Bug #735248: Fix urllib2.parse_http_list.

Lib/test/test_urllib2.py

@@ -45,6 +45,14 @@ def test_statudict(self):
         # test the new-in-2.5 httpresponses dictionary
         self.assertEquals(urllib2.httpresponses[404], "Not Found")
 
+    def test_parse_http_list(self):
+        tests = [('a,b,c', ['a', 'b', 'c']),
+                 ('path"o,l"og"i"cal, example', ['path"o,l"og"i"cal', 'example']),
+                 ('a, b, "c", "d", "e,f", g, h', ['a', 'b', '"c"', '"d"', '"e,f"', 'g', 'h']),
+                 ('a="b\\"c", d="e\\,f", g="h\\\\i"', ['a="b"c"', 'd="e,f"', 'g="h\\i"'])]
+        for string, list in tests:
+            self.assertEquals(urllib2.parse_http_list(string), list)
+
 
 class MockOpener:
     addheaders = []

Lib/urllib2.py

@@ -1072,46 +1072,43 @@ def parse_http_list(s):
     
     In particular, parse comma-separated lists where the elements of
     the list may include quoted-strings.  A quoted-string could
-    contain a comma.
+    contain a comma.  A non-quoted string could have quotes in the
+    middle.  Neither commas nor quotes count if they are escaped.
+    Only double-quotes count, not single-quotes.
     """
-    # XXX this function could probably use more testing
+    res = []
+    part = ''
 
-    list = []
+    escape = quote = False
-    end = len(s)
+    for cur in s:
-    i = 0
+        if escape:
-    inquote = 0
+            part += cur
-    start = 0
+            escape = False
-    while i < end:
+            continue
-        cur = s[i:]
+        if quote:
-        c = cur.find(',')
+            if cur == '\\':
-        q = cur.find('"')
+                escape = True
-        if c == -1:
-            list.append(s[start:])
-            break
-        if q == -1:
-            if inquote:
-                raise ValueError, "unbalanced quotes"
-            else:
-                list.append(s[start:i+c])
-                i = i + c + 1
                 continue
-        if inquote:
+            elif cur == '"':
-            if q < c:
+                quote = False
-                list.append(s[start:i+c])
+            part += cur
-                i = i + c + 1
+            continue
-                start = i
+
-                inquote = 0
+        if cur == ',':
-            else:
+            res.append(part)
-                i = i + q
+            part = ''
-        else:
+            continue
-            if c < q:
+
-                list.append(s[start:i+c])
+        if cur == '"':
-                i = i + c + 1
+            quote = True
-                start = i
+        
-            else:
+        part += cur
-                inquote = 1
+
-                i = i + q + 1
+    # append last part
-    return map(lambda x: x.strip(), list)
+    if part:
+        res.append(part)
+
+    return [part.strip() for part in res]
 
 class FileHandler(BaseHandler):
     # Use local file or FTP depending on form of URL