Serhiy Storchaka added the comment:
Here are patches for all four Python versions. They fixes possible usage of the
followed non-initialized global variables: free_list, numfree, interned,
unicode_empty, static_strings, unicode_latin1, bloom_linebreak,
unicode_default_encoding.
----------
Added file: http://bugs.python.org/file28607/unicode_globals-2.7.patch
Added file: http://bugs.python.org/file28608/unicode_globals-3.2.patch
Added file: http://bugs.python.org/file28609/unicode_globals-3.3.patch
Added file: http://bugs.python.org/file28610/unicode_globals-3.4.patch
_______________________________________
Python tracker <rep...@bugs.python.org>
<http://bugs.python.org/issue10156>
_______________________________________
diff -r 0f24c65fb7e5 Objects/unicodeobject.c
--- a/Objects/unicodeobject.c Sat Jan 05 07:37:47 2013 +0200
+++ b/Objects/unicodeobject.c Mon Jan 07 13:26:16 2013 +0200
@@ -93,15 +93,26 @@
#endif
/* Free list for Unicode objects */
-static PyUnicodeObject *free_list;
-static int numfree;
+static PyUnicodeObject *free_list = NULL;
+static int numfree = 0;
/* The empty Unicode object is shared to improve performance. */
-static PyUnicodeObject *unicode_empty;
+static PyUnicodeObject *unicode_empty = NULL;
+
+#define _Py_RETURN_UNICODE_EMPTY() do { \
+ if (unicode_empty != NULL) \
+ Py_INCREF(unicode_empty); \
+ else { \
+ unicode_empty = _PyUnicode_New(0); \
+ if (unicode_empty != NULL) \
+ Py_INCREF(unicode_empty); \
+ } \
+ return (PyObject *)unicode_empty; \
+ } while (0)
/* Single character Unicode strings in the Latin-1 range are being
shared as well. */
-static PyUnicodeObject *unicode_latin1[256];
+static PyUnicodeObject *unicode_latin1[256] = {NULL};
/* Default encoding to use and assume when NULL is passed as encoding
parameter; it is initialized by _PyUnicode_Init().
@@ -110,7 +121,7 @@
PyUnicode_GetDefaultEncoding() APIs to access this global.
*/
-static char unicode_default_encoding[100];
+static char unicode_default_encoding[100 + 1] = "ascii";
/* Fast detection of the most frequent whitespace characters */
const unsigned char _Py_ascii_whitespace[] = {
@@ -204,7 +215,7 @@
#define BLOOM_MASK unsigned long
-static BLOOM_MASK bloom_linebreak;
+static BLOOM_MASK bloom_linebreak = ~(BLOOM_MASK)0;
#define BLOOM_ADD(mask, ch) ((mask |= (1UL << ((ch) & (BLOOM_WIDTH - 1)))))
#define BLOOM(mask, ch) ((mask & (1UL << ((ch) & (BLOOM_WIDTH - 1)))))
@@ -448,10 +459,8 @@
if (u != NULL) {
/* Optimization for empty strings */
- if (size == 0 && unicode_empty != NULL) {
- Py_INCREF(unicode_empty);
- return (PyObject *)unicode_empty;
- }
+ if (size == 0)
+ _Py_RETURN_UNICODE_EMPTY();
/* Single character Unicode objects in the Latin-1 range are
shared when using this constructor */
@@ -497,10 +506,8 @@
if (u != NULL) {
/* Optimization for empty strings */
- if (size == 0 && unicode_empty != NULL) {
- Py_INCREF(unicode_empty);
- return (PyObject *)unicode_empty;
- }
+ if (size == 0)
+ _Py_RETURN_UNICODE_EMPTY();
/* Single characters are shared when using this constructor.
