Suppose I had a string:
string str = "1111222233334444";
How can I break this string into chunks of some size?
e.g., breaking this into sizes of 4 would return strings:
"1111"
"2222"
"3333"
"4444"
static IEnumerable<string> Split(string str, int chunkSize)
{
return Enumerable.Range(0, str.Length / chunkSize)
.Select(i => str.Substring(i * chunkSize, chunkSize));
}
Please note that additional code might be required to gracefully handle edge cases (null or empty input string, chunkSize == 0, input string length not divisible by chunkSize, etc.). The original question doesn't specify any requirements for these edge cases and in real life the requirements might vary so they are out of scope of this answer.
In a combination of dove+Konstatin's answers...
static IEnumerable<string> WholeChunks(string str, int chunkSize) {
for (int i = 0; i < str.Length; i += chunkSize)
yield return str.Substring(i, chunkSize);
}
This will work for all strings that can be split into a whole number of chunks, and will throw an exception otherwise.
If you want to support strings of any length you could use the following code:
static IEnumerable<string> ChunksUpto(string str, int maxChunkSize) {
for (int i = 0; i < str.Length; i += maxChunkSize)
yield return str.Substring(i, Math.Min(maxChunkSize, str.Length-i));
}
However, the the OP explicitly stated he does not need this; it's somewhat longer and harder to read, slightly slower. In the spirit of KISS and YAGNI, I'd go with the first option: it's probably the most efficient implementation possible, and it's very short, readable, and, importantly, throws an exception for nonconforming input.
Why not loops? Here's something that would do it quite well:
string str = "111122223333444455";
int chunkSize = 4;
int stringLength = str.Length;
for (int i = 0; i < stringLength ; i += chunkSize)
{
if (i + chunkSize > stringLength) chunkSize = stringLength - i;
Console.WriteLine(str.Substring(i, chunkSize));
}
Console.ReadLine();
I don't know how you'd deal with case where the string is not factor of 4, but not saying you're idea is not possible, just wondering the motivation for it if a simple for loop does it very well? Obviously the above could be cleaned and even put in as an extension method.
Or as mentioned in comments, you know it's /4 then
str = "1111222233334444";
for (int i = 0; i < stringLength; i += chunkSize)
{Console.WriteLine(str.Substring(i, chunkSize));}
This is based on #dove solution but implemented as an extension method.
Benefits:
Extension method
Covers corner cases
Splits string with any chars: numbers, letters, other symbols
Code
public static class EnumerableEx
{
public static IEnumerable<string> SplitBy(this string str, int chunkLength)
{
if (String.IsNullOrEmpty(str)) throw new ArgumentException();
if (chunkLength < 1) throw new ArgumentException();
for (int i = 0; i < str.Length; i += chunkLength)
{
if (chunkLength + i > str.Length)
chunkLength = str.Length - i;
yield return str.Substring(i, chunkLength);
}
}
}
Usage
var result = "bobjoecat".SplitBy(3); // bob, joe, cat
Unit tests removed for brevity (see previous revision)
Using regular expressions and Linq:
List<string> groups = (from Match m in Regex.Matches(str, #"\d{4}")
select m.Value).ToList();
I find this to be more readable, but it's just a personal opinion. It can also be a one-liner : ).
How's this for a one-liner?
List<string> result = new List<string>(Regex.Split(target, #"(?<=\G.{4})", RegexOptions.Singleline));
With this regex it doesn't matter if the last chunk is less than four characters, because it only ever looks at the characters behind it.
I'm sure this isn't the most efficient solution, but I just had to toss it out there.
Starting with .NET 6, we can also use the Chunk method:
var result = str
.Chunk(4)
.Select(x => new string(x))
.ToList();
I recently had to write something that accomplishes this at work, so I thought I would post my solution to this problem. As an added bonus, the functionality of this solution provides a way to split the string in the opposite direction and it does correctly handle unicode characters as previously mentioned by Marvin Pinto above. So, here it is:
using System;
using Extensions;
namespace TestCSharp
{
class Program
{
static void Main(string[] args)
{
string asciiStr = "This is a string.";
string unicodeStr = "これは文字列です。";
string[] array1 = asciiStr.Split(4);
string[] array2 = asciiStr.Split(-4);
string[] array3 = asciiStr.Split(7);
string[] array4 = asciiStr.Split(-7);
string[] array5 = unicodeStr.Split(5);
string[] array6 = unicodeStr.Split(-5);
}
}
}
namespace Extensions
{
public static class StringExtensions
{
/// <summary>Returns a string array that contains the substrings in this string that are seperated a given fixed length.</summary>
/// <param name="s">This string object.</param>
/// <param name="length">Size of each substring.
/// <para>CASE: length > 0 , RESULT: String is split from left to right.</para>
/// <para>CASE: length == 0 , RESULT: String is returned as the only entry in the array.</para>
/// <para>CASE: length < 0 , RESULT: String is split from right to left.</para>
/// </param>
/// <returns>String array that has been split into substrings of equal length.</returns>
/// <example>
/// <code>
/// string s = "1234567890";
/// string[] a = s.Split(4); // a == { "1234", "5678", "90" }
/// </code>
/// </example>
public static string[] Split(this string s, int length)
{
System.Globalization.StringInfo str = new System.Globalization.StringInfo(s);
int lengthAbs = Math.Abs(length);
if (str == null || str.LengthInTextElements == 0 || lengthAbs == 0 || str.LengthInTextElements <= lengthAbs)
return new string[] { str.ToString() };
string[] array = new string[(str.LengthInTextElements % lengthAbs == 0 ? str.LengthInTextElements / lengthAbs: (str.LengthInTextElements / lengthAbs) + 1)];
if (length > 0)
for (int iStr = 0, iArray = 0; iStr < str.LengthInTextElements && iArray < array.Length; iStr += lengthAbs, iArray++)
array[iArray] = str.SubstringByTextElements(iStr, (str.LengthInTextElements - iStr < lengthAbs ? str.LengthInTextElements - iStr : lengthAbs));
else // if (length < 0)
for (int iStr = str.LengthInTextElements - 1, iArray = array.Length - 1; iStr >= 0 && iArray >= 0; iStr -= lengthAbs, iArray--)
array[iArray] = str.SubstringByTextElements((iStr - lengthAbs < 0 ? 0 : iStr - lengthAbs + 1), (iStr - lengthAbs < 0 ? iStr + 1 : lengthAbs));
return array;
}
}
}
Also, here is an image link to the results of running this code: http://i.imgur.com/16Iih.png
It's not pretty and it's not fast, but it works, it's a one-liner and it's LINQy:
List<string> a = text.Select((c, i) => new { Char = c, Index = i }).GroupBy(o => o.Index / 4).Select(g => new String(g.Select(o => o.Char).ToArray())).ToList();
This should be much faster and more efficient than using LINQ or other approaches used here.
public static IEnumerable<string> Splice(this string s, int spliceLength)
{
if (s == null)
throw new ArgumentNullException("s");
if (spliceLength < 1)
throw new ArgumentOutOfRangeException("spliceLength");
if (s.Length == 0)
yield break;
var start = 0;
for (var end = spliceLength; end < s.Length; end += spliceLength)
{
yield return s.Substring(start, spliceLength);
start = end;
}
yield return s.Substring(start);
}
You can use morelinq by Jon Skeet. Use Batch like:
string str = "1111222233334444";
int chunkSize = 4;
var chunks = str.Batch(chunkSize).Select(r => new String(r.ToArray()));
This will return 4 chunks for the string "1111222233334444". If the string length is less than or equal to the chunk size Batch will return the string as the only element of IEnumerable<string>
For output:
foreach (var chunk in chunks)
{
Console.WriteLine(chunk);
}
and it will give:
1111
2222
3333
4444
Personally I prefer my solution :-)
It handles:
String lengths that are a multiple of the chunk size.
