[PATCH] Add -B flag to diff-* brothers.

A new diffcore transformation, diffcore-break.c, is introduced.

When the -B flag is given, a patch that represents a complete
rewrite is broken into a deletion followed by a creation.  This
makes it easier to review such a complete rewrite patch.

The -B flag takes the same syntax as the -M and -C flags to
specify the minimum amount of non-source material the resulting
file needs to have to be considered a complete rewrite, and
defaults to 99% if not specified.

As the new test t4008-diff-break-rewrite.sh demonstrates, if a
file is a complete rewrite, it is broken into a delete/create
pair, which can further be subjected to the usual rename
detection if -M or -C is used.  For example, if file0 gets
completely rewritten to make it as if it were rather based on
file1 which itself disappeared, the following happens:

    The original change looks like this:

	file0     --> file0' (quite different from file0)
	file1     --> /dev/null

    After diffcore-break runs, it would become this:

	file0     --> /dev/null
	/dev/null --> file0'
	file1     --> /dev/null

    Then diffcore-rename matches them up:

	file1     --> file0'

The internal score values are finer grained now.  Earlier
maximum of 10000 has been raised to 60000; there is no user
visible changes but there is no reason to waste available bits.

Signed-off-by: Junio C Hamano <junkio@cox.net>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

1 files changed, 207 insertions, 0 deletions

diff --git a/t/t4008-diff-break-rewrite.sh b/t/t4008-diff-break-rewrite.sh
new file mode 100644
index 0000000000..7189462a9e
--- /dev/null
+++ b/t/t4008-diff-break-rewrite.sh
@@ -0,0 +1,207 @@
+#!/bin/sh
+#
+# Copyright (c) 2005 Junio C Hamano
+#
+
+test_description='Break and then rename
+
+We have two very different files, file0 and file1, registered in a tree.
+
+We update file1 so drastically that it is more similar to file0, and
+then remove file0.  With -B, changes to file1 should be broken into
+separate delete and create, resulting in removal of file0, removal of
+original file1 and creation of completely rewritten file1.
+
+Further, with -B and -M together, these three modifications should
+turn into rename-edit of file0 into file1.
+
+Starting from the same two files in the tree, we swap file0 and file1.
+With -B, this should be detected as two complete rewrites, resulting in
+four changes in total.
+
+Further, with -B and -M together, these should turn into two renames.
+'
+. ./test-lib.sh
+
+_x40='[0-9a-f][0-9a-f][0-9a-f][0-9a-f][0-9a-f]'
+_x40="$_x40$_x40$_x40$_x40$_x40$_x40$_x40$_x40"
+sanitize_diff_raw='s/ '"$_x40"' '"$_x40"' \([CDNR]\)[0-9]*	/ X X \1#	/'
+compare_diff_raw () {
+    # When heuristics are improved, the score numbers would change.
+    # Ignore them while comparing.
+    # Also we do not check SHA1 hash generation in this test, which
+    # is a job for t0000-basic.sh
+
+    sed -e "$sanitize_diff_raw" <"$1" >.tmp-1
+    sed -e "$sanitize_diff_raw" <"$2" >.tmp-2
+    diff -u .tmp-1 .tmp-2 && rm -f .tmp-1 .tmp-2
+}
+
+test_expect_success \
+    setup \
+    'cat ../../README >file0 &&
+     cat ../../COPYING >file1 &&
+    git-update-cache --add file0 file1 &&
+    tree=$(git-write-tree) &&
+    echo "$tree"'
+
+test_expect_success \
+    'change file1 with copy-edit of file0 and remove file0' \
+    'sed -e "s/git/GIT/" file0 >file1 &&
+     rm -f file0 &&
+    git-update-cache --remove file0 file1'
+
+test_expect_success \
+    'run diff with -B' \
+    'git-diff-cache -B --cached "$tree" >current'
+
+cat >expected <<\EOF
+:100644 000000 f5deac7be59e7eeab8657fd9ae706fd6a57daed2 0000000000000000000000000000000000000000 D	file0
+:100644 000000 6ff87c4664981e4397625791c8ea3bbb5f2279a3 0000000000000000000000000000000000000000 D100	file1
+:000000 100644 0000000000000000000000000000000000000000 11e331465a89c394dc25c780de230043750c1ec8 N100	file1
+EOF
+
+test_expect_success \
+    'validate result of -B (#1)' \
+    'compare_diff_raw current expected'
+
+test_expect_success \
+    'run diff with -B and -M' \
+    'git-diff-cache -B -M "$tree" >current'
+
+cat >expected <<\EOF
+:100644 100644 f5deac7be59e7eeab8657fd9ae706fd6a57daed2 08bb2fb671deff4c03a4d4a0a1315dff98d5732c R100	file0	file1
+EOF
+
+test_expect_success \
+    'validate result of -B -M (#2)' \
+    'compare_diff_raw current expected'
+
+test_expect_success \
+    'swap file0 and file1' \
+    'rm -f file0 file1 &&
+     git-read-tree -m $tree &&
+     git-checkout-cache -f -u -a &&
+     mv file0 tmp &&
+     mv file1 file0 &&
