Revert "优化循环"

This reverts commit 8da7476b358ad9093dd127172b99bc2d2b46f263.

pdf2zh/high_level.py

@@ -68,16 +68,24 @@ def extract_text_to_fp(
             h, w = box.shape
             vcls = ["abandon", "figure", "table", "isolate_formula", "formula_caption"]
             for i, d in enumerate(page_layout.boxes):
-                x0, y0, x1, y1 = d.xyxy.squeeze()
-                x0, y0, x1, y1 = (
-                    np.clip(int(x0 - 1), 0, w - 1),
-                    np.clip(int(h - y1 - 1), 0, h - 1),
-                    np.clip(int(x1 + 1), 0, w - 1),
-                    np.clip(int(h - y0 + 1), 0, h - 1),
-                )
                 if not page_layout.names[int(d.cls)] in vcls:
+                    x0, y0, x1, y1 = d.xyxy.squeeze()
+                    x0, y0, x1, y1 = (
+                        np.clip(int(x0 - 1), 0, w - 1),
+                        np.clip(int(h - y1 - 1), 0, h - 1),
+                        np.clip(int(x1 + 1), 0, w - 1),
+                        np.clip(int(h - y0 + 1), 0, h - 1),
+                    )
                     box[y0:y1, x0:x1] = i + 2
-                else:
+            for i, d in enumerate(page_layout.boxes):
+                if page_layout.names[int(d.cls)] in vcls:
+                    x0, y0, x1, y1 = d.xyxy.squeeze()
+                    x0, y0, x1, y1 = (
+                        np.clip(int(x0 - 1), 0, w - 1),
+                        np.clip(int(h - y1 - 1), 0, h - 1),
+                        np.clip(int(x1 + 1), 0, w - 1),
+                        np.clip(int(h - y0 + 1), 0, h - 1),
+                    )
                     box[y0:y1, x0:x1] = 0
             layout[page.pageno] = box
             # 新建一个 xref 存放新指令流