Restrict to ASCII, since the input must be UTF-8. */
@@ -1162,13 +1169,10 @@
}
/* Convert to Unicode */
- if (len == 0) {
- Py_INCREF(unicode_empty);
- v = (PyObject *)unicode_empty;
- }
- else
- v = PyUnicode_Decode(s, len, encoding, errors);
-
+ if (len == 0)
+ _Py_RETURN_UNICODE_EMPTY();
+
+ v = PyUnicode_Decode(s, len, encoding, errors);
return v;
onError:
@@ -1381,7 +1385,7 @@
Py_DECREF(v);
strncpy(unicode_default_encoding,
encoding,
- sizeof(unicode_default_encoding));
+ sizeof(unicode_default_encoding) - 1);
return 0;
onError:
@@ -8838,8 +8842,6 @@
void _PyUnicode_Init(void)
{
- int i;
-
/* XXX - move this array to unicodectype.c ? */
Py_UNICODE linebreak[] = {
0x000A, /* LINE FEED */
@@ -8853,15 +8855,10 @@
};
/* Init the implementation */
- free_list = NULL;
- numfree = 0;
unicode_empty = _PyUnicode_New(0);
if (!unicode_empty)
return;
- strcpy(unicode_default_encoding, "ascii");
- for (i = 0; i < 256; i++)
- unicode_latin1[i] = NULL;
if (PyType_Ready(&PyUnicode_Type) < 0)
Py_FatalError("Can't initialize 'unicode'");
@@ -8906,15 +8903,11 @@
{
int i;
- Py_XDECREF(unicode_empty);
- unicode_empty = NULL;
-
- for (i = 0; i < 256; i++) {
- if (unicode_latin1[i]) {
- Py_DECREF(unicode_latin1[i]);
- unicode_latin1[i] = NULL;
- }
- }
+ Py_CLEAR(unicode_empty);
+
+ for (i = 0; i < 256; i++)
+ Py_CLEAR(unicode_latin1[i]);
+
(void)PyUnicode_ClearFreeList();
}
diff -r d2867c430333 Objects/unicodeobject.c
--- a/Objects/unicodeobject.c Sat Jan 05 07:37:47 2013 +0200
+++ b/Objects/unicodeobject.c Mon Jan 07 12:57:32 2013 +0200
@@ -98,18 +98,29 @@
Another way to look at this is that to say that the actual reference
count of a string is: s->ob_refcnt + (s->state ? 2 : 0)
*/
-static PyObject *interned;
+static PyObject *interned = NULL;
/* Free list for Unicode objects */
-static PyUnicodeObject *free_list;
-static int numfree;
+static PyUnicodeObject *free_list = NULL;
+static int numfree = 0;
/* The empty Unicode object is shared to improve performance. */
-static PyUnicodeObject *unicode_empty;
+static PyUnicodeObject *unicode_empty = NULL;
+
+#define _Py_RETURN_UNICODE_EMPTY() do { \
+ if (unicode_empty != NULL) \
+ Py_INCREF(unicode_empty); \
+ else { \
+ unicode_empty = _PyUnicode_New(0); \
+ if (unicode_empty != NULL) \
+ Py_INCREF(unicode_empty); \
+ } \
+ return (PyObject *)unicode_empty; \
+ } while (0)
/* Single character Unicode strings in the Latin-1 range are being
shared as well. */
-static PyUnicodeObject *unicode_latin1[256];
+static PyUnicodeObject *unicode_latin1[256] = {NULL};
/* Fast detection of the most frequent whitespace characters */
const unsigned char _Py_ascii_whitespace[] = {
@@ -214,7 +225,7 @@
#define BLOOM_MASK unsigned long
-static BLOOM_MASK bloom_linebreak;
+static BLOOM_MASK bloom_linebreak = ~(BLOOM_MASK)0;
#define BLOOM_ADD(mask, ch) ((mask |= (1UL << ((ch) & (BLOOM_WIDTH - 1)))))
#define BLOOM(mask, ch) ((mask & (1UL << ((ch) & (BLOOM_WIDTH - 1)))))
@@ -479,10 +490,8 @@
if (u != NULL) {
/* Optimization for empty strings */
- if (size == 0 && unicode_empty != NULL) {
- Py_INCREF(unicode_empty);
- return (PyObject *)unicode_empty;
- }
+ if (size == 0)
+ _Py_RETURN_UNICODE_EMPTY();
/* Single character Unicode objects in the Latin-1 range are
shared when using this constructor */
@@ -528,10 +537,8 @@
if (u != NULL) {
/* Optimization for empty strings */
- if (size == 0 && unicode_empty != NULL) {
- Py_INCREF(unicode_empty);
- return (PyObject *)unicode_empty;
- }
+ if (size == 0)
+ _Py_RETURN_UNICODE_EMPTY();
/* Single characters are shared when using this constructor.
