bpo-16285: Update urllib quoting to RFC 3986

rtnpro · rtnpro · commit 41439a039dd3 · 2017-02-24T15:18:12.000+05:30
Initial work done by ctheune at http://bugs.python.org/file34950/0be3805cade1.diff.
diff --git a/Doc/library/urllib.parse.rst b/Doc/library/urllib.parse.rst
@@ -451,13 +451,17 @@ task isn't already covered by the URL parsing functions above.
 .. function:: quote(string, safe='/', encoding=None, errors=None)
 
    Replace special characters in *string* using the ``%xx`` escape. Letters,
-   digits, and the characters ``'_.-'`` are never quoted. By default, this
+   digits, and the characters ``'_.-~'`` are never quoted. By default, this
    function is intended for quoting the path section of URL. The optional *safe*
    parameter specifies additional ASCII characters that should not be quoted
    --- its default value is ``'/'``.
 
    *string* may be either a :class:`str` or a :class:`bytes`.
 
+   .. versionchanged:: 3.7
+      Moved from RFC 2396 to RFC 3986 for quoting URL strings. "~" is now
+      included in the set of reserved characters.
+
    The optional *encoding* and *errors* parameters specify how to deal with
    non-ASCII characters, as accepted by the :meth:`str.encode` method.
    *encoding* defaults to ``'utf-8'``.
diff --git a/Lib/test/test_urllib.py b/Lib/test/test_urllib.py
@@ -733,7 +733,7 @@ def test_short_content_raises_ContentTooShortError_without_reporthook(self):
 class QuotingTests(unittest.TestCase):
     r"""Tests for urllib.quote() and urllib.quote_plus()
 
-    According to RFC 2396 (Uniform Resource Identifiers), to escape a
+    According to RFC 3986 (Uniform Resource Identifiers), to escape a
     character you write it as '%' + <2 character US-ASCII hex value>.
     The Python code of ``'%' + hex(ord(<character>))[2:]`` escapes a
     character properly. Case does not matter on the hex letters.
@@ -761,7 +761,7 @@ def test_never_quote(self):
         do_not_quote = '' .join(["ABCDEFGHIJKLMNOPQRSTUVWXYZ",
                                  "abcdefghijklmnopqrstuvwxyz",
                                  "0123456789",
-                                 "_.-"])
+                                 "_.-~"])
         result = urllib.parse.quote(do_not_quote)
         self.assertEqual(do_not_quote, result,
                          "using quote(): %r != %r" % (do_not_quote, result))
diff --git a/Lib/urllib/parse.py b/Lib/urllib/parse.py
@@ -704,7 +704,7 @@ def unquote_plus(string, encoding='utf-8', errors='replace'):
 _ALWAYS_SAFE = frozenset(b'ABCDEFGHIJKLMNOPQRSTUVWXYZ'
                          b'abcdefghijklmnopqrstuvwxyz'
                          b'0123456789'
-                         b'_.-')
+                         b'_.-~')
 _ALWAYS_SAFE_BYTES = bytes(_ALWAYS_SAFE)
 _safe_quoters = {}
 
@@ -736,15 +736,18 @@ def quote(string, safe='/', encoding=None, errors=None):
     Each part of a URL, e.g. the path info, the query, etc., has a
     different set of reserved characters that must be quoted.
 
-    RFC 2396 Uniform Resource Identifiers (URI): Generic Syntax lists
+    RFC 3986 Uniform Resource Identifiers (URI): Generic Syntax lists
     the following reserved characters.
 
     reserved    = ";" | "/" | "?" | ":" | "@" | "&" | "=" | "+" |
-                  "$" | ","
+                  "$" | "," | "~"
 
     Each of these characters is reserved in some component of a URL,
     but not necessarily in all of them.
 
+    Python 3.7 updates from using RFC 2396 to RFC 3986 to quote URL strings.
+    Now, "~" is included in the set of reserved characters.
+
     By default, the quote function is intended for quoting the path
     section of a URL.  Thus, it will not encode '/'.  This character
     is reserved, but in typical usage the quote function is being
