Patch #624325: urlparse.urlparse() and urlparse.urlsplit() results

now sport attributes that provide access to the parts of the result.

2 files changed, 216 insertions, 10 deletions

diff --git a/Lib/test/test_urlparse.py b/Lib/test/test_urlparse.py
index 39ada06..5cee458 100644
--- a/Lib/test/test_urlparse.py
+++ b/Lib/test/test_urlparse.py
@@ -12,15 +12,53 @@ class UrlParseTestCase(unittest.TestCase):
     def checkRoundtrips(self, url, parsed, split):
         result = urlparse.urlparse(url)
         self.assertEqual(result, parsed)
+        t = (result.scheme, result.netloc, result.path,
+             result.params, result.query, result.fragment)
+        self.assertEqual(t, parsed)
         # put it back together and it should be the same
         result2 = urlparse.urlunparse(result)
         self.assertEqual(result2, url)
+        self.assertEqual(result2, result.geturl())
+
+        # the result of geturl() is a fixpoint; we can always parse it
+        # again to get the same result:
+        result3 = urlparse.urlparse(result.geturl())
+        self.assertEqual(result3.geturl(), result.geturl())
+        self.assertEqual(result3,          result)
+        self.assertEqual(result3.scheme,   result.scheme)
+        self.assertEqual(result3.netloc,   result.netloc)
+        self.assertEqual(result3.path,     result.path)
+        self.assertEqual(result3.params,   result.params)
+        self.assertEqual(result3.query,    result.query)
+        self.assertEqual(result3.fragment, result.fragment)
+        self.assertEqual(result3.username, result.username)
+        self.assertEqual(result3.password, result.password)
+        self.assertEqual(result3.hostname, result.hostname)
+        self.assertEqual(result3.port,     result.port)
 
         # check the roundtrip using urlsplit() as well
         result = urlparse.urlsplit(url)
         self.assertEqual(result, split)
+        t = (result.scheme, result.netloc, result.path,
+             result.query, result.fragment)
+        self.assertEqual(t, split)
         result2 = urlparse.urlunsplit(result)
         self.assertEqual(result2, url)
+        self.assertEqual(result2, result.geturl())
+
+        # check the fixpoint property of re-parsing the result of geturl()
+        result3 = urlparse.urlsplit(result.geturl())
+        self.assertEqual(result3.geturl(), result.geturl())
+        self.assertEqual(result3,          result)
+        self.assertEqual(result3.scheme,   result.scheme)
+        self.assertEqual(result3.netloc,   result.netloc)
+        self.assertEqual(result3.path,     result.path)
+        self.assertEqual(result3.query,    result.query)
+        self.assertEqual(result3.fragment, result.fragment)
+        self.assertEqual(result3.username, result.username)
+        self.assertEqual(result3.password, result.password)
+        self.assertEqual(result3.hostname, result.hostname)
+        self.assertEqual(result3.port,     result.port)
 
     def test_roundtrips(self):
         testcases = [
@@ -187,6 +225,69 @@ class UrlParseTestCase(unittest.TestCase):
             ]:
             self.assertEqual(urlparse.urldefrag(url), (defrag, frag))
 