Restrict to ASCII, since the input must be UTF-8. */
@@ -1393,15 +1400,11 @@
/* Decoding bytes objects is the most common case and should be fast */
if (PyBytes_Check(obj)) {
- if (PyBytes_GET_SIZE(obj) == 0) {
- Py_INCREF(unicode_empty);
- v = (PyObject *) unicode_empty;
- }
- else {
- v = PyUnicode_Decode(
- PyBytes_AS_STRING(obj), PyBytes_GET_SIZE(obj),
- encoding, errors);
- }
+ if (PyBytes_GET_SIZE(obj) == 0)
+ _Py_RETURN_UNICODE_EMPTY();
+ v = PyUnicode_Decode(
+ PyBytes_AS_STRING(obj), PyBytes_GET_SIZE(obj),
+ encoding, errors);
return v;
}
@@ -1421,12 +1424,11 @@
}
if (buffer.len == 0) {
- Py_INCREF(unicode_empty);
- v = (PyObject *) unicode_empty;
- }
- else
- v = PyUnicode_Decode((char*) buffer.buf, buffer.len, encoding, errors);
-
+ PyBuffer_Release(&buffer);
+ _Py_RETURN_UNICODE_EMPTY();
+ }
+
+ v = PyUnicode_Decode((char*) buffer.buf, buffer.len, encoding, errors);
PyBuffer_Release(&buffer);
return v;
}
@@ -8315,10 +8317,8 @@
Py_ssize_t nchars;
size_t nbytes;
- if (len < 1) {
- Py_INCREF(unicode_empty);
- return (PyObject *)unicode_empty;
- }
+ if (len < 1)
+ _Py_RETURN_UNICODE_EMPTY();
if (len == 1 && PyUnicode_CheckExact(str)) {
/* no repeat, return original string */
@@ -10048,8 +10048,6 @@
void _PyUnicode_Init(void)
{
- int i;
-
/* XXX - move this array to unicodectype.c ? */
Py_UNICODE linebreak[] = {
0x000A, /* LINE FEED */
@@ -10063,14 +10061,10 @@
};
/* Init the implementation */
- free_list = NULL;
- numfree = 0;
unicode_empty = _PyUnicode_New(0);
if (!unicode_empty)
return;
- for (i = 0; i < 256; i++)
- unicode_latin1[i] = NULL;
if (PyType_Ready(&PyUnicode_Type) < 0)
Py_FatalError("Can't initialize 'unicode'");
@@ -10115,15 +10109,11 @@
{
int i;
- Py_XDECREF(unicode_empty);
- unicode_empty = NULL;
-
- for (i = 0; i < 256; i++) {
- if (unicode_latin1[i]) {
- Py_DECREF(unicode_latin1[i]);
- unicode_latin1[i] = NULL;
- }
- }
+ Py_CLEAR(unicode_empty);
+
+ for (i = 0; i < 256; i++)
+ Py_CLEAR(unicode_latin1[i]);
+
(void)PyUnicode_ClearFreeList();
}
@@ -10242,8 +10232,7 @@
"mortal/immortal\n", mortal_size, immortal_size);
Py_DECREF(keys);
PyDict_Clear(interned);
- Py_DECREF(interned);
- interned = NULL;
+ Py_CLEAR(interned);
}
diff -r 13c83199c211 Objects/unicodeobject.c
--- a/Objects/unicodeobject.c Sun Jan 06 16:41:56 2013 +0100
+++ b/Objects/unicodeobject.c Mon Jan 07 12:57:36 2013 +0200
@@ -179,17 +179,32 @@
Another way to look at this is that to say that the actual reference
count of a string is: s->ob_refcnt + (s->state ? 2 : 0)
*/
-static PyObject *interned;
+static PyObject *interned = NULL;
/* The empty Unicode object is shared to improve performance. */
-static PyObject *unicode_empty;
+static PyObject *unicode_empty = NULL;
+
+#define _Py_INCREF_UNICODE_EMPTY() do { \
+ if (unicode_empty != NULL) \
+ Py_INCREF(unicode_empty); \
+ else { \
+ unicode_empty = PyUnicode_New(0, 0); \
+ if (unicode_empty != NULL) \
+ Py_INCREF(unicode_empty); \
+ } \
+ } while (0)
+
+#define _Py_RETURN_UNICODE_EMPTY() do { \
+ _Py_INCREF_UNICODE_EMPTY(); \
+ return unicode_empty; \
+ } while (0)
/* List of static strings. */
-static _Py_Identifier *static_strings;
