konabot/konabot/plugins/roll_dice/roll_dice.py

from io import BytesIO

import cv2
import numpy as np
from PIL import Image, ImageDraw, ImageFont

from konabot.common.path import ASSETS_PATH, FONTS_PATH


def text_to_transparent_image(text, font_size=40, padding=0, text_color=(0, 0, 0)):
    """
    将文本转换为带透明背景的图像，图像大小刚好包含文本
    """
    # 创建临时图像来计算文本尺寸
    temp_image = Image.new('RGB', (1, 1), (255, 255, 255))
    temp_draw = ImageDraw.Draw(temp_image)
    
    font = ImageFont.truetype(FONTS_PATH / "montserrat.otf", font_size)
    
    # 获取文本边界框
    bbox = temp_draw.textbbox((0, 0), text, font=font)
    text_width = bbox[2] - bbox[0]
    text_height = bbox[3] - bbox[1]
    
    # 计算图像大小（文本大小 + 内边距）
    image_width = int(text_width + 2 * padding)
    image_height = int(text_height + 2 * padding)
    
    # 创建RGBA模式的空白图像（带透明通道）
    image = Image.new('RGBA', (image_width, image_height), (0, 0, 0, 0))
    draw = ImageDraw.Draw(image)
    
    # 绘制文本（考虑内边距）
    x = padding - bbox[0]  # 调整起始位置
    y = padding - bbox[1]
    
    # 设置文本颜色（带透明度）
    if len(text_color) == 3:
        text_color = text_color + (255,)  # 添加完全不透明的alpha值
    
    draw.text((x, y), text, fill=text_color, font=font)
    
    # 转换为OpenCV格式（BGRA）
    image_cv = cv2.cvtColor(np.array(image), cv2.COLOR_RGBA2BGRA)
    return image_cv

def perspective_transform(image, target, corners):
    """
    对图像进行透视变换（保持透明通道）
    target: 画布
    corners: 四个角点的坐标，顺序为 [左上, 右上, 右下, 左下]
    """
    height, width = image.shape[:2]
    
    # 源点（原始图像的四个角）
    src_points = np.array([
        [0, 0],           # 左上
        [width-1, 0],     # 右上
        [width-1, height-1], # 右下
        [0, height-1]     # 左下
    ], dtype=np.float32)
    
    # 目标点（变换后的四个角）
    dst_points = np.array(corners, dtype=np.float32)
    
    # 计算透视变换矩阵
    matrix = cv2.getPerspectiveTransform(src_points, dst_points)
    
    # 获取画布大小
    target_height, target_width = target.shape[:2]

    # 应用透视变换（保持所有通道，包括alpha）
    transformed = cv2.warpPerspective(image, matrix, (target_width, target_height), flags=cv2.INTER_LINEAR)

    return transformed, matrix

def blend_with_transparency(background, foreground, position):
    """
    将带透明通道的前景图像合成到背景图像上
    position: 前景图像在背景图像上的位置 (x, y)
    """
    bg = background.copy()
    
    # 如果背景没有alpha通道，添加一个
    if bg.shape[2] == 3:
        bg = cv2.cvtColor(bg, cv2.COLOR_BGR2BGRA)
        bg[:, :, 3] = 255  # 完全不透明
    
    x, y = position
    fg_height, fg_width = foreground.shape[:2]
    bg_height, bg_width = bg.shape[:2]
    
    # 确保位置在图像范围内
    x = max(0, min(x, bg_width - fg_width))
    y = max(0, min(y, bg_height - fg_height))
    
    # 提取前景的alpha通道并归一化
    alpha_foreground = foreground[:, :, 3] / 255.0
    
    # 对于每个颜色通道进行合成
    for c in range(3):
        bg_region = bg[y:y+fg_height, x:x+fg_width, c]
        fg_region = foreground[:, :, c]
        
        # alpha混合公式
        bg[y:y+fg_height, x:x+fg_width, c] = (
            alpha_foreground * fg_region + 
            (1 - alpha_foreground) * bg_region
        )
    
    # 更新背景的alpha通道（如果需要）
    bg_alpha_region = bg[y:y+fg_height, x:x+fg_width, 3]
    bg[y:y+fg_height, x:x+fg_width, 3] = np.maximum(bg_alpha_region, foreground[:, :, 3])
    
    return bg

def precise_blend_with_perspective(background, foreground, corners):
    """
    精确合成：根据四个角点将前景图像透视合成到背景上
    """
    # 创建与背景相同大小的空白图像
    bg_height, bg_width = background.shape[:2]
    
    # 如果背景没有alpha通道，转换为BGRA
    if background.shape[2] == 3:
        background_bgra = cv2.cvtColor(background, cv2.COLOR_BGR2BGRA)
    else:
        background_bgra = background.copy()
    
    # 创建与背景相同大小的前景图层
    foreground_layer = np.zeros((bg_height, bg_width, 4), dtype=np.uint8)
    
    # 计算前景图像在背景中的边界框
    min_x = int(min(corners[:, 0]))
    max_x = int(max(corners[:, 0]))
    min_y = int(min(corners[:, 1]))
    max_y = int(max(corners[:, 1]))
    
    # 将变换后的前景图像放置到对应位置
    fg_height, fg_width = foreground.shape[:2]
    if min_y + fg_height <= bg_height and min_x + fg_width <= bg_width:
        foreground_layer[min_y:min_y+fg_height, min_x:min_x+fg_width] = foreground
    
    # 创建掩码（只在前景有内容的地方合成）
    mask = (foreground_layer[:, :, 3] > 0)
    
    # 合成图像
    result = background_bgra.copy()
    for c in range(3):
        result[:, :, c][mask] = foreground_layer[:, :, c][mask]
    result[:, :, 3][mask] = foreground_layer[:, :, 3][mask]
    
    return result

async def generate_dice_image(number: int) -> BytesIO:
    # 将文本转换为带透明背景的图像
    text = str(number)
    text_image = text_to_transparent_image(
        text, 
        font_size=60, 
        text_color=(0, 0, 0)  # 黑色文字
    )
    
    # 定义3D变换的四个角点（透视效果）
    # 顺序: [左上, 右上, 右下, 左下]
    corners = np.array([
        [16, 30],    # 左上
        [51, 5],     # 右上（上移，创建透视）
        [88, 33],    # 右下
        [49, 62]     # 左下（下移）
    ], dtype=np.float32)
    
    # 加载背景图像，保留透明通道
    background = cv2.imread(str(ASSETS_PATH / "img" / "dice" / "template.png"), cv2.IMREAD_UNCHANGED)


    # 对文本图像进行3D变换（保持透明通道）
    transformed_text, transform_matrix = perspective_transform(text_image, background, corners)
    
    min_x = int(min(corners[:, 0]))
    min_y = int(min(corners[:, 1]))
    final_image_simple = blend_with_transparency(background, transformed_text, (min_x, min_y))

    pil_final = Image.fromarray(final_image_simple)
    # 导入一系列图像
    images: list[Image.Image] = [Image.open(ASSETS_PATH / "img" / "dice" / f"{i}.png") for i in range(1, 12)]
    images.append(pil_final)
    frame_durations = [100] * (len(images) - 1) + [100000]
    # 保存为BytesIO对象
    output = BytesIO()
    images[0].save(output,
               save_all=True,
               append_images=images[1:],
               duration=frame_durations,
               format='GIF',
               loop=1)
    return output