pybind/ceph_argparse: handle non ascii unicode args

we raise UnicodeDecodeError at seeing non-ascii args if we fail to match
it with any command signatures. instead, we should use a unicode string
for representing the error in that case. please note, the exception is not
printed at all in real-world. =)

Fixes: http://tracker.ceph.com/issues/12287
Signed-off-by: Kefu Chai <tchaikov@gmail.com>

src/pybind/ceph_argparse.py

@@ -529,23 +529,20 @@ def __init__(self, prefix=''):
 
     def valid(self, s, partial=False):
         try:
+            if partial:
+                if self.prefix.startswith(s):
+                    self.val = s
+                    return
+            else:
+                if s == self.prefix:
+                    self.val = s
+                    return
+            raise ArgumentPrefix(u'no match for {0}'.format(s))
+        except UnicodeDecodeError:
             # `prefix` can always be converted into unicode when being compared,
             # but `s` could be anything passed by user.
-            s = unicode(s)
-        except UnicodeDecodeError:
             raise ArgumentPrefix("no match for {0}".format(s))
 
-        if partial:
-            if self.prefix.startswith(s):
-                self.val = s
-                return
-        else:
-            if s == self.prefix:
-                self.val = s
-                return
-
-        raise ArgumentPrefix("no match for {0}".format(s))
-
     def __str__(self):
         return self.prefix
 

src/test/pybind/test_ceph_argparse.py

@@ -91,11 +91,17 @@ def check_no_arg(self, prefix, command):
 
 class TestBasic:
 
-	def test_non_ascii_in_non_options(self):
-		# unicode() is not able to convert this str parameter into unicode
-		# using the default encoding 'ascii'. and validate_command() should
-		# not choke on it.
-		assert_is_none(validate_command(sigdict, ['章鱼和鱿鱼']))
+    def test_non_ascii_in_non_options(self):
+        # ArgumentPrefix("no match for {0}".format(s)) is not able to convert
+        # unicode str parameter into str. and validate_command() should not
+        # choke on it.
+        assert_is_none(validate_command(sigdict, [u'章鱼和鱿鱼']))
+        assert_is_none(validate_command(sigdict, [u'–w']))
+        # actually we always pass unicode strings to validate_command() in "ceph"
+        # CLI, but we also use bytestrings in our tests, so make sure it does not
+        # break.
+        assert_is_none(validate_command(sigdict, ['章鱼和鱿鱼']))
+        assert_is_none(validate_command(sigdict, ['–w']))
 
 
 class TestPG(TestArgparse):