Update tooling ignores

game_re/.gitignore

@@ -1,5 +1,5 @@
-gh_auto/*
 gh_ref/*
+old/
 *.bak
 gh_cmake_timestamp
 functions.dat

game_re/CMakeLists.txt

@@ -1,64 +1,71 @@
-add_executable(game_re
-  r3/main.cpp
-  r3/binders/static_mem.cxx
-  gh_global.cxx
-)
-
-target_compile_features(game_re PUBLIC cxx_std_20)
-target_include_directories(game_re PUBLIC ${CMAKE_CURRENT_SOURCE_DIR})
-
-set_target_properties(
-  game_re PROPERTIES
-  RUNTIME_OUTPUT_DIRECTORY ${CMAKE_BINARY_DIR}/bin
-)
-
-if(WIN32 AND R3_32BIT)
-  target_link_libraries(game_re PRIVATE 
-    binkw32
-    d3d8
-    dinput8
+function(setup_target TARGET)
+  add_executable(${TARGET}
+    r3/main.cpp
+    r3/binders/static_mem.cxx
+    gh_global.cxx
   )
-endif()
 
-target_compile_definitions(game_re PRIVATE
-  R3_GAME_DATA_DIR=\"${GAME_DATA_DIR}\"
-)
+  target_compile_features(${TARGET} PUBLIC cxx_std_20)
+  target_include_directories(${TARGET} PUBLIC ${CMAKE_CURRENT_SOURCE_DIR})
 
-get_filename_component(R3_DATA_SEGMENT_FILE "${CMAKE_CURRENT_SOURCE_DIR}/gh_datasegment.bin" ABSOLUTE)
-target_compile_definitions(game_re PRIVATE
-  R3_DATA_SEGMENT_FILE=\"${R3_DATA_SEGMENT_FILE}\"
-)
+  set_target_properties(
+    ${TARGET} PROPERTIES
+    RUNTIME_OUTPUT_DIRECTORY ${CMAKE_BINARY_DIR}/bin
+  )
 
-target_compile_definitions(game_re PRIVATE
-  _CRT_SECURE_NO_WARNINGS=1
-  _CRT_NONSTDC_NO_WARNINGS=1)
+  if(WIN32 AND R3_32BIT)
+    target_link_libraries(${TARGET} PRIVATE
+      binkw32
+      d3d8
+      dinput8
+    )
+  endif()
 
-target_link_libraries(game_re PRIVATE spdlog)
+  target_compile_definitions(${TARGET} PRIVATE
+    R3_GAME_DATA_DIR=\"${GAME_DATA_DIR}\"
+  )
 
-file(GLOB GH_AUTO_SOURCES ${CMAKE_CURRENT_SOURCE_DIR}/gh_auto/*.cxx)
-file(GLOB GH_FIX_SOURCES ${CMAKE_CURRENT_SOURCE_DIR}/gh_fix/*.cxx)
-file(GLOB GH_STUB_SOURCES ${CMAKE_CURRENT_SOURCE_DIR}/gh_stub/*.cxx)
+  get_filename_component(R3_DATA_SEGMENT_FILE "${CMAKE_CURRENT_SOURCE_DIR}/gh_datasegment.bin" ABSOLUTE)
+  target_compile_definitions(${TARGET} PRIVATE
+    R3_DATA_SEGMENT_FILE=\"${R3_DATA_SEGMENT_FILE}\"
+  )
 
-target_sources(game_re PRIVATE
-  ${GH_AUTO_SOURCES}
-  ${GH_FIX_SOURCES}
-  ${GH_STUB_SOURCES}
-)
+  target_compile_definitions(${TARGET} PRIVATE
+    _CRT_SECURE_NO_WARNINGS=1
+    _CRT_NONSTDC_NO_WARNINGS=1)
 
-# Ignore -Wformat-security
-target_compile_options(game_re PRIVATE -Wno-format-security)
+  target_link_libraries(${TARGET} PRIVATE spdlog)
 
