diff options
| -rw-r--r-- | Lib/csv.py | 13 | ||||
| -rw-r--r-- | Lib/test/test_csv.py | 7 |
2 files changed, 17 insertions, 3 deletions
@@ -152,10 +152,13 @@ class Sniffer: quotechar, delimiter, skipinitialspace = \ self._guess_quote_and_delimiter(sample, delimiters) - if delimiter is None: + if not delimiter: delimiter, skipinitialspace = self._guess_delimiter(sample, delimiters) + if not delimiter: + raise Error, "Could not determine delimiter" + class dialect(Dialect): _name = "sniffed" lineterminator = '\r\n' @@ -329,8 +332,12 @@ class Sniffer: data[0].count("%c " % d)) return (d, skipinitialspace) - # finally, just return the first damn character in the list - delim = delims.keys()[0] + # nothing else indicates a preference, pick the character that + # dominates(?) + items = [(v,k) for (k,v) in delims.items()] + items.sort() + delim = items[-1][1] + skipinitialspace = (data[0].count(delim) == data[0].count("%c " % delim)) return (delim, skipinitialspace) diff --git a/Lib/test/test_csv.py b/Lib/test/test_csv.py index 0ad77ef..8511a5a 100644 --- a/Lib/test/test_csv.py +++ b/Lib/test/test_csv.py @@ -852,6 +852,8 @@ Stonecutters Seafood and Chop House, Lemont, IL, 12/19/02, Week Back ''' sample5 = "aaa\tbbb\r\nAAA\t\r\nBBB\t\r\n" + sample6 = "a|b|c\r\nd|e|f\r\n" + sample7 = "'a'|'b'|'c'\r\n'd'|e|f\r\n" def test_has_header(self): sniffer = csv.Sniffer() @@ -882,6 +884,11 @@ Stonecutters Seafood and Chop House, Lemont, IL, 12/19/02, Week Back self.assertEqual(dialect.delimiter, ";") dialect = sniffer.sniff(self.sample5) self.assertEqual(dialect.delimiter, "\t") + dialect = sniffer.sniff(self.sample6) + self.assertEqual(dialect.delimiter, "|") + dialect = sniffer.sniff(self.sample7) + self.assertEqual(dialect.delimiter, "|") + self.assertEqual(dialect.quotechar, "'") if not hasattr(sys, "gettotalrefcount"): if test_support.verbose: print "*** skipping leakage tests ***" |