Update InitialMarkups.py

InitialMarkups.py

@@ -34,11 +34,12 @@ from fuzzywuzzy import fuzz
 import copy
 import tsadropboxretrieval
 
+import json, urllib.parse, copy
 
 def changepdflinks(data_list_JSON, pdflink):
     print('Received JSON:', data_list_JSON)
     
-    # Ensure it's a list of dicts
+    # Ensure list of dicts
     if isinstance(data_list_JSON, str):
         try:
             data_list_JSON = json.loads(data_list_JSON)
@@ -47,29 +48,34 @@ 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)}")
 
+    # Work on a safe copy
+    data_list_JSON = copy.deepcopy(data_list_JSON)
+
     for entry in data_list_JSON:
         old_url = entry.get("NBSLink", "")
         if not old_url:
             continue
 
         parsed = urllib.parse.urlparse(old_url)
-        query = urllib.parse.parse_qs(parsed.query)
-
-        # Replace only if present
-        if "pdfLink" in query:
-            # 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 = urllib.parse.urlencode(query, doseq=True)
-            new_url = urllib.parse.urlunparse(parsed._replace(query=new_query))
-            entry["NBSLink"] = new_url
+        # Extract page/zoom fragment (if present)
+        fragment = parsed.fragment  # e.g. "page=3&zoom=150"
+        print(fragment)
+        # Encode the new pdf link safely
+        encoded_pdf = urllib.parse.quote(pdflink, safe=":/?=&")
 
+        # Construct the new final link: encoded pdf link + old fragment
+        if fragment:
+            new_url = f"{encoded_pdf}#{fragment}"
+        else:
+            new_url = encoded_pdf
+        print(newurl)
+        entry["NBSLink"] = 'https://findconsole-initialmarkups.hf.space/view-pdf?pdfLink='+new_url
+        print(entry["NBSLink"] )
     return data_list_JSON
 
 
+
 def get_regular_font_size_and_color(doc):
     font_sizes = []
     colors = []