-# Ignore -Wmicrosoft-cast
-target_compile_options(game_re PRIVATE -Wno-microsoft-cast)
+  file(GLOB GH_AUTO_SOURCES ${CMAKE_CURRENT_SOURCE_DIR}/gh_auto/*.cxx)
+  file(GLOB GH_FIX_SOURCES ${CMAKE_CURRENT_SOURCE_DIR}/gh_fix/*.cxx)
+  file(GLOB GH_STUB_SOURCES ${CMAKE_CURRENT_SOURCE_DIR}/gh_stub/*.cxx)
 
-# Automatically re-run CMake if any gh_*.cxx files change
-# due to ghidra script runs
-set_property(
-  DIRECTORY
-  APPEND
-  PROPERTY CMAKE_CONFIGURE_DEPENDS ${CMAKE_CURRENT_SOURCE_DIR}/gh_cmake_timestamp
-)
+  target_sources(${TARGET} PRIVATE
+    ${GH_AUTO_SOURCES}
+    ${GH_FIX_SOURCES}
+    ${GH_STUB_SOURCES}
+  )
 
-target_precompile_headers(game_re PRIVATE
-  "$<$<COMPILE_LANGUAGE:CXX>:${CMAKE_CURRENT_SOURCE_DIR}/r3/binders/auto_pch.cxx>"
-)
+  # Ignore -Wformat-security
+  target_compile_options(${TARGET} PRIVATE -Wno-format-security)
+
+  # Ignore -Wmicrosoft-cast
+  target_compile_options(${TARGET} PRIVATE -Wno-microsoft-cast)
+
+  # Automatically re-run CMake if any gh_*.cxx files change
+  # due to ghidra script runs
+  set_property(
+    DIRECTORY
+    APPEND
+    PROPERTY CMAKE_CONFIGURE_DEPENDS ${CMAKE_CURRENT_SOURCE_DIR}/gh_cmake_timestamp
+  )
+
+  target_precompile_headers(${TARGET} PRIVATE
+    "$<$<COMPILE_LANGUAGE:CXX>:${CMAKE_CURRENT_SOURCE_DIR}/r3/binders/auto_pch.cxx>"
+  )
+endfunction()
+
+setup_target(game_re)
+
+setup_target(game_dbg)
+target_compile_definitions(game_dbg PRIVATE RE_DBG_INJECTED=1)

game_re/scan_sources

@@ -6,14 +6,21 @@ set -e
 
 pushd $script_dir
 
-file_list=files.txt
-rm -f $file_list
-for dir in gh_auto gh_stub gh_fix; do
-  for file in $dir/*.cxx; do
-    echo $file >>$file_list
-  done
+mkdir -p logs
+types=(auto ref fix stub)
+for type in "${types[@]}"; do
+    file_list="logs/files_${type}.txt"
+    rm -f "$file_list"
+
+    if [ -d "gh_${type}" ]; then
+        for file in "gh_${type}"/*.cxx; do
+            echo "$file" >>"$file_list"
+        done
+        $tool "@$file_list" -v --type=$type --log-file=logs/log-functions-${type}.txt
+    fi
 done
 
-$tool @$file_list
+$tool gh_global.h -mglobals -v --log-file=logs/log-globals.txt
+$tool -mduplicates -v --log-file=logs/log-duplicates.txt
 
 popd

java/ghidra/Test.java

@@ -1,5 +1,6 @@
 // @category _Reman3
 // @menupath Reman3.Test
+// @importpackage org.sqlite
 
 import ghidra.app.script.GhidraScript;
 import ghidra.program.model.address.Address;
@@ -26,15 +27,15 @@ import java.sql.ResultSet;
 import java.sql.SQLException;
 import java.sql.Statement;
 
-public class Test extends GhidraScript {
-  // Will rebuild all functions
-  public boolean rebuildAllGlobals = true;
-  FunctionDatabase functionDB;
+import org.sqlite.JDBC;
 
