[WIP] bpo-36142: Rework Python init to add _PyPreConfig

Include/Python.h

@@ -128,7 +128,7 @@
 #include "codecs.h"
 #include "pyerrors.h"
 
-#include "coreconfig.h"
+#include "cpython/coreconfig.h"
 #include "pystate.h"
 #include "context.h"
 

Include/coreconfig.h → Include/cpython/coreconfig.h

@@ -1,15 +1,15 @@
 #ifndef Py_PYCORECONFIG_H
 #define Py_PYCORECONFIG_H
+#ifndef Py_LIMITED_API
 #ifdef __cplusplus
 extern "C" {
 #endif
 
-
-#ifndef Py_LIMITED_API
 typedef struct {
     const char *prefix;
     const char *msg;
     int user_err;
+    int exitcode;
 } _PyInitError;
 
 /* Almost all errors causing Python initialization to fail */
@@ -21,48 +21,50 @@ typedef struct {
 #endif
 
 #define _Py_INIT_OK() \
-    (_PyInitError){.prefix = NULL, .msg = NULL, .user_err = 0}
+    (_PyInitError){.prefix = NULL, .msg = NULL, .user_err = 0, .exitcode = -1}
 #define _Py_INIT_ERR(MSG) \
-    (_PyInitError){.prefix = _Py_INIT_GET_FUNC(), .msg = (MSG), .user_err = 0}
+    (_PyInitError){.prefix = _Py_INIT_GET_FUNC(), .msg = (MSG), .user_err = 0, .exitcode = -1}
 /* Error that can be fixed by the user like invalid input parameter.
    Don't abort() the process on such error. */
 #define _Py_INIT_USER_ERR(MSG) \
-    (_PyInitError){.prefix = _Py_INIT_GET_FUNC(), .msg = (MSG), .user_err = 1}
+    (_PyInitError){.prefix = _Py_INIT_GET_FUNC(), .msg = (MSG), .user_err = 1, .exitcode = -1}
 #define _Py_INIT_NO_MEMORY() _Py_INIT_USER_ERR("memory allocation failed")
+#define _Py_INIT_EXIT(EXITCODE) \
+    (_PyInitError){.prefix = NULL, .msg = NULL, .user_err = 0, .exitcode = (EXITCODE)}
 #define _Py_INIT_FAILED(err) \
-    (err.msg != NULL)
+    (err.msg != NULL || err.exitcode != -1)
 
-#endif   /* !defined(Py_LIMITED_API) */
 
 
 typedef struct {
-    /* Install signal handlers? Yes by default. */
-    int install_signal_handlers;
+    int argc;
+    int use_bytes_argv;
+    char * const * bytes_argv;
+    wchar_t * const * wchar_argv;
+} _PyArgv;
+
+
+typedef struct {
+    char *allocator;        /* Memory allocator: PYTHONMALLOC */
+    int dev_mode;           /* Development mode. PYTHONDEVMODE, -X dev */
 
     /* If greater than 0: use environment variables.
        Set to 0 by -E command line option. If set to -1 (default), it is
        set to !Py_IgnoreEnvironmentFlag. */
     int use_environment;
 
-    int use_hash_seed;      /* PYTHONHASHSEED=x */
-    unsigned long hash_seed;
-
-    const char *allocator;  /* Memory allocator: PYTHONMALLOC */
-    int dev_mode;           /* PYTHONDEVMODE, -X dev */
+    /* If greater than 0, enable isolated mode: sys.path contains
+       neither the script's directory nor the user's site-packages directory.
 
