# -*- coding: utf-8 -*-
"""换发型（手绘mask重绘版）

与 hair_swap_debug.py 工作流完全一致，唯一区别在步骤③：
  - debug版：重绘区域 = 原头发mask ∪ 新发型mask（自动计算）
  - 本版：  重绘区域 = 用户手绘mask（白色=重绘，黑色=保留原图）

用户在页面上画哪里，SD 就重绘哪里，完全由用户控制重绘范围。
工作流：输入 → 粗推理 → 手绘mask → warpAffine → SD推理 → 贴回 → 消除接缝
"""
import os
import json
import glob
import time
import shutil
import base64

import cv2
import numpy as np

from gen_super_image import webui_img2img
from common.logger import config
from utils.landmark_processor import high_quality_warpAffine
from utils.landmark_processor import pts_1k_to_137


def hair_swap_manual(origin_img, hand_mask, hair_id, hairstyle_process, landmark_processor,
                     task_id,
                     # ===== 流程开关（真正生效）=====
                     strict_mask=False,       # 步骤⑥ 严格按mask贴回
                     seamless_blend=True,     # 步骤⑦ 泊松融合消除接缝
                     # ===== 尺寸/对齐（真正生效）=====
                     is_hr=True,              # 高清(1152x1536) vs 标清(576x768)
                     dilate_kernel=(6, 18),   # 步骤④ mask膨胀核 (x,y)
                     # ===== SD 推理（仅 denoising 可调，其余webui端固定）=====
                     denoising_strength=0.6,  # 重绘强度（唯一能透传到webui的SD参数）
                     # ===== 贴回/融合（真正生效）=====
                     blend_dilate=(5, 5),     # 步骤⑥ strict mask贴回时mask膨胀核
                     feather_px=0,            # ★ strict贴回边缘羽化像素（0=无羽化硬边缘，>0=高斯模糊边缘）
                     seamless_dilate=(9, 9),  # 步骤⑦ 泊松融合mask膨胀核
                     # ===== enhance 二次增强重绘 =====
                     enhance=False,           # 步骤⑧ 是否对结果再做一次低强度SD重绘（让发丝更清晰）
                     enhance_denoising=0.35,  # enhance 重绘强度（默认0.35，越低越保留原图）
                     ):
    """手绘mask版换发型。

    参数:
        hand_mask: 用户手绘mask，灰度ndarray，白色(255)=重绘区，与 origin_img 同尺寸
        其余参数同 hair_swap_debug
    返回:
        result_img: 最终结果图 BGR
        steps: [{title, desc, images:[{label, b64}]}]
        params_used: 实际使用的参数（回显）
    """
    start_all = time.time()
    steps = []

    hairstyle_dir = config.get('default', 'hairstyleDir')
    user_dir = config.get('default', 'userDir')
    train_dir = config.get('default', 'train_dir')
    userInfo_dir = config.get('default', 'userInfo_dir')

    hair_material_dir = os.path.join(train_dir, hair_id)
    material_save_path = os.path.join(hairstyle_dir, hair_id)
    ref_img_path = os.path.join(material_save_path, "ref_rgb_8uc3_768.png")
    if not os.path.exists(ref_img_path):
        raise FileNotFoundError(f"发型材质不存在: {ref_img_path}")

    user_img_name = f"swapdbg_{task_id}.jpg"
    new_user_img_path = os.path.join(user_dir, user_img_name)
    if os.path.exists(new_user_img_path):
        os.remove(new_user_img_path)
    cv2.imwrite(new_user_img_path, origin_img)
    origin_img = cv2.imread(new_user_img_path)

    ref_img = cv2.imread(ref_img_path)

    # === 步骤1: 输入 ===
    steps.append({
        "title": "① 输入",
        "desc": "用户人像 + 目标发型参考图。参考图来自训练材质 ref_rgb_8uc3_768.png",
        "images": [
            {"label": "用户原图", "b64": _enc(origin_img)},
            {"label": f"发型参考图({hair_id})", "b64": _enc(cv2.resize(ref_img, (origin_img.shape[1], origin_img.shape[0])))},
        ]
    })

