15
\$\begingroup\$

Trying to learn coding in my 30s.

Could anybody review my code and give me some feedback if possible? It works, but I am sure there are better ways to solve this problem.

The problem:

A text is given. Write a program that modifies the casing of letters to uppercase at all places in the text surrounded by <upcase> and </upcase> tags. Tags cannot be nested.

Here is what I've come up with:

namespace Task6Casing
{
    class Program
    {
        static void Main(string[] args)
        {
            Console.Write("Text: ");
            string text = Console.ReadLine();

            char[] textNew = new char[text.Length];

            int i = 0, j = 0, k = 0;

            while (i < text.Length)
            {
                if (text.IndexOf("<upcase>", k) < 0)            // check if there is any <upcase> tag
                {                                               // if no, copy everyting
                    while (i < text.Length)
                    {
                        textNew[j++] = text[i++];
                    }
                }
                else                                  
                {
                    while (i < text.IndexOf("<upcase>", k))     // if there is an <upcase> tag, copy letters until the tag
                    {
                        textNew[j++] = text[i++];
                    }

                    i += 8;                                     // move index i to the position right next to the <upcase> tag
                    k = i;
                }

                if (text.IndexOf("</upcase>", k) < 0)           // check if there is any </upcase> tag
                {                                               // if no, copy everyting in CAPITAL letters
                    while (i < text.Length)
                    {
                        textNew[j++] = Char.ToUpper(text[i++]);
                    }
                }
                else
                {
                    while (i < text.IndexOf("</upcase>", k))    // if there is an </upcase> tag, copy letters in CAP letters until the tag
                    {
                        textNew[j++] = Char.ToUpper(text[i++]);
                    }

                    i += 9;                                     // move index i to the position right next to the </upcase> tag
                }
            }

            foreach(char c in textNew)
            {
                Console.Write(c);
            }
            Console.WriteLine();

        }
    }
}
\$\endgroup\$
7
\$\begingroup\$

Your code is easy to understand and very performant.

Some improvements:

  • String for start / end tag could be stored as constant. That has the advantage that it can be changed on one central location and the length of the string can be accessed like i += START_TAG.Length
  • When using a StringBuilder instead of of the char array newText, the running variable 'j' can be dropped.
  • The 2 code parts
            if (text.IndexOf("<upcase>", k) < 0)            // check if there is
            any <upcase> tag
            {                                               // if no, copy everyting
                while (i < text.Length)
                {
                    textNew[j++] = text[i++];
                }
            }
            else                                  
            {
                while (i < text.IndexOf("<upcase>", k))     // if there is an <upcase> tag, copy letters until the tag
                {
                    textNew[j++] = text[i++];
                }

                i += 8;                                     // move index i to the position right next to the <upcase> tag
                k = i;
            }

and

            if (text.IndexOf("</upcase>", k) < 0)           // check if there is any </upcase> tag
            {                                               // if no, copy everyting in CAPITAL letters
                while (i < text.Length)
                {
                    textNew[j++] = Char.ToUpper(text[i++]);
                }
            }
            else
            {
                while (i < text.IndexOf("</upcase>", k))    // if there is an </upcase> tag, copy letters in CAP letters until the tag
                {
                    textNew[j++] = Char.ToUpper(text[i++]);
                }

                i += 9;                                     // move index i to the position right next to the </upcase> tag
            }

are very simlar. Probably it is possible to create one more generic code fragment that coveres both cases.


Since your solution is still understandable for such a simple use case, it will fast become unmaintainable if the use case becomes more complex. Therefore, it makes sense to think about a more abstract OOP concepts to model the solution.

One alternative impl. (that is probably over engineered for the given problem) gives an idea how a more object oriented design could look like:

        public class Tag
        {
            private readonly Func<char, char> map;
            public Tag(string start, string end, Func<char, char> map)
            {
                this.Start = start;
                this.End = end;
                this.map = map;
            }

            public string Start { get; }
            public string End { get; }
            public char Map(char input) => this.map(input);
        }

        public class TagProcessor
        {
            private readonly Tag tag;
            private readonly StringBuilder output = new StringBuilder();

            private string input;
            private bool isTagOpen;
            private int index;

            public TagProcessor(Tag tag)
            {
                this.tag = tag;
            }

            public string Process(string input)
            {
                this.input = input;
                this.index = 0;
                this.isTagOpen = false;
                this.output.Clear();

                do
                {
                    var tagProcessed = this.TryOpenTag() || this.TryCloseTag();
                    if (!tagProcessed)
                    {
                        this.ApplyCurrentChar();
                    }
                }
                while (this.MoveNext());

                return output.ToString();
            }

            private bool IsEndTag() => input.IndexOf(tag.End, this.index) == this.index;

            private bool IsStartTag() => input.IndexOf(tag.Start, this.index) == this.index;

            private bool MoveNext()
            {
                index++;
                return index < this.input.Length;
            }

            private void ApplyCurrentChar()
            {
                var inputChar = this.input[this.index];
                var transfomed = this.isTagOpen ? tag.Map(inputChar) : inputChar;
                this.output.Append(transfomed);
            }

            private bool TryOpenTag()
            {
                if (!isTagOpen && IsStartTag())
                {
                    this.index += this.tag.Start.Length - 1;
                    this.isTagOpen = true;
                    return true;
                }

                return false;
            }

            private bool TryCloseTag()
            {
                if (isTagOpen && IsEndTag())
                {
                    this.index += this.tag.End.Length - 1;
                    this.isTagOpen = false;
                    return true;
                }

                return false;
            }
        }

        public static void Main(string[] args)
        {
            var processor = new TagProcessor(new Tag("<upcase>", "</upcase>", char.ToUpper));

            var test = new[]
            {
                "abc<upcase>test</upcase>",
                "abc<upcase>test",
                "abc<upcase></upcase>test",
                "abc<upcase>test</upcase>test",
                "abc<upcase>te<upcase>st</upcase>test",
                "a</upcase>bc<upcase>te<upcase>st</upcase>te</upcase>st",
            };

            foreach (var t in test)
                Console.WriteLine(t + ": " + processor.Process(t));
            Console.ReadLine();
        }

The advantages are, that this solution remains readable if the complexity grows (e.g. more tags were added) and it allows to change / extend the logic without understanding the whole parsing logic. Further more, each method has a single pupose which increases comprehensibleness.

