add a few more DecodedURL/parse tests and a couple comments

Author: mahmoud

hyperlink/_url.py

@@ -1517,7 +1517,7 @@ class DecodedURL(object):
     handled automatically.
 
     Where applicable, a UTF-8 encoding is presumed. Be advised that
-    some interactions, can raise :exc:`UnicodeEncodeErrors` and
+    some interactions can raise :exc:`UnicodeEncodeErrors` and
     :exc:`UnicodeDecodeErrors`, just like when working with
     bytestrings. Examples of such interactions include handling query
     strings encoding binary data, and paths containing segments with

hyperlink/test/test_decoded_url.py

@@ -60,8 +60,7 @@ def test_passthroughs(self):
         durl2 = DecodedURL.from_text(TOTAL_URL, lazy=True)
         assert durl2 == durl2.encoded_url.get_decoded_url(lazy=True)
 
-        # TODO change this to the actual value when str() changes get merged
-        assert '%20' in str(DecodedURL.from_text(BASIC_URL).child(' '))
+        assert str(DecodedURL.from_text(BASIC_URL).child(' ')) == 'http://example.com/%20'
 
         assert not (durl == 1)
         assert durl != 1
@@ -89,10 +88,11 @@ def test_query_manipulation(self):
 
         assert durl.set('arg', 'd').get('arg') == ['d']
 
-    def test_equivalences(self):
+    def test_equality_and_hashability(self):
         durl = DecodedURL.from_text(TOTAL_URL)
         durl2 = DecodedURL.from_text(TOTAL_URL)
         burl = DecodedURL.from_text(BASIC_URL)
+        durl_uri = durl.to_uri()
 
         assert durl == durl
         assert durl == durl2
@@ -106,6 +106,14 @@ def test_equivalences(self):
 
         assert len(durl_map) == 1
 
+        durl_map[burl] = burl
+
+        assert len(durl_map) == 2
+
+        durl_map[durl_uri] = durl_uri
+
+        assert len(durl_map) == 3
+
     def test_replace_roundtrip(self):
         durl = DecodedURL.from_text(TOTAL_URL)
 

hyperlink/test/test_parse.py

@@ -8,6 +8,8 @@
 BASIC_URL = 'http://example.com/#'
 TOTAL_URL = "https://%75%73%65%72:%00%00%00%[email protected]:8080/a/nice%20nice/./path/?zot=23%25&zut#frég"
 UNDECODABLE_FRAG_URL = TOTAL_URL + '%C3'
+# the %C3 above percent-decodes to an unpaired \xc3 byte which makes this
+# invalid utf8
 
 
 class TestURL(HyperlinkTestCase):