Unverified Kaydet (Commit) 9e4994d4 authored tarafından Victor Stinner's avatar Victor Stinner Kaydeden (comit) GitHub

bpo-34485: Enhance init_sys_streams() (GH-8978)

Python now gets the locale encoding with C code to initialize the encoding
of standard streams like sys.stdout. Moreover, the encoding is now
initialized to the Python codec name to get a normalized encoding name and
to ensure that the codec is loaded. The change avoids importing
_bootlocale and _locale modules at startup by default.

When the PYTHONIOENCODING environment variable only contains an encoding,
the error handler is now is now set explicitly to "strict".

Rename also get_default_standard_stream_error_handler() to
get_stdio_errors().

Reduce the buffer to format the "cpXXX" string (Windows locale encoding).
üst d500e530
......@@ -171,17 +171,17 @@ class EmbeddingTests(EmbeddingTestsMixin, unittest.TestCase):
"stdout: {out_encoding}:ignore",
"stderr: {out_encoding}:backslashreplace",
"--- Set encoding only ---",
"Expected encoding: latin-1",
"Expected encoding: iso8859-1",
"Expected errors: default",
"stdin: latin-1:{errors}",
"stdout: latin-1:{errors}",
"stderr: latin-1:backslashreplace",
"stdin: iso8859-1:{errors}",
"stdout: iso8859-1:{errors}",
"stderr: iso8859-1:backslashreplace",
"--- Set encoding and errors ---",
"Expected encoding: latin-1",
"Expected encoding: iso8859-1",
"Expected errors: replace",
"stdin: latin-1:replace",
"stdout: latin-1:replace",
"stderr: latin-1:backslashreplace"])
"stdin: iso8859-1:replace",
"stdout: iso8859-1:replace",
"stderr: iso8859-1:backslashreplace"])
expected_output = expected_output.format(
in_encoding=expected_stream_encoding,
out_encoding=expected_stream_encoding,
......
......@@ -668,7 +668,7 @@ class SysModuleTest(unittest.TestCase):
'dump("stdout")',
'dump("stderr")',
))
args = [sys.executable, "-c", code]
args = [sys.executable, "-X", "utf8=0", "-c", code]
if isolated:
args.append("-I")
if encoding is not None:
......@@ -712,8 +712,8 @@ class SysModuleTest(unittest.TestCase):
# have no any effect
out = self.c_locale_get_error_handler(encoding=':')
self.assertEqual(out,
'stdin: strict\n'
'stdout: strict\n'
'stdin: surrogateescape\n'
'stdout: surrogateescape\n'
'stderr: backslashreplace\n')
out = self.c_locale_get_error_handler(encoding='')
self.assertEqual(out,
......
......@@ -139,16 +139,16 @@ class UTF8ModeTests(unittest.TestCase):
out = self.get_output('-X', 'utf8', '-c', code,
PYTHONIOENCODING="latin1")
self.assertEqual(out.splitlines(),
['stdin: latin1/strict',
'stdout: latin1/strict',
'stderr: latin1/backslashreplace'])
['stdin: iso8859-1/strict',
'stdout: iso8859-1/strict',
'stderr: iso8859-1/backslashreplace'])
out = self.get_output('-X', 'utf8', '-c', code,
PYTHONIOENCODING=":namereplace")
self.assertEqual(out.splitlines(),
['stdin: UTF-8/namereplace',
'stdout: UTF-8/namereplace',
'stderr: UTF-8/backslashreplace'])
['stdin: utf-8/namereplace',
'stdout: utf-8/namereplace',
'stderr: utf-8/backslashreplace'])
def test_io(self):
code = textwrap.dedent('''
......
Python now gets the locale encoding with C code to initialize the encoding
of standard streams like sys.stdout. Moreover, the encoding is now
initialized to the Python codec name to get a normalized encoding name and
to ensure that the codec is loaded. The change avoids importing _bootlocale
and _locale modules at startup by default.
Fix the error handler of standard streams like sys.stdout:
PYTHONIOENCODING=":" is now ignored instead of setting the error handler to
"strict".
......@@ -319,7 +319,7 @@ exit:
static PyObject*
PyLocale_getdefaultlocale(PyObject* self, PyObject *Py_UNUSED(ignored))
{
char encoding[100];
char encoding[20];
char locale[100];
PyOS_snprintf(encoding, sizeof(encoding), "cp%d", GetACP());
......
......@@ -113,9 +113,9 @@ static int test_forced_io_encoding(void)
printf("--- Set errors only ---\n");
check_stdio_details(NULL, "ignore");
printf("--- Set encoding only ---\n");
check_stdio_details("latin-1", NULL);
check_stdio_details("iso8859-1", NULL);
printf("--- Set encoding and errors ---\n");
check_stdio_details("latin-1", "replace");
check_stdio_details("iso8859-1", "replace");
/* Check calling after initialization fails */
Py_Initialize();
......
......@@ -244,22 +244,26 @@ error:
return NULL;
}
static char*
get_locale_encoding(void)
static _PyInitError
get_locale_encoding(char **locale_encoding)
{
#if defined(HAVE_LANGINFO_H) && defined(CODESET)
char* codeset = nl_langinfo(CODESET);
if (!codeset || codeset[0] == '\0') {
PyErr_SetString(PyExc_ValueError, "CODESET is not set or empty");
return NULL;
}
return get_codec_name(codeset);
#ifdef MS_WINDOWS
char encoding[20];
PyOS_snprintf(encoding, sizeof(encoding), "cp%d", GetACP());
#elif defined(__ANDROID__)
return get_codec_name("UTF-8");
const char *encoding = "UTF-8";
#else
PyErr_SetNone(PyExc_NotImplementedError);
return NULL;
const char *encoding = nl_langinfo(CODESET);
if (!encoding || encoding[0] == '\0') {
return _Py_INIT_USER_ERR("failed to get the locale encoding: "
"nl_langinfo(CODESET) failed");
}
#endif
*locale_encoding = _PyMem_RawStrdup(encoding);
if (*locale_encoding == NULL) {
return _Py_INIT_NO_MEMORY();
}
return _Py_INIT_OK();
}
static _PyInitError
......@@ -397,7 +401,7 @@ static _LocaleCoercionTarget _TARGET_LOCALES[] = {
};
static const char *
get_default_standard_stream_error_handler(void)
get_stdio_errors(void)
{
const char *ctype_loc = setlocale(LC_CTYPE, NULL);
if (ctype_loc != NULL) {
......@@ -417,8 +421,7 @@ get_default_standard_stream_error_handler(void)
#endif
}
/* Otherwise return NULL to request the typical default error handler */
return NULL;
return "strict";
}
#ifdef PY_COERCE_C_LOCALE
......@@ -1586,9 +1589,17 @@ initfsencoding(PyInterpreterState *interp)
Py_HasFileSystemDefaultEncoding = 1;
}
else {
Py_FileSystemDefaultEncoding = get_locale_encoding();
char *locale_encoding;
_PyInitError err = get_locale_encoding(&locale_encoding);
if (_Py_INIT_FAILED(err)) {
return err;
}
Py_FileSystemDefaultEncoding = get_codec_name(locale_encoding);
PyMem_RawFree(locale_encoding);
if (Py_FileSystemDefaultEncoding == NULL) {
return _Py_INIT_ERR("Unable to get the locale encoding");
return _Py_INIT_ERR("failed to get the Python codec "
"of the locale encoding");
}
Py_HasFileSystemDefaultEncoding = 0;
......@@ -1787,6 +1798,8 @@ init_sys_streams(PyInterpreterState *interp)
PyObject * encoding_attr;
char *pythonioencoding = NULL;
const char *encoding, *errors;
char *locale_encoding = NULL;
char *codec_name = NULL;
_PyInitError res = _Py_INIT_OK();
/* Hack to avoid a nasty recursion issue when Python is invoked
......@@ -1838,21 +1851,46 @@ init_sys_streams(PyInterpreterState *interp)
errors = err;
}
}
if (*pythonioencoding && !encoding) {
if (!encoding && *pythonioencoding) {
encoding = pythonioencoding;
if (!errors) {
errors = "strict";
}
}
}
else if (interp->core_config.utf8_mode) {
encoding = "utf-8";
errors = "surrogateescape";
if (interp->core_config.utf8_mode) {
if (!encoding) {
encoding = "utf-8";
}
if (!errors) {
errors = "surrogateescape";
}
}
if (!errors && !pythonioencoding) {
if (!errors) {
/* Choose the default error handler based on the current locale */
errors = get_default_standard_stream_error_handler();
errors = get_stdio_errors();
}
}
if (encoding == NULL) {
_PyInitError err = get_locale_encoding(&locale_encoding);
if (_Py_INIT_FAILED(err)) {
return err;
}
encoding = locale_encoding;
}
codec_name = get_codec_name(encoding);
if (codec_name == NULL) {
PyErr_SetString(PyExc_RuntimeError,
"failed to get the Python codec name "
"of stdio encoding");
goto error;
}
encoding = codec_name;
/* Set sys.stdin */
fd = fileno(stdin);
/* Under some conditions stdin, stdout and stderr may not be connected
......@@ -1928,6 +1966,8 @@ done:
PyMem_SetAllocator(PYMEM_DOMAIN_RAW, &old_alloc);
PyMem_RawFree(locale_encoding);
PyMem_RawFree(codec_name);
PyMem_Free(pythonioencoding);
Py_XDECREF(bimod);
Py_XDECREF(iomod);
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment