#18155: Regex-escape delimiter, in case it is a regex special char.

bitdancer · bitdancer · commit 925a3225708c · 2013-06-29T18:40:53.000-04:00
Patch by Vajrasky Kok, with slight modification to the tests by me.
diff --git a/Lib/csv.py b/Lib/csv.py
@@ -264,8 +264,9 @@ def _guess_quote_and_delimiter(self, data, delimiters):
 
         # if we see an extra quote between delimiters, we've got a
         # double quoted format
-        dq_regexp = re.compile(r"((%(delim)s)|^)\W*%(quote)s[^%(delim)s\n]*%(quote)s[^%(delim)s\n]*%(quote)s\W*((%(delim)s)|$)" % \
-                               {'delim':delim, 'quote':quotechar}, re.MULTILINE)
+        dq_regexp = re.compile(
+                               r"((%(delim)s)|^)\W*%(quote)s[^%(delim)s\n]*%(quote)s[^%(delim)s\n]*%(quote)s\W*((%(delim)s)|$)" % \
+                               {'delim':re.escape(delim), 'quote':quotechar}, re.MULTILINE)
 
 
 
diff --git a/Lib/test/test_csv.py b/Lib/test/test_csv.py
@@ -796,7 +796,7 @@ class TestSniffer(unittest.TestCase):
 'Tommy''s Place':'Blue Island':'IL':'12/28/02':'Blue Sunday/White Crow'
 'Stonecutters ''Seafood'' and Chop House':'Lemont':'IL':'12/19/02':'Week Back'
 """
-    header = '''\
+    header1 = '''\
 "venue","city","state","date","performers"
 '''
     sample3 = '''\
@@ -815,10 +815,35 @@ class TestSniffer(unittest.TestCase):
     sample6 = "a|b|c\r\nd|e|f\r\n"
     sample7 = "'a'|'b'|'c'\r\n'd'|e|f\r\n"
 
+# Issue 18155: Use a delimiter that is a special char to regex:
+
+    header2 = '''\
+"venue"+"city"+"state"+"date"+"performers"
+'''
+    sample8 = """\
+Harry's+ Arlington Heights+ IL+ 2/1/03+ Kimi Hayes
+Shark City+ Glendale Heights+ IL+ 12/28/02+ Prezence
+Tommy's Place+ Blue Island+ IL+ 12/28/02+ Blue Sunday/White Crow
+Stonecutters Seafood and Chop House+ Lemont+ IL+ 12/19/02+ Week Back
+"""
+    sample9 = """\
+'Harry''s'+ Arlington Heights'+ 'IL'+ '2/1/03'+ 'Kimi Hayes'
+'Shark City'+ Glendale Heights'+' IL'+ '12/28/02'+ 'Prezence'
+'Tommy''s Place'+ Blue Island'+ 'IL'+ '12/28/02'+ 'Blue Sunday/White Crow'
+'Stonecutters ''Seafood'' and Chop House'+ 'Lemont'+ 'IL'+ '12/19/02'+ 'Week Back'
+"""
+
     def test_has_header(self):
         sniffer = csv.Sniffer()
         self.assertEqual(sniffer.has_header(self.sample1), False)
-        self.assertEqual(sniffer.has_header(self.header+self.sample1), True)
+        self.assertEqual(sniffer.has_header(self.header1 + self.sample1),
+                         True)
+
+    def test_has_header_regex_special_delimiter(self):
+        sniffer = csv.Sniffer()
+        self.assertEqual(sniffer.has_header(self.sample8), False)
+        self.assertEqual(sniffer.has_header(self.header2 + self.sample8),
+                         True)
 
     def test_sniff(self):
         sniffer = csv.Sniffer()
@@ -852,13 +877,24 @@ def test_delimiters(self):
         dialect = sniffer.sniff(self.sample7)
         self.assertEqual(dialect.delimiter, "|")
         self.assertEqual(dialect.quotechar, "'")
+        dialect = sniffer.sniff(self.sample8)
+        self.assertEqual(dialect.delimiter, '+')
+        dialect = sniffer.sniff(self.sample9)
+        self.assertEqual(dialect.delimiter, '+')
+        self.assertEqual(dialect.quotechar, "'")
 
     def test_doublequote(self):
         sniffer = csv.Sniffer()
-        dialect = sniffer.sniff(self.header)
+        dialect = sniffer.sniff(self.header1)
+        self.assertFalse(dialect.doublequote)
+        dialect = sniffer.sniff(self.header2)
         self.assertFalse(dialect.doublequote)
         dialect = sniffer.sniff(self.sample2)
         self.assertTrue(dialect.doublequote)
+        dialect = sniffer.sniff(self.sample8)
+        self.assertFalse(dialect.doublequote)
+        dialect = sniffer.sniff(self.sample9)
+        self.assertTrue(dialect.doublequote)
 
 if not hasattr(sys, "gettotalrefcount"):
     if support.verbose: print("*** skipping leakage tests ***")
diff --git a/Misc/ACKS b/Misc/ACKS
@@ -656,6 +656,7 @@ Kubilay Kocak
 Greg Kochanski
 Damon Kohler
 Marko Kohtala
+Vajrasky Kok
 Guido Kollerie
 Jacek Konieczny
 Марк Коренберг
diff --git a/Misc/NEWS b/Misc/NEWS
@@ -38,6 +38,10 @@ Core and Builtins
 Library
 -------
 
+- Issue #18155: The csv module now correctly handles csv files that use
+  a delimter character that has a special meaning in regexes, instead of
+  throwing an exception.
+
 - Issue #14360: encode_quopri can now be successfully used as an encoder
   when constructing a MIMEApplication object.
 
@@ -50,7 +54,7 @@ Library
 
 - Issue #18259: Declare sethostname in socketmodule.c for AIX
 
-- Issue #18167: cgi.FieldStorage no more fails to handle multipart/form-data
+- Issue #18167: cgi.FieldStorage no longer fails to handle multipart/form-data
   when \r\n appears at end of 65535 bytes without other newlines.
 
 - subprocess: Prevent a possible double close of parent pipe fds when the
