Check in python 3.8.1 prebuilts (Windows)
This checks in python to a new llvm-toolchain branch. Nothing else
should be affected.
Built at:
http://fusion-qa/ee88375b-c7dd-4a7b-8d73-ef841db4b0b8
Change-Id: I88145ffae73748d3a10bdfc5ed14f05852336d5f
diff --git a/include/cpython/abstract.h b/include/cpython/abstract.h
new file mode 100644
index 0000000..2ea3209
--- /dev/null
+++ b/include/cpython/abstract.h
@@ -0,0 +1,319 @@
+#ifndef Py_CPYTHON_ABSTRACTOBJECT_H
+# error "this header file must not be included directly"
+#endif
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/* === Object Protocol ================================================== */
+
+#ifdef PY_SSIZE_T_CLEAN
+# define _PyObject_CallMethodId _PyObject_CallMethodId_SizeT
+#endif
+
+/* Convert keyword arguments from the FASTCALL (stack: C array, kwnames: tuple)
+ format to a Python dictionary ("kwargs" dict).
+
+ The type of kwnames keys is not checked. The final function getting
+ arguments is responsible to check if all keys are strings, for example using
+ PyArg_ParseTupleAndKeywords() or PyArg_ValidateKeywordArguments().
+
+ Duplicate keys are merged using the last value. If duplicate keys must raise
+ an exception, the caller is responsible to implement an explicit keys on
+ kwnames. */
+PyAPI_FUNC(PyObject *) _PyStack_AsDict(
+ PyObject *const *values,
+ PyObject *kwnames);
+
+/* Convert (args, nargs, kwargs: dict) into a (stack, nargs, kwnames: tuple).
+
+ Return 0 on success, raise an exception and return -1 on error.
+
+ Write the new stack into *p_stack. If *p_stack is differen than args, it
+ must be released by PyMem_Free().
+
+ The stack uses borrowed references.
+
+ The type of keyword keys is not checked, these checks should be done
+ later (ex: _PyArg_ParseStackAndKeywords). */
+PyAPI_FUNC(int) _PyStack_UnpackDict(
+ PyObject *const *args,
+ Py_ssize_t nargs,
+ PyObject *kwargs,
+ PyObject *const **p_stack,
+ PyObject **p_kwnames);
+
+/* Suggested size (number of positional arguments) for arrays of PyObject*
+ allocated on a C stack to avoid allocating memory on the heap memory. Such
+ array is used to pass positional arguments to call functions of the
+ _PyObject_Vectorcall() family.
+
+ The size is chosen to not abuse the C stack and so limit the risk of stack
+ overflow. The size is also chosen to allow using the small stack for most
+ function calls of the Python standard library. On 64-bit CPU, it allocates
+ 40 bytes on the stack. */
+#define _PY_FASTCALL_SMALL_STACK 5
+
+PyAPI_FUNC(PyObject *) _Py_CheckFunctionResult(PyObject *callable,
+ PyObject *result,
+ const char *where);
+
+/* === Vectorcall protocol (PEP 590) ============================= */
+
+/* Call callable using tp_call. Arguments are like _PyObject_Vectorcall()
+ or _PyObject_FastCallDict() (both forms are supported),
+ except that nargs is plainly the number of arguments without flags. */
+PyAPI_FUNC(PyObject *) _PyObject_MakeTpCall(
+ PyObject *callable,
+ PyObject *const *args, Py_ssize_t nargs,
+ PyObject *keywords);
+
+#define PY_VECTORCALL_ARGUMENTS_OFFSET ((size_t)1 << (8 * sizeof(size_t) - 1))
+
+static inline Py_ssize_t
+PyVectorcall_NARGS(size_t n)
+{
+ return n & ~PY_VECTORCALL_ARGUMENTS_OFFSET;
+}
+
+static inline vectorcallfunc
+_PyVectorcall_Function(PyObject *callable)
+{
+ PyTypeObject *tp = Py_TYPE(callable);
+ Py_ssize_t offset = tp->tp_vectorcall_offset;
+ vectorcallfunc *ptr;
+ if (!PyType_HasFeature(tp, _Py_TPFLAGS_HAVE_VECTORCALL)) {
+ return NULL;
+ }
+ assert(PyCallable_Check(callable));
+ assert(offset > 0);
+ ptr = (vectorcallfunc*)(((char *)callable) + offset);
+ return *ptr;
+}
+
+/* Call the callable object 'callable' with the "vectorcall" calling
+ convention.
+
+ args is a C array for positional arguments.
+
+ nargsf is the number of positional arguments plus optionally the flag
+ PY_VECTORCALL_ARGUMENTS_OFFSET which means that the caller is allowed to
+ modify args[-1].
+
+ kwnames is a tuple of keyword names. The values of the keyword arguments
+ are stored in "args" after the positional arguments (note that the number
+ of keyword arguments does not change nargsf). kwnames can also be NULL if
+ there are no keyword arguments.
+
+ keywords must only contains str strings (no subclass), and all keys must
+ be unique.
+
+ Return the result on success. Raise an exception and return NULL on
+ error. */
+static inline PyObject *
+_PyObject_Vectorcall(PyObject *callable, PyObject *const *args,
+ size_t nargsf, PyObject *kwnames)
+{
+ PyObject *res;
+ vectorcallfunc func;
+ assert(kwnames == NULL || PyTuple_Check(kwnames));
+ assert(args != NULL || PyVectorcall_NARGS(nargsf) == 0);
+ func = _PyVectorcall_Function(callable);
+ if (func == NULL) {
+ Py_ssize_t nargs = PyVectorcall_NARGS(nargsf);
+ return _PyObject_MakeTpCall(callable, args, nargs, kwnames);
+ }
+ res = func(callable, args, nargsf, kwnames);
+ return _Py_CheckFunctionResult(callable, res, NULL);
+}
+
+/* Same as _PyObject_Vectorcall except that keyword arguments are passed as
+ dict, which may be NULL if there are no keyword arguments. */
+PyAPI_FUNC(PyObject *) _PyObject_FastCallDict(
+ PyObject *callable,
+ PyObject *const *args,
+ size_t nargsf,
+ PyObject *kwargs);
+
+/* Call "callable" (which must support vectorcall) with positional arguments
+ "tuple" and keyword arguments "dict". "dict" may also be NULL */
+PyAPI_FUNC(PyObject *) PyVectorcall_Call(PyObject *callable, PyObject *tuple, PyObject *dict);
+
+/* Same as _PyObject_Vectorcall except without keyword arguments */
+static inline PyObject *
+_PyObject_FastCall(PyObject *func, PyObject *const *args, Py_ssize_t nargs)
+{
+ return _PyObject_Vectorcall(func, args, (size_t)nargs, NULL);
+}
+
+/* Call a callable without any arguments */
+static inline PyObject *
+_PyObject_CallNoArg(PyObject *func) {
+ return _PyObject_Vectorcall(func, NULL, 0, NULL);
+}
+
+PyAPI_FUNC(PyObject *) _PyObject_Call_Prepend(
+ PyObject *callable,
+ PyObject *obj,
+ PyObject *args,
+ PyObject *kwargs);
+
+PyAPI_FUNC(PyObject *) _PyObject_FastCall_Prepend(
+ PyObject *callable,
+ PyObject *obj,
+ PyObject *const *args,
+ Py_ssize_t nargs);
+
+/* Like PyObject_CallMethod(), but expect a _Py_Identifier*
+ as the method name. */
+PyAPI_FUNC(PyObject *) _PyObject_CallMethodId(PyObject *obj,
+ _Py_Identifier *name,
+ const char *format, ...);
+
+PyAPI_FUNC(PyObject *) _PyObject_CallMethodId_SizeT(PyObject *obj,
+ _Py_Identifier *name,
+ const char *format,
+ ...);
+
+PyAPI_FUNC(PyObject *) _PyObject_CallMethodIdObjArgs(
+ PyObject *obj,
+ struct _Py_Identifier *name,
+ ...);
+
+PyAPI_FUNC(int) _PyObject_HasLen(PyObject *o);
+
+/* Guess the size of object 'o' using len(o) or o.__length_hint__().
+ If neither of those return a non-negative value, then return the default
+ value. If one of the calls fails, this function returns -1. */
+PyAPI_FUNC(Py_ssize_t) PyObject_LengthHint(PyObject *o, Py_ssize_t);
+
+/* === New Buffer API ============================================ */
+
+/* Return 1 if the getbuffer function is available, otherwise return 0. */
+#define PyObject_CheckBuffer(obj) \
+ (((obj)->ob_type->tp_as_buffer != NULL) && \
+ ((obj)->ob_type->tp_as_buffer->bf_getbuffer != NULL))
+
+/* This is a C-API version of the getbuffer function call. It checks
+ to make sure object has the required function pointer and issues the
+ call.
+
+ Returns -1 and raises an error on failure and returns 0 on success. */
+PyAPI_FUNC(int) PyObject_GetBuffer(PyObject *obj, Py_buffer *view,
+ int flags);
+
+/* Get the memory area pointed to by the indices for the buffer given.
+ Note that view->ndim is the assumed size of indices. */
+PyAPI_FUNC(void *) PyBuffer_GetPointer(Py_buffer *view, Py_ssize_t *indices);
+
+/* Return the implied itemsize of the data-format area from a
+ struct-style description. */
+PyAPI_FUNC(int) PyBuffer_SizeFromFormat(const char *);
+
+/* Implementation in memoryobject.c */
+PyAPI_FUNC(int) PyBuffer_ToContiguous(void *buf, Py_buffer *view,
+ Py_ssize_t len, char order);
+
+PyAPI_FUNC(int) PyBuffer_FromContiguous(Py_buffer *view, void *buf,
+ Py_ssize_t len, char order);
+
+/* Copy len bytes of data from the contiguous chunk of memory
+ pointed to by buf into the buffer exported by obj. Return
+ 0 on success and return -1 and raise a PyBuffer_Error on
+ error (i.e. the object does not have a buffer interface or
+ it is not working).
+
+ If fort is 'F', then if the object is multi-dimensional,
+ then the data will be copied into the array in
+ Fortran-style (first dimension varies the fastest). If
+ fort is 'C', then the data will be copied into the array
+ in C-style (last dimension varies the fastest). If fort
+ is 'A', then it does not matter and the copy will be made
+ in whatever way is more efficient. */
+PyAPI_FUNC(int) PyObject_CopyData(PyObject *dest, PyObject *src);
+
+/* Copy the data from the src buffer to the buffer of destination. */
+PyAPI_FUNC(int) PyBuffer_IsContiguous(const Py_buffer *view, char fort);
+
+/*Fill the strides array with byte-strides of a contiguous
+ (Fortran-style if fort is 'F' or C-style otherwise)
+ array of the given shape with the given number of bytes
+ per element. */
+PyAPI_FUNC(void) PyBuffer_FillContiguousStrides(int ndims,
+ Py_ssize_t *shape,
+ Py_ssize_t *strides,
+ int itemsize,
+ char fort);
+
+/* Fills in a buffer-info structure correctly for an exporter
+ that can only share a contiguous chunk of memory of
+ "unsigned bytes" of the given length.
+
+ Returns 0 on success and -1 (with raising an error) on error. */
+PyAPI_FUNC(int) PyBuffer_FillInfo(Py_buffer *view, PyObject *o, void *buf,
+ Py_ssize_t len, int readonly,
+ int flags);
+
+/* Releases a Py_buffer obtained from getbuffer ParseTuple's "s*". */
+PyAPI_FUNC(void) PyBuffer_Release(Py_buffer *view);
+
+/* ==== Iterators ================================================ */
+
+#define PyIter_Check(obj) \
+ ((obj)->ob_type->tp_iternext != NULL && \
+ (obj)->ob_type->tp_iternext != &_PyObject_NextNotImplemented)
+
+/* === Number Protocol ================================================== */
+
+#define PyIndex_Check(obj) \
+ ((obj)->ob_type->tp_as_number != NULL && \
+ (obj)->ob_type->tp_as_number->nb_index != NULL)
+
+/* === Sequence protocol ================================================ */
+
+/* Assume tp_as_sequence and sq_item exist and that 'i' does not
+ need to be corrected for a negative index. */
+#define PySequence_ITEM(o, i)\
+ ( Py_TYPE(o)->tp_as_sequence->sq_item(o, i) )
+
+#define PY_ITERSEARCH_COUNT 1
+#define PY_ITERSEARCH_INDEX 2
+#define PY_ITERSEARCH_CONTAINS 3
+
+/* Iterate over seq.
+
+ Result depends on the operation:
+
+ PY_ITERSEARCH_COUNT: return # of times obj appears in seq; -1 if
+ error.
+ PY_ITERSEARCH_INDEX: return 0-based index of first occurrence of
+ obj in seq; set ValueError and return -1 if none found;
+ also return -1 on error.
+ PY_ITERSEARCH_CONTAINS: return 1 if obj in seq, else 0; -1 on
+ error. */
+PyAPI_FUNC(Py_ssize_t) _PySequence_IterSearch(PyObject *seq,
+ PyObject *obj, int operation);
+
+/* === Mapping protocol ================================================= */
+
+PyAPI_FUNC(int) _PyObject_RealIsInstance(PyObject *inst, PyObject *cls);
+
+PyAPI_FUNC(int) _PyObject_RealIsSubclass(PyObject *derived, PyObject *cls);
+
+PyAPI_FUNC(char *const *) _PySequence_BytesToCharpArray(PyObject* self);
+
+PyAPI_FUNC(void) _Py_FreeCharPArray(char *const array[]);
+
+/* For internal use by buffer API functions */
+PyAPI_FUNC(void) _Py_add_one_to_index_F(int nd, Py_ssize_t *index,
+ const Py_ssize_t *shape);
+PyAPI_FUNC(void) _Py_add_one_to_index_C(int nd, Py_ssize_t *index,
+ const Py_ssize_t *shape);
+
+/* Convert Python int to Py_ssize_t. Do nothing if the argument is None. */
+PyAPI_FUNC(int) _Py_convert_optional_to_ssize_t(PyObject *, void *);
+
+#ifdef __cplusplus
+}
+#endif
diff --git a/include/cpython/dictobject.h b/include/cpython/dictobject.h
new file mode 100644
index 0000000..64c012a
--- /dev/null
+++ b/include/cpython/dictobject.h
@@ -0,0 +1,94 @@
+#ifndef Py_CPYTHON_DICTOBJECT_H
+# error "this header file must not be included directly"
+#endif
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+typedef struct _dictkeysobject PyDictKeysObject;
+
+/* The ma_values pointer is NULL for a combined table
+ * or points to an array of PyObject* for a split table
+ */
+typedef struct {
+ PyObject_HEAD
+
+ /* Number of items in the dictionary */
+ Py_ssize_t ma_used;
+
+ /* Dictionary version: globally unique, value change each time
+ the dictionary is modified */
+ uint64_t ma_version_tag;
+
+ PyDictKeysObject *ma_keys;
+
+ /* If ma_values is NULL, the table is "combined": keys and values
+ are stored in ma_keys.
+
+ If ma_values is not NULL, the table is splitted:
+ keys are stored in ma_keys and values are stored in ma_values */
+ PyObject **ma_values;
+} PyDictObject;
+
+PyAPI_FUNC(PyObject *) _PyDict_GetItem_KnownHash(PyObject *mp, PyObject *key,
+ Py_hash_t hash);
+PyAPI_FUNC(PyObject *) _PyDict_GetItemIdWithError(PyObject *dp,
+ struct _Py_Identifier *key);
+PyAPI_FUNC(PyObject *) _PyDict_GetItemStringWithError(PyObject *, const char *);
+PyAPI_FUNC(PyObject *) PyDict_SetDefault(
+ PyObject *mp, PyObject *key, PyObject *defaultobj);
+PyAPI_FUNC(int) _PyDict_SetItem_KnownHash(PyObject *mp, PyObject *key,
+ PyObject *item, Py_hash_t hash);
+PyAPI_FUNC(int) _PyDict_DelItem_KnownHash(PyObject *mp, PyObject *key,
+ Py_hash_t hash);
+PyAPI_FUNC(int) _PyDict_DelItemIf(PyObject *mp, PyObject *key,
+ int (*predicate)(PyObject *value));
+PyDictKeysObject *_PyDict_NewKeysForClass(void);
+PyAPI_FUNC(PyObject *) PyObject_GenericGetDict(PyObject *, void *);
+PyAPI_FUNC(int) _PyDict_Next(
+ PyObject *mp, Py_ssize_t *pos, PyObject **key, PyObject **value, Py_hash_t *hash);
+
+/* Get the number of items of a dictionary. */
+#define PyDict_GET_SIZE(mp) (assert(PyDict_Check(mp)),((PyDictObject *)mp)->ma_used)
+PyAPI_FUNC(int) _PyDict_Contains(PyObject *mp, PyObject *key, Py_hash_t hash);
+PyAPI_FUNC(PyObject *) _PyDict_NewPresized(Py_ssize_t minused);
+PyAPI_FUNC(void) _PyDict_MaybeUntrack(PyObject *mp);
+PyAPI_FUNC(int) _PyDict_HasOnlyStringKeys(PyObject *mp);
+Py_ssize_t _PyDict_KeysSize(PyDictKeysObject *keys);
+PyAPI_FUNC(Py_ssize_t) _PyDict_SizeOf(PyDictObject *);
+PyAPI_FUNC(PyObject *) _PyDict_Pop(PyObject *, PyObject *, PyObject *);
+PyObject *_PyDict_Pop_KnownHash(PyObject *, PyObject *, Py_hash_t, PyObject *);
+PyObject *_PyDict_FromKeys(PyObject *, PyObject *, PyObject *);
+#define _PyDict_HasSplitTable(d) ((d)->ma_values != NULL)
+
+PyAPI_FUNC(int) PyDict_ClearFreeList(void);
+
+/* Like PyDict_Merge, but override can be 0, 1 or 2. If override is 0,
+ the first occurrence of a key wins, if override is 1, the last occurrence
+ of a key wins, if override is 2, a KeyError with conflicting key as
+ argument is raised.
