[#70] Fix analyze CRC for cah:/ ContentDirectory resources; add --skip-crc

.gitignore

@@ -40,3 +40,5 @@ UnityFileSystemTestData/UserSettings/
 UnityFileSystemTestData/Packages/
 *.db
 *.csv
+
+*.stackdump

Analyzer/AnalyzerTool.cs

@@ -26,6 +26,7 @@ public int Analyze(
         string databaseName,
         string searchPattern,
         bool skipReferences,
+        bool skipCrc,
         bool verbose,
         bool noRecursion)
     {
@@ -40,6 +41,7 @@ public int Analyze(
             {
                 parser.Verbose = verbose;
                 parser.SkipReferences = skipReferences;
+                parser.SkipCrc = skipCrc;
                 parser.Init(writer.Connection);
 
             }

Analyzer/SQLite/Handlers/ISQLiteHandler.cs

@@ -29,4 +29,5 @@ public interface ISQLiteFileParser : IDisposable
     void Parse(string filename);
     public bool Verbose { get; set; }
     public bool SkipReferences { get; set; }
+    public bool SkipCrc { get; set; }
 }

Analyzer/SQLite/Parsers/AddressablesBuildLayoutParser.cs

@@ -15,6 +15,7 @@ public class AddressablesBuildLayoutParser : ISQLiteFileParser
 
         public bool Verbose { get; set; }
         public bool SkipReferences { get; set; }
+        public bool SkipCrc { get; set; }
 
         public void Dispose()
         {

Analyzer/SQLite/Parsers/SerializedFileParser.cs

@@ -15,6 +15,7 @@ public class SerializedFileParser : ISQLiteFileParser
 
         public bool Verbose { get; set; }
         public bool SkipReferences { get; set; }
+        public bool SkipCrc { get; set; }
 
         public bool CanParse(string filename)
         {
@@ -36,7 +37,7 @@ public void Dispose()
 
         public void Init(SqliteConnection db)
         {
-            m_Writer = new SerializedFileSQLiteWriter(db, SkipReferences);
+            m_Writer = new SerializedFileSQLiteWriter(db, SkipReferences, SkipCrc);
         }
 
         public void Parse(string filename)

Analyzer/SQLite/Writers/SerializedFileSQLiteWriter.cs

@@ -19,6 +19,7 @@ public class SerializedFileSQLiteWriter : IDisposable
     private int m_NextAssetBundleId = 0;
 
     private bool m_SkipReferences;
+    private bool m_SkipCrc;
 
     private IdProvider<string> m_SerializedFileIdProvider = new();
     private ObjectIdProvider m_ObjectIdProvider = new();
@@ -54,11 +55,12 @@ public class SerializedFileSQLiteWriter : IDisposable
     private SqliteConnection m_Database;
     private SqliteCommand m_LastId = new SqliteCommand();
     private SqliteTransaction m_CurrentTransaction = null;
-    public SerializedFileSQLiteWriter(SqliteConnection database, bool skipReferences)
+    public SerializedFileSQLiteWriter(SqliteConnection database, bool skipReferences, bool skipCrc)
     {
         m_Initialized = false;
         m_Database = database;
         m_SkipReferences = skipReferences;
+        m_SkipCrc = skipCrc;
     }
 
     public void Init()
@@ -116,7 +118,7 @@ public void WriteSerializedFile(string relativePath, string fullPath, string con
     {
         using var sf = UnityFileSystem.OpenSerializedFile(fullPath);
         using var reader = new UnityFileReader(fullPath, 64 * 1024 * 1024);
-        using var pptrReader = new PPtrAndCrcProcessor(sf, reader, containingFolder, AddReference);
+        using var pptrReader = new PPtrAndCrcProcessor(sf, reader, containingFolder, m_SkipCrc, AddReference);
         int serializedFileId = m_SerializedFileIdProvider.GetId(Path.GetFileName(fullPath).ToLower());
         int sceneId = -1;
 
@@ -228,7 +230,10 @@ public void WriteSerializedFile(string relativePath, string fullPath, string con
                     m_AddObjectCommand.SetValue("game_object", "");
                 }
 
