Fix the wrong Content-Length in python-server.py for non-ascii charac…

…ters. (#24480)

Resolves: #24479

`python-server.py` currently uses `sys.stdin.read` for reading the
input, and it receives the length in `str` (utf-8 string).
ref: https://docs.python.org/3/library/sys.html

On the other "Content-Length" is the size in **bytes**, therefore we
should not pass `content_length` to `sys.stdin.read`. For example,
`print("こんにちは世界")`'s length is 16 in str, but 30 in bytes.

```
>>> len('print("こんにちは世界")')
16
>>> len('print("こんにちは世界")'.encode())
30
```

This PR have two changes.
1. Replace `sys.stdin.read(content_length)` with
`sys.stdin.buffer.read(content_length).decode()`.
2. Make `_send_message` calculate "Content-Length" from bytes, not str.

By these changes, original issue
#24479 can be resolved.


![image](https://github.com/user-attachments/assets/20e72a26-d4ad-4e16-9c5b-ed41055c95d9)

python_files/python_server.py

@@ -14,7 +14,8 @@
 
 
 def _send_message(msg: str):
-    length_msg = len(msg)
+    # Content-Length is the data size in bytes.
+    length_msg = len(msg.encode())
     STDOUT.buffer.write(f"Content-Length: {length_msg}\r\n\r\n{msg}".encode())
     STDOUT.buffer.flush()
 
@@ -55,10 +56,11 @@ def custom_input(prompt=""):
     try:
         send_request({"prompt": prompt})
         headers = get_headers()
+        # Content-Length is the data size in bytes.
         content_length = int(headers.get("Content-Length", 0))
 
         if content_length:
-            message_text = STDIN.read(content_length)
+            message_text = STDIN.buffer.read(content_length).decode()
             message_json = json.loads(message_text)
             return message_json["result"]["userInput"]
     except Exception:
@@ -74,10 +76,11 @@ def handle_response(request_id):
     while not STDIN.closed:
         try:
             headers = get_headers()
+            # Content-Length is the data size in bytes.
             content_length = int(headers.get("Content-Length", 0))
 
             if content_length:
-                message_text = STDIN.read(content_length)
+                message_text = STDIN.buffer.read(content_length).decode()
                 message_json = json.loads(message_text)
                 our_user_input = message_json["result"]["userInput"]
                 if message_json["id"] == request_id:
@@ -160,7 +163,7 @@ def get_value(self) -> str:
 def get_headers():
     headers = {}
     while True:
-        line = STDIN.readline().strip()
+        line = STDIN.buffer.readline().decode().strip()
         if not line:
             break
         name, value = line.split(":", 1)
@@ -172,10 +175,11 @@ def get_headers():
     while not STDIN.closed:
         try:
             headers = get_headers()
+            # Content-Length is the data size in bytes.
             content_length = int(headers.get("Content-Length", 0))
 
             if content_length:
-                request_text = STDIN.read(content_length)
+                request_text = STDIN.buffer.read(content_length).decode()
                 request_json = json.loads(request_text)
                 if request_json["method"] == "execute":
                     execute(request_json, USER_GLOBALS)