+*/
+PyAPI_FUNC(int) _PyDict_MergeEx(PyObject *mp, PyObject *other, int override);
+PyAPI_FUNC(PyObject *) _PyDict_GetItemId(PyObject *dp, struct _Py_Identifier *key);
+PyAPI_FUNC(int) _PyDict_SetItemId(PyObject *dp, struct _Py_Identifier *key, PyObject *item);
+
+PyAPI_FUNC(int) _PyDict_DelItemId(PyObject *mp, struct _Py_Identifier *key);
+PyAPI_FUNC(void) _PyDict_DebugMallocStats(FILE *out);
+
+int _PyObjectDict_SetItem(PyTypeObject *tp, PyObject **dictptr, PyObject *name, PyObject *value);
+PyObject *_PyDict_LoadGlobal(PyDictObject *, PyDictObject *, PyObject *);
+
+/* _PyDictView */
+
+typedef struct {
+ PyObject_HEAD
+ PyDictObject *dv_dict;
+} _PyDictViewObject;
+
+PyAPI_FUNC(PyObject *) _PyDictView_New(PyObject *, PyTypeObject *);
+PyAPI_FUNC(PyObject *) _PyDictView_Intersect(PyObject* self, PyObject *other);
+
+#ifdef __cplusplus
+}
+#endif
diff --git a/include/cpython/fileobject.h b/include/cpython/fileobject.h
new file mode 100644
index 0000000..57eac13
--- /dev/null
+++ b/include/cpython/fileobject.h
@@ -0,0 +1,32 @@
+#ifndef Py_CPYTHON_FILEOBJECT_H
+# error "this header file must not be included directly"
+#endif
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+PyAPI_FUNC(char *) Py_UniversalNewlineFgets(char *, int, FILE*, PyObject *);
+
+#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03060000
+PyAPI_DATA(const char *) Py_FileSystemDefaultEncodeErrors;
+#endif
+
+#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03070000
+PyAPI_DATA(int) Py_UTF8Mode;
+#endif
+
+/* The std printer acts as a preliminary sys.stderr until the new io
+ infrastructure is in place. */
+PyAPI_FUNC(PyObject *) PyFile_NewStdPrinter(int);
+PyAPI_DATA(PyTypeObject) PyStdPrinter_Type;
+
+typedef PyObject * (*Py_OpenCodeHookFunction)(PyObject *, void *);
+
+PyAPI_FUNC(PyObject *) PyFile_OpenCode(const char *utf8path);
+PyAPI_FUNC(PyObject *) PyFile_OpenCodeObject(PyObject *path);
+PyAPI_FUNC(int) PyFile_SetOpenCodeHook(Py_OpenCodeHookFunction hook, void *userData);
+
+#ifdef __cplusplus
+}
+#endif
diff --git a/include/cpython/initconfig.h b/include/cpython/initconfig.h
new file mode 100644
index 0000000..4b5ceaf
--- /dev/null
+++ b/include/cpython/initconfig.h
@@ -0,0 +1,434 @@
+#ifndef Py_PYCORECONFIG_H
+#define Py_PYCORECONFIG_H
+#ifndef Py_LIMITED_API
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/* --- PyStatus ----------------------------------------------- */
+
+typedef struct {
+ enum {
+ _PyStatus_TYPE_OK=0,
+ _PyStatus_TYPE_ERROR=1,
+ _PyStatus_TYPE_EXIT=2
+ } _type;
+ const char *func;
+ const char *err_msg;
+ int exitcode;
+} PyStatus;
+
+PyAPI_FUNC(PyStatus) PyStatus_Ok(void);
+PyAPI_FUNC(PyStatus) PyStatus_Error(const char *err_msg);
+PyAPI_FUNC(PyStatus) PyStatus_NoMemory(void);
+PyAPI_FUNC(PyStatus) PyStatus_Exit(int exitcode);
+PyAPI_FUNC(int) PyStatus_IsError(PyStatus err);
+PyAPI_FUNC(int) PyStatus_IsExit(PyStatus err);
+PyAPI_FUNC(int) PyStatus_Exception(PyStatus err);
+
+/* --- PyWideStringList ------------------------------------------------ */
+
+typedef struct {
+ /* If length is greater than zero, items must be non-NULL
+ and all items strings must be non-NULL */
+ Py_ssize_t length;
+ wchar_t **items;
+} PyWideStringList;
+
+PyAPI_FUNC(PyStatus) PyWideStringList_Append(PyWideStringList *list,
+ const wchar_t *item);
+PyAPI_FUNC(PyStatus) PyWideStringList_Insert(PyWideStringList *list,
+ Py_ssize_t index,
+ const wchar_t *item);
+
+
+/* --- PyPreConfig ----------------------------------------------- */
+
+typedef struct {
+ int _config_init; /* _PyConfigInitEnum value */
+
+ /* Parse Py_PreInitializeFromBytesArgs() arguments?
+ See PyConfig.parse_argv */
+ int parse_argv;
+
+ /* 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 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;
+
+ /* Set the LC_CTYPE locale to the user preferred locale? If equals to 0,
+ set coerce_c_locale and coerce_c_locale_warn to 0. */
+ int configure_locale;
+
+ /* Coerce the LC_CTYPE locale if it's equal to "C"? (PEP 538)
+
+ Set to 0 by PYTHONCOERCECLOCALE=0. Set to 1 by PYTHONCOERCECLOCALE=1.
+ Set to 2 if the user preferred LC_CTYPE locale is "C".
+
+ If it is equal to 1, LC_CTYPE locale is read to decide if it should be
+ coerced or not (ex: PYTHONCOERCECLOCALE=1). Internally, it is set to 2
+ if the LC_CTYPE locale must be coerced.
+
+ Disable by default (set to 0). Set it to -1 to let Python decide if it
+ should be enabled or not. */
+ int coerce_c_locale;
+
+ /* Emit a warning if the LC_CTYPE locale is coerced?
+
+ Set to 1 by PYTHONCOERCECLOCALE=warn.
+
+ Disable by default (set to 0). Set it to -1 to let Python decide if it
+ should be enabled or not. */
+ int coerce_c_locale_warn;
+
+#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;
+#endif
+
+ /* Enable UTF-8 mode? (PEP 540)
+
+ Disabled by default (equals to 0).
+
+ Set to 1 by "-X utf8" and "-X utf8=1" command line options.
+ Set to 1 by PYTHONUTF8=1 environment variable.
+
+ Set to 0 by "-X utf8=0" and PYTHONUTF8=0.
+
+ If equals to -1, it is set to 1 if the LC_CTYPE locale is "C" or
+ "POSIX", otherwise it is set to 0. Inherit Py_UTF8Mode value value. */
+ int utf8_mode;
+
+ int dev_mode; /* Development mode. PYTHONDEVMODE, -X dev */
+
+ /* Memory allocator: PYTHONMALLOC env var.
+ See PyMemAllocatorName for valid values. */
+ int allocator;
+} PyPreConfig;
+
+PyAPI_FUNC(void) PyPreConfig_InitPythonConfig(PyPreConfig *config);
+PyAPI_FUNC(void) PyPreConfig_InitIsolatedConfig(PyPreConfig *config);
+
+
+/* --- PyConfig ---------------------------------------------- */
+
+typedef struct {
+ int _config_init; /* _PyConfigInitEnum value */
+
+ int isolated; /* Isolated mode? see PyPreConfig.isolated */
+ int use_environment; /* Use environment variables? see PyPreConfig.use_environment */
+ int dev_mode; /* Development mode? See PyPreConfig.dev_mode */
+
+ /* 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 */
+
+ /* Python filesystem encoding and error handler:
+ sys.getfilesystemencoding() and sys.getfilesystemencodeerrors().
+
+ Default encoding and error handler:
+
+ * if Py_SetStandardStreamEncoding() has been called: they have the
+ highest priority;
+ * PYTHONIOENCODING environment variable;
+ * The UTF-8 Mode uses UTF-8/surrogateescape;
+ * If Python forces the usage of the ASCII encoding (ex: C locale
+ or POSIX locale on FreeBSD or HP-UX), use ASCII/surrogateescape;
+ * locale encoding: ANSI code page on Windows, UTF-8 on Android and
+ VxWorks, LC_CTYPE locale encoding on other platforms;
+ * On Windows, "surrogateescape" error handler;
+ * "surrogateescape" error handler if the LC_CTYPE locale is "C" or "POSIX";
+ * "surrogateescape" error handler if the LC_CTYPE locale has been coerced
+ (PEP 538);
+ * "strict" error handler.
+
+ Supported error handlers: "strict", "surrogateescape" and
+ "surrogatepass". The surrogatepass error handler is only supported
+ if Py_DecodeLocale() and Py_EncodeLocale() use directly the UTF-8 codec;
+ it's only used on Windows.
+
+ initfsencoding() updates the encoding to the Python codec name.
+ For example, "ANSI_X3.4-1968" is replaced with "ascii".
+
+ On Windows, sys._enablelegacywindowsfsencoding() sets the
+ encoding/errors to mbcs/replace at runtime.
+
+
+ See Py_FileSystemDefaultEncoding and Py_FileSystemDefaultEncodeErrors.
+ */
+ wchar_t *filesystem_encoding;
+ wchar_t *filesystem_errors;
+
+ wchar_t *pycache_prefix; /* PYTHONPYCACHEPREFIX, -X pycache_prefix=PATH */
+ int parse_argv; /* Parse argv command line arguments? */
+
+ /* Command line arguments (sys.argv).
+
+ Set parse_argv to 1 to parse argv as Python command line arguments
+ and then strip Python arguments from argv.
+
+ If argv is empty, an empty string is added to ensure that sys.argv
+ always exists and is never empty. */
+ PyWideStringList argv;
+
+ /* Program name:
+
+ - If Py_SetProgramName() was called, use its value.
+ - On macOS, use PYTHONEXECUTABLE environment variable if set.
+ - If WITH_NEXT_FRAMEWORK macro is defined, use __PYVENV_LAUNCHER__
+ environment variable is set.
+ - Use argv[0] if available and non-empty.
+ - Use "python" on Windows, or "python3 on other platforms. */
+ wchar_t *program_name;
+
+ PyWideStringList xoptions; /* Command line -X options */
+
+ /* Warnings options: lowest to highest priority. warnings.filters
+ is built in the reverse order (highest to lowest priority). */
+ PyWideStringList warnoptions;
+
+ /* 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
+ site.main() if you want them to be triggered).
+
+ Set to 0 by the -S command line option. If set to -1 (default), it is
+ set to !Py_NoSiteFlag. */
+ int site_import;
+
+ /* Bytes warnings:
+
+ * If equal to 1, issue a warning when comparing bytes or bytearray with
+ str or bytes with int.
+ * If equal or greater to 2, issue an error.
+
+ Incremented by the -b command line option. If set to -1 (default), inherit
+ Py_BytesWarningFlag value. */
+ int bytes_warning;
+
+ /* If greater than 0, enable inspect: when a script is passed as first
+ argument or the -c option is used, enter interactive mode after
+ executing the script or the command, even when sys.stdin does not appear
+ to be a terminal.
+
+ Incremented by the -i command line option. Set to 1 if the PYTHONINSPECT
+ environment variable is non-empty. If set to -1 (default), inherit
+ Py_InspectFlag value. */
+ int inspect;
+
+ /* If greater than 0: enable the interactive mode (REPL).
+
+ Incremented by the -i command line option. If set to -1 (default),
+ inherit Py_InteractiveFlag value. */
+ int interactive;
+
+ /* Optimization level.
+
+ Incremented by the -O command line option. Set by the PYTHONOPTIMIZE
+ environment variable. If set to -1 (default), inherit Py_OptimizeFlag
+ value. */
+ int optimization_level;
+
+ /* If greater than 0, enable the debug mode: turn on parser debugging
+ output (for expert only, depending on compilation options).
+
+ Incremented by the -d command line option. Set by the PYTHONDEBUG
+ environment variable. If set to -1 (default), inherit Py_DebugFlag
+ value. */
+ int parser_debug;
+
+ /* If equal to 0, Python won't try to write ``.pyc`` files on the
+ import of source modules.
+
+ Set to 0 by the -B command line option and the PYTHONDONTWRITEBYTECODE
+ environment variable. If set to -1 (default), it is set to
+ !Py_DontWriteBytecodeFlag. */
+ int write_bytecode;
+
+ /* If greater than 0, enable the verbose mode: print a message each time a
+ module is initialized, showing the place (filename or built-in module)
+ from which it is loaded.
+
+ If greater or equal to 2, print a message for each file that is checked
+ for when searching for a module. Also provides information on module
+ cleanup at exit.
+
+ Incremented by the -v option. Set by the PYTHONVERBOSE environment
+ variable. If set to -1 (default), inherit Py_VerboseFlag value. */
+ int verbose;
+
+ /* If greater than 0, enable the quiet mode: Don't display the copyright
+ and version messages even in interactive mode.
+
+ Incremented by the -q option. If set to -1 (default), inherit
+ Py_QuietFlag value. */
+ int quiet;
+
+ /* If greater than 0, don't add the user site-packages directory to
+ sys.path.
+
+ Set to 0 by the -s and -I command line options , and the PYTHONNOUSERSITE
+ environment variable. If set to -1 (default), it is set to
+ !Py_NoUserSiteDirectory. */
+ int user_site_directory;
+
+ /* If non-zero, configure C standard steams (stdio, stdout,
+ stderr):
+
+ - Set O_BINARY mode on Windows.
+ - If buffered_stdio is equal to zero, make streams unbuffered.
+ Otherwise, enable streams buffering if interactive is non-zero. */
+ int configure_c_stdio;
+
+ /* If equal to 0, enable unbuffered mode: force the stdout and stderr
+ streams to be unbuffered.
+
+ Set to 0 by the -u option. Set by the PYTHONUNBUFFERED environment
+ variable.
+ 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. */
+ wchar_t *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. */
+ wchar_t *stdio_errors;
+
+#ifdef MS_WINDOWS
+ /* 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
+
+ /* Value of the --check-hash-based-pycs command line option:
+
+ - "default" means the 'check_source' flag in hash-based pycs
+ determines invalidation
+ - "always" causes the interpreter to hash the source file for
+ invalidation regardless of value of 'check_source' bit
+ - "never" causes the interpreter to always assume hash-based pycs are
+ valid
+
+ The default value is "default".
+
+ See PEP 552 "Deterministic pycs" for more details. */
+ wchar_t *check_hash_pycs_mode;
+
+ /* --- Path configuration inputs ------------ */
+
+ /* If greater than 0, suppress _PyPathConfig_Calculate() warnings on Unix.
+ The parameter has no effect on Windows.
+
+ If set to -1 (default), inherit !Py_FrozenFlag value. */
+ int pathconfig_warnings;
+
+ wchar_t *pythonpath_env; /* PYTHONPATH environment variable */
+ wchar_t *home; /* PYTHONHOME environment variable,
+ see also Py_SetPythonHome(). */
+
+ /* --- Path configuration outputs ----------- */
+
+ int module_search_paths_set; /* If non-zero, use module_search_paths */
+ PyWideStringList module_search_paths; /* sys.path paths. Computed if
+ module_search_paths_set is equal
+ to zero. */
+
+ wchar_t *executable; /* sys.executable */
+ wchar_t *base_executable; /* sys._base_executable */
+ wchar_t *prefix; /* sys.prefix */
+ wchar_t *base_prefix; /* sys.base_prefix */
+ wchar_t *exec_prefix; /* sys.exec_prefix */
+ wchar_t *base_exec_prefix; /* sys.base_exec_prefix */
+
+ /* --- Parameter only used by Py_Main() ---------- */
+
+ /* Skip the first line of the source ('run_filename' parameter), allowing use of non-Unix forms of
+ "#!cmd". This is intended for a DOS specific hack only.
+
+ Set by the -x command line option. */
+ int skip_source_first_line;
+
+ 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 ---------------------------- */
+
+ /* Install importlib? If set to 0, importlib is not initialized at all.
+ Needed by freeze_importlib. */
+ int _install_importlib;
+
+ /* If equal to 0, stop Python initialization before the "main" phase */
+ int _init_main;
+} PyConfig;
+
+PyAPI_FUNC(void) PyConfig_InitPythonConfig(PyConfig *config);
+PyAPI_FUNC(void) PyConfig_InitIsolatedConfig(PyConfig *config);
+PyAPI_FUNC(void) PyConfig_Clear(PyConfig *);
+PyAPI_FUNC(PyStatus) PyConfig_SetString(
+ PyConfig *config,
+ wchar_t **config_str,
+ const wchar_t *str);
+PyAPI_FUNC(PyStatus) PyConfig_SetBytesString(
+ PyConfig *config,
+ wchar_t **config_str,
+ const char *str);
+PyAPI_FUNC(PyStatus) PyConfig_Read(PyConfig *config);
+PyAPI_FUNC(PyStatus) PyConfig_SetBytesArgv(
+ PyConfig *config,
+ Py_ssize_t argc,
+ char * const *argv);
+PyAPI_FUNC(PyStatus) PyConfig_SetArgv(PyConfig *config,
+ Py_ssize_t argc,
+ wchar_t * const *argv);
+PyAPI_FUNC(PyStatus) PyConfig_SetWideStringList(PyConfig *config,
+ PyWideStringList *list,
+ Py_ssize_t length, wchar_t **items);
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_LIMITED_API */
+#endif /* !Py_PYCORECONFIG_H */
diff --git a/include/cpython/interpreteridobject.h b/include/cpython/interpreteridobject.h
new file mode 100644
index 0000000..67ec587
--- /dev/null
+++ b/include/cpython/interpreteridobject.h
@@ -0,0 +1,19 @@
+#ifndef Py_CPYTHON_INTERPRETERIDOBJECT_H
+# error "this header file must not be included directly"
+#endif
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/* Interpreter ID Object */
+
+PyAPI_DATA(PyTypeObject) _PyInterpreterID_Type;
+
+PyAPI_FUNC(PyObject *) _PyInterpreterID_New(int64_t);
+PyAPI_FUNC(PyObject *) _PyInterpreterState_GetIDObject(PyInterpreterState *);
+PyAPI_FUNC(PyInterpreterState *) _PyInterpreterID_LookUp(PyObject *);
+
+#ifdef __cplusplus
+}
+#endif
diff --git a/include/cpython/object.h b/include/cpython/object.h
new file mode 100644
index 0000000..5a0ac4a
--- /dev/null
+++ b/include/cpython/object.h
@@ -0,0 +1,470 @@
+#ifndef Py_CPYTHON_OBJECT_H
+# error "this header file must not be included directly"
+#endif
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/********************* String Literals ****************************************/
+/* This structure helps managing static strings. The basic usage goes like this:
+ Instead of doing
+
+ r = PyObject_CallMethod(o, "foo", "args", ...);
+
+ do
+
+ _Py_IDENTIFIER(foo);
+ ...
