Improve SmartCN tests: Replace file existence checks with asserts, refine maxlength usage

Author: NehanPathan

src/Lucene.Net.Analysis.SmartCn/Hhmm/BigramDictionary.cs

@@ -266,13 +266,12 @@ public virtual void LoadFromFile(string dctFilePath)
             Span<int> buffer = stackalloc int[3];
             string tmpword;
 
-            // LUCENENET: Removed buffer and intBuffer arrays since BinaryReader handles reading values directly in a more type-safe and readable way.
+            // LUCENENET: Removed intBuffer arrays since BinaryReader handles reading values directly in a more type-safe and readable way.
             // LUCENENET specific - refactored constants for clarity
 
             // The 3756th position (using 1-based counting) corresponds to index 3755 (using 0-based indexing)
             // This matches the original Java implementation which used 3755 + GB2312_FIRST_CHAR in the condition
             const int HEADER_POSITION = 3755;
-            const int MAX_VALID_LENGTH = 1000;
 
             //using (RandomAccessFile dctFile = new RandomAccessFile(dctFilePath, "r"))
             using var dctFile = new FileStream(dctFilePath, FileMode.Open, FileAccess.Read);
@@ -310,7 +309,7 @@ public virtual void LoadFromFile(string dctFilePath)
                     buffer[2] = reader.ReadInt32(); // Skip handle value (unused)
 
                     length = buffer[1];
-                    if (length > 0 && length <= MAX_VALID_LENGTH && dctFile.Position + length <= dctFile.Length)
+                    if (length > 0 && dctFile.Position + length <= dctFile.Length)
                     {
                         byte[] lchBuffer = reader.ReadBytes(length);  // LUCENENET: Use BinaryReader to decode little endian instead of ByteBuffer, since this is the default in .NET
 

src/Lucene.Net.Analysis.SmartCn/Hhmm/WordDictionary.cs

@@ -351,8 +351,9 @@ private int LoadMainDataFromFile(string dctFilePath)
             // The 3756th is used (as a header) to store information.
 
             Span<int> buffer = stackalloc int[3];
+            string tmpword;
 
-            // LUCENENET: Removed buffer and intBuffer arrays since BinaryReader handles reading values directly in a more type-safe and readable way.
+            // LUCENENET: Removed intBuffer arrays since BinaryReader handles reading values directly in a more type-safe and readable way.
             // LUCENENET: Use BinaryReader to simplify endian conversion and stream reading.
 
             using (var dctFile = new FileStream(dctFilePath, FileMode.Open, FileAccess.Read))
@@ -394,7 +395,7 @@ private int LoadMainDataFromFile(string dctFilePath)
                         if (length > 0)
                         {
                             byte[] lchBuffer = reader.ReadBytes(length);
-                            string tmpword = gb2312Encoding.GetString(lchBuffer); // LUCENENET: Use cached encoding instance from base class
+                            tmpword = gb2312Encoding.GetString(lchBuffer); // LUCENENET: Use cached encoding instance from base class
                             wordItem_charArrayTable[i][j] = tmpword.ToCharArray();
                         }
                         else

src/Lucene.Net.Tests.Analysis.SmartCn/Hhmm/TestBuildDictionary.cs

@@ -55,23 +55,22 @@ public void TestBigramDictionary()
             // First test - builds and loads dictionary from .dict file
             BigramDictionary bigramDict = BigramDictionary.GetInstance();
             CheckBigramDictionary(bigramDict);
-            
+
             // Ensure .mem file was created
-            string memFile = System.IO.Path.Combine(tempDir.FullName,  "bigramdict.mem");
+            string memFile = System.IO.Path.Combine(tempDir.FullName, "bigramdict.mem");
             Assert.IsTrue(File.Exists(memFile), "Memory file should be created after first load");
-            
+
             // Delete the original .dict file
-            string dictFile = System.IO.Path.Combine(tempDir.FullName,  "bigramdict.dct");
-            if (File.Exists(dictFile))
-            {
-                File.Delete(dictFile);
-            }
-            
+            string dictFile = System.IO.Path.Combine(tempDir.FullName, "bigramdict.dct");
+            Assert.IsTrue(File.Exists(dictFile), $"{dictFile} does not exist.");
+            File.Delete(dictFile);
+
+
             // Second test - should load from .mem file now
             bigramDict = BigramDictionary.GetInstance();
             CheckBigramDictionary(bigramDict);
         }
-        
+
         private static void CheckBigramDictionary(BigramDictionary bigramDict)
         {
             Assert.AreEqual(10, bigramDict.GetFrequency("啊hello".AsSpan()), "Frequency for '啊hello' is incorrect.");
@@ -84,23 +83,22 @@ public void TestWordDictionary()
             // First test - builds and loads dictionary from .dict file
             WordDictionary wordDict = WordDictionary.GetInstance();
             CheckWordDictionary(wordDict);
-            
+
             // Ensure .mem file was created
             string memFile = System.IO.Path.Combine(tempDir.FullName, "coredict.mem");
             Assert.IsTrue(File.Exists(memFile), "Memory file should be created after first load");
-            
+
             // Delete the original .dict file
             string dictFile = System.IO.Path.Combine(tempDir.FullName, "coredict.dct");
-            if (File.Exists(dictFile))
-            {
-                File.Delete(dictFile);
-            }
-            
+            Assert.IsTrue(File.Exists(dictFile), $"{dictFile} does not exist.");
+            File.Delete(dictFile);
+
+
             // Second test - should load from .mem file now
             wordDict = WordDictionary.GetInstance();
             CheckWordDictionary(wordDict);
         }
-        
+
         private static void CheckWordDictionary(WordDictionary wordDict)
         {
             Assert.AreEqual(30, wordDict.GetFrequency("尼".ToCharArray()), "Frequency for '尼' is incorrect.");