+     mv tmp file1 &&
+     git-update-cache file0 file1'
+
+test_expect_success \
+    'run diff with -B' \
+    'git-diff-cache -B "$tree" >current'
+
+cat >expected <<\EOF
+:100644 000000 f5deac7be59e7eeab8657fd9ae706fd6a57daed2 0000000000000000000000000000000000000000 D100	file0
+:000000 100644 0000000000000000000000000000000000000000 6ff87c4664981e4397625791c8ea3bbb5f2279a3 N100	file0
+:100644 000000 6ff87c4664981e4397625791c8ea3bbb5f2279a3 0000000000000000000000000000000000000000 D100	file1
+:000000 100644 0000000000000000000000000000000000000000 f5deac7be59e7eeab8657fd9ae706fd6a57daed2 N100	file1
+EOF
+
+test_expect_success \
+    'validate result of -B (#3)' \
+    'compare_diff_raw current expected'
+
+test_expect_success \
+    'run diff with -B and -M' \
+    'git-diff-cache -B -M "$tree" >current'
+
+cat >expected <<\EOF
+:100644 100644 6ff87c4664981e4397625791c8ea3bbb5f2279a3 6ff87c4664981e4397625791c8ea3bbb5f2279a3 R100	file1	file0
+:100644 100644 f5deac7be59e7eeab8657fd9ae706fd6a57daed2 f5deac7be59e7eeab8657fd9ae706fd6a57daed2 R100	file0	file1
+EOF
+
+test_expect_success \
+    'validate result of -B -M (#4)' \
+    'compare_diff_raw current expected'
+
+test_expect_success \
+    'make file0 into something completely different' \
+    'rm -f file0 &&
+     ln -s frotz file0 &&
+     git-update-cache file0 file1'
+
+test_expect_success \
+    'run diff with -B' \
+    'git-diff-cache -B "$tree" >current'
+
+cat >expected <<\EOF
+:100644 120000 f5deac7be59e7eeab8657fd9ae706fd6a57daed2 67be421f88824578857624f7b3dc75e99a8a1481 T	file0
+:100644 000000 6ff87c4664981e4397625791c8ea3bbb5f2279a3 0000000000000000000000000000000000000000 D100	file1
+:000000 100644 0000000000000000000000000000000000000000 f5deac7be59e7eeab8657fd9ae706fd6a57daed2 N100	file1
+EOF
+
+test_expect_success \
+    'validate result of -B (#5)' \
+    'compare_diff_raw current expected'
+
+test_expect_success \
+    'run diff with -B' \
+    'git-diff-cache -B -M "$tree" >current'
+
+# This should not mistake file0 as the copy source of new file1
+# due to type differences.
+cat >expected <<\EOF
+:100644 120000 f5deac7be59e7eeab8657fd9ae706fd6a57daed2 67be421f88824578857624f7b3dc75e99a8a1481 T	file0
+:100644 000000 6ff87c4664981e4397625791c8ea3bbb5f2279a3 0000000000000000000000000000000000000000 D100	file1
+:000000 100644 0000000000000000000000000000000000000000 f5deac7be59e7eeab8657fd9ae706fd6a57daed2 N100	file1
+EOF
+
+test_expect_success \
+    'validate result of -B -M (#6)' \
+    'compare_diff_raw current expected'
+
+test_expect_success \
+    'run diff with -M' \
+    'git-diff-cache -M "$tree" >current'
+
+# This should not mistake file0 as the copy source of new file1
+# due to type differences.
+cat >expected <<\EOF
+:100644 120000 f5deac7be59e7eeab8657fd9ae706fd6a57daed2 67be421f88824578857624f7b3dc75e99a8a1481 T	file0
+:100644 100644 6ff87c4664981e4397625791c8ea3bbb5f2279a3 f5deac7be59e7eeab8657fd9ae706fd6a57daed2 M	file1
+EOF
+
+test_expect_success \
+    'validate result of -M (#7)' \
+    'compare_diff_raw current expected'
+
+test_expect_success \
+    'file1 edited to look like file0 and file0 rename-edited to file2' \
+    'rm -f file0 file1 &&
+     git-read-tree -m $tree &&
+     git-checkout-cache -f -u -a &&
+     sed -e "s/git/GIT/" file0 >file1 &&
+     sed -e "s/git/GET/" file0 >file2 &&
+     rm -f file0
+     git-update-cache --add --remove file0 file1 file2'
+
+test_expect_success \
+    'run diff with -B' \
+    'git-diff-cache -B "$tree" >current'
+
+cat >expected <<\EOF
+:100644 000000 f5deac7be59e7eeab8657fd9ae706fd6a57daed2 0000000000000000000000000000000000000000 D	file0
+:100644 000000 6ff87c4664981e4397625791c8ea3bbb5f2279a3 0000000000000000000000000000000000000000 D100	file1
+:000000 100644 0000000000000000000000000000000000000000 08bb2fb671deff4c03a4d4a0a1315dff98d5732c N100	file1
+:000000 100644 0000000000000000000000000000000000000000 f5deac7be59e7eeab8657fd9ae706fd6a57daed2 N	file2
+EOF
+
+test_expect_success \
+    'validate result of -B (#8)' \
+    'compare_diff_raw current expected'
+
+test_expect_success \
+    'run diff with -B -M' \
+    'git-diff-cache -B -M "$tree" >current'
+
+cat >expected <<\EOF
+:100644 100644 f5deac7be59e7eeab8657fd9ae706fd6a57daed2 08bb2fb671deff4c03a4d4a0a1315dff98d5732c C095	file0	file1
+:100644 100644 f5deac7be59e7eeab8657fd9ae706fd6a57daed2 59f832e5c8b3f7e486be15ad0cd3e95ba9af8998 R095	file0	file2
+EOF
+
+test_expect_success \
+    'validate result of -B -M (#9)' \
+    'compare_diff_raw current expected'
+
+test_done