+ r = _PyObject_CallMethodId(o, &PyId_foo, "args", ...);
+
+ PyId_foo is a static variable, either on block level or file level. On first
+ usage, the string "foo" is interned, and the structures are linked. On interpreter
+ shutdown, all strings are released (through _PyUnicode_ClearStaticStrings).
+
+ Alternatively, _Py_static_string allows choosing the variable name.
+ _PyUnicode_FromId returns a borrowed reference to the interned string.
+ _PyObject_{Get,Set,Has}AttrId are __getattr__ versions using _Py_Identifier*.
+*/
+typedef struct _Py_Identifier {
+ struct _Py_Identifier *next;
+ const char* string;
+ PyObject *object;
+} _Py_Identifier;
+
+#define _Py_static_string_init(value) { .next = NULL, .string = value, .object = NULL }
+#define _Py_static_string(varname, value) static _Py_Identifier varname = _Py_static_string_init(value)
+#define _Py_IDENTIFIER(varname) _Py_static_string(PyId_##varname, #varname)
+
+/* buffer interface */
+typedef struct bufferinfo {
+ void *buf;
+ PyObject *obj; /* owned reference */
+ Py_ssize_t len;
+ Py_ssize_t itemsize; /* This is Py_ssize_t so it can be
+ pointed to by strides in simple case.*/
+ int readonly;
+ int ndim;
+ char *format;
+ Py_ssize_t *shape;
+ Py_ssize_t *strides;
+ Py_ssize_t *suboffsets;
+ void *internal;
+} Py_buffer;
+
+typedef int (*getbufferproc)(PyObject *, Py_buffer *, int);
+typedef void (*releasebufferproc)(PyObject *, Py_buffer *);
+
+typedef PyObject *(*vectorcallfunc)(PyObject *callable, PyObject *const *args,
+ size_t nargsf, PyObject *kwnames);
+
+/* Maximum number of dimensions */
+#define PyBUF_MAX_NDIM 64
+
+/* Flags for getting buffers */
+#define PyBUF_SIMPLE 0
+#define PyBUF_WRITABLE 0x0001
+/* we used to include an E, backwards compatible alias */
+#define PyBUF_WRITEABLE PyBUF_WRITABLE
+#define PyBUF_FORMAT 0x0004
+#define PyBUF_ND 0x0008
+#define PyBUF_STRIDES (0x0010 | PyBUF_ND)
+#define PyBUF_C_CONTIGUOUS (0x0020 | PyBUF_STRIDES)
+#define PyBUF_F_CONTIGUOUS (0x0040 | PyBUF_STRIDES)
+#define PyBUF_ANY_CONTIGUOUS (0x0080 | PyBUF_STRIDES)
+#define PyBUF_INDIRECT (0x0100 | PyBUF_STRIDES)
+
+#define PyBUF_CONTIG (PyBUF_ND | PyBUF_WRITABLE)
+#define PyBUF_CONTIG_RO (PyBUF_ND)
+
+#define PyBUF_STRIDED (PyBUF_STRIDES | PyBUF_WRITABLE)
+#define PyBUF_STRIDED_RO (PyBUF_STRIDES)
+
+#define PyBUF_RECORDS (PyBUF_STRIDES | PyBUF_WRITABLE | PyBUF_FORMAT)
+#define PyBUF_RECORDS_RO (PyBUF_STRIDES | PyBUF_FORMAT)
+
+#define PyBUF_FULL (PyBUF_INDIRECT | PyBUF_WRITABLE | PyBUF_FORMAT)
+#define PyBUF_FULL_RO (PyBUF_INDIRECT | PyBUF_FORMAT)
+
+
+#define PyBUF_READ 0x100
+#define PyBUF_WRITE 0x200
+/* End buffer interface */
+
+
+typedef struct {
+ /* Number implementations must check *both*
+ arguments for proper type and implement the necessary conversions
+ in the slot functions themselves. */
+
+ binaryfunc nb_add;
+ binaryfunc nb_subtract;
+ binaryfunc nb_multiply;
+ binaryfunc nb_remainder;
+ binaryfunc nb_divmod;
+ ternaryfunc nb_power;
+ unaryfunc nb_negative;
+ unaryfunc nb_positive;
+ unaryfunc nb_absolute;
+ inquiry nb_bool;
+ unaryfunc nb_invert;
+ binaryfunc nb_lshift;
+ binaryfunc nb_rshift;
+ binaryfunc nb_and;
+ binaryfunc nb_xor;
+ binaryfunc nb_or;
+ unaryfunc nb_int;
+ void *nb_reserved; /* the slot formerly known as nb_long */
+ unaryfunc nb_float;
+
+ binaryfunc nb_inplace_add;
+ binaryfunc nb_inplace_subtract;
+ binaryfunc nb_inplace_multiply;
+ binaryfunc nb_inplace_remainder;
+ ternaryfunc nb_inplace_power;
+ binaryfunc nb_inplace_lshift;
+ binaryfunc nb_inplace_rshift;
+ binaryfunc nb_inplace_and;
+ binaryfunc nb_inplace_xor;
+ binaryfunc nb_inplace_or;
+
+ binaryfunc nb_floor_divide;
+ binaryfunc nb_true_divide;
+ binaryfunc nb_inplace_floor_divide;
+ binaryfunc nb_inplace_true_divide;
+
+ unaryfunc nb_index;
+
+ binaryfunc nb_matrix_multiply;
+ binaryfunc nb_inplace_matrix_multiply;
+} PyNumberMethods;
+
+typedef struct {
+ lenfunc sq_length;
+ binaryfunc sq_concat;
+ ssizeargfunc sq_repeat;
+ ssizeargfunc sq_item;
+ void *was_sq_slice;
+ ssizeobjargproc sq_ass_item;
+ void *was_sq_ass_slice;
+ objobjproc sq_contains;
+
+ binaryfunc sq_inplace_concat;
+ ssizeargfunc sq_inplace_repeat;
+} PySequenceMethods;
+
+typedef struct {
+ lenfunc mp_length;
+ binaryfunc mp_subscript;
+ objobjargproc mp_ass_subscript;
+} PyMappingMethods;
+
+typedef struct {
+ unaryfunc am_await;
+ unaryfunc am_aiter;
+ unaryfunc am_anext;
+} PyAsyncMethods;
+
+typedef struct {
+ getbufferproc bf_getbuffer;
+ releasebufferproc bf_releasebuffer;
+} PyBufferProcs;
+
+/* Allow printfunc in the tp_vectorcall_offset slot for
+ * backwards-compatibility */
+typedef Py_ssize_t printfunc;
+
+typedef struct _typeobject {
+ PyObject_VAR_HEAD
+ const char *tp_name; /* For printing, in format "<module>.<name>" */
+ Py_ssize_t tp_basicsize, tp_itemsize; /* For allocation */
+
+ /* Methods to implement standard operations */
+
+ destructor tp_dealloc;
+ Py_ssize_t tp_vectorcall_offset;
+ getattrfunc tp_getattr;
+ setattrfunc tp_setattr;
+ PyAsyncMethods *tp_as_async; /* formerly known as tp_compare (Python 2)
+ or tp_reserved (Python 3) */
+ reprfunc tp_repr;
+
+ /* Method suites for standard classes */
+
+ PyNumberMethods *tp_as_number;
+ PySequenceMethods *tp_as_sequence;
+ PyMappingMethods *tp_as_mapping;
+
+ /* More standard operations (here for binary compatibility) */
+
+ hashfunc tp_hash;
+ ternaryfunc tp_call;
+ reprfunc tp_str;
+ getattrofunc tp_getattro;
+ setattrofunc tp_setattro;
+
+ /* Functions to access object as input/output buffer */
+ PyBufferProcs *tp_as_buffer;
+
+ /* Flags to define presence of optional/expanded features */
+ unsigned long tp_flags;
+
+ const char *tp_doc; /* Documentation string */
+
+ /* Assigned meaning in release 2.0 */
+ /* call function for all accessible objects */
+ traverseproc tp_traverse;
+
+ /* delete references to contained objects */
+ inquiry tp_clear;
+
+ /* Assigned meaning in release 2.1 */
+ /* rich comparisons */
+ richcmpfunc tp_richcompare;
+
+ /* weak reference enabler */
+ Py_ssize_t tp_weaklistoffset;
+
+ /* Iterators */
+ getiterfunc tp_iter;
+ iternextfunc tp_iternext;
+
+ /* Attribute descriptor and subclassing stuff */
+ struct PyMethodDef *tp_methods;
+ struct PyMemberDef *tp_members;
+ struct PyGetSetDef *tp_getset;
+ struct _typeobject *tp_base;
+ PyObject *tp_dict;
+ descrgetfunc tp_descr_get;
+ descrsetfunc tp_descr_set;
+ Py_ssize_t tp_dictoffset;
+ initproc tp_init;
+ allocfunc tp_alloc;
+ newfunc tp_new;
+ freefunc tp_free; /* Low-level free-memory routine */
+ inquiry tp_is_gc; /* For PyObject_IS_GC */
+ PyObject *tp_bases;
+ PyObject *tp_mro; /* method resolution order */
+ PyObject *tp_cache;
+ PyObject *tp_subclasses;
+ PyObject *tp_weaklist;
+ destructor tp_del;
+
+ /* Type attribute cache version tag. Added in version 2.6 */
+ unsigned int tp_version_tag;
+
+ destructor tp_finalize;
+ vectorcallfunc tp_vectorcall;
+
+ /* bpo-37250: kept for backwards compatibility in CPython 3.8 only */
+ Py_DEPRECATED(3.8) int (*tp_print)(PyObject *, FILE *, int);
+
+#ifdef COUNT_ALLOCS
+ /* these must be last and never explicitly initialized */
+ Py_ssize_t tp_allocs;
+ Py_ssize_t tp_frees;
+ Py_ssize_t tp_maxalloc;
+ struct _typeobject *tp_prev;
+ struct _typeobject *tp_next;
+#endif
+} PyTypeObject;
+
+/* The *real* layout of a type object when allocated on the heap */
+typedef struct _heaptypeobject {
+ /* Note: there's a dependency on the order of these members
+ in slotptr() in typeobject.c . */
+ PyTypeObject ht_type;
+ PyAsyncMethods as_async;
+ PyNumberMethods as_number;
+ PyMappingMethods as_mapping;
+ PySequenceMethods as_sequence; /* as_sequence comes after as_mapping,
+ so that the mapping wins when both
+ the mapping and the sequence define
+ a given operator (e.g. __getitem__).
+ see add_operators() in typeobject.c . */
+ PyBufferProcs as_buffer;
+ PyObject *ht_name, *ht_slots, *ht_qualname;
+ struct _dictkeysobject *ht_cached_keys;
+ /* here are optional user slots, followed by the members. */
+} PyHeapTypeObject;
+
+/* access macro to the members which are floating "behind" the object */
+#define PyHeapType_GET_MEMBERS(etype) \
+ ((PyMemberDef *)(((char *)etype) + Py_TYPE(etype)->tp_basicsize))
+
+PyAPI_FUNC(const char *) _PyType_Name(PyTypeObject *);
+PyAPI_FUNC(PyObject *) _PyType_Lookup(PyTypeObject *, PyObject *);
+PyAPI_FUNC(PyObject *) _PyType_LookupId(PyTypeObject *, _Py_Identifier *);
+PyAPI_FUNC(PyObject *) _PyObject_LookupSpecial(PyObject *, _Py_Identifier *);
+PyAPI_FUNC(PyTypeObject *) _PyType_CalculateMetaclass(PyTypeObject *, PyObject *);
+PyAPI_FUNC(PyObject *) _PyType_GetDocFromInternalDoc(const char *, const char *);
+PyAPI_FUNC(PyObject *) _PyType_GetTextSignatureFromInternalDoc(const char *, const char *);
+
+struct _Py_Identifier;
+PyAPI_FUNC(int) PyObject_Print(PyObject *, FILE *, int);
+PyAPI_FUNC(void) _Py_BreakPoint(void);
+PyAPI_FUNC(void) _PyObject_Dump(PyObject *);
+PyAPI_FUNC(int) _PyObject_IsFreed(PyObject *);
+
+PyAPI_FUNC(int) _PyObject_IsAbstract(PyObject *);
+PyAPI_FUNC(PyObject *) _PyObject_GetAttrId(PyObject *, struct _Py_Identifier *);
+PyAPI_FUNC(int) _PyObject_SetAttrId(PyObject *, struct _Py_Identifier *, PyObject *);
+PyAPI_FUNC(int) _PyObject_HasAttrId(PyObject *, struct _Py_Identifier *);
+/* Replacements of PyObject_GetAttr() and _PyObject_GetAttrId() which
+ don't raise AttributeError.
+
+ Return 1 and set *result != NULL if an attribute is found.
+ Return 0 and set *result == NULL if an attribute is not found;
+ an AttributeError is silenced.
+ Return -1 and set *result == NULL if an error other than AttributeError
+ is raised.
+*/
+PyAPI_FUNC(int) _PyObject_LookupAttr(PyObject *, PyObject *, PyObject **);
+PyAPI_FUNC(int) _PyObject_LookupAttrId(PyObject *, struct _Py_Identifier *, PyObject **);
+PyAPI_FUNC(PyObject **) _PyObject_GetDictPtr(PyObject *);
+PyAPI_FUNC(PyObject *) _PyObject_NextNotImplemented(PyObject *);
+PyAPI_FUNC(void) PyObject_CallFinalizer(PyObject *);
+PyAPI_FUNC(int) PyObject_CallFinalizerFromDealloc(PyObject *);
+
+/* Same as PyObject_Generic{Get,Set}Attr, but passing the attributes
+ dict as the last parameter. */
+PyAPI_FUNC(PyObject *)
+_PyObject_GenericGetAttrWithDict(PyObject *, PyObject *, PyObject *, int);
+PyAPI_FUNC(int)
+_PyObject_GenericSetAttrWithDict(PyObject *, PyObject *,
+ PyObject *, PyObject *);
+
+#define PyType_HasFeature(t,f) (((t)->tp_flags & (f)) != 0)
+
+static inline void _Py_Dealloc_inline(PyObject *op)
+{
+ destructor dealloc = Py_TYPE(op)->tp_dealloc;
+#ifdef Py_TRACE_REFS
+ _Py_ForgetReference(op);
+#else
+ _Py_INC_TPFREES(op);
+#endif
+ (*dealloc)(op);
+}
+#define _Py_Dealloc(op) _Py_Dealloc_inline(op)
+
+
+/* Safely decref `op` and set `op` to `op2`.
+ *
+ * As in case of Py_CLEAR "the obvious" code can be deadly:
+ *
+ * Py_DECREF(op);
+ * op = op2;
+ *
+ * The safe way is:
+ *
+ * Py_SETREF(op, op2);
+ *
+ * That arranges to set `op` to `op2` _before_ decref'ing, so that any code
+ * triggered as a side-effect of `op` getting torn down no longer believes
+ * `op` points to a valid object.
+ *
+ * Py_XSETREF is a variant of Py_SETREF that uses Py_XDECREF instead of
+ * Py_DECREF.
+ */
+
+#define Py_SETREF(op, op2) \
+ do { \
+ PyObject *_py_tmp = _PyObject_CAST(op); \
+ (op) = (op2); \
+ Py_DECREF(_py_tmp); \
+ } while (0)
+
+#define Py_XSETREF(op, op2) \
+ do { \
+ PyObject *_py_tmp = _PyObject_CAST(op); \
+ (op) = (op2); \
+ Py_XDECREF(_py_tmp); \
+ } while (0)
+
+
+PyAPI_DATA(PyTypeObject) _PyNone_Type;
+PyAPI_DATA(PyTypeObject) _PyNotImplemented_Type;
+
+/* Maps Py_LT to Py_GT, ..., Py_GE to Py_LE.
+ * Defined in object.c.
+ */
+PyAPI_DATA(int) _Py_SwappedOp[];
+
+/* This is the old private API, invoked by the macros before 3.2.4.
+ Kept for binary compatibility of extensions using the stable ABI. */
+PyAPI_FUNC(void) _PyTrash_deposit_object(PyObject*);
+PyAPI_FUNC(void) _PyTrash_destroy_chain(void);
+
+PyAPI_FUNC(void)
+_PyDebugAllocatorStats(FILE *out, const char *block_name, int num_blocks,
+ size_t sizeof_block);
+PyAPI_FUNC(void)
+_PyObject_DebugTypeStats(FILE *out);
+
+/* Define a pair of assertion macros:
+ _PyObject_ASSERT_FROM(), _PyObject_ASSERT_WITH_MSG() and _PyObject_ASSERT().
+
+ These work like the regular C assert(), in that they will abort the
+ process with a message on stderr if the given condition fails to hold,
+ but compile away to nothing if NDEBUG is defined.
+
+ However, before aborting, Python will also try to call _PyObject_Dump() on
+ the given object. This may be of use when investigating bugs in which a
+ particular object is corrupt (e.g. buggy a tp_visit method in an extension
+ module breaking the garbage collector), to help locate the broken objects.
