Issue #28701: Replace PyUnicode_CompareWithASCIIString with _PyUnicode_EqualToASCIIString.

The latter function is more readable, faster and doesn't raise exceptions.

4 files changed, 42 insertions, 7 deletions

diff --git a/Objects/longobject.c b/Objects/longobject.c
index 0cc850e..8510e90 100644
--- a/Objects/longobject.c
+++ b/Objects/longobject.c
@@ -4936,9 +4936,9 @@ long_to_bytes(PyLongObject *v, PyObject *args, PyObject *kwds)
         return NULL;
     }
 
-    if (!PyUnicode_CompareWithASCIIString(byteorder_str, "little"))
+    if (_PyUnicode_EqualToASCIIString(byteorder_str, "little"))
         little_endian = 1;
-    else if (!PyUnicode_CompareWithASCIIString(byteorder_str, "big"))
+    else if (_PyUnicode_EqualToASCIIString(byteorder_str, "big"))
         little_endian = 0;
     else {
         PyErr_SetString(PyExc_ValueError,
@@ -5019,9 +5019,9 @@ long_from_bytes(PyTypeObject *type, PyObject *args, PyObject *kwds)
         return NULL;
     }
 
-    if (!PyUnicode_CompareWithASCIIString(byteorder_str, "little"))
+    if (_PyUnicode_EqualToASCIIString(byteorder_str, "little"))
         little_endian = 1;
-    else if (!PyUnicode_CompareWithASCIIString(byteorder_str, "big"))
+    else if (_PyUnicode_EqualToASCIIString(byteorder_str, "big"))
         little_endian = 0;
     else {
         PyErr_SetString(PyExc_ValueError,
diff --git a/Objects/moduleobject.c b/Objects/moduleobject.c
index ac07642..ae72da6 100644
--- a/Objects/moduleobject.c
+++ b/Objects/moduleobject.c
@@ -587,7 +587,7 @@ _PyModule_ClearDict(PyObject *d)
     while (PyDict_Next(d, &pos, &key, &value)) {
         if (value != Py_None && PyUnicode_Check(key)) {
             if (PyUnicode_READ_CHAR(key, 0) != '_' ||
-                PyUnicode_CompareWithASCIIString(key, "__builtins__") != 0)
+                !_PyUnicode_EqualToASCIIString(key, "__builtins__"))
             {
                 if (Py_VerboseFlag > 1) {
                     const char *s = _PyUnicode_AsString(key);
diff --git a/Objects/typeobject.c b/Objects/typeobject.c
index d65fcde..28a2db1 100644
--- a/Objects/typeobject.c
+++ b/Objects/typeobject.c
@@ -2395,7 +2395,7 @@ type_new(PyTypeObject *metatype, PyObject *args, PyObject *kwds)
                 }
                 add_dict++;
             }
-            if (PyUnicode_CompareWithASCIIString(tmp, "__weakref__") == 0) {
+            if (_PyUnicode_EqualToASCIIString(tmp, "__weakref__")) {
                 if (!may_add_weak || add_weak) {
                     PyErr_SetString(PyExc_TypeError,
                         "__weakref__ slot disallowed: "
@@ -2419,7 +2419,7 @@ type_new(PyTypeObject *metatype, PyObject *args, PyObject *kwds)
             if ((add_dict &&
                  _PyUnicode_CompareWithId(tmp, &PyId___dict__) == 0) ||
                 (add_weak &&
-                 PyUnicode_CompareWithASCIIString(tmp, "__weakref__") == 0))
+                 _PyUnicode_EqualToASCIIString(tmp, "__weakref__")))
                 continue;
             tmp =_Py_Mangle(name, tmp);
             if (!tmp) {
diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c
index b7a3fa5..86485bd 100644
--- a/Objects/unicodeobject.c
+++ b/Objects/unicodeobject.c
@@ -10834,6 +10834,41 @@ PyUnicode_CompareWithASCIIString(PyObject* uni, const char* str)
     }
 }
 
+static int
+non_ready_unicode_equal_to_ascii_string(PyObject *unicode, const char *str)
+{
+    size_t i, len;
+    const wchar_t *p;
+    len = (size_t)_PyUnicode_WSTR_LENGTH(unicode);
+    if (strlen(str) != len)
+        return 0;
+    p = _PyUnicode_WSTR(unicode);
+    assert(p);
+    for (i = 0; i < len; i++) {
+        unsigned char c = (unsigned char)str[i];
+        if (c > 128 || p[i] != (wchar_t)c)
+            return 0;
+    }
+    return 1;
+}
+
+int
+_PyUnicode_EqualToASCIIString(PyObject *unicode, const char *str)
+{
+    size_t len;
+    assert(_PyUnicode_CHECK(unicode));
+    if (PyUnicode_READY(unicode) == -1) {
+        /* Memory error or bad data */
+        PyErr_Clear();
+        return non_ready_unicode_equal_to_ascii_string(unicode, str);
+    }
+    if (!PyUnicode_IS_ASCII(unicode))
+        return 0;
+    len = (size_t)PyUnicode_GET_LENGTH(unicode);
+    return strlen(str) == len &&
+           memcmp(PyUnicode_1BYTE_DATA(unicode), str, len) == 0;
+}
+
 
 #define TEST_COND(cond)                         \
     ((cond) ? Py_True : Py_False)