From 9a40c68b694721508f34b3c2d4bccce6bb502087 Mon Sep 17 00:00:00 2001 From: Skip Montanaro Date: Fri, 30 Dec 2005 05:09:48 +0000 Subject: Fix a delimiter detection problem in sniffer. Sniffing "a|b|c\r\n" was returning 'a' as the delimiter. It now returns '|', but not because I understood better what the code was supposed to do. Would someone that understands the idea behind _guess_delimiter() (see its doc string) look to see if my fallback choice is better than before or if it's just serendipity that I picked the proper delimiter? --- Lib/csv.py | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) (limited to 'Lib/csv.py') diff --git a/Lib/csv.py b/Lib/csv.py index 7516380083..f213854783 100644 --- a/Lib/csv.py +++ b/Lib/csv.py @@ -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) -- cgit v1.2.1