[3.14] pythongh-133968: Add PyUnicodeWriter_WriteASCII() function (python#133973) (python#134974)

pythongh-133968: Add PyUnicodeWriter_WriteASCII() function (python#133973)

Replace most PyUnicodeWriter_WriteUTF8() calls with
PyUnicodeWriter_WriteASCII().

(cherry picked from commit f49a07b)

Co-authored-by: Peter Bierma <[email protected]>
Co-authored-by: Bénédikt Tran <[email protected]>

Author: 3 people

Doc/c-api/unicode.rst

@@ -1798,9 +1798,24 @@ object.
 
    See also :c:func:`PyUnicodeWriter_DecodeUTF8Stateful`.
 
+.. c:function:: int PyUnicodeWriter_WriteASCII(PyUnicodeWriter *writer, const char *str, Py_ssize_t size)
+
+   Write the ASCII string *str* into *writer*.
+
+   *size* is the string length in bytes. If *size* is equal to ``-1``, call
+   ``strlen(str)`` to get the string length.
+
+   *str* must only contain ASCII characters. The behavior is undefined if
+   *str* contains non-ASCII characters.
+
+   On success, return ``0``.
+   On error, set an exception, leave the writer unchanged, and return ``-1``.
+
+   .. versionadded:: next
+
 .. c:function:: int PyUnicodeWriter_WriteWideChar(PyUnicodeWriter *writer, const wchar_t *str, Py_ssize_t size)
 
-   Writer the wide string *str* into *writer*.
+   Write the wide string *str* into *writer*.
 
    *size* is a number of wide characters. If *size* is equal to ``-1``, call
    ``wcslen(str)`` to get the string length.

Doc/whatsnew/3.14.rst

@@ -2584,6 +2584,7 @@ New features
   * :c:func:`PyUnicodeWriter_Discard`
   * :c:func:`PyUnicodeWriter_Finish`
   * :c:func:`PyUnicodeWriter_Format`
+  * :c:func:`PyUnicodeWriter_WriteASCII`
   * :c:func:`PyUnicodeWriter_WriteChar`
   * :c:func:`PyUnicodeWriter_WriteRepr`
   * :c:func:`PyUnicodeWriter_WriteStr`
@@ -2860,7 +2861,7 @@ Deprecated
     :c:func:`PyUnicodeWriter_WriteSubstring(writer, str, start, end) <PyUnicodeWriter_WriteSubstring>`.
   * :c:func:`!_PyUnicodeWriter_WriteASCIIString`:
     replace ``_PyUnicodeWriter_WriteASCIIString(&writer, str)`` with
-    :c:func:`PyUnicodeWriter_WriteUTF8(writer, str) <PyUnicodeWriter_WriteUTF8>`.
+    :c:func:`PyUnicodeWriter_WriteASCII(writer, str) <PyUnicodeWriter_WriteASCII>`.
   * :c:func:`!_PyUnicodeWriter_WriteLatin1String`:
     replace ``_PyUnicodeWriter_WriteLatin1String(&writer, str)`` with
     :c:func:`PyUnicodeWriter_WriteUTF8(writer, str) <PyUnicodeWriter_WriteUTF8>`.

Include/cpython/unicodeobject.h

@@ -478,6 +478,10 @@ PyAPI_FUNC(int) PyUnicodeWriter_WriteUTF8(
     PyUnicodeWriter *writer,
     const char *str,
     Py_ssize_t size);
+PyAPI_FUNC(int) PyUnicodeWriter_WriteASCII(
+    PyUnicodeWriter *writer,
+    const char *str,
+    Py_ssize_t size);
 PyAPI_FUNC(int) PyUnicodeWriter_WriteWideChar(
     PyUnicodeWriter *writer,
     const wchar_t *str,

Lib/test/test_capi/test_unicode.py

@@ -1776,6 +1776,13 @@ def test_utf8(self):
         self.assertEqual(writer.finish(),
                          "ascii-latin1=\xE9-euro=\u20AC.")
 
+    def test_ascii(self):
+        writer = self.create_writer(0)
+        writer.write_ascii(b"Hello ", -1)
+        writer.write_ascii(b"", 0)
+        writer.write_ascii(b"Python! <truncated>", 6)
+        self.assertEqual(writer.finish(), "Hello Python")
+
     def test_invalid_utf8(self):
         writer = self.create_writer(0)
         with self.assertRaises(UnicodeDecodeError):

Misc/NEWS.d/next/C_API/2025-05-13-16-06-46.gh-issue-133968.6alWst.rst

@@ -0,0 +1,4 @@
+Add :c:func:`PyUnicodeWriter_WriteASCII` function to write an ASCII string
+into a :c:type:`PyUnicodeWriter`. The function is faster than
+:c:func:`PyUnicodeWriter_WriteUTF8`, but has an undefined behavior if the
+input string contains non-ASCII characters. Patch by Victor Stinner.

