diff --git a/Doc/Manual/Python.html b/Doc/Manual/Python.html index 45725065d..6dc0ff9ba 100644 --- a/Doc/Manual/Python.html +++ b/Doc/Manual/Python.html @@ -5962,8 +5962,8 @@ When this method is called from Python 3, the return value is the following text string:

-
->>> s = test.non_utf8_c_str()
+
+>>> s = example.non_utf8_c_str()
 >>> s
 'h\udce9llo wörld'
 

@@ -5974,7 +5974,7 @@ bytes are represented as high surrogate characters that can be used to obtain
 the original byte sequence:
 

 
-
+
 >>> b = s.encode('utf-8', errors='surrogateescape')
 >>> b
 b'h\xe9llo w\xc3\xb6rld'
@@ -5985,7 +5985,7 @@ One can then attempt a different encoding, if desired (or simply leave the
 byte string as a raw sequence of bytes for use in binary protocols):
 

 
-
+
 >>> b.decode('latin-1')
 'héllo wörld'
 

@@ -5995,7 +5995,7 @@ Note, however, that text strings containing surrogate characters are rejected
 with the default strict codec error handler. For example:
 

 
-
+
 >>> with open('test', 'w') as f:
 ...     print(s, file=f)
 ...
diff --git a/Examples/test-suite/python/unicode_strings_runme.py b/Examples/test-suite/python/unicode_strings_runme.py
index 2d26599aa..e1fc7adec 100644
--- a/Examples/test-suite/python/unicode_strings_runme.py
+++ b/Examples/test-suite/python/unicode_strings_runme.py
@@ -1,4 +1,14 @@
+import sys
+
 import unicode_strings
 
-unicode_strings.test_c_str()
-unicode_strings.test_std_string()
+# The 'u' string prefix isn't valid in Python 3.0 - 3.2 and is redundant
+# in 3.3+. Since this file is run through 2to3 before testing, though,
+# mark this as a unicode string in 2.x so it'll become a str in 3.x.
+test_string = u'h\udce9llo w\u00f6rld'
+
+if sys.version_info[0:2] >= (3, 1):
+    if unicode_strings.non_utf8_c_str() != test_string:
+        raise ValueError('Test comparison mismatch')
+    if unicode_strings.non_utf8_std_string() != test_string:
+        raise ValueError('Test comparison mismatch')
diff --git a/Examples/test-suite/unicode_strings.i b/Examples/test-suite/unicode_strings.i
index f4a8b8b50..56063c8a4 100644
--- a/Examples/test-suite/unicode_strings.i
+++ b/Examples/test-suite/unicode_strings.i
@@ -4,12 +4,12 @@
 
 %inline %{
 
-const char* test_c_str(void) {
-        return "h\xe9llo";
+const char* non_utf8_c_str(void) {
+        return "h\xe9llo w\xc3\xb6rld";
 }
 
-std::string test_std_string(void) {
-        return std::string("h\xe9llo");
+std::string non_utf8_std_string(void) {
+        return std::string("h\xe9llo w\xc3\xb6rld");
 }
 
 %}