Unity C++ Native Plugin Examples

Unity scripting environment runs C# Mono container which supports native C/C++ plugins with Mono PInvoke. This allows easy integration of native library functions to both pass and receive data between Unity managed C# and native platform code.

Basic concept is simple. Native function descriptor that specify calling convention and dynamically loaded library (DDL) tell Mono how it’s parameters and returns values should be converted. Mono handles things mostly automatically from there on.

Some care is required to do this efficiently. C# PInvoke defines marshaling as a protocol to serialize and deserialize managed objects back and forth towards native code. This may generate lot of overhead. Mono garbage collector might accidentally destroy memory of an object while it’s used in the native code space.

Example C++ code is for a native Win32 plugin but is trivial to port to any platform.

Basic Data

Passing simple integral types, integers and arrays of them is straightforward.

Native c code.

extern "C" {

#define PLUGINEX(rtype) UNITY_INTERFACE_EXPORT rtype UNITY_INTERFACE_API

    PLUGINEX(int) ReturnInt()
    {
        return 0xBABE;
    }

    PLUGINEX(void) AcceptArray1(char *arr, int length)
    {
        for (int i = 0; i < length; i++) {
           arr[i] = 'A' + i;
        }
    }
}

C# declarations and example calling code.

[DllImport("ptest")]
private static extern int ReturnInt();

[DllImport("ptest")]
private static extern void AcceptArray1([In, Out] byte[] arr, int length);

void TestIntegral() {
    // return int
    print(ReturnInt());

    // accept byte array, uses marshaling to pass array back and forth
    byte[] arr1 = { 0, 0, 0 };
    AcceptArray1(arr1, arr1.Length);
    for (int i = 0; i < arr1.Length; i++)
    {
        print("arr" + i + "=" + arr1[i]);
    }
}
Strings

Strings are passed and returned as character arrays. It’s possible to use automatic marshaling conversions and return dynamically allocated strings that will be automatically deallocated.

Native c code.

extern "C" {

#define PLUGINEX(rtype) UNITY_INTERFACE_EXPORT rtype UNITY_INTERFACE_API

	PLUGINEX(bool) AcceptStr(LPCSTR pStr)
	{
		return !strcmp(pStr, "FOO");
	}
	PLUGINEX(LPSTR) ReturnDynamicStr()
	{		
		LPSTR str = (LPSTR)CoTaskMemAlloc(512);
		strcpy_s(str, 512, "Dynamic string");
		return str;
	}

	PLUGINEX(LPCSTR) ReturnConstStr()
	{		
		return "Constant string";
	}
}

C# declarations and example calling code.

[DllImport("ptest")]
private static extern bool AcceptStr([MarshalAs(UnmanagedType.LPStr)] string ansiStr);

// automatically deallocates the return string with CoTaskMemFree
[DllImport("ptest")]
[return: MarshalAs(UnmanagedType.LPStr)]
private static extern string ReturnDynamicStr();

[DllImport("ptest")]
private static extern IntPtr ReturnConstStr();


void TestStrings() {
    // accept string
    bool r1 = AcceptStr("BAR");
    bool r2 = AcceptStr("FOO");
    print("r1=" + r1); // r1=false
    print("r2=" + r2); // r1=true

    // return dynamically allocated string
    string s1 = ReturnDynamicStr();
    print("s1=" + s1);

    // return constant string
    string s2 = Marshal.PtrToStringAnsi(ReturnConstStr());
    print("s2=" + s2);
}
Arrays

Both dynamic and constant arrays can be supported but some helper functions are needed.

Native c code.

extern "C" {

#define PLUGINEX(rtype) UNITY_INTERFACE_EXPORT rtype UNITY_INTERFACE_API

	PLUGINEX(void) AcceptArray1(char *arr, int length)
	{
		for (int i = 0; i < length; i++) {
			arr[i] = 'A' + i;
		}
	}

	PLUGINEX(void) AcceptArray2(char *arr, int length)
	{
		for (int i = 0; i < length; i++) {
			arr[i] = 'A' + i;
		}
	}

	PLUGINEX(int) AcceptStrArray(const char* const *strArray, int size)
	{
		int total = 0;
		for (int i = 0; i < size; i++) {
			auto str = strArray[i];
			total += (int)strlen(str);
		}
		// return total length of the strings in the array to demonstrate that
		// it was passed correctly
		return total;
	}

	PLUGINEX(LPBYTE) ReturnDynamicByteArray(int &pSize)
	{
		pSize = 0xFF;
		LPBYTE pData = (LPBYTE)CoTaskMemAlloc(pSize);

		// fill with example data
		for (int i = 0; i < pSize; i++) {
			pData[i] = i + 1;
		}

		return pData;
	}

	PLUGINEX(LPSTR*) ReturnDynamicStrArray(int &pSize)
	{
		// Allocate an array with pointers to 3 dynamically allocated strings
		pSize = 3;
		LPSTR* pData = (LPSTR*)CoTaskMemAlloc((pSize)*sizeof(LPSTR));		
		pData[0] = (LPSTR)CoTaskMemAlloc(128);
		pData[1] = (LPSTR)CoTaskMemAlloc(128);
		pData[2] = (LPSTR)CoTaskMemAlloc(128);

		strcpy_s(pData[0], 128, "String 1");
		strcpy_s(pData[1], 128, "String 2");
		strcpy_s(pData[2], 128, "String 3");

		return pData;
	}
}

C# declarations and example calling code.


[DllImport("ptest")]
private static extern void AcceptArray1(IntPtr arr, int length);

[DllImport("ptest")]
private static extern void AcceptArray2(IntPtr arr, int length);

[DllImport("ptest")]
private static extern int AcceptStrArray(IntPtr array, int size);

[DllImport("ptest")]
private static extern IntPtr ReturnDynamicByteArray(ref int size);

[DllImport("ptest")]
private static extern IntPtr ReturnDynamicStrArray(ref int size);

///// Helper functions for marshalling /////

// Convert and copy array of strings to raw memory
private static IntPtr MarshalStringArray(string[] strArr)
{
    IntPtr[] dataArr = new IntPtr[strArr.Length];
    for (int i = 0; i < strArr.Length; i++)
    {
        dataArr[i] = Marshal.StringToCoTaskMemAnsi(strArr[i]);
    }
    IntPtr dataNative = Marshal.AllocCoTaskMem(Marshal.SizeOf(typeof(IntPtr)) * strArr.Length);
    Marshal.Copy(dataArr, 0, dataNative, dataArr.Length);

    return dataNative;
}

// Decodes string array from raw pointer
private static string[] MarshalStringArray(IntPtr dataPtr, int arraySize)
{
    var dataPtrArray = new IntPtr[arraySize];
    var strArray = new String[arraySize];
    Marshal.Copy(dataPtr, dataPtrArray, 0, arraySize);
    for (int i = 0; i < arraySize; i++)
    {
        strArray[i] = Marshal.PtrToStringAnsi(dataPtrArray[i]);
        Marshal.FreeCoTaskMem(dataPtrArray[i]);
    }
    Marshal.FreeCoTaskMem(dataPtr);
    return strArray;
}

// Dellocates encoded string array
private static void CleanUpNativeStrArray(IntPtr dataPtr, int arraySize)
{
    var dataPtrArray = new IntPtr[arraySize];
    Marshal.Copy(dataPtr, dataPtrArray, 0, arraySize);
    for (int i = 0; i < arraySize; i++)
    {
        Marshal.FreeCoTaskMem(dataPtrArray[i]);
    }
    Marshal.FreeCoTaskMem(dataPtr);
}

void TestArrays() {

    // accept byte array, uses marshalling to pass array back and forth
    byte[] arr1 = { 0, 0, 0 };
    AcceptArray1(arr1, arr1.Length);
    for (int i = 0; i < arr1.Length; i++)
    {
        print("arr" + i + "=" + arr1[i]);
    }

