diff options
| author | Victor Stinner <victor.stinner@haypocalc.com> | 2010-12-27 20:12:13 (GMT) |
|---|---|---|
| committer | Victor Stinner <victor.stinner@haypocalc.com> | 2010-12-27 20:12:13 (GMT) |
| commit | 83098a4095a66b6562db88802fec5ea108414d58 (patch) | |
| tree | c25cfb3b50826ccb72add185ab0623f516602cc0 /Parser | |
| parent | cb428f01625f99937b59431a53cc8f6013bd3cc2 (diff) | |
| download | cpython-83098a4095a66b6562db88802fec5ea108414d58.zip cpython-83098a4095a66b6562db88802fec5ea108414d58.tar.gz cpython-83098a4095a66b6562db88802fec5ea108414d58.tar.bz2 | |
Issue #10778: decoding_fgets() decodes the filename from the filesystem
encoding instead of UTF-8.
Diffstat (limited to 'Parser')
| -rw-r--r-- | Parser/tokenizer.c | 17 |
1 files changed, 11 insertions, 6 deletions
diff --git a/Parser/tokenizer.c b/Parser/tokenizer.c index 28dcea1..441d05a 100644 --- a/Parser/tokenizer.c +++ b/Parser/tokenizer.c @@ -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 |