diff options
| author | Miss Islington (bot) <31488909+miss-islington@users.noreply.github.com> | 2023-11-27 18:57:34 (GMT) |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2023-11-27 18:57:34 (GMT) |
| commit | 7140716c883d8f40716543e827fa396609f39962 (patch) | |
| tree | 43cb67a31f3df4c667436797416ea844108f3f69 | |
| parent | 4463d2e01886824ccc7857205f6acb9a3d01d0ab (diff) | |
| download | cpython-7140716c883d8f40716543e827fa396609f39962.zip cpython-7140716c883d8f40716543e827fa396609f39962.tar.gz cpython-7140716c883d8f40716543e827fa396609f39962.tar.bz2 | |
[3.12] gh-112387: Fix error positions for decoded strings with backwards tokenize errors (GH-112409) (#112468)
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 00c5f62..5183aaa 100644 --- a/Lib/test/test_syntax.py +++ b/Lib/test/test_syntax.py @@ -2296,6 +2296,10 @@ 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 6390a66..e832422 100644 --- a/Parser/pegen_errors.c +++ b/Parser/pegen_errors.c @@ -276,6 +276,10 @@ 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 |