    // accept byte array, passes no-copy raw memory pointer
    byte[] arr2 = { 0, 0, 0 };
    GCHandle h = GCHandle.Alloc(arr2, GCHandleType.Pinned);
    AcceptArray2(h.AddrOfPinnedObject(), arr2.Length);
    for (int i = 0; i < arr2.Length; i++)
    {
        print("arr" + i + "=" + arr2[i]);
    }
    h.Free();

    // return dynamically allocated byte array
    int arraySize = 0;
    IntPtr dataPtr = ReturnDynamicByteArray(ref arraySize);
    byte[] data = new byte[arraySize];
    Marshal.Copy(dataPtr, data, 0, arraySize);
    Marshal.FreeCoTaskMem(dataPtr); // deallocate unmanaged memory
    print("data["+arraySize+"] = [" + data[0] + ", " + data[1] + ", " + data[2] + ",...]");

    // return dynamically allocated string array
    arraySize = 0;
    dataPtr = ReturnDynamicStrArray(ref arraySize);
    String[] strArray = MarshalStringArray(dataPtr, arraySize);
    print("strArray["+arraySize+"] = [" + String.Join(",", strArray) + "]");

    // string array as parameter
    dataPtr = MarshalStringArray(new String[] { "foo1", "foo2", "foo3" });
    int len = AcceptStrArray(dataPtr, arraySize);
    print("len=" + len);
    CleanUpNativeStrArray(dataPtr, arraySize);

}
Structures and Arrays of Structures

Array handling is similar to the string arrays. Most objects can be passed as is but if they have array properties those must be of fixed size.

Native c code.

extern "C" {

#define PLUGINEX(rtype) UNITY_INTERFACE_EXPORT rtype UNITY_INTERFACE_API

	struct ExampleStruct {
		INT16 val1;
		INT32 array1[3];
		INT16 array2len;
		INT32 array2[10];
		LPSTR str1;
	};

	PLUGINEX(int) AcceptStruct(ExampleStruct &s)
	{
		// Modify struct
		s.val1 -= 1111;
		for (int i= 0; i < 3; i++) {
			s.array1[i] += 1;			
		}
		for (int i = 0; i < s.array2len; i++) {
			s.array2[i] += 10;
		}
		// return length of the string in the argument struct to demonstrate that
		// it was passed correctly
		return (int)strlen(s.str1);
	}

	struct ExamplePoint {
		FLOAT x;
		FLOAT y;
		FLOAT z;
	};

	PLUGINEX(ExamplePoint *) ReturnArrayOfPoints(int &size)
	{
		size = 4;
		ExamplePoint *pointArr = (ExamplePoint*)CoTaskMemAlloc(sizeof(ExamplePoint) * size);

		// fill with some example data
		for (int i = 0; i < size; i++) {
			pointArr[i] = { i + 0.1f, i + 0.2f, i + 0.3f };
		}
		return pointArr;
	}

	// this return type is blittable
	// https://stackoverflow.com/questions/10320502/c-sharp-calling-c-function-that-returns-struct-with-fixed-size-char-array
	//
	PLUGINEX(ExamplePoint) ReturnStruct()
	{		
		return { 1, 2, 3 };
	}	
}

C# declarations and example calling code.

[StructLayout(LayoutKind.Sequential)]
public struct ExamplePoint
{
    public float x;
    public float y;
    public float z;

    // for debugging
    public override String ToString()
    {
        return "{" + x + ","+ y + "," + z + "}";
    }
}

[DllImport("ptest")]
private static extern IntPtr ReturnArrayOfPoints(ref int size);

[StructLayout(LayoutKind.Sequential, CharSet = CharSet.Ansi)]
public struct ExampleStruct
{
    public UInt16 val1;
    [MarshalAsAttribute(UnmanagedType.ByValArray, SizeConst = 3)]
    public UInt32[] array1;
    public UInt16 array2len;
    [MarshalAsAttribute(UnmanagedType.ByValArray, SizeConst = 10)]
    public UInt32[] array2;
    [MarshalAs(UnmanagedType.LPStr)]
    public string str1;
}

