traverseda
/
cpython
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Issue #10778: decoding_fgets() decodes the filename from the filesystem 

encoding instead of UTF-8.
This commit is contained in:
Victor Stinner 2010-12-27 20:12:13 +00:00
parent cb428f0162
commit 83098a4095
1 changed files with 11 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
Parser/tokenizer.c
View File

@ -545,6 +545,7 @@ decoding_fgets(char *s, int size, struct tok_state *tok)
{
char *line = NULL;
int badchar = 0;
PyObject *filename;
for (;;) {
if (tok->decoding_state == STATE_NORMAL) {
/* We already have a codec associated with
@ -585,12 +586,16 @@ decoding_fgets(char *s, int size, struct tok_state *tok)
if (badchar) {
/* Need to add 1 to the line number, since this line
has not been counted, yet. */
PyErr_Format(PyExc_SyntaxError,
"Non-UTF-8 code starting with '\\x%.2x' "
"in file %.200s on line %i, "
"but no encoding declared; "
"see http://python.org/dev/peps/pep-0263/ for details",
badchar, tok->filename, tok->lineno + 1);
filename = PyUnicode_DecodeFSDefault(tok->filename);
if (filename != NULL) {
PyErr_Format(PyExc_SyntaxError,
"Non-UTF-8 code starting with '\\x%.2x' "
"in file %.200U on line %i, "
"but no encoding declared; "
"see http://python.org/dev/peps/pep-0263/ for details",
badchar, filename, tok->lineno + 1);
Py_DECREF(filename);
}
return error_ret(tok);
}
#endif