Issue 3723: Fixed initialization of subinterpreters

The patch fixes several issues with Py_NewInterpreter as well as the demo for multiple subinterpreters.
Most of the patch was written by MvL with help from Benjamin, Amaury and me. Graham Dumpleton has verified that this patch fixes an issue with mod_wsgi.

9 files changed, 43 insertions, 3 deletions

diff --git a/Demo/embed/importexc.c b/Demo/embed/importexc.c
index 375ce1b..59b1d01 100644
--- a/Demo/embed/importexc.c
+++ b/Demo/embed/importexc.c
@@ -1,14 +1,20 @@
 #include <Python.h>
 
-char* cmd = "import exceptions";
+#if 0
+char* cmd = "import codecs, encodings.utf_8, types; print(types)";
+#else
+char* cmd = "import types; print(types)";
+#endif
 
 int main()
 {
+	printf("Initialize interpreter\n");
 	Py_Initialize();
 	PyEval_InitThreads();
 	PyRun_SimpleString(cmd);
 	Py_EndInterpreter(PyThreadState_Get());
 
+	printf("\nInitialize subinterpreter\n");
 	Py_NewInterpreter();
 	PyRun_SimpleString(cmd);
 	Py_Finalize();
diff --git a/Include/pystate.h b/Include/pystate.h
index 8508da0..e02df88 100644
--- a/Include/pystate.h
+++ b/Include/pystate.h
@@ -27,6 +27,7 @@ typedef struct _is {
     PyObject *codec_search_path;
     PyObject *codec_search_cache;
     PyObject *codec_error_registry;
+    int codecs_initialized;
 
 #ifdef HAVE_DLOPEN
     int dlopenflags;
diff --git a/Misc/NEWS b/Misc/NEWS
index 72a482e..b8d17c1 100644
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -15,6 +15,8 @@ What's New in Python 3.0 beta 5
 Core and Builtins
 -----------------
 
+- Issue 3723: Fixed initialization of subinterpreters.
+
 - Issue #4213: The file system encoding is now normalized by the
   codec subsystem, for example UTF-8 is turned into utf-8.
 
diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c
index ecd44cb..2beb098 100644
--- a/Objects/unicodeobject.c
+++ b/Objects/unicodeobject.c
@@ -1346,6 +1346,19 @@ PyObject *PyUnicode_AsEncodedString(PyObject *unicode,
 #endif
 	else if (strcmp(encoding, "ascii") == 0)
 	    return PyUnicode_AsASCIIString(unicode);
+        /* During bootstrap, we may need to find the encodings
+           package, to load the file system encoding, and require the
+           file system encoding in order to load the encodings
+           package.
+
+           Break out of this dependency by assuming that the path to
+           the encodings module is ASCII-only.  XXX could try wcstombs
+           instead, if the file system encoding is the locale's
+           encoding. */
+        else if (Py_FileSystemDefaultEncoding &&
+                 strcmp(encoding, Py_FileSystemDefaultEncoding) == 0 &&
+                 !PyThreadState_GET()->interp->codecs_initialized)
+	    return PyUnicode_AsASCIIString(unicode);            
     }
 
     /* Encode via the codec registry */
diff --git a/Python/bltinmodule.c b/Python/bltinmodule.c
index 8159fe8..d7f5084 100644
--- a/Python/bltinmodule.c
+++ b/Python/bltinmodule.c
@@ -2282,7 +2282,7 @@ static struct PyModuleDef builtinsmodule = {
 	PyModuleDef_HEAD_INIT,
 	"builtins",
 	builtin_doc,
-	0,
+	-1, /* multiple "initialization" just copies the module dict. */
 	builtin_methods,
 	NULL,
 	NULL,
diff --git a/Python/codecs.c b/Python/codecs.c
index 66576c4..ebddc09 100644
--- a/Python/codecs.c
+++ b/Python/codecs.c
@@ -869,5 +869,6 @@ static int _PyCodecRegistry_Init(void)
 	return -1;
     }
     Py_DECREF(mod);
+    interp->codecs_initialized = 1;
     return 0;
 }
diff --git a/Python/pystate.c b/Python/pystate.c
index 9479256..2a9b744 100644
--- a/Python/pystate.c
+++ b/Python/pystate.c
@@ -76,6 +76,7 @@ PyInterpreterState_New(void)
 		interp->codec_search_path = NULL;
 		interp->codec_search_cache = NULL;
 		interp->codec_error_registry = NULL;
+		interp->codecs_initialized = 0;
 #ifdef HAVE_DLOPEN
 #ifdef RTLD_NOW
                 interp->dlopenflags = RTLD_NOW;
diff --git a/Python/pythonrun.c b/Python/pythonrun.c
index 4fb2b3e..61cdf6d 100644
--- a/Python/pythonrun.c
+++ b/Python/pythonrun.c
@@ -562,8 +562,13 @@ Py_NewInterpreter(void)
 			goto handle_error;
 		Py_INCREF(interp->builtins);
 	}
+
+	/* initialize builtin exceptions */
+	_PyExc_Init();
+
 	sysmod = _PyImport_FindExtension("sys", "sys");
 	if (bimod != NULL && sysmod != NULL) {
+		PyObject *pstderr;
 		interp->sysdict = PyModule_GetDict(sysmod);
 		if (interp->sysdict == NULL)
 			goto handle_error;
@@ -571,7 +576,18 @@ Py_NewInterpreter(void)
 		PySys_SetPath(Py_GetPath());
 		PyDict_SetItemString(interp->sysdict, "modules",
 				     interp->modules);
+		/* Set up a preliminary stderr printer until we have enough
+		   infrastructure for the io module in place. */
+		pstderr = PyFile_NewStdPrinter(fileno(stderr));
+		if (pstderr == NULL)
+			Py_FatalError("Py_Initialize: can't set preliminary stderr");
+		PySys_SetObject("stderr", pstderr);
+		PySys_SetObject("__stderr__", pstderr);
+
 		_PyImportHooks_Init();
+                if (initstdio() < 0)
+                    Py_FatalError(
+                        "Py_Initialize: can't initialize sys standard streams");
 		initmain();
 		if (!Py_NoSiteFlag)
 			initsite();
diff --git a/Python/sysmodule.c b/Python/sysmodule.c
index 952f7e5..af960bc 100644
--- a/Python/sysmodule.c
+++ b/Python/sysmodule.c
@@ -1231,7 +1231,7 @@ static struct PyModuleDef sysmodule = {
 	PyModuleDef_HEAD_INIT,
 	"sys",
 	sys_doc,
-	0,
+	-1, /* multiple "initialization" just copies the module dict. */
 	sys_methods,
 	NULL,
 	NULL,