[DllImport("ptest")]
private static extern int AcceptStruct(ref ExampleStruct s);

[DllImport("ptest")]
private static extern ExamplePoint ReturnStruct(); 


void TestStructures() {
    // Structure as parameter
    ExampleStruct s = new ExampleStruct
    {
        val1 = 9999,
        array1 = new UInt32[3],
        array2 = new UInt32[10]
    };
    s.array1[0] = 1;
    s.array1[1] = 2;
    s.array1[2] = 3;
    s.array2len = 5;
    s.array2[0] = 10;
    s.array2[1] = 11;
    s.array2[2] = 12;
    s.array2[3] = 13;
    s.array2[4] = 14;
    s.str1 = "Cat is a feline";

    len = AcceptStruct(ref s);
    print("s.val1=" + s.val1 + " len=" + len);

    // return struct
    ExamplePoint p = ReturnStruct();

    // Marshal array of point objects
    arraySize = 0;
    dataPtr = ReturnArrayOfPoints(ref arraySize);
    ExamplePoint[] pointArr = new ExamplePoint[arraySize];

    // memory layout
    // |float|float|float|float|float|float|float|float|float|float..
    // |   ExamplePoint0 |   ExamplePoint1 |   ExamplePoint2 |
    int offset = 0;
    int pointSize = Marshal.SizeOf(typeof(ExamplePoint));
    for(int i=0; i < arraySize; i++)
    {
        pointArr[i] = (ExamplePoint)Marshal.PtrToStructure(new IntPtr(dataPtr.ToInt32() + offset), typeof(ExamplePoint));
        offset += pointSize;
    }
    print("pointArr["+arraySize+"]=["+pointArr[0]+", "+pointArr[1]+",...]");
    Marshal.FreeCoTaskMem(dataPtr);

}

Many of these examples can be done in cleaner way using MarshalAsAttribute. Code above does show what is happening under the hood.

Get full implementation ftom https://github.com/tikonen/blog/tree/master/unityplugin

Git revision as compiler definition in build with CMake

This is how to auto-generate a version header file with git revision (SHA) and the exact build time as C defines. Include header in your source as convenient way to have access to the exact git version for the application version string or diagnostics output.

Header file with the git revision and build timestamp.

// gitversion.h
#pragma once

#define GIT_REVISION "f8d2aca"
#define BUILD_TIMESTAMP "2017-07-14T20:24:36"

CMake script generates the header in cmake build directory

# cmake/gitversion.cmake
cmake_minimum_required(VERSION 3.0.0)

message(STATUS "Resolving GIT Version")

set(_build_version "unknown")

find_package(Git)
if(GIT_FOUND)
  execute_process(
    COMMAND ${GIT_EXECUTABLE} rev-parse --short HEAD
    WORKING_DIRECTORY "${local_dir}"
    OUTPUT_VARIABLE _build_version
    ERROR_QUIET
    OUTPUT_STRIP_TRAILING_WHITESPACE
  )
  message( STATUS "GIT hash: ${_build_version}")
else()
  message(STATUS "GIT not found")
endif()

string(TIMESTAMP _time_stamp)

configure_file(${local_dir}/cmake/gitversion.h.in ${output_dir}/gitversion.h @ONLY)

It’s possible to run this script only once in configuration, but you could also use it in main CMakeLists.txt to execute it before every build.

