mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-07-24 11:44:31 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 8

[3.12] gh-116042: Fix location for SyntaxErrors of invalid escapes in the tokenizer (GH-116049) (#130065)

Browse source 
(cherry picked from commit 56eda25633)
This commit is contained in:
Pablo Galindo Salgado 2025-02-13 01:42:24 +00:00 • committed by GitHub
parent 719d08cccf
commit 5e8a9eb13d
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 82 additions and 18 deletions
Download patch file Download diff file Expand all files Collapse all files

53
Parser/string_parser.c
View file

@ -9,7 +9,7 @@
//// STRING HANDLING FUNCTIONS ////
static int
warn_invalid_escape_sequence(Parser *p, const char *first_invalid_escape, Token *t)
warn_invalid_escape_sequence(Parser *p, const char* buffer, const char *first_invalid_escape, Token *t)
{
if (p->call_invalid_rules) {
// Do not report warnings if we are in the second pass of the parser
@ -38,8 +38,46 @@ warn_invalid_escape_sequence(Parser *p, const char *first_invalid_escape, Token
else {
category = PyExc_DeprecationWarning;
}
// Calculate the lineno and the col_offset of the invalid escape sequence
const char *start = buffer;
const char *end = first_invalid_escape;
int lineno = t->lineno;
int col_offset = t->col_offset;
while (start < end) {
if (*start == '\n') {
lineno++;
col_offset = 0;
}
else {
col_offset++;
}
start++;
}
// Count the number of quotes in the token
char first_quote = 0;
if (lineno == t->lineno) {
int quote_count = 0;
char* tok = PyBytes_AsString(t->bytes);
for (int i = 0; i < PyBytes_Size(t->bytes); i++) {
if (tok[i] == '\'' || tok[i] == '\"') {
if (quote_count == 0) {
first_quote = tok[i];
}
if (tok[i] == first_quote) {
quote_count++;
}
} else {
break;
}
}
col_offset += quote_count;
}
if (PyErr_WarnExplicitObject(category, msg, p->tok->filename,
t->lineno, NULL, NULL) < 0) {
lineno, NULL, NULL) < 0) {
if (PyErr_ExceptionMatches(category)) {
/* Replace the Syntax/DeprecationWarning exception with a SyntaxError
to get a more accurate error report */
@ -50,11 +88,12 @@ warn_invalid_escape_sequence(Parser *p, const char *first_invalid_escape, Token
error location, if p->known_err_token is not set. */
p->known_err_token = t;
if (octal) {
RAISE_SYNTAX_ERROR("invalid octal escape sequence '\\%.3s'",
first_invalid_escape);
RAISE_ERROR_KNOWN_LOCATION(p, PyExc_SyntaxError, lineno, col_offset-1, lineno, col_offset+1,
"invalid octal escape sequence '\\%.3s'", first_invalid_escape);
}
else {
RAISE_SYNTAX_ERROR("invalid escape sequence '\\%c'", c);
RAISE_ERROR_KNOWN_LOCATION(p, PyExc_SyntaxError, lineno, col_offset-1, lineno, col_offset+1,
"invalid escape sequence '\\%c'", c);
}
}
Py_DECREF(msg);
@ -148,7 +187,7 @@ decode_unicode_with_escapes(Parser *parser, const char *s, size_t len, Token *t)
// HACK: later we can simply pass the line no, since we don't preserve the tokens
// when we are decoding the string but we preserve the line numbers.
if (v != NULL && first_invalid_escape != NULL && t != NULL) {
if (warn_invalid_escape_sequence(parser, first_invalid_escape, t) < 0) {
if (warn_invalid_escape_sequence(parser, s, first_invalid_escape, t) < 0) {
/* We have not decref u before because first_invalid_escape points
inside u. */
Py_XDECREF(u);
@ -170,7 +209,7 @@ decode_bytes_with_escapes(Parser *p, const char *s, Py_ssize_t len, Token *t)
}
if (first_invalid_escape != NULL) {
if (warn_invalid_escape_sequence(p, first_invalid_escape, t) < 0) {
if (warn_invalid_escape_sequence(p, s, first_invalid_escape, t) < 0) {
Py_DECREF(result);
return NULL;
}