bpo-43510: Implement PEP 597 opt-in EncodingWarning. (GH-19481)

See [PEP 597](https://www.python.org/dev/peps/pep-0597/).

* Add `-X warn_default_encoding` and `PYTHONWARNDEFAULTENCODING`.
* Add EncodingWarning
* Add io.text_encoding()
* open(), TextIOWrapper() emits EncodingWarning when encoding is omitted and warn_default_encoding is enabled.
* _pyio.TextIOWrapper() uses UTF-8 as fallback default encoding used when failed to import locale module. (used during building Python)
* bz2, configparser, gzip, lzma, pathlib, tempfile modules use io.text_encoding().
* What's new entry

3 files changed, 99 insertions, 1 deletions

diff --git a/Modules/_io/_iomodule.c b/Modules/_io/_iomodule.c
index 9147648..652c2ce 100644
--- a/Modules/_io/_iomodule.c
+++ b/Modules/_io/_iomodule.c
@@ -10,6 +10,7 @@
 #define PY_SSIZE_T_CLEAN
 #include "Python.h"
 #include "_iomodule.h"
+#include "pycore_pystate.h"       // _PyInterpreterState_GET()
 
 #ifdef HAVE_SYS_TYPES_H
 #include <sys/types.h>
@@ -33,6 +34,7 @@ PyObject *_PyIO_str_fileno = NULL;
 PyObject *_PyIO_str_flush = NULL;
 PyObject *_PyIO_str_getstate = NULL;
 PyObject *_PyIO_str_isatty = NULL;
+PyObject *_PyIO_str_locale = NULL;
 PyObject *_PyIO_str_newlines = NULL;
 PyObject *_PyIO_str_nl = NULL;
 PyObject *_PyIO_str_peek = NULL;
@@ -504,6 +506,43 @@ _io_open_impl(PyObject *module, PyObject *file, const char *mode,
     return NULL;
 }
 
+
+/*[clinic input]
+_io.text_encoding
+    encoding: object
+    stacklevel: int = 2
+    /
+
+A helper function to choose the text encoding.
+
+When encoding is not None, just return it.
+Otherwise, return the default text encoding (i.e. "locale").
+
+This function emits an EncodingWarning if encoding is None and
+sys.flags.warn_default_encoding is true.
+
+This can be used in APIs with an encoding=None parameter.
+However, please consider using encoding="utf-8" for new APIs.
+[clinic start generated code]*/
+
+static PyObject *
+_io_text_encoding_impl(PyObject *module, PyObject *encoding, int stacklevel)
+/*[clinic end generated code: output=91b2cfea6934cc0c input=bf70231213e2a7b4]*/
+{
+    if (encoding == NULL || encoding == Py_None) {
+        PyInterpreterState *interp = _PyInterpreterState_GET();
+        if (_PyInterpreterState_GetConfig(interp)->warn_default_encoding) {
+            PyErr_WarnEx(PyExc_EncodingWarning,
+                         "'encoding' argument not specified", stacklevel);
+        }
+        Py_INCREF(_PyIO_str_locale);
+        return _PyIO_str_locale;
+    }
+    Py_INCREF(encoding);
+    return encoding;
+}
+
+
 /*[clinic input]
 _io.open_code
 
@@ -629,6 +668,7 @@ iomodule_free(PyObject *mod) {
 
 static PyMethodDef module_methods[] = {
     _IO_OPEN_METHODDEF
+    _IO_TEXT_ENCODING_METHODDEF
     _IO_OPEN_CODE_METHODDEF
     {NULL, NULL}
 };
@@ -747,6 +787,7 @@ PyInit__io(void)
     ADD_INTERNED(flush)
     ADD_INTERNED(getstate)
     ADD_INTERNED(isatty)
+    ADD_INTERNED(locale)
     ADD_INTERNED(newlines)
     ADD_INTERNED(peek)
     ADD_INTERNED(read)
diff --git a/Modules/_io/clinic/_iomodule.c.h b/Modules/_io/clinic/_iomodule.c.h
index dc7b5ff..91c55b1 100644
--- a/Modules/_io/clinic/_iomodule.c.h
+++ b/Modules/_io/clinic/_iomodule.c.h
@@ -272,6 +272,52 @@ exit:
     return return_value;
 }
 
+PyDoc_STRVAR(_io_text_encoding__doc__,
+"text_encoding($module, encoding, stacklevel=2, /)\n"
+"--\n"
+"\n"
+"A helper function to choose the text encoding.\n"
+"\n"
+"When encoding is not None, just return it.\n"
+"Otherwise, return the default text encoding (i.e. \"locale\").\n"
+"\n"
+"This function emits an EncodingWarning if encoding is None and\n"
+"sys.flags.warn_default_encoding is true.\n"
+"\n"
+"This can be used in APIs with an encoding=None parameter.\n"
+"However, please consider using encoding=\"utf-8\" for new APIs.");
+
+#define _IO_TEXT_ENCODING_METHODDEF    \
+    {"text_encoding", (PyCFunction)(void(*)(void))_io_text_encoding, METH_FASTCALL, _io_text_encoding__doc__},
+
+static PyObject *
+_io_text_encoding_impl(PyObject *module, PyObject *encoding, int stacklevel);
+
+static PyObject *
+_io_text_encoding(PyObject *module, PyObject *const *args, Py_ssize_t nargs)
+{
+    PyObject *return_value = NULL;
+    PyObject *encoding;
+    int stacklevel = 2;
+
+    if (!_PyArg_CheckPositional("text_encoding", nargs, 1, 2)) {
+        goto exit;
+    }
+    encoding = args[0];
+    if (nargs < 2) {
+        goto skip_optional;
+    }
+    stacklevel = _PyLong_AsInt(args[1]);
+    if (stacklevel == -1 && PyErr_Occurred()) {
+        goto exit;
+    }
+skip_optional:
+    return_value = _io_text_encoding_impl(module, encoding, stacklevel);
+
+exit:
+    return return_value;
+}
+
 PyDoc_STRVAR(_io_open_code__doc__,
 "open_code($module, /, path)\n"
 "--\n"
@@ -313,4 +359,4 @@ _io_open_code(PyObject *module, PyObject *const *args, Py_ssize_t nargs, PyObjec
 exit:
     return return_value;
 }
-/*[clinic end generated code: output=5c0dd7a262c30ebc input=a9049054013a1b77]*/
+/*[clinic end generated code: output=06e055d1d80b835d input=a9049054013a1b77]*/
diff --git a/Modules/_io/textio.c b/Modules/_io/textio.c
index 03001ec..6f89a87 100644
--- a/Modules/_io/textio.c
+++ b/Modules/_io/textio.c
@@ -1124,6 +1124,17 @@ _io_TextIOWrapper___init___impl(textio *self, PyObject *buffer,
     self->b2cratio = 0.0;
 
     if (encoding == NULL) {
+        PyInterpreterState *interp = _PyInterpreterState_GET();
+        if (_PyInterpreterState_GetConfig(interp)->warn_default_encoding) {
+            PyErr_WarnEx(PyExc_EncodingWarning,
+                         "'encoding' argument not specified", 1);
+        }
+    }
+    else if (strcmp(encoding, "locale") == 0) {
+        encoding = NULL;
+    }
+
+    if (encoding == NULL) {
         /* Try os.device_encoding(fileno) */
         PyObject *fileno;
         state = IO_STATE();