+public class Test extends GhidraScript {
   @Override
   public void run() throws Exception {
     RecompileConfig.INSTANCE = new RecompileConfig(this);
     
+    java.sql.DriverManager.registerDriver(new JDBC());
+
     // Example SQLite usage
     testSQLite();
   }
@@ -80,14 +81,4 @@ public class Test extends GhidraScript {
       throw e;
     }
   }
-
-  private void scanDirectory(File directory, FunctionDatabase.Type type) throws Exception {
-    File[] files = directory.listFiles((dir, name) -> name.endsWith(".cxx"));
-    if (files == null)
-      return;
-
-    for (File file : files) {
-      scanFile(file, type);
-    }
-  }
 }

java/ghidra/re3lib/FunctionDatabase.java

@@ -16,7 +16,8 @@ public class FunctionDatabase {
   public enum Type {
     Auto,
     Fix,
-    Stub
+    Stub,
+    Ref
   }
 
   public class Dependency implements java.io.Serializable {

java/ghidra/readme.md

@@ -1,3 +1,13 @@
 # Ghidra Scripts
 
-Add this to your scripts folder and run to generate c code for all functions in the project
+Add this to your ghidra scripts folder to add the reman decompile scripts to ghidra
+
+NOTE: Make sure to also add the include `sqlite-jdbc-3.49.1.0.jar` to the ghidra scripts folders, as this is required for the ghidra scripts to read the decompile database.
+
+## Decompile database
+
+The decompile database is a sqlite database that contains a list of all files that implement decompiled functions and their source address. It is used to regenerate files, check for duplicates, and more.
+
+To generate the database from the current set of files, run the scan_sources script in the /game_re folder.
+
+Make sure you have set up the tooling by running the /tooling/setup script.

