mirror of
https://github.com/python/cpython.git
synced 2025-09-26 18:29:57 +00:00
bpo-34013: Move the Python 2 hints from the exception constructor to the parser (GH-27392)
This commit is contained in:
parent
6948964ecf
commit
ecc3c8e421
5 changed files with 28 additions and 224 deletions
|
@ -1475,9 +1475,6 @@ ComplexExtendsException(PyExc_Exception, AttributeError,
|
|||
* SyntaxError extends Exception
|
||||
*/
|
||||
|
||||
/* Helper function to customize error message for some syntax errors */
|
||||
static int _report_missing_parentheses(PySyntaxErrorObject *self);
|
||||
|
||||
static int
|
||||
SyntaxError_init(PySyntaxErrorObject *self, PyObject *args, PyObject *kwds)
|
||||
{
|
||||
|
@ -1520,18 +1517,6 @@ SyntaxError_init(PySyntaxErrorObject *self, PyObject *args, PyObject *kwds)
|
|||
PyErr_SetString(PyExc_TypeError, "end_offset must be provided when end_lineno is provided");
|
||||
return -1;
|
||||
}
|
||||
|
||||
/*
|
||||
* Issue #21669: Custom error for 'print' & 'exec' as statements
|
||||
*
|
||||
* Only applies to SyntaxError instances, not to subclasses such
|
||||
* as TabError or IndentationError (see issue #31161)
|
||||
*/
|
||||
if (Py_IS_TYPE(self, (PyTypeObject *)PyExc_SyntaxError) &&
|
||||
self->text && PyUnicode_Check(self->text) &&
|
||||
_report_missing_parentheses(self) < 0) {
|
||||
return -1;
|
||||
}
|
||||
}
|
||||
return 0;
|
||||
}
|
||||
|
@ -3033,189 +3018,3 @@ _PyErr_TrySetFromCause(const char *format, ...)
|
|||
PyErr_Restore(new_exc, new_val, new_tb);
|
||||
return new_val;
|
||||
}
|
||||
|
||||
|
||||
/* To help with migration from Python 2, SyntaxError.__init__ applies some
|
||||
* heuristics to try to report a more meaningful exception when print and
|
||||
* exec are used like statements.
|
||||
*
|
||||
* The heuristics are currently expected to detect the following cases:
|
||||
* - top level statement
|
||||
* - statement in a nested suite
|
||||
* - trailing section of a one line complex statement
|
||||
*
|
||||
* They're currently known not to trigger:
|
||||
* - after a semi-colon
|
||||
*
|
||||
* The error message can be a bit odd in cases where the "arguments" are
|
||||
* completely illegal syntactically, but that isn't worth the hassle of
|
||||
* fixing.
|
||||
*
|
||||
* We also can't do anything about cases that are legal Python 3 syntax
|
||||
* but mean something entirely different from what they did in Python 2
|
||||
* (omitting the arguments entirely, printing items preceded by a unary plus
|
||||
* or minus, using the stream redirection syntax).
|
||||
*/
|
||||
|
||||
|
||||
// Static helper for setting legacy print error message
|
||||
static int
|
||||
_set_legacy_print_statement_msg(PySyntaxErrorObject *self, Py_ssize_t start)
|
||||
{
|
||||
// PRINT_OFFSET is to remove the `print ` prefix from the data.
|
||||
const int PRINT_OFFSET = 6;
|
||||
const int STRIP_BOTH = 2;
|
||||
Py_ssize_t start_pos = start + PRINT_OFFSET;
|
||||
Py_ssize_t text_len = PyUnicode_GET_LENGTH(self->text);
|
||||
Py_UCS4 semicolon = ';';
|
||||
Py_ssize_t end_pos = PyUnicode_FindChar(self->text, semicolon,
|
||||
start_pos, text_len, 1);
|
||||
if (end_pos < -1) {
|
||||
return -1;
|
||||
} else if (end_pos == -1) {
|
||||
end_pos = text_len;
|
||||
}
|
||||
|
||||
PyObject *data = PyUnicode_Substring(self->text, start_pos, end_pos);
|
||||
if (data == NULL) {
|
||||
return -1;
|
||||
}
|
||||
|
||||
PyObject *strip_sep_obj = PyUnicode_FromString(" \t\r\n");
|
||||
if (strip_sep_obj == NULL) {
|
||||
Py_DECREF(data);
|
||||
return -1;
|
||||
}
|
||||
|
||||
PyObject *new_data = _PyUnicode_XStrip(data, STRIP_BOTH, strip_sep_obj);
|
||||
Py_DECREF(data);
|
||||
Py_DECREF(strip_sep_obj);
|
||||
if (new_data == NULL) {
|
||||
return -1;
|
||||
}
|
||||
// gets the modified text_len after stripping `print `
|
||||
text_len = PyUnicode_GET_LENGTH(new_data);
|
||||
