pythongh-119182: Add PyUnicodeWriter C API (python#119184)

Doc/c-api/unicode.rst

@@ -1502,3 +1502,87 @@ They all return ``NULL`` or ``-1`` if an exception occurs.
    :c:func:`PyUnicode_InternInPlace`, returning either a new Unicode string
    object that has been interned, or a new ("owned") reference to an earlier
    interned string object with the same value.
+
+PyUnicodeWriter
+^^^^^^^^^^^^^^^
+
+The :c:type:`PyUnicodeWriter` API can be used to create a Python :class:`str`
+object.
+
+.. versionadded:: 3.14
+
+.. c:type:: PyUnicodeWriter
+
+   A Unicode writer instance.
+
+   The instance must be destroyed by :c:func:`PyUnicodeWriter_Finish` on
+   success, or :c:func:`PyUnicodeWriter_Discard` on error.
+
+.. c:function:: PyUnicodeWriter* PyUnicodeWriter_Create(Py_ssize_t length)
+
+   Create a Unicode writer instance.
+
+   Set an exception and return ``NULL`` on error.
+
+.. c:function:: PyObject* PyUnicodeWriter_Finish(PyUnicodeWriter *writer)
+
+   Return the final Python :class:`str` object and destroy the writer instance.
+
+   Set an exception and return ``NULL`` on error.
+
+.. c:function:: void PyUnicodeWriter_Discard(PyUnicodeWriter *writer)
+
+   Discard the internal Unicode buffer and destroy the writer instance.
+
+.. c:function:: int PyUnicodeWriter_WriteChar(PyUnicodeWriter *writer, Py_UCS4 ch)
+
+   Write the single Unicode character *ch* into *writer*.
+
+   On success, return ``0``.
+   On error, set an exception, leave the writer unchanged, and return ``-1``.
+
+.. c:function:: int PyUnicodeWriter_WriteUTF8(PyUnicodeWriter *writer, const char *str, Py_ssize_t size)
+
+   Decode the string *str* from UTF-8 in strict mode and write the output into *writer*.
+
+   *size* is the string length in bytes. If *size* is equal to ``-1``, call
+   ``strlen(str)`` to get the string length.
+
+   On success, return ``0``.
+   On error, set an exception, leave the writer unchanged, and return ``-1``.
+
+   To use a different error handler than ``strict``,
+   :c:func:`PyUnicode_DecodeUTF8` can be used with
+   :c:func:`PyUnicodeWriter_WriteStr`.
+
+.. c:function:: int PyUnicodeWriter_WriteStr(PyUnicodeWriter *writer, PyObject *obj)
+
+   Call :c:func:`PyObject_Str` on *obj* and write the output into *writer*.
+
+   On success, return ``0``.
+   On error, set an exception, leave the writer unchanged, and return ``-1``.
+
+.. c:function:: int PyUnicodeWriter_WriteRepr(PyUnicodeWriter *writer, PyObject *obj)
+
+   Call :c:func:`PyObject_Repr` on *obj* and write the output into *writer*.
+
+   On success, return ``0``.
+   On error, set an exception, leave the writer unchanged, and return ``-1``.
+
+.. c:function:: int PyUnicodeWriter_WriteSubstring(PyUnicodeWriter *writer, PyObject *str, Py_ssize_t start, Py_ssize_t end)
+
+   Write the substring ``str[start:end]`` into *writer*.
+
+   *str* must be Python :class:`str` object. *start* must be greater than or
+   equal to 0, and less than or equal to *end*. *end* must be less than or
+   equal to *str* length.
+
+   On success, return ``0``.
+   On error, set an exception, leave the writer unchanged, and return ``-1``.
+
+.. c:function:: int PyUnicodeWriter_Format(PyUnicodeWriter *writer, const char *format, ...)
+
+   Similar to :c:func:`PyUnicode_FromFormat`, but write the output directly into *writer*.
+
+   On success, return ``0``.
+   On error, set an exception, leave the writer unchanged, and return ``-1``.

Doc/whatsnew/3.14.rst

@@ -283,6 +283,21 @@ New Features
 * Add :c:func:`PyLong_GetSign` function to get the sign of :class:`int` objects.
   (Contributed by Sergey B Kirpichev in :gh:`116560`.)
 
