#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <3ds.h>
#include <citro3d.h>
#include <string.h>
#include "vshader_shbin.h"


#define CLEAR_COLOR (0x68B0D8FF)

#define DISPLAY_TRANSFER_FLAGS \
	(GX_TRANSFER_FLIP_VERT(0) | GX_TRANSFER_OUT_TILED(0) | GX_TRANSFER_RAW_COPY(0) | \
	GX_TRANSFER_IN_FORMAT(GX_TRANSFER_FMT_RGB8) | GX_TRANSFER_OUT_FORMAT(GX_TRANSFER_FMT_RGB8) | \
	GX_TRANSFER_SCALING(GX_TRANSFER_SCALE_NO))


static DVLB_s* vshader_dvlb;
static shaderProgram_s program;
static int uLoc_projection;
static C3D_Mtx projection;
static C3D_Tex maintex;



static void sceneInit(void)
{
	// Load the vertex shader, create a shader program and bind it
	vshader_dvlb = DVLB_ParseFile((u32*)vshader_shbin, vshader_shbin_size);
	shaderProgramInit(&program);
	shaderProgramSetVsh(&program, &vshader_dvlb->DVLE[0]);
	C3D_BindProgram(&program);

	// Get the location of the uniforms
	uLoc_projection = shaderInstanceGetUniformLocation(program.vertexShader, "projection");

	// Configure attributes for use with the vertex shader
	// Attribute format and element count are ignored in immediate mode
	C3D_AttrInfo* attrInfo = C3D_GetAttrInfo();
	AttrInfo_Init(attrInfo);
	AttrInfo_AddLoader(attrInfo, 0, GPU_FLOAT, 3); // v0=position xyz
	AttrInfo_AddLoader(attrInfo, 1, GPU_FLOAT, 2); // v1=texcoord xy

	// Compute the projection matrix
	Mtx_OrthoTilt(&projection, 0.0, 400.0, 0.0, 240.0, 0.0, 1.0, true);

	FILE *f = fopen("sdmc:/rgb_gba_test.bin", "rb");
	u8 *const data = linearAlloc(256 * 256 * 3);
	u8 *dst = data;
	for(u32 i = 0; i < 160; i++)
	{
		fread(dst, 240 * 3, 1, f);
		dst += 256 * 3;
	}
	fclose(f);
	GSPGPU_FlushDataCache(data, 256 * 256 * 3);

	C3D_TexInit(&maintex, 256, 256, GPU_RGB8);
	const u32 flags = (GX_TRANSFER_FLIP_VERT(0) | GX_TRANSFER_OUT_TILED(1) | GX_TRANSFER_RAW_COPY(0) |
		GX_TRANSFER_IN_FORMAT(GX_TRANSFER_FMT_RGB8) | GX_TRANSFER_OUT_FORMAT(GX_TRANSFER_FMT_RGB8) |
		GX_TRANSFER_SCALING(GX_TRANSFER_SCALE_NO));
	C3D_SyncDisplayTransfer((u32*)data, GX_BUFFER_DIM(256, 256), (u32*)maintex.data, GX_BUFFER_DIM(256, 256), flags);
	linearFree(data);

	C3D_TexSetFilter(&maintex, GPU_LINEAR, GPU_NEAREST);
	//C3D_TexSetWrap(&maintex, GPU_CLAMP_TO_EDGE, GPU_CLAMP_TO_EDGE);
	C3D_TexBind(0, &maintex);

	// Configure the first fragment shading substage to just pass through the vertex color
	// See https://www.opengl.org/sdk/docs/man2/xhtml/glTexEnv.xml for more insight
	C3D_TexEnv* env = C3D_GetTexEnv(0);
	C3D_TexEnvInit(env);
	C3D_TexEnvSrc(env, C3D_Both, GPU_TEXTURE0, 0, 0);
	C3D_TexEnvFunc(env, C3D_Both, GPU_REPLACE);
	//C3D_TexEnvScale(env, C3D_Both, GPU_TEVSCALE_2);