String lengths that are NOT a multiple of the chunk size.
String lengths that are smaller than the chunk size.
NULL and empty strings (throws an exception).
Chunk sizes smaller than 1 (throws an exception).
It is implemented as a extension method, and it calculates the number of chunks is going to generate beforehand. It checks the last chunk because in case the text length is not a multiple it needs to be shorter. Clean, short, easy to understand... and works!
public static string[] Split(this string value, int chunkSize)
{
if (string.IsNullOrEmpty(value)) throw new ArgumentException("The string cannot be null.");
if (chunkSize < 1) throw new ArgumentException("The chunk size should be equal or greater than one.");
int remainder;
int divResult = Math.DivRem(value.Length, chunkSize, out remainder);
int numberOfChunks = remainder > 0 ? divResult + 1 : divResult;
var result = new string[numberOfChunks];
int i = 0;
while (i < numberOfChunks - 1)
{
result[i] = value.Substring(i * chunkSize, chunkSize);
i++;
}
int lastChunkSize = remainder > 0 ? remainder : chunkSize;
result[i] = value.Substring(i * chunkSize, lastChunkSize);
return result;
}
Simple and short:
// this means match a space or not a space (anything) up to 4 characters
var lines = Regex.Matches(str, #"[\s\S]{0,4}").Cast<Match>().Select(x => x.Value);
I know question is years old, but here is a Rx implementation. It handles the length % chunkSize != 0 problem out of the box:
public static IEnumerable<string> Chunkify(this string input, int size)
{
if(size < 1)
throw new ArgumentException("size must be greater than 0");
return input.ToCharArray()
.ToObservable()
.Buffer(size)
.Select(x => new string(x.ToArray()))
.ToEnumerable();
}
public static IEnumerable<IEnumerable<T>> SplitEvery<T>(this IEnumerable<T> values, int n)
{
var ls = values.Take(n);
var rs = values.Skip(n);
return ls.Any() ?
Cons(ls, SplitEvery(rs, n)) :
Enumerable.Empty<IEnumerable<T>>();
}
public static IEnumerable<T> Cons<T>(T x, IEnumerable<T> xs)
{
yield return x;
foreach (var xi in xs)
yield return xi;
}
Best , Easiest and Generic Answer :).
string originalString = "1111222233334444";
List<string> test = new List<string>();
int chunkSize = 4; // change 4 with the size of strings you want.
for (int i = 0; i < originalString.Length; i = i + chunkSize)
{
if (originalString.Length - i >= chunkSize)
test.Add(originalString.Substring(i, chunkSize));
else
test.Add(originalString.Substring(i,((originalString.Length - i))));
}
static IEnumerable<string> Split(string str, int chunkSize)
{
IEnumerable<string> retVal = Enumerable.Range(0, str.Length / chunkSize)
.Select(i => str.Substring(i * chunkSize, chunkSize))
if (str.Length % chunkSize > 0)
retVal = retVal.Append(str.Substring(str.Length / chunkSize * chunkSize, str.Length % chunkSize));
return retVal;
}
It correctly handles input string length not divisible by chunkSize.
Please note that additional code might be required to gracefully handle edge cases (null or empty input string, chunkSize == 0).
static IEnumerable<string> Split(string str, double chunkSize)
{
return Enumerable.Range(0, (int) Math.Ceiling(str.Length/chunkSize))
.Select(i => new string(str
.Skip(i * (int)chunkSize)
.Take((int)chunkSize)
.ToArray()));
}
and another approach:
using System;
using System.Collections.Generic;
using System.Linq;
public class Program
{
public static void Main()
{
var x = "Hello World";
foreach(var i in x.ChunkString(2)) Console.WriteLine(i);
}
}
public static class Ext{
public static IEnumerable<string> ChunkString(this string val, int chunkSize){
return val.Select((x,i) => new {Index = i, Value = x})
.GroupBy(x => x.Index/chunkSize, x => x.Value)
.Select(x => string.Join("",x));
}
}
Six years later o_O
Just because
public static IEnumerable<string> Split(this string str, int chunkSize, bool remainingInFront)
{
var count = (int) Math.Ceiling(str.Length/(double) chunkSize);
Func<int, int> start = index => remainingInFront ? str.Length - (count - index)*chunkSize : index*chunkSize;
Func<int, int> end = index => Math.Min(str.Length - Math.Max(start(index), 0), Math.Min(start(index) + chunkSize - Math.Max(start(index), 0), chunkSize));
return Enumerable.Range(0, count).Select(i => str.Substring(Math.Max(start(i), 0),end(i)));
}
or
private static Func<bool, int, int, int, int, int> start = (remainingInFront, length, count, index, size) =>
remainingInFront ? length - (count - index) * size : index * size;
private static Func<bool, int, int, int, int, int, int> end = (remainingInFront, length, count, index, size, start) =>
Math.Min(length - Math.Max(start, 0), Math.Min(start + size - Math.Max(start, 0), size));
public static IEnumerable<string> Split(this string str, int chunkSize, bool remainingInFront)
{
var count = (int)Math.Ceiling(str.Length / (double)chunkSize);
return Enumerable.Range(0, count).Select(i => str.Substring(
Math.Max(start(remainingInFront, str.Length, count, i, chunkSize), 0),
end(remainingInFront, str.Length, count, i, chunkSize, start(remainingInFront, str.Length, count, i, chunkSize))
));
}
AFAIK all edge cases are handled.
Console.WriteLine(string.Join(" ", "abc".Split(2, false))); // ab c
Console.WriteLine(string.Join(" ", "abc".Split(2, true))); // a bc
Console.WriteLine(string.Join(" ", "a".Split(2, true))); // a
Console.WriteLine(string.Join(" ", "a".Split(2, false))); // a
List<string> SplitString(int chunk, string input)
{
List<string> list = new List<string>();
int cycles = input.Length / chunk;
if (input.Length % chunk != 0)
cycles++;
for (int i = 0; i < cycles; i++)
{
try
{
list.Add(input.Substring(i * chunk, chunk));
}
catch
{
list.Add(input.Substring(i * chunk));
}
}
return list;
}
I took this to another level. Chucking is an easy one liner, but in my case I needed whole words as well. Figured I would post it, just in case someone else needs something similar.
static IEnumerable<string> Split(string orgString, int chunkSize, bool wholeWords = true)
{
if (wholeWords)
{
List<string> result = new List<string>();
StringBuilder sb = new StringBuilder();
if (orgString.Length > chunkSize)
{
string[] newSplit = orgString.Split(' ');
foreach (string str in newSplit)
{
if (sb.Length != 0)
sb.Append(" ");
if (sb.Length + str.Length > chunkSize)
{
result.Add(sb.ToString());
sb.Clear();
}
sb.Append(str);
}
result.Add(sb.ToString());
}
else
result.Add(orgString);
return result;
}
else
return new List<string>(Regex.Split(orgString, #"(?<=\G.{" + chunkSize + "})", RegexOptions.Singleline));
}
Results based on below comment:
string msg = "336699AABBCCDDEEFF";
foreach (string newMsg in Split(msg, 2, false))
{
Console.WriteLine($">>{newMsg}<<");
}
Console.ReadKey();
Results:
>>33<<
>>66<<
>>99<<
>>AA<<
>>BB<<
>>CC<<
>>DD<<
>>EE<<
>>FF<<
>><<
Another way to pull it:
List<string> splitData = (List<string>)Split(msg, 2, false);
for (int i = 0; i < splitData.Count - 1; i++)
{
Console.WriteLine($">>{splitData[i]}<<");
}
Console.ReadKey();
New Results:
>>33<<
>>66<<
>>99<<
>>AA<<
>>BB<<
>>CC<<
>>DD<<
>>EE<<
>>FF<<
An important tip if the string that is being chunked needs to support all Unicode characters.
If the string is to support international characters like 𠀋, then split up the string using the System.Globalization.StringInfo class. Using StringInfo, you can split up the string based on number of text elements.
string internationalString = '𠀋';
The above string has a Length of 2, because the String.Length property returns the number of Char objects in this instance, not the number of Unicode characters.
Changed slightly to return parts whose size not equal to chunkSize
public static IEnumerable<string> Split(this string str, int chunkSize)
{
var splits = new List<string>();
if (str.Length < chunkSize) { chunkSize = str.Length; }
splits.AddRange(Enumerable.Range(0, str.Length / chunkSize).Select(i => str.Substring(i * chunkSize, chunkSize)));
splits.Add(str.Length % chunkSize > 0 ? str.Substring((str.Length / chunkSize) * chunkSize, str.Length - ((str.Length / chunkSize) * chunkSize)) : string.Empty);
return (IEnumerable<string>)splits;
}
I think this is an straight forward answer:
public static IEnumerable<string> Split(this string str, int chunkSize)
{
if(string.IsNullOrEmpty(str) || chunkSize<1)
throw new ArgumentException("String can not be null or empty and chunk size should be greater than zero.");
var chunkCount = str.Length / chunkSize + (str.Length % chunkSize != 0 ? 1 : 0);
for (var i = 0; i < chunkCount; i++)
{
var startIndex = i * chunkSize;
if (startIndex + chunkSize >= str.Length)
yield return str.Substring(startIndex);
else
yield return str.Substring(startIndex, chunkSize);
}
}
And it covers edge cases.
static List<string> GetChunks(string value, int chunkLength)
{
var res = new List<string>();
int count = (value.Length / chunkLength) + (value.Length % chunkLength > 0 ? 1 : 0);
Enumerable.Range(0, count).ToList().ForEach(f => res.Add(value.Skip(f * chunkLength).Take(chunkLength).Select(z => z.ToString()).Aggregate((a,b) => a+b)));
return res;
}
demo
Here's my 2 cents:
IEnumerable<string> Split(string str, int chunkSize)
{
while (!string.IsNullOrWhiteSpace(str))
{
var chunk = str.Take(chunkSize).ToArray();
str = str.Substring(chunk.Length);
yield return new string(chunk);
}
}//Split
I've slightly build up on João's solution.
What I've done differently is in my method you can actually specify whether you want to return the array with remaining characters or whether you want to truncate them if the end characters do not match your required chunk length, I think it's pretty flexible and the code is fairly straight forward:
using System;
using System.Linq;
using System.Text.RegularExpressions;
namespace SplitFunction
{
class Program
{
static void Main(string[] args)
{
string text = "hello, how are you doing today?";
string[] chunks = SplitIntoChunks(text, 3,false);
if (chunks != null)
{
chunks.ToList().ForEach(e => Console.WriteLine(e));
}
Console.ReadKey();
}
private static string[] SplitIntoChunks(string text, int chunkSize, bool truncateRemaining)
{
string chunk = chunkSize.ToString();
string pattern = truncateRemaining ? ".{" + chunk + "}" : ".{1," + chunk + "}";
string[] chunks = null;
if (chunkSize > 0 && !String.IsNullOrEmpty(text))
chunks = (from Match m in Regex.Matches(text,pattern)select m.Value).ToArray();
return chunks;
}
}
}
public static List<string> SplitByMaxLength(this string str)
{
List<string> splitString = new List<string>();
for (int index = 0; index < str.Length; index += MaxLength)
{
splitString.Add(str.Substring(index, Math.Min(MaxLength, str.Length - index)));
}
return splitString;
}
I can't remember who gave me this, but it works great. I speed tested a number of ways to break Enumerable types into groups. The usage would just be like this...
List<string> Divided = Source3.Chunk(24).Select(Piece => string.Concat<char>(Piece)).ToList();
The extention code would look like this...
