summaryrefslogtreecommitdiffstats
path: root/Objects/unicodeobject.c
diff options
context:
space:
mode:
Diffstat (limited to 'Objects/unicodeobject.c')
-rw-r--r--Objects/unicodeobject.c91
1 files changed, 36 insertions, 55 deletions
diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c
index 7c38362..ab36357 100644
--- a/Objects/unicodeobject.c
+++ b/Objects/unicodeobject.c
@@ -1029,8 +1029,7 @@ resize_copy(PyObject *unicode, Py_ssize_t length)
if (_PyUnicode_KIND(unicode) != PyUnicode_WCHAR_KIND) {
PyObject *copy;
- if (PyUnicode_READY(unicode) == -1)
- return NULL;
+ assert(PyUnicode_IS_READY(unicode));
copy = PyUnicode_New(length, PyUnicode_MAX_CHAR_VALUE(unicode));
if (copy == NULL)
@@ -1974,14 +1973,11 @@ unicode_char(Py_UCS4 ch)
unicode = PyUnicode_New(1, ch);
if (unicode == NULL)
return NULL;
- switch (PyUnicode_KIND(unicode)) {
- case PyUnicode_1BYTE_KIND:
- PyUnicode_1BYTE_DATA(unicode)[0] = (Py_UCS1)ch;
- break;
- case PyUnicode_2BYTE_KIND:
+
+ assert(PyUnicode_KIND(unicode) != PyUnicode_1BYTE_KIND);
+ if (PyUnicode_KIND(unicode) == PyUnicode_2BYTE_KIND) {
PyUnicode_2BYTE_DATA(unicode)[0] = (Py_UCS2)ch;
- break;
- default:
+ } else {
assert(PyUnicode_KIND(unicode) == PyUnicode_4BYTE_KIND);
PyUnicode_4BYTE_DATA(unicode)[0] = ch;
}
@@ -3412,11 +3408,9 @@ PyUnicode_EncodeLocale(PyObject *unicode, const char *errors)
{
Py_ssize_t wlen, wlen2;
wchar_t *wstr;
- PyObject *bytes = NULL;
char *errmsg;
- PyObject *reason = NULL;
- PyObject *exc;
- size_t error_pos;
+ PyObject *bytes, *reason, *exc;
+ size_t error_pos, errlen;
int surrogateescape;
if (locale_error_handler(errors, &surrogateescape) < 0)
@@ -3471,6 +3465,7 @@ PyUnicode_EncodeLocale(PyObject *unicode, const char *errors)
len2 = wcstombs(PyBytes_AS_STRING(bytes), wstr, len+1);
if (len2 == (size_t)-1 || len2 > len) {
+ Py_DECREF(bytes);
error_pos = (size_t)-1;
goto encode_error;
}
@@ -3486,17 +3481,15 @@ encode_error:
error_pos = wcstombs_errorpos(wstr);
PyMem_Free(wstr);
- Py_XDECREF(bytes);
-
- if (errmsg != NULL) {
- size_t errlen;
- wstr = Py_DecodeLocale(errmsg, &errlen);
- if (wstr != NULL) {
- reason = PyUnicode_FromWideChar(wstr, errlen);
- PyMem_RawFree(wstr);
- } else
- errmsg = NULL;
+
+ wstr = Py_DecodeLocale(errmsg, &errlen);
+ if (wstr != NULL) {
+ reason = PyUnicode_FromWideChar(wstr, errlen);
+ PyMem_RawFree(wstr);
+ } else {
+ errmsg = NULL;
}
+
if (errmsg == NULL)
reason = PyUnicode_FromString(
"wcstombs() encountered an unencodable "
@@ -3512,7 +3505,7 @@ encode_error:
Py_DECREF(reason);
if (exc != NULL) {
PyCodec_StrictErrors(exc);
- Py_XDECREF(exc);
+ Py_DECREF(exc);
}
return NULL;
}
@@ -3719,10 +3712,9 @@ PyUnicode_DecodeLocaleAndSize(const char *str, Py_ssize_t len,
size_t wlen, wlen2;
PyObject *unicode;
int surrogateescape;
- size_t error_pos;
+ size_t error_pos, errlen;
char *errmsg;
- PyObject *reason = NULL; /* initialize to prevent gcc warning */
- PyObject *exc;
+ PyObject *exc, *reason = NULL; /* initialize to prevent gcc warning */
if (locale_error_handler(errors, &surrogateescape) < 0)
return NULL;
@@ -3780,19 +3772,16 @@ PyUnicode_DecodeLocaleAndSize(const char *str, Py_ssize_t len,
return unicode;
decode_error:
- reason = NULL;
errmsg = strerror(errno);
assert(errmsg != NULL);
error_pos = mbstowcs_errorpos(str, len);
- if (errmsg != NULL) {
- size_t errlen;
- wstr = Py_DecodeLocale(errmsg, &errlen);
- if (wstr != NULL) {
- reason = PyUnicode_FromWideChar(wstr, errlen);
- PyMem_RawFree(wstr);
- }
+ wstr = Py_DecodeLocale(errmsg, &errlen);
+ if (wstr != NULL) {
+ reason = PyUnicode_FromWideChar(wstr, errlen);
+ PyMem_RawFree(wstr);
}
+
if (reason == NULL)
reason = PyUnicode_FromString(
"mbstowcs() encountered an invalid multibyte sequence");
@@ -3807,7 +3796,7 @@ decode_error:
Py_DECREF(reason);
if (exc != NULL) {
PyCodec_StrictErrors(exc);
- Py_XDECREF(exc);
+ Py_DECREF(exc);
}
return NULL;
}
@@ -4248,7 +4237,7 @@ unicode_decode_call_errorhandler_wchar(
