diff --git a/Include/pystate.h b/Include/pystate.h --- a/Include/pystate.h +++ b/Include/pystate.h @@ -31,6 +31,7 @@ typedef struct _is { PyObject *codec_search_cache; PyObject *codec_error_registry; int codecs_initialized; + int fscodec_initialized; #ifdef HAVE_DLOPEN int dlopenflags; @@ -73,9 +74,9 @@ typedef struct _ts { struct _frame *frame; int recursion_depth; char overflowed; /* The stack has overflowed. Allow 50 more calls - to handle the runtime error. */ - char recursion_critical; /* The current calls must not cause - a stack overflow. */ + to handle the runtime error. */ + char recursion_critical; /* The current calls must not cause + a stack overflow. */ /* 'tracing' keeps track of the execution depth when tracing/profiling. This is to prevent the actual trace/profile code from being recorded in the trace/profile. */ diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c --- a/Objects/unicodeobject.c +++ b/Objects/unicodeobject.c @@ -1653,7 +1653,17 @@ PyUnicode_EncodeFSDefault(PyObject *unic PyUnicode_GET_SIZE(unicode), "surrogateescape"); #else - if (Py_FileSystemDefaultEncoding) { + PyInterpreterState *interp = PyThreadState_GET()->interp; + /* Bootstrap check: if the filesystem codec is implemented in Python, we + cannot use it to encode and decode filenames before it is loaded. Load + the Python codec requires to encode at least its own filename. Use the C + version of the locale codec until the codec registry is initialized and + the Python codec is loaded. + + Py_FileSystemDefaultEncoding is shared between all interpreters, we + cannot only rely on it: check also interp->fscodec_initialized for + subinterpreters. */ + if (Py_FileSystemDefaultEncoding && interp->fscodec_initialized) { return PyUnicode_AsEncodedString(unicode, Py_FileSystemDefaultEncoding, "surrogateescape"); @@ -1843,12 +1853,17 @@ PyUnicode_DecodeFSDefaultAndSize(const c #elif defined(__APPLE__) return PyUnicode_DecodeUTF8(s, size, "surrogateescape"); #else - /* During the early bootstrapping process, Py_FileSystemDefaultEncoding - can be undefined. If it is case, decode using UTF-8. The following assumes - that Py_FileSystemDefaultEncoding is set to a built-in encoding during the - bootstrapping process where the codecs aren't ready yet. - */ - if (Py_FileSystemDefaultEncoding) { + PyInterpreterState *interp = PyThreadState_GET()->interp; + /* Bootstrap check: if the filesystem codec is implemented in Python, we + cannot use it to encode and decode filenames before it is loaded. Load + the Python codec requires to encode at least its own filename. Use the C + version of the locale codec until the codec registry is initialized and + the Python codec is loaded. + + Py_FileSystemDefaultEncoding is shared between all interpreters, we + cannot only rely on it: check also interp->fscodec_initialized for + subinterpreters. */ + if (Py_FileSystemDefaultEncoding && interp->fscodec_initialized) { return PyUnicode_Decode(s, size, Py_FileSystemDefaultEncoding, "surrogateescape"); diff --git a/Python/pystate.c b/Python/pystate.c --- a/Python/pystate.c +++ b/Python/pystate.c @@ -79,6 +79,7 @@ PyInterpreterState_New(void) interp->codec_search_cache = NULL; interp->codec_error_registry = NULL; interp->codecs_initialized = 0; + interp->fscodec_initialized = 0; #ifdef HAVE_DLOPEN #ifdef RTLD_NOW interp->dlopenflags = RTLD_NOW; diff --git a/Python/pythonrun.c b/Python/pythonrun.c --- a/Python/pythonrun.c +++ b/Python/pythonrun.c @@ -53,7 +53,7 @@ extern grammar _PyParser_Grammar; /* Fro /* Forward */ static void initmain(void); -static void initfsencoding(void); +static int initfsencoding(PyInterpreterState *interp); static void initsite(void); static int initstdio(void); static void flush_io(void); @@ -298,7 +298,8 @@ Py_InitializeEx(int install_sigs) _PyTime_Init(); - initfsencoding(); + if (initfsencoding(interp) < 0) + Py_FatalError("Py_Initialize: unable to load the file system codec"); if (install_sigs) initsigs(); /* Signal handling stuff, including initintr() */ @@ -618,6 +619,10 @@ Py_NewInterpreter(void) Py_DECREF(pstderr); _PyImportHooks_Init(); + + if (initfsencoding(interp) < 0) + goto handle_error; + if (initstdio() < 0) Py_FatalError( "Py_Initialize: can't initialize sys standard streams"); @@ -632,7 +637,7 @@ Py_NewInterpreter(void) handle_error: /* Oops, it didn't work. Undo it all. */ - PyErr_Print(); + PyErr_PrintEx(0); PyThreadState_Clear(tstate); PyThreadState_Swap(save_tstate); PyThreadState_Delete(tstate); @@ -730,8 +735,8 @@ initmain(void) } } -static void -initfsencoding(void) +static int +initfsencoding(PyInterpreterState *interp) { PyObject *codec; #if defined(HAVE_LANGINFO_H) && defined(CODESET) @@ -748,7 +753,8 @@ initfsencoding(void) Py_FileSystemDefaultEncoding = codeset; Py_HasFileSystemDefaultEncoding = 0; - return; + interp->fscodec_initialized = 1; + return 0; } #endif @@ -758,10 +764,11 @@ initfsencoding(void) /* Such error can only occurs in critical situations: no more * memory, import a module of the standard library failed, * etc. */ - Py_FatalError("Py_Initialize: unable to load the file system codec"); - } else { - Py_DECREF(codec); + return -1; } + Py_DECREF(codec); + interp->fscodec_initialized = 1; + return 0; } /* Import the site module (not into __main__ though) */