diff --git a/apps/api/app/api/routes/ai_avatar_render.py b/apps/api/app/api/routes/ai_avatar_render.py index d9e96d1b7..b05818856 100644 --- a/apps/api/app/api/routes/ai_avatar_render.py +++ b/apps/api/app/api/routes/ai_avatar_render.py @@ -210,11 +210,17 @@ def generate_avatar_smart_cover( if not video_url.startswith(("http://", "https://")): raise HTTPException(status_code=400, detail="video_url 必须是合法的 HTTP/HTTPS URL") + # 兼容：顶层 title_image_dataurl 透传进 title_config（前端可以放在任一位置） + title_config = getattr(body, "title_config", None) + top_dataurl = getattr(body, "title_image_dataurl", None) + if top_dataurl and isinstance(title_config, dict) and not title_config.get("title_image_dataurl"): + title_config = {**title_config, "title_image_dataurl": top_dataurl} + try: cover_url = generate_smart_cover( video_url, max_frames=body.max_frames, - title_config=getattr(body, "title_config", None), + title_config=title_config, ) except Exception as exc: logger.error( diff --git a/apps/api/app/schemas/ai_avatar_render.py b/apps/api/app/schemas/ai_avatar_render.py index 84761c2f4..a574b4012 100644 --- a/apps/api/app/schemas/ai_avatar_render.py +++ b/apps/api/app/schemas/ai_avatar_render.py @@ -110,12 +110,21 @@ class AiAvatarRenderProgressResponse(BaseModel): class SmartCoverRequest(BaseModel): - """智能封面请求 — MediaKit 抽帧 + 质量评分选最佳帧 + 可选标题 drawtext 叠加.""" + """智能封面请求 — MediaKit 抽帧 + 质量评分选最佳帧 + 可选标题叠加.""" video_url: str = Field(..., description="数字人视频 URL（对口型/渲染成片）") max_frames: int = Field(5, ge=1, le=10, description="抽帧数量（默认 5）") title_config: Optional[dict[str, Any]] = Field( - None, description="标题配置；传入时在封面上用 drawtext 叠加标题（竖屏 720x1280）" + None, + description="标题配置；传入时在封面上叠加标题。" + "若 title_config 含 title_image_dataurl（前端 Canvas 渲染的 PNG dataURL），" + "后端用 overlay 叠加图片图层实现所见即所得；否则降级用 drawtext 重画文字。", + ) + title_image_dataurl: Optional[str] = Field( + None, + description="前端 Canvas 渲染的标题 PNG dataURL（data:image/png;base64,...）；" + "传入时后端用 overlay 叠加图片图层，不再用 drawtext 重画文字。" + "推荐方式：直接放在 title_config.title_image_dataurl 里透传，本字段为兼容保留。", ) diff --git a/apps/api/app/services/ai_avatar_cover_service.py b/apps/api/app/services/ai_avatar_cover_service.py index fe561633b..50f8b994d 100644 --- a/apps/api/app/services/ai_avatar_cover_service.py +++ b/apps/api/app/services/ai_avatar_cover_service.py @@ -10,6 +10,8 @@ from __future__ import annotations +import base64 +import binascii import logging import os import subprocess @@ -159,19 +161,35 @@ def select_best_cover_frame(video_url: str, *, max_frames: int = 5) -> str: def apply_title_to_cover(local_frame: str, *, title_config: dict | None) -> str: - """用 ffmpeg drawtext 在封面图上叠加标题，返回叠加后图片的本地路径. + """在封面图上叠加标题，返回叠加后图片的本地路径. - ffmpeg 失败时回退返回原始 local_frame。竖屏封面按 720x1280 计算位置。 + 优先使用前端 Canvas 渲染的 PNG 图层（overlay=0:0，所见即所得）； + 无 title_image_dataurl 时降级到 drawtext 重画文字。 + ffmpeg 失败时回退返回原始 local_frame。竖屏封面按 720x1280 计算位置（drawtext 降级路径）。 """ if not title_config or not isinstance(title_config, dict): return local_frame - text = (title_config.get("text") or title_config.get("content") or "").strip() + text = ( + title_config.get("text") + or title_config.get("content") + or title_config.get("title") + or "" + ).strip() if not text: return local_frame enabled = title_config.get("enabled", True) if not enabled: return local_frame + # 优先：前端 Canvas 渲染的 PNG 图层 + title_dataurl = title_config.get("title_image_dataurl") + if isinstance(title_dataurl, str) and title_dataurl.startswith("data:image/"): + out_path = _overlay_title_png_on_image(local_frame, title_dataurl) + if out_path: + return out_path + logger.warning("[数字人封面] PNG 叠加失败，回退 drawtext") + + # 降级：drawtext 重画文字 try: from packages.domain.video_filter_builder import build_title_drawtext_filter @@ -194,7 +212,7 @@ def apply_title_to_cover(local_frame: str, *, title_config: dict | None) -> str: "-y", titled_path, ] - logger.info("[数字人封面] 叠加标题: text=%s", text[:30]) + logger.info("[数字人封面] drawtext 叠加标题: text=%s", text[:30]) result = subprocess.run( cmd, capture_output=True, @@ -217,6 +235,64 @@ def apply_title_to_cover(local_frame: str, *, title_config: dict | None) -> str: return local_frame +def _overlay_title_png_on_image(local_frame: str, dataurl: str) -> str | None: + """解码 title PNG dataURL 并用 ffmpeg overlay 叠加到封面图上。 + + 成功返回新文件路径；失败返回 None。 + """ + try: + header, b64 = dataurl.split(",", 1) + if "base64" not in header: + return None + png_bytes = base64.b64decode(b64, validate=True) + if not png_bytes: + return None + + base_dir = os.path.dirname(local_frame) + title_png = os.path.join(base_dir, f"title_{uuid.uuid4().hex[:8]}.png") + with open(title_png, "wb") as f: + f.write(png_bytes) + + base, ext = os.path.splitext(local_frame) + titled_path = f"{base}_titled{ext or '.jpg'}" + cmd = [ + "ffmpeg", + "-i", + local_frame, + "-i", + title_png, + "-filter_complex", + "[0:v][1:v]overlay=0:0", + "-y", + titled_path, + ] + logger.info("[数字人封面] PNG overlay 叠加标题") + result = subprocess.run( + cmd, + capture_output=True, + text=True, + timeout=30, + ) + # 清理临时 PNG + try: + os.unlink(title_png) + except OSError: + pass + if result.returncode != 0: + logger.warning( + "[数字人封面] PNG overlay 失败: exit=%s stderr=%s", + result.returncode, + (result.stderr or "")[-300:], + ) + return None + if not os.path.exists(titled_path) or os.path.getsize(titled_path) == 0: + return None + return titled_path + except (binascii.Error, ValueError, OSError) as exc: + logger.warning("[数字人封面] PNG 解码/overlay 异常: %s", exc, exc_info=True) + return None + + def persist_cover_to_oss( frame_url: str, *, diff --git a/apps/api/app/services/ai_avatar_render_service.py b/apps/api/app/services/ai_avatar_render_service.py index a86d3bb8e..41a052fc2 100644 --- a/apps/api/app/services/ai_avatar_render_service.py +++ b/apps/api/app/services/ai_avatar_render_service.py @@ -9,6 +9,8 @@ from __future__ import annotations +import base64 +import binascii import logging import os import subprocess @@ -27,6 +29,7 @@ from packages.adapters.sqlalchemy_impl.models import ( from packages.domain.video_filter_builder import ( build_broll_overlay_filter, build_title_drawtext_filter, + build_title_overlay_filter, ) from packages.shared.storage import get_shared_storage_service @@ -248,29 +251,12 @@ class AiAvatarRenderService: output_height=output_height, ) - # 标题叠加（传入实际输出尺寸，保证位置计算正确） - title_filter = build_title_drawtext_filter( - job.title_config, - output_width=output_width, - output_height=output_height, - ) - - filter_complex = "" - final_label = None - if broll_filter and title_filter: - # B-roll → 标题叠在 B-roll 输出上 - filter_complex = broll_filter + f";[{broll_label}]{title_filter}[vout_titled]" - final_label = "vout_titled" - elif broll_filter: - filter_complex = broll_filter - final_label = broll_label - elif title_filter: - filter_complex = f"[0:v]{title_filter}[vout_titled]" - final_label = "vout_titled" - else: - # 无滤镜：直接拷贝视频流 - filter_complex = "" - final_label = None + # 标题叠加路径：优先前端 Canvas 渲染的 PNG 图层（所见即所得）， + # 无 title_image_dataurl 时降级到 drawtext 重画文字。 + title_cfg = job.title_config if isinstance(job.title_config, dict) else {} + title_dataurl = (title_cfg or {}).get("title_image_dataurl") if title_cfg else None + use_title_png = isinstance(title_dataurl, str) and title_dataurl.startswith("data:image/") + title_input_index = 1 + len(job.b_roll_segments or []) if use_title_png else None job.progress = 40 self.db.commit() @@ -279,9 +265,81 @@ class AiAvatarRenderService: with tempfile.TemporaryDirectory() as tmpdir: output_video_path = os.path.join(tmpdir, "output.mp4") + # 在临时目录里解码保存标题 PNG（with 退出自动清理） + title_png_path: Optional[str] = None + extra_inputs: list[str] = [] + title_filter = None + if use_title_png: + try: + title_png_path = os.path.join(tmpdir, f"title_{job.id}.png") + self._save_title_dataurl_to_file(title_dataurl, dst_path=title_png_path) + extra_inputs.append(title_png_path) + logger.info( + "[数字人渲染] 标题 PNG 已保存: %s (input index %d)", title_png_path, title_input_index + ) + except Exception as exc: + logger.warning("[数字人渲染] 标题 PNG 解码/保存失败，降级 drawtext: %s", exc) + title_png_path = None + extra_inputs = [] + + # 构建标题滤镜 + final_label = None + if title_png_path and title_input_index is not None: + title_input_label = f"[{title_input_index}:v]" + base_label = f"[{broll_label}]" if broll_label else "[0:v]" + title_filter = build_title_overlay_filter( + title_cfg, + output_width=output_width, + output_height=output_height, + title_png_path=title_png_path, + title_input_label=title_input_label, + base_label=base_label, + output_label="vout_titled", + ) + if not title_filter: + # build 返回 None → 文件不存在（极端并发情况），降级 drawtext + title_png_path = None + extra_inputs = [] + + if title_png_path: + # overlay 路径 + if broll_filter and title_filter: + filter_complex = broll_filter + f";{title_filter}" + elif broll_filter: + filter_complex = broll_filter + final_label = broll_label + elif title_filter: + filter_complex = title_filter + else: + filter_complex = "" + if title_filter: + final_label = "vout_titled" + elif not final_label: + final_label = None + else: + # 降级：drawtext 重画文字 + title_filter = build_title_drawtext_filter( + title_cfg, + output_width=output_width, + output_height=output_height, + ) + if broll_filter and title_filter: + filter_complex = broll_filter + f";[{broll_label}]{title_filter}[vout_titled]" + final_label = "vout_titled" + elif broll_filter: + filter_complex = broll_filter + final_label = broll_label + elif title_filter: + filter_complex = f"[0:v]{title_filter}[vout_titled]" + final_label = "vout_titled" + else: + filter_complex = "" + final_label = None + cmd_list = self._build_ffmpeg_command( input_video=input_video_path, b_roll_segments=job.b_roll_segments, + extra_inputs=extra_inputs, filter_complex=filter_complex, final_label=final_label, output_path=output_video_path, @@ -408,6 +466,44 @@ class AiAvatarRenderService: os.unlink(tmp.name) raise + @staticmethod + def _save_title_dataurl_to_file(dataurl: str, *, dst_path: str | None = None, job_id: str = "") -> str: + """解码前端传来的 data:image/png;base64,... 并保存为本地 PNG 文件。 + + Args: + dataurl: 完整 dataURL 字符串 + dst_path: 指定输出路径；为 None 时创建临时文件并返回路径 + job_id: 仅在 dst_path 为空时用于临时文件命名 + + Returns: + 保存后的本地文件路径 + """ + if not isinstance(dataurl, str) or not dataurl.startswith("data:image/"): + raise ValueError("title_image_dataurl 不是合法的 data:image URL") + # 拆分 data:image/png;base64, + try: + header, b64 = dataurl.split(",", 1) + except ValueError as exc: + raise ValueError("title_image_dataurl 缺少 base64 payload") from exc + if "base64" not in header: + raise ValueError("title_image_dataurl 不是 base64 编码") + try: + png_bytes = base64.b64decode(b64, validate=True) + except (binascii.Error, ValueError) as exc: + raise ValueError(f"title_image_dataurl base64 解码失败: {exc}") from exc + if not png_bytes: + raise ValueError("title_image_dataurl 解码后为空") + + if dst_path: + out_path = dst_path + with open(out_path, "wb") as f: + f.write(png_bytes) + return out_path + suffix = f"_title_{job_id}.png" if job_id else "_title.png" + with tempfile.NamedTemporaryFile(suffix=suffix, delete=False) as tmp: + tmp.write(png_bytes) + return tmp.name + @staticmethod def _probe_video_resolution(video_path: str) -> tuple[int, int]: """用 ffprobe 探测视频分辨率，返回 (width, height)；失败返回 (0, 0)。""" @@ -444,6 +540,7 @@ class AiAvatarRenderService: *, input_video: str, b_roll_segments: list[dict[str, Any]], + extra_inputs: list[str] | None = None, filter_complex: str, final_label: Optional[str], output_path: str, @@ -460,6 +557,9 @@ class AiAvatarRenderService: asset_url = seg.get("asset_url", "") if asset_url: cmd.extend(["-i", asset_url]) + # 额外输入（例如前端 Canvas 渲染的标题 PNG） + for extra in extra_inputs or []: + cmd.extend(["-i", extra]) if filter_complex and final_label: cmd.extend( diff --git a/apps/web/src/pages/ai-avatar/AiAvatarPage.tsx b/apps/web/src/pages/ai-avatar/AiAvatarPage.tsx index a13d0bd1c..af31176c2 100644 --- a/apps/web/src/pages/ai-avatar/AiAvatarPage.tsx +++ b/apps/web/src/pages/ai-avatar/AiAvatarPage.tsx @@ -32,6 +32,7 @@ import { buildTitleConfigPayload, buildCoverConfigPayload, } from "./utils/contract" +import { renderTitleToPngDataUrl, getVideoResolution } from "./utils/titleCanvas" /** 面板折叠状态 */ type PanelKey = "video" | "voice" | "script" | "lipsync" | "title" | "cover" @@ -210,6 +211,23 @@ const AiAvatarPage: React.FC = () => { try { // 确保有 project_id（AI数字人入口独立，不在项目内，自动取默认项目；#1860 P0 bugfix） const defaultProject = await getOrCreateDefaultProject() + + // 用 Canvas 预渲染标题为 PNG dataURL（所见即所得，后端用 overlay 直接叠加） + let titleImageDataUrl: string | null = null + if (state.titleConfig.title?.trim()) { + try { + const res = await getVideoResolution(state.lipsyncJob.output_video_url || "") + titleImageDataUrl = renderTitleToPngDataUrl({ + titleConfig: state.titleConfig, + videoWidth: res.width, + videoHeight: res.height, + }) + } catch (canvasErr) { + console.warn("[渲染] 标题 Canvas 渲染失败，降级 drawtext:", canvasErr) + titleImageDataUrl = null + } + } + const job = await submitRender({ lipsync_job_id: state.lipsyncJob.id, script_id: state.script?.id, @@ -223,7 +241,7 @@ const AiAvatarPage: React.FC = () => { pip_position: seg.pip_position, pip_scale: seg.pip_scale, })) as never, - title_config: buildTitleConfigPayload(state.titleConfig), + title_config: buildTitleConfigPayload(state.titleConfig, titleImageDataUrl), // 封面不阻塞渲染：用户未选定封面时传空 dict，后端不生成封面；渲染完成后再单独抽帧 cover_config: state.coverConfig.smart_cover_url || diff --git a/apps/web/src/pages/ai-avatar/api/aiAvatar.ts b/apps/web/src/pages/ai-avatar/api/aiAvatar.ts index 25ec6cf85..813415916 100644 --- a/apps/web/src/pages/ai-avatar/api/aiAvatar.ts +++ b/apps/web/src/pages/ai-avatar/api/aiAvatar.ts @@ -58,7 +58,7 @@ export const getLipsyncJob = async (id: string): Promise => { return response.data } -/* ── 智能封面（MediaKit 抽帧 + 质量评分选最佳帧 + 可选 drawtext 标题叠加） ── */ +/* ── 智能封面（MediaKit 抽帧 + 质量评分选最佳帧 + 可选标题 overlay/drawtext 叠加） ── */ export const generateSmartCover = async ( video_url: string, title_config?: Record | null, @@ -67,7 +67,7 @@ export const generateSmartCover = async ( const response = await apiClient.post<{ cover_url: string; status: string; message: string }>( "/ai-avatar/render/smart-cover", { video_url, max_frames, title_config: title_config ?? null }, - // smart-cover 链路：下载视频+抽帧+drawtext 加标题+上传 OSS，需要较长时间，120s 超时 + // smart-cover 链路：下载视频+抽帧+overlay/drawtext 加标题+上传 OSS，需要较长时间，120s 超时 { timeout: 120000 }, ) return response.data @@ -82,6 +82,7 @@ export const submitRender = async (data: { cover_config?: Record project_id?: string }): Promise => { + // title_config 内可含 title_image_dataurl（前端 Canvas 渲染的 PNG dataURL） const response = await apiClient.post("/ai-avatar/render", data) return response.data } diff --git a/apps/web/src/pages/ai-avatar/utils/contract.ts b/apps/web/src/pages/ai-avatar/utils/contract.ts index 19d4843db..d8d361028 100644 --- a/apps/web/src/pages/ai-avatar/utils/contract.ts +++ b/apps/web/src/pages/ai-avatar/utils/contract.ts @@ -28,10 +28,13 @@ export function normalizeEmotion(raw: string | undefined | null): VoiceEmotion { * 后端真实字段：text(或content)、font(或font_preset)、font_size(或size)、 * font_color(或color，可传 #RRGGBB)、position(top/center/bottom/custom)、 * enabled、bold、stroke{enabled,width,color}、shadow{enabled,color,offset_x,offset_y}、 - * pos_x/pos_y(custom 时)。 + * pos_x/pos_y(custom 时)、title_image_dataurl（前端 Canvas 渲染的 PNG dataURL，WYSIWYG 路径优先）。 * 口播标题默认 position=bottom（不传后端会默认 top 跑到画面顶部）。 */ -export function buildTitleConfigPayload(cfg: AiAvatarTitleConfig): Record { +export function buildTitleConfigPayload( + cfg: AiAvatarTitleConfig, + titleImageDataUrl?: string | null, +): Record { const text = (cfg.title || "").trim() if (!text) return {} const position = cfg.position || "bottom" @@ -53,6 +56,10 @@ export function buildTitleConfigPayload(cfg: AiAvatarTitleConfig): Record l.trim()) + .filter((l) => l.length > 0) + if (lines.length === 0) return null + + const canvas = document.createElement("canvas") + canvas.width = videoWidth + canvas.height = videoHeight + const ctx = canvas.getContext("2d") + if (!ctx) return null + + const size = Math.max(12, Math.round(titleConfig.size || 48)) + const bold = !!titleConfig.bold + const italic = !!titleConfig.italic + const color = titleConfig.color || "#ffffff" + const stroke = !!titleConfig.stroke + const shadow = !!titleConfig.shadow + + // 字体族 fallback 链：优先中文字体 + const fontFamily = + '"Noto Sans CJK SC","Source Han Sans CN","PingFang SC","Microsoft YaHei",sans-serif' + const fontParts: string[] = [] + if (italic) fontParts.push("italic") + if (bold) fontParts.push("bold") + fontParts.push(`${size}px`, fontFamily) + ctx.font = fontParts.join(" ") + ctx.fillStyle = color + ctx.textAlign = "center" + ctx.textBaseline = "middle" + + // 阴影（shadow=true 时开启） + if (shadow) { + ctx.shadowColor = "rgba(0,0,0,0.8)" + ctx.shadowBlur = 4 + ctx.shadowOffsetX = 0 + ctx.shadowOffsetY = 2 + } + + // 位置计算：与 PanelLipsyncPreview 的 CSS 对齐 + // 预览用 top/bottom 8px padding + transform translateX(-50%) 居中； + // 这里画到整尺寸 canvas，padding 按比例放大到全分辨率（预览缩放 0.35x 时 8px ≈ 23px 全尺寸， + // 为更贴近原 CSS 16px 安全边距，用 16px 作为内边距）。 + const PAD = 16 + let centerX = videoWidth / 2 + let startY: number + const position = titleConfig.position || "bottom" + const lineGap = size * 1.2 + const totalTextH = lines.length * lineGap - (lineGap - size) // 所有行的总高度 + // 文本块顶部 y（textBaseline=middle 时首行基线） + let firstLineY: number + if ( + position === "custom" && + typeof titleConfig.pos_x === "number" && + typeof titleConfig.pos_y === "number" + ) { + centerX = (Math.max(0, Math.min(100, titleConfig.pos_x)) / 100) * videoWidth + const centerY = (Math.max(0, Math.min(100, titleConfig.pos_y)) / 100) * videoHeight + firstLineY = centerY - totalTextH / 2 + size / 2 + } else if (position === "top") { + // 顶部：y = size/2 + PAD + firstLineY = size / 2 + PAD + } else if (position === "center") { + firstLineY = videoHeight / 2 - totalTextH / 2 + size / 2 + } else { + // bottom（默认） + firstLineY = videoHeight - totalTextH - PAD + size / 2 + } + + // 描边参数（stroke=true 或 bold 默认细描边模拟粗体时都画； + // 注意：浏览器原生 bold 已经是粗体 glyph，Canvas 这里对 stroke=true 才加黑描边， + // 与预览 CSS 的 WebkitTextStroke 保持一致，不对 bold 自动加描边避免双粗）。 + const doStroke = stroke + // 逐行绘制 + lines.forEach((line, idx) => { + const y = firstLineY + idx * lineGap + if (doStroke) { + const prevShadowColor = ctx.shadowColor + const prevShadowBlur = ctx.shadowBlur + // 描边不要带阴影（避免黑色描边发虚） + ctx.shadowColor = "rgba(0,0,0,0)" + ctx.shadowBlur = 0 + ctx.lineWidth = Math.max(2, size * 0.06) + ctx.strokeStyle = "#000000" + ctx.lineJoin = "round" + ctx.strokeText(line, centerX, y) + // 恢复阴影 + if (shadow) { + ctx.shadowColor = "rgba(0,0,0,0.8)" + ctx.shadowBlur = 4 + } else { + ctx.shadowColor = prevShadowColor + ctx.shadowBlur = prevShadowBlur + } + } + ctx.fillText(line, centerX, y) + }) + + try { + return canvas.toDataURL("image/png") + } catch { + return null + } +} + +/** + * 获取视频真实分辨率（HTMLVideoElement + loadedmetadata，超时 3 秒兜底 720×1280）。 + */ +export function getVideoResolution( + videoUrl: string, + timeoutMs = 3000, +): Promise<{ width: number; height: number }> { + return new Promise((resolve) => { + if (!videoUrl) { + resolve({ width: 720, height: 1280 }) + return + } + const video = document.createElement("video") + video.preload = "metadata" + video.muted = true + video.playsInline = true + video.crossOrigin = "anonymous" + let settled = false + const done = (w: number, h: number) => { + if (settled) return + settled = true + video.removeAttribute("src") + video.load() + resolve({ width: w, height: h }) + } + const timer = window.setTimeout(() => done(720, 1280), timeoutMs) + video.onloadedmetadata = () => { + window.clearTimeout(timer) + const w = video.videoWidth || 720 + const h = video.videoHeight || 1280 + done(w, h) + } + video.onerror = () => { + window.clearTimeout(timer) + done(720, 1280) + } + video.src = videoUrl + }) +} diff --git a/packages/domain/video_filter_builder.py b/packages/domain/video_filter_builder.py index 496e68d5a..91f82959f 100755 --- a/packages/domain/video_filter_builder.py +++ b/packages/domain/video_filter_builder.py @@ -420,44 +420,29 @@ def _escape_drawtext_text(text: str) -> str: return result -# 粗体字体文件映射：服务器镜像只保留了 NotoSansSC-VF.ttf（可变字体，已删除 -# NotoSansCJK-Bold.ttc 以避免 Mono 变体问题，见 worker-base.Dockerfile）， -# 因此无法通过 fontfile 切换到 Bold 字重。这里保留路径列表作为未来扩展， -# 实际加粗通过 borderw 黑色描边实现（见下）。 -DRAWTEXT_BOLD_FONT_SEARCH_PATHS: list[str] = [ - "/usr/share/fonts/opentype/noto/NotoSansCJK-Bold.ttc", - "/usr/share/fonts/noto-cjk/NotoSansCJK-Bold.ttc", - "/usr/share/fonts/google-noto-cjk/NotoSansCJK-Bold.ttc", - "/usr/share/fonts/truetype/noto/NotoSansSC-Bold.ttf", - "/usr/share/fonts/noto/NotoSansSC-Bold.ttf", -] +# 粗体字体已由前端 Canvas 直接渲染（Canvas 使用浏览器原生粗体 glyph）， +# FFmpeg 侧不再需要查找 Bold 字体文件；drawtext 仅作为旧版前端的降级路径， +# 通过 borderw 黑色细描边模拟粗体（见 build_title_drawtext_filter）。 -def _resolve_font_path(font_name: str, bold: bool = False) -> str: +def _resolve_font_path(font_name: str) -> str: """解析字体名到服务器实际字体文件路径。 查找策略： 1. 通过 DRAWTEXT_FONT_MAP 映射前端字体名到服务器关键字 - 2. bold=True 时优先查找粗体变体；找不到回退常规字重 - 3. 在 DRAWTEXT_FONT_SEARCH_PATHS 中查找匹配路径 - 4. 未找到则返回空字符串（drawtext 使用内置默认字体） + 2. 在 DRAWTEXT_FONT_SEARCH_PATHS 中查找匹配路径 + 3. 未找到则返回空字符串（drawtext 使用内置默认字体） + + 注：粗体已由前端 Canvas 渲染时直接用浏览器 bold glyph 绘制， + 此处仅作为旧版前端降级路径，无需切换 Bold 字体文件。 """ keyword = DRAWTEXT_FONT_MAP.get(font_name, font_name) import os - if bold: - for path in DRAWTEXT_BOLD_FONT_SEARCH_PATHS: - if keyword.lower() in path.lower() and os.path.isfile(path): - return path - # 粗体文件找不到时，再查常规字重（后面会用描边兜底加粗） for path in DRAWTEXT_FONT_SEARCH_PATHS: if keyword.lower() in path.lower() and os.path.isfile(path): return path # fallback：遍历搜索任意可用字体 - if bold: - for path in DRAWTEXT_BOLD_FONT_SEARCH_PATHS: - if os.path.isfile(path): - return path for path in DRAWTEXT_FONT_SEARCH_PATHS: if os.path.isfile(path): return path @@ -493,8 +478,10 @@ def build_title_drawtext_filter( if not title_config or not isinstance(title_config, dict): return None - # 字段名归一化：兼容 content/text、font_preset/font 两套命名 - text = (title_config.get("text") or title_config.get("content") or "").strip() + # 字段名归一化：兼容 content/text/title 三套命名 + text = ( + title_config.get("text") or title_config.get("content") or title_config.get("title") or "" + ).strip() if not text: return None @@ -518,8 +505,8 @@ def build_title_drawtext_filter( # ── 构建 drawtext 参数 ── params: list[str] = [] - # 字体文件：粗体优先使用 Bold 字体文件，避免同色描边造成字形偏移/重影 - font_path = _resolve_font_path(font_name, bold=bold) + # 字体文件（drawtext 降级路径：粗体通过 borderw 黑色描边模拟） + font_path = _resolve_font_path(font_name) if font_path: escaped_path = font_path.replace("\\", "\\\\").replace(":", "\\\\:").replace("'", "\\\\'") params.append(f"fontfile='{escaped_path}'") @@ -599,6 +586,43 @@ def build_title_drawtext_filter( return "drawtext=" + ":".join(params) +def build_title_overlay_filter( + title_config: dict[str, Any], + output_width: int, # noqa: ARG001 - 保留参数签名，PNG 已按视频分辨率绘制 + output_height: int, # noqa: ARG001 + title_png_path: str, + *, + title_input_label: str = "[1:v]", + base_label: str = "[0:v]", + output_label: str = "vout_titled", +) -> str | None: + """构建标题 PNG 图层 overlay 滤镜（WYSIWYG 路径）。 + + 前端用 Canvas 把标题画成与视频同分辨率的透明 PNG（所见即所得）， + 后端直接 overlay=0:0 叠加即可，PNG 透明区域不遮挡视频。 + + Args: + title_config: 标题配置 dict（仅用来判断降级） + output_width: 输出宽度（未使用，PNG 已按该分辨率绘制） + output_height: 输出高度（未使用） + title_png_path: 已保存到本地的标题 PNG 文件路径 + title_input_label: 标题 PNG 在 filter_complex 中的输入标签（默认 "[1:v]"） + base_label: 前序滤镜输出标签（如 B-roll 输出 "[vout]"） + output_label: overlay 输出标签名 + + Returns: + overlay 滤镜字符串；title_png_path 为空/文件不存在时返回 None（降级到 drawtext） + """ + import os + + if not title_png_path or not os.path.isfile(title_png_path): + return None + if not title_config or not isinstance(title_config, dict): + return None + + return f"{base_label}{title_input_label}overlay=0:0[{output_label}]" + + # ── B-roll 叠加滤镜 ───────────────────────────────────────────────────────── diff --git a/tests/unit/test_video_filter_builder.py b/tests/unit/test_video_filter_builder.py index a0d039236..61aa2aabb 100755 --- a/tests/unit/test_video_filter_builder.py +++ b/tests/unit/test_video_filter_builder.py @@ -13,6 +13,7 @@ from __future__ import annotations +import os import unittest from dataclasses import FrozenInstanceError from unittest.mock import patch @@ -29,10 +30,12 @@ from packages.domain.video_filter_builder import ( ClipFilterChain, _escape_drawtext_text, _resolve_font_path, + build_broll_overlay_filter, build_clip_filter, build_concat_filter, build_filter_complex, build_title_drawtext_filter, + build_title_overlay_filter, build_xfade_filter, chain_filters, has_audio, @@ -1161,5 +1164,97 @@ class TestDrawtextNotDictConfig(unittest.TestCase): self.assertIsNone(build_title_drawtext_filter([1, 2, 3])) +class TestTitleOverlay(unittest.TestCase): + """build_title_overlay_filter 单元测试（WYSIWYG PNG 叠加路径）。""" + + def test_overlay_filter_format(self): + """PNG 文件存在时返回正确的 overlay 滤镜字符串。""" + import tempfile + + with tempfile.NamedTemporaryFile(suffix=".png", delete=False) as tmp: + tmp.write(b"\x89PNG\r\n\x1a\n") + tmp_path = tmp.name + try: + result = build_title_overlay_filter( + {"text": "标题"}, + output_width=720, + output_height=1280, + title_png_path=tmp_path, + title_input_label="[2:v]", + base_label="[vout]", + output_label="vout_titled", + ) + self.assertIsNotNone(result) + self.assertIn("[vout][2:v]overlay=0:0[vout_titled]", result) + finally: + os.unlink(tmp_path) + + def test_overlay_default_labels(self): + """不传 label 参数时使用默认 [0:v] / [1:v] / vout_titled。""" + import tempfile + + with tempfile.NamedTemporaryFile(suffix=".png", delete=False) as tmp: + tmp.write(b"\x89PNG\r\n\x1a\n") + tmp_path = tmp.name + try: + result = build_title_overlay_filter( + {"text": "标题"}, + output_width=720, + output_height=1280, + title_png_path=tmp_path, + ) + self.assertEqual(result, "[0:v][1:v]overlay=0:0[vout_titled]") + finally: + os.unlink(tmp_path) + + def test_overlay_returns_none_when_png_missing(self): + """PNG 文件不存在时返回 None，供调用方降级到 drawtext。""" + result = build_title_overlay_filter( + {"text": "标题"}, + output_width=720, + output_height=1280, + title_png_path="/nonexistent/path/title.png", + ) + self.assertIsNone(result) + + def test_overlay_returns_none_for_empty_config(self): + """title_config 为空/非 dict 时返回 None。""" + import tempfile + + with tempfile.NamedTemporaryFile(suffix=".png", delete=False) as tmp: + tmp.write(b"\x89PNG\r\n\x1a\n") + tmp_path = tmp.name + try: + self.assertIsNone( + build_title_overlay_filter( + None, + output_width=720, + output_height=1280, + title_png_path=tmp_path, + ) + ) + self.assertIsNone( + build_title_overlay_filter( + "not a dict", + output_width=720, + output_height=1280, + title_png_path=tmp_path, + ) + ) + finally: + os.unlink(tmp_path) + + def test_overlay_returns_none_for_empty_path(self): + """title_png_path 为空字符串时返回 None。""" + self.assertIsNone( + build_title_overlay_filter( + {"text": "标题"}, + output_width=720, + output_height=1280, + title_png_path="", + ) + ) + + if __name__ == "__main__": unittest.main()