Fix T47856: Cycles problem when running from multi-byte path

This is a mix of regression and old unsupported configuration.

Regression was caused by some checks added on Blender side which was
checking whether python function returned error or not. This made it
impossible to enable Cycles when running from a file path which can't
be encoded with MBCS codepage.

Non-regression issue was that it wasn't possible to use pre-compiled
CUDA kernels when running from a path with non-ascii multi-byte
characters.

This commit fixes regression and CUDA parts, but OSL still can't be
used from a non-ascii location because it uses non-widechar API to
work with file paths by the looks of it. Not sure we can solve this
just from our side by using some codepage trick (UTF-16?) since even
oslc fails to compile shader when there are non-ascii characters in
the path.

intern/cycles/blender/blender_python.cpp

@@ -138,19 +138,29 @@ void python_thread_state_restore(void **python_thread_state)
 
 static const char *PyC_UnicodeAsByte(PyObject *py_str, PyObject **coerce)
 {
-#ifdef WIN32
+	const char *result = _PyUnicode_AsString(py_str);
-	/* bug [#31856] oddly enough, Python3.2 --> 3.3 on Windows will throw an
+	if(result) {
-	 * exception here this needs to be fixed in python:
+		/* 99% of the time this is enough but we better support non unicode
-	 * see: bugs.python.org/issue15859 */
+		 * chars since blender doesnt limit this.
-	if(!PyUnicode_Check(py_str)) {
+		 */
-		PyErr_BadArgument();
+		return result;
-		return "";
 	}
-#endif
+	else {
-	if((*coerce = PyUnicode_EncodeFSDefault(py_str))) {
+		PyErr_Clear();
-		return PyBytes_AS_STRING(*coerce);
+		if(PyBytes_Check(py_str)) {
+			return PyBytes_AS_STRING(py_str);
+		}
+		else if((*coerce = PyUnicode_EncodeFSDefault(py_str))) {
+			return PyBytes_AS_STRING(*coerce);
+		}
+		else {
+			/* Clear the error, so Cycles can be at leadt used without
+			 * GPU and OSL support,
+			 */
+			PyErr_Clear();
+			return "";
+		}
 	}
-	return "";
 }
 
 static PyObject *init_func(PyObject * /*self*/, PyObject *args)

intern/cycles/render/osl.cpp

@@ -202,13 +202,26 @@ void OSLShaderManager::shading_system_init()
 	if(ss_shared_users == 0) {
 		services_shared = new OSLRenderServices();
 
+		string shader_path = path_get("shader");
+#ifdef _WIN32
+		/* Annoying thing, Cycles stores paths in UTF-8 codepage, so it can
+		 * operate with file paths with any character. This requires to use wide
+		 * char functions, but OSL uses old fashioned ANSI functions which means:
+		 *
+		 * - We have to convert our paths to ANSI before passing to OSL
+		 * - OSL can't be used when there's a multi-byte character in the path
+		 *   to the shaders folder.
+		 */
+		shader_path = string_to_ansi(shader_path);
+#endif
+
 		ss_shared = new OSL::ShadingSystem(services_shared, ts_shared, &errhandler);
 		ss_shared->attribute("lockgeom", 1);
 		ss_shared->attribute("commonspace", "world");
-		ss_shared->attribute("searchpath:shader", path_get("shader"));
+		ss_shared->attribute("searchpath:shader", shader_path);
 		ss_shared->attribute("greedyjit", 1);
 
-		VLOG(1) << "Using shader search path: " << path_get("shader");
+		VLOG(1) << "Using shader search path: " << shader_path;
 
 		/* our own ray types */
 		static const char *raytypes[] = {

intern/cycles/util/util_path.cpp

@@ -56,7 +56,6 @@ typedef struct _stat path_stat_t;
 #  ifndef S_ISDIR
 #    define S_ISDIR(x) (((x) & _S_IFDIR) == _S_IFDIR)
 #  endif
-#  define mkdir(path, mode) _mkdir(path)
 #else
 typedef struct stat path_stat_t;
 #endif
@@ -626,7 +625,12 @@ static bool create_directories_recursivey(const string& path)
 		}
 	}
 
