Issue python#15096: Drop support for the ur string prefix

Christian Heimes · Christian Heimes · commit 0b3847de6dbe · 2012-06-20T11:17:58.000+02:00
diff --git a/Doc/reference/lexical_analysis.rst b/Doc/reference/lexical_analysis.rst
@@ -401,7 +401,7 @@ String literals are described by the following lexical definitions:
 
 .. productionlist::
    stringliteral: [`stringprefix`](`shortstring` | `longstring`)
-   stringprefix: "r" | "u" | "ur" | "R" | "U" | "UR" | "Ur" | "uR"
+   stringprefix: "r" | "u" | "R" | "U"
    shortstring: "'" `shortstringitem`* "'" | '"' `shortstringitem`* '"'
    longstring: "'''" `longstringitem`* "'''" | '"""' `longstringitem`* '"""'
    shortstringitem: `shortstringchar` | `stringescapeseq`
@@ -444,19 +444,21 @@ must be expressed with escapes.
 As of Python 3.3 it is possible again to prefix unicode strings with a
 ``u`` prefix to simplify maintenance of dual 2.x and 3.x codebases.
 
-Both string and bytes literals may optionally be prefixed with a letter ``'r'``
+Bytes literals may optionally be prefixed with a letter ``'r'``
 or ``'R'``; such strings are called :dfn:`raw strings` and treat backslashes as
 literal characters.  As a result, in string literals, ``'\U'`` and ``'\u'``
-escapes in raw strings are not treated specially.
+escapes in raw strings are not treated specially. Given that Python 2.x's raw
+unicode literals behave differently than Python 3.x's the ``'ur'`` syntax
+is not supported.
 
    .. versionadded:: 3.3
       The ``'rb'`` prefix of raw bytes literals has been added as a synonym
       of ``'br'``.
 
    .. versionadded:: 3.3
-      Support for the unicode legacy literal (``u'value'``) and other
-      versions were reintroduced to simplify the maintenance of dual
-      Python 2.x and 3.x codebases.  See :pep:`414` for more information.
+      Support for the unicode legacy literal (``u'value'``) was reintroduced
+      to simplify the maintenance of dual Python 2.x and 3.x codebases.
+      See :pep:`414` for more information.
 
 In triple-quoted strings, unescaped newlines and quotes are allowed (and are
 retained), except that three unescaped quotes in a row terminate the string.  (A
diff --git a/Lib/test/test_strlit.py b/Lib/test/test_strlit.py
@@ -123,6 +123,15 @@ def test_eval_bytes_raw(self):
         self.assertRaises(SyntaxError, eval, """ rrb'' """)
         self.assertRaises(SyntaxError, eval, """ rbb'' """)
 
+    def test_eval_str_u(self):
+        self.assertEqual(eval(""" u'x' """), 'x')
+        self.assertEqual(eval(""" U'\u00e4' """), 'ä')
+        self.assertEqual(eval(""" u'\N{LATIN SMALL LETTER A WITH DIAERESIS}' """), 'ä')
+        self.assertRaises(SyntaxError, eval, """ ur'' """)
+        self.assertRaises(SyntaxError, eval, """ ru'' """)
+        self.assertRaises(SyntaxError, eval, """ bu'' """)
+        self.assertRaises(SyntaxError, eval, """ ub'' """)
+
     def check_encoding(self, encoding, extra=""):
         modname = "xx_" + encoding.replace("-", "_")
         fn = os.path.join(self.tmpdir, modname + ".py")
diff --git a/Lib/test/test_tokenize.py b/Lib/test/test_tokenize.py
@@ -299,24 +299,6 @@
     STRING     'u"abc"'      (1, 0) (1, 6)
     OP         '+'           (1, 7) (1, 8)
     STRING     'U"abc"'      (1, 9) (1, 15)
-    >>> dump_tokens("ur'abc' + uR'abc' + Ur'abc' + UR'abc'")
-    ENCODING   'utf-8'       (0, 0) (0, 0)
-    STRING     "ur'abc'"     (1, 0) (1, 7)
-    OP         '+'           (1, 8) (1, 9)
-    STRING     "uR'abc'"     (1, 10) (1, 17)
-    OP         '+'           (1, 18) (1, 19)
-    STRING     "Ur'abc'"     (1, 20) (1, 27)
-    OP         '+'           (1, 28) (1, 29)
-    STRING     "UR'abc'"     (1, 30) (1, 37)
-    >>> dump_tokens('ur"abc" + uR"abc" + Ur"abc" + UR"abc"')
-    ENCODING   'utf-8'       (0, 0) (0, 0)
-    STRING     'ur"abc"'     (1, 0) (1, 7)
-    OP         '+'           (1, 8) (1, 9)
-    STRING     'uR"abc"'     (1, 10) (1, 17)
-    OP         '+'           (1, 18) (1, 19)
-    STRING     'Ur"abc"'     (1, 20) (1, 27)
-    OP         '+'           (1, 28) (1, 29)
-    STRING     'UR"abc"'     (1, 30) (1, 37)
 
