Initial Persp generation

utils.py

@@ -34,6 +34,43 @@ def pdf_image_of_solution(root_dir, label):
     if os.path.exists(pdf_path):
         return pdf_path
 
+def pdf_images_of_contexts(root_dir, label, all_labels):
+    text2_dir = os.path.join(root_dir, "Text2")
+    if not os.path.isdir(text2_dir):
+        return []
+
+    # Map safe labels (with '/' replaced by '_') to their chronological index
+    safe_to_idx = {l.replace("/", "_"): i for i, l in enumerate(all_labels)}
+
+    safe_target = label.replace("/", "_")
+    target_idx = safe_to_idx.get(safe_target, -1)
+
+    if target_idx == -1:
+        return []
+
+    pertinent_contexts = []
+
+    for filename in os.listdir(text2_dir):
+        if filename.startswith("CTXT ") and filename.endswith(".pdf"):
+            # Extract "first_label -> last_label" from "CTXT first_label -> last_label.pdf"
+            core = filename[5:-4]
+            parts = core.split(" -> ")
+
+            if len(parts) == 2:
+                first_safe, last_safe = parts
+                first_idx = safe_to_idx.get(first_safe, -1)
+                last_idx = safe_to_idx.get(last_safe, -1)
+
+                # Check if the current label falls within the context's validity range
+                if first_idx != -1 and last_idx != -1:
+                    if first_idx <= target_idx <= last_idx:
+                        pdf_path = os.path.join(text2_dir, filename)
+                        pertinent_contexts.append((first_idx, pdf_path))
+
+    # Sort by first_idx to ensure contexts are returned in logical reading order
+    pertinent_contexts.sort(key=lambda x: x[0])
+    return [path for _, path in pertinent_contexts]    
+
 
 def get_exam_file_content(folder_path, mode, label):
     """