gh-76535: Make PyUnicode_ToLowerFull and friends public

Make `PyUnicode_ToLowerFull`, `PyUnicode_ToUpperFull` and
`PyUnicode_ToTitleFull` public and rename them to `PyUnicode_ToLower`
etc.

Author: lysnikolaou

Doc/c-api/unicode.rst

@@ -307,6 +307,36 @@ These APIs can be used for fast direct character conversions:
    possible.  This function does not raise exceptions.
 
 
+.. c:function:: Py_ssize_t PyUnicode_ToLower(Py_UCS4 ch, Py_UCS4 *buffer)
+
+   Convert *ch* to lower case, store result in *buffer*, which should be
+   able to hold as many characters needed for *ch* to be lower cased
+   (maximum three), and return the number of characters stored.
+   Passing a ``NULL`` buffer returns the buffer size needed.
+
+   .. versionadded:: next
+
+
+.. c:function:: Py_ssize_t PyUnicode_ToUpper(Py_UCS4 ch, Py_UCS4 *buffer)
+
+   Convert *ch* to lower case, store result in *buffer*, which should be
+   able to hold as many characters needed for *ch* to be lower cased
+   (maximum three), and return the number of characters stored.
+   Passing a ``NULL`` buffer returns the buffer size needed.
+
+   .. versionadded:: next
+
+
+.. c:function:: Py_ssize_t PyUnicode_ToTitle(Py_UCS4 ch, Py_UCS4 *buffer)
+
+   Convert *ch* to lower case, store result in *buffer*, which should be
+   able to hold as many characters needed for *ch* to be lower cased
+   (maximum three), and return the number of characters stored.
+   Passing a ``NULL`` buffer returns the buffer size needed.
+
+   .. versionadded:: next
+
+
 These APIs can be used to work with surrogates:
 
 .. c:function:: int Py_UNICODE_IS_SURROGATE(Py_UCS4 ch)

Include/cpython/unicodeobject.h

@@ -733,6 +733,21 @@ PyAPI_FUNC(int) _PyUnicode_IsAlpha(
     Py_UCS4 ch       /* Unicode character */
     );
 
+PyAPI_FUNC(int) PyUnicode_ToLower(
+    Py_UCS4 ch,     /* Unicode character */
+    Py_UCS4 *res    /* Output buffer */
+    );
+
+PyAPI_FUNC(int) PyUnicode_ToUpper(
+    Py_UCS4 ch,     /* Unicode character */
+    Py_UCS4 *res    /* Output buffer */
+    );
+
+PyAPI_FUNC(int) PyUnicode_ToTitle(
+    Py_UCS4 ch,     /* Unicode character */
+    Py_UCS4 *res    /* Output buffer */
+    );
+
 // Helper array used by Py_UNICODE_ISSPACE().
 PyAPI_DATA(const unsigned char) _Py_ascii_whitespace[];
 

Include/internal/pycore_unicodeobject.h

@@ -15,9 +15,6 @@ extern "C" {
 
 extern int _PyUnicode_IsXidStart(Py_UCS4 ch);
 extern int _PyUnicode_IsXidContinue(Py_UCS4 ch);
-extern int _PyUnicode_ToLowerFull(Py_UCS4 ch, Py_UCS4 *res);
-extern int _PyUnicode_ToTitleFull(Py_UCS4 ch, Py_UCS4 *res);
-extern int _PyUnicode_ToUpperFull(Py_UCS4 ch, Py_UCS4 *res);
 extern int _PyUnicode_ToFoldedFull(Py_UCS4 ch, Py_UCS4 *res);
 extern int _PyUnicode_IsCaseIgnorable(Py_UCS4 ch);
 extern int _PyUnicode_IsCased(Py_UCS4 ch);

Objects/unicodectype.c

@@ -198,51 +198,67 @@ Py_UCS4 _PyUnicode_ToLowercase(Py_UCS4 ch)
     return ch + ctype->lower;
 }
 
-int _PyUnicode_ToLowerFull(Py_UCS4 ch, Py_UCS4 *res)
+int PyUnicode_ToLower(Py_UCS4 ch, Py_UCS4 *res)
 {
     const _PyUnicode_TypeRecord *ctype = gettyperecord(ch);
 
     if (ctype->flags & EXTENDED_CASE_MASK) {
         int index = ctype->lower & 0xFFFF;
         int n = ctype->lower >> 24;
         int i;
-        for (i = 0; i < n; i++)
-            res[i] = _PyUnicode_ExtendedCase[index + i];
+        for (i = 0; i < n; i++) {
+            if (res != NULL) {
+                res[i] = _PyUnicode_ExtendedCase[index + i];
+            }
+        }
         return n;
     }
-    res[0] = ch + ctype->lower;
+
+    if (res != NULL) {
+        res[0] = ch + ctype->lower;
+    }
     return 1;
 }
 
