Unit test for string containing multi-byte UTF-8

There are two tests here. One demonstrating existing, correct
behavior for `data=bytes`, and another, failing, test for the case
where `data=string` and the string contains multi-byte UTF-8.

Author: bruceadams

tests/test_requests.py

@@ -1808,6 +1808,23 @@ def test_autoset_header_values_are_native(self, httpbin):
 
         assert p.headers["Content-Length"] == length
 
+    def test_content_length_for_bytes_data(self, httpbin):
+        data = "This is a string containing multi-byte UTF-8 ☃️"
+        encoded_data = data.encode("utf-8")
+        length = str(len(encoded_data))
+        req = requests.Request("POST", httpbin("post"), data=encoded_data)
+        p = req.prepare()
+
+        assert p.headers["Content-Length"] == length
+
+    def test_content_length_for_string_data_counts_bytes(self, httpbin):
+        data = "This is a string containing multi-byte UTF-8 ☃️"
+        length = str(len(data.encode("utf-8")))
+        req = requests.Request("POST", httpbin("post"), data=data)
+        p = req.prepare()
+
+        assert p.headers["Content-Length"] == length
+
     def test_nonhttp_schemes_dont_check_URLs(self):
         test_urls = (
             "data:image/gif;base64,R0lGODlhAQABAHAAACH5BAUAAAAALAAAAAABAAEAAAICRAEAOw==",