summaryrefslogtreecommitdiffstats
path: root/Python
diff options
context:
space:
mode:
Diffstat (limited to 'Python')
-rw-r--r--Python/ast.c66
-rw-r--r--Python/ceval.c17
-rw-r--r--Python/codecs.c21
3 files changed, 80 insertions, 24 deletions
diff --git a/Python/ast.c b/Python/ast.c
index 76daf6f..91e7d01 100644
--- a/Python/ast.c
+++ b/Python/ast.c
@@ -4113,8 +4113,34 @@ decode_utf8(struct compiling *c, const char **sPtr, const char *end)
return PyUnicode_DecodeUTF8(t, s - t, NULL);
}
+static int
+warn_invalid_escape_sequence(struct compiling *c, const node *n,
+ char first_invalid_escape_char)
+{
+ PyObject *msg = PyUnicode_FromFormat("invalid escape sequence \\%c",
+ first_invalid_escape_char);
+ if (msg == NULL) {
+ return -1;
+ }
+ if (PyErr_WarnExplicitObject(PyExc_DeprecationWarning, msg,
+ c->c_filename, LINENO(n),
+ NULL, NULL) < 0 &&
+ PyErr_ExceptionMatches(PyExc_DeprecationWarning))
+ {
+ const char *s = PyUnicode_AsUTF8(msg);
+ if (s != NULL) {
+ ast_error(c, n, s);
+ }
+ Py_DECREF(msg);
+ return -1;
+ }
+ Py_DECREF(msg);
+ return 0;
+}
+
static PyObject *
-decode_unicode_with_escapes(struct compiling *c, const char *s, size_t len)
+decode_unicode_with_escapes(struct compiling *c, const node *n, const char *s,
+ size_t len)
{
PyObject *v, *u;
char *buf;
@@ -4167,11 +4193,41 @@ decode_unicode_with_escapes(struct compiling *c, const char *s, size_t len)
len = p - buf;
s = buf;
- v = PyUnicode_DecodeUnicodeEscape(s, len, NULL);
+ const char *first_invalid_escape;
+ v = _PyUnicode_DecodeUnicodeEscape(s, len, NULL, &first_invalid_escape);
+
+ if (v != NULL && first_invalid_escape != NULL) {
+ if (warn_invalid_escape_sequence(c, n, *first_invalid_escape) < 0) {
+ /* We have not decref u before because first_invalid_escape points
+ inside u. */
+ Py_XDECREF(u);
+ Py_DECREF(v);
+ return NULL;
+ }
+ }
Py_XDECREF(u);
return v;
}
+static PyObject *
+decode_bytes_with_escapes(struct compiling *c, const node *n, const char *s,
+ size_t len)
+{
+ const char *first_invalid_escape;
+ PyObject *result = _PyBytes_DecodeEscape(s, len, NULL, 0, NULL,
+ &first_invalid_escape);
+ if (result == NULL)
+ return NULL;
+
+ if (first_invalid_escape != NULL) {
+ if (warn_invalid_escape_sequence(c, n, *first_invalid_escape) < 0) {
+ Py_DECREF(result);
+ return NULL;
+ }
+ }
+ return result;
+}
+
/* Compile this expression in to an expr_ty. Add parens around the
expression, in order to allow leading spaces in the expression. */
static expr_ty
@@ -4310,7 +4366,7 @@ done:
literal_end-literal_start,
NULL, NULL);
else
- *literal = decode_unicode_with_escapes(c, literal_start,
+ *literal = decode_unicode_with_escapes(c, n, literal_start,
literal_end-literal_start);
if (!*literal)
return -1;
@@ -5048,12 +5104,12 @@ parsestr(struct compiling *c, const node *n, int *bytesmode, int *rawmode,
if (*rawmode)
*result = PyBytes_FromStringAndSize(s, len);
else
- *result = PyBytes_DecodeEscape(s, len, NULL, /* ignored */ 0, NULL);
+ *result = decode_bytes_with_escapes(c, n, s, len);
} else {
if (*rawmode)
*result = PyUnicode_DecodeUTF8Stateful(s, len, NULL, NULL);
else
- *result = decode_unicode_with_escapes(c, s, len);
+ *result = decode_unicode_with_escapes(c, n, s, len);
}
return *result == NULL ? -1 : 0;
}
diff --git a/Python/ceval.c b/Python/ceval.c
index 82cc9a2..2df94cf 100644
--- a/Python/ceval.c
+++ b/Python/ceval.c
@@ -1424,6 +1424,12 @@ _PyEval_EvalFrameDefault(PyFrameObject *f, int throwflag)
PyObject *right = POP();
PyObject *left = TOP();
PyObject *sum;
+ /* NOTE(haypo): Please don't try to micro-optimize int+int on
+ CPython using bytecode, it is simply worthless.
+ See http://bugs.python.org/issue21955 and
+ http://bugs.python.org/issue10044 for the discussion. In short,
+ no patch shown any impact on a realistic benchmark, only a minor
+ speedup on microbenchmarks. */
if (PyUnicode_CheckExact(left) &&
PyUnicode_CheckExact(right)) {
sum = unicode_concatenate(left, right, f, next_instr);
@@ -1538,7 +1544,7 @@ _PyEval_EvalFrameDefault(PyFrameObject *f, int throwflag)
TARGET(SET_ADD) {
PyObject *v = POP();
- PyObject *set = stack_pointer[-oparg];
+ PyObject *set = PEEK(oparg);
int err;
err = PySet_Add(set, v);
Py_DECREF(v);
@@ -2796,7 +2802,7 @@ _PyEval_EvalFrameDefault(PyFrameObject *f, int throwflag)
PyObject *map;
int err;
STACKADJ(-2);
- map = stack_pointer[-oparg]; /* dict */
+ map = PEEK(oparg); /* dict */
assert(PyDict_CheckExact(map));
err = PyDict_SetItem(map, key, value); /* map[key] = value */
Py_DECREF(value);
@@ -4266,6 +4272,9 @@ do_raise(PyObject *exc, PyObject *cause)
goto raise_error;
}
+ assert(type != NULL);
+ assert(value != NULL);
+
if (cause) {
PyObject *fixed_cause;
if (PyExceptionClass_Check(cause)) {
@@ -4292,8 +4301,8 @@ do_raise(PyObject *exc, PyObject *cause)
PyErr_SetObject(type, value);
/* PyErr_SetObject incref's its arguments */
- Py_XDECREF(value);
- Py_XDECREF(type);
+ Py_DECREF(value);
+ Py_DECREF(type);
return 0;
raise_error:
diff --git a/Python/codecs.c b/Python/codecs.c
index fe57d0d..96b3611 100644
--- a/Python/codecs.c
+++ b/Python/codecs.c
@@ -867,17 +867,14 @@ PyObject *PyCodec_BackslashReplaceErrors(PyObject *exc)
Py_UCS4 c;
if (PyObject_TypeCheck(exc, (PyTypeObject *)PyExc_UnicodeDecodeError)) {
- unsigned char *p;
+ const unsigned char *p;
if (PyUnicodeDecodeError_GetStart(exc, &start))
return NULL;
if (PyUnicodeDecodeError_GetEnd(exc, &end))
return NULL;
if (!(object = PyUnicodeDecodeError_GetObject(exc)))
return NULL;
- if (!(p = (unsigned char*)PyBytes_AsString(object))) {
- Py_DECREF(object);
- return NULL;
- }
+ p = (const unsigned char*)PyBytes_AS_STRING(object);
res = PyUnicode_New(4 * (end - start), 127);
if (res == NULL) {
Py_DECREF(object);
@@ -1220,7 +1217,7 @@ PyCodec_SurrogatePassErrors(PyObject *exc)
return restuple;
}
else if (PyObject_TypeCheck(exc, (PyTypeObject *)PyExc_UnicodeDecodeError)) {
- unsigned char *p;
+ const unsigned char *p;
Py_UCS4 ch = 0;
if (PyUnicodeDecodeError_GetStart(exc, &start))
return NULL;
@@ -1228,10 +1225,7 @@ PyCodec_SurrogatePassErrors(PyObject *exc)
return NULL;
if (!(object = PyUnicodeDecodeError_GetObject(exc)))
return NULL;
- if (!(p = (unsigned char*)PyBytes_AsString(object))) {
- Py_DECREF(object);
- return NULL;
- }
+ p = (const unsigned char*)PyBytes_AS_STRING(object);
if (!(encode = PyUnicodeDecodeError_GetEncoding(exc))) {
Py_DECREF(object);
return NULL;
@@ -1338,7 +1332,7 @@ PyCodec_SurrogateEscapeErrors(PyObject *exc)
}
else if (PyObject_TypeCheck(exc, (PyTypeObject *)PyExc_UnicodeDecodeError)) {
PyObject *str;
- unsigned char *p;
+ const unsigned char *p;
Py_UCS2 ch[4]; /* decode up to 4 bad bytes. */
int consumed = 0;
if (PyUnicodeDecodeError_GetStart(exc, &start))
@@ -1347,10 +1341,7 @@ PyCodec_SurrogateEscapeErrors(PyObject *exc)
return NULL;
if (!(object = PyUnicodeDecodeError_GetObject(exc)))
return NULL;
- if (!(p = (unsigned char*)PyBytes_AsString(object))) {
- Py_DECREF(object);
- return NULL;
- }
+ p = (const unsigned char*)PyBytes_AS_STRING(object);
while (consumed < 4 && consumed < end-start) {
/* Refuse to escape ASCII bytes. */
if (p[start+consumed] < 128)
generated by cgit v0.12 at 2025-08-08 08:26:00 (GMT)