tooling/.gitignore

@@ -1,5 +1,6 @@
 build/
 .claude/
+tmps/
 bin/
 *.db
 *.txt

tooling/Notes.md

@@ -0,0 +1,177 @@
+# C++ Function/Global Parser Tool - Database Output Summary
+
+## Overview
+This tool parses C++ source files using Tree-sitter to extract function and global variable information along with their memory addresses from comments. The extracted data is stored in an SQLite database for analysis and lookup purposes.
+
+## Database Schema
+
+The tool creates an SQLite database (default: `gh.db`) with three main tables:
+
+### 1. Functions Table
+```sql
+CREATE TABLE Functions (
+    filepath TEXT,
+    name TEXT,
+    address TEXT,
+    PRIMARY KEY (name, filepath)
+);
+```
+
+**Purpose**: Stores function definitions that have function bodies (actual implementations)
+- `filepath`: Source file path where the function is defined
+- `name`: Function name (identifier)
+- `address`: 8-character hexadecimal memory address extracted from comments
+- **Primary Key**: Combination of name and filepath (allows same function name in different files)
+
+### 2. Imports Table
+```sql
+CREATE TABLE Imports (
+    filepath TEXT,
+    name TEXT,
+    address TEXT,
+    PRIMARY KEY (name, filepath)
+);
+```
+
+**Purpose**: Stores function declarations without bodies (imports/forward declarations)
+- Same schema as Functions table
+- Distinguishes between function definitions and declarations
+- Useful for tracking external function references
+
+### 3. Globals Table
+```sql
+CREATE TABLE Globals (
+    filepath TEXT,
+    name TEXT,
+    address TEXT
+);
+```
+
+**Purpose**: Stores global variable declarations marked with `extern`
+- `filepath`: Source file path where the global is declared
+- `name`: Global variable name (identifier)
+- `address`: 8-character hexadecimal memory address from comments
+- **No Primary Key**: Allows duplicate global names across files
+
+## Address Format
+
+The tool extracts addresses from C++ comments using this regex pattern:
+```regex
+//\s*([0-9a-fA-F]{8})
+```
+
+**Expected Comment Format**:
+```cpp
+void myFunction(); // 12345678
+extern int globalVar; // ABCDEF00
+```
+
+- Addresses must be exactly 8 hexadecimal characters
+- Can be uppercase or lowercase
+- Must be in a C++ line comment (`//`)
+- Whitespace after `//` is optional
+
+## Tool Modes
+
+### 1. Functions Mode (`-m functions`)
+- **Default mode**
+- Parses C++ files for function definitions and declarations
+- Populates `Functions` and `Imports` tables
+- Distinguishes between functions with bodies vs. declarations only
+
+### 2. Globals Mode (`-m globals`)
+- Parses C++ files for `extern` global variable declarations
+- Populates `Globals` table
+- Only processes variables marked with `extern` storage class
+
+### 3. Duplicates Mode (`-m duplicates`)
+- **Analysis mode** - doesn't process files
+- Checks existing database for duplicate addresses and names
+- Reports conflicts across all tables
+- Returns exit code 1 if duplicates found, 0 if clean
+
+### 4. Dump-Tree Mode (`-m dump-tree`)
+- **Debug mode** - doesn't use database
+- Outputs Tree-sitter AST for debugging parsing issues
+- Useful for understanding how the parser interprets source code
+
+## Data Quality Checks
+
+The tool includes built-in validation:
+
+### Duplicate Address Detection
+- Scans all tables for addresses used multiple times
+- Reports format: `"DUPLICATE ADDRESS: {address} appears {count} times in: {entries}"`
+- Cross-references Functions, Imports, and Globals tables
+
+### Duplicate Name Detection
+- Checks for function names appearing in multiple files
+- Checks for global names appearing in multiple files
+- Helps identify naming conflicts and potential issues
+
+## Usage Examples
+
+### Basic Function Extraction
+```bash
+./tool file1.cpp file2.cpp -d output.db -m functions
+```
+
+### Global Variable Extraction
+```bash
+./tool globals.h -d output.db -m globals
+```
+
+### Batch Processing with File List
+```bash
+./tool -l filelist.txt -d output.db -m functions
+```
+
+### Quality Assurance Check
+```bash
+./tool -d output.db -m duplicates
+```
+
+## Database Queries for Users
+
+### Find Function by Name
+```sql
+SELECT * FROM Functions WHERE name = 'functionName';
+SELECT * FROM Imports WHERE name = 'functionName';
+```
+
+### Find All Symbols at Address
+```sql
+SELECT 'Function' as type, name, filepath FROM Functions WHERE address = '12345678'
+UNION ALL
+SELECT 'Import' as type, name, filepath FROM Imports WHERE address = '12345678'
+UNION ALL
+SELECT 'Global' as type, name, filepath FROM Globals WHERE address = '12345678';
+```
+
+### List All Functions in File
+```sql
+SELECT name, address FROM Functions WHERE filepath = 'path/to/file.cpp'
+ORDER BY name;
+```
+
+### Find Functions Without Addresses
+```sql
+SELECT name, filepath FROM Functions WHERE address = '' OR address IS NULL;
+```
+
+### Address Range Analysis
+```sql
+SELECT name, address, filepath FROM Functions
+WHERE CAST(address AS INTEGER) BETWEEN 0x10000000 AND 0x20000000
+ORDER BY CAST(address AS INTEGER);
+```
+
+## Integration Considerations
+
+- **Database Format**: Standard SQLite3 - compatible with most tools and languages
+- **File Paths**: Relative to the game source directory, meaning there will be gh_auto, gh_fix subfolders. (relative to the game_re folder in repo root)
+- **Address Format**: Always 8-character hex strings (32 bit addresses) - pad with leading zeros if needed
+- **Case Sensitivity**: Function/global names are case-sensitive as per C++ standards
+- **Unicode Support**: Handles UTF-8 encoded source files
+
+This database serves as a comprehensive symbol table for reverse engineering, debugging, and code analysis workflows.

