Merged revisions 80004 via svnmerge from

svn+ssh://pythondev@svn.python.org/python/trunk

........
  r80004 | r.david.murray | 2010-04-12 12:35:19 -0400 (Mon, 12 Apr 2010) | 13 lines

  Issue #7585: use tab between components in unified and context diff headers.

  Instead of spaces between the filename and date (or whatever the string
  is that follows the filename, if any) use tabs.  This is what the unix
  'diff' command does, for example, and difflib was intended to follow
  the 'standard' way of doing diffs.  This improves compatibility with
  patch tools.  The docs and examples are also changed to recommended that
  the date format used be the ISO 8601 format, which is what modern diff
  tools emit by default.

  Patch by Anatoly Techtonik.
........

diff --git a/Doc/library/difflib.rst b/Doc/library/difflib.rst
index 433764c6c5711eebc48c20c5aa3fc66fe5dec733..566de72687b6592a3b0f32c6b33e01b604c3ae1e 100644 (file)
--- a/Doc/library/difflib.rst
+++ b/Doc/library/difflib.rst
@@ -140,8 +140,8 @@ diffs. For comparing directories and files, see also, the :mod:`filecmp` module.
 
    The context diff format normally has a header for filenames and modification
    times.  Any or all of these may be specified using strings for *fromfile*,
-   *tofile*, *fromfiledate*, and *tofiledate*. The modification times are normally
-   expressed in the format returned by :func:`time.ctime`.  If not specified, the
+   *tofile*, *fromfiledate*, and *tofiledate*.  The modification times are normally
+   expressed in the ISO 8601 format. If not specified, the
    strings default to blanks.
 
       >>> s1 = ['bacon\n', 'eggs\n', 'ham\n', 'guido\n']
@@ -272,8 +272,8 @@ diffs. For comparing directories and files, see also, the :mod:`filecmp` module.
 
    The context diff format normally has a header for filenames and modification
    times.  Any or all of these may be specified using strings for *fromfile*,
-   *tofile*, *fromfiledate*, and *tofiledate*. The modification times are normally
-   expressed in the format returned by :func:`time.ctime`.  If not specified, the
+   *tofile*, *fromfiledate*, and *tofiledate*.  The modification times are normally
+   expressed in the ISO 8601 format. If not specified, the
    strings default to blanks.
 
 

diff --git a/Lib/difflib.py b/Lib/difflib.py
index 292bba9ca9ff9e23f600eb33e299cc0919e0d0a4..92d58fab80ae01b4bc8549cabecc0d4b9cbdfd07 100644 (file)
--- a/Lib/difflib.py
+++ b/Lib/difflib.py
@@ -1160,18 +1160,18 @@ def unified_diff(a, b, fromfile='', tofile='', fromfiledate='',
 
     The unidiff format normally has a header for filenames and modification
     times.  Any or all of these may be specified using strings for
-    'fromfile', 'tofile', 'fromfiledate', and 'tofiledate'.  The modification
-    times are normally expressed in the format returned by time.ctime().
+    'fromfile', 'tofile', 'fromfiledate', and 'tofiledate'.
+    The modification times are normally expressed in the ISO 8601 format.
 
     Example:
 
     >>> for line in unified_diff('one two three four'.split(),
     ...             'zero one tree four'.split(), 'Original', 'Current',
-    ...             'Sat Jan 26 23:30:50 1991', 'Fri Jun 06 10:20:52 2003',
+    ...             '2005-01-26 23:30:50', '2010-04-02 10:20:52',
     ...             lineterm=''):
-    ...     print(line)
-    --- Original Sat Jan 26 23:30:50 1991
-    +++ Current Fri Jun 06 10:20:52 2003
+    ...     print(line)                 # doctest: +NORMALIZE_WHITESPACE
+    --- Original        2005-01-26 23:30:50
+    +++ Current         2010-04-02 10:20:52
     @@ -1,4 +1,4 @@
     +zero
      one
@@ -1184,8 +1184,10 @@ def unified_diff(a, b, fromfile='', tofile='', fromfiledate='',
     started = False
     for group in SequenceMatcher(None,a,b).get_grouped_opcodes(n):
         if not started:
-            yield '--- %s %s%s' % (fromfile, fromfiledate, lineterm)
-            yield '+++ %s %s%s' % (tofile, tofiledate, lineterm)
+            fromdate = '\t%s' % fromfiledate if fromfiledate else ''
+            todate = '\t%s' % tofiledate if tofiledate else ''
+            yield '--- %s%s%s' % (fromfile, fromdate, lineterm)
+            yield '+++ %s%s%s' % (tofile, todate, lineterm)
             started = True
         i1, i2, j1, j2 = group[0][1], group[-1][2], group[0][3], group[-1][4]
         yield "@@ -%d,%d +%d,%d @@%s" % (i1+1, i2-i1, j1+1, j2-j1, lineterm)
@@ -1223,17 +1225,16 @@ def context_diff(a, b, fromfile='', tofile='',
     The context diff format normally has a header for filenames and
     modification times.  Any or all of these may be specified using
     strings for 'fromfile', 'tofile', 'fromfiledate', and 'tofiledate'.
-    The modification times are normally expressed in the format returned
-    by time.ctime().  If not specified, the strings default to blanks.
+    The modification times are normally expressed in the ISO 8601 format.
+    If not specified, the strings default to blanks.
 