-                if (!m_SkipReferences)
+                // The walk both extracts references and accumulates the CRC, so it is needed
+                // unless both are disabled. When CRC is on but references are off, the walk
+                // still resolves referenced object ids (AddReference skips the insert).
+                if (!m_SkipReferences || !m_SkipCrc)
                 {
                     crc32 = pptrReader.Process(currentObjectId, offset, root);
                 }
@@ -264,15 +269,23 @@ public void WriteSerializedFile(string relativePath, string fullPath, string con
         }
     }
 
+    // Callback from PPtrAndCrcProcessor for each reference discovered in the SerializedFile
     private int AddReference(long objectId, int fileId, long pathId, string propertyPath, string propertyType)
     {
+        // Always resolve the id so the CRC stays stable; only persist the row when references
+        // are being extracted.
         var referencedObjectId = m_ObjectIdProvider.GetId((m_LocalToDbFileId[fileId], pathId));
-        m_AddReferenceCommand.SetTransaction(m_CurrentTransaction);
-        m_AddReferenceCommand.SetValue("object", objectId);
-        m_AddReferenceCommand.SetValue("referenced_object", referencedObjectId);
-        m_AddReferenceCommand.SetValue("property_path", propertyPath);
-        m_AddReferenceCommand.SetValue("property_type", propertyType);
-        m_AddReferenceCommand.ExecuteNonQuery();
+
+        if (!m_SkipReferences)
+        {
+            m_AddReferenceCommand.SetTransaction(m_CurrentTransaction);
+            m_AddReferenceCommand.SetValue("object", objectId);
+            m_AddReferenceCommand.SetValue("referenced_object", referencedObjectId);
+            m_AddReferenceCommand.SetValue("property_path", propertyPath);
+            m_AddReferenceCommand.SetValue("property_type", propertyType);
+            m_AddReferenceCommand.ExecuteNonQuery();
+        }
+
         return referencedObjectId;
     }
 

Documentation/analyzer.md

@@ -47,7 +47,7 @@ case, Unity will include the asset in all the AssetBundles with a reference to i
 view_potential_duplicates provides the number of instances and the total size of the potentially
 duplicated assets. It also lists all the AssetBundles where the asset was found.
 
-If the skipReferences option is used, there will be a lot of false positives in that view. Otherwise,
+If the `--skip-crc` option is used, there will be a lot of false positives in that view. Otherwise,
 it should be very accurate because CRCs are used to determine if objects are identical.
 
 ## asset_view (AssetBundleProcessor)

Documentation/command-analyze.md

@@ -13,7 +13,8 @@ UnityDataTool analyze <path> [options]
 | `<path>` | Path to folder containing files to analyze | *(required)* |
 | `-o, --output-file <file>` | Output database filename | `database.db` |
 | `-p, --search-pattern <pattern>` | File search pattern (`*` and `?` supported) | `*` |
-| `-s, --skip-references` | Skip CRC and reference extraction (faster, smaller DB) | `false` |
+| `-s, --skip-references` | Do not extract references (smaller DB, no `refs` table). CRC is still computed. | `false` |
+| `--skip-crc` | Skip the CRC32 checksum calculation (faster; `objects.crc32` will be 0) | `false` |
 | `-v, --verbose` | Show more information during analysis | `false` |
 | `--no-recurse` | Do not recurse into sub-directories | `false` |
 | `-d, --typetree-data <file>` | Load an external TypeTree data file before processing (Unity 6.5+) | — |
@@ -30,9 +31,9 @@ Analyze only `.bundle` files and specify a custom database name:
 UnityDataTool analyze /path/to/asset/bundles -o my_database.db -p "*.bundle"
 ```
 
-Fast analysis (skip reference tracking):
+Fastest analysis (skip both reference extraction and CRC):
 ```bash
-UnityDataTool analyze /path/to/bundles -s
+UnityDataTool analyze /path/to/bundles --skip-references --skip-crc
 ```
 
 See also [Analyze Examples](../../Documentation/analyze-examples.md).
@@ -121,23 +122,27 @@ See [Comparing Builds](../../Documentation/comparing-builds.md) for strategies t
 
 ### Slow Analyze times, large output database
 
-Consider using the `--skip-references` argument.
+Two independent flags reduce analyze time and database size:
 
-A real life analyze of a big Addressables build shows how large a difference this can make:
+* `--skip-crc` skips the CRC32 calculation. This is usually the largest time saver, because computing a CRC requires reading the full content of every object, including large texture, mesh and audio data in companion `.resS`/`.resource` files.
+* `--skip-references` skips reference extraction, which is the largest contributor to database size (the `refs` table). The references are not needed for core asset inventory and size information.
 
-* 208 seconds and producted a 500MB database (not specifying --skip-reference)
-* 9 seconds and produced a 68 MB file (with --skip-reference)
+For the fastest, smallest result, combine them.
 
-The references are not needed for core asset inventory and size information. 
+A real life analyze of a big Addressables build, skipping both references and CRC, shows how large a difference this can make:
 
-Note: When specifying `--skip-reference` some functionality is lost:
+* 208 seconds and produced a 500MB database (default)
+* 9 seconds and produced a 68 MB file (with `--skip-references --skip-crc`)
+
+When `--skip-references` is used, some functionality is lost:
 
 * the `find-refs` command will not work
 * `view_material_shader_refs` and `view_material_texture_refs` will be empty
+* `script_object_view` will be empty
 * Queries that look at the relationship between objects will not work.  For example the refs table is required to link between a `MonoBehaviour` and its `MonoScript`.
-* The `objects.crc32` column will be NULL/0 for all objects. This means:
-  * No detection of identical objects by content hash (See [Comparing Builds](../../Documentation/comparing-builds.md))
-  * The `view_potential_duplicates` view relies partially on CRC32 to distinguish true duplicates
 
-Future work: The refs table contains a lot of repeated strings and could be made smaller and more efficient.  It might also be prudent to control the CRC32 calculation using an independent flag.
+When `--skip-crc` is used, the `objects.crc32` column will be 0 for all objects. This means:
+
+* No detection of identical objects by content hash (See [Comparing Builds](../../Documentation/comparing-builds.md))
+* The `view_potential_duplicates` view relies partially on CRC32 to distinguish true duplicates
 

UnityDataTool/Program.cs

@@ -1,5 +1,6 @@
 using System;
 using System.CommandLine;
+using System.CommandLine.Invocation;
 using System.IO;
 using System.Threading.Tasks;
 using UnityDataTools.Analyzer;
@@ -41,7 +42,8 @@ static Command BuildAnalyzeCommand()
     {
         var pathArg = new Argument<DirectoryInfo>("path", "The path to the directory containing the files to analyze").ExistingOnly();
         var oOpt = new Option<string>(aliases: new[] { "--output-file", "-o" }, description: "Filename of the output database", getDefaultValue: () => "database.db");
-        var sOpt = new Option<bool>(aliases: new[] { "--skip-references", "-s" }, description: "Skip CRC and do not extract references");
+        var sOpt = new Option<bool>(aliases: new[] { "--skip-references", "-s" }, description: "Do not extract references (CRC is still computed unless --skip-crc is also given)");
+        var scOpt = new Option<bool>(aliases: new[] { "--skip-crc" }, description: "Skip CRC checksum calculation");
         var rOpt = new Option<bool>(aliases: new[] { "--extract-references", "-r" }) { IsHidden = true };
         var pOpt = new Option<string>(aliases: new[] { "--search-pattern", "-p" }, description: "File search pattern", getDefaultValue: () => "*");
         var vOpt = new Option<bool>(aliases: new[] { "--verbose", "-v" }, description: "Verbose output");
@@ -53,6 +55,7 @@ static Command BuildAnalyzeCommand()
             pathArg,
             oOpt,
             sOpt,
+            scOpt,
             rOpt,
             pOpt,
             vOpt,
@@ -61,14 +64,28 @@ static Command BuildAnalyzeCommand()
         };
 
         analyzeCommand.AddAlias("analyse");
-        analyzeCommand.SetHandler(
-            (DirectoryInfo di, string o, bool s, bool r, string p, bool v, bool noRecurse, FileInfo d) =>
+        // Bound via InvocationContext because the option count exceeds the strongly-typed
+        // SetHandler overloads.
+        analyzeCommand.SetHandler((InvocationContext context) =>
+        {
+            var d = context.ParseResult.GetValueForOption(dOpt);
+            var ttResult = LoadTypeTreeDataFile(d);
+            if (ttResult != 0)
             {
-                var ttResult = LoadTypeTreeDataFile(d);
-                if (ttResult != 0) return Task.FromResult(ttResult);
-                return Task.FromResult(HandleAnalyze(di, o, s, r, p, v, noRecurse));
-            },
-            pathArg, oOpt, sOpt, rOpt, pOpt, vOpt, recurseOpt, dOpt);
+                context.ExitCode = ttResult;
+                return;
+            }
+
+            context.ExitCode = HandleAnalyze(
+                context.ParseResult.GetValueForArgument(pathArg),
+                context.ParseResult.GetValueForOption(oOpt),
+                context.ParseResult.GetValueForOption(sOpt),
+                context.ParseResult.GetValueForOption(scOpt),
+                context.ParseResult.GetValueForOption(rOpt),
+                context.ParseResult.GetValueForOption(pOpt),
+                context.ParseResult.GetValueForOption(vOpt),
+                context.ParseResult.GetValueForOption(recurseOpt));
+        });
 
         return analyzeCommand;
     }
@@ -293,6 +310,7 @@ static int HandleAnalyze(
         DirectoryInfo path,
         string outputFile,
         bool skipReferences,
+        bool skipCrc,
         bool extractReferences,
         string searchPattern,
         bool verbose,
@@ -305,7 +323,7 @@ static int HandleAnalyze(
             Console.WriteLine("WARNING: --extract-references, -r option is deprecated (references are now extracted by default)");
         }
 
-        return analyzer.Analyze(path.FullName, outputFile, searchPattern, skipReferences, verbose, noRecurse);
+        return analyzer.Analyze(path.FullName, outputFile, searchPattern, skipReferences, skipCrc, verbose, noRecurse);
     }
 
     static int HandleFindReferences(FileInfo databasePath, string outputFile, long? objectId, string objectName, string objectType, bool findAll)

UnityFileSystem.Tests/UnityFileSystemTests.cs

@@ -244,6 +244,25 @@ public void ReadFile_InvalidHandle_ThrowsException()
         Assert.Throws<ObjectDisposedException>(() => file.Read(10, new byte[10]));
     }
 
+    // Ranges that cross the internal buffer boundary (and a partial final chunk) must
+    // produce the same CRC as a single-buffer read. TextFile.txt is 21 bytes; an 8-byte
+    // buffer forces three chunks (8 + 8 + 5).
+    [TestCase(0, 21)]  // whole file, partial final chunk
+    [TestCase(0, 16)]  // exact multiple of the buffer size
+    [TestCase(3, 15)]  // unaligned start, crosses two boundaries
+    [TestCase(0, 8)]   // exactly one buffer
+    [TestCase(2, 5)]   // entirely within one buffer
+    public void ComputeCRC_RangeCrossingBuffer_MatchesSingleBufferRead(long offset, int size)
+    {
+        var path = Path.Combine(Context.TestDataFolder, "TextFile.txt");
+
+        using var singleBufferReader = new UnityFileReader(path, 1024 * 1024);
+        var expected = singleBufferReader.ComputeCRC(offset, size);
+
+        using var smallBufferReader = new UnityFileReader(path, 8);
+        Assert.AreEqual(expected, smallBufferReader.ComputeCRC(offset, size));
+    }
+
     [Test]
     public void OpenFile_ArchiveFileSystem_ReturnsFile()
     {

UnityFileSystem/UnityFileReader.cs

@@ -117,16 +117,18 @@ public byte ReadUInt8(long fileOffset)
         return m_Buffer[offset];
     }
 
+    // Computes the CRC32 over a contiguous range, reading the file in buffer-sized chunks.
     public uint ComputeCRC(long fileOffset, int size, uint crc32 = 0)
     {
-        var readSize = size > m_Buffer.Length ? m_Buffer.Length : size;
-        var readBytes = 0;
+        var remaining = size;
 
-        while (readBytes < size)
+        while (remaining > 0)
         {
-            var offset = GetBufferOffset(fileOffset, readSize);
-            crc32 = Crc32Algorithm.Append(crc32, m_Buffer, offset, readSize);
-            readBytes += readSize;
+            var chunk = (int)Math.Min(m_Buffer.Length, remaining);
+            var offset = GetBufferOffset(fileOffset, chunk);
+            crc32 = Crc32Algorithm.Append(crc32, m_Buffer, offset, chunk);
+            fileOffset += chunk;
+            remaining -= chunk;
         }
 
         return crc32;