diff options
| author | Miss Islington (bot) <31488909+miss-islington@users.noreply.github.com> | 2023-11-27 19:05:20 (GMT) |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2023-11-27 19:05:20 (GMT) |
| commit | 390a5b81a97a36d5166a62e7850fadfe9eba3cc3 (patch) | |
| tree | 29de44b648d3d6c707f7b420c5b18352a283c154 | |
| parent | 43b081bfc49173405576b8eba09a6ca86aac641b (diff) | |
| download | cpython-390a5b81a97a36d5166a62e7850fadfe9eba3cc3.zip cpython-390a5b81a97a36d5166a62e7850fadfe9eba3cc3.tar.gz cpython-390a5b81a97a36d5166a62e7850fadfe9eba3cc3.tar.bz2 | |
[3.11] gh-112387: Fix error positions for decoded strings with backwards tokenize errors (GH-112409) (#112469)
gh-112387: Fix error positions for decoded strings with backwards tokenize errors (GH-112409)
(cherry picked from commit 45d648597b1146431bf3d91041e60d7f040e70bf)
Signed-off-by: Pablo Galindo <pablogsal@gmail.com>
Co-authored-by: Pablo Galindo Salgado <Pablogsal@gmail.com>
| -rw-r--r-- | Lib/test/test_syntax.py | 4 | ||||
| -rw-r--r-- | Misc/NEWS.d/next/Core and Builtins/2023-11-25-22-39-44.gh-issue-112387.AbBq5W.rst | 2 | ||||
| -rw-r--r-- | Parser/pegen_errors.c | 4 |
3 files changed, 10 insertions, 0 deletions
diff --git a/Lib/test/test_syntax.py b/Lib/test/test_syntax.py index bbd22ec..88d117f 100644 --- a/Lib/test/test_syntax.py +++ b/Lib/test/test_syntax.py @@ -2143,6 +2143,10 @@ func( """ self._check_error(code, "parenthesis '\\)' does not match opening parenthesis '\\['") + # Examples with dencodings + s = b'# coding=latin\n(aaaaaaaaaaaaaaaaa\naaaaaaaaaaa\xb5' + self._check_error(s, "'\(' was never closed") + def test_error_string_literal(self): self._check_error("'blech", "unterminated string literal") diff --git a/Misc/NEWS.d/next/Core and Builtins/2023-11-25-22-39-44.gh-issue-112387.AbBq5W.rst b/Misc/NEWS.d/next/Core and Builtins/2023-11-25-22-39-44.gh-issue-112387.AbBq5W.rst new file mode 100644 index 0000000..adac11b --- /dev/null +++ b/Misc/NEWS.d/next/Core and Builtins/2023-11-25-22-39-44.gh-issue-112387.AbBq5W.rst @@ -0,0 +1,2 @@ +Fix error positions for decoded strings with backwards tokenize errors. +Patch by Pablo Galindo diff --git a/Parser/pegen_errors.c b/Parser/pegen_errors.c index 29d5a6e..fb9fa29 100644 --- a/Parser/pegen_errors.c +++ b/Parser/pegen_errors.c @@ -270,6 +270,10 @@ get_error_line_from_tokenizer_buffers(Parser *p, Py_ssize_t lineno) Py_ssize_t relative_lineno = p->starting_lineno ? lineno - p->starting_lineno + 1 : lineno; const char* buf_end = p->tok->fp_interactive ? p->tok->interactive_src_end : p->tok->inp; + if (buf_end < cur_line) { + buf_end = cur_line + strlen(cur_line); + } + for (int i = 0; i < relative_lineno - 1; i++) { char *new_line = strchr(cur_line, '\n'); // The assert is here for debug builds but the conditional that |