Issue 11747: Fix output format for context diffs.

Lib/difflib.py

@@ -1140,6 +1140,21 @@ def IS_CHARACTER_JUNK(ch, ws=" \t"):
     return ch in ws
 
 
+########################################################################
+###  Unified Diff
+########################################################################
+
+def _format_range_unified(start, stop):
+    'Convert range to the "ed" format'
+    # Per the diff spec at http://www.unix.org/single_unix_specification/
+    beginning = start + 1     # lines start numbering with one
+    length = stop - start
+    if length == 1:
+        return '{}'.format(beginning)
+    if not length:
+        beginning -= 1        # empty ranges begin at line just before the range
+    return '{},{}'.format(beginning, length)
+
 def unified_diff(a, b, fromfile='', tofile='', fromfiledate='',
                  tofiledate='', n=3, lineterm='\n'):
     r"""
@@ -1160,18 +1175,18 @@ 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
@@ -1184,23 +1199,45 @@ 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)
             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)
+            fromdate = '\t{}'.format(fromfiledate) if fromfiledate else ''
+            todate = '\t{}'.format(tofiledate) if tofiledate else ''
+            yield '--- {}{}{}'.format(fromfile, fromdate, lineterm)
+            yield '+++ {}{}{}'.format(tofile, todate, lineterm)
+
+        first, last = group[0], group[-1]
+        file1_range = _format_range_unified(first[1], last[2])
+        file2_range = _format_range_unified(first[3], last[4])
+        yield '@@ -{} +{} @@{}'.format(file1_range, file2_range, lineterm)
+
         for tag, i1, i2, j1, j2 in group:
             if tag == 'equal':
                 for line in a[i1:i2]:
                     yield ' ' + line
                 continue
-            if tag == 'replace' or tag == 'delete':
+            if tag in {'replace', 'delete'}:
                 for line in a[i1:i2]:
                     yield '-' + line
-            if tag == 'replace' or tag == 'insert':
+            if tag in {'replace', 'insert'}:
                 for line in b[j1:j2]:
                     yield '+' + line
 
+
+########################################################################
+###  Context Diff
+########################################################################
+
+def _format_range_context(start, stop):
+    'Convert range to the "ed" format'
+    # Per the diff spec at http://www.unix.org/single_unix_specification/
+    beginning = start + 1     # lines start numbering with one
+    length = stop - start
+    if not length:
+        beginning -= 1        # empty ranges begin at line just before the range
+    if length <= 1:
+        return '{}'.format(beginning)
+    return '{},{}'.format(beginning, beginning + length - 1)
+
 # See http://www.unix.org/single_unix_specification/
 def context_diff(a, b, fromfile='', tofile='',
                  fromfiledate='', tofiledate='', n=3, lineterm='\n'):
@@ -1223,17 +1260,16 @@ 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
@@ -1247,36 +1283,36 @@ def context_diff(a, b, fromfile='', tofile='',
       four
     """
 
+    prefix = dict(insert='+ ', delete='- ', replace='! ', equal='  ')
     started = False
-    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)
             started = True
+            fromdate = '\t{}'.format(fromfiledate) if fromfiledate else ''
+            todate = '\t{}'.format(tofiledate) if tofiledate else ''
+            yield '*** {}{}{}'.format(fromfile, fromdate, lineterm)
+            yield '--- {}{}{}'.format(tofile, todate, lineterm)
 
-        yield '***************%s' % (lineterm,)
-        if group[-1][2] - group[0][1] >= 2:
-            yield '*** %d,%d ****%s' % (group[0][1]+1, group[-1][2], lineterm)
-        else:
-            yield '*** %d ****%s' % (group[-1][2], lineterm)
-        visiblechanges = [e for e in group if e[0] in ('replace', 'delete')]
-        if visiblechanges:
+        first, last = group[0], group[-1]
+        yield '***************' + lineterm
+
+        file1_range = _format_range_context(first[1], last[2])
+        yield '*** {} ****{}'.format(file1_range, lineterm)
+
+        if any(tag in {'replace', 'delete'} for tag, _, _, _, _ in group):
             for tag, i1, i2, _, _ in group:
                 if tag != 'insert':
                     for line in a[i1:i2]:
-                        yield prefixmap[tag] + line
+                        yield prefix[tag] + line
 
-        if group[-1][4] - group[0][3] >= 2:
-            yield '--- %d,%d ----%s' % (group[0][3]+1, group[-1][4], lineterm)
-        else:
-            yield '--- %d ----%s' % (group[-1][4], lineterm)
-        visiblechanges = [e for e in group if e[0] in ('replace', 'insert')]
-        if visiblechanges:
+        file2_range = _format_range_context(first[3], last[4])
+        yield '--- {} ----{}'.format(file2_range, lineterm)
+
+        if any(tag in {'replace', 'insert'} for tag, _, _, _, _ in group):
             for tag, _, _, j1, j2 in group:
                 if tag != 'delete':
                     for line in b[j1:j2]:
-                        yield prefixmap[tag] + line
+                        yield prefix[tag] + line
 
 def ndiff(a, b, linejunk=None, charjunk=IS_CHARACTER_JUNK):
     r"""

Lib/test/test_difflib.py

@@ -159,10 +159,73 @@ 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_range_format_unified(self):
+        # Per the diff spec at http://www.unix.org/single_unix_specification/
+        spec = '''\
+           Each <range> field shall be of the form:
+             %1d", <beginning line number>  if the range contains exactly one line,
+           and:
+            "%1d,%1d", <beginning line number>, <number of lines> otherwise.
+           If a range is empty, its beginning line number shall be the number of
+           the line just before the range, or 0 if the empty range starts the file.
+        '''
+        fmt = difflib._format_range_unified
+        self.assertEqual(fmt(3,3), '3,0')
+        self.assertEqual(fmt(3,4), '4')
+        self.assertEqual(fmt(3,5), '4,2')
+        self.assertEqual(fmt(3,6), '4,3')
+        self.assertEqual(fmt(0,0), '0,0')
+
+    def test_range_format_context(self):
+        # Per the diff spec at http://www.unix.org/single_unix_specification/
+        spec = '''\
+           The range of lines in file1 shall be written in the following format
+           if the range contains two or more lines:
+               "*** %d,%d ****\n", <beginning line number>, <ending line number>
+           and the following format otherwise:
+               "*** %d ****\n", <ending line number>
+           The ending line number of an empty range shall be the number of the preceding line,
+           or 0 if the range is at the start of the file.
+
+           Next, the range of lines in file2 shall be written in the following format
+           if the range contains two or more lines:
+               "--- %d,%d ----\n", <beginning line number>, <ending line number>
+           and the following format otherwise:
+               "--- %d ----\n", <ending line number>
+        '''
+        fmt = difflib._format_range_context
+        self.assertEqual(fmt(3,3), '3')
+        self.assertEqual(fmt(3,4), '4')
+        self.assertEqual(fmt(3,5), '4,5')
+        self.assertEqual(fmt(3,6), '4,6')
+        self.assertEqual(fmt(0,0), '0')
+
+
 def test_main():
     difflib.HtmlDiff._default_prefix = 0
     Doctests = doctest.DocTestSuite(difflib)
-    run_unittest(TestSFpatches, TestSFbugs, Doctests)
+    run_unittest(TestSFpatches, TestSFbugs, Doctests, TestOutputFormat)
 
 if __name__ == '__main__':
     test_main()