    # === 步骤2: 粗推理 infer_hairstyle_diy_jy ===
    start = time.time()
    work_dir = os.path.join(userInfo_dir, task_id)
    os.makedirs(work_dir, exist_ok=True)
    import torch
    with torch.no_grad():
        img_res, status, _, landmarks_1k, isEyeOccluded = hairstyle_process.infer_hairstyle_diy_jy(
            origin_img, ref_img, os.path.join(work_dir, task_id), f"{task_id}.png")
    if status != 0:
        raise RuntimeError("发型粗推理失败")
    t_coarse = time.time() - start

    steps.append({
        "title": "② 粗推理 (infer_hairstyle_diy_jy)",
        "desc": f"用 SPADE 风格迁移模型把目标发型粗略合成到用户脸上。这步只产生粗略效果，细节由后续 SD 推理完善。耗时 {t_coarse:.1f}s",
        "images": [
            {"label": "粗推理结果", "b64": _enc(img_res)},
        ]
    })

    # === 步骤3: 手绘mask作为重绘区（核心区别：完全由用户控制）===
    start = time.time()
    # 手绘mask归一化为 0/255 灰度，保证尺寸与原图一致
    if hand_mask.shape[:2] != origin_img.shape[:2]:
        hand_mask = cv2.resize(hand_mask, (origin_img.shape[1], origin_img.shape[0]),
                               interpolation=cv2.INTER_NEAREST)
    if hand_mask.ndim == 3:
        hand_mask = cv2.cvtColor(hand_mask, cv2.COLOR_BGR2GRAY)
    # 二值化（前端传过来已是黑白，这里再保底阈值化）
    _, hand_mask_bin = cv2.threshold(hand_mask, 30, 255, cv2.THRESH_BINARY)
    matting_merge = hand_mask_bin

    # 统计手绘区域占比，便于调试
    mask_area_ratio = float((hand_mask_bin > 0).sum()) / hand_mask_bin.size * 100

    # 同时展示自动计算的mask作对比（仅展示，不参与重绘）
    user_material_dir = os.path.join(work_dir, task_id)
    hair_matting_path = os.path.join(user_material_dir, "hair_mask_2.png")
    user_orig_mask_path = os.path.join(user_material_dir, "user_orig_mask.png")
    origin_matting = cv2.imread(user_orig_mask_path, cv2.IMREAD_GRAYSCALE)
    new_matting = cv2.imread(hair_matting_path, cv2.IMREAD_GRAYSCALE)
    auto_merge = None
    if origin_matting is not None and new_matting is not None:
        auto_merge = np.max(np.stack([origin_matting, new_matting], axis=2), axis=2).astype(np.uint8)

    step3_images = [
        {"label": "用户手绘mask(重绘区)", "b64": _enc_mask(hand_mask_bin)},
    ]
    if origin_matting is not None:
        step3_images.append({"label": "自动:原头发mask(仅对比)", "b64": _enc_mask(origin_matting)})
    if new_matting is not None:
        step3_images.append({"label": "自动:新发型mask(仅对比)", "b64": _enc_mask(new_matting)})
    if auto_merge is not None:
        step3_images.append({"label": "自动合并(普通换发型会用)", "b64": _enc_mask(auto_merge)})

    steps.append({
        "title": "③ 手绘mask（核心：用户控制重绘区）",
        "desc": f"重绘区域完全由用户手绘决定，白色区域={mask_area_ratio:.1f}%。SD 只在这些区域重绘，其余保留原图。下方对比图展示自动计算的mask（仅供参考，不参与本次重绘）。",
        "images": step3_images
    })