#region Chunk Logic
private class ChunkedEnumerable<T> : IEnumerable<T>
{
class ChildEnumerator : IEnumerator<T>
{
ChunkedEnumerable<T> parent;
int position;
bool done = false;
T current;
public ChildEnumerator(ChunkedEnumerable<T> parent)
{
this.parent = parent;
position = -1;
parent.wrapper.AddRef();
}
public T Current
{
get
{
if (position == -1 || done)
{
throw new InvalidOperationException();
}
return current;
}
}
public void Dispose()
{
if (!done)
{
done = true;
parent.wrapper.RemoveRef();
}
}
object System.Collections.IEnumerator.Current
{
get { return Current; }
}
public bool MoveNext()
{
position++;
if (position + 1 > parent.chunkSize)
{
done = true;
}
if (!done)
{
done = !parent.wrapper.Get(position + parent.start, out current);
}
return !done;
}
public void Reset()
{
// per http://msdn.microsoft.com/en-us/library/system.collections.ienumerator.reset.aspx
throw new NotSupportedException();
}
}
EnumeratorWrapper<T> wrapper;
int chunkSize;
int start;
public ChunkedEnumerable(EnumeratorWrapper<T> wrapper, int chunkSize, int start)
{
this.wrapper = wrapper;
this.chunkSize = chunkSize;
this.start = start;
}
public IEnumerator<T> GetEnumerator()
{
return new ChildEnumerator(this);
}
System.Collections.IEnumerator System.Collections.IEnumerable.GetEnumerator()
{
return GetEnumerator();
}
}
private class EnumeratorWrapper<T>
{
public EnumeratorWrapper(IEnumerable<T> source)
{
SourceEumerable = source;
}
IEnumerable<T> SourceEumerable { get; set; }
Enumeration currentEnumeration;
class Enumeration
{
public IEnumerator<T> Source { get; set; }
public int Position { get; set; }
public bool AtEnd { get; set; }
}
public bool Get(int pos, out T item)
{
if (currentEnumeration != null && currentEnumeration.Position > pos)
{
currentEnumeration.Source.Dispose();
currentEnumeration = null;
}
if (currentEnumeration == null)
{
currentEnumeration = new Enumeration { Position = -1, Source = SourceEumerable.GetEnumerator(), AtEnd = false };
}
item = default(T);
if (currentEnumeration.AtEnd)
{
return false;
}
while (currentEnumeration.Position < pos)
{
currentEnumeration.AtEnd = !currentEnumeration.Source.MoveNext();
currentEnumeration.Position++;
if (currentEnumeration.AtEnd)
{
return false;
}
}
item = currentEnumeration.Source.Current;
return true;
}
int refs = 0;
// needed for dispose semantics
public void AddRef()
{
refs++;
}
public void RemoveRef()
{
refs--;
if (refs == 0 && currentEnumeration != null)
{
var copy = currentEnumeration;
currentEnumeration = null;
copy.Source.Dispose();
}
}
}
/// <summary>Speed Checked. Works Great!</summary>
public static IEnumerable<IEnumerable<T>> Chunk<T>(this IEnumerable<T> source, int chunksize)
{
if (chunksize < 1) throw new InvalidOperationException();
var wrapper = new EnumeratorWrapper<T>(source);
int currentPos = 0;
T ignore;
try
{
wrapper.AddRef();
while (wrapper.Get(currentPos, out ignore))
{
yield return new ChunkedEnumerable<T>(wrapper, chunksize, currentPos);
currentPos += chunksize;
}
}
finally
{
wrapper.RemoveRef();
}
}
#endregion
class StringHelper
{
static void Main(string[] args)
{
string str = "Hi my name is vikas bansal and my email id is bansal.vks#gmail.com";
int offSet = 10;
List<string> chunks = chunkMyStr(str, offSet);
Console.Read();
}
static List<string> chunkMyStr(string str, int offSet)
{
List<string> resultChunks = new List<string>();
for (int i = 0; i < str.Length; i += offSet)
{
string temp = str.Substring(i, (str.Length - i) > offSet ? offSet : (str.Length - i));
Console.WriteLine(temp);
resultChunks.Add(temp);
}
return resultChunks;
}
}
In data sometimes the same product will be named with a roman numeral while other times it will be a digit.
Example Samsung Galaxy SII verses Samsung Galaxy S2
How can the II be converted to the value 2?
I've noticed some really complicated solutions here but this is a really simple problem. I made a solution that avoided the need to hard code the "exceptions" (IV, IX, XL, etc). I used a for loop to look ahead at the next character in the Roman numeral string to see if the number associated with the numeral should be subtracted or added to the total. For simplicity's sake I'm assuming all input is valid.
private static Dictionary<char, int> RomanMap = new Dictionary<char, int>()
{
{'I', 1},
{'V', 5},
{'X', 10},
{'L', 50},
{'C', 100},
{'D', 500},
{'M', 1000}
};
public static int RomanToInteger(string roman)
{
int number = 0;
for (int i = 0; i < roman.Length; i++)
{
if (i + 1 < roman.Length && RomanMap[roman[i]] < RomanMap[roman[i + 1]])
{
number -= RomanMap[roman[i]];
}
else
{
number += RomanMap[roman[i]];
}
}
return number;
}
I initially tried using a foreach on the string which I think was a slightly more readable solution but I ended up adding every single number and subtracting it twice later if it turned out to be one of the exceptions, which I didn't like. I'll post it here anyway for posterity.
public static int RomanToInteger(string roman)
{
int number = 0;
char previousChar = roman[0];
foreach(char currentChar in roman)
{
number += RomanMap[currentChar];
if(RomanMap[previousChar] < RomanMap[currentChar])
{
number -= RomanMap[previousChar] * 2;
}
previousChar = currentChar;
}
return number;
}
This is my solution
public int SimplerConverter(string number)
{
number = number.ToUpper();
var result = 0;
foreach (var letter in number)
{
result += ConvertLetterToNumber(letter);
}
if (number.Contains("IV")|| number.Contains("IX"))
result -= 2;
if (number.Contains("XL")|| number.Contains("XC"))
result -= 20;
if (number.Contains("CD")|| number.Contains("CM"))
result -= 200;
return result;
}
private int ConvertLetterToNumber(char letter)
{
switch (letter)
{
case 'M':
{
return 1000;
}
case 'D':
{
return 500;
}
case 'C':
{
return 100;
}
case 'L':
{
return 50;
}
case 'X':
{
return 10;
}
case 'V':
{
return 5;
}
case 'I':
{
return 1;
}
default:
{
throw new ArgumentException("Ivalid charakter");
}
}
}
A more simple and readable C# implementation that:
maps I to 1, V to 5, X to 10, L to 50, C to 100, D to 500, M to 1000.
uses one single foreach loop (foreach used on purpose, with previous value
hold).
adds the mapped number to the total.
subtracts twice the number added before, if I before V or X, X before L or C, C before D or M (not all chars are allowed here!).
returns 0 (not used in Roman numerals) on empty string, wrong letter
or not allowed char used for subtraction.
remark: it's still not totally complete, we didn't check all possible conditions for a valid input string!
Code:
private static Dictionary<char, int> _romanMap = new Dictionary<char, int>
{
{'I', 1}, {'V', 5}, {'X', 10}, {'L', 50}, {'C', 100}, {'D', 500}, {'M', 1000}
};
public static int ConvertRomanToNumber(string text)
{
int totalValue = 0, prevValue = 0;
foreach (var c in text)
{
if (!_romanMap.ContainsKey(c))
return 0;
var crtValue = _romanMap[c];
totalValue += crtValue;
if (prevValue != 0 && prevValue < crtValue)
{
if (prevValue == 1 && (crtValue == 5 || crtValue == 10)
|| prevValue == 10 && (crtValue == 50 || crtValue == 100)
|| prevValue == 100 && (crtValue == 500 || crtValue == 1000))
totalValue -= 2 * prevValue;
else
return 0;
}
prevValue = crtValue;
}
return totalValue;
}
I landed here searching for a small implementation of a Roman Numerals parser but wasn't satisfied by the provided answers in terms of size and elegance. I leave my final, recursive implementation here, to help others searching a small implementation.
Convert Roman Numerals by Recursion
The algorithm is able to handle numerals in irregular subtractive notation (f.e. XIIX).
This implementation may only work with well-formed (strings matching /[mdclxvi]*/i) roman numerals.
The implementation is not optimized for speed.
// returns the value for a roman literal
private static int romanValue(int index)
{
int basefactor = ((index % 2) * 4 + 1); // either 1 or 5...
// ...multiplied with the exponentation of 10, if the literal is `x` or higher
return index > 1 ? (int) (basefactor * System.Math.Pow(10.0, index / 2)) : basefactor;
}
public static int FromRoman(string roman)
{
roman = roman.ToLower();
string literals = "mdclxvi";
int value = 0, index = 0;
foreach (char literal in literals)
{
value = romanValue(literals.Length - literals.IndexOf(literal) - 1);
index = roman.IndexOf(literal);
if (index > -1)
return FromRoman(roman.Substring(index + 1)) + (index > 0 ? value - FromRoman(roman.Substring(0, index)) : value);
}
return 0;
}
Try it using this .Netfiddle: https://dotnetfiddle.net/veaNk3
How does it work?