+#ifdef _WIN32
+	wstring path_wc = string_to_wstring(path);
+	return _wmkdir(path_wc.c_str()) == 0;
+#else
 	return mkdir(path.c_str(), 0777) == 0;
+#endif
 }
 
 void path_create_directories(const string& filepath)
@@ -745,7 +749,13 @@ string path_source_replace_includes(const string& source_, const string& path)
 
 FILE *path_fopen(const string& path, const string& mode)
 {
+#ifdef _WIN32
+	wstring path_wc = string_to_wstring(path);
+	wstring mode_wc = string_to_wstring(mode);
+	return _wfopen(path_wc.c_str(), mode_wc.c_str());
+#else
 	return fopen(path.c_str(), mode.c_str());
+#endif
 }
 
 void path_cache_clear_except(const string& name, const set<string>& except)

intern/cycles/util/util_string.cpp

@@ -165,14 +165,14 @@ string string_from_bool(bool var)
 
 wstring string_to_wstring(const string& str)
 {
-	const int length_wc = MultiByteToWideChar(CP_ACP,
+	const int length_wc = MultiByteToWideChar(CP_UTF8,
 	                                          0,
 	                                          str.c_str(),
 	                                          str.length(),
 	                                          NULL,
 	                                          0);
 	wstring str_wc(length_wc, 0);
-	MultiByteToWideChar(CP_ACP,
+	MultiByteToWideChar(CP_UTF8,
 	                    0,
 	                    str.c_str(),
 	                    str.length(),
@@ -183,7 +183,7 @@ wstring string_to_wstring(const string& str)
 
 string string_from_wstring(const wstring& str)
 {
-	int length_mb = WideCharToMultiByte(CP_ACP,
+	int length_mb = WideCharToMultiByte(CP_UTF8,
 	                                    0,
 	                                    str.c_str(),
 	                                    str.size(),
@@ -191,7 +191,7 @@ string string_from_wstring(const wstring& str)
 	                                    0,
 	                                    NULL, NULL);
 	string str_mb(length_mb, 0);
-	WideCharToMultiByte(CP_ACP,
+	WideCharToMultiByte(CP_UTF8,
 	                    0,
 	                    str.c_str(),
 	                    str.size(),
@@ -201,6 +201,42 @@ string string_from_wstring(const wstring& str)
 	return str_mb;
 }
 
+string string_to_ansi(const string& str)
+{
+	const int length_wc = MultiByteToWideChar(CP_UTF8,
+	                                          0,
+	                                          str.c_str(),
+	                                          str.length(),
+	                                          NULL,
+	                                          0);
+	wstring str_wc(length_wc, 0);
+	MultiByteToWideChar(CP_UTF8,
+	                    0,
+	                    str.c_str(),
+	                    str.length(),
+	                    &str_wc[0],
+	                    length_wc);
+
+	int length_mb = WideCharToMultiByte(CP_ACP,
+	                                    0,
+	                                    str_wc.c_str(),
+	                                    str_wc.size(),
+	                                    NULL,
+	                                    0,
+	                                    NULL, NULL);
+
+	string str_mb(length_mb, 0);
+	WideCharToMultiByte(CP_ACP,
+	                    0,
+	                    str_wc.c_str(),
+	                    str_wc.size(),
+	                    &str_mb[0],
+	                    length_mb,
+	                    NULL, NULL);
+
+	return str_mb;
+}
+
 #endif  /* _WIN32 */
 
 CCL_NAMESPACE_END

intern/cycles/util/util_string.h

@@ -50,11 +50,16 @@ string string_from_bool(const bool var);
 /* Wide char strings are only used on Windows to deal with non-ascii
  * characters in file names and such. No reason to use such strings
  * for something else at this moment.
+ *
+ * Please note that strings are expected to be in UTF-8 codepage, and
+ * if ANSI is needed then explicit conversion required.
+ *
  */
 #ifdef _WIN32
 using std::wstring;
 wstring string_to_wstring(const string& path);
 string string_from_wstring(const wstring& path);
+string string_to_ansi(const string& str);
 #endif
 
 CCL_NAMESPACE_END