bpo-35100: add unquote_to_bytes_plus to the urllib.parse module

Doc/library/urllib.parse.rst

@@ -603,6 +603,18 @@ task isn't already covered by the URL parsing functions above.
    Example: ``unquote_to_bytes('a%26%EF')`` yields ``b'a&\xef'``.
 
 
+.. function:: unquote_to_bytes_plus(string)
+
+   Like :func:`unquote_to_bytes`, but also replace plus signs with spaces, as
+   required for unquoting HTML form values.
+
+   *string* must be a :class:`str`.
+
+   Example: ``unquote_to_bytes_plus('/El+Ni%C3%B1o/')`` yields ``b'/El Ni\xc3\xb1o'``.
+
+   .. versionadded:: 3.9
+
+
 .. function:: urlencode(query, doseq=False, safe='', encoding=None, \
                         errors=None, quote_via=quote_plus)
 

Lib/test/test_urlparse.py

@@ -925,6 +925,12 @@ def test_unquote_to_bytes(self):
         result = urllib.parse.unquote_to_bytes('')
         self.assertEqual(result, b'')
 
+    def test_unquote_to_bytes_plus(self):
+        result = urllib.parse.unquote_to_bytes_plus('abc%20def')
+        self.assertEqual(result, b'abc def')
+        result = urllib.parse.unquote_to_bytes_plus('abc+def')
+        self.assertEqual(result, b'abc def')
+
     def test_quote_errors(self):
         self.assertRaises(TypeError, urllib.parse.quote, b'foo',
                           encoding='utf-8')

Lib/urllib/parse.py

@@ -36,8 +36,9 @@
            "urlsplit", "urlunsplit", "urlencode", "parse_qs",
            "parse_qsl", "quote", "quote_plus", "quote_from_bytes",
            "unquote", "unquote_plus", "unquote_to_bytes",
-           "DefragResult", "ParseResult", "SplitResult",
-           "DefragResultBytes", "ParseResultBytes", "SplitResultBytes"]
+           "unquote_to_bytes_plus", "DefragResult", "ParseResult",
+           "SplitResult", "DefragResultBytes", "ParseResultBytes",
+           "SplitResultBytes"]
 
 # A classification of schemes.
 # The empty string classifies URLs with no scheme specified,
@@ -755,6 +756,15 @@ def unquote_plus(string, encoding='utf-8', errors='replace'):
     string = string.replace('+', ' ')
     return unquote(string, encoding, errors)
 
+def unquote_to_bytes_plus(string):
+    """Like unquote_to_bytes(), but also replace plus signs with spaces, as
+    required for unquoting HTML form values.
+
+    unquote_to_bytes_plus('%7e/abc+def') -> b'~/abc def'
+    """
+    string = string.replace('+', ' ')
+    return unquote_to_bytes(string)
+
 _ALWAYS_SAFE = frozenset(b'ABCDEFGHIJKLMNOPQRSTUVWXYZ'
                          b'abcdefghijklmnopqrstuvwxyz'
                          b'0123456789'

Misc/NEWS.d/next/Library/2019-06-10-20-20-11.bpo-35100.kVNUfa.rst

@@ -0,0 +1 @@
+Add :func:`urllib.parse.unquote_to_bytes_plus`. Patch contributed by Andrew Gates.