-    /* Enable faulthandler?
-       Set to 1 by -X faulthandler and PYTHONFAULTHANDLER. -1 means unset. */
-    int faulthandler;
+       Set to 1 by the -I command line option. If set to -1 (default), inherit
+       Py_IsolatedFlag value. */
+    int isolated;
 
-    /* Enable tracemalloc?
-       Set by -X tracemalloc=N and PYTHONTRACEMALLOC. -1 means unset */
-    int tracemalloc;
+    /* Enable UTF-8 mode?
+       Set by -X utf8 command line option and PYTHONUTF8 environment variable.
+       If set to -1 (default), inherit Py_UTF8Mode value. */
+    int utf8_mode;
 
-    int import_time;        /* PYTHONPROFILEIMPORTTIME, -X importtime */
-    int show_ref_count;     /* -X showrefcount */
-    int show_alloc_count;   /* -X showalloccount */
-    int dump_refs;          /* PYTHONDUMPREFS */
-    int malloc_stats;       /* PYTHONMALLOCSTATS */
     int coerce_c_locale;    /* PYTHONCOERCECLOCALE, -1 means unknown */
     int coerce_c_locale_warn; /* PYTHONCOERCECLOCALE=warn */
 
@@ -102,10 +104,81 @@ typedef struct {
     char *filesystem_encoding;
     char *filesystem_errors;
 
-    /* Enable UTF-8 mode?
-       Set by -X utf8 command line option and PYTHONUTF8 environment variable.
-       If set to -1 (default), inherit Py_UTF8Mode value. */
-    int utf8_mode;
+    /* Encoding of sys.stdin, sys.stdout and sys.stderr.
+       Value set from PYTHONIOENCODING environment variable and
+       Py_SetStandardStreamEncoding() function.
+       See also 'stdio_errors' attribute. */
+    char *stdio_encoding;
+
+    /* Error handler of sys.stdin and sys.stdout.
+       Value set from PYTHONIOENCODING environment variable and
+       Py_SetStandardStreamEncoding() function.
+       See also 'stdio_encoding' attribute. */
+    char *stdio_errors;
+
+#ifdef MS_WINDOWS
+    /* If greater than 1, use the "mbcs" encoding instead of the UTF-8
+       encoding for the filesystem encoding.
+
+       Set to 1 if the PYTHONLEGACYWINDOWSFSENCODING environment variable is
+       set to a non-empty string. If set to -1 (default), inherit
+       Py_LegacyWindowsFSEncodingFlag value.
+
+       See PEP 529 for more details. */
+    int legacy_windows_fs_encoding;
+
+    /* If greater than zero, use io.FileIO instead of WindowsConsoleIO for sys
+       standard streams.
+
+       Set to 1 if the PYTHONLEGACYWINDOWSSTDIO environment variable is set to
+       a non-empty string. If set to -1 (default), inherit
+       Py_LegacyWindowsStdioFlag value.
+
+       See PEP 528 for more details. */
+    int legacy_windows_stdio;
+#endif
+} _PyPreConfig;
+
+#ifdef MS_WINDOWS
+#  define _PyPreConfig_WINDOWS_INIT \
+        .legacy_windows_fs_encoding = -1, \
+        .legacy_windows_stdio = -1,
+#else
+#  define _PyPreConfig_WINDOWS_INIT
+#endif
+
+#define _PyPreConfig_INIT \
+    (_PyPreConfig){ \
+        _PyPreConfig_WINDOWS_INIT \
+        .use_environment = -1, \
+        .isolated = -1, \
+        .utf8_mode = -1, \
+        .coerce_c_locale = -1 \
+        }
+
+
+typedef struct {
+    _PyPreConfig preconfig;
+
+    /* Install signal handlers? Yes by default. */
+    int install_signal_handlers;
+
+    int use_hash_seed;      /* PYTHONHASHSEED=x */
+    unsigned long hash_seed;
+
+    /* Enable faulthandler?
+       Set to 1 by -X faulthandler and PYTHONFAULTHANDLER. -1 means unset. */
+    int faulthandler;
+
+    /* Enable tracemalloc?
+       Set by -X tracemalloc=N and PYTHONTRACEMALLOC. -1 means unset */
+    int tracemalloc;
+
+    int import_time;        /* PYTHONPROFILEIMPORTTIME, -X importtime */
+    int show_ref_count;     /* -X showrefcount */
+    int show_alloc_count;   /* -X showalloccount */
+    int dump_refs;          /* PYTHONDUMPREFS */
+    int malloc_stats;       /* PYTHONMALLOCSTATS */
 
     wchar_t *pycache_prefix; /* PYTHONPYCACHEPREFIX, -X pycache_prefix=PATH */
 
@@ -139,13 +212,6 @@ typedef struct {
     wchar_t *dll_path;      /* Windows DLL path */
 #endif
 