tooling/files.sh

@@ -3,19 +3,18 @@ set -e
 tool=build/clang-x86_64-pc-windows-msvc/Release/r3_gh_tool
 cmake --build build/clang-x86_64-pc-windows-msvc/Release --target r3_gh_tool
 
-scan_dir=tmps/gh_auto
-file_list=files.txt
-rm -f $file_list
-for file in tmps/gh_auto/*.cxx; do
-    echo $file >>$file_list
-done
-for file in tmps/gh_stub/*.cxx; do
-    echo $file >>$file_list
-done
-for file in tmps/gh_fix/*.cxx; do
-    echo $file >>$file_list
+types=(auto ref fix stub)
+for type in "${types[@]}"; do
+    file_list="files_${type}.txt"
+    rm -f "$file_list"
+
+    if [ -d "tmps/gh_${type}" ]; then
+        for file in "tmps/gh_${type}"/*.cxx; do
+            echo "$file" >>"$file_list"
+        done
+        $tool "@$file_list" -v --type=$type --log-file=log-functions.txt
+    fi
 done
 
-$tool @$file_list -v --log-file=log-functions.txt
 $tool tmps/gh_global.h -mglobals -v --log-file=log-globals.txt
 $tool -mduplicates -v --log-file=log-duplicates.txt

tooling/setup

@@ -1,11 +1,13 @@
 #!/bin/bash
 
+script_dir=$(readlink -f $(dirname "$0"))
+pushd $script_dir
+
 # Create build directory if it doesn't exist
-mkdir -p build/tmp
 
 if [ ! -d "build/tmp" ]; then
     # Configure project using CMake with Ninja generator for Release build
-    cmake -S . -B build/tmp -G Ninja -DCMAKE_BUILD_TYPE=Release
+    cmake -B build/tmp -G Ninja -DCMAKE_BUILD_TYPE=Release
 fi
 
 # Build project using Ninja
@@ -21,3 +23,5 @@ if [[ "$OSTYPE" == "msys" || "$OSTYPE" == "win32" ]]; then
 else
     cp build/tmp/r3_gh_tool bin/
 fi
+
+popd

tooling/tool.cpp

@@ -18,6 +18,38 @@ extern "C" TSLanguage *tree_sitter_cpp();
 // Global address regex pattern
 const std::regex ADDRESS_REGEX(R"(//\s*([0-9a-fA-F]{8}))");
 
+// Add enum for file types
+enum class FileType { Auto, Fix, Stub, Ref };
+
+// Helper function to convert string to FileType
+FileType stringToFileType(const std::string &type_str) {
+  if (type_str == "auto")
+    return FileType::Auto;
+  if (type_str == "fix")
+    return FileType::Fix;
+  if (type_str == "stub")
+    return FileType::Stub;
+  if (type_str == "ref")
+    return FileType::Ref;
+  throw std::invalid_argument("Invalid file type: " + type_str);
+}
+
+// Helper function to convert FileType to string
+std::string fileTypeToString(FileType type) {
+  switch (type) {
+  case FileType::Auto:
+    return "auto";
+  case FileType::Fix:
+    return "fix";
+  case FileType::Stub:
+    return "stub";
+  case FileType::Ref:
+    return "ref";
+  default:
+    throw std::logic_error(fmt::format("Invalid file type: {}", (int)type));
+  }
+}
+
 // Helper function to check if a comment contains an address
 bool hasAddressPattern(const std::string &comment) {
   return std::regex_search(comment, ADDRESS_REGEX);
@@ -47,6 +79,7 @@ struct FunctionInfo {
   std::string address;
   std::string filepath;
   bool is_import;
+  FileType type; // Add type field
 };
 