     >>> dump_tokens("b'abc' + B'abc'")
     ENCODING   'utf-8'       (0, 0) (0, 0)
@@ -642,15 +624,15 @@
 
 Legacy unicode literals:
 
-    >>> dump_tokens("Örter = u'places'\\ngrün = UR'green'")
+    >>> dump_tokens("Örter = u'places'\\ngrün = U'green'")
     ENCODING   'utf-8'       (0, 0) (0, 0)
     NAME       'Örter'       (1, 0) (1, 5)
     OP         '='           (1, 6) (1, 7)
     STRING     "u'places'"   (1, 8) (1, 17)
     NEWLINE    '\\n'          (1, 17) (1, 18)
     NAME       'grün'        (2, 0) (2, 4)
     OP         '='           (2, 5) (2, 6)
-    STRING     "UR'green'"   (2, 7) (2, 16)
+    STRING     "U'green'"    (2, 7) (2, 15)
 """
 
 from test import support
diff --git a/Lib/tokenize.py b/Lib/tokenize.py
@@ -127,7 +127,7 @@ def maybe(*choices): return group(*choices) + '?'
 Imagnumber = group(r'[0-9]+[jJ]', Floatnumber + r'[jJ]')
 Number = group(Imagnumber, Floatnumber, Intnumber)
 
-StringPrefix = r'(?:[uUbB][rR]?|[rR][bB]?)?'
+StringPrefix = r'(?:[bB][rR]?|[rR][bB]?|[uU])?'
 
 # Tail end of ' string.
 Single = r"[^'\\]*(?:\\.[^'\\]*)*'"
@@ -183,12 +183,8 @@ def _compile(expr):
            "rB'''": Single3, 'rB"""': Double3,
            "RB'''": Single3, 'RB"""': Double3,
            "u'''": Single3, 'u"""': Double3,
-           "ur'''": Single3, 'ur"""': Double3,
            "R'''": Single3, 'R"""': Double3,
            "U'''": Single3, 'U"""': Double3,
-           "uR'''": Single3, 'uR"""': Double3,
-           "Ur'''": Single3, 'Ur"""': Double3,
-           "UR'''": Single3, 'UR"""': Double3,
            'r': None, 'R': None, 'b': None, 'B': None,
            'u': None, 'U': None}
 
@@ -201,8 +197,7 @@ def _compile(expr):
           "rb'''", 'rb"""', "rB'''", 'rB"""',
           "Rb'''", 'Rb"""', "RB'''", 'RB"""',
           "u'''", 'u"""', "U'''", 'U"""',
-          "ur'''", 'ur"""', "Ur'''", 'Ur"""',
-          "uR'''", 'uR"""', "UR'''", 'UR"""'):
+          ):
     triple_quoted[t] = t
 single_quoted = {}
 for t in ("'", '"',
@@ -213,8 +208,7 @@ def _compile(expr):
           "rb'", 'rb"', "rB'", 'rB"',
           "Rb'", 'Rb"', "RB'", 'RB"' ,
           "u'", 'u"', "U'", 'U"',
-          "ur'", 'ur"', "Ur'", 'Ur"',
-          "uR'", 'uR"', "UR'", 'UR"' ):
+          ):
     single_quoted[t] = t
 
 tabsize = 8
diff --git a/Misc/NEWS b/Misc/NEWS
@@ -10,6 +10,9 @@ What's New in Python 3.3.0 Beta 1?
 Core and Builtins
 -----------------
 
+- Issue #15096: Removed support for ur'' as the raw notation isn't
+  compatible with Python 2.x's raw unicode strings.
+
 - Issue #13783: Generator objects now use the identifier APIs internally
 
 - Issue #14874: Restore charmap decoding speed to pre-PEP 393 levels.
diff --git a/Parser/tokenizer.c b/Parser/tokenizer.c
@@ -1412,7 +1412,7 @@ tok_get(register struct tok_state *tok, char **p_start, char **p_end)
     /* Identifier (most frequent token!) */
     nonascii = 0;
     if (is_potential_identifier_start(c)) {
-        /* Process b"", r"", u"", br"", rb"" and ur"" */
+        /* Process b"", r"", u"", br"" and rb"" */
         int saw_b = 0, saw_r = 0, saw_u = 0;
         while (1) {
             if (!(saw_b || saw_u) && (c == 'b' || c == 'B'))
@@ -1421,7 +1421,8 @@ tok_get(register struct tok_state *tok, char **p_start, char **p_end)
                want to support it in arbitrary order like byte literals. */
             else if (!(saw_b || saw_u || saw_r) && (c == 'u' || c == 'U'))
                 saw_u = 1;
-            else if (!saw_r && (c == 'r' || c == 'R'))
+            /* ur"" and ru"" are not supported */
+            else if (!(saw_r || saw_u) && (c == 'r' || c == 'R'))
                 saw_r = 1;
             else
                 break;
