Add & improve string extensions and add tests

src/CuteUtils.Tests/Misc/StringExtTests.cs

@@ -0,0 +1,161 @@
+using CuteUtils.Misc;
+
+namespace CuteUtils.Tests.Misc;
+
+[TestClass]
+public class StringExtTests_Coverage
+{
+    [TestMethod]
+    public void ToFileName_EmptyAndNull_ReturnsEmptyOrThrows()
+    {
+        Assert.AreEqual("", "".ToFileName());
+        Assert.AreEqual("", "".ToFileName(allowSpaces: false));
+
+        string? nullStr = null;
+        _ = Assert.ThrowsExactly<NullReferenceException>(() => nullStr!.ToFileName());
+    }
+
+    [TestMethod]
+    public void ToFileName_NormalizesUnicodeAccents()
+    {
+        string input = "Ångström Îñţérñåţîöñåļ";
+        string output = input.ToFileName();
+
+        Assert.IsFalse(output.Any(c => c > 127));  // no extended unicode
+        Assert.Contains("An", output);       // Å -> A + n (typical decompose)
+    }
+
+    [TestMethod]
+    public void ToFileName_LongString_TrimsProperly()
+    {
+        string longInput = new('x', 500);
+        string result = longInput.ToFileName();
+
+        Assert.IsLessThanOrEqualTo(255, result.Length, "File name should be trimmed to FS-safe length");
+    }
+
+    [TestMethod]
+    public void ToPath_EmptyAndNull_ReturnsEmptyOrThrows()
+    {
+        Assert.AreEqual("", "".ToPath());
+
+        string? nullStr = null;
+        _ = Assert.ThrowsExactly<NullReferenceException>(() => nullStr!.ToPath());
+    }
+
+    [TestMethod]
+    public void ToPath_RemovesBothFileAndPathInvalidChars()
+    {
+        string input = "t<>e\"s|t/dir\\name:*?";
+        string output = input.ToPath();
+
+        foreach (char c in Path.GetInvalidPathChars())
+        {
+            Assert.DoesNotContain(c, output);
+        }
+    }
+
+    [TestMethod]
+    public void Truncate_HandlesNull_Throws()
+    {
+        string? nullStr = null;
+        _ = Assert.ThrowsExactly<NullReferenceException>(() => nullStr!.Truncate(5));
+    }
+
+    [TestMethod]
+    public void Truncate_LongString_Performance()
+    {
+        string longStr = new('x', 10_000);
+        string result = longStr.Truncate(100);
+
+        Assert.AreEqual(100, result.Length);
+    }
+
+    [TestMethod]
+    public void CorrectNewLine_EmptyString_ReturnsEmpty()
+    {
+        Assert.AreEqual("", "".CorrectNewLine());
+    }
+
+    [TestMethod]
+    public void CorrectNewLine_Mixed_Newlines_Normalizes()
+    {
+        string mixed = "a\r\nb\nc\rd";
+
+        string result = mixed.CorrectNewLine();
+
+        if (Environment.OSVersion.Platform == PlatformID.Unix)
+        {
+            Assert.AreEqual("a\nb\nc\nd", result);
+        }
+        else
+        {
+            Assert.AreEqual("a\r\nb\r\nc\r\nd", result);
+        }
+    }
+
+    [TestMethod]
+    public void RemoveWhitespaces_UnicodeSpaces()
+    {
+        string input = "a\u2003b\u3000c"; // em-space, ideographic space
+        Assert.AreEqual("abc", input.RemoveWhitespaces());
+    }
+
+    [TestMethod]
+    public void Reverse_EmptyAndSingleCharacter()
+    {
+        Assert.AreEqual("", "".Reverse());
+        Assert.AreEqual("a", "a".Reverse());
+    }
+
+    [TestMethod]
+    public void Reverse_UnicodeCombiningCharacters()
+    {
+        string input = "e\u0301"; // é composed as e + diacritic
+        string result = input.Reverse();
+
+        Assert.AreEqual("\u0301e", result);
+    }
+
+    [TestMethod]
+    public void ReplaceCaseInsensitive_UnicodeCase()
+    {
+        string input = "Straße"; // Eszett
+        string replaced = input.ReplaceCaseInsensitive("ß", "ss");
+
+        Assert.AreEqual("Strasse", replaced);
+    }
+
+    [TestMethod]
+    public void ReplaceCaseInsensitive_ReplacesOverlappingCorrectly()
+    {
+        string input = "aaaa";
+        string replaced = input.ReplaceCaseInsensitive("aa", "b");
+
+        Assert.AreEqual("bb", replaced); // correct non-overlapping behavior
+    }
+
+    [TestMethod]
+    public void RemoveDiacritics_RemovesAccents_PreservesBaseCharacters()
+    {
+        // composed character
+        string caf = "café";
+        Assert.AreEqual("cafe", caf.RemoveDiacritics());
+
+        // another composed example (Å -> A or Ang depending on normalization)
+        string ang = "Ångström";
+        Assert.AreEqual("Angstrom", ang.RemoveDiacritics());
+
+        // decomposed form: e + combining acute accent
+        string decomposed = "e\u0301"; // e + ◌́
+        Assert.AreEqual("e", decomposed.RemoveDiacritics());
+
+        // empty string stays empty
+        Assert.AreEqual(string.Empty, string.Empty.RemoveDiacritics());
+
+        // null behavior: current implementation will throw NullReferenceException
+        string? nullStr = null;
+        _ = Assert.ThrowsExactly<NullReferenceException>(() => nullStr!.RemoveDiacritics());
+    }
+
+}

src/CuteUtils/Misc/StringExtentions.cs

@@ -1,169 +1,172 @@
 using System.Globalization;
 using System.Text;
+using System.Text.RegularExpressions;
 
 namespace CuteUtils.Misc;
 
