@lumy-pack/scene-sieve 0.0.5 → 0.0.7

package/dist/pipeline-worker.mjs

@@ -51,15 +51,8 @@ var DEFAULT_MAX_FRAMES = 300;
 var NORMALIZATION_PERCENTILE = 0.9;
 var WORKSPACE_PREFIX = `${APP_NAME}-`;
 var TEMP_BASE_DIR = tmpdir();
-var SUPPORTED_VIDEO_EXTENSIONS = [
-  ".mp4",
-  ".mov",
-  ".avi",
-  ".mkv",
-  ".webm"
-];
-var SUPPORTED_GIF_EXTENSIONS = [".gif"];
 var FRAME_OUTPUT_EXTENSION = ".jpg";
+var FRAME_FILENAME_PATTERN = "frame_%06d.jpg";
 var OPENCV_BATCH_SIZE = 10;
 var DBSCAN_ALPHA = 0.03;
 var DBSCAN_MIN_PTS = 4;
@@ -199,7 +192,13 @@ function computeIoU(a, b) {
   return union === 0 ? 0 : intersection / union;
 }
 var IoUTracker = class {
+  constructor(fps = DEFAULT_FPS, iouThreshold = IOU_THRESHOLD, animationThreshold = ANIMATION_FRAME_THRESHOLD) {
+    this.fps = fps;
+    this.iouThreshold = iouThreshold;
+    this.animationThreshold = animationThreshold;
+  }
   regions = [];
+  extractedAnimations = [];
   update(boxes, pairIndex) {
     const animationIndices = /* @__PURE__ */ new Set();
     const matched = /* @__PURE__ */ new Set();
@@ -215,7 +214,7 @@ var IoUTracker = class {
           bestRegionIdx = ri;
         }
       }
-      if (bestIoU > IOU_THRESHOLD && bestRegionIdx !== -1) {
+      if (bestIoU > this.iouThreshold && bestRegionIdx !== -1) {
         const region = this.regions[bestRegionIdx];
         const gap = pairIndex - region.lastSeen;
         region.box = box;
@@ -223,13 +222,14 @@ var IoUTracker = class {
         region.lastSeen = pairIndex;
         region.weight *= Math.pow(DECAY_LAMBDA, gap);
         matched.add(bestRegionIdx);
-        if (region.consecutiveCount >= ANIMATION_FRAME_THRESHOLD) {
+        if (region.consecutiveCount >= this.animationThreshold) {
           animationIndices.add(bi);
         }
       } else {
         this.regions.push({
           box,
           consecutiveCount: 1,
+          firstSeen: pairIndex,
           lastSeen: pairIndex,
           weight: 1
         });
@@ -241,17 +241,45 @@ var IoUTracker = class {
         this.regions[ri].weight *= Math.pow(DECAY_LAMBDA, gap);
       }
     }
-    this.regions = this.regions.filter((r) => r.weight > 0.01);
+    for (let i = 0; i < this.regions.length; i++) {
+      const region = this.regions[i];
+      if (region.weight <= 0.01 && !matched.has(i)) {
+        this.collectAnimation(region);
+      }
+    }
+    this.regions = this.regions.filter(
+      (r, i) => r.weight > 0.01 || matched.has(i)
+    );
     return animationIndices;
   }
+  collectAnimation(region) {
+    if (region.consecutiveCount >= this.animationThreshold) {
+      const durationMs = region.consecutiveCount / this.fps * 1e3;
+      this.extractedAnimations.push({
+        type: "loading_spinner",
+        // 기본값으로 loading_spinner 사용
+        boundingBox: region.box,
+        startFrameId: region.firstSeen,
+        endFrameId: region.lastSeen,
+        durationMs
+      });
+    }
+  }
+  flushAndGetAnimations() {
+    for (const region of this.regions) {
+      this.collectAnimation(region);
+    }
+    this.regions = [];
+    return this.extractedAnimations;
+  }
   getAnimationWeight(boxIndex, boxes) {
     if (boxIndex >= boxes.length) return 0;
     const box = boxes[boxIndex];
     let maxWeight = 0;
     for (const region of this.regions) {
-      if (region.consecutiveCount >= ANIMATION_FRAME_THRESHOLD) {
+      if (region.consecutiveCount >= this.animationThreshold) {
         const iou = computeIoU(box, region.box);
-        if (iou > IOU_THRESHOLD) {
+        if (iou > this.iouThreshold) {
           maxWeight = Math.max(maxWeight, region.weight);
         }
       }
@@ -473,13 +501,17 @@ async function analyzeBatch(cvLib, frames, scale, tracker, pairOffset) {
 }
 async function analyzeFrames(ctx) {
   const { frames } = ctx;
-  if (frames.length < 2) return [];
+  if (frames.length < 2) return { edges: [], animations: [] };
   logger.debug(
     `Analyzing ${frames.length} frames in batches of ${OPENCV_BATCH_SIZE}`
   );
   const cvLib = await ensureOpenCV();
   const edges = [];
-  const tracker = new IoUTracker();
+  const tracker = new IoUTracker(
+    ctx.options.fps,
+    ctx.options.iouThreshold,
+    ctx.options.animationThreshold
+  );
   const scale = ctx.options.scale;
   for (let i = 0; i < frames.length - 1; i += OPENCV_BATCH_SIZE) {
     const batchEnd = Math.min(i + OPENCV_BATCH_SIZE + 1, frames.length);
@@ -492,8 +524,11 @@ async function analyzeFrames(ctx) {
     );
     ctx.emitProgress(progress);
   }
-  logger.debug(`Computed ${edges.length} score edges`);
-  return edges;
+  const animations = tracker.flushAndGetAnimations();
+  logger.debug(
+    `Computed ${edges.length} score edges and ${animations.length} animations`
+  );
+  return { edges, animations };
 }
 
