[PATCH] mdiff/patch: fix bad hunk handling for unified diffs with zero context

[Nicolas Venegas]

# HG changeset patch
# User Nicolas Venegas <nvenegas at atlassian.com>
# Date 1320886559 28800
# Branch stable
# Node ID 2e86b1aca7c2b716da5be6a5e3ff951e6c914aca
# Parent  54c0517c0fe8af4f8851a1bbb5bb229f0e7dd853
mdiff/patch: fix bad hunk handling for unified diffs with zero context

Prior to this patch "hg diff -U0", i.e., zero lines of context, would
output hunk headers with a start line one greater than what GNU patch
and git output. Guido van Rossum documents the unified diff format[1]
as having a start line value "one lower than one would expect" for
zero length hunks.

Comparing the behaviour of the three systems prior to this patch in
transforming

  c1
  c3

to

  c1
  c2
  c3

- GNU "diff -U0" reports the hunk as "@@ -1,0 +2 @@"
- "git diff -U0" reports the hunk as "@@ -1,0 +2 @@"
- "hg diff -U0" reports the hunk as "@@ -2,0 +2,1 @@"

After this patch, "hg diff -U0" reports "@@ -1,0 +2,1 @@".

Since "hg export --config diff.unified=0" outputs zero-context unified
diffs, "hg import" has also been updated to account for start lines
one less than expected for zero length hunk ranges.

[1]: http://www.artima.com/weblogs/viewpost.jsp?thread=164293

diff -r 54c0517c0fe8 -r 2e86b1aca7c2 mercurial/mdiff.py
--- a/mercurial/mdiff.py	Fri Nov 04 10:31:38 2011 +0100
+++ b/mercurial/mdiff.py	Wed Nov 09 16:55:59 2011 -0800
@@ -180,8 +180,14 @@
             # the file more than once.
             lastfunc[0] = astart
 
-        yield "@@ -%d,%d +%d,%d @@%s\n" % (astart + 1, alen,
-                                           bstart + 1, blen, func)
+        # zero-length hunk ranges report their start line as one less
+        if alen:
+            astart += 1
+        if blen:
+            bstart += 1
+
+        yield "@@ -%d,%d +%d,%d @@%s\n" % (astart, alen,
+                                           bstart, blen, func)
         for x in delta:
             yield x
         for x in xrange(a2, aend):
diff -r 54c0517c0fe8 -r 2e86b1aca7c2 mercurial/patch.py
--- a/mercurial/patch.py	Fri Nov 04 10:31:38 2011 +0100
+++ b/mercurial/patch.py	Wed Nov 09 16:55:59 2011 -0800
@@ -723,11 +723,10 @@
 
         # fast case first, no offsets, no fuzz
         old = h.old()
-        # patch starts counting at 1 unless we are adding the file
-        if h.starta == 0:
-            start = 0
-        else:
-            start = h.starta + self.offset - 1
+        start = h.starta + self.offset
+        # zero length hunk ranges already have their start decremented
+        if h.lena:
+            start -= 1
         orig_start = start
         # if there's skew we want to emit the "(offset %d lines)" even
         # when the hunk cleanly applies at start + skew, so skip the
diff -r 54c0517c0fe8 -r 2e86b1aca7c2 tests/test-diff-unified.t
--- a/tests/test-diff-unified.t	Fri Nov 04 10:31:38 2011 +0100
+++ b/tests/test-diff-unified.t	Wed Nov 09 16:55:59 2011 -0800
@@ -89,23 +89,65 @@
   abort: diff context lines count must be an integer, not 'foo'
   [255]
 
-test off-by-one error with diff -p
+0 lines of context hunk header matches gnu diff hunk header
 
-  $ hg init diffp
-  $ cd diffp
-  $ echo a > a
-  $ hg ci -Ama
-  adding a
-  $ rm a
-  $ echo b > a
-  $ echo a >> a
-  $ echo c >> a
-  $ hg diff -U0 -p --nodates
-  diff -r cb9a9f314b8b a
-  --- a/a
-  +++ b/a
-  @@ -1,0 +1,1 @@
-  +b
-  @@ -2,0 +3,1 @@ a
-  +c
+  $ hg init diffzero
+  $ cd diffzero
+  $ cat > f1 << EOF
+  > c2
+  > c4
+  > c5
+  > EOF
+  $ hg commit -Am0
+  adding f1
 
+  $ cat > f2 << EOF
+  > c1
+  > c2
+  > c3
+  > c4
+  > EOF
+  $ diff -U0 f1 f2
+  --- f1	* (glob)
+  +++ f2	* (glob)
+  @@ -0,0 +1 @@
+  +c1
+  @@ -1,0 +3 @@
+  +c3
+  @@ -3 +4,0 @@
+  -c5
+  [1]
+
+  $ mv f2 f1
+  $ hg diff -U0 --nodates
+  diff -r 55d8ff78db23 f1
+  --- a/f1
+  +++ b/f1
+  @@ -0,0 +1,1 @@
+  +c1
+  @@ -1,0 +3,1 @@
+  +c3
+  @@ -3,1 +4,0 @@
+  -c5
+
+  $ hg diff -U0 --nodates --git
+  diff --git a/f1 b/f1
+  --- a/f1
+  +++ b/f1
+  @@ -0,0 +1,1 @@
+  +c1
+  @@ -1,0 +3,1 @@
+  +c3
+  @@ -3,1 +4,0 @@
+  -c5
+
+  $ hg diff -U0 --nodates -p
+  diff -r 55d8ff78db23 f1
+  --- a/f1
+  +++ b/f1
+  @@ -0,0 +1,1 @@
+  +c1
+  @@ -1,0 +3,1 @@ c2
+  +c3
+  @@ -3,1 +4,0 @@ c4
+  -c5
diff -r 54c0517c0fe8 -r 2e86b1aca7c2 tests/test-import.t
--- a/tests/test-import.t	Fri Nov 04 10:31:38 2011 +0100
+++ b/tests/test-import.t	Wed Nov 09 16:55:59 2011 -0800
@@ -958,3 +958,39 @@
   $ diff want have
   $ cd ..
 
+import a unified diff with no lines of context (diff -U0)
+
+  $ hg init diffzero
+  $ cd diffzero
+  $ cat > f << EOF
+  > c2
+  > c4
+  > c5
+  > EOF
+  $ hg commit -Am0
+  adding f
+
+  $ hg import --no-commit - << EOF
+  > # HG changeset patch
+  > # User test
+  > # Date 0 0
+  > # Node ID f4974ab632f3dee767567b0576c0ec9a4508575c
+  > # Parent  8679a12a975b819fae5f7ad3853a2886d143d794
+  > 1
+  > diff -r 8679a12a975b -r f4974ab632f3 f
+  > --- a/f	Thu Jan 01 00:00:00 1970 +0000
+  > +++ b/f	Thu Jan 01 00:00:00 1970 +0000
+  > @@ -0,0 +1,1 @@
+  > +c1
+  > @@ -1,0 +3,1 @@
+  > +c3
+  > @@ -3,1 +4,0 @@
+  > -c5
+  > EOF
+  applying patch from stdin
+
+  $ cat f
+  c1
+  c2
+  c3
+  c4