+* Add a new :c:type:`PyUnicodeWriter` API to create a Python :class:`str`
+  object:
+
+  * :c:func:`PyUnicodeWriter_Create`.
+  * :c:func:`PyUnicodeWriter_Discard`.
+  * :c:func:`PyUnicodeWriter_Finish`.
+  * :c:func:`PyUnicodeWriter_WriteChar`.
+  * :c:func:`PyUnicodeWriter_WriteUTF8`.
+  * :c:func:`PyUnicodeWriter_WriteStr`.
+  * :c:func:`PyUnicodeWriter_WriteRepr`.
+  * :c:func:`PyUnicodeWriter_WriteSubstring`.
+  * :c:func:`PyUnicodeWriter_Format`.
+
+  (Contributed by Victor Stinner in :gh:`119182`.)
+
 Porting to Python 3.14
 ----------------------
 

Include/cpython/unicodeobject.h

@@ -444,7 +444,40 @@ PyAPI_FUNC(PyObject*) PyUnicode_FromKindAndData(
     Py_ssize_t size);
 
 
-/* --- _PyUnicodeWriter API ----------------------------------------------- */
+/* --- Public PyUnicodeWriter API ----------------------------------------- */
+
+typedef struct PyUnicodeWriter PyUnicodeWriter;
+
+PyAPI_FUNC(PyUnicodeWriter*) PyUnicodeWriter_Create(Py_ssize_t length);
+PyAPI_FUNC(void) PyUnicodeWriter_Discard(PyUnicodeWriter *writer);
+PyAPI_FUNC(PyObject*) PyUnicodeWriter_Finish(PyUnicodeWriter *writer);
+
+PyAPI_FUNC(int) PyUnicodeWriter_WriteChar(
+    PyUnicodeWriter *writer,
+    Py_UCS4 ch);
+PyAPI_FUNC(int) PyUnicodeWriter_WriteUTF8(
+    PyUnicodeWriter *writer,
+    const char *str,
+    Py_ssize_t size);
+
+PyAPI_FUNC(int) PyUnicodeWriter_WriteStr(
+    PyUnicodeWriter *writer,
+    PyObject *obj);
+PyAPI_FUNC(int) PyUnicodeWriter_WriteRepr(
+    PyUnicodeWriter *writer,
+    PyObject *obj);
+PyAPI_FUNC(int) PyUnicodeWriter_WriteSubstring(
+    PyUnicodeWriter *writer,
+    PyObject *str,
+    Py_ssize_t start,
+    Py_ssize_t end);
+PyAPI_FUNC(int) PyUnicodeWriter_Format(
+    PyUnicodeWriter *writer,
+    const char *format,
+    ...);
+
+
+/* --- Private _PyUnicodeWriter API --------------------------------------- */
 
 typedef struct {
     PyObject *buffer;
@@ -466,7 +499,7 @@ typedef struct {
     /* If readonly is 1, buffer is a shared string (cannot be modified)
        and size is set to 0. */
     unsigned char readonly;
-} _PyUnicodeWriter ;
+} _PyUnicodeWriter;
 
 // Initialize a Unicode writer.
 //

Misc/NEWS.d/next/C API/2024-06-07-22-12-30.gh-issue-119182.yt8Ar7.rst

@@ -0,0 +1,13 @@
+Add a new :c:type:`PyUnicodeWriter` API to create a Python :class:`str` object:
+
+* :c:func:`PyUnicodeWriter_Create`.
+* :c:func:`PyUnicodeWriter_Discard`.
+* :c:func:`PyUnicodeWriter_Finish`.
+* :c:func:`PyUnicodeWriter_WriteChar`.
+* :c:func:`PyUnicodeWriter_WriteUTF8`.
+* :c:func:`PyUnicodeWriter_WriteStr`.
+* :c:func:`PyUnicodeWriter_WriteRepr`.
+* :c:func:`PyUnicodeWriter_WriteSubstring`.
+* :c:func:`PyUnicodeWriter_Format`.
+
+Patch by Victor Stinner.