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
diff --git a/Python/initconfig.c b/Python/initconfig.c
index 7886d09..27ae48d 100644
--- a/Python/initconfig.c
+++ b/Python/initconfig.c
@@ -94,6 +94,7 @@ static const char usage_3[] = "\
otherwise activate automatically)\n\
-X pycache_prefix=PATH: enable writing .pyc files to a parallel tree rooted at the\n\
given directory instead of to the code tree\n\
+ -X warn_default_encoding: enable opt-in EncodingWarning for 'encoding=None'\n\
\n\
--check-hash-based-pycs always|default|never:\n\
control how Python invalidates hash-based .pyc files\n\
@@ -129,7 +130,8 @@ static const char usage_6[] =
"PYTHONBREAKPOINT: if this variable is set to 0, it disables the default\n"
" debugger. It can be set to the callable of your debugger of choice.\n"
"PYTHONDEVMODE: enable the development mode.\n"
-"PYTHONPYCACHEPREFIX: root directory for bytecode cache (pyc) files.\n";
+"PYTHONPYCACHEPREFIX: root directory for bytecode cache (pyc) files.\n"
+"PYTHONWARNDEFAULTENCODING: enable opt-in EncodingWarning for 'encoding=None'.\n";
#if defined(MS_WINDOWS)
# define PYTHONHOMEHELP "<prefix>\\python{major}{minor}"
@@ -600,6 +602,7 @@ config_check_consistency(const PyConfig *config)
assert(config->malloc_stats >= 0);
assert(config->site_import >= 0);
assert(config->bytes_warning >= 0);
+ assert(config->warn_default_encoding >= 0);
assert(config->inspect >= 0);
assert(config->interactive >= 0);
assert(config->optimization_level >= 0);
@@ -698,6 +701,7 @@ _PyConfig_InitCompatConfig(PyConfig *config)
config->parse_argv = 0;
config->site_import = -1;
config->bytes_warning = -1;
+ config->warn_default_encoding = 0;
config->inspect = -1;
config->interactive = -1;
config->optimization_level = -1;
@@ -906,6 +910,7 @@ _PyConfig_Copy(PyConfig *config, const PyConfig *config2)
COPY_ATTR(site_import);
COPY_ATTR(bytes_warning);
+ COPY_ATTR(warn_default_encoding);
COPY_ATTR(inspect);
COPY_ATTR(interactive);
COPY_ATTR(optimization_level);
@@ -1007,6 +1012,7 @@ _PyConfig_AsDict(const PyConfig *config)
SET_ITEM_WSTR(platlibdir);
SET_ITEM_INT(site_import);
SET_ITEM_INT(bytes_warning);
+ SET_ITEM_INT(warn_default_encoding);
SET_ITEM_INT(inspect);
SET_ITEM_INT(interactive);
SET_ITEM_INT(optimization_level);
@@ -1271,6 +1277,7 @@ _PyConfig_FromDict(PyConfig *config, PyObject *dict)
GET_WSTRLIST(warnoptions);
GET_UINT(site_import);
GET_UINT(bytes_warning);
+ GET_UINT(warn_default_encoding);
GET_UINT(inspect);
GET_UINT(interactive);
GET_UINT(optimization_level);
diff --git a/Python/preconfig.c b/Python/preconfig.c
index b8b0c3a..ae1cc3f 100644
--- a/Python/preconfig.c
+++ b/Python/preconfig.c
@@ -169,6 +169,7 @@ _PyPreCmdline_SetConfig(const _PyPreCmdline *cmdline, PyConfig *config)
COPY_ATTR(isolated);
COPY_ATTR(use_environment);
COPY_ATTR(dev_mode);
+ COPY_ATTR(warn_default_encoding);
return _PyStatus_OK();
#undef COPY_ATTR
@@ -257,9 +258,17 @@ _PyPreCmdline_Read(_PyPreCmdline *cmdline, const PyPreConfig *preconfig)
cmdline->dev_mode = 0;
}
+ // warn_default_encoding
+ if (_Py_get_xoption(&cmdline->xoptions, L"warn_default_encoding")
+ || _Py_GetEnv(cmdline->use_environment, "PYTHONWARNDEFAULTENCODING"))
+ {
+ cmdline->warn_default_encoding = 1;
+ }
+
assert(cmdline->use_environment >= 0);
assert(cmdline->isolated >= 0);
assert(cmdline->dev_mode >= 0);
+ assert(cmdline->warn_default_encoding >= 0);
return _PyStatus_OK();
}
diff --git a/Python/sysmodule.c b/Python/sysmodule.c
index 686b6ca..54d70ef 100644
--- a/Python/sysmodule.c
+++ b/Python/sysmodule.c
@@ -2514,6 +2514,7 @@ static PyStructSequence_Field flags_fields[] = {
{"isolated", "-I"},
{"dev_mode", "-X dev"},
{"utf8_mode", "-X utf8"},
+ {"warn_default_encoding", "-X warn_default_encoding"},
{0}
};
@@ -2521,7 +2522,7 @@ static PyStructSequence_Desc flags_desc = {
"sys.flags", /* name */
flags__doc__, /* doc */
flags_fields, /* fields */
- 15
+ 16
};
static int
@@ -2560,6 +2561,7 @@ set_flags_from_config(PyInterpreterState *interp, PyObject *flags)
SetFlag(config->isolated);
SetFlagObj(PyBool_FromLong(config->dev_mode));
SetFlag(preconfig->utf8_mode);
+ SetFlag(config->warn_default_encoding);
#undef SetFlagObj
#undef SetFlag
return 0;