diff options
author | R David Murray <rdmurray@bitdance.com> | 2013-06-29 22:40:53 (GMT) |
---|---|---|
committer | R David Murray <rdmurray@bitdance.com> | 2013-06-29 22:40:53 (GMT) |
commit | 925a3225708c40c8cd58a7475c5a6d3bd89db01d (patch) | |
tree | d55f128b7c4b5b6757c6d2c96f5e6a62a54a4243 /Lib/test/test_csv.py | |
parent | e4e530e7e8fa6883e553c898ea063dae82535fd1 (diff) | |
download | cpython-925a3225708c40c8cd58a7475c5a6d3bd89db01d.zip cpython-925a3225708c40c8cd58a7475c5a6d3bd89db01d.tar.gz cpython-925a3225708c40c8cd58a7475c5a6d3bd89db01d.tar.bz2 |
#18155: Regex-escape delimiter, in case it is a regex special char.
Patch by Vajrasky Kok, with slight modification to the tests by me.
Diffstat (limited to 'Lib/test/test_csv.py')
-rw-r--r-- | Lib/test/test_csv.py | 42 |
1 files changed, 39 insertions, 3 deletions
diff --git a/Lib/test/test_csv.py b/Lib/test/test_csv.py index 96f8aa7..5e28586 100644 --- a/Lib/test/test_csv.py +++ b/Lib/test/test_csv.py @@ -796,7 +796,7 @@ Stonecutters Seafood and Chop House, Lemont, IL, 12/19/02, Week Back '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 @@ Stonecutters Seafood and Chop House, Lemont, IL, 12/19/02, Week Back 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 @@ Stonecutters Seafood and Chop House, Lemont, IL, 12/19/02, Week Back 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 ***") |