+
+ The WITH_MSG variant allows you to supply an additional message that Python
+ will attempt to print to stderr, after the object dump. */
+#ifdef NDEBUG
+ /* No debugging: compile away the assertions: */
+# define _PyObject_ASSERT_FROM(obj, expr, msg, filename, lineno, func) \
+ ((void)0)
+#else
+ /* With debugging: generate checks: */
+# define _PyObject_ASSERT_FROM(obj, expr, msg, filename, lineno, func) \
+ ((expr) \
+ ? (void)(0) \
+ : _PyObject_AssertFailed((obj), Py_STRINGIFY(expr), \
+ (msg), (filename), (lineno), (func)))
+#endif
+
+#define _PyObject_ASSERT_WITH_MSG(obj, expr, msg) \
+ _PyObject_ASSERT_FROM(obj, expr, msg, __FILE__, __LINE__, __func__)
+#define _PyObject_ASSERT(obj, expr) \
+ _PyObject_ASSERT_WITH_MSG(obj, expr, NULL)
+
+#define _PyObject_ASSERT_FAILED_MSG(obj, msg) \
+ _PyObject_AssertFailed((obj), NULL, (msg), __FILE__, __LINE__, __func__)
+
+/* Declare and define _PyObject_AssertFailed() even when NDEBUG is defined,
+ to avoid causing compiler/linker errors when building extensions without
+ NDEBUG against a Python built with NDEBUG defined.
+
+ msg, expr and function can be NULL. */
+PyAPI_FUNC(void) _PyObject_AssertFailed(
+ PyObject *obj,
+ const char *expr,
+ const char *msg,
+ const char *file,
+ int line,
+ const char *function);
+
+/* Check if an object is consistent. For example, ensure that the reference
+ counter is greater than or equal to 1, and ensure that ob_type is not NULL.
+
+ Call _PyObject_AssertFailed() if the object is inconsistent.
+
+ If check_content is zero, only check header fields: reduce the overhead.
+
+ The function always return 1. The return value is just here to be able to
+ write:
+
+ assert(_PyObject_CheckConsistency(obj, 1)); */
+PyAPI_FUNC(int) _PyObject_CheckConsistency(
+ PyObject *op,
+ int check_content);
+
+#ifdef __cplusplus
+}
+#endif
diff --git a/include/cpython/objimpl.h b/include/cpython/objimpl.h
new file mode 100644
index 0000000..f121922
--- /dev/null
+++ b/include/cpython/objimpl.h
@@ -0,0 +1,113 @@
+#ifndef Py_CPYTHON_OBJIMPL_H
+# error "this header file must not be included directly"
+#endif
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/* This function returns the number of allocated memory blocks, regardless of size */
+PyAPI_FUNC(Py_ssize_t) _Py_GetAllocatedBlocks(void);
+
+/* Macros */
+#ifdef WITH_PYMALLOC
+PyAPI_FUNC(int) _PyObject_DebugMallocStats(FILE *out);
+#endif
+
+
+typedef struct {
+ /* user context passed as the first argument to the 2 functions */
+ void *ctx;
+
+ /* allocate an arena of size bytes */
+ void* (*alloc) (void *ctx, size_t size);
+
+ /* free an arena */
+ void (*free) (void *ctx, void *ptr, size_t size);
+} PyObjectArenaAllocator;
+
+/* Get the arena allocator. */
+PyAPI_FUNC(void) PyObject_GetArenaAllocator(PyObjectArenaAllocator *allocator);
+
+/* Set the arena allocator. */
+PyAPI_FUNC(void) PyObject_SetArenaAllocator(PyObjectArenaAllocator *allocator);
+
+
+PyAPI_FUNC(Py_ssize_t) _PyGC_CollectNoFail(void);
+PyAPI_FUNC(Py_ssize_t) _PyGC_CollectIfEnabled(void);
+
+
+/* Test if an object has a GC head */
+#define PyObject_IS_GC(o) \
+ (PyType_IS_GC(Py_TYPE(o)) \
+ && (Py_TYPE(o)->tp_is_gc == NULL || Py_TYPE(o)->tp_is_gc(o)))
+
+/* GC information is stored BEFORE the object structure. */
+typedef struct {
+ // Pointer to next object in the list.
+ // 0 means the object is not tracked
+ uintptr_t _gc_next;
+
+ // Pointer to previous object in the list.
+ // Lowest two bits are used for flags documented later.
+ uintptr_t _gc_prev;
+} PyGC_Head;
+
+#define _Py_AS_GC(o) ((PyGC_Head *)(o)-1)
+
+/* True if the object is currently tracked by the GC. */
+#define _PyObject_GC_IS_TRACKED(o) (_Py_AS_GC(o)->_gc_next != 0)
+
+/* True if the object may be tracked by the GC in the future, or already is.
+ This can be useful to implement some optimizations. */
+#define _PyObject_GC_MAY_BE_TRACKED(obj) \
+ (PyObject_IS_GC(obj) && \
+ (!PyTuple_CheckExact(obj) || _PyObject_GC_IS_TRACKED(obj)))
+
+
+/* Bit flags for _gc_prev */
+/* Bit 0 is set when tp_finalize is called */
+#define _PyGC_PREV_MASK_FINALIZED (1)
+/* Bit 1 is set when the object is in generation which is GCed currently. */
+#define _PyGC_PREV_MASK_COLLECTING (2)
+/* The (N-2) most significant bits contain the real address. */
+#define _PyGC_PREV_SHIFT (2)
+#define _PyGC_PREV_MASK (((uintptr_t) -1) << _PyGC_PREV_SHIFT)
+
+// Lowest bit of _gc_next is used for flags only in GC.
+// But it is always 0 for normal code.
+#define _PyGCHead_NEXT(g) ((PyGC_Head*)(g)->_gc_next)
+#define _PyGCHead_SET_NEXT(g, p) ((g)->_gc_next = (uintptr_t)(p))
+
+// Lowest two bits of _gc_prev is used for _PyGC_PREV_MASK_* flags.
+#define _PyGCHead_PREV(g) ((PyGC_Head*)((g)->_gc_prev & _PyGC_PREV_MASK))
+#define _PyGCHead_SET_PREV(g, p) do { \
+ assert(((uintptr_t)p & ~_PyGC_PREV_MASK) == 0); \
+ (g)->_gc_prev = ((g)->_gc_prev & ~_PyGC_PREV_MASK) \
+ | ((uintptr_t)(p)); \
+ } while (0)
+
+#define _PyGCHead_FINALIZED(g) \
+ (((g)->_gc_prev & _PyGC_PREV_MASK_FINALIZED) != 0)
+#define _PyGCHead_SET_FINALIZED(g) \
+ ((g)->_gc_prev |= _PyGC_PREV_MASK_FINALIZED)
+
+#define _PyGC_FINALIZED(o) \
+ _PyGCHead_FINALIZED(_Py_AS_GC(o))
+#define _PyGC_SET_FINALIZED(o) \
+ _PyGCHead_SET_FINALIZED(_Py_AS_GC(o))
+
+
+PyAPI_FUNC(PyObject *) _PyObject_GC_Malloc(size_t size);
+PyAPI_FUNC(PyObject *) _PyObject_GC_Calloc(size_t size);
+
+
+/* Test if a type supports weak references */
+#define PyType_SUPPORTS_WEAKREFS(t) ((t)->tp_weaklistoffset > 0)
+
+#define PyObject_GET_WEAKREFS_LISTPTR(o) \
+ ((PyObject **) (((char *) (o)) + Py_TYPE(o)->tp_weaklistoffset))
+
+#ifdef __cplusplus
+}
+#endif
diff --git a/include/cpython/pyerrors.h b/include/cpython/pyerrors.h
new file mode 100644
index 0000000..e3098b3
--- /dev/null
+++ b/include/cpython/pyerrors.h
@@ -0,0 +1,182 @@
+#ifndef Py_CPYTHON_ERRORS_H
+# error "this header file must not be included directly"
+#endif
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/* Error objects */
+
+/* PyException_HEAD defines the initial segment of every exception class. */
+#define PyException_HEAD PyObject_HEAD PyObject *dict;\
+ PyObject *args; PyObject *traceback;\
+ PyObject *context; PyObject *cause;\
+ char suppress_context;
+
+typedef struct {
+ PyException_HEAD
+} PyBaseExceptionObject;
+
+typedef struct {
+ PyException_HEAD
+ PyObject *msg;
+ PyObject *filename;
+ PyObject *lineno;
+ PyObject *offset;
+ PyObject *text;
+ PyObject *print_file_and_line;
+} PySyntaxErrorObject;
+
+typedef struct {
+ PyException_HEAD
+ PyObject *msg;
+ PyObject *name;
+ PyObject *path;
+} PyImportErrorObject;
+
+typedef struct {
+ PyException_HEAD
+ PyObject *encoding;
+ PyObject *object;
+ Py_ssize_t start;
+ Py_ssize_t end;
+ PyObject *reason;
+} PyUnicodeErrorObject;
+
+typedef struct {
+ PyException_HEAD
+ PyObject *code;
+} PySystemExitObject;
+
+typedef struct {
+ PyException_HEAD
+ PyObject *myerrno;
+ PyObject *strerror;
+ PyObject *filename;
+ PyObject *filename2;
+#ifdef MS_WINDOWS
+ PyObject *winerror;
+#endif
+ Py_ssize_t written; /* only for BlockingIOError, -1 otherwise */
+} PyOSErrorObject;
+
+typedef struct {
+ PyException_HEAD
+ PyObject *value;
+} PyStopIterationObject;
+
+/* Compatibility typedefs */
+typedef PyOSErrorObject PyEnvironmentErrorObject;
+#ifdef MS_WINDOWS
+typedef PyOSErrorObject PyWindowsErrorObject;
+#endif
+
+/* Error handling definitions */
+
+PyAPI_FUNC(void) _PyErr_SetKeyError(PyObject *);
+_PyErr_StackItem *_PyErr_GetTopmostException(PyThreadState *tstate);
+
+/* Context manipulation (PEP 3134) */
+
+PyAPI_FUNC(void) _PyErr_ChainExceptions(PyObject *, PyObject *, PyObject *);
+
+/* */
+
+#define PyExceptionClass_Name(x) (((PyTypeObject*)(x))->tp_name)
+
+/* Convenience functions */
+
+#ifdef MS_WINDOWS
+Py_DEPRECATED(3.3)
+PyAPI_FUNC(PyObject *) PyErr_SetFromErrnoWithUnicodeFilename(
+ PyObject *, const Py_UNICODE *);
+#endif /* MS_WINDOWS */
+
+/* Like PyErr_Format(), but saves current exception as __context__ and
+ __cause__.
+ */
+PyAPI_FUNC(PyObject *) _PyErr_FormatFromCause(
+ PyObject *exception,
+ const char *format, /* ASCII-encoded string */
+ ...
+ );
+
+#ifdef MS_WINDOWS
+/* XXX redeclare to use WSTRING */
+Py_DEPRECATED(3.3)
+PyAPI_FUNC(PyObject *) PyErr_SetFromWindowsErrWithUnicodeFilename(
+ int, const Py_UNICODE *);
+Py_DEPRECATED(3.3)
+PyAPI_FUNC(PyObject *) PyErr_SetExcFromWindowsErrWithUnicodeFilename(
+ PyObject *,int, const Py_UNICODE *);
+#endif
+
+/* In exceptions.c */
+
+/* Helper that attempts to replace the current exception with one of the
+ * same type but with a prefix added to the exception text. The resulting
+ * exception description looks like:
+ *
+ * prefix (exc_type: original_exc_str)
+ *
+ * Only some exceptions can be safely replaced. If the function determines
+ * it isn't safe to perform the replacement, it will leave the original
+ * unmodified exception in place.
+ *
+ * Returns a borrowed reference to the new exception (if any), NULL if the
+ * existing exception was left in place.
+ */
+PyAPI_FUNC(PyObject *) _PyErr_TrySetFromCause(
+ const char *prefix_format, /* ASCII-encoded string */
+ ...
+ );
+
+/* In signalmodule.c */
+
+int PySignal_SetWakeupFd(int fd);
+PyAPI_FUNC(int) _PyErr_CheckSignals(void);
+
+/* Support for adding program text to SyntaxErrors */
+
+PyAPI_FUNC(void) PyErr_SyntaxLocationObject(
+ PyObject *filename,
+ int lineno,
+ int col_offset);
+
+PyAPI_FUNC(PyObject *) PyErr_ProgramTextObject(
+ PyObject *filename,
+ int lineno);
+
+/* Create a UnicodeEncodeError object */
+Py_DEPRECATED(3.3) PyAPI_FUNC(PyObject *) PyUnicodeEncodeError_Create(
+ const char *encoding, /* UTF-8 encoded string */
+ const Py_UNICODE *object,
+ Py_ssize_t length,
+ Py_ssize_t start,
+ Py_ssize_t end,
+ const char *reason /* UTF-8 encoded string */
+ );
+
+/* Create a UnicodeTranslateError object */
+Py_DEPRECATED(3.3) PyAPI_FUNC(PyObject *) PyUnicodeTranslateError_Create(
+ const Py_UNICODE *object,
+ Py_ssize_t length,
+ Py_ssize_t start,
+ Py_ssize_t end,
+ const char *reason /* UTF-8 encoded string */
+ );
+PyAPI_FUNC(PyObject *) _PyUnicodeTranslateError_Create(
+ PyObject *object,
+ Py_ssize_t start,
+ Py_ssize_t end,
+ const char *reason /* UTF-8 encoded string */
+ );
+
+PyAPI_FUNC(void) _PyErr_WriteUnraisableMsg(
+ const char *err_msg,
+ PyObject *obj);
+
+#ifdef __cplusplus
+}
+#endif
diff --git a/include/cpython/pylifecycle.h b/include/cpython/pylifecycle.h
new file mode 100644
index 0000000..2f3a0db
--- /dev/null
+++ b/include/cpython/pylifecycle.h
@@ -0,0 +1,78 @@
+#ifndef Py_CPYTHON_PYLIFECYCLE_H
+# error "this header file must not be included directly"
+#endif
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/* Only used by applications that embed the interpreter and need to
+ * override the standard encoding determination mechanism
+ */
+PyAPI_FUNC(int) Py_SetStandardStreamEncoding(const char *encoding,
+ const char *errors);
+
+/* PEP 432 Multi-phase initialization API (Private while provisional!) */
+
+PyAPI_FUNC(PyStatus) Py_PreInitialize(
+ const PyPreConfig *src_config);
+PyAPI_FUNC(PyStatus) Py_PreInitializeFromBytesArgs(
+ const PyPreConfig *src_config,
+ Py_ssize_t argc,
+ char **argv);
+PyAPI_FUNC(PyStatus) Py_PreInitializeFromArgs(
+ const PyPreConfig *src_config,
+ Py_ssize_t argc,
+ wchar_t **argv);
+
+PyAPI_FUNC(int) _Py_IsCoreInitialized(void);
+
+
+/* Initialization and finalization */
+
+PyAPI_FUNC(PyStatus) Py_InitializeFromConfig(
+ const PyConfig *config);
+PyAPI_FUNC(PyStatus) _Py_InitializeFromArgs(
+ const PyConfig *config,
+ Py_ssize_t argc,
+ char * const *argv);
+PyAPI_FUNC(PyStatus) _Py_InitializeFromWideArgs(
+ const PyConfig *config,
+ Py_ssize_t argc,
+ wchar_t * const *argv);
+PyAPI_FUNC(PyStatus) _Py_InitializeMain(void);
+
+PyAPI_FUNC(int) Py_RunMain(void);
+
+
+PyAPI_FUNC(void) _Py_NO_RETURN Py_ExitStatusException(PyStatus err);
+
+/* Py_PyAtExit is for the atexit module, Py_AtExit is for low-level
+ * exit functions.
+ */
+PyAPI_FUNC(void) _Py_PyAtExit(void (*func)(PyObject *), PyObject *);
+
+/* Restore signals that the interpreter has called SIG_IGN on to SIG_DFL. */
+PyAPI_FUNC(void) _Py_RestoreSignals(void);
+
+PyAPI_FUNC(int) Py_FdIsInteractive(FILE *, const char *);
+
+PyAPI_FUNC(void) _Py_SetProgramFullPath(const wchar_t *);
+
+PyAPI_FUNC(const char *) _Py_gitidentifier(void);
+PyAPI_FUNC(const char *) _Py_gitversion(void);
+
+PyAPI_FUNC(int) _Py_IsFinalizing(void);
+
+/* Random */
+PyAPI_FUNC(int) _PyOS_URandom(void *buffer, Py_ssize_t size);
+PyAPI_FUNC(int) _PyOS_URandomNonblock(void *buffer, Py_ssize_t size);
+
+/* Legacy locale support */
+PyAPI_FUNC(int) _Py_CoerceLegacyLocale(int warn);
+PyAPI_FUNC(int) _Py_LegacyLocaleDetected(int warn);
+PyAPI_FUNC(char *) _Py_SetLocaleFromEnv(int category);
+
+#ifdef __cplusplus
+}
+#endif
diff --git a/include/cpython/pymem.h b/include/cpython/pymem.h
new file mode 100644
index 0000000..79f063b
--- /dev/null
+++ b/include/cpython/pymem.h
@@ -0,0 +1,108 @@
+#ifndef Py_CPYTHON_PYMEM_H
+# error "this header file must not be included directly"
+#endif
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+PyAPI_FUNC(void *) PyMem_RawMalloc(size_t size);
+PyAPI_FUNC(void *) PyMem_RawCalloc(size_t nelem, size_t elsize);
+PyAPI_FUNC(void *) PyMem_RawRealloc(void *ptr, size_t new_size);
+PyAPI_FUNC(void) PyMem_RawFree(void *ptr);
+
+/* Try to get the allocators name set by _PyMem_SetupAllocators(). */
+PyAPI_FUNC(const char*) _PyMem_GetCurrentAllocatorName(void);
+
+PyAPI_FUNC(void *) PyMem_Calloc(size_t nelem, size_t elsize);
+
+/* strdup() using PyMem_RawMalloc() */
+PyAPI_FUNC(char *) _PyMem_RawStrdup(const char *str);
+
+/* strdup() using PyMem_Malloc() */
+PyAPI_FUNC(char *) _PyMem_Strdup(const char *str);
+
+/* wcsdup() using PyMem_RawMalloc() */
+PyAPI_FUNC(wchar_t*) _PyMem_RawWcsdup(const wchar_t *str);
+
+
+typedef enum {
+ /* PyMem_RawMalloc(), PyMem_RawRealloc() and PyMem_RawFree() */
+ PYMEM_DOMAIN_RAW,
+
+ /* PyMem_Malloc(), PyMem_Realloc() and PyMem_Free() */
+ PYMEM_DOMAIN_MEM,
+
+ /* PyObject_Malloc(), PyObject_Realloc() and PyObject_Free() */
+ PYMEM_DOMAIN_OBJ
+} PyMemAllocatorDomain;
+
+typedef enum {
+ PYMEM_ALLOCATOR_NOT_SET = 0,
+ PYMEM_ALLOCATOR_DEFAULT = 1,
+ PYMEM_ALLOCATOR_DEBUG = 2,
+ PYMEM_ALLOCATOR_MALLOC = 3,
+ PYMEM_ALLOCATOR_MALLOC_DEBUG = 4,
+#ifdef WITH_PYMALLOC
+ PYMEM_ALLOCATOR_PYMALLOC = 5,
+ PYMEM_ALLOCATOR_PYMALLOC_DEBUG = 6,
+#endif
+} PyMemAllocatorName;
+
+
+typedef struct {
+ /* user context passed as the first argument to the 4 functions */
+ void *ctx;
+
+ /* allocate a memory block */
+ void* (*malloc) (void *ctx, size_t size);
+
+ /* allocate a memory block initialized by zeros */
+ void* (*calloc) (void *ctx, size_t nelem, size_t elsize);
+
+ /* allocate or resize a memory block */
+ void* (*realloc) (void *ctx, void *ptr, size_t new_size);
+
+ /* release a memory block */
+ void (*free) (void *ctx, void *ptr);
+} PyMemAllocatorEx;
+
+/* Get the memory block allocator of the specified domain. */
+PyAPI_FUNC(void) PyMem_GetAllocator(PyMemAllocatorDomain domain,
+ PyMemAllocatorEx *allocator);
+
+/* Set the memory block allocator of the specified domain.
