Issue #23684: Clarify the return value of the scheme attribute of ParseResult and...

Patch by Martin Panter.

diff --git a/Doc/library/urllib.parse.rst b/Doc/library/urllib.parse.rst
index 154a521fa1e42ef0fc31a2a31dd103a84b95595f..fbbabcadf9df7abfd43757896f7df5fdcd7001dc 100644 (file)
--- a/Doc/library/urllib.parse.rst
+++ b/Doc/library/urllib.parse.rst
@@ -76,13 +76,15 @@ or on combining URL components into a URL string.
        ParseResult(scheme='', netloc='', path='help/Python.html', params='',
                   query='', fragment='')
 
-   If the *scheme* argument is specified, it gives the default addressing
-   scheme, to be used only if the URL does not specify one.  The default value for
-   this argument is the empty string.
+   The *scheme* argument gives the default addressing scheme, to be
+   used only if the URL does not specify one.  It should be the same type
+   (text or bytes) as *urlstring*, except that the default value ``''`` is
+   always allowed, and is automatically converted to ``b''`` if appropriate.
 
    If the *allow_fragments* argument is false, fragment identifiers are not
-   recognized and parsed as part of the preceding component.  The default value
-   for this argument is :const:`True`.
+   recognized.  Instead, they are parsed as part of the path, parameters
+   or query component, and :attr:`fragment` is set to the empty string in
+   the return value.
 
    The return value is actually an instance of a subclass of :class:`tuple`.  This
    class has the following additional read-only convenience attributes:
@@ -90,7 +92,7 @@ or on combining URL components into a URL string.
    +------------------+-------+--------------------------+----------------------+
    | Attribute        | Index | Value                    | Value if not present |
    +==================+=======+==========================+======================+
-   | :attr:`scheme`   | 0     | URL scheme specifier     | empty string         |
+   | :attr:`scheme`   | 0     | URL scheme specifier     | *scheme* parameter   |
    +------------------+-------+--------------------------+----------------------+
    | :attr:`netloc`   | 1     | Network location part    | empty string         |
    +------------------+-------+--------------------------+----------------------+
@@ -206,7 +208,7 @@ or on combining URL components into a URL string.
    +------------------+-------+-------------------------+----------------------+
    | Attribute        | Index | Value                   | Value if not present |
    +==================+=======+=========================+======================+
-   | :attr:`scheme`   | 0     | URL scheme specifier    | empty string         |
+   | :attr:`scheme`   | 0     | URL scheme specifier    | *scheme* parameter   |
    +------------------+-------+-------------------------+----------------------+
    | :attr:`netloc`   | 1     | Network location part   | empty string         |
    +------------------+-------+-------------------------+----------------------+

diff --git a/Lib/test/test_urlparse.py b/Lib/test/test_urlparse.py
index ad9820bf23e80e2107509275216c3c49f909ff47..1775ef33536655134a2851a9b510a74f16210004 100644 (file)
--- a/Lib/test/test_urlparse.py
+++ b/Lib/test/test_urlparse.py
@@ -663,6 +663,47 @@ class UrlParseTestCase(unittest.TestCase):
         self.assertEqual(urllib.parse.urlparse(b"x-newscheme://foo.com/stuff?query"),
                          (b'x-newscheme', b'foo.com', b'/stuff', b'', b'query', b''))
 
+    def test_default_scheme(self):
+        # Exercise the scheme parameter of urlparse() and urlsplit()
+        for func in (urllib.parse.urlparse, urllib.parse.urlsplit):
+            with self.subTest(function=func):
+                result = func("http://example.net/", "ftp")
+                self.assertEqual(result.scheme, "http")
+                result = func(b"http://example.net/", b"ftp")
+                self.assertEqual(result.scheme, b"http")
+                self.assertEqual(func("path", "ftp").scheme, "ftp")
+                self.assertEqual(func("path", scheme="ftp").scheme, "ftp")
+                self.assertEqual(func(b"path", scheme=b"ftp").scheme, b"ftp")
+                self.assertEqual(func("path").scheme, "")
+                self.assertEqual(func(b"path").scheme, b"")
+                self.assertEqual(func(b"path", "").scheme, b"")
+
+    def test_parse_fragments(self):
+        # Exercise the allow_fragments parameter of urlparse() and urlsplit()
+        tests = (
+            ("http:#frag", "path"),
+            ("//example.net#frag", "path"),
+            ("index.html#frag", "path"),
+            (";a=b#frag", "params"),
+            ("?a=b#frag", "query"),
+            ("#frag", "path"),
+        )
+        for url, attr in tests:
+            for func in (urllib.parse.urlparse, urllib.parse.urlsplit):
+                if attr == "params" and func is urllib.parse.urlsplit:
+                    attr = "path"
+                with self.subTest(url=url, function=func):
+                    result = func(url, allow_fragments=False)
+                    self.assertEqual(result.fragment, "")
+                    self.assertTrue(getattr(result, attr).endswith("#frag"))
+                    self.assertEqual(func(url, "", False).fragment, "")
+
+                    result = func(url, allow_fragments=True)
+                    self.assertEqual(result.fragment, "frag")
+                    self.assertFalse(getattr(result, attr).endswith("frag"))
+                    self.assertEqual(func(url, "", True).fragment, "frag")
+                    self.assertEqual(func(url).fragment, "frag")
+
     def test_mixed_types_rejected(self):
         # Several functions that process either strings or ASCII encoded bytes
         # accept multiple arguments. Check they reject mixed type input