dotnet format

Author: Nick-Nuon

benchmark/Benchmark.cs

@@ -15,8 +15,8 @@ namespace SimdUnicodeBenchmarks
     public class Checker
     {
         List<char[]> names;
-        List<char[]> nonAsciichars;
-public List<byte[]> nonAsciiByteArrays; // Declare at the class level
+        List<char[]> nonAsciichars;
+        public List<byte[]> nonAsciiByteArrays; // Declare at the class level
 
         List<bool> results;
 
@@ -56,8 +56,8 @@ public static char[] GetRandomASCIIString(uint n)
         public static char[] GetRandomNonASCIIString(uint n)
         {
             // Chose a few Latin Extended-A and Latin Extended-B characters alongside ASCII chars
-            var allowedChars = "abcdefghijkmnopqrstuvwxyzABCDEFGHJKLMNOPQRSTUVWXYZ01234567é89šžŸũŭůűųŷŹźŻżŽ";
-            
+            var allowedChars = "abcdefghijkmnopqrstuvwxyzABCDEFGHJKLMNOPQRSTUVWXYZ01234567é89šžŸũŭůűųŷŹźŻżŽ";
+
             var chars = new char[n];
             var rd = new Random(12345); // fixed seed
 
@@ -71,7 +71,7 @@ public static char[] GetRandomNonASCIIString(uint n)
 
 
 
-        [Params(100, 200, 500,1000,2000)]
+        [Params(100, 200, 500, 1000, 2000)]
         public uint N;
 
 

test/AsciiTest.cs

@@ -79,8 +79,8 @@ public void HardCodedSequencesTest()
         foreach (var sequence in goodsequences)
         {
             Assert.True(SimdUnicode.Ascii.IsAscii(sequence), "Expected valid ASCII sequence");
-            Assert.True(SimdUnicode.Ascii.SIMDIsAscii(sequence), "Expected SIMDIsAscii to validate ASCII sequence");
-            
+            Assert.True(SimdUnicode.Ascii.SIMDIsAscii(sequence), "Expected SIMDIsAscii to validate ASCII sequence");
+
         }
 
         foreach (var sequence in badsequences)
@@ -91,7 +91,7 @@ public void HardCodedSequencesTest()
     }
 
     [Fact]
-    public void Test_random_ASCII_sequences_of_varying_lengths()
+    public void Test_ASCII_generator()
     {
         const int NUM_TRIALS = 1000;
         const int MAX_LENGTH = 255;
@@ -126,17 +126,16 @@ public void Test_random_ASCII_sequences_of_varying_lengths()
 
 
     [Fact]
-    // This mimics the no_error_ASCII test
-    public void TestNoErrorASCII()
+    public void TestNoErrorGetIndexOfFirstNonAsciiByte()
     {
         const int NUM_TRIALS = 1000;
         const int LENGTH = 512;
         RandomUtf8 utf8Generator = new RandomUtf8(0, 100, 0, 0, 0);  // Only ASCII/one-bytes
 
         for (int trial = 0; trial < NUM_TRIALS; trial++)
         {
-            byte[] ascii = utf8Generator.Generate(LENGTH);
-            
+            byte[] ascii = utf8Generator.Generate(LENGTH);
+
             unsafe
             {
                 fixed (byte* pAscii = ascii)
@@ -152,8 +151,7 @@ public void TestNoErrorASCII()
     }
 
     [Fact]
-    // This mimics the error_ASCII test
-    public void TestErrorASCII()
+    public void TestErrorGetIndexOfFirstNonAsciiByte()
     {
         const int NUM_TRIALS = 1000;
         const int LENGTH = 512;
@@ -182,7 +180,7 @@ public void TestErrorASCII()
                 ascii[i] -= 0b10000000;
             }
         }
-    }
-
-    
+    }
+
+
 }

test/helpers/randomutf8.cs

@@ -6,10 +6,10 @@ public class RandomUtf8
 {
     // Internal random number generator
     private Random gen;
-    
+
     // Array of probabilities for each UTF-8 byte count (1-byte, 2-bytes, etc.)
     private double[] probabilities;
-    
+
     // Maximum number of bytes a UTF-8 character can be (based on the standard)
     private const int maxByteLength = 4;
 
@@ -28,11 +28,11 @@ public byte[] Generate(int outputBytes)
         {
             uint codePoint = GenerateCodePoint();
             byte[] utf8Bytes = EncodeToUTF8(codePoint);
-            
+
             // Ensure we don't exceed the desired length
             if (result.Count + utf8Bytes.Length > outputBytes)
                 break;
-                
+
             result.AddRange(utf8Bytes);
         }
         return result.ToArray();
@@ -56,13 +56,13 @@ public byte[] Generate(int outputBytes, long seed)
     private uint GenerateCodePoint()
     {
         int byteCount = PickRandomByteCount();
-        
+
         // Depending on the byte count, generate an appropriate UTF-8 sequence
         switch (byteCount)
         {
             // Each case follows UTF-8 encoding rules for 1-byte, 2-byte, 3-byte, and 4-byte sequences
             case 1: return (uint)gen.Next(0x00, 0x80); // 1-byte sequence
-            case 2: return (uint)((gen.Next(0xC2, 0xDF) << 8) | (0x80 | gen.Next(0x00, 0x40))); 
+            case 2: return (uint)((gen.Next(0xC2, 0xDF) << 8) | (0x80 | gen.Next(0x00, 0x40)));
             case 3: return (uint)((gen.Next(0xE0, 0xEF) << 16) | ((0x80 | gen.Next(0x00, 0x40)) << 8) | (0x80 | gen.Next(0x00, 0x40)));
             case 4: return (uint)((gen.Next(0xF0, 0xF4) << 24) | ((0x80 | gen.Next(0x00, 0x40)) << 16) | ((0x80 | gen.Next(0x00, 0x40)) << 8) | (0x80 | gen.Next(0x00, 0x40)));
             default: throw new InvalidOperationException($"Invalid byte count: {byteCount}"); // Guard clause for invalid byte count
@@ -74,30 +74,30 @@ private int PickRandomByteCount()
     {
         double randomValue = gen.NextDouble() * probabilities.Sum();
         double cumulative = 0.0;
-        
+
         // Check each cumulative probability until the random value is less than the cumulative sum
         for (int i = 0; i < maxByteLength; i++)
         {
             cumulative += probabilities[i];
             if (randomValue <= cumulative)
                 return i + 1; // Return the byte count
         }
-        
+
         return maxByteLength; // Default to max byte length
     }
 
     // Convert the generated code point into a valid UTF-8 sequence
     private byte[] EncodeToUTF8(uint codePoint)
     {
         var result = new List<byte>();
-        
+
         // Break the code point into its constituent bytes
         while (codePoint != 0)
         {
             result.Add((byte)(codePoint & 0xFF));
             codePoint >>= 8;
         }
-        
+
         result.Reverse(); // Reverse to get the bytes in the correct order
         return result.ToArray();
     }