+
+ The new allocator must return a distinct non-NULL pointer when requesting
+ zero bytes.
+
+ For the PYMEM_DOMAIN_RAW domain, the allocator must be thread-safe: the GIL
+ is not held when the allocator is called.
+
+ If the new allocator is not a hook (don't call the previous allocator), the
+ PyMem_SetupDebugHooks() function must be called to reinstall the debug hooks
+ on top on the new allocator. */
+PyAPI_FUNC(void) PyMem_SetAllocator(PyMemAllocatorDomain domain,
+ PyMemAllocatorEx *allocator);
+
+/* Setup hooks to detect bugs in the following Python memory allocator
+ functions:
+
+ - PyMem_RawMalloc(), PyMem_RawRealloc(), PyMem_RawFree()
+ - PyMem_Malloc(), PyMem_Realloc(), PyMem_Free()
+ - PyObject_Malloc(), PyObject_Realloc() and PyObject_Free()
+
+ Newly allocated memory is filled with the byte 0xCB, freed memory is filled
+ with the byte 0xDB. Additional checks:
+
+ - detect API violations, ex: PyObject_Free() called on a buffer allocated
+ by PyMem_Malloc()
+ - detect write before the start of the buffer (buffer underflow)
+ - detect write after the end of the buffer (buffer overflow)
+
+ The function does nothing if Python is not compiled is debug mode. */
+PyAPI_FUNC(void) PyMem_SetupDebugHooks(void);
+
+#ifdef __cplusplus
+}
+#endif
diff --git a/include/cpython/pystate.h b/include/cpython/pystate.h
new file mode 100644
index 0000000..94b0809
--- /dev/null
+++ b/include/cpython/pystate.h
@@ -0,0 +1,251 @@
+#ifndef Py_CPYTHON_PYSTATE_H
+# error "this header file must not be included directly"
+#endif
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "cpython/initconfig.h"
+
+PyAPI_FUNC(int) _PyInterpreterState_RequiresIDRef(PyInterpreterState *);
+PyAPI_FUNC(void) _PyInterpreterState_RequireIDRef(PyInterpreterState *, int);
+
+PyAPI_FUNC(PyObject *) _PyInterpreterState_GetMainModule(PyInterpreterState *);
+
+/* State unique per thread */
+
+/* Py_tracefunc return -1 when raising an exception, or 0 for success. */
+typedef int (*Py_tracefunc)(PyObject *, struct _frame *, int, PyObject *);
+
+/* The following values are used for 'what' for tracefunc functions
+ *
+ * To add a new kind of trace event, also update "trace_init" in
+ * Python/sysmodule.c to define the Python level event name
+ */
+#define PyTrace_CALL 0
+#define PyTrace_EXCEPTION 1
+#define PyTrace_LINE 2
+#define PyTrace_RETURN 3
+#define PyTrace_C_CALL 4
+#define PyTrace_C_EXCEPTION 5
+#define PyTrace_C_RETURN 6
+#define PyTrace_OPCODE 7
+
+
+typedef struct _err_stackitem {
+ /* This struct represents an entry on the exception stack, which is a
+ * per-coroutine state. (Coroutine in the computer science sense,
+ * including the thread and generators).
+ * This ensures that the exception state is not impacted by "yields"
+ * from an except handler.
+ */
+ PyObject *exc_type, *exc_value, *exc_traceback;
+
+ struct _err_stackitem *previous_item;
+
+} _PyErr_StackItem;
+
+
+// The PyThreadState typedef is in Include/pystate.h.
+struct _ts {
+ /* See Python/ceval.c for comments explaining most fields */
+
+ struct _ts *prev;
+ struct _ts *next;
+ PyInterpreterState *interp;
+
+ struct _frame *frame;
+ int recursion_depth;
+ char overflowed; /* The stack has overflowed. Allow 50 more calls
+ to handle the runtime error. */
+ char recursion_critical; /* The current calls must not cause
+ a stack overflow. */
+ int stackcheck_counter;
+
+ /* 'tracing' keeps track of the execution depth when tracing/profiling.
+ This is to prevent the actual trace/profile code from being recorded in
+ the trace/profile. */
+ int tracing;
+ int use_tracing;
+
+ Py_tracefunc c_profilefunc;
+ Py_tracefunc c_tracefunc;
+ PyObject *c_profileobj;
+ PyObject *c_traceobj;
+
+ /* The exception currently being raised */
+ PyObject *curexc_type;
+ PyObject *curexc_value;
+ PyObject *curexc_traceback;
+
+ /* The exception currently being handled, if no coroutines/generators
+ * are present. Always last element on the stack referred to be exc_info.
+ */
+ _PyErr_StackItem exc_state;
+
+ /* Pointer to the top of the stack of the exceptions currently
+ * being handled */
+ _PyErr_StackItem *exc_info;
+
+ PyObject *dict; /* Stores per-thread state */
+
+ int gilstate_counter;
+
+ PyObject *async_exc; /* Asynchronous exception to raise */
+ unsigned long thread_id; /* Thread id where this tstate was created */
+
+ int trash_delete_nesting;
+ PyObject *trash_delete_later;
+
+ /* Called when a thread state is deleted normally, but not when it
+ * is destroyed after fork().
+ * Pain: to prevent rare but fatal shutdown errors (issue 18808),
+ * Thread.join() must wait for the join'ed thread's tstate to be unlinked
+ * from the tstate chain. That happens at the end of a thread's life,
+ * in pystate.c.
+ * The obvious way doesn't quite work: create a lock which the tstate
+ * unlinking code releases, and have Thread.join() wait to acquire that
+ * lock. The problem is that we _are_ at the end of the thread's life:
+ * if the thread holds the last reference to the lock, decref'ing the
+ * lock will delete the lock, and that may trigger arbitrary Python code
+ * if there's a weakref, with a callback, to the lock. But by this time
+ * _PyRuntime.gilstate.tstate_current is already NULL, so only the simplest
+ * of C code can be allowed to run (in particular it must not be possible to
+ * release the GIL).
+ * So instead of holding the lock directly, the tstate holds a weakref to
+ * the lock: that's the value of on_delete_data below. Decref'ing a
+ * weakref is harmless.
+ * on_delete points to _threadmodule.c's static release_sentinel() function.
+ * After the tstate is unlinked, release_sentinel is called with the
+ * weakref-to-lock (on_delete_data) argument, and release_sentinel releases
+ * the indirectly held lock.
+ */
+ void (*on_delete)(void *);
+ void *on_delete_data;
+
+ int coroutine_origin_tracking_depth;
+
+ PyObject *async_gen_firstiter;
+ PyObject *async_gen_finalizer;
+
+ PyObject *context;
+ uint64_t context_ver;
+
+ /* Unique thread state id. */
+ uint64_t id;
+
+ /* XXX signal handlers should also be here */
+
+};
+
+/* Get the current interpreter state.
+
+ Issue a fatal error if there no current Python thread state or no current
+ interpreter. It cannot return NULL.
+
+ The caller must hold the GIL.*/
+PyAPI_FUNC(PyInterpreterState *) _PyInterpreterState_Get(void);
+
+PyAPI_FUNC(int) _PyState_AddModule(PyObject*, struct PyModuleDef*);
+PyAPI_FUNC(void) _PyState_ClearModules(void);
+PyAPI_FUNC(PyThreadState *) _PyThreadState_Prealloc(PyInterpreterState *);
+
+/* Similar to PyThreadState_Get(), but don't issue a fatal error
+ * if it is NULL. */
+PyAPI_FUNC(PyThreadState *) _PyThreadState_UncheckedGet(void);
+
+/* PyGILState */
+
+/* Helper/diagnostic function - return 1 if the current thread
+ currently holds the GIL, 0 otherwise.
+
+ The function returns 1 if _PyGILState_check_enabled is non-zero. */
+PyAPI_FUNC(int) PyGILState_Check(void);
+
+/* Get the single PyInterpreterState used by this process' GILState
+ implementation.
+
+ This function doesn't check for error. Return NULL before _PyGILState_Init()
+ is called and after _PyGILState_Fini() is called.
+
+ See also _PyInterpreterState_Get() and _PyInterpreterState_GET_UNSAFE(). */
+PyAPI_FUNC(PyInterpreterState *) _PyGILState_GetInterpreterStateUnsafe(void);
+
+/* The implementation of sys._current_frames() Returns a dict mapping
+ thread id to that thread's current frame.
+*/
+PyAPI_FUNC(PyObject *) _PyThread_CurrentFrames(void);
+
+/* Routines for advanced debuggers, requested by David Beazley.
+ Don't use unless you know what you are doing! */
+PyAPI_FUNC(PyInterpreterState *) PyInterpreterState_Main(void);
+PyAPI_FUNC(PyInterpreterState *) PyInterpreterState_Head(void);
+PyAPI_FUNC(PyInterpreterState *) PyInterpreterState_Next(PyInterpreterState *);
+PyAPI_FUNC(PyThreadState *) PyInterpreterState_ThreadHead(PyInterpreterState *);
+PyAPI_FUNC(PyThreadState *) PyThreadState_Next(PyThreadState *);
+
+typedef struct _frame *(*PyThreadFrameGetter)(PyThreadState *self_);
+
+/* cross-interpreter data */
+
+struct _xid;
+
+// _PyCrossInterpreterData is similar to Py_buffer as an effectively
+// opaque struct that holds data outside the object machinery. This
+// is necessary to pass safely between interpreters in the same process.
+typedef struct _xid {
+ // data is the cross-interpreter-safe derivation of a Python object
+ // (see _PyObject_GetCrossInterpreterData). It will be NULL if the
+ // new_object func (below) encodes the data.
+ void *data;
+ // obj is the Python object from which the data was derived. This
+ // is non-NULL only if the data remains bound to the object in some
+ // way, such that the object must be "released" (via a decref) when
+ // the data is released. In that case the code that sets the field,
+ // likely a registered "crossinterpdatafunc", is responsible for
+ // ensuring it owns the reference (i.e. incref).
+ PyObject *obj;
+ // interp is the ID of the owning interpreter of the original
+ // object. It corresponds to the active interpreter when
+ // _PyObject_GetCrossInterpreterData() was called. This should only
+ // be set by the cross-interpreter machinery.
+ //
+ // We use the ID rather than the PyInterpreterState to avoid issues
+ // with deleted interpreters. Note that IDs are never re-used, so
+ // each one will always correspond to a specific interpreter
+ // (whether still alive or not).
+ int64_t interp;
+ // new_object is a function that returns a new object in the current
+ // interpreter given the data. The resulting object (a new
+ // reference) will be equivalent to the original object. This field
+ // is required.
+ PyObject *(*new_object)(struct _xid *);
+ // free is called when the data is released. If it is NULL then
+ // nothing will be done to free the data. For some types this is
+ // okay (e.g. bytes) and for those types this field should be set
+ // to NULL. However, for most the data was allocated just for
+ // cross-interpreter use, so it must be freed when
+ // _PyCrossInterpreterData_Release is called or the memory will
+ // leak. In that case, at the very least this field should be set
+ // to PyMem_RawFree (the default if not explicitly set to NULL).
+ // The call will happen with the original interpreter activated.
+ void (*free)(void *);
+} _PyCrossInterpreterData;
+
+PyAPI_FUNC(int) _PyObject_GetCrossInterpreterData(PyObject *, _PyCrossInterpreterData *);
+PyAPI_FUNC(PyObject *) _PyCrossInterpreterData_NewObject(_PyCrossInterpreterData *);
+PyAPI_FUNC(void) _PyCrossInterpreterData_Release(_PyCrossInterpreterData *);
+
+PyAPI_FUNC(int) _PyObject_CheckCrossInterpreterData(PyObject *);
+
+/* cross-interpreter data registry */
+
+typedef int (*crossinterpdatafunc)(PyObject *, struct _xid *);
+
+PyAPI_FUNC(int) _PyCrossInterpreterData_RegisterClass(PyTypeObject *, crossinterpdatafunc);
+PyAPI_FUNC(crossinterpdatafunc) _PyCrossInterpreterData_Lookup(PyObject *);
+
+#ifdef __cplusplus
+}
+#endif
diff --git a/include/cpython/sysmodule.h b/include/cpython/sysmodule.h
new file mode 100644
index 0000000..72d8ffe
--- /dev/null
+++ b/include/cpython/sysmodule.h
@@ -0,0 +1,21 @@
+#ifndef Py_CPYTHON_SYSMODULE_H
+# error "this header file must not be included directly"
+#endif
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+PyAPI_FUNC(PyObject *) _PySys_GetObjectId(_Py_Identifier *key);
+PyAPI_FUNC(int) _PySys_SetObjectId(_Py_Identifier *key, PyObject *);
+
+PyAPI_FUNC(size_t) _PySys_GetSizeOf(PyObject *);
+
+typedef int(*Py_AuditHookFunction)(const char *, PyObject *, void *);
+
+PyAPI_FUNC(int) PySys_Audit(const char*, const char *, ...);
+PyAPI_FUNC(int) PySys_AddAuditHook(Py_AuditHookFunction, void*);
+
+#ifdef __cplusplus
+}
+#endif
diff --git a/include/cpython/traceback.h b/include/cpython/traceback.h
new file mode 100644
index 0000000..746097d
--- /dev/null
+++ b/include/cpython/traceback.h
@@ -0,0 +1,22 @@
+#ifndef Py_CPYTHON_TRACEBACK_H
+# error "this header file must not be included directly"
+#endif
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+typedef struct _traceback {
+ PyObject_HEAD
+ struct _traceback *tb_next;
+ struct _frame *tb_frame;
+ int tb_lasti;
+ int tb_lineno;
+} PyTracebackObject;
+
+PyAPI_FUNC(int) _Py_DisplaySourceLine(PyObject *, PyObject *, int, int);
+PyAPI_FUNC(void) _PyTraceback_Add(const char *, const char *, int);
+
+#ifdef __cplusplus
+}
+#endif
diff --git a/include/cpython/tupleobject.h b/include/cpython/tupleobject.h
new file mode 100644
index 0000000..1565f2a
--- /dev/null
+++ b/include/cpython/tupleobject.h
@@ -0,0 +1,36 @@
+#ifndef Py_CPYTHON_TUPLEOBJECT_H
+# error "this header file must not be included directly"
+#endif
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+typedef struct {
+ PyObject_VAR_HEAD
+ /* ob_item contains space for 'ob_size' elements.
+ Items must normally not be NULL, except during construction when
+ the tuple is not yet visible outside the function that builds it. */
+ PyObject *ob_item[1];
+} PyTupleObject;
+
+PyAPI_FUNC(int) _PyTuple_Resize(PyObject **, Py_ssize_t);
+PyAPI_FUNC(void) _PyTuple_MaybeUntrack(PyObject *);
+
+/* Macros trading safety for speed */
+
+/* Cast argument to PyTupleObject* type. */
+#define _PyTuple_CAST(op) (assert(PyTuple_Check(op)), (PyTupleObject *)(op))
+
+#define PyTuple_GET_SIZE(op) Py_SIZE(_PyTuple_CAST(op))
+
+#define PyTuple_GET_ITEM(op, i) (_PyTuple_CAST(op)->ob_item[i])
+
+/* Macro, *only* to be used to fill in brand new tuples */
+#define PyTuple_SET_ITEM(op, i, v) (_PyTuple_CAST(op)->ob_item[i] = v)
+
+PyAPI_FUNC(void) _PyTuple_DebugMallocStats(FILE *out);
+
+#ifdef __cplusplus
+}
+#endif
diff --git a/include/cpython/unicodeobject.h b/include/cpython/unicodeobject.h
new file mode 100644
index 0000000..54a13e3
--- /dev/null
+++ b/include/cpython/unicodeobject.h
@@ -0,0 +1,1239 @@
+#ifndef Py_CPYTHON_UNICODEOBJECT_H
+# error "this header file must not be included directly"
+#endif
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/* Py_UNICODE was the native Unicode storage format (code unit) used by
+ Python and represents a single Unicode element in the Unicode type.