+static _Py_Identifier *static_strings = NULL;
/* Single character Unicode strings in the Latin-1 range are being
shared as well. */
-static PyObject *unicode_latin1[256];
+static PyObject *unicode_latin1[256] = {NULL};
/* Fast detection of the most frequent whitespace characters */
const unsigned char _Py_ascii_whitespace[] = {
@@ -416,9 +431,8 @@
len = _PyUnicode_WSTR_LENGTH(unicode);
if (len == 0) {
- Py_INCREF(unicode_empty);
Py_DECREF(unicode);
- return unicode_empty;
+ _Py_RETURN_UNICODE_EMPTY();
}
if (len == 1) {
@@ -450,8 +464,8 @@
length = PyUnicode_GET_LENGTH(unicode);
if (length == 0) {
if (unicode != unicode_empty) {
- Py_INCREF(unicode_empty);
Py_DECREF(unicode);
+ _Py_RETURN_UNICODE_EMPTY();
}
return unicode_empty;
}
@@ -528,7 +542,7 @@
#define BLOOM_MASK unsigned long
-static BLOOM_MASK bloom_linebreak;
+static BLOOM_MASK bloom_linebreak = ~(BLOOM_MASK)0;
#define BLOOM_ADD(mask, ch) ((mask |= (1UL << ((ch) & (BLOOM_WIDTH - 1)))))
#define BLOOM(mask, ch) ((mask & (1UL << ((ch) & (BLOOM_WIDTH - 1)))))
@@ -1582,9 +1596,9 @@
return 0;
if (length == 0) {
+ _Py_INCREF_UNICODE_EMPTY();
Py_DECREF(*p_unicode);
*p_unicode = unicode_empty;
- Py_INCREF(*p_unicode);
return 0;
}
@@ -1731,10 +1745,8 @@
some optimizations which share commonly used objects. */
/* Optimization for empty strings */
- if (size == 0 && unicode_empty != NULL) {
- Py_INCREF(unicode_empty);
- return unicode_empty;
- }
+ if (size == 0)
+ _Py_RETURN_UNICODE_EMPTY();
/* Single character Unicode objects in the Latin-1 range are
shared when using this constructor */
@@ -1890,10 +1902,8 @@
PyObject *res;
unsigned char max_char;
- if (size == 0) {
- Py_INCREF(unicode_empty);
- return unicode_empty;
- }
+ if (size == 0)
+ _Py_RETURN_UNICODE_EMPTY();
assert(size > 0);
if (size == 1)
return get_latin1_char(u[0]);
@@ -1913,10 +1923,8 @@
PyObject *res;
Py_UCS2 max_char;
- if (size == 0) {
- Py_INCREF(unicode_empty);
- return unicode_empty;
- }
+ if (size == 0)
+ _Py_RETURN_UNICODE_EMPTY();
assert(size > 0);
if (size == 1) {
Py_UCS4 ch = u[0];
@@ -1951,10 +1959,8 @@
PyObject *res;
Py_UCS4 max_char;
- if (size == 0) {
- Py_INCREF(unicode_empty);
- return unicode_empty;
- }
+ if (size == 0)
+ _Py_RETURN_UNICODE_EMPTY();
assert(size > 0);
if (size == 1) {
Py_UCS4 ch = u[0];
@@ -2246,10 +2252,8 @@
PyUnicode_FromWideChar(register const wchar_t *w, Py_ssize_t size)
{
if (w == NULL) {
- if (size == 0) {
- Py_INCREF(unicode_empty);
- return unicode_empty;
- }
+ if (size == 0)
+ _Py_RETURN_UNICODE_EMPTY();
PyErr_BadInternalCall();
return NULL;
}
@@ -3004,15 +3008,11 @@
/* Decoding bytes objects is the most common case and should be fast */
if (PyBytes_Check(obj)) {
- if (PyBytes_GET_SIZE(obj) == 0) {
- Py_INCREF(unicode_empty);
- v = unicode_empty;
- }
- else {
- v = PyUnicode_Decode(
- PyBytes_AS_STRING(obj), PyBytes_GET_SIZE(obj),
- encoding, errors);
- }
+ if (PyBytes_GET_SIZE(obj) == 0)
+ _Py_RETURN_UNICODE_EMPTY();
+ v = PyUnicode_Decode(
+ PyBytes_AS_STRING(obj), PyBytes_GET_SIZE(obj),
+ encoding, errors);
return v;
}
@@ -3032,12 +3032,11 @@
}
if (buffer.len == 0) {
- Py_INCREF(unicode_empty);