Modules/_json.c

@@ -1476,13 +1476,13 @@ encoder_listencode_obj(PyEncoderObject *s, PyUnicodeWriter *writer,
     int rv;
 
     if (obj == Py_None) {
-      return PyUnicodeWriter_WriteUTF8(writer, "null", 4);
+      return PyUnicodeWriter_WriteASCII(writer, "null", 4);
     }
     else if (obj == Py_True) {
-      return PyUnicodeWriter_WriteUTF8(writer, "true", 4);
+      return PyUnicodeWriter_WriteASCII(writer, "true", 4);
     }
     else if (obj == Py_False) {
-      return PyUnicodeWriter_WriteUTF8(writer, "false", 5);
+      return PyUnicodeWriter_WriteASCII(writer, "false", 5);
     }
     else if (PyUnicode_Check(obj)) {
         PyObject *encoded = encoder_encode_string(s, obj);
@@ -1655,7 +1655,7 @@ encoder_listencode_dict(PyEncoderObject *s, PyUnicodeWriter *writer,
 
     if (PyDict_GET_SIZE(dct) == 0) {
         /* Fast path */
-        return PyUnicodeWriter_WriteUTF8(writer, "{}", 2);
+        return PyUnicodeWriter_WriteASCII(writer, "{}", 2);
     }
 
     if (s->markers != Py_None) {
@@ -1756,7 +1756,7 @@ encoder_listencode_list(PyEncoderObject *s, PyUnicodeWriter *writer,
         return -1;
     if (PySequence_Fast_GET_SIZE(s_fast) == 0) {
         Py_DECREF(s_fast);
-        return PyUnicodeWriter_WriteUTF8(writer, "[]", 2);
+        return PyUnicodeWriter_WriteASCII(writer, "[]", 2);
     }
 
     if (s->markers != Py_None) {

Modules/_ssl.c

@@ -563,7 +563,7 @@ fill_and_set_sslerror(_sslmodulestate *state,
                 goto fail;
             }
         }
-        if (PyUnicodeWriter_WriteUTF8(writer, "] ", 2) < 0) {
+        if (PyUnicodeWriter_WriteASCII(writer, "] ", 2) < 0) {
             goto fail;
         }
     }

Modules/_testcapi/unicode.c

@@ -332,6 +332,27 @@ writer_write_utf8(PyObject *self_raw, PyObject *args)
 }
 
 
+static PyObject*
+writer_write_ascii(PyObject *self_raw, PyObject *args)
+{
+    WriterObject *self = (WriterObject *)self_raw;
+    if (writer_check(self) < 0) {
+        return NULL;
+    }
+
+    char *str;
+    Py_ssize_t size;
+    if (!PyArg_ParseTuple(args, "yn", &str, &size)) {
+        return NULL;
+    }
+
+    if (PyUnicodeWriter_WriteASCII(self->writer, str, size) < 0) {
+        return NULL;
+    }
+    Py_RETURN_NONE;
+}
+
+
 static PyObject*
 writer_write_widechar(PyObject *self_raw, PyObject *args)
 {
@@ -513,6 +534,7 @@ writer_finish(PyObject *self_raw, PyObject *Py_UNUSED(args))
 static PyMethodDef writer_methods[] = {
     {"write_char", _PyCFunction_CAST(writer_write_char), METH_VARARGS},
     {"write_utf8", _PyCFunction_CAST(writer_write_utf8), METH_VARARGS},
+    {"write_ascii", _PyCFunction_CAST(writer_write_ascii), METH_VARARGS},
     {"write_widechar", _PyCFunction_CAST(writer_write_widechar), METH_VARARGS},
     {"write_ucs4", _PyCFunction_CAST(writer_write_ucs4), METH_VARARGS},
     {"write_str", _PyCFunction_CAST(writer_write_str), METH_VARARGS},

Objects/genericaliasobject.c

@@ -65,7 +65,7 @@ ga_repr_items_list(PyUnicodeWriter *writer, PyObject *p)
 
     for (Py_ssize_t i = 0; i < len; i++) {
         if (i > 0) {
-            if (PyUnicodeWriter_WriteUTF8(writer, ", ", 2) < 0) {
+            if (PyUnicodeWriter_WriteASCII(writer, ", ", 2) < 0) {
                 return -1;
             }
         }
@@ -109,7 +109,7 @@ ga_repr(PyObject *self)
     }
     for (Py_ssize_t i = 0; i < len; i++) {
         if (i > 0) {
-            if (PyUnicodeWriter_WriteUTF8(writer, ", ", 2) < 0) {
+            if (PyUnicodeWriter_WriteASCII(writer, ", ", 2) < 0) {
                 goto error;
             }
         }
@@ -126,7 +126,7 @@ ga_repr(PyObject *self)
     }
     if (len == 0) {
         // for something like tuple[()] we should print a "()"
-        if (PyUnicodeWriter_WriteUTF8(writer, "()", 2) < 0) {
+        if (PyUnicodeWriter_WriteASCII(writer, "()", 2) < 0) {
             goto error;
         }
     }

Objects/typevarobject.c

@@ -192,7 +192,7 @@ constevaluator_call(PyObject *self, PyObject *args, PyObject *kwargs)
             for (Py_ssize_t i = 0; i < PyTuple_GET_SIZE(value); i++) {
                 PyObject *item = PyTuple_GET_ITEM(value, i);
                 if (i > 0) {
-                    if (PyUnicodeWriter_WriteUTF8(writer, ", ", 2) < 0) {
+                    if (PyUnicodeWriter_WriteASCII(writer, ", ", 2) < 0) {
                         PyUnicodeWriter_Discard(writer);
                         return NULL;
                     }
@@ -273,7 +273,7 @@ _Py_typing_type_repr(PyUnicodeWriter *writer, PyObject *p)
     }
 
     if (p == (PyObject *)&_PyNone_Type) {
-        return PyUnicodeWriter_WriteUTF8(writer, "None", 4);
+        return PyUnicodeWriter_WriteASCII(writer, "None", 4);
     }
 
     if ((rc = PyObject_HasAttrWithError(p, &_Py_ID(__origin__))) > 0 &&