 // src/core/extractor.ts
@@ -533,9 +568,6 @@ function deriveOutputPath(inputPath) {
   const name = basename(inputPath, extname(inputPath));
   return resolve(dir, `${name}_scenes`);
 }
-function isSupportedFile(filePath, extensions) {
-  return extensions.includes(extname(filePath).toLowerCase());
-}
 
 // src/core/extractor.ts
 async function extractFrames(ctx) {
@@ -548,32 +580,47 @@ async function extractFrames(ctx) {
   if (!exists) {
     throw new Error(`Input file not found: ${inputPath}`);
   }
-  const allExtensions = [
-    ...SUPPORTED_VIDEO_EXTENSIONS,
-    ...SUPPORTED_GIF_EXTENSIONS
-  ];
-  if (!isSupportedFile(inputPath, allExtensions)) {
-    throw new Error(`Unsupported file format: ${inputPath}`);
+  const metadata = await getVideoMetadata(inputPath).catch((err) => {
+    logger.debug(`ffprobe failed: ${err.message}`);
+    return null;
+  });
+  if (!metadata || !metadata.format) {
+    throw new Error(`Could not read file metadata: ${inputPath}`);
+  }
+  const formatName = metadata.format.format_name ?? "";
+  const duration = parseFloat(metadata.format.duration ?? "0");
+  const hasVideoStream = metadata.streams?.some((s) => s.codec_type === "video") ?? false;
+  if (!hasVideoStream) {
+    throw new Error(
+      `No video stream found in file: ${inputPath} (detected format: ${formatName})`
+    );
   }
-  logger.debug(`Extracting frames from: ${inputPath}`);
+  logger.debug(
+    `Detected format: ${formatName} (Duration: ${duration.toFixed(1)}s), path: ${inputPath}`
+  );
   await ensureDir(framesDir);
   let effectiveFps = fps;
-  const duration = await getVideoDuration(inputPath).catch(() => 0);
   if (duration > 0) {
     const fpsCap = maxFrames / duration;
     effectiveFps = Math.min(fps, fpsCap);
     effectiveFps = Math.max(0.5, effectiveFps);
     logger.debug(
-      `Duration: ${duration.toFixed(1)}s, FPS: ${fps} \u2192 effective: ${effectiveFps.toFixed(2)} (maxFrames: ${maxFrames})`
+      `FPS: ${fps} \u2192 effective: ${effectiveFps.toFixed(2)} (maxFrames: ${maxFrames})`
     );
   }
-  const frames = await extractByFps(inputPath, framesDir, effectiveFps, scale);
+  const frames = await extractByFps(
+    inputPath,
+    framesDir,
+    effectiveFps,
+    scale,
+    duration
+  );
   ctx.emitProgress(100);
   logger.debug(`Extracted ${frames.length} frames`);
   return frames;
 }
-async function extractByFps(inputPath, outputDir, fps, scale) {
-  const outputPattern = join2(outputDir, "frame_%06d.jpg");
+async function extractByFps(inputPath, outputDir, fps, scale, duration) {
+  const outputPattern = join2(outputDir, FRAME_FILENAME_PATTERN);
   await execa(ffmpegPath, [
     "-i",
     inputPath,
@@ -583,34 +630,26 @@ async function extractByFps(inputPath, outputDir, fps, scale) {
     "2",
     outputPattern
   ]);
-  return buildFrameList(outputDir, inputPath);
+  return buildFrameList(outputDir, duration);
 }
-async function getVideoDuration(inputPath) {
+async function getVideoMetadata(inputPath) {
   const { stdout } = await execa(ffprobePath, [
     "-v",
     "quiet",
     "-print_format",
     "json",
     "-show_format",
+    "-show_streams",
     inputPath
   ]);
-  const metadata = JSON.parse(stdout);
-  return parseFloat(metadata.format?.duration ?? "0");
+  return JSON.parse(stdout);
 }
-async function buildFrameList(framesDir, inputPath) {
+async function buildFrameList(framesDir, duration) {
   const files = await readdir(framesDir);
   const jpgFiles = files.filter((f) => f.endsWith(".jpg")).sort();
   if (jpgFiles.length === 0) {
     return [];
   }
-  let duration = 0;
