mirror of
https://github.com/python/cpython
synced 2024-10-14 11:58:12 +00:00
Fix for problem with Sniffer class. If your delimiter is whitespace and the
last field was empty it would strip the delimiter and incorrectly guess that "" was the delimiter. Reported in c.l.py by Laurent Laporte. Will backport.
This commit is contained in:
parent
e08fa29d0e
commit
91bb70c5c0
|
@ -271,7 +271,7 @@ def _guess_delimiter(self, data, delimiters):
|
|||
for char in ascii:
|
||||
metaFrequency = charFrequency.get(char, {})
|
||||
# must count even if frequency is 0
|
||||
freq = line.strip().count(char)
|
||||
freq = line.count(char)
|
||||
# value is the mode
|
||||
metaFrequency[freq] = metaFrequency.get(freq, 0) + 1
|
||||
charFrequency[char] = metaFrequency
|
||||
|
|
|
@ -836,7 +836,6 @@ 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 = '''\
|
||||
"venue","city","state","date","performers"
|
||||
'''
|
||||
|
@ -852,6 +851,8 @@ class TestSniffer(unittest.TestCase):
|
|||
47483648;43.0;170;abc;def
|
||||
'''
|
||||
|
||||
sample5 = "aaa\tbbb\r\nAAA\t\r\nBBB\t\r\n"
|
||||
|
||||
def test_has_header(self):
|
||||
sniffer = csv.Sniffer()
|
||||
self.assertEqual(sniffer.has_header(self.sample1), False)
|
||||
|
@ -879,6 +880,8 @@ def test_delimiters(self):
|
|||
self.assertEqual(dialect.delimiter, "/")
|
||||
dialect = sniffer.sniff(self.sample4)
|
||||
self.assertEqual(dialect.delimiter, ";")
|
||||
dialect = sniffer.sniff(self.sample5)
|
||||
self.assertEqual(dialect.delimiter, "\t")
|
||||
|
||||
if not hasattr(sys, "gettotalrefcount"):
|
||||
if test_support.verbose: print "*** skipping leakage tests ***"
|
||||
|
|
Loading…
Reference in a new issue