 struct GlobalInfo {
@@ -81,11 +114,11 @@ public:
                      &delete_imports_stmt,
                      "Failed to prepare delete imports statement");
     prepareStatement("INSERT OR REPLACE INTO Functions (filepath, name, "
-                     "address) VALUES (?, ?, ?)",
+                     "address, type) VALUES (?, ?, ?, ?)",
                      &insert_functions_stmt,
                      "Failed to prepare insert functions statement");
-    prepareStatement("INSERT OR REPLACE INTO Imports (filepath, name, address) "
-                     "VALUES (?, ?, ?)",
+    prepareStatement("INSERT OR REPLACE INTO Imports (filepath, name, address, "
+                     "type) VALUES (?, ?, ?, ?)",
                      &insert_imports_stmt,
                      "Failed to prepare insert imports statement");
     prepareStatement("DELETE FROM Globals WHERE filepath = ?",
@@ -128,6 +161,7 @@ public:
     sqlite3_bind_text(stmt, 1, func.filepath.c_str(), -1, SQLITE_STATIC);
     sqlite3_bind_text(stmt, 2, func.name.c_str(), -1, SQLITE_STATIC);
     sqlite3_bind_text(stmt, 3, func.address.c_str(), -1, SQLITE_STATIC);
+    sqlite3_bind_int(stmt, 4, static_cast<int>(func.type));
     sqlite3_step(stmt);
   }
 
@@ -157,8 +191,8 @@ public:
     }
 
     const char *create_tables = R"(
-            CREATE TABLE IF NOT EXISTS Functions (filepath TEXT, name TEXT, address TEXT, PRIMARY KEY (name, filepath));
-            CREATE TABLE IF NOT EXISTS Imports (filepath TEXT, name TEXT, address TEXT, PRIMARY KEY (name, filepath));
+            CREATE TABLE IF NOT EXISTS Functions (filepath TEXT, name TEXT, address TEXT, type INTEGER DEFAULT 0, PRIMARY KEY (name, filepath));
+            CREATE TABLE IF NOT EXISTS Imports (filepath TEXT, name TEXT, address TEXT, type INTEGER DEFAULT 0, PRIMARY KEY (name, filepath));
             CREATE TABLE IF NOT EXISTS Globals (filepath TEXT, name TEXT, address TEXT);
         )";
 
@@ -197,7 +231,7 @@ public:
   bool checkDuplicateAddresses() {
     const char *sql = R"(
       WITH all_addresses AS (
-        SELECT 'Functions' as table_name, name, address, filepath FROM Functions WHERE address != ''
+        SELECT 'Functions' as table_name, name, address, filepath FROM Functions WHERE address != '' AND type != 3
         UNION ALL
         SELECT 'Globals' as table_name, name, address, filepath FROM Globals WHERE address != ''
       )
@@ -239,6 +273,7 @@ public:
       SELECT name, COUNT(*) as count,
              GROUP_CONCAT(filepath, '; ') as filepaths
       FROM Functions
+      WHERE type != 3
       GROUP BY name
       HAVING COUNT(*) > 1
       ORDER BY name;
@@ -390,7 +425,7 @@ bool hasFunctionBody(TSNode node) {
 }
 
 void findFunctions(TSNode node, const char *source_code, uint32_t source_length,
-                   std::vector<FunctionInfo> &functions) {
+                   std::vector<FunctionInfo> &functions, FileType file_type) {
   const char *type = ts_node_type(node);
 
   if (strcmp(type, "function_definition") == 0 ||
@@ -409,7 +444,8 @@ void findFunctions(TSNode node, const char *source_code, uint32_t source_length,
         FunctionInfo func{func_name, address, "",
                           strcmp(type, "function_definition") == 0
                               ? !hasFunctionBody(node)
-                              : true};
+                              : true,
+                          file_type}; // Add file_type parameter
         functions.push_back(func);
       }
       // We'll never nest function declarations
@@ -422,8 +458,8 @@ void findFunctions(TSNode node, const char *source_code, uint32_t source_length,
 
   uint32_t child_count = ts_node_child_count(node);
   for (uint32_t i = 0; i < child_count; i++) {
-    findFunctions(ts_node_child(node, i), source_code, source_length,
-                  functions);
+    findFunctions(ts_node_child(node, i), source_code, source_length, functions,
+                  file_type);
   }
 }
 