# Example CMakeLists.txt
cmake_minimum_required(VERSION 3.7.0)
project(Main)

set(_target Main)
add_executable(${_target} src/main.c)

add_custom_command(TARGET ${_target}
  PRE_BUILD
  COMMAND ${CMAKE_COMMAND}
    -Dlocal_dir="${CMAKE_CURRENT_SOURCE_DIR}"
    -Doutput_dir="${CMAKE_CURRENT_BINARY_DIR}"
    -P "${CMAKE_CURRENT_SOURCE_DIR}/cmake/gitversion.cmake"
)

# for finding generated gitversion.h
target_include_directories(${_target} PRIVATE ${CMAKE_BINARY_DIR})

Caveats!
– Build steps are executed only if the build is really needed, if target is up to date no command is executed.
– All build steps are not supported when using the Unix Makefile generator.

Get full example from https://github.com/tikonen/blog/tree/master/cmake/git_version

update_directory command for CMake

CMake offers several platform independent commands for manipulating files that are used often in the custom build commands. (For more details see Command-Line Tool Mode.)

One of the more useful ones is the copy_directory that is commonly used in post-build step to copy configuration and support files (configs, DLLs, …) to the binary directory so program can be directly executed in a IDE or debugger.
Unfortunately this command always overwrites the contents of the destination directory so all changes in the target folder are lost, this is a problem when developer wants to keep local configuration changes during development.

Here is how you can implement a custom update_directory that works exactly like copy_directory but writes files to the destination folder only if they are missing or the file timestamp is older.

# cmake/update_directory.cmake
file(GLOB_RECURSE _file_list RELATIVE "${src_dir}" "${src_dir}/*")

foreach( each_file ${_file_list} )
  set(destinationfile "${dst_dir}/${each_file}")
  set(sourcefile "${src_dir}/${each_file}")
  if(NOT EXISTS ${destinationfile} OR ${sourcefile} IS_NEWER_THAN ${destinationfile})
    get_filename_component(destinationdir ${destinationfile} DIRECTORY)
    file(COPY ${sourcefile} DESTINATION ${destinationdir})
  endif()
endforeach(each_file)

This is how you might use it in CMakeLists.txt

# Example CMakeLists.txt
cmake_minimum_required(VERSION 3.7.0)
project(Dummy)

set(_target Dummy)
add_executable(${_target} src/dummy.c)

set(source_dir "${CMAKE_CURRENT_SOURCE_DIR}/configs")
set(dest_dir "$<TARGET_FILE_DIR:${_target}>")

# Copy changed files from config to the binary folder after
# a successful build
add_custom_command(TARGET ${_target}
  POST_BUILD
  COMMAND ${CMAKE_COMMAND}
    -Dsrc_dir="${source_dir}"
    -Ddst_dir="${dest_dir}"
    -P "${CMAKE_CURRENT_SOURCE_DIR}/cmake/update_directory.cmake"
)

Caveat! CMake post build steps are executed only if the build is really needed, if target is up to date no command is executed.

Get full example from https://github.com/tikonen/blog/tree/master/cmake/update_directory

C++11 Variadic Templates implementation of parameterized strings

C++11 introduces variadic templates that allow nice way to have generic functions with unknown arguments, especially when used in recursive way. This makes easy to implement functions that before were cumbersome to write or hard to use.

Nice use case are parametric formatted strings where part of the strings are replaced with run time data. For example:

"Hello {0}, how are you?"
"Hello {name}, you logged in last {date}".

This find of format is quite easy to implement with recursive variadic templates so that it supports both indexed  and named replacement.

inline std::string format_r(int /*pos*/, std::string format) { return format; }
inline std::string format(const std::string format) { return format; }

template <typename T, typename... ARGS>
std::string format_r(int pos, std::string format, const T&amp; value, ARGS... args);

// convenience short hand for building a format parameter
template <typename... ARGS>
std::pair<ARGS...> _p(ARGS... args) { return std::make_pair(std::forward<ARGS>(args)...); };

template <typename K, typename T, typename... ARGS>
std::string format_r(int pos, std::string format, const std::pair<K, T>& value, ARGS... args)
{
    std::ostringstream os;
    os << value.second;
    auto parameter = str("{", value.first, "}");
    replace_all(format, parameter, std::string(os.str()));
    return format_r(pos + 1, format, std::forward<ARGS>(args)...);
}

template <typename T, typename... ARGS>
std::string format_r(int pos, std::string format, const &T value, ARGS... args)
{
    return format_r(pos, format, std::make_pair(str(pos), value), std::forward<ARGS>(args)...);
}

template <typename T, typename... ARGS>
std::string format(const std::string format, const &T value, ARGS... args)
{
    return format_r(0, format, value, std::forward<ARGS>(args)...);
}

 

Format function wraps a recursive function that builds the string by replacing one parameter at a time and then processing it again for the next argument until it runs out of parameters.

String conversions are handled with std::ostringstream that supports overloaded ‘<<‘ operation for most common data types.

Format function can be called with index formatting:

using util::format;
format("Hello {0}!", "World"); // Hello World
format("{0} {1}!", "Hello", "World"); // Hello World
format("{0} + {1} = {2}", 1, 2, 3); // 1 + 2 = 3

Or alternatively with explicit parameter names:

using util;
format("Hello {what}!", _p("what", "World"));
format("{word} {other}!", _p("word", "World"), _p("other", "World"));
format("{a} + {b} = {c}", _p("a", 1), _p("b", 2), _p("c", 3));

Get full implementation ftom https://github.com/tikonen/blog/tree/master/variadicformat

Quick and robust C++ CSV reader with boost

This is quick and simple CSV reader based on Boost regular expression token iterator. Parser splits the input with a regular expressions and returns the result as a collection of vectors of strings.
Regular expression handles neatly lot of the complicated edge cases such as empty columns, quoted text, etc..

Parser code

#include <boost/regex.hpp>

// used to split the file in lines
const boost::regex linesregx("\\r\\n|\\n\\r|\\n|\\r");

// used to split each line to tokens, assuming ',' as column separator
const boost::regex fieldsregx(",(?=(?:[^\"]*\"[^\"]*\")*(?![^\"]*\"))");

typedef std::vector<std::string> Row;

std::vector<Row> parse(const char* data, unsigned int length)
{
    std::vector<Row> result;

    // iterator splits data to lines
    boost::cregex_token_iterator li(data, data + length, linesregx, -1);
    boost::cregex_token_iterator end;

    while (li != end) {
        std::string line = li->str();
        ++li;

        // Split line to tokens
        boost::sregex_token_iterator ti(line.begin(), line.end(), fieldsregx, -1);
        boost::sregex_token_iterator end2;

        std::vector<std::string> row;
        while (ti != end2) {
            std::string token = ti->str();
            ++ti;
            row.push_back(token);
        }
        if (line.back() == ',') {
            // last character was a separator
            row.push_back("");
        }
        result.push_back(row);
    }
    return result;
}

Example

CSV data with common problem cases, such as empty quotes, commas inside quotes and empty last column.

a,b,c
1,"cat",3
",2",dog,4
3,a b,5
4,empty,
5,,empty
6,"",empty2
7,x,long story no commas
8,y,"some, commas, here,"

Read and parse the CSV data above and output the parsed result

int main(int argc, char*argv[])
{
	// read example file
	std::ifstream infile;
	infile.open("example.csv");
	char buffer[1024];
	infile.read(buffer, sizeof(buffer));
	buffer[infile.tellg()] = '\0';

	// parse file
	std::vector<Row> result  = parse(buffer, strlen(buffer));

	// print out result
	for(size_t r=0; r < result.size(); r++) {
		Row& row = result[r];
		for(size_t c=0; c < row.size() - 1; c++) {
			std::cout << row[c] << "\t";
		}
		std::cout << row.back() << std::endl;
	}
}

Output

$ ./reader
a      	b      	c
1      	"cat"  	3
",2"   	dog    	4
3      	a b    	5
4      	empty
5      	        empty
6      	""      empty2
7      	x      	long story no commas
8      	y      	"some, commas, here,"

See full example code in Github: https://github.com/tikonen/blog/tree/master/boostcsvreader