-  try {
-    duration = await getVideoDuration(inputPath);
-  } catch {
-    logger.debug(
-      "Could not determine video duration; using frame index for timestamps"
-    );
-  }
   return jpgFiles.map((file, index) => ({
     id: index,
     timestamp: duration > 0 && jpgFiles.length > 1 ? duration * index / (jpgFiles.length - 1) : index,
@@ -636,13 +675,44 @@ async function finalizeOutput(ctx, selectedFrames) {
   const outputPath = ctx.options.outputPath;
   const quality = ctx.options.quality;
   const outputFiles = [];
+  const framesMetadata = [];
+  const totalFramesCount = ctx.frames.length;
+  const padding = Math.max(4, String(totalFramesCount).length);
   for (let i = 0; i < selectedFrames.length; i++) {
     const frame = selectedFrames[i];
-    const destName = `scene_${String(i + 1).padStart(3, "0")}.jpg`;
-    const destPath = join3(stagingDir, destName);
+    const fileName = `frame_${String(frame.id + 1).padStart(padding, "0")}.jpg`;
+    const destPath = join3(stagingDir, fileName);
     await sharp2(frame.extractPath).jpeg({ quality, mozjpeg: true }).toFile(destPath);
-    outputFiles.push(join3(outputPath, destName));
+    outputFiles.push(join3(outputPath, fileName));
+    framesMetadata.push({
+      step: i + 1,
+      fileName,
+      frameId: frame.id + 1,
+      timestampMs: Math.round(frame.timestamp * 1e3)
+    });
   }
+  const metadata = {
+    video: {
+      originalDurationMs: Math.round(
+        (ctx.frames.length > 0 ? ctx.frames[ctx.frames.length - 1].timestamp : 0) * 1e3
+      ),
+      fps: ctx.options.fps,
+      resolution: {
+        width: ctx.options.scale,
+        height: Math.round(ctx.options.scale * 9 / 16)
+      }
+    },
+    frames: framesMetadata,
+    animations: (ctx.animations || []).map((anim) => ({
+      ...anim,
+      startFrameId: anim.startFrameId + 1,
+      endFrameId: anim.endFrameId + 1,
+      durationMs: Math.round(anim.durationMs)
+    }))
+  };
+  const metadataPath = join3(stagingDir, ".metadata.json");
+  await writeFile(metadataPath, JSON.stringify(metadata, null, 2));
+  outputFiles.push(join3(outputPath, ".metadata.json"));
   await ensureDir(join3(outputPath, ".."));
   await rm(outputPath, { recursive: true, force: true });
   await rename(stagingDir, outputPath);
@@ -706,6 +776,8 @@ function resolveOptions(options2) {
     maxFrames: options2.maxFrames ?? DEFAULT_MAX_FRAMES,
     scale: options2.scale ?? DEFAULT_SCALE,
     quality: options2.quality ?? DEFAULT_QUALITY,
+    iouThreshold: options2.iouThreshold ?? IOU_THRESHOLD,
+    animationThreshold: options2.animationThreshold ?? ANIMATION_FRAME_THRESHOLD,
     debug: options2.debug ?? false
   };
 }
@@ -976,7 +1048,9 @@ async function runPipeline(options2) {
     }
     ctx.emitProgress(100);
     ctx.status = "ANALYZING";
-    ctx.graph = await analyzeFrames(ctx);
+    const { edges, animations } = await analyzeFrames(ctx);
+    ctx.graph = edges;
+    ctx.animations = animations;
     ctx.status = "PRUNING";
     const survivingIds = pruneByThresholdWithCap(
       ctx.graph,
@@ -1009,6 +1083,15 @@ async function runPipeline(options2) {
       prunedFramesCount: prunedFrames.length,
       outputFiles,
       outputBuffers,
+      animations: ctx.animations,
+      video: {
+        originalDurationMs: ctx.frames.length / ctx.options.fps * 1e3,
+        fps: ctx.options.fps,
+        resolution: {
+          width: ctx.options.scale,
+          height: Math.round(ctx.options.scale * 9 / 16)
+        }
+      },
       executionTimeMs: Date.now() - startTime
     };
   } catch (error) {