This algorithm calculates the value of a Roman Numeral by taking the highest value from the Roman Numeral and adding/subtracting recursively the value of the remaining left/right parts of the literal.
ii X iiv # Pick the greatest value in the literal `iixiiv` (symbolized by uppercase)
Then recursively reevaluate and subtract the lefthand-side and add the righthand-side:
(iiv) + x - (ii) # Subtract the lefthand-side, add the righthand-side
(V - (ii)) + x - ((I) + i) # Pick the greatest values, again
(v - ((I) + i)) + x - ((i) + i) # Pick the greatest value of the last numeral compound
Finally the numerals are substituted by their integer values:
(5 - ((1) + 1)) + 10 - ((1) + 1)
(5 - (2)) + 10 - (2)
3 + 10 - 2
= 11
I wrote a simple Roman Numeral Converter just now, but it doesn't do a whole lot of error checking, but it seems to work for everything I could throw at it that is properly formatted.
public class RomanNumber
{
public string Numeral { get; set; }
public int Value { get; set; }
public int Hierarchy { get; set; }
}
public List<RomanNumber> RomanNumbers = new List<RomanNumber>
{
new RomanNumber {Numeral = "M", Value = 1000, Hierarchy = 4},
//{"CM", 900},
new RomanNumber {Numeral = "D", Value = 500, Hierarchy = 4},
//{"CD", 400},
new RomanNumber {Numeral = "C", Value = 100, Hierarchy = 3},
//{"XC", 90},
new RomanNumber {Numeral = "L", Value = 50, Hierarchy = 3},
//{"XL", 40},
new RomanNumber {Numeral = "X", Value = 10, Hierarchy = 2},
//{"IX", 9},
new RomanNumber {Numeral = "V", Value = 5, Hierarchy = 2},
//{"IV", 4},
new RomanNumber {Numeral = "I", Value = 1, Hierarchy = 1}
};
/// <summary>
/// Converts the roman numeral to int, assumption roman numeral is properly formatted.
/// </summary>
/// <param name="romanNumeralString">The roman numeral string.</param>
/// <returns></returns>
private int ConvertRomanNumeralToInt(string romanNumeralString)
{
if (romanNumeralString == null) return int.MinValue;
var total = 0;
for (var i = 0; i < romanNumeralString.Length; i++)
{
// get current value
var current = romanNumeralString[i].ToString();
var curRomanNum = RomanNumbers.First(rn => rn.Numeral.ToUpper() == current.ToUpper());
// last number just add the value and exit
if (i + 1 == romanNumeralString.Length)
{
total += curRomanNum.Value;
break;
}
// check for exceptions IV, IX, XL, XC etc
var next = romanNumeralString[i + 1].ToString();
var nextRomanNum = RomanNumbers.First(rn => rn.Numeral.ToUpper() == next.ToUpper());
// exception found
if (curRomanNum.Hierarchy == (nextRomanNum.Hierarchy - 1))
{
total += nextRomanNum.Value - curRomanNum.Value;
i++;
}
else
{
total += curRomanNum.Value;
}
}
return total;
}
private static int convertRomanToInt(String romanNumeral)
{
Dictionary<Char, Int32> romanMap = new Dictionary<char, int>
{
{'I', 1 },
{'V', 5},
{'X', 10},
{'L', 50},
{'C', 100},
{'D', 500},
{'M', 1000}
};
Int32 result = 0;
for (Int32 index = romanNumeral.Length - 1, last = 0; index >= 0; index--)
{
Int32 current = romanMap[romanNumeral[index]];
result += (current < last ? -current : current);
last = current;
}
return result;
}
With Humanizer library you can change Roman numerals to numbers using the FromRoman extension
"IV".FromRoman() => 4
And reverse operation using the ToRoman extension.
4.ToRoman() => "IV"
Borrowed a lot from System.Linq on this one. String implements IEnumerable<char>, so I figured that was appropriate since we are treating it as an enumerable object anyways. Tested it against a bunch of random numbers, including 1, 3, 4, 8, 83, 99, 404, 555, 846, 927, 1999, 2420.
public static IDictionary<char, int> CharValues
{
get
{
return new Dictionary<char, int>
{{'I', 1}, {'V', 5}, {'X', 10}, {'L', 50}, {'C', 100}, {'D', 500}, {'M', 1000}};
}
}
public static int RomanNumeralToInteger(IEnumerable<char> romanNumerals)
{
int retVal = 0;
//go backwards
for (int i = romanNumerals.Count() - 1; i >= 0; i--)
{
//get current character
char c = romanNumerals.ElementAt(i);
//error checking
if (!CharValues.ContainsKey(c)) throw new InvalidRomanNumeralCharacterException(c);
//determine if we are adding or subtracting
bool op = romanNumerals.Skip(i).Any(rn => CharValues[rn] > CharValues[c]);
//then do so
retVal = op ? retVal - CharValues[c] : retVal + CharValues[c];
}
return retVal;
}
Solution with fulfilling the "subtractive notation" semantics checks
None of the current solutions completely fulfills the entire set of rules
for the "subtractive notation". "IIII" -> is not possible. Each of the solutions results a 4. Also the strings: "CCCC", "VV", "IC", "IM" are invalid.
A good online-converter to check the semantics is https://www.romannumerals.org/converter
So, if you really want doing a completely semantics-check, it's much more complex.
My approach was to first write the unit tests with the semantic checks. Then to write the code. Then to reduce the loops with some linq expressions.
Maybe there is a smarter solution, but I think the following code fullfills the rules to convert a roman numerals string.
After the code section, there is a section with my unit tests.
