update from asus 106

backend/dataset.py

@@ -14,6 +14,7 @@ Label files are plain YOLO:
 import os
 import shutil
 import time
+from typing import List, Optional
 
 from backend import batches, config, db, jobs, projects, review
 
@@ -74,12 +75,55 @@ def _next_split(cur, project_id: int, val_every: int) -> str:
     return "val" if position % val_every == val_every - 1 else "train"
 
 
-def write_data_yaml(project: dict, batch_ids: list = None) -> str:
+def sync_labels(project_id: int, selected_class_ids: Optional[List[int]] = None) -> dict:
+    """Re-sync label files on disk for all merged frames in the project dataset."""
+    project = projects.get(project_id)
+    root = dataset_dir(project["slug"])
+    with db.cursor() as cur:
+        cur.execute(
+            "SELECT d.frame_id, d.label_rel FROM dataset_items d WHERE d.project_id = ?",
+            (project_id,),
+        )
+        items = cur.fetchall()
+
+    class_map = None
+    if selected_class_ids is not None and len(selected_class_ids) > 0:
+        class_map = {cid: idx for idx, cid in enumerate(sorted(selected_class_ids))}
+
+    synced_files = 0
+    total_lines = 0
+    for frame_id, label_rel in items:
+        annotations = review.listing(frame_id)
+        if class_map is not None:
+            annotations = [a for a in annotations if a["class_id"] in class_map]
+
+        lines = []
+        for item in annotations:
+            mapped_cid = class_map[item["class_id"]] if class_map is not None else item["class_id"]
+            lines.append(_label_line(mapped_cid, item["geometry"], project["label_type"]))
+
+        path = os.path.join(root, label_rel)
+        os.makedirs(os.path.dirname(path), exist_ok=True)
+        with open(path, "w", encoding="utf-8") as f:
+            f.write("\n".join(lines) + ("\n" if lines else ""))
+        synced_files += 1
+        total_lines += len(lines)
+
+    return {"synced_files": synced_files, "total_lines": total_lines}
+
+
+def write_data_yaml(project: dict, batch_ids: list = None, selected_class_ids: Optional[List[int]] = None) -> str:
     """Rebuild data.yaml from the project's classes (REQ-051)."""
+    sync_labels(project["id"], selected_class_ids=selected_class_ids)
     root = dataset_dir(project["slug"])
     os.makedirs(root, exist_ok=True)
     counts = summary(project["id"])["splits"]
-    names = ", ".join(f"'{item['name']}'" for item in project["classes"])
+
+    target_classes = project["classes"]
+    if selected_class_ids is not None and len(selected_class_ids) > 0:
+        target_classes = [c for c in project["classes"] if c["class_id"] in selected_class_ids]
+
+    names = ", ".join(f"'{item['name']}'" for item in target_classes)
 
     if batch_ids:
         with db.cursor() as cur: