resize_copy() now supports legacy ready strings

diff --git a/Include/unicodeobject.h b/Include/unicodeobject.h
index ecf83866b6a62eeb7fc8c2e0d009e67303eb0ec2..be45b0277c5dc5f02312de0f70bddd81c1d2beeb 100644 (file)
--- a/Include/unicodeobject.h
+++ b/Include/unicodeobject.h
@@ -220,6 +220,7 @@ typedef struct {
        - compact ascii:
 
          * structure = PyASCIIObject
+         * test: PyUnicode_IS_COMPACT_ASCII(op)
          * kind = PyUnicode_1BYTE_KIND
          * compact = 1
          * ascii = 1
@@ -231,6 +232,7 @@ typedef struct {
        - compact:
 
          * structure = PyCompactUnicodeObject
+         * test: PyUnicode_IS_ASCII(op) && !PyUnicode_IS_COMPACT(op)
          * kind = PyUnicode_1BYTE_KIND, PyUnicode_2BYTE_KIND or
            PyUnicode_4BYTE_KIND
          * compact = 1
@@ -247,6 +249,7 @@ typedef struct {
        - legacy string, not ready:
 
          * structure = PyUnicodeObject
+         * test: kind == PyUnicode_WCHAR_KIND
          * length = 0 (use wstr_length)
          * hash = -1
          * kind = PyUnicode_WCHAR_KIND
@@ -262,6 +265,7 @@ typedef struct {
        - legacy string, ready:
 
          * structure = PyUnicodeObject structure
+         * test: !PyUnicode_IS_COMPACT(op) && kind != PyUnicode_WCHAR_KIND
          * kind = PyUnicode_1BYTE_KIND, PyUnicode_2BYTE_KIND or
            PyUnicode_4BYTE_KIND
          * compact = 0

diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c
index 681bfe3b5831f448c8fea606aa73a0af880dbff7..ddb7baa2de3568b9d9edae5de718fbf934125539 100644 (file)
--- a/Objects/unicodeobject.c
+++ b/Objects/unicodeobject.c
@@ -688,26 +688,19 @@ static int
 resize_inplace(PyObject *unicode, Py_ssize_t length)
 {
     wchar_t *wstr;
+    Py_ssize_t new_size;
     assert(!PyUnicode_IS_COMPACT(unicode));
     assert(Py_REFCNT(unicode) == 1);
 
     if (PyUnicode_IS_READY(unicode)) {
         Py_ssize_t char_size;
-        Py_ssize_t new_size;
         int share_wstr, share_utf8;
         void *data;
 
         data = _PyUnicode_DATA_ANY(unicode);
-        assert(data != NULL);
         char_size = PyUnicode_KIND(unicode);
         share_wstr = _PyUnicode_SHARE_WSTR(unicode);
         share_utf8 = _PyUnicode_SHARE_UTF8(unicode);
-        if (!share_utf8 && _PyUnicode_HAS_UTF8_MEMORY(unicode))
-        {
-            PyObject_DEL(_PyUnicode_UTF8(unicode));
-            _PyUnicode_UTF8(unicode) = NULL;
-            _PyUnicode_UTF8_LENGTH(unicode) = 0;
-        }
 
         if (length > (PY_SSIZE_T_MAX / char_size - 1)) {
             PyErr_NoMemory();
@@ -715,6 +708,13 @@ resize_inplace(PyObject *unicode, Py_ssize_t length)
         }
         new_size = (length + 1) * char_size;
 
+        if (!share_utf8 && _PyUnicode_HAS_UTF8_MEMORY(unicode))
+        {
+            PyObject_DEL(_PyUnicode_UTF8(unicode));
+            _PyUnicode_UTF8(unicode) = NULL;
+            _PyUnicode_UTF8_LENGTH(unicode) = 0;
+        }
+
         data = (PyObject *)PyObject_REALLOC(data, new_size);
         if (data == NULL) {
             PyErr_NoMemory();
@@ -743,8 +743,9 @@ resize_inplace(PyObject *unicode, Py_ssize_t length)
         PyErr_NoMemory();
         return -1;
     }
+    new_size = sizeof(wchar_t) * (length + 1);
     wstr =  _PyUnicode_WSTR(unicode);
-    wstr = PyObject_REALLOC(wstr, sizeof(wchar_t) * (length + 1));
+    wstr = PyObject_REALLOC(wstr, new_size);
     if (!wstr) {
         PyErr_NoMemory();
         return -1;
@@ -760,9 +761,11 @@ static PyObject*
 resize_copy(PyObject *unicode, Py_ssize_t length)
 {
     Py_ssize_t copy_length;
-    if (PyUnicode_IS_COMPACT(unicode)) {
+    if (_PyUnicode_KIND(unicode) != PyUnicode_WCHAR_KIND) {
         PyObject *copy;
-        assert(PyUnicode_IS_READY(unicode));
+
+        if (PyUnicode_READY(unicode) < 0)
+            return NULL;
 
         copy = PyUnicode_New(length, PyUnicode_MAX_CHAR_VALUE(unicode));
         if (copy == NULL)
@@ -774,8 +777,7 @@ resize_copy(PyObject *unicode, Py_ssize_t length)
     }
     else {
         PyObject *w;
-        assert(_PyUnicode_WSTR(unicode) != NULL);
-        assert(_PyUnicode_DATA_ANY(unicode) == NULL);
+
         w = (PyObject*)_PyUnicode_New(length);
         if (w == NULL)
             return NULL;