+ With PEP 393, Py_UNICODE is deprecated and replaced with a
+ typedef to wchar_t. */
+#define PY_UNICODE_TYPE wchar_t
+/* Py_DEPRECATED(3.3) */ typedef wchar_t Py_UNICODE;
+
+/* --- Internal Unicode Operations ---------------------------------------- */
+
+/* Since splitting on whitespace is an important use case, and
+ whitespace in most situations is solely ASCII whitespace, we
+ optimize for the common case by using a quick look-up table
+ _Py_ascii_whitespace (see below) with an inlined check.
+
+ */
+#define Py_UNICODE_ISSPACE(ch) \
+ ((ch) < 128U ? _Py_ascii_whitespace[(ch)] : _PyUnicode_IsWhitespace(ch))
+
+#define Py_UNICODE_ISLOWER(ch) _PyUnicode_IsLowercase(ch)
+#define Py_UNICODE_ISUPPER(ch) _PyUnicode_IsUppercase(ch)
+#define Py_UNICODE_ISTITLE(ch) _PyUnicode_IsTitlecase(ch)
+#define Py_UNICODE_ISLINEBREAK(ch) _PyUnicode_IsLinebreak(ch)
+
+#define Py_UNICODE_TOLOWER(ch) _PyUnicode_ToLowercase(ch)
+#define Py_UNICODE_TOUPPER(ch) _PyUnicode_ToUppercase(ch)
+#define Py_UNICODE_TOTITLE(ch) _PyUnicode_ToTitlecase(ch)
+
+#define Py_UNICODE_ISDECIMAL(ch) _PyUnicode_IsDecimalDigit(ch)
+#define Py_UNICODE_ISDIGIT(ch) _PyUnicode_IsDigit(ch)
+#define Py_UNICODE_ISNUMERIC(ch) _PyUnicode_IsNumeric(ch)
+#define Py_UNICODE_ISPRINTABLE(ch) _PyUnicode_IsPrintable(ch)
+
+#define Py_UNICODE_TODECIMAL(ch) _PyUnicode_ToDecimalDigit(ch)
+#define Py_UNICODE_TODIGIT(ch) _PyUnicode_ToDigit(ch)
+#define Py_UNICODE_TONUMERIC(ch) _PyUnicode_ToNumeric(ch)
+
+#define Py_UNICODE_ISALPHA(ch) _PyUnicode_IsAlpha(ch)
+
+#define Py_UNICODE_ISALNUM(ch) \
+ (Py_UNICODE_ISALPHA(ch) || \
+ Py_UNICODE_ISDECIMAL(ch) || \
+ Py_UNICODE_ISDIGIT(ch) || \
+ Py_UNICODE_ISNUMERIC(ch))
+
+#define Py_UNICODE_COPY(target, source, length) \
+ memcpy((target), (source), (length)*sizeof(Py_UNICODE))
+
+#define Py_UNICODE_FILL(target, value, length) \
+ do {Py_ssize_t i_; Py_UNICODE *t_ = (target); Py_UNICODE v_ = (value);\
+ for (i_ = 0; i_ < (length); i_++) t_[i_] = v_;\
+ } while (0)
+
+/* macros to work with surrogates */
+#define Py_UNICODE_IS_SURROGATE(ch) (0xD800 <= (ch) && (ch) <= 0xDFFF)
+#define Py_UNICODE_IS_HIGH_SURROGATE(ch) (0xD800 <= (ch) && (ch) <= 0xDBFF)
+#define Py_UNICODE_IS_LOW_SURROGATE(ch) (0xDC00 <= (ch) && (ch) <= 0xDFFF)
+/* Join two surrogate characters and return a single Py_UCS4 value. */
+#define Py_UNICODE_JOIN_SURROGATES(high, low) \
+ (((((Py_UCS4)(high) & 0x03FF) << 10) | \
+ ((Py_UCS4)(low) & 0x03FF)) + 0x10000)
+/* high surrogate = top 10 bits added to D800 */
+#define Py_UNICODE_HIGH_SURROGATE(ch) (0xD800 - (0x10000 >> 10) + ((ch) >> 10))
+/* low surrogate = bottom 10 bits added to DC00 */
+#define Py_UNICODE_LOW_SURROGATE(ch) (0xDC00 + ((ch) & 0x3FF))
+
+/* Check if substring matches at given offset. The offset must be
+ valid, and the substring must not be empty. */
+
+#define Py_UNICODE_MATCH(string, offset, substring) \
+ ((*((string)->wstr + (offset)) == *((substring)->wstr)) && \
+ ((*((string)->wstr + (offset) + (substring)->wstr_length-1) == *((substring)->wstr + (substring)->wstr_length-1))) && \
+ !memcmp((string)->wstr + (offset), (substring)->wstr, (substring)->wstr_length*sizeof(Py_UNICODE)))
+
+/* --- Unicode Type ------------------------------------------------------- */
+
+/* ASCII-only strings created through PyUnicode_New use the PyASCIIObject
+ structure. state.ascii and state.compact are set, and the data
+ immediately follow the structure. utf8_length and wstr_length can be found
+ in the length field; the utf8 pointer is equal to the data pointer. */
+typedef struct {
+ /* There are 4 forms of Unicode strings:
+
+ - compact ascii:
+
+ * structure = PyASCIIObject
+ * test: PyUnicode_IS_COMPACT_ASCII(op)
+ * kind = PyUnicode_1BYTE_KIND
+ * compact = 1
+ * ascii = 1
+ * ready = 1
+ * (length is the length of the utf8 and wstr strings)
+ * (data starts just after the structure)
+ * (since ASCII is decoded from UTF-8, the utf8 string are the data)
+
+ - compact:
+
+ * structure = PyCompactUnicodeObject
+ * test: PyUnicode_IS_COMPACT(op) && !PyUnicode_IS_ASCII(op)
+ * kind = PyUnicode_1BYTE_KIND, PyUnicode_2BYTE_KIND or
+ PyUnicode_4BYTE_KIND
+ * compact = 1
+ * ready = 1
+ * ascii = 0
+ * utf8 is not shared with data
+ * utf8_length = 0 if utf8 is NULL
+ * wstr is shared with data and wstr_length=length
+ if kind=PyUnicode_2BYTE_KIND and sizeof(wchar_t)=2
+ or if kind=PyUnicode_4BYTE_KIND and sizeof(wchar_t)=4
+ * wstr_length = 0 if wstr is NULL
+ * (data starts just after the structure)
+
+ - legacy string, not ready:
+
+ * structure = PyUnicodeObject
+ * test: kind == PyUnicode_WCHAR_KIND
+ * length = 0 (use wstr_length)
+ * hash = -1
+ * kind = PyUnicode_WCHAR_KIND
+ * compact = 0
+ * ascii = 0
+ * ready = 0
+ * interned = SSTATE_NOT_INTERNED
+ * wstr is not NULL
+ * data.any is NULL
+ * utf8 is NULL
+ * utf8_length = 0
+
+ - legacy string, ready:
+
+ * structure = PyUnicodeObject structure
+ * test: !PyUnicode_IS_COMPACT(op) && kind != PyUnicode_WCHAR_KIND
+ * kind = PyUnicode_1BYTE_KIND, PyUnicode_2BYTE_KIND or
+ PyUnicode_4BYTE_KIND
+ * compact = 0
+ * ready = 1
+ * data.any is not NULL
+ * utf8 is shared and utf8_length = length with data.any if ascii = 1
+ * utf8_length = 0 if utf8 is NULL
+ * wstr is shared with data.any and wstr_length = length
+ if kind=PyUnicode_2BYTE_KIND and sizeof(wchar_t)=2
+ or if kind=PyUnicode_4BYTE_KIND and sizeof(wchar_4)=4
+ * wstr_length = 0 if wstr is NULL
+
+ Compact strings use only one memory block (structure + characters),
+ whereas legacy strings use one block for the structure and one block
+ for characters.
+
+ Legacy strings are created by PyUnicode_FromUnicode() and
+ PyUnicode_FromStringAndSize(NULL, size) functions. They become ready
+ when PyUnicode_READY() is called.
+
+ See also _PyUnicode_CheckConsistency().
+ */
+ PyObject_HEAD
+ Py_ssize_t length; /* Number of code points in the string */
+ Py_hash_t hash; /* Hash value; -1 if not set */
+ struct {
+ /*
+ SSTATE_NOT_INTERNED (0)
+ SSTATE_INTERNED_MORTAL (1)
+ SSTATE_INTERNED_IMMORTAL (2)
+
+ If interned != SSTATE_NOT_INTERNED, the two references from the
+ dictionary to this object are *not* counted in ob_refcnt.
+ */
+ unsigned int interned:2;
+ /* Character size:
+
+ - PyUnicode_WCHAR_KIND (0):
+
+ * character type = wchar_t (16 or 32 bits, depending on the
+ platform)
+
+ - PyUnicode_1BYTE_KIND (1):
+
+ * character type = Py_UCS1 (8 bits, unsigned)
+ * all characters are in the range U+0000-U+00FF (latin1)
+ * if ascii is set, all characters are in the range U+0000-U+007F
+ (ASCII), otherwise at least one character is in the range
+ U+0080-U+00FF
+
+ - PyUnicode_2BYTE_KIND (2):
+
+ * character type = Py_UCS2 (16 bits, unsigned)
+ * all characters are in the range U+0000-U+FFFF (BMP)
+ * at least one character is in the range U+0100-U+FFFF
+
+ - PyUnicode_4BYTE_KIND (4):
+
+ * character type = Py_UCS4 (32 bits, unsigned)
+ * all characters are in the range U+0000-U+10FFFF
+ * at least one character is in the range U+10000-U+10FFFF
+ */
+ unsigned int kind:3;
+ /* Compact is with respect to the allocation scheme. Compact unicode
+ objects only require one memory block while non-compact objects use
+ one block for the PyUnicodeObject struct and another for its data
+ buffer. */
+ unsigned int compact:1;
+ /* The string only contains characters in the range U+0000-U+007F (ASCII)
+ and the kind is PyUnicode_1BYTE_KIND. If ascii is set and compact is
+ set, use the PyASCIIObject structure. */
+ unsigned int ascii:1;
+ /* The ready flag indicates whether the object layout is initialized
+ completely. This means that this is either a compact object, or
+ the data pointer is filled out. The bit is redundant, and helps
+ to minimize the test in PyUnicode_IS_READY(). */
+ unsigned int ready:1;
+ /* Padding to ensure that PyUnicode_DATA() is always aligned to
+ 4 bytes (see issue #19537 on m68k). */
+ unsigned int :24;
+ } state;
+ wchar_t *wstr; /* wchar_t representation (null-terminated) */
+} PyASCIIObject;
+
+/* Non-ASCII strings allocated through PyUnicode_New use the
+ PyCompactUnicodeObject structure. state.compact is set, and the data
+ immediately follow the structure. */
+typedef struct {
+ PyASCIIObject _base;
+ Py_ssize_t utf8_length; /* Number of bytes in utf8, excluding the
+ * terminating \0. */
+ char *utf8; /* UTF-8 representation (null-terminated) */
+ Py_ssize_t wstr_length; /* Number of code points in wstr, possible
+ * surrogates count as two code points. */
+} PyCompactUnicodeObject;
+
+/* Strings allocated through PyUnicode_FromUnicode(NULL, len) use the
+ PyUnicodeObject structure. The actual string data is initially in the wstr
+ block, and copied into the data block using _PyUnicode_Ready. */
+typedef struct {
+ PyCompactUnicodeObject _base;
+ union {
+ void *any;
+ Py_UCS1 *latin1;
+ Py_UCS2 *ucs2;
+ Py_UCS4 *ucs4;
+ } data; /* Canonical, smallest-form Unicode buffer */
+} PyUnicodeObject;
+
+PyAPI_FUNC(int) _PyUnicode_CheckConsistency(
+ PyObject *op,
+ int check_content);
+
+/* Fast access macros */
+#define PyUnicode_WSTR_LENGTH(op) \
+ (PyUnicode_IS_COMPACT_ASCII(op) ? \
+ ((PyASCIIObject*)op)->length : \
+ ((PyCompactUnicodeObject*)op)->wstr_length)
+
+/* Returns the deprecated Py_UNICODE representation's size in code units
+ (this includes surrogate pairs as 2 units).
+ If the Py_UNICODE representation is not available, it will be computed
+ on request. Use PyUnicode_GET_LENGTH() for the length in code points. */
+
+/* Py_DEPRECATED(3.3) */
+#define PyUnicode_GET_SIZE(op) \
+ (assert(PyUnicode_Check(op)), \
+ (((PyASCIIObject *)(op))->wstr) ? \
+ PyUnicode_WSTR_LENGTH(op) : \
+ ((void)PyUnicode_AsUnicode(_PyObject_CAST(op)),\
+ assert(((PyASCIIObject *)(op))->wstr), \
+ PyUnicode_WSTR_LENGTH(op)))
+
+/* Py_DEPRECATED(3.3) */
+#define PyUnicode_GET_DATA_SIZE(op) \
+ (PyUnicode_GET_SIZE(op) * Py_UNICODE_SIZE)
+
+/* Alias for PyUnicode_AsUnicode(). This will create a wchar_t/Py_UNICODE
+ representation on demand. Using this macro is very inefficient now,
+ try to port your code to use the new PyUnicode_*BYTE_DATA() macros or
+ use PyUnicode_WRITE() and PyUnicode_READ(). */
+
+/* Py_DEPRECATED(3.3) */
+#define PyUnicode_AS_UNICODE(op) \
+ (assert(PyUnicode_Check(op)), \
+ (((PyASCIIObject *)(op))->wstr) ? (((PyASCIIObject *)(op))->wstr) : \
+ PyUnicode_AsUnicode(_PyObject_CAST(op)))
+
+/* Py_DEPRECATED(3.3) */
+#define PyUnicode_AS_DATA(op) \
+ ((const char *)(PyUnicode_AS_UNICODE(op)))
+
+
+/* --- Flexible String Representation Helper Macros (PEP 393) -------------- */
+
+/* Values for PyASCIIObject.state: */
+
+/* Interning state. */
+#define SSTATE_NOT_INTERNED 0
+#define SSTATE_INTERNED_MORTAL 1
+#define SSTATE_INTERNED_IMMORTAL 2
+
+/* Return true if the string contains only ASCII characters, or 0 if not. The
+ string may be compact (PyUnicode_IS_COMPACT_ASCII) or not, but must be
+ ready. */
+#define PyUnicode_IS_ASCII(op) \
+ (assert(PyUnicode_Check(op)), \
+ assert(PyUnicode_IS_READY(op)), \
+ ((PyASCIIObject*)op)->state.ascii)
+
+/* Return true if the string is compact or 0 if not.
+ No type checks or Ready calls are performed. */
+#define PyUnicode_IS_COMPACT(op) \
+ (((PyASCIIObject*)(op))->state.compact)
+
+/* Return true if the string is a compact ASCII string (use PyASCIIObject
+ structure), or 0 if not. No type checks or Ready calls are performed. */
+#define PyUnicode_IS_COMPACT_ASCII(op) \
+ (((PyASCIIObject*)op)->state.ascii && PyUnicode_IS_COMPACT(op))
+
+enum PyUnicode_Kind {
+/* String contains only wstr byte characters. This is only possible
+ when the string was created with a legacy API and _PyUnicode_Ready()
+ has not been called yet. */
+ PyUnicode_WCHAR_KIND = 0,
+/* Return values of the PyUnicode_KIND() macro: */
+ PyUnicode_1BYTE_KIND = 1,
+ PyUnicode_2BYTE_KIND = 2,
+ PyUnicode_4BYTE_KIND = 4
+};
+
+/* Return pointers to the canonical representation cast to unsigned char,
+ Py_UCS2, or Py_UCS4 for direct character access.
+ No checks are performed, use PyUnicode_KIND() before to ensure
+ these will work correctly. */
+
+#define PyUnicode_1BYTE_DATA(op) ((Py_UCS1*)PyUnicode_DATA(op))
+#define PyUnicode_2BYTE_DATA(op) ((Py_UCS2*)PyUnicode_DATA(op))
+#define PyUnicode_4BYTE_DATA(op) ((Py_UCS4*)PyUnicode_DATA(op))
+
+/* Return one of the PyUnicode_*_KIND values defined above. */
+#define PyUnicode_KIND(op) \
+ (assert(PyUnicode_Check(op)), \
+ assert(PyUnicode_IS_READY(op)), \
+ ((PyASCIIObject *)(op))->state.kind)
+
+/* Return a void pointer to the raw unicode buffer. */
+#define _PyUnicode_COMPACT_DATA(op) \
+ (PyUnicode_IS_ASCII(op) ? \
+ ((void*)((PyASCIIObject*)(op) + 1)) : \
+ ((void*)((PyCompactUnicodeObject*)(op) + 1)))
+
+#define _PyUnicode_NONCOMPACT_DATA(op) \
+ (assert(((PyUnicodeObject*)(op))->data.any), \
+ ((((PyUnicodeObject *)(op))->data.any)))
+
+#define PyUnicode_DATA(op) \
+ (assert(PyUnicode_Check(op)), \
+ PyUnicode_IS_COMPACT(op) ? _PyUnicode_COMPACT_DATA(op) : \
+ _PyUnicode_NONCOMPACT_DATA(op))
+
+/* In the access macros below, "kind" may be evaluated more than once.
+ All other macro parameters are evaluated exactly once, so it is safe
+ to put side effects into them (such as increasing the index). */
+
+/* Write into the canonical representation, this macro does not do any sanity
+ checks and is intended for usage in loops. The caller should cache the
+ kind and data pointers obtained from other macro calls.
