Faster annotating : 2 threads

annotating.py

@@ -385,9 +385,10 @@ def compose_label_image(base_img, label, result, hmin,
 def natural_key(text):
     return [int(c) if c.isdigit() else c.lower() for c in re.split(r'(\d+)', str(text))]
 
+import concurrent.futures
 
-def process_correction(root_dir, data, all_labels, overwrite=False):
-    for student_id, labels in data.items():
+def process_student(student_id, labels_data, root_dir, all_labels, overwrite):
+    """Helper function to process a single student."""
 
     # Prepare output directory: Dir/Anot_CopieID
     output_dir = os.path.join(root_dir, "Anot", f"Copie{student_id}")
@@ -396,7 +397,7 @@ def process_correction(root_dir, data, all_labels, overwrite=False):
     concat_path = os.path.join(output_dir, "Concat.jpg")
     if os.path.exists(concat_path) and not overwrite:
         print(f"Skipping Copie {student_id} (Concat.jpg exists)")
-            continue
+        return
 
     print("Processing :", student_id)
 
@@ -405,12 +406,12 @@ def process_correction(root_dir, data, all_labels, overwrite=False):
         shutil.rmtree(output_dir)
     os.makedirs(output_dir)
 
-        d_notes = dict.fromkeys(all_labels,"")
+    d_notes = dict.fromkeys(all_labels, "")
     label_images = []
 
-        labels = sorted(list(labels.items()), key=natural_key)
+    sorted_labels = sorted(list(labels_data.items()), key=natural_key)
 
-        for label, content in labels:
+    for label, content in sorted_labels:
         # 1. Find PDF path
         copie_folder = f"Copie{student_id}"
         pdf_rel_path = os.path.join(copie_folder, f"{label}.pdf")
@@ -454,6 +455,19 @@ def process_correction(root_dir, data, all_labels, overwrite=False):
             cy += img.height
         canvas.save(concat_path)
 
+
+def process_correction(root_dir, data, all_labels, overwrite=False):
+    with concurrent.futures.ThreadPoolExecutor(max_workers=2) as executor:
+        # Create a list of futures
+        futures = []
+        for student_id, labels in sorted(data.items()):
+            futures.append(
+                executor.submit(process_student, student_id, labels, root_dir, all_labels, overwrite)
+            )
+
+        # Wait for all threads to complete
+        concurrent.futures.wait(futures)
+
 import argparse
 if __name__ == "__main__":
     parser = argparse.ArgumentParser(description="Annotate copies")