	C3D_TexEnv* env1 = C3D_GetTexEnv(1);
	C3D_TexEnvInit(env1);
	C3D_TexEnvSrc(env1, C3D_Both, GPU_PREVIOUS, GPU_PREVIOUS, 0);
	C3D_TexEnvFunc(env1, C3D_Both, GPU_MODULATE);
}

static void sceneRender(void)
{
	// Update the uniforms
	C3D_FVUnifMtx4x4(GPU_VERTEX_SHADER, uLoc_projection, &projection);
// with scake=1.5, then xShift=20
// 
// with scake=1.0, then xShift=80, the reason is 256 is change to 512
// 80 0 0.5 1
// 0 0.6875 0 0		--> 0.6875 = 1-80/256
// 320 0 0.5 1
// 0.46875 0.6875 0 0    --> 120/256 1-80/256
// 80 160 0.5 1
// 0 1 0 0
// 320 160 0.5 1
// 0.46875 1 0 0
	// Draw a textured quad directly
	C3D_ImmDrawBegin(GPU_TRIANGLE_STRIP);
		const float scale = 1.5f;
		const float xShift = (400.0f - (240.0f * scale)) / 2.0f;

		// Bottom left corner.
		C3D_ImmSendAttrib(xShift, 0.0f, 0.5f, 1.0f);                   // v0=position xyz
		C3D_ImmSendAttrib(0.0f, 1.0f - (160.0f / 256.0f), 0.0f, 0.0f); // v1=texcoord xy

		// Bottom right corner.
		C3D_ImmSendAttrib(240.0f * scale + xShift, 0.0f, 0.5f, 1.0f);
		C3D_ImmSendAttrib(1.0f * 240.0f / 256.0f, 1.0f - (160.0f / 256.0f), 0.0f, 0.0f);

		// Top left corner.
		C3D_ImmSendAttrib(xShift, 160.0f * scale, 0.5f, 1.0f);
		C3D_ImmSendAttrib(0.0f, 1.0f, 0.0f, 0.0f);

		// Top right corner.
		C3D_ImmSendAttrib(240.0f * scale + xShift, 160.0f * scale, 0.5f, 1.0f);
		C3D_ImmSendAttrib(1.0f * 240.0f / 256.0f, 1.0f, 0.0f, 0.0f);
	C3D_ImmDrawEnd();
}

static void sceneExit(void)
{
	// Free the shader program
	shaderProgramFree(&program);
	DVLB_Free(vshader_dvlb);
	C3D_TexDelete(&maintex);
}

int main()
{
	// Initialize graphics
	gfxInit(GSP_BGR8_OES, GSP_RGB565_OES, false);
	C3D_Init(C3D_DEFAULT_CMDBUF_SIZE);

	// Initialize the render target
	C3D_RenderTarget* target = C3D_RenderTargetCreate(240, 400, GPU_RB_RGB8, GPU_RB_DEPTH24_STENCIL8);
	C3D_StencilTest(false, GPU_ALWAYS, 0, 0, 0);
	C3D_EarlyDepthTest(false, GPU_EARLYDEPTH_GEQUAL, 0);
	C3D_DepthTest(false, GPU_ALWAYS, GPU_WRITE_COLOR);
	C3D_AlphaTest(false, GPU_ALWAYS, 0);
	C3D_RenderTargetSetOutput(target, GFX_TOP, GFX_LEFT, DISPLAY_TRANSFER_FLAGS);

	// Initialize the scene
	sceneInit();

	// Main loop
	while (aptMainLoop())
	{
		hidScanInput();

		// Respond to user input
		u32 kDown = hidKeysDown();
		if (kDown & KEY_START)
			break; // break in order to return to hbmenu

		// Render the scene
		C3D_FrameBegin(C3D_FRAME_SYNCDRAW);
			C3D_RenderTargetClear(target, C3D_CLEAR_ALL, CLEAR_COLOR, 0);
			C3D_FrameDrawOn(target);
			sceneRender();
		C3D_FrameEnd(0);
	}

	// Deinitialize the scene
	sceneExit();

	C3D_RenderTargetDelete(target);

	// Deinitialize graphics
	C3D_Fini();
	gfxExit();
	return 0;
}


// -Wl,-wrap=GX_ProcessCommandList
Result __wrap_GX_ProcessCommandList(u32* buf0a, u32 buf0s, u8 flags)
{
	static u32 dumped = 0;

	if(dumped == 0)
	{
		dumped++;

		FILE *f = fopen("sdmc:/first_cmdlist.bin", "wb");
		fwrite(buf0a, buf0s, 1, f);
		fclose(f);
	}
	else if(dumped == 1)
	{
		dumped++;

		FILE *f = fopen("sdmc:/second_cmdlist.bin", "wb");
		fwrite(buf0a, buf0s, 1, f);
		fclose(f);
	}

	return __real_GX_ProcessCommandList(buf0a, buf0s, flags);
}