Merge branch 'hfalcic-master' - Python unicode surrogate escape strings

* hfalcic-master:
  unicode_strings test: manually check values instead of using assert
  unicode_strings_runme.py: fix version check
  unicode_strings test: check return values
  Python unicode_strings test case: restrict to Python > 3.0
  Python 3 'surrogateescape' docs: fix div class for Python code

Doc/Manual/Python.html

@@ -5962,8 +5962,8 @@ When this method is called from Python 3, the return value is the following
 text string:
 </p>
 
-<div class="code"><pre>
+<div class="targetlang"><pre>
-&gt;&gt;&gt; s = test.non_utf8_c_str()
+&gt;&gt;&gt; s = example.non_utf8_c_str()
 &gt;&gt;&gt; s
 'h\udce9llo w&#246;rld'
 </pre></div>
@@ -5974,7 +5974,7 @@ bytes are represented as high surrogate characters that can be used to obtain
 the original byte sequence:
 </p>
 
-<div class="code"><pre>
+<div class="targetlang"><pre>
 &gt;&gt;&gt; b = s.encode('utf-8', errors='surrogateescape')
 &gt;&gt;&gt; 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):
 </p>
 
-<div class="code"><pre>
+<div class="targetlang"><pre>
 &gt;&gt;&gt; b.decode('latin-1')
 'h&#233;llo w&#195;&#182;rld'
 </pre></div>
@@ -5995,7 +5995,7 @@ Note, however, that text strings containing surrogate characters are rejected
 with the default <tt>strict</tt> codec error handler. For example:
 </p>
 
-<div class="code"><pre>
+<div class="targetlang"><pre>
 &gt;&gt;&gt; with open('test', 'w') as f:
 ...     print(s, file=f)
 ...

Examples/test-suite/python/unicode_strings_runme.py

@@ -1,4 +1,14 @@
+import sys
+
 import unicode_strings
 
-unicode_strings.test_c_str()
+# The 'u' string prefix isn't valid in Python 3.0 - 3.2 and is redundant
-unicode_strings.test_std_string()
+# 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')

Examples/test-suite/unicode_strings.i

@@ -4,12 +4,12 @@
 
 %inline %{
 
-const char* test_c_str(void) {
+const char* non_utf8_c_str(void) {
-        return "h\xe9llo";
+        return "h\xe9llo w\xc3\xb6rld";
 }
 
-std::string test_std_string(void) {
+std::string non_utf8_std_string(void) {
-        return std::string("h\xe9llo");
+        return std::string("h\xe9llo w\xc3\xb6rld");
 }
 
 %}