public class RomanNumerals
{
private List<Tuple<char, ushort, char?[]>> _validNumerals = new List<Tuple<char, ushort, char?[]>>()
{
new Tuple<char, ushort, char?[]>('I', 1, new char? [] {'V', 'X'}),
new Tuple<char, ushort, char?[]>('V', 5, null),
new Tuple<char, ushort, char?[]>('X', 10, new char?[] {'L', 'C'}),
new Tuple<char, ushort, char?[]>('L', 50, null),
new Tuple<char, ushort, char?[]>('C', 100, new char? [] {'D', 'M'}),
new Tuple<char, ushort, char?[]>('D', 500, null),
new Tuple<char, ushort, char?[]>('M', 1000, new char? [] {null, null})
};
public int TranslateRomanNumeral(string input)
{
var inputList = input?.ToUpper().ToList();
if (inputList == null || inputList.Any(x => _validNumerals.Select(t => t.Item1).Contains(x) == false))
{
throw new ArgumentException();
}
char? valForSubtraction = null;
int result = 0;
bool noAdding = false;
int equalSum = 0;
for (int i = 0; i < inputList.Count; i++)
{
var currentNumeral = _validNumerals.FirstOrDefault(s => s.Item1 == inputList[i]);
var nextNumeral = i < inputList.Count - 1 ? _validNumerals.FirstOrDefault(s => s.Item1 == inputList[i + 1]) : null;
bool currentIsDecimalPower = currentNumeral?.Item3?.Any() ?? false;
if (nextNumeral != null)
{
// Syntax and Semantics checks
if ((currentNumeral.Item2 < nextNumeral.Item2) && (currentIsDecimalPower == false || currentNumeral.Item3.Any(s => s == nextNumeral.Item1) == false) ||
(currentNumeral.Item2 == nextNumeral.Item2) && (currentIsDecimalPower == false || nextNumeral.Item1 == valForSubtraction) ||
(currentIsDecimalPower && result > 0 && ((nextNumeral.Item2 -currentNumeral.Item2) > result )) ||
(currentNumeral.Item2 > nextNumeral.Item2) && (nextNumeral.Item1 == valForSubtraction)
)
{
throw new ArgumentException();
}
if (currentNumeral.Item2 == nextNumeral.Item2)
{
equalSum += equalSum == 0 ? currentNumeral.Item2 + nextNumeral.Item2 : nextNumeral.Item2;
int? smallest = null;
var list = _validNumerals.Where(p => _validNumerals.FirstOrDefault(s => s.Item1 == currentNumeral.Item1).Item3.Any(s2 => s2 != null && s2 == p.Item1)).ToList();
if (list.Any())
{
smallest = list.Select(s3 => s3.Item2).ToList().Min();
}
// Another Semantics check
if (currentNumeral.Item3 != null && equalSum >= (smallest - currentNumeral.Item2))
{
throw new ArgumentException();
}
result += noAdding ? 0 : currentNumeral.Item2 + nextNumeral.Item2;
noAdding = !noAdding;
valForSubtraction = null;
}
else
if (currentNumeral.Item2 < nextNumeral.Item2)
{
equalSum = 0;
result += nextNumeral.Item2 - currentNumeral.Item2;
valForSubtraction = currentNumeral.Item1;
noAdding = true;
}
else
if (currentNumeral.Item2 > nextNumeral.Item2)
{
equalSum = 0;
result += noAdding ? 0 : currentNumeral.Item2;
noAdding = false;
valForSubtraction = null;
}
}
else
{
result += noAdding ? 0 : currentNumeral.Item2;
}
}
return result;
}
}
Here are the UNIT tests
[TestFixture]
public class RomanNumeralsTests
{
[Test]
public void TranslateRomanNumeral_WhenArgumentIsNull_RaiseArgumentNullException()
{
var romanNumerals = new RomanNumerals();
Assert.Throws<ArgumentException>(() => romanNumerals.TranslateRomanNumeral(null));
}
[TestCase("A")]
[TestCase("-")]
[TestCase("BXA")]
[TestCase("MMXK")]
public void TranslateRomanNumeral_WhenInvalidNumeralSyntax_RaiseException(string input)
{
var romanNumerals = new RomanNumerals();
Assert.Throws<ArgumentException>(() => romanNumerals.TranslateRomanNumeral(input));
}
[TestCase("IIII")]
[TestCase("CCCC")]
[TestCase("VV")]
[TestCase("IC")]
[TestCase("IM")]
[TestCase("XM")]
[TestCase("IL")]
[TestCase("MCDXCXI")]
[TestCase("MCDDXC")]
public void TranslateRomanNumeral_WhenInvalidNumeralSemantics_RaiseException(string input)
{
var romanNumerals = new RomanNumerals();
Assert.Throws<ArgumentException>(() => romanNumerals.TranslateRomanNumeral(input));
}
[TestCase("I", 1)]
[TestCase("II", 2)]
[TestCase("III", 3)]
[TestCase("IV", 4)]
[TestCase("XLII", 42)]
[TestCase("MMXIII", 2013)]
[TestCase("MXI", 1011)]
[TestCase("MCDXCIX", 1499)]
[TestCase("MMXXII", 2022)]
[TestCase("V", 5)]
[TestCase("VI", 6)]
[TestCase("CX", 110)]
[TestCase("CCCLXXV", 375)]
[TestCase("MD", 1500)]
[TestCase("MDLXXV", 1575)]
[TestCase("MDCL", 1650)]
[TestCase("MDCCXXV", 1725)]
[TestCase("MDCCC", 1800)]
[TestCase("MDCCCLXXV", 1875)]
[TestCase("MCML", 1950)]
[TestCase("MMXXV", 2025)]
[TestCase("MMC", 2100)]
[TestCase("MMCLXXV", 2175)]
[TestCase("MMCCL", 2250)]
[TestCase("MMCCCXXV", 2325)]
[TestCase("MMCD", 2400)]
[TestCase("MMCDLXXV", 2475)]
[TestCase("MMDL", 2550)]
[TestCase("MMMMMMMM", 8000)]
[TestCase("MMMMMMMMIV", 8004)]
public void TranslateRomanNumeral_WhenValidNumeral_Translate(string input, int output)
{
var romanNumerals = new RomanNumerals();
var result = romanNumerals.TranslateRomanNumeral(input);
Assert.That(result.Equals(output));
}
}
private static Dictionary<char, int> RomanNumberMap = new Dictionary<char, int> {
{'I', 1},
{'V', 5},
{'X', 10},
{'L', 50},
{'C', 100},
{'D', 500},
{'M', 1000}
};
private const string RomanNumberValidationRegEx = "^(?=[MDCLXVI])M*(C[MD]|D?C{0,3})(X[CL]|L?X{0,3})(I[XV]|V?I{0,3})$";
private static int ConvertToRomanNumberToInteger(string romanNumber)
{
if (!Regex.IsMatch(romanNumber, RomanNumberValidationRegEx))
{
throw new ArgumentOutOfRangeException(romanNumber);
}
int result = 0;
for (int i = 0; i < romanNumber.Length; i++)
{
int currentVal = RomanNumberMap[romanNumber[i]];
if (romanNumber.Length > i + 1)
{
int nextVal = RomanNumberMap[romanNumber[i + 1]];
if (nextVal > currentVal)
{
result = result + (nextVal - currentVal);
i++;
continue;
}
}
result = result + currentVal;
}
return result;
}
I will suggest a simplest method for this by using array in .net : comments are given in C# section for explanation
VB.net
Public Class Form1
Dim indx() As Integer = {1, 2, 3, 4, 5, 10, 50, 100, 500, 1000}
Dim row() As String = {"I", "II", "III", "IV", "V", "X", "L", "C", "D", "M"}
Dim limit As Integer = 9
Dim output As String = ""
Private Sub Button1_Click(ByVal sender As System.Object, ByVal e As System.EventArgs) Handles Button1.Click
Dim num As Integer
output = ""
num = CInt(txt1.Text)
While num > 0
num = find(num)
End While
txt2.Text = output
End Sub
Public Function find(ByVal Num As Integer) As Integer
Dim i As Integer = 0
While indx(i) <= Num
i += 1
End While
If i <> 0 Then
limit = i - 1
Else
limit = 0
End If
output = output & row(limit)
Num = Num - indx(limit)
Return Num
End Function
End Class
C#
using Microsoft.VisualBasic;
using System;
using System.Collections;
using System.Collections.Generic;
using System.Data;
using System.Diagnostics;
public class Form1
{
int[] indx = {
1,
2,
3,
4,
5,
10,
50,
100,
500,
1000
// initialize array of integers
};
string[] row = {
"I",
"II",
"III",
"IV",
"V",
"X",
"L",
"C",
"D",
"M"
//Carasponding roman letters in for the numbers in the array
};
// integer to indicate the position index for link two arrays
int limit = 9;
//string to store output
string output = "";
private void Button1_Click(System.Object sender, System.EventArgs e)
{
int num = 0;
// stores the input
output = "";
// clear output before processing
num = Convert.ToInt32(txt1.Text);
// get integer value from the textbox
//Loop until the value became 0
while (num > 0) {
num = find(num);
//call function for processing
}
txt2.Text = output;
// display the output in text2
}
public int find(int Num)
{
int i = 0;
// loop variable initialized with 0
//Loop until the indx(i).value greater than or equal to num
while (indx(i) <= Num) {
i += 1;
}
// detemine the value of limit depends on the itetration
if (i != 0) {
limit = i - 1;
} else {
limit = 0;
}
output = output + row(limit);
//row(limit) is appended with the output
Num = Num - indx(limit);
// calculate next num value
return Num;
//return num value for next itetration
}
}
I refer from this blog. You could just reverse the roman numeral , then all the thing would be more easier compare to make the comparison.
public static int pairConversion(int dec, int lastNum, int lastDec)
{
if (lastNum > dec)
return lastDec - dec;
else return lastDec + dec;
}
public static int ConvertRomanNumtoInt(string strRomanValue)
{
var dec = 0;
var lastNum = 0;
foreach (var c in strRomanValue.Reverse())
{
switch (c)
{
case 'I':
dec = pairConversion(1, lastNum, dec);
lastNum = 1;
break;
case 'V':
dec=pairConversion(5,lastNum, dec);
lastNum = 5;
break;
case 'X':
dec = pairConversion(10, lastNum, dec);
lastNum = 10;
break;
case 'L':
dec = pairConversion(50, lastNum, dec);
lastNum = 50;
break;
case 'C':
dec = pairConversion(100, lastNum, dec);
lastNum = 100;
break;
case 'D':
dec = pairConversion(500, lastNum, dec);
lastNum = 500;
break;
case 'M':
dec = pairConversion(1000, lastNum, dec);
lastNum = 1000;
break;
}
}
return dec;
}
This one uses a stack:
public int RomanToInt(string s)
{
var dict = new Dictionary<char, int>();
dict['I'] = 1;
dict['V'] = 5;
dict['X'] = 10;
dict['L'] = 50;
dict['C'] = 100;
dict['D'] = 500;
dict['M'] = 1000;
Stack<char> st = new Stack<char>();
foreach (char ch in s.ToCharArray())
st.Push(ch);
int result = 0;
while (st.Count > 0)
{
var c1=st.Pop();
var ch1 = dict[c1];
if (st.Count > 0)
{
var c2 = st.Peek();
var ch2 = dict[c2];
if (ch2 < ch1)
{
result += (ch1 - ch2);
st.Pop();
}
else
{
result += ch1;
}
}
else
{
result += ch1;
}
}
return result;
}
I wrote this just using arrays.
I omit the testing code here, but it looks it works properly.
public static class RomanNumber {
static string[] units = { "", "I", "II", "III", "IV", "V", "VI", "VII", "VIII", "IX" };
static string[] tens = { "", "X", "XX", "XXX", "XL", "L", "LX", "LXX", "LXXX", "XC" };
static string[] hundreds = { "", "C", "CC", "CCC", "CD", "D", "DC", "DCC", "DCCC", "CM" };
static string[] thousands = { "", "M", "MM", "MMM" };
static public bool IsRomanNumber(string source) {
try {
return RomanNumberToInt(source) > 0;
}
catch {
return false;
}
}
/// <summary>
/// Parses a string containing a roman number.
/// </summary>
/// <param name="source">source string</param>
/// <returns>The integer value of the parsed roman numeral</returns>
/// <remarks>
/// Throws an exception on invalid source.
/// Throws an exception if source is not a valid roman number.
/// Supports roman numbers from "I" to "MMMCMXCIX" ( 1 to 3999 )
/// NOTE : "IMMM" is not valid</remarks>
public static int RomanNumberToInt(string source) {
if (String.IsNullOrWhiteSpace(source)) {
throw new ArgumentNullException();
}
int total = 0;
string buffer = source;
// parse the last four characters in the string
// each time we check the buffer against a number array,
// starting from units up to thousands
// we quit as soon as there are no remaing characters to parse
total += RipOff(buffer, units, out buffer);
if (buffer != null) {
total += (RipOff(buffer, tens, out buffer)) * 10;
}
if (buffer != null) {
total += (RipOff(buffer, hundreds, out buffer)) * 100;
}
if (buffer != null) {
total += (RipOff(buffer, thousands, out buffer)) * 1000;
}
// after parsing for thousands, if there is any character left, this is not a valid roman number
if (buffer != null) {
throw new ArgumentException(String.Format("{0} is not a valid roman number", buffer));
}
return total;
}
/// <summary>
/// Given a string, takes the four characters on the right,
/// search an element in the numbers array and returns the remaing characters.
/// </summary>
/// <param name="source">source string to parse</param>
/// <param name="numbers">array of roman numerals</param>
/// <param name="left">remaining characters on the left</param>
/// <returns>If it finds a roman numeral returns its integer value; otherwise returns zero</returns>
public static int RipOff(string source, string[] numbers, out string left) {
int result = 0;
string buffer = null;
// we take the last four characters : this is the length of the longest numeral in our arrays
// ("VIII", "LXXX", "DCCC")
// or all if source length is 4 or less
if (source.Length > 4) {
buffer = source.Substring(source.Length - 4);
left = source.Substring(0, source.Length - 4);
}
else {
buffer = source;
left = null;
}
// see if buffer exists in the numbers array
// if it does not, skip the first character and try again
// until buffer contains only one character
// append the skipped character to the left arguments
while (!numbers.Contains(buffer)) {
if (buffer.Length == 1) {
left = source; // failed
break;
}
else {
left += buffer.Substring(0, 1);
buffer = buffer.Substring(1);
}
}
if (buffer.Length > 0) {
if (numbers.Contains(buffer)) {
result = Array.IndexOf(numbers, buffer);
}
}
return result;
}
}
}
EDIT
Forget about it !
Just look at BrunoLM solution here.
It's simple and elegant.
The only caveat is that it does not check the source.