     Example:
 
     >>> print(''.join(context_diff('one\ntwo\nthree\nfour\n'.splitlines(1),
-    ...       'zero\none\ntree\nfour\n'.splitlines(1), 'Original', 'Current',
-    ...       'Sat Jan 26 23:30:50 1991', 'Fri Jun 06 10:22:46 2003')),
+    ...       'zero\none\ntree\nfour\n'.splitlines(1), 'Original', 'Current')),
     ...       end="")
-    *** Original Sat Jan 26 23:30:50 1991
-    --- Current Fri Jun 06 10:22:46 2003
+    *** Original
+    --- Current
     ***************
     *** 1,4 ****
       one
@@ -1251,8 +1252,10 @@ def context_diff(a, b, fromfile='', tofile='',
     prefixmap = {'insert':'+ ', 'delete':'- ', 'replace':'! ', 'equal':'  '}
     for group in SequenceMatcher(None,a,b).get_grouped_opcodes(n):
         if not started:
-            yield '*** %s %s%s' % (fromfile, fromfiledate, lineterm)
-            yield '--- %s %s%s' % (tofile, tofiledate, lineterm)
+            fromdate = '\t%s' % fromfiledate if fromfiledate else ''
+            todate = '\t%s' % tofiledate if tofiledate else ''
+            yield '*** %s%s%s' % (fromfile, fromdate, lineterm)
+            yield '--- %s%s%s' % (tofile, todate, lineterm)
             started = True
 
         yield '***************%s' % (lineterm,)

diff --git a/Lib/test/test_difflib.py b/Lib/test/test_difflib.py
index 852aae9b31e77a966cbf1f864a29f5d3957fad06..6c9bde61a4a5f27f16b4be8fd25011964b9d3907 100644 (file)
--- a/Lib/test/test_difflib.py
+++ b/Lib/test/test_difflib.py
@@ -159,10 +159,32 @@ class TestSFpatches(unittest.TestCase):
         difflib.SequenceMatcher(None, old, new).get_opcodes()
 
 
+class TestOutputFormat(unittest.TestCase):
+    def test_tab_delimiter(self):
+        args = ['one', 'two', 'Original', 'Current',
+            '2005-01-26 23:30:50', '2010-04-02 10:20:52']
+        ud = difflib.unified_diff(*args, lineterm='')
+        self.assertEqual(list(ud)[0:2], [
+                           "--- Original\t2005-01-26 23:30:50",
+                           "+++ Current\t2010-04-02 10:20:52"])
+        cd = difflib.context_diff(*args, lineterm='')
+        self.assertEqual(list(cd)[0:2], [
+                           "*** Original\t2005-01-26 23:30:50",
+                           "--- Current\t2010-04-02 10:20:52"])
+
+    def test_no_trailing_tab_on_empty_filedate(self):
+        args = ['one', 'two', 'Original', 'Current']
+        ud = difflib.unified_diff(*args, lineterm='')
+        self.assertEqual(list(ud)[0:2], ["--- Original", "+++ Current"])
+
+        cd = difflib.context_diff(*args, lineterm='')
+        self.assertEqual(list(cd)[0:2], ["*** Original", "--- Current"])
+
+
 def test_main():
     difflib.HtmlDiff._default_prefix = 0
     Doctests = doctest.DocTestSuite(difflib)
-    run_unittest(TestSFpatches, TestSFbugs, Doctests)
+    run_unittest(TestSFpatches, TestSFbugs, TestOutputFormat, Doctests)
 
 if __name__ == '__main__':
     test_main()

diff --git a/Misc/ACKS b/Misc/ACKS
index 845759594b40a0a53d879871b07845b39f3d0a64..d2c01aa9f591a097eb4b8925af8ad391bf38f29f 100644 (file)
--- a/Misc/ACKS
+++ b/Misc/ACKS
@@ -755,6 +755,7 @@ Christian Tanzer
 Steven Taschuk
 Monty Taylor
 Amy Taylor
+Anatoly Techtonik
 Tobias Thelen
 James Thomas
 Robin Thomas

diff --git a/Misc/NEWS b/Misc/NEWS
index e34d63e99bf780b1ab473f5472bf4ed110349461..8f80a967f9bff3546b20c1bf193b54ae41ca6b7f 100644 (file)
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -312,6 +312,10 @@ C-API
 Library
 -------
 
+- Issue #7585: difflib context and unified diffs now place a tab between
+  filename and date, conforming to the 'standards' they were originally
+  designed to follow.  This improves compatibility with patch tools.
+
 - Issue #7472: Fixed typo in email.encoders module; messages using ISO-2022
   character sets will now consistently use a Content-Transfer-Encoding of
   7bit rather than sometimes being marked as 8bit.