Update InitialMarkups.py

InitialMarkups.py

@@ -34,34 +34,24 @@ from fuzzywuzzy import fuzz
 import copy
 import tsadropboxretrieval
 
-    
-        
+  
+
 def changepdflinks(data_list_JSON, pdflink):
     print("changepdflinks called with:", pdflink)
 
-    # --- Validate input format ---
     if isinstance(data_list_JSON, str):
-        if data_list_JSON.strip().startswith('['):
-            try:
-                data_list_JSON = json.loads(data_list_JSON)
-            except json.JSONDecodeError:
-                raise ValueError(f"Invalid JSON string passed: {data_list_JSON[:200]}")
-        else:
-            raise ValueError(f"Expected JSON string but got something else: {data_list_JSON[:200]}")
-    elif not isinstance(data_list_JSON, list):
-        raise ValueError(f"Input must be JSON string or list, got {type(data_list_JSON)}")
-
-    # --- Normalize the incoming PDF link (avoid double-encoding) ---
-    pdflink = pdflink.strip()
-    # If somehow encoded multiple times, decode until stable
-    prev = None
-    decoded = pdflink
+        data_list_JSON = json.loads(data_list_JSON)
+
+    # Normalize link (decode if double-encoded)
+    prev, decoded = None, pdflink
     while decoded != prev:
         prev = decoded
         decoded = urllib.parse.unquote(decoded)
-    safe_pdf_link = decoded
+    safe_pdf_link = decoded.strip()
+
+    # Re-encode ONCE for embedding in ?pdfLink=
+    encoded_pdf_link = urllib.parse.quote(safe_pdf_link, safe='')
 
-    # --- Update each entry ---
     for entry in data_list_JSON:
         old_url = entry.get("NBSLink", "")
         if not old_url:
@@ -70,36 +60,31 @@ def changepdflinks(data_list_JSON, pdflink):
         parsed = urllib.parse.urlparse(old_url)
         query = urllib.parse.parse_qs(parsed.query)
 
-        # Only replace the pdfLink parameter
+        # Replace pdfLink safely
         if "pdfLink" in query:
-            query["pdfLink"] = [safe_pdf_link]
+            query["pdfLink"] = [encoded_pdf_link]
 
-        # Rebuild query manually to avoid double encoding
+        # Rebuild query with proper escaping for all other params
         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)}")
+                query_parts.append(f"{key}={value}")
 
         new_query = "&".join(query_parts)
 
-        # Preserve everything else
-        new_url = f"{parsed.scheme}://{parsed.netloc}{parsed.path}"
-        if new_query:
-            new_url += f"?{new_query}"
+        new_url = f"{parsed.scheme}://{parsed.netloc}{parsed.path}?{new_query}"
         if parsed.fragment:
             new_url += f"#{parsed.fragment}"
 
         entry["NBSLink"] = new_url
 
-        # 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 = []