Update InitialMarkups.py

InitialMarkups.py

@@ -37,8 +37,9 @@ import tsadropboxretrieval
     
         
 def changepdflinks(data_list_JSON, pdflink):
-    print('henaaaa weee',data_list_JSON)
-    
+    print("changepdflinks called with:", pdflink)
+
+    # --- Validate input format ---
     if isinstance(data_list_JSON, str):
         if data_list_JSON.strip().startswith('['):
             try:
@@ -50,31 +51,55 @@ def changepdflinks(data_list_JSON, pdflink):
     elif not isinstance(data_list_JSON, list):
         raise ValueError(f"Input must be JSON string or list, got {type(data_list_JSON)}")
 
-    # Loop through all entries and update their NBSLink
+    # --- Normalize the incoming PDF link (avoid double-encoding) ---
+    pdflink = pdflink.strip()
+    # If somehow encoded multiple times, decode until stable
+    prev = None
+    decoded = pdflink
+    while decoded != prev:
+        prev = decoded
+        decoded = urllib.parse.unquote(decoded)
+    safe_pdf_link = decoded
+
+    # --- Update each entry ---
     for entry in data_list_JSON:
         old_url = entry.get("NBSLink", "")
+        if not old_url:
+            continue
 
-        # Parse URL and query params
         parsed = urllib.parse.urlparse(old_url)
         query = urllib.parse.parse_qs(parsed.query)
 
-        # Replace only the 'pdfLink' parameter if present
+        # Only replace the pdfLink parameter
         if "pdfLink" in query:
-            query["pdfLink"] = [pdflink]
+            query["pdfLink"] = [safe_pdf_link]
+
+        # Rebuild query manually to avoid double encoding
+        query_parts = []
+        for key, values in query.items():
+            for value in values:
+                if key == "pdfLink":
+                    query_parts.append(f"{key}={value}")
+                else:
+                    query_parts.append(f"{key}={urllib.parse.quote_plus(value)}")
 
-            # Rebuild query string
-            new_query = urllib.parse.urlencode(query, doseq=True)
+        new_query = "&".join(query_parts)
 
-            # Rebuild full URL with the same fragment (page/zoom)
-            new_url = f"{parsed.scheme}://{parsed.netloc}{parsed.path}?{new_query}"
-            if parsed.fragment:
-                new_url += f"#{parsed.fragment}"
+        # Preserve everything else
+        new_url = f"{parsed.scheme}://{parsed.netloc}{parsed.path}"
+        if new_query:
+            new_url += f"?{new_query}"
+        if parsed.fragment:
+            new_url += f"#{parsed.fragment}"
 
-            # Update the entry
-            entry["NBSLink"] = new_url
+        entry["NBSLink"] = new_url
 
-    return data_list_JSON
+        # Debugging
+        print("\n--- URL Update ---")
+        print("OLD:", old_url)
+        print("NEW:", new_url)
 
+    return data_list_JSON
 def get_regular_font_size_and_color(doc):
     font_sizes = []
     colors = []