mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-07-16 15:55:18 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 8

Fix gdb/libpython.py for not ready Unicode strings

Browse source 
_PyUnicode_CheckConsistency() checks also hash and length value for not ready
Unicode strings.
This commit is contained in:
Victor Stinner 2011-11-04 20:54:05 +01:00
parent 2fc507fe45
commit e30c0a1014
3 changed files with 10 additions and 10 deletions
Download patch file Download diff file Expand all files Collapse all files

8
Include/unicodeobject.h
View file

@ -231,22 +231,24 @@ typedef struct {
* utf8_length = 0 if utf8 is NULL * utf8_length = 0 if utf8 is NULL
* wstr is shared with data and wstr_length=length * wstr is shared with data and wstr_length=length
if kind=PyUnicode_2BYTE_KIND and sizeof(wchar_t)=2 if kind=PyUnicode_2BYTE_KIND and sizeof(wchar_t)=2
or if kind=PyUnicode_4BYTE_KIND and sizeof(wchar_4)=4 or if kind=PyUnicode_4BYTE_KIND and sizeof(wchar_t)=4
* wstr_length = 0 if wstr is NULL * wstr_length = 0 if wstr is NULL
* (data starts just after the structure) * (data starts just after the structure)
- legacy string, not ready: - legacy string, not ready:
* structure = PyUnicodeObject * structure = PyUnicodeObject
* length = 0 (use wstr_length)
* hash = -1
* kind = PyUnicode_WCHAR_KIND * kind = PyUnicode_WCHAR_KIND
* compact = 0 * compact = 0
* ascii = 0 * ascii = 0
* ready = 0 * ready = 0
* interned = SSTATE_NOT_INTERNED
* wstr is not NULL * wstr is not NULL
* data.any is NULL * data.any is NULL
* utf8 is NULL * utf8 is NULL
* utf8_length = 0 * utf8_length = 0
* interned = SSTATE_NOT_INTERNED
- legacy string, ready: - legacy string, ready:
@ -258,7 +260,7 @@ typedef struct {
* data.any is not NULL * data.any is not NULL
* utf8 is shared and utf8_length = length with data.any if ascii = 1 * utf8 is shared and utf8_length = length with data.any if ascii = 1
* utf8_length = 0 if utf8 is NULL * utf8_length = 0 if utf8 is NULL
* wstr is shared and wstr_length = length with data.any * wstr is shared with data.any and wstr_length = length
if kind=PyUnicode_2BYTE_KIND and sizeof(wchar_t)=2 if kind=PyUnicode_2BYTE_KIND and sizeof(wchar_t)=2
or if kind=PyUnicode_4BYTE_KIND and sizeof(wchar_4)=4 or if kind=PyUnicode_4BYTE_KIND and sizeof(wchar_4)=4
* wstr_length = 0 if wstr is NULL * wstr_length = 0 if wstr is NULL

7
Objects/unicodeobject.c
View file

@ -328,18 +328,21 @@ _PyUnicode_CheckConsistency(PyObject *op, int check_content)
assert(ascii->state.ascii == 0); assert(ascii->state.ascii == 0);
assert(ascii->state.ready == 1); assert(ascii->state.ready == 1);
assert (compact->utf8 != data); assert (compact->utf8 != data);
} else { }
else {
PyUnicodeObject *unicode = (PyUnicodeObject *)op; PyUnicodeObject *unicode = (PyUnicodeObject *)op;
data = unicode->data.any; data = unicode->data.any;
if (kind == PyUnicode_WCHAR_KIND) { if (kind == PyUnicode_WCHAR_KIND) {
assert(ascii->length == 0);
assert(ascii->hash == -1);
assert(ascii->state.compact == 0); assert(ascii->state.compact == 0);
assert(ascii->state.ascii == 0); assert(ascii->state.ascii == 0);
assert(ascii->state.ready == 0); assert(ascii->state.ready == 0);
assert(ascii->state.interned == SSTATE_NOT_INTERNED);
assert(ascii->wstr != NULL); assert(ascii->wstr != NULL);
assert(data == NULL); assert(data == NULL);
assert(compact->utf8 == NULL); assert(compact->utf8 == NULL);
assert(ascii->state.interned == SSTATE_NOT_INTERNED);
} }
else { else {
assert(kind == PyUnicode_1BYTE_KIND assert(kind == PyUnicode_1BYTE_KIND

5
Tools/gdb/libpython.py
View file

@ -1123,9 +1123,6 @@ class PyUnicodeObjectPtr(PyObjectPtr):
return _type_Py_UNICODE.sizeof return _type_Py_UNICODE.sizeof
def proxyval(self, visited): def proxyval(self, visited):
# From unicodeobject.h:
# Py_ssize_t length; /* Length of raw Unicode data in buffer */
# Py_UNICODE *str; /* Raw Unicode buffer */
if _is_pep393: if _is_pep393:
# Python 3.3 and newer # Python 3.3 and newer
may_have_surrogates = False may_have_surrogates = False
@ -1138,8 +1135,6 @@ class PyUnicodeObjectPtr(PyObjectPtr):
# string is not ready # string is not ready
may_have_surrogates = True may_have_surrogates = True
field_str = ascii['wstr'] field_str = ascii['wstr']
if not is_compact_ascii:
field_length = compact('wstr_length')
else: else:
if is_compact_ascii: if is_compact_ascii:
field_str = ascii.address + 1 field_str = ascii.address + 1