From 6933c4ace915d3143e79d90b918b6fd600c3d0e6 Mon Sep 17 00:00:00 2001 From: "Miss Islington (bot)" <31488909+miss-islington@users.noreply.github.com> Date: Thu, 25 Jul 2024 09:29:36 +0200 Subject: [PATCH] [3.13] gh-113785: csv: fields starting with escapechar are not quoted (GH-122110) (GH-122258) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit (cherry picked from commit a3327dbfd4db9e5ad1ca514963d503abbbbfede7) Co-authored-by: MikoĊ‚aj Kuranowski --- Lib/test/test_csv.py | 4 ++++ .../Library/2024-07-22-08-14-04.gh-issue-113785.6B_KNB.rst | 1 + Modules/_csv.c | 1 - 3 files changed, 5 insertions(+), 1 deletion(-) create mode 100644 Misc/NEWS.d/next/Library/2024-07-22-08-14-04.gh-issue-113785.6B_KNB.rst diff --git a/Lib/test/test_csv.py b/Lib/test/test_csv.py index d74ab7e016f..c718ee1203c 100644 --- a/Lib/test/test_csv.py +++ b/Lib/test/test_csv.py @@ -454,6 +454,10 @@ class Test_Csv(unittest.TestCase): quoting=csv.QUOTE_STRINGS) self._read_test(['1,@,3,@,5'], [['1', ',3,', '5']], quotechar='@') self._read_test(['1,\0,3,\0,5'], [['1', ',3,', '5']], quotechar='\0') + self._read_test(['1\\.5,\\.5,.5'], [[1.5, 0.5, 0.5]], + quoting=csv.QUOTE_NONNUMERIC, escapechar='\\') + self._read_test(['1\\.5,\\.5,"\\.5"'], [[1.5, 0.5, ".5"]], + quoting=csv.QUOTE_STRINGS, escapechar='\\') def test_read_skipinitialspace(self): self._read_test(['no space, space, spaces,\ttab'], diff --git a/Misc/NEWS.d/next/Library/2024-07-22-08-14-04.gh-issue-113785.6B_KNB.rst b/Misc/NEWS.d/next/Library/2024-07-22-08-14-04.gh-issue-113785.6B_KNB.rst new file mode 100644 index 00000000000..89d44a3f79c --- /dev/null +++ b/Misc/NEWS.d/next/Library/2024-07-22-08-14-04.gh-issue-113785.6B_KNB.rst @@ -0,0 +1 @@ +:mod:`csv` now correctly parses numeric fields (when used with :const:`csv.QUOTE_NONNUMERIC` or :const:`csv.QUOTE_STRINGS`) which start with an escape character. diff --git a/Modules/_csv.c b/Modules/_csv.c index 9d6b66d4938..8d35d3bcee3 100644 --- a/Modules/_csv.c +++ b/Modules/_csv.c @@ -749,7 +749,6 @@ parse_process_char(ReaderObj *self, _csvstate *module_state, Py_UCS4 c) } else if (c == dialect->escapechar) { /* possible escaped character */ - self->unquoted_field = false; self->state = ESCAPED_CHAR; } else if (c == ' ' && dialect->skipinitialspace)