bpo-32308: Replace empty matches adjacent to a previous non-empty match in re.sub(). (#4846)

6 files changed, 35 insertions, 25 deletions

diff --git a/Doc/howto/regex.rst b/Doc/howto/regex.rst
index fa8c693..87a6b1a 100644
--- a/Doc/howto/regex.rst
+++ b/Doc/howto/regex.rst
@@ -1140,12 +1140,12 @@ new string value and the number of replacements  that were performed::
    >>> p.subn('colour', 'no colours at all')
    ('no colours at all', 0)
 
-Empty matches are replaced only when they're not adjacent to a previous match.
+Empty matches are replaced only when they're not adjacent to a previous empty match.
 ::
 
    >>> p = re.compile('x*')
    >>> p.sub('-', 'abxd')
-   '-a-b-d-'
+   '-a-b--d-'
 
 If *replacement* is a string, any backslash escapes in it are processed.  That
 is, ``\n`` is converted to a single newline character, ``\r`` is converted to a
diff --git a/Doc/library/re.rst b/Doc/library/re.rst
index dae1d7e..9b175f4 100644
--- a/Doc/library/re.rst
+++ b/Doc/library/re.rst
@@ -708,12 +708,15 @@ form.
    That way, separator components are always found at the same relative
    indices within the result list.
 
-   The pattern can match empty strings. ::
+   Empty matches for the pattern split the string only when not adjacent
+   to a previous empty match.
 
       >>> re.split(r'\b', 'Words, words, words.')
       ['', 'Words', ', ', 'words', ', ', 'words', '.']
+      >>> re.split(r'\W*', '...words...')
+      ['', '', 'w', 'o', 'r', 'd', 's', '', '']
       >>> re.split(r'(\W*)', '...words...')
-      ['', '...', 'w', '', 'o', '', 'r', '', 'd', '', 's', '...', '']
+      ['', '...', '', '', 'w', '', 'o', '', 'r', '', 'd', '', 's', '...', '', '', '']
 
    .. versionchanged:: 3.1
       Added the optional flags argument.
@@ -778,8 +781,8 @@ form.
    The optional argument *count* is the maximum number of pattern occurrences to be
    replaced; *count* must be a non-negative integer.  If omitted or zero, all
    occurrences will be replaced. Empty matches for the pattern are replaced only
-   when not adjacent to a previous match, so ``sub('x*', '-', 'abc')`` returns
-   ``'-a-b-c-'``.
+   when not adjacent to a previous empty match, so ``sub('x*', '-', 'abxd')`` returns
+   ``'-a-b--d-'``.
 
    In string-type *repl* arguments, in addition to the character escapes and
    backreferences described above,
@@ -805,6 +808,9 @@ form.
       Unknown escapes in *repl* consisting of ``'\'`` and an ASCII letter
       now are errors.
 
+      Empty matches for the pattern are replaced when adjacent to a previous
+      non-empty match.
+
 
 .. function:: subn(pattern, repl, string, count=0, flags=0)
 
diff --git a/Doc/whatsnew/3.7.rst b/Doc/whatsnew/3.7.rst
index 1924881..1311e9e 100644
--- a/Doc/whatsnew/3.7.rst
+++ b/Doc/whatsnew/3.7.rst
@@ -881,8 +881,9 @@ Changes in the Python API
 * The result of splitting a string on a :mod:`regular expression <re>`
   that could match an empty string has been changed.  For example
   splitting on ``r'\s*'`` will now split not only on whitespaces as it
-  did previously, but also between any pair of non-whitespace
-  characters.  The previous behavior can be restored by changing the pattern
+  did previously, but also on empty strings before all non-whitespace
+  characters and just before the end of the string.
+  The previous behavior can be restored by changing the pattern
   to ``r'\s+'``.  A :exc:`FutureWarning` was emitted for such patterns since
   Python 3.5.
 
@@ -893,7 +894,13 @@ Changes in the Python API
   positions 2--3.  To match only blank lines, the pattern should be rewritten
   as ``r'(?m)^[^\S\n]*$'``.
 
-  (Contributed by Serhiy Storchaka in :issue:`25054`.)
+  :func:`re.sub()` now replaces empty matches adjacent to a previous
+  non-empty match.  For example ``re.sub('x*', '-', 'abxd')`` returns now
+  ``'-a-b--d-'`` instead of ``'-a-b--d-'`` (the first minus between 'b' and
+  'd' replaces 'x', and the second minus replaces an empty string between
+  'x' and 'd').
+
+  (Contributed by Serhiy Storchaka in :issue:`25054` and :issue:`32308`.)
 