+ index is the index in the string (starts at 0) and value is the new
+ code point value which should be written to that location. */
+#define PyUnicode_WRITE(kind, data, index, value) \
+ do { \
+ switch ((kind)) { \
+ case PyUnicode_1BYTE_KIND: { \
+ ((Py_UCS1 *)(data))[(index)] = (Py_UCS1)(value); \
+ break; \
+ } \
+ case PyUnicode_2BYTE_KIND: { \
+ ((Py_UCS2 *)(data))[(index)] = (Py_UCS2)(value); \
+ break; \
+ } \
+ default: { \
+ assert((kind) == PyUnicode_4BYTE_KIND); \
+ ((Py_UCS4 *)(data))[(index)] = (Py_UCS4)(value); \
+ } \
+ } \
+ } while (0)
+
+/* Read a code point from the string's canonical representation. No checks
+ or ready calls are performed. */
+#define PyUnicode_READ(kind, data, index) \
+ ((Py_UCS4) \
+ ((kind) == PyUnicode_1BYTE_KIND ? \
+ ((const Py_UCS1 *)(data))[(index)] : \
+ ((kind) == PyUnicode_2BYTE_KIND ? \
+ ((const Py_UCS2 *)(data))[(index)] : \
+ ((const Py_UCS4 *)(data))[(index)] \
+ ) \
+ ))
+
+/* PyUnicode_READ_CHAR() is less efficient than PyUnicode_READ() because it
+ calls PyUnicode_KIND() and might call it twice. For single reads, use
+ PyUnicode_READ_CHAR, for multiple consecutive reads callers should
+ cache kind and use PyUnicode_READ instead. */
+#define PyUnicode_READ_CHAR(unicode, index) \
+ (assert(PyUnicode_Check(unicode)), \
+ assert(PyUnicode_IS_READY(unicode)), \
+ (Py_UCS4) \
+ (PyUnicode_KIND((unicode)) == PyUnicode_1BYTE_KIND ? \
+ ((const Py_UCS1 *)(PyUnicode_DATA((unicode))))[(index)] : \
+ (PyUnicode_KIND((unicode)) == PyUnicode_2BYTE_KIND ? \
+ ((const Py_UCS2 *)(PyUnicode_DATA((unicode))))[(index)] : \
+ ((const Py_UCS4 *)(PyUnicode_DATA((unicode))))[(index)] \
+ ) \
+ ))
+
+/* Returns the length of the unicode string. The caller has to make sure that
+ the string has it's canonical representation set before calling
+ this macro. Call PyUnicode_(FAST_)Ready to ensure that. */
+#define PyUnicode_GET_LENGTH(op) \
+ (assert(PyUnicode_Check(op)), \
+ assert(PyUnicode_IS_READY(op)), \
+ ((PyASCIIObject *)(op))->length)
+
+
+/* Fast check to determine whether an object is ready. Equivalent to
+ PyUnicode_IS_COMPACT(op) || ((PyUnicodeObject*)(op))->data.any) */
+
+#define PyUnicode_IS_READY(op) (((PyASCIIObject*)op)->state.ready)
+
+/* PyUnicode_READY() does less work than _PyUnicode_Ready() in the best
+ case. If the canonical representation is not yet set, it will still call
+ _PyUnicode_Ready().
+ Returns 0 on success and -1 on errors. */
+#define PyUnicode_READY(op) \
+ (assert(PyUnicode_Check(op)), \
+ (PyUnicode_IS_READY(op) ? \
+ 0 : _PyUnicode_Ready(_PyObject_CAST(op))))
+
+/* Return a maximum character value which is suitable for creating another
+ string based on op. This is always an approximation but more efficient
+ than iterating over the string. */
+#define PyUnicode_MAX_CHAR_VALUE(op) \
+ (assert(PyUnicode_IS_READY(op)), \
+ (PyUnicode_IS_ASCII(op) ? \
+ (0x7f) : \
+ (PyUnicode_KIND(op) == PyUnicode_1BYTE_KIND ? \
+ (0xffU) : \
+ (PyUnicode_KIND(op) == PyUnicode_2BYTE_KIND ? \
+ (0xffffU) : \
+ (0x10ffffU)))))
+
+/* === Public API ========================================================= */
+
+/* --- Plain Py_UNICODE --------------------------------------------------- */
+
+/* With PEP 393, this is the recommended way to allocate a new unicode object.
+ This function will allocate the object and its buffer in a single memory
+ block. Objects created using this function are not resizable. */
+PyAPI_FUNC(PyObject*) PyUnicode_New(
+ Py_ssize_t size, /* Number of code points in the new string */
+ Py_UCS4 maxchar /* maximum code point value in the string */
+ );
+
+/* Initializes the canonical string representation from the deprecated
+ wstr/Py_UNICODE representation. This function is used to convert Unicode
+ objects which were created using the old API to the new flexible format
+ introduced with PEP 393.
+
+ Don't call this function directly, use the public PyUnicode_READY() macro
+ instead. */
+PyAPI_FUNC(int) _PyUnicode_Ready(
+ PyObject *unicode /* Unicode object */
+ );
+
+/* Get a copy of a Unicode string. */
+PyAPI_FUNC(PyObject*) _PyUnicode_Copy(
+ PyObject *unicode
+ );
+
+/* Copy character from one unicode object into another, this function performs
+ character conversion when necessary and falls back to memcpy() if possible.
+
+ Fail if to is too small (smaller than *how_many* or smaller than
+ len(from)-from_start), or if kind(from[from_start:from_start+how_many]) >
+ kind(to), or if *to* has more than 1 reference.
+
+ Return the number of written character, or return -1 and raise an exception
+ on error.
+
+ Pseudo-code:
+
+ how_many = min(how_many, len(from) - from_start)
+ to[to_start:to_start+how_many] = from[from_start:from_start+how_many]
+ return how_many
+
+ Note: The function doesn't write a terminating null character.
+ */
+PyAPI_FUNC(Py_ssize_t) PyUnicode_CopyCharacters(
+ PyObject *to,
+ Py_ssize_t to_start,
+ PyObject *from,
+ Py_ssize_t from_start,
+ Py_ssize_t how_many
+ );
+
+/* Unsafe version of PyUnicode_CopyCharacters(): don't check arguments and so
+ may crash if parameters are invalid (e.g. if the output string
+ is too short). */
+PyAPI_FUNC(void) _PyUnicode_FastCopyCharacters(
+ PyObject *to,
+ Py_ssize_t to_start,
+ PyObject *from,
+ Py_ssize_t from_start,
+ Py_ssize_t how_many
+ );
+
+/* Fill a string with a character: write fill_char into
+ unicode[start:start+length].
+
+ Fail if fill_char is bigger than the string maximum character, or if the
+ string has more than 1 reference.
+
+ Return the number of written character, or return -1 and raise an exception
+ on error. */
+PyAPI_FUNC(Py_ssize_t) PyUnicode_Fill(
+ PyObject *unicode,
+ Py_ssize_t start,
+ Py_ssize_t length,
+ Py_UCS4 fill_char
+ );
+
+/* Unsafe version of PyUnicode_Fill(): don't check arguments and so may crash
+ if parameters are invalid (e.g. if length is longer than the string). */
+PyAPI_FUNC(void) _PyUnicode_FastFill(
+ PyObject *unicode,
+ Py_ssize_t start,
+ Py_ssize_t length,
+ Py_UCS4 fill_char
+ );
+
+/* Create a Unicode Object from the Py_UNICODE buffer u of the given
+ size.
+
+ u may be NULL which causes the contents to be undefined. It is the
+ user's responsibility to fill in the needed data afterwards. Note
+ that modifying the Unicode object contents after construction is
+ only allowed if u was set to NULL.
+
+ The buffer is copied into the new object. */
+/* Py_DEPRECATED(3.3) */ PyAPI_FUNC(PyObject*) PyUnicode_FromUnicode(
+ const Py_UNICODE *u, /* Unicode buffer */
+ Py_ssize_t size /* size of buffer */
+ );
+
+/* Create a new string from a buffer of Py_UCS1, Py_UCS2 or Py_UCS4 characters.
+ Scan the string to find the maximum character. */
+PyAPI_FUNC(PyObject*) PyUnicode_FromKindAndData(
+ int kind,
+ const void *buffer,
+ Py_ssize_t size);
+
+/* Create a new string from a buffer of ASCII characters.
+ WARNING: Don't check if the string contains any non-ASCII character. */
+PyAPI_FUNC(PyObject*) _PyUnicode_FromASCII(
+ const char *buffer,
+ Py_ssize_t size);
+
+/* Compute the maximum character of the substring unicode[start:end].
+ Return 127 for an empty string. */
+PyAPI_FUNC(Py_UCS4) _PyUnicode_FindMaxChar (
+ PyObject *unicode,
+ Py_ssize_t start,
+ Py_ssize_t end);
+
+/* Return a read-only pointer to the Unicode object's internal
+ Py_UNICODE buffer.
+ If the wchar_t/Py_UNICODE representation is not yet available, this
+ function will calculate it. */
+/* Py_DEPRECATED(3.3) */ PyAPI_FUNC(Py_UNICODE *) PyUnicode_AsUnicode(
+ PyObject *unicode /* Unicode object */
+ );
+
+/* Similar to PyUnicode_AsUnicode(), but raises a ValueError if the string
+ contains null characters. */
+PyAPI_FUNC(const Py_UNICODE *) _PyUnicode_AsUnicode(
+ PyObject *unicode /* Unicode object */
+ );
+
+/* Return a read-only pointer to the Unicode object's internal
+ Py_UNICODE buffer and save the length at size.
+ If the wchar_t/Py_UNICODE representation is not yet available, this
+ function will calculate it. */
+
+/* Py_DEPRECATED(3.3) */ PyAPI_FUNC(Py_UNICODE *) PyUnicode_AsUnicodeAndSize(
+ PyObject *unicode, /* Unicode object */
+ Py_ssize_t *size /* location where to save the length */
+ );
+
+/* Get the maximum ordinal for a Unicode character. */
+Py_DEPRECATED(3.3) PyAPI_FUNC(Py_UNICODE) PyUnicode_GetMax(void);
+
+
+/* --- _PyUnicodeWriter API ----------------------------------------------- */
+
+typedef struct {
+ PyObject *buffer;
+ void *data;
+ enum PyUnicode_Kind kind;
+ Py_UCS4 maxchar;
+ Py_ssize_t size;
+ Py_ssize_t pos;
+
+ /* minimum number of allocated characters (default: 0) */
+ Py_ssize_t min_length;
+
+ /* minimum character (default: 127, ASCII) */
+ Py_UCS4 min_char;
+
+ /* If non-zero, overallocate the buffer (default: 0). */
+ unsigned char overallocate;
+
+ /* If readonly is 1, buffer is a shared string (cannot be modified)
+ and size is set to 0. */
+ unsigned char readonly;
+} _PyUnicodeWriter ;
+
+/* Initialize a Unicode writer.
+ *
+ * By default, the minimum buffer size is 0 character and overallocation is
+ * disabled. Set min_length, min_char and overallocate attributes to control
+ * the allocation of the buffer. */
+PyAPI_FUNC(void)
+_PyUnicodeWriter_Init(_PyUnicodeWriter *writer);
+
+/* Prepare the buffer to write 'length' characters
+ with the specified maximum character.
+
+ Return 0 on success, raise an exception and return -1 on error. */
+#define _PyUnicodeWriter_Prepare(WRITER, LENGTH, MAXCHAR) \
+ (((MAXCHAR) <= (WRITER)->maxchar \
+ && (LENGTH) <= (WRITER)->size - (WRITER)->pos) \
+ ? 0 \
+ : (((LENGTH) == 0) \
+ ? 0 \
+ : _PyUnicodeWriter_PrepareInternal((WRITER), (LENGTH), (MAXCHAR))))
+
+/* Don't call this function directly, use the _PyUnicodeWriter_Prepare() macro
+ instead. */
+PyAPI_FUNC(int)
+_PyUnicodeWriter_PrepareInternal(_PyUnicodeWriter *writer,
+ Py_ssize_t length, Py_UCS4 maxchar);
+
+/* Prepare the buffer to have at least the kind KIND.
+ For example, kind=PyUnicode_2BYTE_KIND ensures that the writer will
+ support characters in range U+000-U+FFFF.
+
+ Return 0 on success, raise an exception and return -1 on error. */
+#define _PyUnicodeWriter_PrepareKind(WRITER, KIND) \
+ (assert((KIND) != PyUnicode_WCHAR_KIND), \
+ (KIND) <= (WRITER)->kind \
+ ? 0 \
+ : _PyUnicodeWriter_PrepareKindInternal((WRITER), (KIND)))
+
+/* Don't call this function directly, use the _PyUnicodeWriter_PrepareKind()
+ macro instead. */
+PyAPI_FUNC(int)
+_PyUnicodeWriter_PrepareKindInternal(_PyUnicodeWriter *writer,
+ enum PyUnicode_Kind kind);
+
+/* Append a Unicode character.
+ Return 0 on success, raise an exception and return -1 on error. */
+PyAPI_FUNC(int)
+_PyUnicodeWriter_WriteChar(_PyUnicodeWriter *writer,
+ Py_UCS4 ch
+ );
+
+/* Append a Unicode string.
+ Return 0 on success, raise an exception and return -1 on error. */
+PyAPI_FUNC(int)
+_PyUnicodeWriter_WriteStr(_PyUnicodeWriter *writer,
+ PyObject *str /* Unicode string */
+ );
+
+/* Append a substring of a Unicode string.
+ Return 0 on success, raise an exception and return -1 on error. */
+PyAPI_FUNC(int)
+_PyUnicodeWriter_WriteSubstring(_PyUnicodeWriter *writer,
+ PyObject *str, /* Unicode string */
+ Py_ssize_t start,
+ Py_ssize_t end
+ );
+
+/* Append an ASCII-encoded byte string.
+ Return 0 on success, raise an exception and return -1 on error. */
+PyAPI_FUNC(int)
+_PyUnicodeWriter_WriteASCIIString(_PyUnicodeWriter *writer,
+ const char *str, /* ASCII-encoded byte string */
+ Py_ssize_t len /* number of bytes, or -1 if unknown */
+ );
+
+/* Append a latin1-encoded byte string.
+ Return 0 on success, raise an exception and return -1 on error. */
+PyAPI_FUNC(int)
+_PyUnicodeWriter_WriteLatin1String(_PyUnicodeWriter *writer,
+ const char *str, /* latin1-encoded byte string */
+ Py_ssize_t len /* length in bytes */
+ );
+
+/* Get the value of the writer as a Unicode string. Clear the
+ buffer of the writer. Raise an exception and return NULL
+ on error. */
+PyAPI_FUNC(PyObject *)
+_PyUnicodeWriter_Finish(_PyUnicodeWriter *writer);
+
+/* Deallocate memory of a writer (clear its internal buffer). */
+PyAPI_FUNC(void)
+_PyUnicodeWriter_Dealloc(_PyUnicodeWriter *writer);
+
+
+/* Format the object based on the format_spec, as defined in PEP 3101
+ (Advanced String Formatting). */
+PyAPI_FUNC(int) _PyUnicode_FormatAdvancedWriter(
+ _PyUnicodeWriter *writer,
+ PyObject *obj,
+ PyObject *format_spec,
+ Py_ssize_t start,
+ Py_ssize_t end);
+
+/* --- wchar_t support for platforms which support it --------------------- */
+
+#ifdef HAVE_WCHAR_H
+PyAPI_FUNC(void*) _PyUnicode_AsKind(PyObject *s, unsigned int kind);
+#endif
+
+/* --- Manage the default encoding ---------------------------------------- */
+
+/* Returns a pointer to the default encoding (UTF-8) of the
+ Unicode object unicode and the size of the encoded representation
+ in bytes stored in *size.
+
+ In case of an error, no *size is set.
+
+ This function caches the UTF-8 encoded string in the unicodeobject
+ and subsequent calls will return the same string. The memory is released
+ when the unicodeobject is deallocated.
+
+ _PyUnicode_AsStringAndSize is a #define for PyUnicode_AsUTF8AndSize to
+ support the previous internal function with the same behaviour.
+
+ *** This API is for interpreter INTERNAL USE ONLY and will likely
+ *** be removed or changed in the future.
+
+ *** If you need to access the Unicode object as UTF-8 bytes string,
+ *** please use PyUnicode_AsUTF8String() instead.
+*/
+
+PyAPI_FUNC(const char *) PyUnicode_AsUTF8AndSize(
+ PyObject *unicode,
+ Py_ssize_t *size);
+
+#define _PyUnicode_AsStringAndSize PyUnicode_AsUTF8AndSize
+
+/* Returns a pointer to the default encoding (UTF-8) of the
+ Unicode object unicode.
+
+ Like PyUnicode_AsUTF8AndSize(), this also caches the UTF-8 representation
+ in the unicodeobject.
+
+ _PyUnicode_AsString is a #define for PyUnicode_AsUTF8 to
+ support the previous internal function with the same behaviour.
+
+ Use of this API is DEPRECATED since no size information can be
+ extracted from the returned data.
+
+ *** This API is for interpreter INTERNAL USE ONLY and will likely
+ *** be removed or changed for Python 3.1.
+
+ *** If you need to access the Unicode object as UTF-8 bytes string,
+ *** please use PyUnicode_AsUTF8String() instead.