Py_ssize_t *endinpos, PyObject **exceptionObject, const char **inptr,
PyObject **output, Py_ssize_t *outpos)
{
- static const char *argparse = "O!n;decoding error handler must return (str, int) tuple";
+ static const char *argparse = "Un;decoding error handler must return (str, int) tuple";
PyObject *restuple = NULL;
PyObject *repunicode = NULL;
@@ -4281,10 +4270,10 @@ unicode_decode_call_errorhandler_wchar(
if (restuple == NULL)
goto onError;
if (!PyTuple_Check(restuple)) {
- PyErr_SetString(PyExc_TypeError, &argparse[4]);
+ PyErr_SetString(PyExc_TypeError, &argparse[3]);
goto onError;
}
- if (!PyArg_ParseTuple(restuple, argparse, &PyUnicode_Type, &repunicode, &newpos))
+ if (!PyArg_ParseTuple(restuple, argparse, &repunicode, &newpos))
goto onError;
/* Copy back the bytes variables, which might have been modified by the
@@ -4292,9 +4281,6 @@ unicode_decode_call_errorhandler_wchar(
inputobj = PyUnicodeDecodeError_GetObject(*exceptionObject);
if (!inputobj)
goto onError;
- if (!PyBytes_Check(inputobj)) {
- PyErr_Format(PyExc_TypeError, "exception attribute object must be bytes");
- }
*input = PyBytes_AS_STRING(inputobj);
insize = PyBytes_GET_SIZE(inputobj);
*inend = *input + insize;
@@ -4335,7 +4321,7 @@ unicode_decode_call_errorhandler_wchar(
*inptr = *input + newpos;
/* we made it! */
- Py_XDECREF(restuple);
+ Py_DECREF(restuple);
return 0;
overflow:
@@ -4356,7 +4342,7 @@ unicode_decode_call_errorhandler_writer(
Py_ssize_t *endinpos, PyObject **exceptionObject, const char **inptr,
_PyUnicodeWriter *writer /* PyObject **output, Py_ssize_t *outpos */)
{
- static const char *argparse = "O!n;decoding error handler must return (str, int) tuple";
+ static const char *argparse = "Un;decoding error handler must return (str, int) tuple";
PyObject *restuple = NULL;
PyObject *repunicode = NULL;
@@ -4383,10 +4369,10 @@ unicode_decode_call_errorhandler_writer(
if (restuple == NULL)
goto onError;
if (!PyTuple_Check(restuple)) {
- PyErr_SetString(PyExc_TypeError, &argparse[4]);
+ PyErr_SetString(PyExc_TypeError, &argparse[3]);
goto onError;
}
- if (!PyArg_ParseTuple(restuple, argparse, &PyUnicode_Type, &repunicode, &newpos))
+ if (!PyArg_ParseTuple(restuple, argparse, &repunicode, &newpos))
goto onError;
/* Copy back the bytes variables, which might have been modified by the
@@ -4394,9 +4380,6 @@ unicode_decode_call_errorhandler_writer(
inputobj = PyUnicodeDecodeError_GetObject(*exceptionObject);
if (!inputobj)
goto onError;
- if (!PyBytes_Check(inputobj)) {
- PyErr_Format(PyExc_TypeError, "exception attribute object must be bytes");
- }
*input = PyBytes_AS_STRING(inputobj);
insize = PyBytes_GET_SIZE(inputobj);
*inend = *input + insize;
@@ -4411,8 +4394,6 @@ unicode_decode_call_errorhandler_writer(
goto onError;
}
- if (PyUnicode_READY(repunicode) < 0)
- goto onError;
replen = PyUnicode_GET_LENGTH(repunicode);
if (replen > 1) {
writer->min_length += replen - 1;
@@ -4428,7 +4409,7 @@ unicode_decode_call_errorhandler_writer(
*inptr = *input + newpos;
/* we made it! */
- Py_XDECREF(restuple);
+ Py_DECREF(restuple);
return 0;
onError:
@@ -8663,7 +8644,7 @@ unicode_translate_call_errorhandler(const char *errors,
Py_ssize_t startpos, Py_ssize_t endpos,
Py_ssize_t *newpos)
{
- static const char *argparse = "O!n;translating error handler must return (str, int) tuple";
+ static const char *argparse = "Un;translating error handler must return (str, int) tuple";
Py_ssize_t i_newpos;
PyObject *restuple;
@@ -8685,11 +8666,11 @@ unicode_translate_call_errorhandler(const char *errors,
if (restuple == NULL)
return NULL;
if (!PyTuple_Check(restuple)) {
- PyErr_SetString(PyExc_TypeError, &argparse[4]);
+ PyErr_SetString(PyExc_TypeError, &argparse[3]);
Py_DECREF(restuple);
return NULL;
}
- if (!PyArg_ParseTuple(restuple, argparse, &PyUnicode_Type,
+ if (!PyArg_ParseTuple(restuple, argparse,
&resunicode, &i_newpos)) {
Py_DECREF(restuple);
return NULL;
generated by cgit v0.12 at 2025-04-28 08:51:19 (GMT)