const char *maybe_end_arg = "";
|
||||
if (text_len > 0 && PyUnicode_READ_CHAR(new_data, text_len-1) == ',') {
|
||||
maybe_end_arg = " end=\" \"";
|
||||
}
|
||||
PyObject *error_msg = PyUnicode_FromFormat(
|
||||
"Missing parentheses in call to 'print'. Did you mean print(%U%s)?",
|
||||
new_data, maybe_end_arg
|
||||
);
|
||||
Py_DECREF(new_data);
|
||||
if (error_msg == NULL)
|
||||
return -1;
|
||||
|
||||
Py_XSETREF(self->msg, error_msg);
|
||||
return 1;
|
||||
}
|
||||
|
||||
static int
|
||||
_check_for_legacy_statements(PySyntaxErrorObject *self, Py_ssize_t start)
|
||||
{
|
||||
/* Return values:
|
||||
* -1: an error occurred
|
||||
* 0: nothing happened
|
||||
* 1: the check triggered & the error message was changed
|
||||
*/
|
||||
static PyObject *print_prefix = NULL;
|
||||
static PyObject *exec_prefix = NULL;
|
||||
Py_ssize_t text_len = PyUnicode_GET_LENGTH(self->text), match;
|
||||
int kind = PyUnicode_KIND(self->text);
|
||||
const void *data = PyUnicode_DATA(self->text);
|
||||
|
||||
/* Ignore leading whitespace */
|
||||
while (start < text_len) {
|
||||
Py_UCS4 ch = PyUnicode_READ(kind, data, start);
|
||||
if (!Py_UNICODE_ISSPACE(ch))
|
||||
break;
|
||||
start++;
|
||||
}
|
||||
/* Checking against an empty or whitespace-only part of the string */
|
||||
if (start == text_len) {
|
||||
return 0;
|
||||
}
|
||||
|
||||
/* Check for legacy print statements */
|
||||
if (print_prefix == NULL) {
|
||||
print_prefix = PyUnicode_InternFromString("print ");
|
||||
if (print_prefix == NULL) {
|
||||
return -1;
|
||||
}
|
||||
}
|
||||
match = PyUnicode_Tailmatch(self->text, print_prefix,
|
||||
start, text_len, -1);
|
||||
if (match == -1) {
|
||||
return -1;
|
||||
}
|
||||
if (match) {
|
||||
return _set_legacy_print_statement_msg(self, start);
|
||||
}
|
||||
|
||||
/* Check for legacy exec statements */
|
||||
if (exec_prefix == NULL) {
|
||||
exec_prefix = PyUnicode_InternFromString("exec ");
|
||||
if (exec_prefix == NULL) {
|
||||
return -1;
|
||||
}
|
||||
}
|
||||
match = PyUnicode_Tailmatch(self->text, exec_prefix, start, text_len, -1);
|
||||
if (match == -1) {
|
||||
return -1;
|
||||
}
|
||||
if (match) {
|
||||
PyObject *msg = PyUnicode_FromString("Missing parentheses in call "
|
||||
"to 'exec'");
|
||||
if (msg == NULL) {
|
||||
return -1;
|
||||
}
|
||||
Py_XSETREF(self->msg, msg);
|
||||
return 1;
|
||||
}
|
||||
/* Fall back to the default error message */
|
||||
return 0;
|
||||
}
|
||||
|
||||
static int
|
||||
_report_missing_parentheses(PySyntaxErrorObject *self)
|
||||
{
|
||||
Py_UCS4 left_paren = 40;
|
||||
Py_ssize_t left_paren_index;
|
||||
Py_ssize_t text_len = PyUnicode_GET_LENGTH(self->text);
|
||||
int legacy_check_result = 0;
|
||||
|
||||
/* Skip entirely if there is an opening parenthesis */
|
||||
left_paren_index = PyUnicode_FindChar(self->text, left_paren,
|
||||
0, text_len, 1);
|
||||
if (left_paren_index < -1) {
|
||||
return -1;
|
||||
}
|
||||
if (left_paren_index != -1) {
|
||||
/* Use default error message for any line with an opening paren */
|
||||
return 0;
|
||||
}
|
||||
/* Handle the simple statement case */
|
||||
legacy_check_result = _check_for_legacy_statements(self, 0);
|
||||
if (legacy_check_result < 0) {
|
||||
return -1;
|
||||
|
||||
}
|
||||
if (legacy_check_result == 0) {
|
||||
/* Handle the one-line complex statement case */
|
||||
Py_UCS4 colon = 58;
|
||||
Py_ssize_t colon_index;
|
||||
colon_index = PyUnicode_FindChar(self->text, colon,
|
||||
0, text_len, 1);
|
||||
if (colon_index < -1) {
|
||||
return -1;
|
||||
}
|
||||
if (colon_index >= 0 && colon_index < text_len) {
|
||||
/* Check again, starting from just after the colon */
|
||||
if (_check_for_legacy_statements(self, colon_index+1) < 0) {
|
||||
return -1;
|
||||
}
|
||||
}
|
||||
}
|
||||
return 0;
|
||||
}
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue