gh-92536: PEP 623: Remove wstr and legacy APIs from Unicode (GH-92537)

This commit is contained in:
Inada Naoki 2022-05-12 14:48:38 +09:00 committed by GitHub
parent 68fec31364
commit f9c9354a7a
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
35 changed files with 199 additions and 2090 deletions

View file

@ -225,11 +225,7 @@ dl_funcptr _PyImport_FindSharedFuncptrWindows(const char *prefix,
_Py_CheckPython3();
#if USE_UNICODE_WCHAR_CACHE
const wchar_t *wpathname = _PyUnicode_AsUnicode(pathname);
#else /* USE_UNICODE_WCHAR_CACHE */
wchar_t *wpathname = PyUnicode_AsWideCharString(pathname, NULL);
#endif /* USE_UNICODE_WCHAR_CACHE */
if (wpathname == NULL)
return NULL;
@ -251,9 +247,7 @@ dl_funcptr _PyImport_FindSharedFuncptrWindows(const char *prefix,
LOAD_LIBRARY_SEARCH_DEFAULT_DIRS |
LOAD_LIBRARY_SEARCH_DLL_LOAD_DIR);
Py_END_ALLOW_THREADS
#if !USE_UNICODE_WCHAR_CACHE
PyMem_Free(wpathname);
#endif /* USE_UNICODE_WCHAR_CACHE */
/* restore old error mode settings */
SetErrorMode(old_mode);

View file

@ -1244,18 +1244,12 @@ _Py_stat(PyObject *path, struct stat *statbuf)
#ifdef MS_WINDOWS
int err;
#if USE_UNICODE_WCHAR_CACHE
const wchar_t *wpath = _PyUnicode_AsUnicode(path);
#else /* USE_UNICODE_WCHAR_CACHE */
wchar_t *wpath = PyUnicode_AsWideCharString(path, NULL);
#endif /* USE_UNICODE_WCHAR_CACHE */
if (wpath == NULL)
return -2;
err = _Py_wstat(wpath, statbuf);
#if !USE_UNICODE_WCHAR_CACHE
PyMem_Free(wpath);
#endif /* USE_UNICODE_WCHAR_CACHE */
return err;
#else
int ret;
@ -1663,11 +1657,8 @@ _Py_fopen_obj(PyObject *path, const char *mode)
Py_TYPE(path));
return NULL;
}
#if USE_UNICODE_WCHAR_CACHE
const wchar_t *wpath = _PyUnicode_AsUnicode(path);
#else /* USE_UNICODE_WCHAR_CACHE */
wchar_t *wpath = PyUnicode_AsWideCharString(path, NULL);
#endif /* USE_UNICODE_WCHAR_CACHE */
if (wpath == NULL)
return NULL;
@ -1675,9 +1666,7 @@ _Py_fopen_obj(PyObject *path, const char *mode)
wmode, Py_ARRAY_LENGTH(wmode));
if (usize == 0) {
PyErr_SetFromWindowsErr(0);
#if !USE_UNICODE_WCHAR_CACHE
PyMem_Free(wpath);
#endif /* USE_UNICODE_WCHAR_CACHE */
return NULL;
}
@ -1687,9 +1676,7 @@ _Py_fopen_obj(PyObject *path, const char *mode)
Py_END_ALLOW_THREADS
} while (f == NULL
&& errno == EINTR && !(async_err = PyErr_CheckSignals()));
#if !USE_UNICODE_WCHAR_CACHE
PyMem_Free(wpath);
#endif /* USE_UNICODE_WCHAR_CACHE */
#else
PyObject *bytes;
const char *path_bytes;

View file

@ -1012,58 +1012,6 @@ convertsimple(PyObject *arg, const char **p_format, va_list *p_va, int flags,
break;
}
case 'u': /* raw unicode buffer (Py_UNICODE *) */
case 'Z': /* raw unicode buffer or None */
{
if (PyErr_WarnFormat(PyExc_DeprecationWarning, 1,
"getargs: The '%c' format is deprecated. Use 'U' instead.", c)) {
return NULL;
}
_Py_COMP_DIAG_PUSH
_Py_COMP_DIAG_IGNORE_DEPR_DECLS
Py_UNICODE **p = va_arg(*p_va, Py_UNICODE **);
if (*format == '#') {
/* "u#" or "Z#" */
REQUIRE_PY_SSIZE_T_CLEAN;
Py_ssize_t *psize = va_arg(*p_va, Py_ssize_t*);
if (c == 'Z' && arg == Py_None) {
*p = NULL;
*psize = 0;
}
else if (PyUnicode_Check(arg)) {
Py_ssize_t len;
*p = PyUnicode_AsUnicodeAndSize(arg, &len);
if (*p == NULL)
RETURN_ERR_OCCURRED;
*psize = len;
}
else
return converterr(c == 'Z' ? "str or None" : "str",
arg, msgbuf, bufsize);
format++;
} else {
/* "u" or "Z" */
if (c == 'Z' && arg == Py_None)
*p = NULL;
else if (PyUnicode_Check(arg)) {
Py_ssize_t len;
*p = PyUnicode_AsUnicodeAndSize(arg, &len);
if (*p == NULL)
RETURN_ERR_OCCURRED;
if (wcslen(*p) != (size_t)len) {
PyErr_SetString(PyExc_ValueError, "embedded null character");
RETURN_ERR_OCCURRED;
}
} else
return converterr(c == 'Z' ? "str or None" : "str",
arg, msgbuf, bufsize);
}
break;
_Py_COMP_DIAG_POP
}
case 'e': {/* encoded string */
char **buffer;
const char *encoding;
@ -2685,8 +2633,6 @@ skipitem(const char **p_format, va_list *p_va, int flags)
case 's': /* string */
case 'z': /* string or None */
case 'y': /* bytes */
case 'u': /* unicode string */
case 'Z': /* unicode string or None */
case 'w': /* buffer, read-write */
{
if (p_va != NULL) {

View file

@ -1077,7 +1077,6 @@ _Py_DumpASCII(int fd, PyObject *text)
int truncated;
int kind;
void *data = NULL;
wchar_t *wstr = NULL;
Py_UCS4 ch;
if (!PyUnicode_Check(text))
@ -1085,13 +1084,7 @@ _Py_DumpASCII(int fd, PyObject *text)
size = ascii->length;
kind = ascii->state.kind;
if (kind == PyUnicode_WCHAR_KIND) {
wstr = ascii->wstr;
if (wstr == NULL)
return;
size = _PyCompactUnicodeObject_CAST(text)->wstr_length;
}
else if (ascii->state.compact) {
if (ascii->state.compact) {
if (ascii->state.ascii)
data = ascii + 1;
else
@ -1132,10 +1125,7 @@ _Py_DumpASCII(int fd, PyObject *text)
}
for (i=0; i < size; i++) {
if (kind != PyUnicode_WCHAR_KIND)
ch = PyUnicode_READ(kind, data, i);
else
ch = wstr[i];
ch = PyUnicode_READ(kind, data, i);
if (' ' <= ch && ch <= 126) {
/* printable ASCII character */
char c = (char)ch;