Update InitialMarkups.py

InitialMarkups.py

@@ -34,23 +34,18 @@ from fuzzywuzzy import fuzz
 import copy
 import tsadropboxretrieval
 
-  
 
 def changepdflinks(data_list_JSON, pdflink):
-    print("changepdflinks called with:", pdflink)
-
+    print('Received JSON:', data_list_JSON)
+    
+    # Ensure it's a list of dicts
     if isinstance(data_list_JSON, str):
-        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.strip()
-
-    # Re-encode ONCE for embedding in ?pdfLink=
-    encoded_pdf_link = urllib.parse.quote(safe_pdf_link, safe='')
+        try:
+            data_list_JSON = json.loads(data_list_JSON)
+        except json.JSONDecodeError:
+            raise ValueError(f"Invalid JSON string passed: {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)}")
 
     for entry in data_list_JSON:
         old_url = entry.get("NBSLink", "")
@@ -60,30 +55,20 @@ def changepdflinks(data_list_JSON, pdflink):
         parsed = urllib.parse.urlparse(old_url)
         query = urllib.parse.parse_qs(parsed.query)
 
-        # Replace pdfLink safely
+        # Replace only if present
         if "pdfLink" in query:
-            query["pdfLink"] = [encoded_pdf_link]
-
-        # Rebuild query with proper escaping for all other params
-        query_parts = []
-        for key, values in query.items():
-            for value in values:
-                query_parts.append(f"{key}={value}")
+            # Decode old link for readability
+            decoded_pdf_link = urllib.parse.unquote(query["pdfLink"][0])
+            
+            # Assign the new one (encode once)
+            query["pdfLink"] = [urllib.parse.quote(pdflink, safe=":/")]
 
-        new_query = "&".join(query_parts)
-
-        new_url = f"{parsed.scheme}://{parsed.netloc}{parsed.path}?{new_query}"
-        if parsed.fragment:
-            new_url += f"#{parsed.fragment}"
-
-        entry["NBSLink"] = new_url
-
-        print("\n--- URL Update ---")
-        print("OLD:", old_url)
-        print("NEW:", new_url)
+            new_query = urllib.parse.urlencode(query, doseq=True)
+            new_url = urllib.parse.urlunparse(parsed._replace(query=new_query))
+            entry["NBSLink"] = new_url
 
     return data_list_JSON
- 
+
 
 def get_regular_font_size_and_color(doc):
     font_sizes = []