- v = unicode_empty;
- }
- else
- v = PyUnicode_Decode((char*) buffer.buf, buffer.len, encoding, errors);
-
+ PyBuffer_Release(&buffer);
+ _Py_RETURN_UNICODE_EMPTY();
+ }
+
+ v = PyUnicode_Decode((char*) buffer.buf, buffer.len, encoding, errors);
PyBuffer_Release(&buffer);
return v;
}
@@ -4717,8 +4716,7 @@
if (size == 0) {
if (consumed)
*consumed = 0;
- Py_INCREF(unicode_empty);
- return unicode_empty;
+ _Py_RETURN_UNICODE_EMPTY();
}
/* ASCII is equivalent to the first 128 ordinals in Unicode. */
@@ -5229,8 +5227,7 @@
if (q == e) {
if (consumed)
*consumed = size;
- Py_INCREF(unicode_empty);
- return unicode_empty;
+ _Py_RETURN_UNICODE_EMPTY();
}
#ifdef BYTEORDER_IS_LITTLE_ENDIAN
@@ -6551,10 +6548,8 @@
PyObject *errorHandler = NULL;
PyObject *exc = NULL;
- if (size == 0) {
- Py_INCREF(unicode_empty);
- return unicode_empty;
- }
+ if (size == 0)
+ _Py_RETURN_UNICODE_EMPTY();
/* ASCII is equivalent to the first 128 ordinals in Unicode. */
if (size == 1 && (unsigned char)s[0] < 128)
@@ -6933,8 +6928,7 @@
if (chunk_size == 0 && done) {
if (v != NULL)
break;
- Py_INCREF(unicode_empty);
- return unicode_empty;
+ _Py_RETURN_UNICODE_EMPTY();
}
@@ -9493,9 +9487,7 @@
/* If empty sequence, return u"". */
if (seqlen == 0) {
Py_DECREF(fseq);
- Py_INCREF(unicode_empty);
- res = unicode_empty;
- return res;
+ _Py_RETURN_UNICODE_EMPTY();
}
/* If singleton sequence with an exact Unicode, return that. */
@@ -10195,7 +10187,7 @@
}
new_size = slen + n * (len2 - len1);
if (new_size == 0) {
- Py_INCREF(unicode_empty);
+ _Py_INCREF_UNICODE_EMPTY();
u = unicode_empty;
goto done;
}
@@ -11662,10 +11654,8 @@
PyErr_SetString(PyExc_IndexError, "string index out of range");
return NULL;
}
- if (start >= length || end < start) {
- Py_INCREF(unicode_empty);
- return unicode_empty;
- }
+ if (start >= length || end < start)
+ _Py_RETURN_UNICODE_EMPTY();
length = end - start;
if (PyUnicode_IS_ASCII(self)) {
@@ -11792,10 +11782,8 @@
PyObject *u;
Py_ssize_t nchars, n;
- if (len < 1) {
- Py_INCREF(unicode_empty);
- return unicode_empty;
- }
+ if (len < 1)
+ _Py_RETURN_UNICODE_EMPTY();
/* no repeat, return original string */
if (len == 1)
@@ -12914,8 +12902,7 @@
{
if (writer->pos == 0) {
Py_XDECREF(writer->buffer);
- Py_INCREF(unicode_empty);
- return unicode_empty;
+ _Py_RETURN_UNICODE_EMPTY();
}
if (writer->readonly) {
assert(PyUnicode_GET_LENGTH(writer->buffer) == writer->pos);
@@ -13133,8 +13120,7 @@
}
if (slicelength <= 0) {
- Py_INCREF(unicode_empty);
- return unicode_empty;
+ _Py_RETURN_UNICODE_EMPTY();
} else if (start == 0 && step == 1 &&
slicelength == PyUnicode_GET_LENGTH(self)) {
return unicode_result_unchanged(self);
@@ -13964,10 +13950,8 @@
if (!PyArg_ParseTupleAndKeywords(args, kwds, "|Oss:str",
kwlist, &x, &encoding, &errors))
return NULL;
- if (x == NULL) {
- Py_INCREF(unicode_empty);
- return unicode_empty;
- }
+ if (x == NULL)
+ _Py_RETURN_UNICODE_EMPTY();
if (encoding == NULL && errors == NULL)
return PyObject_Str(x);
else
@@ -14151,9 +14135,11 @@
};
/* Init the implementation */
- unicode_empty = PyUnicode_New(0, 0);
- if (!unicode_empty)
- Py_FatalError("Can't create empty string");
+ if (unicode_empty == NULL) {
+ unicode_empty = PyUnicode_New(0, 0);
+ if (!unicode_empty)
+ Py_FatalError("Can't create empty string");
+ }
assert(_PyUnicode_CheckConsistency(unicode_empty, 1));
for (i = 0; i < 256; i++)
@@ -14197,15 +14183,10 @@
{
int i;
- Py_XDECREF(unicode_empty);
- unicode_empty = NULL;
-
- for (i = 0; i < 256; i++) {
- if (unicode_latin1[i]) {
- Py_DECREF(unicode_latin1[i]);
- unicode_latin1[i] = NULL;
- }
- }
+ Py_CLEAR(unicode_empty);
+
+ for (i = 0; i < 256; i++)
+ Py_CLEAR(unicode_latin1[i]);
_PyUnicode_ClearStaticStrings();
(void)PyUnicode_ClearFreeList();
}
@@ -14334,8 +14315,7 @@
"mortal/immortal\n", mortal_size, immortal_size);
Py_DECREF(keys);
PyDict_Clear(interned);
- Py_DECREF(interned);
- interned = NULL;
+ Py_CLEAR(interned);
}
diff -r b6284d2aaada Objects/unicodeobject.c
--- a/Objects/unicodeobject.c Sun Jan 06 16:14:22 2013 -0500
+++ b/Objects/unicodeobject.c Mon Jan 07 13:06:23 2013 +0200
@@ -171,17 +171,32 @@
Another way to look at this is that to say that the actual reference
count of a string is: s->ob_refcnt + (s->state ? 2 : 0)
*/
-static PyObject *interned;
+static PyObject *interned = NULL;
/* The empty Unicode object is shared to improve performance. */
-static PyObject *unicode_empty;
+static PyObject *unicode_empty = NULL;
+
+#define _Py_INCREF_UNICODE_EMPTY() do { \
+ if (unicode_empty != NULL) \
+ Py_INCREF(unicode_empty); \
+ else { \
+ unicode_empty = PyUnicode_New(0, 0); \
+ if (unicode_empty != NULL) \
+ Py_INCREF(unicode_empty); \
+ } \
+ } while (0)
+
+#define _Py_RETURN_UNICODE_EMPTY() do { \
+ _Py_INCREF_UNICODE_EMPTY(); \
+ return unicode_empty; \
+ } while (0)
/* List of static strings. */
-static _Py_Identifier *static_strings;
+static _Py_Identifier *static_strings = NULL;
/* Single character Unicode strings in the Latin-1 range are being
shared as well. */
-static PyObject *unicode_latin1[256];
+static PyObject *unicode_latin1[256] = {NULL};
/* Fast detection of the most frequent whitespace characters */
const unsigned char _Py_ascii_whitespace[] = {
@@ -406,9 +421,8 @@
len = _PyUnicode_WSTR_LENGTH(unicode);
if (len == 0) {
- Py_INCREF(unicode_empty);
Py_DECREF(unicode);
- return unicode_empty;
+ _Py_RETURN_UNICODE_EMPTY();
}
if (len == 1) {
@@ -442,8 +456,8 @@
length = PyUnicode_GET_LENGTH(unicode);
if (length == 0) {
if (unicode != unicode_empty) {
- Py_INCREF(unicode_empty);
Py_DECREF(unicode);
+ _Py_RETURN_UNICODE_EMPTY();
}
return unicode_empty;
}
@@ -520,7 +534,7 @@
#define BLOOM_MASK unsigned long
-static BLOOM_MASK bloom_linebreak;
+static BLOOM_MASK bloom_linebreak = ~(BLOOM_MASK)0;
#define BLOOM_ADD(mask, ch) ((mask |= (1UL << ((ch) & (BLOOM_WIDTH - 1)))))
#define BLOOM(mask, ch) ((mask & (1UL << ((ch) & (BLOOM_WIDTH - 1)))))
@@ -1602,9 +1616,9 @@
return 0;
if (length == 0) {
+ _Py_INCREF_UNICODE_EMPTY();
Py_DECREF(*p_unicode);
*p_unicode = unicode_empty;
- Py_INCREF(*p_unicode);
return 0;
}
@@ -1727,10 +1741,8 @@
some optimizations which share commonly used objects. */
/* Optimization for empty strings */
- if (size == 0 && unicode_empty != NULL) {
- Py_INCREF(unicode_empty);