+    def test_urlsplit_attributes(self):
+        url = "HTTP://WWW.PYTHON.ORG/doc/#frag"
+        p = urlparse.urlsplit(url)
+        self.assertEqual(p.scheme, "http")
+        self.assertEqual(p.netloc, "WWW.PYTHON.ORG")
+        self.assertEqual(p.path, "/doc/")
+        self.assertEqual(p.query, "")
+        self.assertEqual(p.fragment, "frag")
+        self.assertEqual(p.username, None)
+        self.assertEqual(p.password, None)
+        self.assertEqual(p.hostname, "www.python.org")
+        self.assertEqual(p.port, None)
+        # geturl() won't return exactly the original URL in this case
+        # since the scheme is always case-normalized
+        #self.assertEqual(p.geturl(), url)
+
+        url = "http://User:Pass@www.python.org:080/doc/?query=yes#frag"
+        p = urlparse.urlsplit(url)
+        self.assertEqual(p.scheme, "http")
+        self.assertEqual(p.netloc, "User:Pass@www.python.org:080")
+        self.assertEqual(p.path, "/doc/")
+        self.assertEqual(p.query, "query=yes")
+        self.assertEqual(p.fragment, "frag")
+        self.assertEqual(p.username, "User")
+        self.assertEqual(p.password, "Pass")
+        self.assertEqual(p.hostname, "www.python.org")
+        self.assertEqual(p.port, 80)
+        self.assertEqual(p.geturl(), url)
+
+    def test_attributes_bad_port(self):
+        """Check handling of non-integer ports."""
+        p = urlparse.urlsplit("http://www.example.net:foo")
+        self.assertEqual(p.netloc, "www.example.net:foo")
+        self.assertRaises(ValueError, lambda: p.port)
+
+        p = urlparse.urlparse("http://www.example.net:foo")
+        self.assertEqual(p.netloc, "www.example.net:foo")
+        self.assertRaises(ValueError, lambda: p.port)
+
+    def test_attributes_without_netloc(self):
+        # This example is straight from RFC 3261.  It looks like it
+        # should allow the username, hostname, and port to be filled
+        # in, but doesn't.  Since it's a URI and doesn't use the
+        # scheme://netloc syntax, the netloc and related attributes
+        # should be left empty.
+        uri = "sip:alice@atlanta.com;maddr=239.255.255.1;ttl=15"
+        p = urlparse.urlsplit(uri)
+        self.assertEqual(p.netloc, "")
+        self.assertEqual(p.username, None)
+        self.assertEqual(p.password, None)
+        self.assertEqual(p.hostname, None)
+        self.assertEqual(p.port, None)
+        self.assertEqual(p.geturl(), uri)
+
+        p = urlparse.urlparse(uri)
+        self.assertEqual(p.netloc, "")
+        self.assertEqual(p.username, None)
+        self.assertEqual(p.password, None)
+        self.assertEqual(p.hostname, None)
+        self.assertEqual(p.port, None)
+        self.assertEqual(p.geturl(), uri)
+
+
 def test_main():
     test_support.run_unittest(UrlParseTestCase)
 
diff --git a/Lib/urlparse.py b/Lib/urlparse.py
index 8d44853..eade040 100644
--- a/Lib/urlparse.py
+++ b/Lib/urlparse.py
@@ -41,7 +41,111 @@ def clear_cache():
     _parse_cache = {}
 
