Skip to content

Add state tracking for unicode #39

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
nanjekyejoannah wants to merge 5 commits into from
Closed

Add state tracking for unicode #39

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
507db05
unicode parsing fix for encoding
nanjekyejoannah May 1, 2024
93a383e
fix unicode test
nanjekyejoannah May 1, 2024
0a20ce6
remove commented code
nanjekyejoannah May 1, 2024
95c6eef
Fix errors that come with adding state in _object
nanjekyejoannah Jun 19, 2024
21674a7
remove temp files
nanjekyejoannah Jun 19, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions Include/object.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -105,6 +105,7 @@ whose size is determined when the object is allocated.
*/
typedef struct _object {
PyObject_HEAD
Py_ssize_t ob_bstate;
} PyObject;

typedef struct {
Expand Down
32 changes: 29 additions & 3 deletions Objects/unicodeobject.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1209,12 +1209,32 @@ PyObject *PyUnicode_FromEncodedObject(register PyObject *obj,
return PyObject_Unicode(obj);
}
#else
#endif

// if (PyUnicode_Check(obj)) {
Copy link
Member

@ltratt ltratt May 1, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Should we just delete this chunk?

// PyErr_SetString(PyExc_TypeError,
// "'decode()' is not supported on Unicode in 3.x: convert the string to bytes.");
// obj->ob_bstate = BSTATE_BYTE;
// if ((obj->ob_bstate == BSTATE_BYTE) &&
// PyErr_WarnPy3k(
// "'decode()' is not supported on Unicode in 3.x: convert the string to bytes.", 1) < 0) {
// return NULL;
// }
// return NULL;
// return PyObject_Unicode(obj);
// }

if (PyUnicode_Check(obj)) {
obj->ob_bstate = BSTATE_BYTE;
if ((obj->ob_bstate == BSTATE_BYTE) &&
PyErr_WarnPy3k(
"'decode()' is not supported on Unicode in 3.x: convert the string to bytes.", 1) < 0) {
return NULL;
}
PyErr_SetString(PyExc_TypeError,
"decoding Unicode is not supported");
return NULL;
}
#endif

/* Coerce object */
if (PyString_Check(obj)) {
Expand Down Expand Up @@ -1304,8 +1324,14 @@ PyObject *PyUnicode_AsDecodedObject(PyObject *unicode,
goto onError;
}

if (PyErr_WarnPy3k("decoding Unicode is not supported in 3.x", 1) < 0)
goto onError;
if (PyString_CheckExact(unicode)) {
unicode->ob_bstate = BSTATE_BYTE;
}

if ((unicode->ob_bstate == BSTATE_BYTE) &&
PyErr_WarnPy3k("'decode()' is not supported on Unicode in 3.x: convert the string to bytes.", 1) < 0) {
return NULL;
}

if (encoding == NULL)
encoding = PyUnicode_GetDefaultEncoding();
Expand Down