#ifndef Py_CPYTHON_UNICODEOBJECT_H
#  error "this header file must not be included directly"
#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. */
Py_DEPRECATED(3.13) typedef wchar_t PY_UNICODE_TYPE;
Py_DEPRECATED(3.13) typedef wchar_t Py_UNICODE;


/* --- Internal Unicode Operations ---------------------------------------- */

// Static inline functions to work with surrogates
static inline int Py_UNICODE_IS_SURROGATE(Py_UCS4 ch) {
    return (0xD800 data.any;
    assert(data != NULL);
    return data;
}

PyAPI_FUNC(void*) PyUnicode_DATA(PyObject *op);

static inline void* _PyUnicode_DATA(PyObject *op) {
    if (PyUnicode_IS_COMPACT(op)) {
        return _PyUnicode_COMPACT_DATA(op);
    }
    return _PyUnicode_NONCOMPACT_DATA(op);
}
#define PyUnicode_DATA(op) _PyUnicode_DATA(_PyObject_CAST(op))

/* 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_STATIC_CAST(Py_UCS1*, PyUnicode_DATA(op))
#define PyUnicode_2BYTE_DATA(op) _Py_STATIC_CAST(Py_UCS2*, PyUnicode_DATA(op))
#define PyUnicode_4BYTE_DATA(op) _Py_STATIC_CAST(Py_UCS4*, PyUnicode_DATA(op))

/* Returns the length of the unicode string. */
static inline Py_ssize_t PyUnicode_GET_LENGTH(PyObject *op) {
    return _PyASCIIObject_CAST(op)->length;
}
#define PyUnicode_GET_LENGTH(op) PyUnicode_GET_LENGTH(_PyObject_CAST(op))

/* Returns the cached hash, or -1 if not cached yet. */
static inline Py_hash_t
PyUnstable_Unicode_GET_CACHED_HASH(PyObject *op) {
#ifdef Py_GIL_DISABLED
    return _Py_atomic_load_ssize_relaxed(&_PyASCIIObject_CAST(op)->hash);
#else
    return _PyASCIIObject_CAST(op)->hash;
#endif
}

/* Write into the canonical representation, this function 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 function 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. */
static inline void PyUnicode_WRITE(int kind, void *data,
                                   Py_ssize_t index, Py_UCS4 value)
{
    assert(index >= 0);
    if (kind == PyUnicode_1BYTE_KIND) {
        assert(value pos)                  \
     ? 0                                                              \
     : (((LENGTH) == 0)                                               \
        ? 0                                                           \
        : _PyUnicodeWriter_PrepareInternal((WRITER), (LENGTH), (MAXCHAR))))

/* Don't call this function directly, use the _PyUnicodeWriter_Prepare() macro
   instead. */
_Py_DEPRECATED_EXTERNALLY(3.14) 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)                    \
    ((KIND) kind                                         \
     ? 0                                                              \
     : _PyUnicodeWriter_PrepareKindInternal((WRITER), (KIND)))

/* Don't call this function directly, use the _PyUnicodeWriter_PrepareKind()
   macro instead. */
_Py_DEPRECATED_EXTERNALLY(3.14) PyAPI_FUNC(int) _PyUnicodeWriter_PrepareKindInternal(
    _PyUnicodeWriter *writer,
    int kind);

/* Append a Unicode character.
   Return 0 on success, raise an exception and return -1 on error. */
_Py_DEPRECATED_EXTERNALLY(3.14) 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. */
_Py_DEPRECATED_EXTERNALLY(3.14) 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. */
_Py_DEPRECATED_EXTERNALLY(3.14) 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. */
_Py_DEPRECATED_EXTERNALLY(3.14) 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. */
_Py_DEPRECATED_EXTERNALLY(3.14) 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. */
_Py_DEPRECATED_EXTERNALLY(3.14) PyAPI_FUNC(PyObject *) _PyUnicodeWriter_Finish(
    _PyUnicodeWriter *writer);

/* Deallocate memory of a writer (clear its internal buffer). */
_Py_DEPRECATED_EXTERNALLY(3.14) PyAPI_FUNC(void) _PyUnicodeWriter_Dealloc(
    _PyUnicodeWriter *writer);


/* --- Manage the default encoding ---------------------------------------- */

/* 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.
*/

PyAPI_FUNC(const char *) PyUnicode_AsUTF8(PyObject *unicode);

// Deprecated alias kept for backward compatibility
Py_DEPRECATED(3.14) static inline const char*
_PyUnicode_AsString(PyObject *unicode)
{
    return PyUnicode_AsUTF8(unicode);
}


/* === Characters Type APIs =============================================== */

/* 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_IsWhitespace(
    const Py_UCS4 ch         /* Unicode character */
    );

PyAPI_FUNC(int) _PyUnicode_IsLinebreak(
    const Py_UCS4 ch         /* Unicode character */
    );

PyAPI_FUNC(Py_UCS4) _PyUnicode_ToLowercase(
    Py_UCS4 ch       /* Unicode character */
    );

PyAPI_FUNC(Py_UCS4) _PyUnicode_ToUppercase(
    Py_UCS4 ch       /* Unicode character */
    );

PyAPI_FUNC(Py_UCS4) _PyUnicode_ToTitlecase(
    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 */
    );

// Helper array used by Py_UNICODE_ISSPACE().
PyAPI_DATA(const unsigned char) _Py_ascii_whitespace[];

// 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.
static inline int Py_UNICODE_ISSPACE(Py_UCS4 ch) {
    if (ch < 128) {
        return _Py_ascii_whitespace[ch];
    }
    return _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)

static inline int Py_UNICODE_ISALNUM(Py_UCS4 ch) {
   return (Py_UNICODE_ISALPHA(ch)
           || Py_UNICODE_ISDECIMAL(ch)
           || Py_UNICODE_ISDIGIT(ch)
           || Py_UNICODE_ISNUMERIC(ch));
}


/* === Misc functions ===================================================== */

// Return an interned Unicode object for an Identifier; may fail if there is no
// memory.
Py_DEPRECATED(3.15) PyAPI_FUNC(PyObject*) _PyUnicode_FromId(_Py_Identifier*);