gh-103925: Fix csv.Sniffer for a quoted field ending a CRLF line (GH-103926)

"$" does not match before "\r" even in the MULTILINE mode, so such a
field was not found and the delimiter was guessed from character
frequencies instead, which could give a letter.

Co-authored-by: Serhiy Storchaka <storchaka@gmail.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

diff --git a/Lib/csv.py b/Lib/csv.py
index b2aaf5fd9fa91e6a866c82fb02f07c95cd17b114..6cae34c705777ddd990cbe1d9381d2b4ae64c8e9 100644 (file)
--- a/Lib/csv.py
+++ b/Lib/csv.py
@@ -281,10 +281,10 @@ class Sniffer:
         import re
 
         matches = []
-        for restr in (r'(?P<delim>[^\w\n"\'])(?P<space> ?)(?P<quote>["\']).*?(?P=quote)(?P=delim)', # ,".*?",
-                      r'(?:^|\n)(?P<quote>["\']).*?(?P=quote)(?P<delim>[^\w\n"\'])(?P<space> ?)',   #  ".*?",
-                      r'(?P<delim>[^\w\n"\'])(?P<space> ?)(?P<quote>["\']).*?(?P=quote)(?:$|\n)',   # ,".*?"
-                      r'(?:^|\n)(?P<quote>["\']).*?(?P=quote)(?:$|\n)'):                            #  ".*?" (no delim, no space)
+        for restr in (r'(?P<delim>[^\w\n"\'])(?P<space> ?)(?P<quote>["\']).*?(?P=quote)(?P=delim)',   # ,".*?",
+                      r'(?:^|\n)(?P<quote>["\']).*?(?P=quote)(?P<delim>[^\w\n"\'])(?P<space> ?)',     #  ".*?",
+                      r'(?P<delim>[^\w\n"\'])(?P<space> ?)(?P<quote>["\']).*?(?P=quote)(?:$|\r|\n)',  # ,".*?"
+                      r'(?:^|\n)(?P<quote>["\']).*?(?P=quote)(?:$|\r|\n)'):                           #  ".*?" (no delim, no space)
             regexp = re.compile(restr, re.DOTALL | re.MULTILINE)
             matches = regexp.findall(data)
             if matches:

diff --git a/Lib/test/test_csv.py b/Lib/test/test_csv.py
index 7327c1bd5f505307cfab30451e870a730810d85e..2ab529b51c207d02dc7a01d5b427c35de41b0786 100644 (file)
--- a/Lib/test/test_csv.py
+++ b/Lib/test/test_csv.py
@@ -1415,6 +1415,9 @@ ghi\0jkl
     sample18.append("v,twenty_one")  # 'u' was not skipped
     sample18 = '\n'.join(sample18)
 
+    sample19 = ('time,title\r\n'
+                '2020-10-01,"Pocket - Save news, videos, stories and more"\r\n')
+
     def test_issue43625(self):
         sniffer = csv.Sniffer()
         self.assertTrue(sniffer.has_header(self.sample12))
@@ -1494,6 +1497,9 @@ ghi\0jkl
                                sniffer.sniff, self.sample15)
         self.assertRaisesRegex(csv.Error, "Could not determine delimiter",
                                sniffer.sniff, self.sample16)
+        dialect = sniffer.sniff(self.sample19)
+        self.assertEqual(dialect.delimiter, ',')
+        self.assertEqual(dialect.quotechar, '"')
 
     def test_doublequote(self):
         sniffer = csv.Sniffer()

diff --git a/Misc/NEWS.d/next/Library/2023-04-27-14-50-03.gh-issue-103925.khC-El.rst b/Misc/NEWS.d/next/Library/2023-04-27-14-50-03.gh-issue-103925.khC-El.rst
new file mode 100644 (file)
index 0000000..858ce6e
--- /dev/null
+++ b/Misc/NEWS.d/next/Library/2023-04-27-14-50-03.gh-issue-103925.khC-El.rst
@@ -0,0 +1,3 @@
+Fix :meth:`csv.Sniffer.sniff` for a sample with ``\r\n`` line endings in
+which a quoted field ends a line: a letter could be detected as the
+delimiter.