package/dist/types/index.d.ts

@@ -17,6 +17,8 @@ export interface SieveOptionsBase {
     maxFrames?: number;
     scale?: number;
     quality?: number;
+    iouThreshold?: number;
+    animationThreshold?: number;
     debug?: boolean;
     onProgress?: (phase: ProgressPhase, percent: number) => void;
 }
@@ -32,6 +34,8 @@ export interface ResolvedOptions {
     maxFrames: number;
     scale: number;
     quality: number;
+    iouThreshold: number;
+    animationThreshold: number;
     debug: boolean;
 }
 export interface SieveResult {
@@ -40,8 +44,25 @@ export interface SieveResult {
     prunedFramesCount: number;
     outputFiles: string[];
     outputBuffers?: Buffer[];
+    animations?: AnimationMetadata[];
+    video?: VideoMetadata;
     executionTimeMs: number;
 }
+export interface AnimationMetadata {
+    type: string;
+    boundingBox: BoundingBox;
+    startFrameId: number;
+    endFrameId: number;
+    durationMs: number;
+}
+export interface VideoMetadata {
+    originalDurationMs: number;
+    fps: number;
+    resolution: {
+        width: number;
+        height: number;
+    };
+}
 export interface FrameNode {
     id: number;
     timestamp: number;
@@ -75,7 +96,12 @@ export interface ProcessContext {
     workspacePath: string;
     frames: FrameNode[];
     graph: ScoreEdge[];
+    animations?: AnimationMetadata[];
     status: 'INIT' | ProgressPhase | 'SUCCESS' | 'FAILED';
     emitProgress: (percent: number) => void;
     error?: Error;
 }
+export interface AnalysisResult {
+    edges: ScoreEdge[];
+    animations: AnimationMetadata[];
+}

package/dist/utils/paths.d.ts

@@ -16,4 +16,3 @@ export declare function resolveAbsolute(p: string): string;
  * e.g., /path/to/video.mp4 -> /path/to/video_scenes
  */
 export declare function deriveOutputPath(inputPath: string): string;
-export declare function isSupportedFile(filePath: string, extensions: string[]): boolean;

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@lumy-pack/scene-sieve",
-  "version": "0.0.5",
+  "version": "0.0.7",
   "description": "CLI tool for extracting key frames from video and GIF files",
   "keywords": [
     "cli",