feat: add admin dashboard, pipeline service, lightbox, and update dependencies

app/services/pdf_image_extractor.py

@@ -16,6 +16,7 @@ import re
 from pathlib import Path
 
 from app.services.pdf_downloader import paper_dir
+from app.utils import TMP_DIR
 
 logger = logging.getLogger(__name__)
 
@@ -40,10 +41,7 @@ def _find_nearby_labels(
     """
     matched: list[str] = []
     for rect in rects:
-        if isinstance(rect, (list, tuple)):
-            y_min, y_max = rect[1], rect[3]
-        else:
-            y_min, y_max = rect.y0, rect.y1
+        y_min, y_max = rect.y0, rect.y1
 
         for label_key, positions in labels.items():
             for label_page, label_y in positions:
@@ -69,7 +67,7 @@ def extract_images_from_pdf(arxiv_id: str, pdf_path: Path | None = None) -> int:
     import pymupdf
 
     if pdf_path is None:
-        pdf_path = Path("data/tmp") / arxiv_id / "paper.pdf"
+        pdf_path = TMP_DIR / arxiv_id / "paper.pdf"
 
     if not pdf_path.exists():
         logger.warning("PDF not found for %s: %s", arxiv_id, pdf_path)
@@ -162,10 +160,7 @@ def extract_images_from_pdf(arxiv_id: str, pdf_path: Path | None = None) -> int:
                     continue
 
                 margin = 5
-                if isinstance(bbox, (list, tuple)):
-                    x0, y0, x1, y1 = bbox
-                else:
-                    x0, y0, x1, y1 = bbox.x0, bbox.y0, bbox.x1, bbox.y1
+                x0, y0, x1, y1 = bbox.x0, bbox.y0, bbox.x1, bbox.y1
                 clip_rect = pymupdf.Rect(x0 - margin, y0 - margin, x1 + margin, y1 + margin)
 
                 zoom = 2