update

app.py

@@ -39,7 +39,13 @@ from vocab import all_tokenizers
 from util import *
 from examples import example_fn
 
-
+get_window_url_params = """
+    function(url_params) {
+        const params = new URLSearchParams(window.location.search);
+        url_params = JSON.stringify(Object.fromEntries(params));
+        return url_params;
+        }
+    """
 
 with gr.Blocks(css="css/style.css", title="Tokenizer Arena") as demo:
     gr.HTML("""<h1 align="center">Tokenizer Arena ⚔️</h1>""")
@@ -175,8 +181,9 @@ with gr.Blocks(css="css/style.css", title="Tokenizer Arena") as demo:
     demo.load(_js=open("js/onload.js", "r", encoding="utf-8").read())
     demo.load(
         fn=on_load,
-        inputs=None,
+        inputs=[user_input],  # 这里只需要传个空object即可。
         outputs=[user_input, tokenizer_type_1, tokenizer_type_2],
+        _js=get_window_url_params
     )
 
 

util.py

@@ -109,29 +109,39 @@ default_tokenizer_type_1 = "llama"
 default_tokenizer_type_2 = "gpt_35_turbo"
 
 
-def on_load(request: gr.Request):
+def on_load(url_params, request: gr.Request):
     """
     onLoad
     """
+
     text = None
     tokenizer_type_1 = None
     tokenizer_type_2 = None
-    query_params = {}
+    try:
+        url_params = json.loads(url_params)
+    except:
+        url_params = {}
     if request:
-        logger.info(str(request.headers))
+        try:
+            logger.info(str(request.headers))
+            logger.info(str(request.query_params))
+        except:
+            pass
         client_ip = request.client.host
         # local_ip = socket.gethostbyname(socket.gethostbyname(""))
         # headers = request.kwargs['headers']
         # if headers and 'x-forwarded-for' in headers:
         #     x_forwarded_for = headers['x-forwarded-for']
         #     client_ip = x_forwarded_for.split(' ')[0] if x_forwarded_for else ""
-        if "referer" in request.headers:
-            query_params = parse_qs(urlparse(request.headers["referer"]).query)
-            query_params = {k: v[0] for k, v in query_params.items() if len(v) > 0}
-        tokenizer_type_1 = query_params.get("tokenizer1", default_tokenizer_type_1)
-        tokenizer_type_2 = query_params.get("tokenizer2", default_tokenizer_type_2)
-        text = query_params.get("text", default_user_input)
-        logger.info(f"client_ip: {client_ip}; params: {query_params}")
+        # if "referer" in request.headers:   # not work for huggingface-space
+        #     url_params = parse_qs(urlparse(request.headers["referer"]).query)
+        #     url_params = {k: v[0] for k, v in url_params.items() if len(v) > 0}
+        tokenizer_type_1 = url_params.get("tokenizer1", default_tokenizer_type_1)
+        tokenizer_type_2 = url_params.get("tokenizer2", default_tokenizer_type_2)
+        text = url_params.get("text", default_user_input)
+
+
+        logger.info(f"client_ip: {client_ip}; params: {url_params}")
     return text, tokenizer_type_1, tokenizer_type_2