    # === 步骤4: warpAffine 变换 ===
    dst_size = (1152, 1536) if is_hr else (576, 768)
    box_info = hairstyle_process.get_body_info(img_res)
    box_w = box_info[2] - box_info[0]
    box_h = box_info[3] - box_info[1]
    scale = min(dst_size[1] / max(box_h, 1), dst_size[0] / max(box_w, 1))
    rotate_center = [(box_info[2] + box_info[0]) * 0.5, (box_info[3] + box_info[1]) * 0.5]
    M = cv2.getRotationMatrix2D(rotate_center, 0, scale)
    M[:, 2] += np.float32([dst_size[0] * 0.5, dst_size[1] * 0.5]) - np.float32(rotate_center)

    crop_result = high_quality_warpAffine(img_res, M, dst_size)
    crop_matting = cv2.warpAffine(matting_merge, M, dst_size)
    mask = (crop_matting > 10).astype(np.float32)
    dk = tuple(max(1, int(x)) for x in dilate_kernel)
    mask_dilate = cv2.dilate(mask, np.ones(dk, np.uint8))
    mask_dilate = np.clip(mask_dilate * 255, 0, 255).astype(np.uint8)
    final_img = crop_result

    steps.append({
        "title": "④ warpAffine 对齐裁剪",
        "desc": f"检测身体框，计算缩放/平移矩阵，把图和mask对齐裁剪到 {dst_size[0]}x{dst_size[1]} 送入 webui。可调：is_hr={is_hr}(决定尺寸), dilate_kernel={dk}",
        "images": [
            {"label": f"裁剪后图({dst_size[0]}x{dst_size[1]})", "b64": _enc(_shrink(crop_result))},
            {"label": f"mask膨胀后(dilate={dk})", "b64": _enc_mask(_shrink(mask_dilate, nearest=True))},
        ]
    })

    # === 步骤5: 读取 config/prompt ===
    config_json_path = os.path.join(material_save_path, "config.json")
    with open(config_json_path, "r") as f:
        in_gender = json.load(f)["gender"]
    images_dir = os.path.join(hair_material_dir, "images")
    txt_dir = os.path.join(images_dir, os.listdir(images_dir)[0])
    txt_path = glob.glob(txt_dir + '/*.txt')[0]
    with open(txt_path, 'r') as f:
        p_tag = f.readline()
        if "titor hairstyle, faceless, no human, gray background, simple background" in p_tag:
            p_tag = p_tag[p_tag.find("simple background, ") + len("simple background, "):]
        else:
            p_tag = ""

    # === 步骤6: webui 推理（走 photo_service + LoRA）===
    start = time.time()
    sd_result = webui_img2img(
        img=final_img, mask_img=mask_dilate,
        in_gender=in_gender, task_id=task_id,
        hair_id=hair_id, lora_material_path=hair_material_dir,
        tag=p_tag, is_hr=is_hr,
        denoising_strength=denoising_strength, inference_port="57860")
    t_sd = time.time() - start

    steps.append({
        "title": "⑤ SD 推理 (webui img2img inpainting + LoRA)",
        "desc": f"加载发型LoRA，在mask区域用SD重绘新发型。这是生成发丝细节的关键步骤。耗时 {t_sd:.1f}s。可调：denoising={denoising_strength}（其余 cfg=7/steps=20/sampler=DPM++ 2M Karras/mask_blur=11/seed=123456789 在webui端固定）",
        "images": [
            {"label": "webui输出(SD重绘结果)", "b64": _enc(_shrink(sd_result))},
        ]
    })

    # === 步骤7: warpAffine 贴回原图 ===
    M_inv = cv2.invertAffineTransform(M)
    result_full = origin_img.copy()
    cv2.warpAffine(sd_result, M_inv, (origin_img.shape[1], origin_img.shape[0]),
                   dst=result_full, borderMode=cv2.BORDER_TRANSPARENT, flags=cv2.INTER_LANCZOS4)