- return unicode_empty;
- }
+ if (size == 0)
+ _Py_RETURN_UNICODE_EMPTY();
/* Single character Unicode objects in the Latin-1 range are
shared when using this constructor */
@@ -1886,10 +1898,8 @@
PyObject *res;
unsigned char max_char;
- if (size == 0) {
- Py_INCREF(unicode_empty);
- return unicode_empty;
- }
+ if (size == 0)
+ _Py_RETURN_UNICODE_EMPTY();
assert(size > 0);
if (size == 1)
return get_latin1_char(u[0]);
@@ -1909,10 +1919,8 @@
PyObject *res;
Py_UCS2 max_char;
- if (size == 0) {
- Py_INCREF(unicode_empty);
- return unicode_empty;
- }
+ if (size == 0)
+ _Py_RETURN_UNICODE_EMPTY();
assert(size > 0);
if (size == 1) {
Py_UCS4 ch = u[0];
@@ -1947,10 +1955,8 @@
PyObject *res;
Py_UCS4 max_char;
- if (size == 0) {
- Py_INCREF(unicode_empty);
- return unicode_empty;
- }
+ if (size == 0)
+ _Py_RETURN_UNICODE_EMPTY();
assert(size > 0);
if (size == 1) {
Py_UCS4 ch = u[0];
@@ -2242,10 +2248,8 @@
PyUnicode_FromWideChar(register const wchar_t *w, Py_ssize_t size)
{
if (w == NULL) {
- if (size == 0) {
- Py_INCREF(unicode_empty);
- return unicode_empty;
- }
+ if (size == 0)
+ _Py_RETURN_UNICODE_EMPTY();
PyErr_BadInternalCall();
return NULL;
}
@@ -2822,15 +2826,11 @@
/* Decoding bytes objects is the most common case and should be fast */
if (PyBytes_Check(obj)) {
- if (PyBytes_GET_SIZE(obj) == 0) {
- Py_INCREF(unicode_empty);
- v = unicode_empty;
- }
- else {
- v = PyUnicode_Decode(
- PyBytes_AS_STRING(obj), PyBytes_GET_SIZE(obj),
- encoding, errors);
- }
+ if (PyBytes_GET_SIZE(obj) == 0)
+ _Py_RETURN_UNICODE_EMPTY();
+ v = PyUnicode_Decode(
+ PyBytes_AS_STRING(obj), PyBytes_GET_SIZE(obj),
+ encoding, errors);
return v;
}
@@ -2850,12 +2850,11 @@
}
if (buffer.len == 0) {
- Py_INCREF(unicode_empty);
- v = unicode_empty;
- }
- else
- v = PyUnicode_Decode((char*) buffer.buf, buffer.len, encoding, errors);
-
+ PyBuffer_Release(&buffer);
+ _Py_RETURN_UNICODE_EMPTY();
+ }
+
+ v = PyUnicode_Decode((char*) buffer.buf, buffer.len, encoding, errors);
PyBuffer_Release(&buffer);
return v;
}
@@ -4198,8 +4197,7 @@
if (size == 0) {
if (consumed)
*consumed = 0;
- Py_INCREF(unicode_empty);
- return unicode_empty;
+ _Py_RETURN_UNICODE_EMPTY();
}
/* Start off assuming it's all ASCII. Widen later as necessary. */
@@ -4606,8 +4604,7 @@
if (size == 0) {
if (consumed)
*consumed = 0;
- Py_INCREF(unicode_empty);
- return unicode_empty;
+ _Py_RETURN_UNICODE_EMPTY();
}
/* ASCII is equivalent to the first 128 ordinals in Unicode. */
@@ -4865,8 +4862,7 @@
if (q == e) {
if (consumed)
*consumed = size;
- Py_INCREF(unicode_empty);
- return unicode_empty;
+ _Py_RETURN_UNICODE_EMPTY();
}
#ifdef WORDS_BIGENDIAN
@@ -5105,8 +5101,7 @@
if (q == e) {
if (consumed)
*consumed = size;
- Py_INCREF(unicode_empty);
- return unicode_empty;
+ _Py_RETURN_UNICODE_EMPTY();
}
#if PY_LITTLE_ENDIAN
@@ -5380,10 +5375,8 @@
Py_ssize_t len;
len = length_of_escaped_ascii_string(s, size);
- if (len == 0) {
- Py_INCREF(unicode_empty);
- return unicode_empty;
- }
+ if (len == 0)
+ _Py_RETURN_UNICODE_EMPTY();
/* After length_of_escaped_ascii_string() there are two alternatives,
either the string is pure ASCII with named escapes like \n, etc.
@@ -5774,10 +5767,8 @@
PyObject *errorHandler = NULL;
PyObject *exc = NULL;
- if (size == 0) {
- Py_INCREF(unicode_empty);
- return unicode_empty;
- }
+ if (size == 0)
+ _Py_RETURN_UNICODE_EMPTY();
/* Escaped strings will always be longer than the resulting
Unicode string, so we start with size here and then reduce the
@@ -5981,10 +5972,8 @@
1))
return NULL;
- if (size == 0) {
- Py_INCREF(unicode_empty);
- return unicode_empty;
- }
+ if (size == 0)
+ _Py_RETURN_UNICODE_EMPTY();
/* XXX overflow detection missing */
_PyUnicodeWriter_Init(&writer, 0);
@@ -6432,10 +6421,8 @@
PyObject *errorHandler = NULL;
PyObject *exc = NULL;
- if (size == 0) {
- Py_INCREF(unicode_empty);
- return unicode_empty;
- }
+ if (size == 0)
+ _Py_RETURN_UNICODE_EMPTY();
/* ASCII is equivalent to the first 128 ordinals in Unicode. */
if (size == 1 && (unsigned char)s[0] < 128)
@@ -6813,8 +6800,7 @@
if (chunk_size == 0 && done) {
if (v != NULL)
break;
- Py_INCREF(unicode_empty);
- return unicode_empty;
+ _Py_RETURN_UNICODE_EMPTY();
}
@@ -7291,10 +7277,8 @@
if (mapping == NULL)
return PyUnicode_DecodeLatin1(s, size, errors);
- if (size == 0) {
- Py_INCREF(unicode_empty);
- return unicode_empty;
- }
+ if (size == 0)
+ _Py_RETURN_UNICODE_EMPTY();
_PyUnicodeWriter_Init(&writer, 0);
if (_PyUnicodeWriter_Prepare(&writer, size, 127) == -1)
goto onError;
@@ -9333,9 +9317,7 @@
/* If empty sequence, return u"". */
if (seqlen == 0) {
Py_DECREF(fseq);
- Py_INCREF(unicode_empty);
- res = unicode_empty;
- return res;
+ _Py_RETURN_UNICODE_EMPTY();
}
/* If singleton sequence with an exact Unicode, return that. */
@@ -10035,7 +10017,7 @@
}
new_size = slen + n * (len2 - len1);
if (new_size == 0) {
- Py_INCREF(unicode_empty);
+ _Py_INCREF_UNICODE_EMPTY();
u = unicode_empty;
goto done;
}
@@ -11538,10 +11520,8 @@
PyErr_SetString(PyExc_IndexError, "string index out of range");
return NULL;
}
- if (start >= length || end < start) {
- Py_INCREF(unicode_empty);
- return unicode_empty;
- }
+ if (start >= length || end < start)
+ _Py_RETURN_UNICODE_EMPTY();
length = end - start;
if (PyUnicode_IS_ASCII(self)) {
@@ -11668,10 +11648,8 @@
PyObject *u;
Py_ssize_t nchars, n;
- if (len < 1) {
- Py_INCREF(unicode_empty);
- return unicode_empty;
- }
+ if (len < 1)
+ _Py_RETURN_UNICODE_EMPTY();
/* no repeat, return original string */
if (len == 1)
@@ -12811,8 +12789,7 @@
{
if (writer->pos == 0) {
Py_XDECREF(writer->buffer);
- Py_INCREF(unicode_empty);
- return unicode_empty;
+ _Py_RETURN_UNICODE_EMPTY();
}
if (writer->readonly) {
assert(PyUnicode_GET_LENGTH(writer->buffer) == writer->pos);
@@ -13030,8 +13007,7 @@
}
if (slicelength <= 0) {
- Py_INCREF(unicode_empty);
- return unicode_empty;
+ _Py_RETURN_UNICODE_EMPTY();
} else if (start == 0 && step == 1 &&
slicelength == PyUnicode_GET_LENGTH(self)) {
return unicode_result_unchanged(self);
@@ -14035,10 +14011,8 @@
if (!PyArg_ParseTupleAndKeywords(args, kwds, "|Oss:str",
kwlist, &x, &encoding, &errors))
return NULL;
- if (x == NULL) {
- Py_INCREF(unicode_empty);
- return unicode_empty;
- }
+ if (x == NULL)
+ _Py_RETURN_UNICODE_EMPTY();
if (encoding == NULL && errors == NULL)
return PyObject_Str(x);
else
@@ -14222,9 +14196,11 @@
};
/* Init the implementation */
- unicode_empty = PyUnicode_New(0, 0);
- if (!unicode_empty)
- Py_FatalError("Can't create empty string");
+ if (unicode_empty == NULL) {
+ unicode_empty = PyUnicode_New(0, 0);
+ if (!unicode_empty)
+ Py_FatalError("Can't create empty string");
+ }
assert(_PyUnicode_CheckConsistency(unicode_empty, 1));
for (i = 0; i < 256; i++)
@@ -14268,15 +14244,10 @@
{
int i;
- Py_XDECREF(unicode_empty);
- unicode_empty = NULL;
-
- for (i = 0; i < 256; i++) {
- if (unicode_latin1[i]) {
- Py_DECREF(unicode_latin1[i]);
- unicode_latin1[i] = NULL;
- }
- }
+ Py_CLEAR(unicode_empty);
+
+ for (i = 0; i < 256; i++)
+ Py_CLEAR(unicode_latin1[i]);
_PyUnicode_ClearStaticStrings();
(void)PyUnicode_ClearFreeList();
}
@@ -14405,8 +14376,7 @@
"mortal/immortal\n", mortal_size, immortal_size);
Py_DECREF(keys);
PyDict_Clear(interned);
- Py_DECREF(interned);
- interned = NULL;
+ Py_CLEAR(interned);
}
_______________________________________________
Python-bugs-list mailing list
Unsubscribe:
http://mail.python.org/mailman/options/python-bugs-list/archive%40mail-archive.com
