Patch from Thomas Barr so that csv.Sniffer will set doublequote property.

Closes issue 6606.

1 files changed, 17 insertions, 5 deletions

diff --git a/Lib/csv.py b/Lib/csv.py
index ff51a86..3db5dac 100644
--- a/Lib/csv.py
+++ b/Lib/csv.py
@@ -170,7 +170,7 @@ class Sniffer:
         Returns a dialect (or None) corresponding to the sample
         """
 
-        quotechar, delimiter, skipinitialspace = \
+        quotechar, doublequote, delimiter, skipinitialspace = \
                    self._guess_quote_and_delimiter(sample, delimiters)
         if not delimiter:
             delimiter, skipinitialspace = self._guess_delimiter(sample,
@@ -184,8 +184,8 @@ class Sniffer:
             lineterminator = '\r\n'
             quoting = QUOTE_MINIMAL
             # escapechar = ''
-            doublequote = False
 
+        dialect.doublequote = doublequote
         dialect.delimiter = delimiter
         # _csv.reader won't accept a quotechar of ''
         dialect.quotechar = quotechar or '"'
@@ -217,8 +217,8 @@ class Sniffer:
                 break
 
         if not matches:
-            return ('', None, 0) # (quotechar, delimiter, skipinitialspace)
-
+            # (quotechar, doublequote, delimiter, skipinitialspace)
+            return ('', False, None, 0)
         quotes = {}
         delims = {}
         spaces = 0
@@ -255,7 +255,19 @@ class Sniffer:
             delim = ''
             skipinitialspace = 0
 
-        return (quotechar, delim, skipinitialspace)
+        # 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)
+
+
+
+        if dq_regexp.search(data):
+            doublequote = True
+        else:
+            doublequote = False
+
+        return (quotechar, doublequote, delim, skipinitialspace)
 
 
     def _guess_delimiter(self, data, delimiters):