    result_strict = origin_img.copy()
    sd_result_back = np.zeros_like(origin_img)
    cv2.warpAffine(sd_result, M_inv, (origin_img.shape[1], origin_img.shape[0]),
                   dst=sd_result_back, borderMode=cv2.BORDER_CONSTANT, borderValue=(0, 0, 0), flags=cv2.INTER_LANCZOS4)
    mask_back = np.zeros(origin_img.shape[:2], dtype=np.uint8)
    cv2.warpAffine(mask_dilate, M_inv, (origin_img.shape[1], origin_img.shape[0]),
                   dst=mask_back, borderMode=cv2.BORDER_CONSTANT, borderValue=0, flags=cv2.INTER_NEAREST)
    bd = tuple(max(1, int(x)) for x in blend_dilate)
    mask_back = cv2.dilate(mask_back, np.ones(bd, np.uint8))
    # ★ 边缘羽化：对mask_back做高斯模糊，让融合边缘平滑过渡（feather_px=模糊核半径）
    feather_info = ""
    # 先算一份硬边缘版本（feather=0），用于对比展示
    hard_blend = (mask_back.astype(np.float32) / 255)[..., None]
    result_strict_hard = (sd_result_back.astype(np.float32) * hard_blend +
                          origin_img.astype(np.float32) * (1 - hard_blend))
    result_strict_hard = np.clip(result_strict_hard, 0, 255).astype(np.uint8)
    result_strict_hard[mask_back == 0] = origin_img[mask_back == 0]

    if feather_px and feather_px > 0:
        k = max(1, int(feather_px)) * 2 + 1  # 高斯核必须是奇数
        mask_back_blur = cv2.GaussianBlur(mask_back, (k, k), 0)
        mask_blend = (mask_back_blur.astype(np.float32) / 255)[..., None]
        feather_info = f"，边缘羽化{feather_px}px"
    else:
        mask_blend = hard_blend
    result_strict = (sd_result_back.astype(np.float32) * mask_blend +
                     origin_img.astype(np.float32) * (1 - mask_blend))
    result_strict = np.clip(result_strict, 0, 255).astype(np.uint8)
    result_strict[mask_back == 0] = origin_img[mask_back == 0]

    # ★ 羽化对比图：左=硬边缘(feather=0) 右=当前羽化，裁剪mask边界附近放大
    feather_compare = None
    if feather_px and feather_px > 0:
        ys, xs = np.where(mask_back > 10)
        if len(ys) > 0:
            x1 = max(0, xs.min()-20); x2 = min(origin_img.shape[1], xs.max()+20)
            y1 = max(0, ys.min()-20); y2 = min(origin_img.shape[0], ys.max()+20)
            hard_crop = result_strict_hard[y1:y2, x1:x2]
            blur_crop = result_strict[y1:y2, x1:x2]
            sep = np.full((hard_crop.shape[0], 3, 3), 128, dtype=np.uint8)
            feather_compare = np.hstack([hard_crop, sep, blur_crop])

    result = result_strict if strict_mask else result_full

    step6_images = [
        {"label": "用户原图", "b64": _enc(origin_img)},
        {"label": "整框覆盖", "b64": _enc(result_full)},
        {"label": "严格mask贴回", "b64": _enc(result_strict)},
        {"label": f"当前选用({'严格mask' if strict_mask else '整框覆盖'})", "b64": _enc(result)},
    ]
    if feather_compare is not None:
        step6_images.append({"label": f"★ 羽化对比(左=硬边 右=羽化{feather_px}px)", "b64": _enc(feather_compare)})
    steps.append({
        "title": "⑥ 贴回原图",
        "desc": f"把SD结果逆warpAffine贴回用户原图。可调：strict_mask={strict_mask}, blend_dilate={bd}{feather_info}。整框覆盖=整个裁剪框覆盖原图；严格mask=只在mask区域融合，mask外保留原图",
        "images": step6_images
    })