-    /* If greater than 0, enable isolated mode: sys.path contains
-       neither the script's directory nor the user's site-packages directory.
-
-       Set to 1 by the -I command line option. If set to -1 (default), inherit
-       Py_IsolatedFlag value. */
-    int isolated;
-
     /* If equal to zero, disable the import of the module site and the
        site-dependent manipulations of sys.path that it entails. Also disable
        these manipulations if site is explicitly imported later (call
@@ -239,39 +305,12 @@ typedef struct {
        If set to -1 (default), it is set to !Py_UnbufferedStdioFlag. */
     int buffered_stdio;
 
-    /* Encoding of sys.stdin, sys.stdout and sys.stderr.
-       Value set from PYTHONIOENCODING environment variable and
-       Py_SetStandardStreamEncoding() function.
-       See also 'stdio_errors' attribute. */
-    char *stdio_encoding;
-
-    /* Error handler of sys.stdin and sys.stdout.
-       Value set from PYTHONIOENCODING environment variable and
-       Py_SetStandardStreamEncoding() function.
-       See also 'stdio_encoding' attribute. */
-    char *stdio_errors;
-
-#ifdef MS_WINDOWS
-    /* If greater than 1, use the "mbcs" encoding instead of the UTF-8
-       encoding for the filesystem encoding.
-
-       Set to 1 if the PYTHONLEGACYWINDOWSFSENCODING environment variable is
-       set to a non-empty string. If set to -1 (default), inherit
-       Py_LegacyWindowsFSEncodingFlag value.
-
-       See PEP 529 for more details. */
-    int legacy_windows_fs_encoding;
-
-    /* If greater than zero, use io.FileIO instead of WindowsConsoleIO for sys
-       standard streams.
-
-       Set to 1 if the PYTHONLEGACYWINDOWSSTDIO environment variable is set to
-       a non-empty string. If set to -1 (default), inherit
-       Py_LegacyWindowsStdioFlag value.
+    /* Skip the first line of the source: -x command line option */
+    int skip_source_first_line;
 
-       See PEP 528 for more details. */
-    int legacy_windows_stdio;
-#endif
+    wchar_t *run_command;   /* -c command line argument */
+    wchar_t *run_module;    /* -m command line argument */
+    wchar_t *run_filename;  /* Trailing command line argument without -c or -m */
 
     /* --- Private fields -------- */
 
@@ -301,26 +340,15 @@ typedef struct {
 
 } _PyCoreConfig;
 
-#ifdef MS_WINDOWS
-#  define _PyCoreConfig_WINDOWS_INIT \
-        .legacy_windows_fs_encoding = -1, \
-        .legacy_windows_stdio = -1,
-#else
-#  define _PyCoreConfig_WINDOWS_INIT
-#endif
-
 #define _PyCoreConfig_INIT \
     (_PyCoreConfig){ \
+        .preconfig = _PyPreConfig_INIT, \
         .install_signal_handlers = 1, \
-        .use_environment = -1, \
         .use_hash_seed = -1, \
         .faulthandler = -1, \
         .tracemalloc = -1, \
-        .coerce_c_locale = -1, \
-        .utf8_mode = -1, \
         .argc = -1, \
         .nmodule_search_path = -1, \
-        .isolated = -1, \
         .site_import = -1, \
         .bytes_warning = -1, \
         .inspect = -1, \
@@ -332,39 +360,17 @@ typedef struct {
         .quiet = -1, \
         .user_site_directory = -1, \
         .buffered_stdio = -1, \
-        _PyCoreConfig_WINDOWS_INIT \
         ._install_importlib = 1, \
         ._check_hash_pycs_mode = "default", \
         ._frozen = -1}
 /* Note: _PyCoreConfig_INIT sets other fields to 0/NULL */
 
-
-#ifndef Py_LIMITED_API
-PyAPI_FUNC(_PyInitError) _PyCoreConfig_Read(_PyCoreConfig *config);
-PyAPI_FUNC(void) _PyCoreConfig_Clear(_PyCoreConfig *);
-PyAPI_FUNC(int) _PyCoreConfig_Copy(
-    _PyCoreConfig *config,
-    const _PyCoreConfig *config2);
-PyAPI_FUNC(_PyInitError) _PyCoreConfig_InitPathConfig(_PyCoreConfig *config);
-PyAPI_FUNC(_PyInitError) _PyCoreConfig_SetPathConfig(
-    const _PyCoreConfig *config);
-PyAPI_FUNC(void) _PyCoreConfig_GetGlobalConfig(_PyCoreConfig *config);
-PyAPI_FUNC(void) _PyCoreConfig_SetGlobalConfig(const _PyCoreConfig *config);
-PyAPI_FUNC(const char*) _PyCoreConfig_GetEnv(
-    const _PyCoreConfig *config,
-    const char *name);
-PyAPI_FUNC(int) _PyCoreConfig_GetEnvDup(
-    const _PyCoreConfig *config,
-    wchar_t **dest,
-    wchar_t *wname,
-    char *name);
-
 /* Used by _testcapi.get_global_config() and _testcapi.get_core_config() */
 PyAPI_FUNC(PyObject *) _Py_GetGlobalVariablesAsDict(void);
 PyAPI_FUNC(PyObject *) _PyCoreConfig_AsDict(const _PyCoreConfig *config);
-#endif
 
 #ifdef __cplusplus
 }
 #endif
-#endif /* !Py_PYCORECONFIG_H */
+#endif   /* !Py_LIMITED_API */
+#endif   /* !Py_PYCORECONFIG_H */

Include/cpython/pylifecycle.h

@@ -39,7 +39,7 @@ PyAPI_FUNC(_PyInitError) _Py_InitializeMainInterpreter(
 
 PyAPI_FUNC(_PyInitError) _Py_InitializeFromConfig(
     const _PyCoreConfig *config);
-PyAPI_FUNC(void) _Py_NO_RETURN _Py_FatalInitError(_PyInitError err);
+PyAPI_FUNC(void) _Py_NO_RETURN _Py_ExitInitError(_PyInitError err);
 
 /* Py_PyAtExit is for the atexit module, Py_AtExit is for low-level
  * exit functions.
@@ -64,7 +64,7 @@ PyAPI_FUNC(int) _PyOS_URandomNonblock(void *buffer, Py_ssize_t size);
 
 /* Legacy locale support */
 PyAPI_FUNC(void) _Py_CoerceLegacyLocale(int warn);
-PyAPI_FUNC(int) _Py_LegacyLocaleDetected(void);
+PyAPI_FUNC(int) _Py_LegacyLocaleDetected(const char *ctype_locale);
 PyAPI_FUNC(char *) _Py_SetLocaleFromEnv(int category);
 
 #ifdef __cplusplus

Include/cpython/pystate.h

@@ -6,6 +6,8 @@
 extern "C" {
 #endif
 
+#include "coreconfig.h"
+
 /* Placeholders while working on the new configuration API
  *
  * See PEP 432 for final anticipated contents

Include/fileobject.h

@@ -27,6 +27,9 @@ PyAPI_DATA(const char *) Py_FileSystemDefaultEncoding;
 PyAPI_DATA(const char *) Py_FileSystemDefaultEncodeErrors;
 #endif
 PyAPI_DATA(int) Py_HasFileSystemDefaultEncoding;
+#ifdef Py_BUILD_CORE
+PyAPI_DATA(int) _Py_HasFileSystemDefaultEncodeErrors;
+#endif
 
 #if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03070000
 PyAPI_DATA(int) Py_UTF8Mode;