\$\endgroup\$
4
\$\begingroup\$

This loop

    while (i < text.IndexOf("<upcase>", k))
    {
        ....
    }

invokes IndexOf multiple times for nothing. I'd call it just once and use the result:

    const int upcasePos = text.IndexOf("<upcase>", k);
    if (upcasePos < 0)
    {
        while (i < text.Length)
        {
            textNew[j++] = text[i++];
        }
    }
    else                                  
    {
        while (i < upcasePos)
        {
            textNew[j++] = text[i++];
        }

        ....
    }

Edit

You can also speed things up by getting rid of char-by-char iteration, and instead processing longer parts of the string at once with standard routines. Here's an outline:

    StringBuilder sb = new StringBuilder();

    for (int k = 0; k < text.length; )
    {
         int tagOpen = text.IndexOf("<upcase>", k));
         if (tagOpen < 0)
         {
             sb.Append(text.Substring(k));  // take the tail
             break;
         }

         sb.Append(text.Substring(k, tagOpen - k));
         k = tagOpen + 8;                   // skip the tag

         int tagClose = text.IndexOf("</upcase>", k));
         if (tagClose < 0)
         {
             sb.Append(text.Substring(k).toUpper());  // take the tail in upper case
             break;
         }

         sb.Append(text.Substring(k, tagClose - k).toUpper());
         k = tagClose + 9;                  // skip the tag
    }

    result = sb.ToString();   // return this
\$\endgroup\$
3
\$\begingroup\$

Below is a refactoring of your algorithm with some inline comments.

string Review(string text)
{
  const string startTag = "<upcase>"; // Use declared string rather than string literals
  const string endTag = "</upcase>";

  // textNew is a somewhat "backward" name. result or newText would be better
  char[] result = new char[text.Length];
  // Instantiate each variable on a single line. It's easier to find and maintain
  // Provide some meaningful names instead for i, j and k. (i, j and k may be alright in a lessser complex context, but here they easily lose their meaining through the loop)
  int curIndex = 0;
  int resultIndex = 0;
  int searchIndex = 0;

  while (curIndex < text.Length)
  {
    if (text.IndexOf(startTag, searchIndex) < 0) 
    {        
      while (curIndex < text.Length)
      {
        result[resultIndex++] = text[curIndex++];
      }
    }
    else
    {
      // Repeatedly calling the same function with the same values is inefficient
      int startIndex = text.IndexOf(startTag, searchIndex);
      while (curIndex < startIndex)
      {
        result[resultIndex++] = text[curIndex++];
      }

      curIndex += startTag.Length; // Use the length of the tag string instead of a magic number
      searchIndex = curIndex;
    }

    if (text.IndexOf(endTag, searchIndex) < 0)
    {                                       
      while (curIndex < text.Length)
      {
        result[resultIndex++] = Char.ToUpper(text[curIndex++]);
      }
    }
    else
    {
      // Repeatedly calling the same function with the same values is inefficient
      int endIndex = text.IndexOf(endTag, searchIndex);
      while (curIndex < endIndex)
      {
        result[resultIndex++] = Char.ToUpper(text[curIndex++]);
      }

      curIndex += endTag.Length; // Use the length of the tag string instead of a magic number
    }
  }

  // Return the result instead of write it to the console.
  return new string(result.Take(resultIndex).ToArray()); // You have to truncate the char array in order to prevent a trailing new line
  //OR: return new string(textNew).TrimEnd('\0');
}

Below is some other approaches that you may find useful for inspiration:

string ToUpperInTags(string text)
{
  const string start = "<upcase>";
  const string stop = "</upcase>";

  List<string> fragments = new List<string>();
  int curIndex = 0;
  while (curIndex < text.Length)
  {
    int startIndex = text.IndexOf(start, curIndex);
    if (startIndex >= 0)
    {
      fragments.Add(text.Substring(curIndex, startIndex - curIndex));
      int stopIndex = text.IndexOf(stop, startIndex + start.Length);
      if (stopIndex < 0) throw new InvalidOperationException($"Unpaired start at {startIndex}");
      fragments.Add(text.Substring(startIndex + start.Length, stopIndex - (startIndex + start.Length)).ToUpper());
      curIndex = stopIndex + stop.Length;
    }
    else
    {
      fragments.Add(text.Substring(curIndex));
      break;
    }
  }

  return string.Join("", fragments);
}

string ToUpperInTags2(string text)
{
  string pattern = @"(?<start><upcase>)(?<content>[^<>]*)(?<stop></upcase>)?";
  foreach (Match match in Regex.Matches(text, pattern))
  {
    text = Regex.Replace(text, $"{match.Groups["start"]}{match.Groups["content"]}{match.Groups["stop"]}", match.Groups["content"].Value.ToUpper());
  }

  return text;
}

string ToUpperInTags3(string text)
{
  string pattern = @"<upcase>(?<content>[^<>]*)(</upcase>)?";
  return Regex.Replace(text, pattern, m => m.Groups["content"].Value.ToUpper());
}

They don't all behave exactly as yours, and are just provided for inspiration for further study...

\$\endgroup\$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.