 /// <summary>
-/// <see cref="string"/> Extensions
+/// Provides extension methods for working with <see cref="string"/> values.
 /// </summary>
 public static class StringExt
 {
+    internal static string Sanitize(string str, char[] invalidChars, bool allowSpaces)
+    {
+        if (!allowSpaces)
+        {
+            str = str.Replace(" ", string.Empty);
+        }
+
+        foreach (char c in invalidChars)
+        {
+            str = str.Replace(c.ToString(), string.Empty);
+        }
+
+        return str.RemoveDiacritics();
+    }
+
     /// <summary>
-    /// Removes all invalid chars from the specified <see cref="string"/>
+    /// Converts the string into a valid file name by removing invalid characters
+    /// and optionally removing spaces. Diacritics (accents) are also removed.
     /// </summary>
-    /// <param name="str"></param>
-    /// <param name="allowSpaces"></param>
-    /// <returns></returns>
+    /// <param name="str">The input string.</param>
+    /// <param name="allowSpaces">Whether spaces should be preserved.</param>
+    /// <returns>A sanitized string that is safe to use as a file name.</returns>
     public static string ToFileName(this string str, bool allowSpaces = false)
     {
-        char[] invalidChars = Path.GetInvalidFileNameChars();
+        string path = Sanitize(str, Path.GetInvalidFileNameChars(), allowSpaces);
 
-        if (!allowSpaces)
+        if (path.Length > 255)
         {
-            str = str.Replace(" ", string.Empty);
+            path = path[..255];
         }
 
-        foreach (char item in invalidChars)
-        {
-            str = str.Replace(item.ToString(), string.Empty);
-        }
-
-        string normalizedString = str.Normalize(NormalizationForm.FormD);
-        StringBuilder stringBuilder = new StringBuilder();
-
-        foreach (char c in normalizedString)
-        {
-            UnicodeCategory unicodeCategory = CharUnicodeInfo.GetUnicodeCategory(c);
-            if (unicodeCategory != UnicodeCategory.NonSpacingMark)
-            {
-                _ = stringBuilder.Append(c);
-            }
-        }
-
-        return stringBuilder.ToString().Normalize(NormalizationForm.FormC);
+        return path;
     }
 
     /// <summary>
-    /// Removes all invalid chars from the specified <see cref="string"/>
+    /// Converts the string into a valid file system path segment by removing invalid characters
+    /// and optionally removing spaces. Diacritics (accents) are also removed.
     /// </summary>
-    /// <param name="str"></param>
-    /// <param name="allowSpaces"></param>
-    /// <returns></returns>
+    /// <param name="str">The input string.</param>
+    /// <param name="allowSpaces">Whether spaces should be preserved.</param>
+    /// <returns>A sanitized string that is safe to use as a path segment.</returns>
     public static string ToPath(this string str, bool allowSpaces = false)
     {
-        char[] invalidChars = Path.GetInvalidPathChars();
-
-        if (!allowSpaces)
-        {
-            str = str.Replace(" ", string.Empty);
-        }
-
-        foreach (char item in invalidChars)
-        {
-            str = str.Replace(item.ToString(), string.Empty);
-        }
-
-        string normalizedString = str.Normalize(NormalizationForm.FormD);
-        StringBuilder stringBuilder = new StringBuilder();
-
-        foreach (char c in normalizedString)
-        {
-            UnicodeCategory unicodeCategory = CharUnicodeInfo.GetUnicodeCategory(c);
-            if (unicodeCategory != UnicodeCategory.NonSpacingMark)
-            {
-                _ = stringBuilder.Append(c);
-            }
-        }
-
-        return stringBuilder.ToString().Normalize(NormalizationForm.FormC);
+        return Sanitize(str, Path.GetInvalidPathChars(), allowSpaces);
     }
 
     /// <summary>
-    /// Truncates a <see cref="string"/> to the specified length.
+    /// Returns a truncated version of the string with a maximum length.
     /// </summary>
-    /// <param name="str"></param>
-    /// <param name="length"></param>
-    /// <returns></returns>
+    /// <param name="str">The input string.</param>
+    /// <param name="length">The maximum allowed length.</param>
+    /// <returns>
+    /// The truncated string if the input exceeds <paramref name="length"/>;
+    /// otherwise, the original string.
+    /// </returns>
     public static string Truncate(this string str, int length)
     {
-        if (str.Length > length && length > 0)
-        {
-            return str[..length];
-        }
-
-        return str;
+        return (length > 0 && str.Length > length) ? str[..length] : str;
     }
 