 * :class:`tracemalloc.Traceback` frames are now sorted from oldest to most
   recent to be more consistent with :mod:`traceback`.
diff --git a/Lib/test/test_re.py b/Lib/test/test_re.py
index aaed3d8..9fed4be 100644
--- a/Lib/test/test_re.py
+++ b/Lib/test/test_re.py
@@ -213,11 +213,6 @@ class ReTests(unittest.TestCase):
         self.assertEqual(re.sub(r'(\S)\s+(\S)', r'\1 \2', 'hello  there'),
                          'hello there')
 
-    def test_bug_462270(self):
-        # Test for empty sub() behaviour, see SF bug #462270
-        self.assertEqual(re.sub('x*', '-', 'abxd'), '-a-b-d-')
-        self.assertEqual(re.sub('x+', '-', 'abxd'), 'ab-d')
-
     def test_symbolic_groups(self):
         re.compile(r'(?P<a>x)(?P=a)(?(a)y)')
         re.compile(r'(?P<a1>x)(?P=a1)(?(a1)y)')
@@ -331,10 +326,10 @@ class ReTests(unittest.TestCase):
                          ['', 'a', '', '', 'c'])
 
         for sep, expected in [
-            (':*', ['', 'a', 'b', 'c', '']),
-            ('(?::*)', ['', 'a', 'b', 'c', '']),
-            ('(:*)', ['', ':', 'a', ':', 'b', '::', 'c', '', '']),
-            ('(:)*', ['', ':', 'a', ':', 'b', ':', 'c', None, '']),
+            (':*', ['', '', 'a', '', 'b', '', 'c', '']),
+            ('(?::*)', ['', '', 'a', '', 'b', '', 'c', '']),
+            ('(:*)', ['', ':', '', '', 'a', ':', '', '', 'b', '::', '', '', 'c', '', '']),
+            ('(:)*', ['', ':', '', None, 'a', ':', '', None, 'b', ':', '', None, 'c', None, '']),
         ]:
             with self.subTest(sep=sep):
                 self.assertTypedEqual(re.split(sep, ':a:b::c'), expected)
@@ -357,7 +352,7 @@ class ReTests(unittest.TestCase):
         self.assertEqual(re.split("(:+)", ":a:b::c", maxsplit=2),
                          ['', ':', 'a', ':', 'b::c'])
         self.assertEqual(re.split("(:*)", ":a:b::c", maxsplit=2),
-                         ['', ':', 'a', ':', 'b::c'])
+                         ['', ':', '', '', 'a:b::c'])
 
     def test_re_findall(self):
         self.assertEqual(re.findall(":+", "abc"), [])
@@ -1753,13 +1748,13 @@ class ReTests(unittest.TestCase):
     def test_zerowidth(self):
         # Issues 852532, 1647489, 3262, 25054.
         self.assertEqual(re.split(r"\b", "a::bc"), ['', 'a', '::', 'bc', ''])
-        self.assertEqual(re.split(r"\b|:+", "a::bc"), ['', 'a', '', 'bc', ''])
-        self.assertEqual(re.split(r"(?<!\w)(?=\w)|:+", "a::bc"), ['', 'a', 'bc'])
+        self.assertEqual(re.split(r"\b|:+", "a::bc"), ['', 'a', '', '', 'bc', ''])
+        self.assertEqual(re.split(r"(?<!\w)(?=\w)|:+", "a::bc"), ['', 'a', '', 'bc'])
         self.assertEqual(re.split(r"(?<=\w)(?!\w)|:+", "a::bc"), ['a', '', 'bc', ''])
 
         self.assertEqual(re.sub(r"\b", "-", "a::bc"), '-a-::-bc-')
-        self.assertEqual(re.sub(r"\b|:+", "-", "a::bc"), '-a--bc-')
-        self.assertEqual(re.sub(r"(\b|:+)", r"[\1]", "a::bc"), '[]a[][::]bc[]')
+        self.assertEqual(re.sub(r"\b|:+", "-", "a::bc"), '-a---bc-')
+        self.assertEqual(re.sub(r"(\b|:+)", r"[\1]", "a::bc"), '[]a[][::][]bc[]')
 
         self.assertEqual(re.findall(r"\b|:+", "a::bc"), ['', '', '::', '', ''])
         self.assertEqual(re.findall(r"\b|\w+", "a::bc"),
diff --git a/Misc/NEWS.d/next/Library/2017-12-13-20-31-30.bpo-32308.CUbsb2.rst b/Misc/NEWS.d/next/Library/2017-12-13-20-31-30.bpo-32308.CUbsb2.rst
new file mode 100644
index 0000000..d760d608
--- /dev/null
+++ b/Misc/NEWS.d/next/Library/2017-12-13-20-31-30.bpo-32308.CUbsb2.rst
@@ -0,0 +1,2 @@
+:func:`re.sub()` now replaces empty matches adjacent to a previous non-empty
+match.
diff --git a/Modules/_sre.c b/Modules/_sre.c
index 68fc523..b6be6f6 100644
--- a/Modules/_sre.c
+++ b/Modules/_sre.c
@@ -955,7 +955,7 @@ _sre_SRE_Pattern_split_impl(PatternObject *self, PyObject *string,
         }
 
         n = n + 1;
-        state.must_advance = 1;
+        state.must_advance = (state.ptr == state.start);
         last = state.start = state.ptr;
 
     }
@@ -1109,7 +1109,7 @@ pattern_subx(PatternObject* self, PyObject* ptemplate, PyObject* string,
 
         i = e;
         n = n + 1;
-        state.must_advance = 1;
+        state.must_advance = (state.ptr == state.start);
         state.start = state.ptr;
     }