    # === 步骤8: 消除接缝（泊松无缝融合）===
    if strict_mask and seamless_blend:
        start_enhance = time.time()
        try:
            sd_back = np.zeros_like(origin_img)
            cv2.warpAffine(sd_result, M_inv, (origin_img.shape[1], origin_img.shape[0]),
                           dst=sd_back, borderMode=cv2.BORDER_CONSTANT, borderValue=(0, 0, 0), flags=cv2.INTER_LANCZOS4)
            mask_back2 = np.zeros(origin_img.shape[:2], dtype=np.uint8)
            cv2.warpAffine(mask_dilate, M_inv, (origin_img.shape[1], origin_img.shape[0]),
                           dst=mask_back2, borderMode=cv2.BORDER_CONSTANT, borderValue=0, flags=cv2.INTER_NEAREST)
            sd2 = tuple(max(1, int(x)) for x in seamless_dilate)
            mask_back2 = cv2.dilate(mask_back2, np.ones(sd2, np.uint8))
            ys2, xs2 = np.where(mask_back2 > 10)
            if len(ys2) > 10:
                cx2 = int((xs2.min() + xs2.max()) / 2)
                cy2 = int((ys2.min() + ys2.max()) / 2)
                result = cv2.seamlessClone(sd_back, origin_img, mask_back2, (cx2, cy2), cv2.NORMAL_CLONE)
                t_seamless = time.time() - start_enhance
                steps.append({
                    "title": "⑦ 泊松融合消除接缝 (seamlessClone)",
                    "desc": f"严格mask模式下边缘有接缝/色差。泊松融合保持SD结果内部梯度，把边缘梯度过渡到原图，消除突变。耗时 {t_seamless:.1f}s。可调：seamless_dilate={sd2}",
                    "images": [
                        {"label": "融合前(有接缝)", "b64": _enc(result_strict)},
                        {"label": "融合后(最终)", "b64": _enc(result)},
                    ]
                })
        except Exception as e:
            steps.append({
                "title": "⑦ 泊松融合（失败）",
                "desc": f"泊松融合失败({e})，回退到严格mask结果",
                "images": [{"label": "最终结果", "b64": _enc(result)}]
            })

    # === 步骤⑧: enhance 二次增强重绘（可选，让发丝更清晰）===
    # ★ enhance 固定基于「严格mask贴回」的图（result_strict），不受 strict_mask 开关影响
    if enhance:
        start_enh = time.time()
        try:
            from utils import enhance_hair
            # enhance 的输入图固定用严格mask贴回的结果（mask外保留原图）
            enh_input = result_strict
            # ★ enhance 重绘区域 = 原图头发区域 ∪ 手绘mask（并集）
            # origin_matting 是用户原头发mask，hand_mask_bin 是用户手绘mask
            if origin_matting is not None:
                enh_mask = np.max(np.stack([origin_matting, hand_mask_bin], axis=2), axis=2).astype(np.uint8)
            else:
                enh_mask = hand_mask_bin
            # ★ mask 再往外扩大 10%（相对mask外接矩形短边，避免边缘漏掉）
            ys, xs = np.where(enh_mask > 10)
            if len(ys) > 0:
                short_side = min(xs.max() - xs.min(), ys.max() - ys.min())
                dilate_px = max(1, int(short_side * 0.10))  # 短边的10%
                enh_mask = cv2.dilate(enh_mask, np.ones((dilate_px, dilate_px), np.uint8))

            # ★ 用瞳距换算 3cm = 多少像素（瞳距≈6.3cm）
            # 1k关键点 [691]=左眼中心, [792]=右眼中心
            cm3_px = 0  # 3cm对应的像素数
            try:
                lm = np.asarray(landmarks_1k)
                left_eye = lm[691]; right_eye = lm[792]
                pupil_dist_px = np.linalg.norm(np.array(left_eye) - np.array(right_eye))
                cm3_px = max(1, int(pupil_dist_px / 6.3 * 3))  # 瞳距/6.3cm × 3cm
            except Exception as e:
                print(f"[enhance] 瞳距换算失败({e})，3cm按40px")