-int _PyUnicode_ToTitleFull(Py_UCS4 ch, Py_UCS4 *res)
+int PyUnicode_ToTitle(Py_UCS4 ch, Py_UCS4 *res)
 {
     const _PyUnicode_TypeRecord *ctype = gettyperecord(ch);
 
     if (ctype->flags & EXTENDED_CASE_MASK) {
         int index = ctype->title & 0xFFFF;
         int n = ctype->title >> 24;
         int i;
-        for (i = 0; i < n; i++)
-            res[i] = _PyUnicode_ExtendedCase[index + i];
+        for (i = 0; i < n; i++) {
+            if (res != NULL) {
+                res[i] = _PyUnicode_ExtendedCase[index + i];
+            }
+        }
         return n;
     }
-    res[0] = ch + ctype->title;
+    if (res != NULL) {
+        res[0] = ch + ctype->title;
+    }
     return 1;
 }
 
-int _PyUnicode_ToUpperFull(Py_UCS4 ch, Py_UCS4 *res)
+int PyUnicode_ToUpper(Py_UCS4 ch, Py_UCS4 *res)
 {
     const _PyUnicode_TypeRecord *ctype = gettyperecord(ch);
 
     if (ctype->flags & EXTENDED_CASE_MASK) {
         int index = ctype->upper & 0xFFFF;
         int n = ctype->upper >> 24;
         int i;
-        for (i = 0; i < n; i++)
-            res[i] = _PyUnicode_ExtendedCase[index + i];
+        for (i = 0; i < n; i++) {
+            if (res != NULL) {
+                res[i] = _PyUnicode_ExtendedCase[index + i];
+            }
+        }
         return n;
     }
-    res[0] = ch + ctype->upper;
+    if (res != NULL) {
+        res[0] = ch + ctype->upper;
+    }
     return 1;
 }
 
@@ -258,7 +274,7 @@ int _PyUnicode_ToFoldedFull(Py_UCS4 ch, Py_UCS4 *res)
             res[i] = _PyUnicode_ExtendedCase[index + i];
         return n;
     }
-    return _PyUnicode_ToLowerFull(ch, res);
+    return PyUnicode_ToLowerFull(ch, res);
 }
 
 int _PyUnicode_IsCased(Py_UCS4 ch)

Objects/unicodeobject.c

@@ -10003,7 +10003,7 @@ lower_ucs4(int kind, const void *data, Py_ssize_t length, Py_ssize_t i,
         mapped[0] = handle_capital_sigma(kind, data, length, i);
         return 1;
     }
-    return _PyUnicode_ToLowerFull(c, mapped);
+    return PyUnicode_ToLower(c, mapped);
 }
 
 static Py_ssize_t
@@ -10014,7 +10014,7 @@ do_capitalize(int kind, const void *data, Py_ssize_t length, Py_UCS4 *res, Py_UC
     Py_UCS4 c, mapped[3];
 
     c = PyUnicode_READ(kind, data, 0);
-    n_res = _PyUnicode_ToTitleFull(c, mapped);
+    n_res = PyUnicode_ToTitle(c, mapped);
     for (j = 0; j < n_res; j++) {
         *maxchar = Py_MAX(*maxchar, mapped[j]);
         res[k++] = mapped[j];
@@ -10041,7 +10041,7 @@ do_swapcase(int kind, const void *data, Py_ssize_t length, Py_UCS4 *res, Py_UCS4
             n_res = lower_ucs4(kind, data, length, i, c, mapped);
         }
         else if (Py_UNICODE_ISLOWER(c)) {
-            n_res = _PyUnicode_ToUpperFull(c, mapped);
+            n_res = PyUnicode_ToUpper(c, mapped);
         }
         else {
             n_res = 1;
@@ -10067,7 +10067,7 @@ do_upper_or_lower(int kind, const void *data, Py_ssize_t length, Py_UCS4 *res,
         if (lower)
             n_res = lower_ucs4(kind, data, length, i, c, mapped);
         else
-            n_res = _PyUnicode_ToUpperFull(c, mapped);
+            n_res = PyUnicode_ToUpper(c, mapped);
         for (j = 0; j < n_res; j++) {
             *maxchar = Py_MAX(*maxchar, mapped[j]);
             res[k++] = mapped[j];
@@ -10120,7 +10120,7 @@ do_title(int kind, const void *data, Py_ssize_t length, Py_UCS4 *res, Py_UCS4 *m
         if (previous_is_cased)
             n_res = lower_ucs4(kind, data, length, i, c, mapped);
         else
-            n_res = _PyUnicode_ToTitleFull(c, mapped);
+            n_res = PyUnicode_ToTitle(c, mapped);
 
         for (j = 0; j < n_res; j++) {
             *maxchar = Py_MAX(*maxchar, mapped[j]);