From dfea8a16242e43037025de18acbe1218ac002bb9 Mon Sep 17 00:00:00 2001
From: Kyle Larose <kyle@agilicus.com>
Date: Thu, 30 Mar 2023 10:48:52 -0400
Subject: [PATCH] handle invalid characeters in encoding

When establishing a connection to an SSH server, WebSSH tries to guess
at its encoding using a command sent prior to opening the terminal.
Unfortunately, sometimes this can return data which does not form proper
input for the `encode` function used by `is_valid_encoding` to test
whether the encoding is known.

In particular, we ran in to a case where the server was returning a
string which had a \0 in it when converted to ascii. That raised a
`ValueError` (as opposed to `LookupError`), which was uncaught.

Handle the `ValueError` case as well, treating it as an unknown encoding
so that we fall back on the default.
---
 tests/test_handler.py | 25 ++++++++++++++++++++++++-
 webssh/utils.py       |  2 ++
 2 files changed, 26 insertions(+), 1 deletion(-)

diff --git a/tests/test_handler.py b/tests/test_handler.py
index 2f30d9d..a9ad924 100644
--- a/tests/test_handler.py
+++ b/tests/test_handler.py
@@ -1,3 +1,4 @@
+import io
 import unittest
 import paramiko
 
@@ -7,7 +8,7 @@ from tests.utils import read_file, make_tests_data_path
 from webssh import handler
 from webssh import worker
 from webssh.handler import (
-    MixinHandler, WsockHandler, PrivateKey, InvalidValueError
+    IndexHandler, MixinHandler, WsockHandler, PrivateKey, InvalidValueError, SSHClient
 )
 
 try:
@@ -315,3 +316,25 @@ class TestWsockHandler(unittest.TestCase):
         obj.worker_ref = ref
         WsockHandler.on_message(obj, b'{"data": "somestuff"}')
         obj.close.assert_called_with(reason='Worker closed')
+
+class TestIndexHandler(unittest.TestCase):
+    def test_null_in_encoding(self):
+        handler = Mock(spec=IndexHandler)
+
+        # This is a little nasty, but the index handler has a lot of
+        # dependencies to mock. Mocking out everything but the bits
+        # we want to test lets us test this case without needing to
+        # refactor the relevant code out of IndexHandler
+        def parse_encoding(data):
+            return IndexHandler.parse_encoding(handler, data)
+        handler.parse_encoding = parse_encoding
+
+        ssh = Mock(spec=SSHClient)
+        stdin = io.BytesIO()
+        stdout = io.BytesIO(initial_bytes=b"UTF-8\0")
+        stderr = io.BytesIO()
+        ssh.exec_command.return_value = (stdin, stdout, stderr)
+
+        encoding = IndexHandler.get_default_encoding(handler, ssh)
+        self.assertEquals("utf-8", encoding)
+
diff --git a/webssh/utils.py b/webssh/utils.py
index 845ca56..454b1cf 100644
--- a/webssh/utils.py
+++ b/webssh/utils.py
@@ -59,6 +59,8 @@ def is_valid_encoding(encoding):
         u'test'.encode(encoding)
     except LookupError:
         return False
+    except ValueError:
+        return False
     return True