@@ -454,7 +490,8 @@ std::vector<std::string> readFileList(const std::string &list_file) {
   return files;
 }
 
-bool processFile(const std::string &filepath, DatabaseManager &db) {
+bool processFile(const std::string &filepath, DatabaseManager &db,
+                 FileType file_type) {
   std::ifstream file(filepath);
   if (!file.is_open()) {
     spdlog::error("Could not open file {}", filepath);
@@ -482,17 +519,18 @@ bool processFile(const std::string &filepath, DatabaseManager &db) {
 
   std::vector<FunctionInfo> functions;
   findFunctions(root_node, file_content.c_str(), file_content.length(),
-                functions);
+                functions, file_type);
 
   for (auto &func : functions) {
     func.filepath = filepath;
     db.insertFunction(func);
-    spdlog::debug("{}: {} @ {} in {}", func.is_import ? "Import" : "Function",
-                  func.name, func.address, filepath);
+    spdlog::debug("{}: {} @ {} in {} (type: {})",
+                  func.is_import ? "Import" : "Function", func.name,
+                  func.address, filepath, fileTypeToString(func.type));
   }
 
-  spdlog::info("Processed {} functions/imports from {}", functions.size(),
-               filepath);
+  spdlog::info("Processed {} functions/imports from {} (type: {})",
+               functions.size(), filepath, fileTypeToString(file_type));
 
   ts_tree_delete(tree);
   ts_parser_delete(parser);
@@ -741,6 +779,7 @@ int main(int argc, char *argv[]) {
   std::string db_path = "gh.db";
   std::string mode = "functions";
   std::string log_file = "";
+  std::string type_str = "auto"; // Add type string variable
   bool verbose = false;
 
   app.add_option("files", input_files,
@@ -755,11 +794,24 @@ int main(int argc, char *argv[]) {
       ->default_val("functions")
       ->check(
           CLI::IsMember({"functions", "globals", "duplicates", "dump-tree"}));
+  app.add_option("-t,--type", type_str,
+                 "File type: 'auto', 'fix', 'stub', or 'ref'")
+      ->default_val("auto")
+      ->check(CLI::IsMember({"auto", "fix", "stub", "ref"}));
   app.add_flag("-v,--verbose", verbose, "Enable verbose logging (debug level)");
   app.add_flag("--log-file", log_file, "Enable logging to file");
 
   CLI11_PARSE(app, argc, argv);
 
+  // Convert string to FileType enum
+  FileType file_type;
+  try {
+    file_type = stringToFileType(type_str);
+  } catch (const std::invalid_argument &e) {
+    spdlog::error("Invalid file type: {}", type_str);
+    return 1;
+  }
+
   // Set log level based on verbose flag
   if (verbose) {
     spdlog::set_level(spdlog::level::debug);
@@ -830,10 +882,10 @@ int main(int argc, char *argv[]) {
       db.beginTransaction();
 
       for (const auto &filepath : files_to_process) {
-        spdlog::info("=== Processing: {} ===", filepath);
+        spdlog::info("=== Processing: {} (type: {}) ===", filepath, type_str);
         bool success = false;
         if (mode == "functions") {
-          success = processFile(filepath, db);
+          success = processFile(filepath, db, file_type);
         } else if (mode == "globals") {
           success = processGlobalsFile(filepath, db);
         }
@@ -860,6 +912,7 @@ int main(int argc, char *argv[]) {
     spdlog::info("=== Summary ===");
     spdlog::info("Processed {} files successfully", processed_count);
     spdlog::info("Mode: {}", mode);
+    spdlog::info("File type: {}", type_str);
     if (mode != "dump-tree") {
       spdlog::info("Database saved to: {}", db_path);
     }