Miscs (Interro 28)

splitting_int.py

@@ -8,6 +8,9 @@ import shutil
 from pathlib import Path
 from collections import defaultdict
 
+carreau = 1000 // 38
+
+
 def decode_json(pdf_file):
     file_path = Path(pdf_file)
     with open(file_path.with_suffix(".json"), "r") as f:
@@ -26,8 +29,7 @@ def decode_json(pdf_file):
     for d in bb_list:
         (b, label) = d["box_2d"], d["label"]
         pn = page_number(b)
-        carreau = 1000 // 38
-        result.append((label, pn, b[0] - int(carreau), b[2]-int(carreau), b[1], b[3]))
+        result.append((label, pn, b[0] - carreau, b[2]-carreau, b[1], b[3]))
     result.sort(key=lambda x: (x[1], x[2]))
     return (name, result)
 
@@ -98,7 +100,7 @@ def split_an_interro(base_dir, input_pdf, coords_list):
 
         # RULE 2: Determine stopping label
         for next_item in coords_list[idx + 1:]:
-            n_clean, n_type, n_pn, n_y_start, _, _, _ = next_item
+            n_clean, n_type, n_pn, n_y_start, n_y_end, _, _ = next_item
 
             if c_type == "L":
                 is_stop = (n_type in ("L", "N"))
@@ -109,7 +111,9 @@ def split_an_interro(base_dir, input_pdf, coords_list):
 
             if is_stop:
                 end_page = n_pn
-                end_y_target_raw = n_y_start
+                # end_y_target_raw = n_y_start
+                # On avait retiré un carreau précédemment, on le rajoute…
+                end_y_target_raw = min(n_y_start + int(1.25 * carreau), 1000)
                 break
 
         # RULES 3 & 4: Calculate horizontal boundaries (0.0 to 1.0 fraction of local page width)