+
+*/
+
+PyAPI_FUNC(const char *) PyUnicode_AsUTF8(PyObject *unicode);
+
+#define _PyUnicode_AsString PyUnicode_AsUTF8
+
+/* --- Generic Codecs ----------------------------------------------------- */
+
+/* Encodes a Py_UNICODE buffer of the given size and returns a
+ Python string object. */
+Py_DEPRECATED(3.3) PyAPI_FUNC(PyObject*) PyUnicode_Encode(
+ const Py_UNICODE *s, /* Unicode char buffer */
+ Py_ssize_t size, /* number of Py_UNICODE chars to encode */
+ const char *encoding, /* encoding */
+ const char *errors /* error handling */
+ );
+
+/* --- UTF-7 Codecs ------------------------------------------------------- */
+
+Py_DEPRECATED(3.3) PyAPI_FUNC(PyObject*) PyUnicode_EncodeUTF7(
+ const Py_UNICODE *data, /* Unicode char buffer */
+ Py_ssize_t length, /* number of Py_UNICODE chars to encode */
+ int base64SetO, /* Encode RFC2152 Set O characters in base64 */
+ int base64WhiteSpace, /* Encode whitespace (sp, ht, nl, cr) in base64 */
+ const char *errors /* error handling */
+ );
+
+PyAPI_FUNC(PyObject*) _PyUnicode_EncodeUTF7(
+ PyObject *unicode, /* Unicode object */
+ int base64SetO, /* Encode RFC2152 Set O characters in base64 */
+ int base64WhiteSpace, /* Encode whitespace (sp, ht, nl, cr) in base64 */
+ const char *errors /* error handling */
+ );
+
+/* --- UTF-8 Codecs ------------------------------------------------------- */
+
+PyAPI_FUNC(PyObject*) _PyUnicode_AsUTF8String(
+ PyObject *unicode,
+ const char *errors);
+
+Py_DEPRECATED(3.3) PyAPI_FUNC(PyObject*) PyUnicode_EncodeUTF8(
+ const Py_UNICODE *data, /* Unicode char buffer */
+ Py_ssize_t length, /* number of Py_UNICODE chars to encode */
+ const char *errors /* error handling */
+ );
+
+/* --- UTF-32 Codecs ------------------------------------------------------ */
+
+Py_DEPRECATED(3.3) PyAPI_FUNC(PyObject*) PyUnicode_EncodeUTF32(
+ const Py_UNICODE *data, /* Unicode char buffer */
+ Py_ssize_t length, /* number of Py_UNICODE chars to encode */
+ const char *errors, /* error handling */
+ int byteorder /* byteorder to use 0=BOM+native;-1=LE,1=BE */
+ );
+
+PyAPI_FUNC(PyObject*) _PyUnicode_EncodeUTF32(
+ PyObject *object, /* Unicode object */
+ const char *errors, /* error handling */
+ int byteorder /* byteorder to use 0=BOM+native;-1=LE,1=BE */
+ );
+
+/* --- UTF-16 Codecs ------------------------------------------------------ */
+
+/* Returns a Python string object holding the UTF-16 encoded value of
+ the Unicode data.
+
+ If byteorder is not 0, output is written according to the following
+ byte order:
+
+ byteorder == -1: little endian
+ byteorder == 0: native byte order (writes a BOM mark)
+ byteorder == 1: big endian
+
+ If byteorder is 0, the output string will always start with the
+ Unicode BOM mark (U+FEFF). In the other two modes, no BOM mark is
+ prepended.
+
+ Note that Py_UNICODE data is being interpreted as UTF-16 reduced to
+ UCS-2. This trick makes it possible to add full UTF-16 capabilities
+ at a later point without compromising the APIs.
+
+*/
+Py_DEPRECATED(3.3) PyAPI_FUNC(PyObject*) PyUnicode_EncodeUTF16(
+ const Py_UNICODE *data, /* Unicode char buffer */
+ Py_ssize_t length, /* number of Py_UNICODE chars to encode */
+ const char *errors, /* error handling */
+ int byteorder /* byteorder to use 0=BOM+native;-1=LE,1=BE */
+ );
+
+PyAPI_FUNC(PyObject*) _PyUnicode_EncodeUTF16(
+ PyObject* unicode, /* Unicode object */
+ const char *errors, /* error handling */
+ int byteorder /* byteorder to use 0=BOM+native;-1=LE,1=BE */
+ );
+
+/* --- Unicode-Escape Codecs ---------------------------------------------- */
+
+/* Helper for PyUnicode_DecodeUnicodeEscape that detects invalid escape
+ chars. */
+PyAPI_FUNC(PyObject*) _PyUnicode_DecodeUnicodeEscape(
+ const char *string, /* Unicode-Escape encoded string */
+ Py_ssize_t length, /* size of string */
+ const char *errors, /* error handling */
+ const char **first_invalid_escape /* on return, points to first
+ invalid escaped char in
+ string. */
+);
+
+Py_DEPRECATED(3.3) PyAPI_FUNC(PyObject*) PyUnicode_EncodeUnicodeEscape(
+ const Py_UNICODE *data, /* Unicode char buffer */
+ Py_ssize_t length /* Number of Py_UNICODE chars to encode */
+ );
+
+/* --- Raw-Unicode-Escape Codecs ------------------------------------------ */
+
+Py_DEPRECATED(3.3) PyAPI_FUNC(PyObject*) PyUnicode_EncodeRawUnicodeEscape(
+ const Py_UNICODE *data, /* Unicode char buffer */
+ Py_ssize_t length /* Number of Py_UNICODE chars to encode */
+ );
+
+/* --- Latin-1 Codecs ----------------------------------------------------- */
+
+PyAPI_FUNC(PyObject*) _PyUnicode_AsLatin1String(
+ PyObject* unicode,
+ const char* errors);
+
+Py_DEPRECATED(3.3) PyAPI_FUNC(PyObject*) PyUnicode_EncodeLatin1(
+ const Py_UNICODE *data, /* Unicode char buffer */
+ Py_ssize_t length, /* Number of Py_UNICODE chars to encode */
+ const char *errors /* error handling */
+ );
+
+/* --- ASCII Codecs ------------------------------------------------------- */
+
+PyAPI_FUNC(PyObject*) _PyUnicode_AsASCIIString(
+ PyObject* unicode,
+ const char* errors);
+
+Py_DEPRECATED(3.3) PyAPI_FUNC(PyObject*) PyUnicode_EncodeASCII(
+ const Py_UNICODE *data, /* Unicode char buffer */
+ Py_ssize_t length, /* Number of Py_UNICODE chars to encode */
+ const char *errors /* error handling */
+ );
+
+/* --- Character Map Codecs ----------------------------------------------- */
+
+Py_DEPRECATED(3.3) PyAPI_FUNC(PyObject*) PyUnicode_EncodeCharmap(
+ const Py_UNICODE *data, /* Unicode char buffer */
+ Py_ssize_t length, /* Number of Py_UNICODE chars to encode */
+ PyObject *mapping, /* encoding mapping */
+ const char *errors /* error handling */
+ );
+
+PyAPI_FUNC(PyObject*) _PyUnicode_EncodeCharmap(
+ PyObject *unicode, /* Unicode object */
+ PyObject *mapping, /* encoding mapping */
+ const char *errors /* error handling */
+ );
+
+/* Translate a Py_UNICODE buffer of the given length by applying a
+ character mapping table to it and return the resulting Unicode
+ object.
+
+ The mapping table must map Unicode ordinal integers to Unicode strings,
+ Unicode ordinal integers or None (causing deletion of the character).
+
+ Mapping tables may be dictionaries or sequences. Unmapped character
+ ordinals (ones which cause a LookupError) are left untouched and
+ are copied as-is.
+
+*/
+Py_DEPRECATED(3.3) PyAPI_FUNC(PyObject *) PyUnicode_TranslateCharmap(
+ const Py_UNICODE *data, /* Unicode char buffer */
+ Py_ssize_t length, /* Number of Py_UNICODE chars to encode */
+ PyObject *table, /* Translate table */
+ const char *errors /* error handling */
+ );
+
+/* --- MBCS codecs for Windows -------------------------------------------- */
+
+#ifdef MS_WINDOWS
+Py_DEPRECATED(3.3) PyAPI_FUNC(PyObject*) PyUnicode_EncodeMBCS(
+ const Py_UNICODE *data, /* Unicode char buffer */
+ Py_ssize_t length, /* number of Py_UNICODE chars to encode */
+ const char *errors /* error handling */
+ );
+#endif
+
+/* --- Decimal Encoder ---------------------------------------------------- */
+
+/* Takes a Unicode string holding a decimal value and writes it into
+ an output buffer using standard ASCII digit codes.
+
+ The output buffer has to provide at least length+1 bytes of storage
+ area. The output string is 0-terminated.
+
+ The encoder converts whitespace to ' ', decimal characters to their
+ corresponding ASCII digit and all other Latin-1 characters except
+ \0 as-is. Characters outside this range (Unicode ordinals 1-256)
+ are treated as errors. This includes embedded NULL bytes.
+
+ Error handling is defined by the errors argument:
+
+ NULL or "strict": raise a ValueError
+ "ignore": ignore the wrong characters (these are not copied to the
+ output buffer)
+ "replace": replaces illegal characters with '?'
+
+ Returns 0 on success, -1 on failure.
+
+*/
+
+/* Py_DEPRECATED(3.3) */ PyAPI_FUNC(int) PyUnicode_EncodeDecimal(
+ Py_UNICODE *s, /* Unicode buffer */
+ Py_ssize_t length, /* Number of Py_UNICODE chars to encode */
+ char *output, /* Output buffer; must have size >= length */
+ const char *errors /* error handling */
+ );
+
+/* Transforms code points that have decimal digit property to the
+ corresponding ASCII digit code points.
+
+ Returns a new Unicode string on success, NULL on failure.
+*/
+
+/* Py_DEPRECATED(3.3) */
+PyAPI_FUNC(PyObject*) PyUnicode_TransformDecimalToASCII(
+ Py_UNICODE *s, /* Unicode buffer */
+ Py_ssize_t length /* Number of Py_UNICODE chars to transform */
+ );
+
+/* Coverts a Unicode object holding a decimal value to an ASCII string
+ for using in int, float and complex parsers.
+ Transforms code points that have decimal digit property to the
+ corresponding ASCII digit code points. Transforms spaces to ASCII.
+ Transforms code points starting from the first non-ASCII code point that
+ is neither a decimal digit nor a space to the end into '?'. */
+
+PyAPI_FUNC(PyObject*) _PyUnicode_TransformDecimalAndSpaceToASCII(
+ PyObject *unicode /* Unicode object */
+ );
+
+/* --- Methods & Slots ---------------------------------------------------- */
+
+PyAPI_FUNC(PyObject *) _PyUnicode_JoinArray(
+ PyObject *separator,
+ PyObject *const *items,
+ Py_ssize_t seqlen
+ );
+
+/* Test whether a unicode is equal to ASCII identifier. Return 1 if true,
+ 0 otherwise. The right argument must be ASCII identifier.
+ Any error occurs inside will be cleared before return. */
+PyAPI_FUNC(int) _PyUnicode_EqualToASCIIId(
+ PyObject *left, /* Left string */
+ _Py_Identifier *right /* Right identifier */
+ );
+
+/* Test whether a unicode is equal to ASCII string. Return 1 if true,
+ 0 otherwise. The right argument must be ASCII-encoded string.
+ Any error occurs inside will be cleared before return. */
+PyAPI_FUNC(int) _PyUnicode_EqualToASCIIString(
+ PyObject *left,
+ const char *right /* ASCII-encoded string */
+ );
+
+/* Externally visible for str.strip(unicode) */
+PyAPI_FUNC(PyObject *) _PyUnicode_XStrip(
+ PyObject *self,
+ int striptype,
+ PyObject *sepobj
+ );
+
+/* Using explicit passed-in values, insert the thousands grouping
+ into the string pointed to by buffer. For the argument descriptions,
+ see Objects/stringlib/localeutil.h */
+PyAPI_FUNC(Py_ssize_t) _PyUnicode_InsertThousandsGrouping(
+ _PyUnicodeWriter *writer,
+ Py_ssize_t n_buffer,
+ PyObject *digits,
+ Py_ssize_t d_pos,
+ Py_ssize_t n_digits,
+ Py_ssize_t min_width,
+ const char *grouping,
+ PyObject *thousands_sep,
+ Py_UCS4 *maxchar);
+
+/* === Characters Type APIs =============================================== */
+
+/* Helper array used by Py_UNICODE_ISSPACE(). */
+
+PyAPI_DATA(const unsigned char) _Py_ascii_whitespace[];
+
+/* These should not be used directly. Use the Py_UNICODE_IS* and
+ Py_UNICODE_TO* macros instead.
+
+ These APIs are implemented in Objects/unicodectype.c.
+
+*/
+
+PyAPI_FUNC(int) _PyUnicode_IsLowercase(
+ Py_UCS4 ch /* Unicode character */
+ );
+
+PyAPI_FUNC(int) _PyUnicode_IsUppercase(
+ Py_UCS4 ch /* Unicode character */
+ );
+
+PyAPI_FUNC(int) _PyUnicode_IsTitlecase(
+ Py_UCS4 ch /* Unicode character */
+ );
+
+PyAPI_FUNC(int) _PyUnicode_IsXidStart(
+ Py_UCS4 ch /* Unicode character */
+ );
+
+PyAPI_FUNC(int) _PyUnicode_IsXidContinue(
+ Py_UCS4 ch /* Unicode character */
+ );
+
+PyAPI_FUNC(int) _PyUnicode_IsWhitespace(
+ const Py_UCS4 ch /* Unicode character */
+ );
+
+PyAPI_FUNC(int) _PyUnicode_IsLinebreak(
+ const Py_UCS4 ch /* Unicode character */
+ );
+
+/* Py_DEPRECATED(3.3) */ PyAPI_FUNC(Py_UCS4) _PyUnicode_ToLowercase(
+ Py_UCS4 ch /* Unicode character */
+ );
+
+/* Py_DEPRECATED(3.3) */ PyAPI_FUNC(Py_UCS4) _PyUnicode_ToUppercase(
+ Py_UCS4 ch /* Unicode character */
+ );
+
+Py_DEPRECATED(3.3) PyAPI_FUNC(Py_UCS4) _PyUnicode_ToTitlecase(
+ Py_UCS4 ch /* Unicode character */
+ );
+
+PyAPI_FUNC(int) _PyUnicode_ToLowerFull(
+ Py_UCS4 ch, /* Unicode character */
+ Py_UCS4 *res
+ );
+
+PyAPI_FUNC(int) _PyUnicode_ToTitleFull(
+ Py_UCS4 ch, /* Unicode character */
+ Py_UCS4 *res
+ );
+
+PyAPI_FUNC(int) _PyUnicode_ToUpperFull(
+ Py_UCS4 ch, /* Unicode character */
+ Py_UCS4 *res
+ );
+
+PyAPI_FUNC(int) _PyUnicode_ToFoldedFull(
+ Py_UCS4 ch, /* Unicode character */
+ Py_UCS4 *res
+ );
+
+PyAPI_FUNC(int) _PyUnicode_IsCaseIgnorable(
+ Py_UCS4 ch /* Unicode character */
+ );
+
+PyAPI_FUNC(int) _PyUnicode_IsCased(
+ Py_UCS4 ch /* Unicode character */
+ );
+
+PyAPI_FUNC(int) _PyUnicode_ToDecimalDigit(
+ Py_UCS4 ch /* Unicode character */
+ );
+
+PyAPI_FUNC(int) _PyUnicode_ToDigit(
+ Py_UCS4 ch /* Unicode character */
+ );
+
+PyAPI_FUNC(double) _PyUnicode_ToNumeric(
+ Py_UCS4 ch /* Unicode character */
+ );
+
+PyAPI_FUNC(int) _PyUnicode_IsDecimalDigit(
+ Py_UCS4 ch /* Unicode character */
+ );
+
+PyAPI_FUNC(int) _PyUnicode_IsDigit(
+ Py_UCS4 ch /* Unicode character */
+ );
+
+PyAPI_FUNC(int) _PyUnicode_IsNumeric(
+ Py_UCS4 ch /* Unicode character */
+ );
+
+PyAPI_FUNC(int) _PyUnicode_IsPrintable(
+ Py_UCS4 ch /* Unicode character */
+ );
+
+PyAPI_FUNC(int) _PyUnicode_IsAlpha(
+ Py_UCS4 ch /* Unicode character */
+ );
+
+Py_DEPRECATED(3.3) PyAPI_FUNC(size_t) Py_UNICODE_strlen(
+ const Py_UNICODE *u
+ );
+
+Py_DEPRECATED(3.3) PyAPI_FUNC(Py_UNICODE*) Py_UNICODE_strcpy(
+ Py_UNICODE *s1,
+ const Py_UNICODE *s2);
+
+Py_DEPRECATED(3.3) PyAPI_FUNC(Py_UNICODE*) Py_UNICODE_strcat(
+ Py_UNICODE *s1, const Py_UNICODE *s2);
+
+Py_DEPRECATED(3.3) PyAPI_FUNC(Py_UNICODE*) Py_UNICODE_strncpy(
+ Py_UNICODE *s1,
+ const Py_UNICODE *s2,
+ size_t n);
+
+Py_DEPRECATED(3.3) PyAPI_FUNC(int) Py_UNICODE_strcmp(
+ const Py_UNICODE *s1,
+ const Py_UNICODE *s2
+ );
+
+Py_DEPRECATED(3.3) PyAPI_FUNC(int) Py_UNICODE_strncmp(
+ const Py_UNICODE *s1,
+ const Py_UNICODE *s2,
+ size_t n
+ );
+
+Py_DEPRECATED(3.3) PyAPI_FUNC(Py_UNICODE*) Py_UNICODE_strchr(
+ const Py_UNICODE *s,
+ Py_UNICODE c
+ );
+
+Py_DEPRECATED(3.3) PyAPI_FUNC(Py_UNICODE*) Py_UNICODE_strrchr(
+ const Py_UNICODE *s,
+ Py_UNICODE c
+ );
+
+PyAPI_FUNC(PyObject*) _PyUnicode_FormatLong(PyObject *, int, int, int);
+
+/* Create a copy of a unicode string ending with a nul character. Return NULL
+ and raise a MemoryError exception on memory allocation failure, otherwise
+ return a new allocated buffer (use PyMem_Free() to free the buffer). */
+
+Py_DEPRECATED(3.3) PyAPI_FUNC(Py_UNICODE*) PyUnicode_AsUnicodeCopy(
+ PyObject *unicode
+ );
+
+/* Return an interned Unicode object for an Identifier; may fail if there is no memory.*/
+PyAPI_FUNC(PyObject*) _PyUnicode_FromId(_Py_Identifier*);
+/* Clear all static strings. */
+PyAPI_FUNC(void) _PyUnicode_ClearStaticStrings(void);
+
+/* Fast equality check when the inputs are known to be exact unicode types
+ and where the hash values are equal (i.e. a very probable match) */
+PyAPI_FUNC(int) _PyUnicode_EQ(PyObject *, PyObject *);
+
+#ifdef __cplusplus
+}
+#endif
