Merge branch 'jh/dirstat'

* jh/dirstat:
  --dirstat: In case of renames, use target filename instead of source filename
  Teach --dirstat not to completely ignore rearranged lines within a file
  --dirstat-by-file: Make it faster and more correct
  --dirstat: Describe non-obvious differences relative to --stat or regular diff

Documentation/diff-options.txt

@@ -72,6 +72,10 @@ endif::git-format-patch[]
 	a cut-off percent (3% by default) are not shown. The cut-off percent
 	can be set with `--dirstat=<limit>`. Changes in a child directory are not
 	counted for the parent directory, unless `--cumulative` is used.
++
+Note that the `--dirstat` option computes the changes while ignoring
+the amount of pure code movements within a file.  In other words,
+rearranging lines in a file is not counted as much as other changes.
 
 --dirstat-by-file[=<limit>]::
 	Same as `--dirstat`, but counts changed files instead of lines.

diff.c

@@ -1538,8 +1538,36 @@ static void show_dirstat(struct diff_options *options)
 		struct diff_filepair *p = q->queue[i];
 		const char *name;
 		unsigned long copied, added, damage;
+		int content_changed;
 
-		name = p->one->path ? p->one->path : p->two->path;
+		name = p->two->path ? p->two->path : p->one->path;
+
+		if (p->one->sha1_valid && p->two->sha1_valid)
+			content_changed = hashcmp(p->one->sha1, p->two->sha1);
+		else
+			content_changed = 1;
+
+		if (!content_changed) {
+			/*
+			 * The SHA1 has not changed, so pre-/post-content is
+			 * identical. We can therefore skip looking at the
+			 * file contents altogether.
+			 */
+			damage = 0;
+			goto found_damage;
+		}
+
+		if (DIFF_OPT_TST(options, DIRSTAT_BY_FILE)) {
+			/*
+			 * In --dirstat-by-file mode, we don't really need to
+			 * look at the actual file contents at all.
+			 * The fact that the SHA1 changed is enough for us to
+			 * add this file to the list of results
+			 * (with each file contributing equal damage).
+			 */
+			damage = 1;
+			goto found_damage;
+		}
 
 		if (DIFF_FILE_VALID(p->one) && DIFF_FILE_VALID(p->two)) {
 			diff_populate_filespec(p->one, 0);
@@ -1563,14 +1591,18 @@ static void show_dirstat(struct diff_options *options)
 		/*
 		 * Original minus copied is the removed material,
 		 * added is the new material.  They are both damages
-		 * made to the preimage. In --dirstat-by-file mode, count
-		 * damaged files, not damaged lines. This is done by
-		 * counting only a single damaged line per file.
+		 * made to the preimage.
+		 * If the resulting damage is zero, we know that
+		 * diffcore_count_changes() considers the two entries to
+		 * be identical, but since content_changed is true, we
+		 * know that there must have been _some_ kind of change,
+		 * so we force all entries to have damage > 0.
 		 */
 		damage = (p->one->size - copied) + added;
-		if (DIFF_OPT_TST(options, DIRSTAT_BY_FILE) && damage > 0)
+		if (!damage)
 			damage = 1;
 
+found_damage:
 		ALLOC_GROW(dir.files, dir.nr + 1, dir.alloc);
 		dir.files[dir.nr].name = name;
 		dir.files[dir.nr].changed = damage;

t/t4013-diff-various.sh

@@ -80,18 +80,31 @@ test_expect_success setup '
 
 	git config log.showroot false &&
 	git commit --amend &&
+
+	GIT_AUTHOR_DATE="2006-06-26 00:06:00 +0000" &&
+	GIT_COMMITTER_DATE="2006-06-26 00:06:00 +0000" &&
+	export GIT_AUTHOR_DATE GIT_COMMITTER_DATE &&
+	git checkout -b rearrange initial &&
+	for i in B A; do echo $i; done >dir/sub &&
+	git add dir/sub &&
+	git commit -m "Rearranged lines in dir/sub" &&
+	git checkout master &&
+
 	git show-branch
 '
 
 : <<\EOF
 ! [initial] Initial
  * [master] Merge branch 'side'
-  ! [side] Side
----
- -  [master] Merge branch 'side'
- *+ [side] Side
- *  [master^] Second
-+*+ [initial] Initial
+  ! [rearrange] Rearranged lines in dir/sub
+   ! [side] Side
+----
+  +  [rearrange] Rearranged lines in dir/sub
+ -   [master] Merge branch 'side'
+ * + [side] Side
+ *   [master^] Third
+ *   [master~2] Second
++*++ [initial] Initial
 EOF
 
 V=`git version | sed -e 's/^git version //' -e 's/\./\\./g'`
@@ -287,6 +300,8 @@ diff --no-index --name-status -- dir2 dir
 diff --no-index dir dir3
 diff master master^ side
 diff --dirstat master~1 master~2
+diff --dirstat initial rearrange
+diff --dirstat-by-file initial rearrange
 EOF
 
 test_expect_success 'log -S requires an argument' '

t/t4013/diff.diff_--dirstat-by-file_initial_rearrange

@@ -0,0 +1,3 @@
+$ git diff --dirstat-by-file initial rearrange
+ 100.0% dir/
+$

t/t4013/diff.diff_--dirstat_initial_rearrange

@@ -0,0 +1,3 @@
+$ git diff --dirstat initial rearrange
+ 100.0% dir/
+$

t/t4013/diff.format-patch_--stdout_--cover-letter_-n_initial..master^

@@ -1,7 +1,7 @@
 $ git format-patch --stdout --cover-letter -n initial..master^
 From 9a6d4949b6b76956d9d5e26f2791ec2ceff5fdc0 Mon Sep 17 00:00:00 2001
 From: C O Mitter <committer@example.com>
-Date: Mon, 26 Jun 2006 00:05:00 +0000
+Date: Mon, 26 Jun 2006 00:06:00 +0000
 Subject: [DIFFERENT_PREFIX 0/2] *** SUBJECT HERE ***
 
 *** BLURB HERE ***

t/t4013/diff.log_--decorate=full_--all

@@ -1,4 +1,10 @@
 $ git log --decorate=full --all
+commit cd4e72fd96faed3f0ba949dc42967430374e2290 (refs/heads/rearrange)
+Author: A U Thor <author@example.com>
+Date:   Mon Jun 26 00:06:00 2006 +0000
+
+    Rearranged lines in dir/sub
+
 commit 59d314ad6f356dd08601a4cd5e530381da3e3c64 (HEAD, refs/heads/master)
 Merge: 9a6d494 c7a2ab9
 Author: A U Thor <author@example.com>

t/t4013/diff.log_--decorate_--all

@@ -1,4 +1,10 @@
 $ git log --decorate --all
+commit cd4e72fd96faed3f0ba949dc42967430374e2290 (rearrange)
+Author: A U Thor <author@example.com>
+Date:   Mon Jun 26 00:06:00 2006 +0000
+
+    Rearranged lines in dir/sub
+
 commit 59d314ad6f356dd08601a4cd5e530381da3e3c64 (HEAD, master)
 Merge: 9a6d494 c7a2ab9
 Author: A U Thor <author@example.com>