     /// <summary>
-    /// Truncates a <see cref="string"/> to the specified length.
+    /// Returns a truncated version of the string with a maximum length,
+    /// optionally appending an ellipsis ("...") if the string is shortened.
     /// </summary>
-    /// <param name="str"></param>
-    /// <param name="length"></param>
-    /// <param name="ellipsis"></param>
-    /// <returns></returns>
+    /// <param name="str">The input string.</param>
+    /// <param name="length">The maximum allowed length.</param>
+    /// <param name="ellipsis">Whether to append "..." when truncated.</param>
+    /// <returns>The truncated string, with optional ellipsis.</returns>
     public static string Truncate(this string str, int length, bool ellipsis)
     {
-        if (str.Length > length && length > 0)
+        if (length <= 0 || str.Length <= length)
         {
-            if (ellipsis && length > 3)
-            {
-                return $"{str[..(length - 3)]}...";
-            }
-            else
-            {
-                return str[..length];
-            }
+            return str;
         }
 
-        return str;
+        if (ellipsis && length > 3)
+        {
+            return $"{str[..(length - 3)]}...";
+        }
+
+        return str[..length];
     }
 
     /// <summary>
-    /// Uses the correct newline <see cref="string"/> defined for this environment.
+    /// Normalizes newline characters in the string to the current environment's newline format.
     /// </summary>
-    /// <param name="str"></param>
-    /// <returns></returns>
+    /// <param name="str">The input string.</param>
+    /// <returns>
+    /// A string where all newline sequences are converted to
+    /// <see cref="Environment.NewLine"/>.
+    /// </returns>
+    /// <remarks>
+    /// This method safely normalizes mixed newline styles (CR, LF, CRLF).
+    /// </remarks>
     public static string CorrectNewLine(this string str)
     {
-        if (Environment.OSVersion.Platform == PlatformID.Unix)
-        {
-            str = str.Replace("\r\n", "\n");
-        }
-        else
-        {
-            str = str.Replace("\n", "\r\n"); //Ik that this can produce wrong results
-        }
-
-        return str;
+        return str
+            .Replace("\r\n", "\n")
+            .Replace("\r", "\n")
+            .Replace("\n", Environment.NewLine);
     }
 
     /// <summary>
-    /// Removes all white spaces from the specified <see cref="string"/>
+    /// Removes all whitespace characters from the string.
     /// </summary>
-    /// <param name="str"></param>
-    /// <returns></returns>
+    /// <param name="str">The input string.</param>
+    /// <returns>The string with all whitespace removed.</returns>
     public static string RemoveWhitespaces(this string str)
     {
-        StringBuilder result = new StringBuilder();
-        foreach (char c in str)
-        {
-            if (!char.IsWhiteSpace(c))
-            {
-                _ = result.Append(c);
-            }
-        }
-        return result.ToString();
+        return new string(str.Where(c => !char.IsWhiteSpace(c)).ToArray());
     }
 
     /// <summary>
-    /// Reverses the specified <see cref="string"/>
+    /// Returns a new string with the characters reversed.
     /// </summary>
-    /// <param name="str"></param>
-    /// <returns></returns>
+    /// <param name="str">The input string.</param>
+    /// <returns>The reversed string.</returns>
     public static string Reverse(this string str)
     {
-        char[] array = str.ToCharArray();
-        Array.Reverse(array);
-        return new string(array);
+        char[] arr = str.ToCharArray();
+        Array.Reverse(arr);
+        return new string(arr);
     }
-}
+
+    /// <summary>
+    /// Replaces all occurrences of a substring with another string,
+    /// using a case-insensitive comparison.
+    /// </summary>
+    /// <param name="input">The input string.</param>
+    /// <param name="search">The substring to search for.</param>
+    /// <param name="replacement">The replacement text.</param>
+    /// <returns>The modified string.</returns>
+    public static string ReplaceCaseInsensitive(this string input, string search, string replacement)
+    {
+        return Regex.Replace(input, Regex.Escape(search), replacement.Replace("$", "$$"), RegexOptions.IgnoreCase);
+    }
+
+    /// <summary>
+    /// Removes diacritic marks (accents) from characters in the string.
+    /// </summary>
+    /// <param name="str">The input string.</param>
+    /// <returns>The string with diacritics removed.</returns>
+    /// <remarks>
+    /// This is useful for normalization and for generating file-safe names.
+    /// </remarks>
+    public static string RemoveDiacritics(this string str)
+    {
+        string normalized = str.Normalize(NormalizationForm.FormD);
+        StringBuilder sb = new StringBuilder(normalized.Length);
+
+        foreach (char c in normalized)
+        {
+            if (CharUnicodeInfo.GetUnicodeCategory(c) != UnicodeCategory.NonSpacingMark)
+            {
+                _ = sb.Append(c);
+            }
+        }
+
+        return sb.ToString().Normalize(NormalizationForm.FormC);
+    }
+}