This is my solution:
/// <summary>
/// Converts a Roman number string into a Arabic number
/// </summary>
/// <param name="romanNumber">the Roman number string</param>
/// <returns>the Arabic number (0 if the given string is not convertible to a Roman number)</returns>
public static int ToArabicNumber(string romanNumber)
{
string[] replaceRom = { "CM", "CD", "XC", "XL", "IX", "IV" };
string[] replaceNum = { "DCCCC", "CCCC", "LXXXX", "XXXX", "VIIII", "IIII" };
string[] roman = { "M", "CM", "D", "CD", "C", "XC", "L", "XL", "X", "IX", "V", "IV", "I" };
int[] arabic = { 1000, 900, 500, 400, 100, 90, 50, 40, 10, 9, 5, 4, 1 };
return Enumerable.Range(0, replaceRom.Length)
.Aggregate
(
romanNumber,
(agg, cur) => agg.Replace(replaceRom[cur], replaceNum[cur]),
agg => agg.ToArray()
)
.Aggregate
(
0,
(agg, cur) =>
{
int idx = Array.IndexOf(roman, cur.ToString());
return idx < 0 ? 0 : agg + arabic[idx];
},
agg => agg
);
}
/// <summary>
/// Converts a Arabic number into a Roman number string
/// </summary>
/// <param name="arabicNumber">the Arabic number</param>
/// <returns>the Roman number string</returns>
public static string ToRomanNumber(int arabicNumber)
{
string[] roman = { "M", "CM", "D", "CD", "C", "XC", "L", "XL", "X", "IX", "V", "IV", "I" };
int[] arabic = { 1000, 900, 500, 400, 100, 90, 50, 40, 10, 9, 5, 4, 1 };
return Enumerable.Range(0, arabic.Length)
.Aggregate
(
Tuple.Create(arabicNumber, string.Empty),
(agg, cur) =>
{
int remainder = agg.Item1 % arabic[cur];
string concat = agg.Item2 + string.Concat(Enumerable.Range(0, agg.Item1 / arabic[cur]).Select(num => roman[cur]));
return Tuple.Create(remainder, concat);
},
agg => agg.Item2
);
}
Here's the Explanation how the methods work:
ToArabicNumber
First aggregation step is to Replace the Roman Number special cases (e.g.: IV -> IIII). Second Aggregate step simply sums up the equivalent Arabic number of the Roman letter (e.g. V -> 5)
ToRomanNumber:
I start the aggregation with the given Arabic number. For each step the number will be divided by the equivalent number of the Roman letter. The remainder of this division is then the input for the next step. The division Result will be translated to the Equivalent Roman Number character which will be appended to the result string.
private static HashMap<Character, Integer> romanMap = new HashMap<>() {{
put('I', 1); put('V', 5); put('X', 10); put('L', 50);
put('C', 100); put('D', 500); put('M', 1000);
}};
private static int convertRomanToInt(String romanNumeral) {
int total = 0;
romanNumeral = romanNumeral.toUpperCase();
//add every Roman numeral
for(int i = 0; i < romanNumeral.length(); i++) {
total += romanMap.get(romanNumeral.charAt(i));
}
//remove the Roman numerals that are followed
//directly by a larger Roman numeral
for(int i = 0; i < romanNumeral.length()-1; i++) {
if(romanMap.get(romanNumeral.charAt(i))
< romanMap.get(romanNumeral.charAt(i+1))) {
total -= 2* romanMap.get(romanNumeral.charAt(i));
}
}
return total;
}
//note that the topmost solution does not solve this Roman numeral
//but mine does
//also note that this solution is a preference of simplicity over complexity
public static void main(String[] args) {
String rn = "CcLXxiV"; //274
System.out.println("Convert " + rn + " to " + convertRomanToInt(rn));
}
/*
this uses the string object Replace() & Split() methods
*/
int ToNumber(string roman){
/*
the 0 padding after the comma delimiter allows adding up the extra index produced by Split, which is not numerical
*/
string s1=roman.Replace("CM","900,0");
s1=s1.Replace("M","1000,0");
s1=s1.Replace("CD","400,0");
s1=s1.Replace("D","500,0");
s1=s1.Replace("XC","90,0");
s1=s1.Replace("C","100,0");
s1=s1.Replace("XL","40,0");
s1=s1.Replace("L","50,0");
s1=s1.Replace("IX","9,0");
s1=s1.Replace("X","10,0");
s1=s1.Replace("IV","4,0");
s1=s1.Replace("V","5,0");
s1=s1.Replace("I","1,0");
string[] spl=s1.Split(",");
int rlt=0;
for(int i=0;i<spl.Count();i++)
{
rlt+= Convert.ToInt32(spl[i].ToString());
}
return rlt;
}
Here is my O(n) solution in JavaScript
const NUMERAL = {
'I': 1,
'V': 5,
'X': 10,
'L': 50,
'C': 100,
'D': 500,
'M': 1000,
}
var romanToInt = function(s) {
if (s.length === 1) return +NUMERAL[s];
let number = 0;
for (let i = 0; i < s.length; i++) {
let num = +NUMERAL[s[i]];
let prev = +NUMERAL[s[i-1]];
if (prev < num) number += num - (2 * prev);
else number += num;
}
return number;
};
FWIW, here is a "try parse" version of David DeMar's answer:
private static readonly Dictionary<char, int> _romanMap = new Dictionary<char, int>() { { 'I', 1 }, { 'V', 5 }, { 'X', 10 }, { 'L', 50 }, { 'C', 100 }, { 'D', 500 }, { 'M', 1000 } };
public static bool TryParseRoman(string text, out int value)
{
value = 0;
if (string.IsNullOrEmpty(text))
return false;
var number = 0;
for (var i = 0; i < text.Length; i++)
{
if (!_romanMap.TryGetValue(text[i], out var num))
return false;
if ((i + 1) < text.Length)
{
if (!_romanMap.TryGetValue(text[i + 1], out var num2))
return false;
if (num < num2)
{
number -= num;
continue;
}
}
number += num;
}
value = number;
return true;
}
public class Solution {
public int RomanToInt(string s) {
var dict = new Dictionary<char,int>{
{'I',1},
{'V',5},
{'X',10},
{'L',50},
{'C',100},
{'M',1000},
{'D',500},
};
var result = 0; //What am I gonna return it from method ?
for(int i=0; i<s.Length; i++)
{
if(i+1<s.Length && dict[s[i]] < dict[s[i+1]])
{
result -=dict[s[i]];
}
else
{
result +=dict[s[i]];
}
}
return result;
}
}
public int RomanToInt(string s)
{
char[] romans = { 'I', 'V', 'X', 'L', 'C', 'D', 'M' };
int[] nums = { 1, 5, 10, 50, 100, 500, 1000 };
int result = 0;
foreach (char c in s)
{
for (int i = 0; i < romans.Length; i++)
{
if (romans[i] == c)
{
result += nums[i];
}
}
}
if (s.Contains("IV") || s.Contains("IX"))
result -= 2;
if (s.Contains("XL") || s.Contains("XC"))
result -= 20;
if (s.Contains("CD") || s.Contains("CM"))
result -= 200;
return result;
}
public static int ConvertRomanNumtoInt(string strRomanValue)
{
Dictionary RomanNumbers = new Dictionary
{
{"M", 1000},
{"CM", 900},
{"D", 500},
{"CD", 400},
{"C", 100},
{"XC", 90},
{"L", 50},
{"XL", 40},
{"X", 10},
{"IX", 9},
{"V", 5},
{"IV", 4},
{"I", 1}
};
int retVal = 0;
foreach (KeyValuePair pair in RomanNumbers)
{
while (strRomanValue.IndexOf(pair.Key.ToString()) == 0)
{
retVal += int.Parse(pair.Value.ToString());
strRomanValue = strRomanValue.Substring(pair.Key.ToString().Length);
}
}
return retVal;
}