 
-def urlparse(url, scheme='', allow_fragments=1):
+class BaseResult(tuple):
+    """Base class for the parsed result objects.
+
+    This provides the attributes shared by the two derived result
+    objects as read-only properties.  The derived classes are
+    responsible for checking the right number of arguments were
+    supplied to the constructor.
+
+    """
+
+    __slots__ = ()
+
+    # Attributes that access the basic components of the URL:
+
+    @property
+    def scheme(self):
+        return self[0]
+
+    @property
+    def netloc(self):
+        return self[1]
+
+    @property
+    def path(self):
+        return self[2]
+
+    @property
+    def query(self):
+        return self[-2]
+
+    @property
+    def fragment(self):
+        return self[-1]
+
+    # Additional attributes that provide access to parsed-out portions
+    # of the netloc:
+
+    @property
+    def username(self):
+        netloc = self.netloc
+        if "@" in netloc:
+            userinfo = netloc.split("@", 1)[0]
+            if ":" in userinfo:
+                userinfo = userinfo.split(":", 1)[0]
+            return userinfo
+        return None
+
+    @property
+    def password(self):
+        netloc = self.netloc
+        if "@" in netloc:
+            userinfo = netloc.split("@", 1)[0]
+            if ":" in userinfo:
+                return userinfo.split(":", 1)[1]
+        return None
+
+    @property
+    def hostname(self):
+        netloc = self.netloc
+        if "@" in netloc:
+            netloc = netloc.split("@", 1)[1]
+        if ":" in netloc:
+            netloc = netloc.split(":", 1)[0]
+        return netloc.lower() or None
+
+    @property
+    def port(self):
+        netloc = self.netloc
+        if "@" in netloc:
+            netloc = netloc.split("@", 1)[1]
+        if ":" in netloc:
+            port = netloc.split(":", 1)[1]
+            return int(port, 10)
+        return None
+
+
+class SplitResult(BaseResult):
+
+    __slots__ = ()
+
+    def __new__(cls, scheme, netloc, path, query, fragment):
+        return BaseResult.__new__(
+            cls, (scheme, netloc, path, query, fragment))
+
+    def geturl(self):
+        return urlunsplit(self)
+
+
+class ParseResult(BaseResult):
+
+    __slots__ = ()
+
+    def __new__(cls, scheme, netloc, path, params, query, fragment):
+        return BaseResult.__new__(
+            cls, (scheme, netloc, path, params, query, fragment))
+
+    @property
+    def params(self):
+        return self[3]
+
+    def geturl(self):
+        return urlunparse(self)
+
+
+def urlparse(url, scheme='', allow_fragments=True):
     """Parse a URL into 6 components:
     <scheme>://<netloc>/<path>;<params>?<query>#<fragment>
     Return a 6-tuple: (scheme, netloc, path, params, query, fragment).
@@ -53,7 +157,7 @@ def urlparse(url, scheme='', allow_fragments=1):
         url, params = _splitparams(url)
     else:
         params = ''
-    return scheme, netloc, url, params, query, fragment
+    return ParseResult(scheme, netloc, url, params, query, fragment)
 
 def _splitparams(url):
     if '/'  in url:
@@ -73,12 +177,13 @@ def _splitnetloc(url, start=0):
         delim = len(url)
     return url[start:delim], url[delim:]
 
-def urlsplit(url, scheme='', allow_fragments=1):
+def urlsplit(url, scheme='', allow_fragments=True):
     """Parse a URL into 5 components:
     <scheme>://<netloc>/<path>?<query>#<fragment>
     Return a 5-tuple: (scheme, netloc, path, query, fragment).
     Note that we don't break the components up in smaller bits
     (e.g. netloc is a single string) and we don't expand % escapes."""
+    allow_fragments = bool(allow_fragments)
     key = url, scheme, allow_fragments
     cached = _parse_cache.get(key, None)
     if cached:
@@ -97,9 +202,9 @@ def urlsplit(url, scheme='', allow_fragments=1):
                 url, fragment = url.split('#', 1)
             if '?' in url:
                 url, query = url.split('?', 1)
-            tuple = scheme, netloc, url, query, fragment
-            _parse_cache[key] = tuple
-            return tuple
+            v = SplitResult(scheme, netloc, url, query, fragment)
+            _parse_cache[key] = v
+            return v
         for c in url[:i]:
             if c not in scheme_chars:
                 break
@@ -111,9 +216,9 @@ def urlsplit(url, scheme='', allow_fragments=1):
         url, fragment = url.split('#', 1)
     if scheme in uses_query and '?' in url:
         url, query = url.split('?', 1)
-    tuple = scheme, netloc, url, query, fragment
-    _parse_cache[key] = tuple
-    return tuple
+    v = SplitResult(scheme, netloc, url, query, fragment)
+    _parse_cache[key] = v
+    return v
 
 def urlunparse((scheme, netloc, url, params, query, fragment)):
     """Put a parsed URL back together again.  This may result in a
@@ -136,7 +241,7 @@ def urlunsplit((scheme, netloc, url, query, fragment)):
         url = url + '#' + fragment
     return url
 
-def urljoin(base, url, allow_fragments = 1):
+def urljoin(base, url, allow_fragments=True):
     """Join a base URL and a possibly relative URL to form an absolute
     interpretation of the latter."""
     if not base: