@lumy-pack/scene-sieve 0.0.4 → 0.0.6

package/dist/index.mjs

@@ -44,6 +44,7 @@ var DEFAULT_THRESHOLD = 0.5;
 var DEFAULT_FPS = 5;
 var DEFAULT_SCALE = 720;
 var DEFAULT_QUALITY = 80;
+var DEFAULT_MAX_FRAMES = 300;
 var NORMALIZATION_PERCENTILE = 0.9;
 var WORKSPACE_PREFIX = `${APP_NAME}-`;
 var TEMP_BASE_DIR = tmpdir();
@@ -56,8 +57,8 @@ var SUPPORTED_VIDEO_EXTENSIONS = [
 ];
 var SUPPORTED_GIF_EXTENSIONS = [".gif"];
 var FRAME_OUTPUT_EXTENSION = ".jpg";
+var FRAME_FILENAME_PATTERN = "frame_%06d.jpg";
 var OPENCV_BATCH_SIZE = 10;
-var MIN_IFRAME_COUNT = 3;
 var DBSCAN_ALPHA = 0.03;
 var DBSCAN_MIN_PTS = 4;
 var IOU_THRESHOLD = 0.9;
@@ -196,7 +197,13 @@ 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();
@@ -212,7 +219,7 @@ 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;
@@ -220,13 +227,14 @@ 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
         });
@@ -238,17 +246,45 @@ 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);
         }
       }
@@ -470,13 +506,17 @@ 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);
@@ -489,8 +529,11 @@ 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
@@ -537,7 +580,7 @@ function isSupportedFile(filePath, extensions) {
 // src/core/extractor.ts
 async function extractFrames(ctx) {
   const framesDir = join2(ctx.workspacePath, "frames");
-  const { inputPath, fps, scale } = ctx.options;
+  const { inputPath, fps, maxFrames, scale } = ctx.options;
   if (!inputPath) {
     throw new Error("inputPath is required for frame extraction");
   }
@@ -554,41 +597,23 @@ async function extractFrames(ctx) {
   }
   logger.debug(`Extracting frames from: ${inputPath}`);
   await ensureDir(framesDir);
-  const isGif = isSupportedFile(inputPath, SUPPORTED_GIF_EXTENSIONS);
-  let frames;
-  if (isGif) {
-    logger.debug("GIF detected \u2014 using FPS extraction");
-    frames = await extractByFps(inputPath, framesDir, fps, scale);
-  } else {
-    frames = await extractIFrames(inputPath, framesDir, scale);
-    if (frames.length < MIN_IFRAME_COUNT) {
-      logger.debug(
-        `Insufficient I-frames (${frames.length}), falling back to FPS mode`
-      );
-      frames = await extractByFps(inputPath, framesDir, fps, scale);
-    }
+  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})`
+    );
   }
+  const frames = await extractByFps(inputPath, framesDir, effectiveFps, scale);
   ctx.emitProgress(100);
   logger.debug(`Extracted ${frames.length} frames`);
   return frames;
 }
-async function extractIFrames(inputPath, outputDir, scale) {
-  const outputPattern = join2(outputDir, "frame_%06d.jpg");
-  await execa(ffmpegPath, [
-    "-i",
-    inputPath,
-    "-vf",
-    `select='eq(pict_type,I)',scale=-1:${scale}`,
-    "-vsync",
-    "vfr",
-    "-q:v",
-    "2",
-    outputPattern
-  ]);
-  return buildFrameList(outputDir, inputPath);
-}
 async function extractByFps(inputPath, outputDir, fps, scale) {
-  const outputPattern = join2(outputDir, "frame_%06d.jpg");
+  const outputPattern = join2(outputDir, FRAME_FILENAME_PATTERN);
   await execa(ffmpegPath, [
     "-i",
     inputPath,
@@ -637,7 +662,7 @@ async function buildFrameList(framesDir, inputPath) {
 import { join as join4 } from "path";
 
 // src/core/workspace.ts
-import { rename, rm, writeFile } from "fs/promises";
+import { readdir as readdir2, rename, rm, stat as stat2, writeFile } from "fs/promises";
 import { join as join3 } from "path";
 import sharp2 from "sharp";
 async function createWorkspace(sessionId) {
@@ -651,13 +676,44 @@ 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);
@@ -670,6 +726,7 @@ async function cleanupWorkspace(workspacePath) {
   } catch {
   }
 }
+var STALE_THRESHOLD_MS = 60 * 60 * 1e3;
 async function writeInputBuffer(buffer, workspacePath) {
   const inputDir = join3(workspacePath, "input");
   await ensureDir(inputDir);
@@ -717,8 +774,11 @@ function resolveOptions(options) {
     pruneMode,
     outputPath,
     fps: options.fps ?? DEFAULT_FPS,
+    maxFrames: options.maxFrames ?? DEFAULT_MAX_FRAMES,
     scale: options.scale ?? DEFAULT_SCALE,
     quality: options.quality ?? DEFAULT_QUALITY,
+    iouThreshold: options.iouThreshold ?? IOU_THRESHOLD,
+    animationThreshold: options.animationThreshold ?? ANIMATION_FRAME_THRESHOLD,
     debug: options.debug ?? false
   };
 }
@@ -989,7 +1049,9 @@ async function runPipeline(options) {
     }
     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,
@@ -1022,6 +1084,15 @@ async function runPipeline(options) {
       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) {