            # ★ 减掉发际线带：从头发下边界向上 3cm 的带状区域
            # 头发下边界 = enh_mask 每列最下面的头发像素；向上3cm内的区域擦除
            enh_mask_before = enh_mask.copy()  # 保存减发际线前的mask（可视化用）
            if cm3_px > 0:
                # 找每列头发mask的最下像素行
                cols = np.where(enh_mask.max(axis=0) > 10)[0]
                for c in cols:
                    col_ys = np.where(enh_mask[:, c] > 10)[0]
                    if len(col_ys) == 0:
                        continue
                    bottom_y = col_ys.max()  # 该列头发最下像素
                    # 擦除 [bottom_y - cm3_px, bottom_y] 这一段（发际线带）
                    top_erase = max(0, bottom_y - cm3_px)
                    enh_mask[top_erase:bottom_y+1, c] = 0
            prompt = "high quality, detailed hair strands, realistic hair texture, sharp focus"
            enhanced = enhance_hair.webui_img2img(enh_input, enh_mask, prompt=prompt,
                                                   denoising_strength=enhance_denoising)
            t_enh = time.time() - start_enh
            # enhance 重绘区域可视化
            try:
                from hairline_mask import make_overlay
                enh_overlay = make_overlay(enh_input, enh_mask, alpha=0.45)
                enh_overlay_before = make_overlay(enh_input, enh_mask_before, alpha=0.45)
            except Exception:
                enh_overlay = enh_input; enh_overlay_before = enh_input
            steps.append({
                "title": "⑧ enhance 二次增强重绘",
                "desc": f"基于「严格mask贴回」图做低强度SD重绘(denoising={enhance_denoising})。重绘区=原图头发∪手绘mask外扩10%({dilate_px}px)，再从发际线向上减掉3cm({cm3_px}px)。耗时 {t_enh:.1f}s",
                "images": [
                    {"label": "严格mask贴回(enhance输入)", "b64": _enc(enh_input)},
                    {"label": "① 重绘区(外扩后,未减发际线)", "b64": _enc_mask(enh_mask_before)},
                    {"label": "② 减发际线带后(最终mask)", "b64": _enc_mask(enh_mask)},
                    {"label": "③ 减之前叠加图", "b64": _enc(enh_overlay_before)},
                    {"label": "④ 最终mask叠加图", "b64": _enc(enh_overlay)},
                    {"label": "⑤ 增强后(最终)", "b64": _enc(enhanced)},
                ]
            })
            result = enhanced
        except Exception as e:
            steps.append({
                "title": "⑧ enhance（失败）",
                "desc": f"enhance增强失败({e})，使用未增强结果",
                "images": [{"label": "最终结果", "b64": _enc(result)}]
            })

    # 清理临时文件
    try:
        shutil.rmtree(user_material_dir)
        os.remove(new_user_img_path)
    except Exception:
        pass

    params_used = {
        "strict_mask": strict_mask, "seamless_blend": seamless_blend,
        "is_hr": is_hr, "dilate_kernel": list(dilate_kernel),
        "denoising_strength": denoising_strength,
        "blend_dilate": list(blend_dilate), "feather_px": feather_px,
        "seamless_dilate": list(seamless_dilate),
        "enhance": enhance, "enhance_denoising": enhance_denoising,
        "mask_area_ratio_pct": round(mask_area_ratio, 1),
        "gender": in_gender, "tag": p_tag, "dst_size": list(dst_size),
        "total_time": round(time.time() - start_all, 1),
    }
    print(f"[swap_manual] 总耗时: {params_used['total_time']}s")
    return result, steps, params_used


def _shrink(img, max_side=1024, nearest=False):
    """缩小图片便于前端展示"""
    h, w = img.shape[:2]
    if max(h, w) <= max_side:
        return img
    sc = max_side / max(h, w)
    interp = cv2.INTER_NEAREST if nearest else cv2.INTER_AREA
    return cv2.resize(img, (int(w * sc), int(h * sc)), interpolation=interp)


def _enc(img):
    _, buf = cv2.imencode(".jpg", img, [cv2.IMWRITE_JPEG_QUALITY, 80])
    return base64.b64encode(buf).decode()


def _enc_mask(mask):
    if mask.ndim == 2:
        colored = cv2.applyColorMap(mask, cv2.COLORMAP_JET)
    else:
        colored = mask
    _, buf = cv2.imencode(".jpg", colored, [cv2.IMWRITE_JPEG_QUALITY, 80])
    return base64.b64encode(buf).decode()