 7 digit number, etc...
So have an algorithm that knows the length of your starting number, how many digits you plan on removing, and the length of your ending number. Then just pick out the numbers.
This is just quick and dirty code:
string startingNumber = "9999903040404"; // "100023";
int numberOfCharactersToRemove = 3;
string endingNumber = string.Empty;
int endingNumberLength = startingNumber.Length - numberOfCharactersToRemove;
while (endingNumber.Length < endingNumberLength)
{
if (string.IsNullOrEmpty(endingNumber))
{
// Find the smallest digit in the starting number
for (int i = 1; i <= 9; i++)
{
if (startingNumber.Contains(i.ToString()))
{
endingNumber += i.ToString();
startingNumber = startingNumber.Remove(startingNumber.IndexOf(i.ToString()), 1);
break;
}
}
}
else if (startingNumber.Contains("0"))
{
// Add any zeroes
endingNumber += "0";
startingNumber = startingNumber.Remove(startingNumber.IndexOf("0"), 1);
}
else
{
// Add any remaining numbers from least to greatest
for (int i = 1; i <= 9; i++)
{
if (startingNumber.Contains(i.ToString()))
{
endingNumber += i.ToString();
startingNumber = startingNumber.Remove(startingNumber.IndexOf(i.ToString()), 1);
break;
}
}
}
}
Console.WriteLine(endingNumber);
100023 starting number resulted in 100 being the end result
9999903040404 starting number resulted in 3000044499 being the end result
Here's my version to fix this problem:
DESIGN:
You can sort your list using a binary tree , there are a lot of
implementations , I picked this one
Then you can keep track of the number of the Zeros you have in your
string Finally you will end up with two lists: I named one
SortedDigitsList and the other one ZeroDigitsList
perform a switch case to determine which last 3 digits should be
returned
Here's the complete code:
class MainProgram2
{
static void Main()
{
Tree theTree = new Tree();
Console.WriteLine("Please Enter the string you want to process:");
string input = Console.ReadLine();
foreach (char c in input)
{
// Check if it's a digit or not
if (c >= '0' && c <= '9')
{
theTree.Insert((int)Char.GetNumericValue(c));
}
}
//End of for each (char c in input)
Console.WriteLine("Inorder traversal resulting Tree Sort without the zeros");
theTree.Inorder(theTree.ReturnRoot());
Console.WriteLine(" ");
//Format the output depending on how many zeros you have
Console.WriteLine("The final 3 digits are");
switch (theTree.ZeroDigitsList.Count)
{
case 0:
{
Console.WriteLine("{0}{1}{2}", theTree.SortedDigitsList[0], theTree.SortedDigitsList[1], theTree.SortedDigitsList[2]);
break;
}
case 1:
{
Console.WriteLine("{0}{1}{2}", theTree.SortedDigitsList[0], 0, theTree.SortedDigitsList[2]);
break;
}
default:
{
Console.WriteLine("{0}{1}{2}", theTree.SortedDigitsList[0], 0, 0);
break;
}
}
Console.ReadLine();
}
}//End of main()
}
class Node
{
public int item;
public Node leftChild;
public Node rightChild;
public void displayNode()
{
Console.Write("[");
Console.Write(item);
Console.Write("]");
}
}
class Tree
{
public List<int> SortedDigitsList { get; set; }
public List<int> ZeroDigitsList { get; set; }
public Node root;
public Tree()
{
root = null;
SortedDigitsList = new List<int>();
ZeroDigitsList = new List<int>();
}
public Node ReturnRoot()
{
return root;
}
public void Insert(int id)
{
Node newNode = new Node();
newNode.item = id;
if (root == null)
root = newNode;
else
{
Node current = root;
Node parent;
while (true)
{
parent = current;
if (id < current.item)
{
current = current.leftChild;
if (current == null)
{
parent.leftChild = newNode;
return;
}
}
else
{
current = current.rightChild;
if (current == null)
{
parent.rightChild = newNode;
return;
}
}
}
}
}
//public void Preorder(Node Root)
//{
// if (Root != null)
// {
// Console.Write(Root.item + " ");
// Preorder(Root.leftChild);
// Preorder(Root.rightChild);
// }
//}
public void Inorder(Node Root)
{
if (Root != null)
{
Inorder(Root.leftChild);
if (Root.item > 0)
{
SortedDigitsList.Add(Root.item);
Console.Write(Root.item + " ");
}
else
{
ZeroDigitsList.Add(Root.item);
}
Inorder(Root.rightChild);
}
}

Categories