Merge branch 'pw/diff-color-moved-fix'

Correctness and performance update to "diff --color-moved" feature.

* pw/diff-color-moved-fix:
  diff --color-moved: intern strings
  diff: use designated initializers for emitted_diff_symbol
  diff --color-moved-ws=allow-indentation-change: improve hash lookups
  diff --color-moved: stop clearing potential moved blocks
  diff --color-moved: shrink potential moved blocks as we go
  diff --color-moved: unify moved block growth functions
  diff --color-moved: call comparison function directly
  diff --color-moved-ws=allow-indentation-change: simplify and optimize
  diff: simplify allow-indentation-change delta calculation
  diff --color-moved: avoid false short line matches and bad zebra coloring
  diff --color-moved=zebra: fix alternate coloring
  diff --color-moved: rewind when discarding pmb
  diff --color-moved: factor out function
  diff --color-moved: clear all flags on blocks that are too short
  diff --color-moved: add perf tests

1 files changed, 194 insertions, 11 deletions

diff --git a/t/t4015-diff-whitespace.sh b/t/t4015-diff-whitespace.sh
index ca5adabe14..9babf13bc9 100755
--- a/t/t4015-diff-whitespace.sh
+++ b/t/t4015-diff-whitespace.sh
@@ -1442,6 +1442,143 @@ test_expect_success 'detect permutations inside moved code -- dimmed-zebra' '
 	test_cmp expected actual
 '
 
+test_expect_success 'zebra alternate color is only used when necessary' '
+	cat >old.txt <<-\EOF &&
+	line 1A should be marked as oldMoved newMovedAlternate
+	line 1B should be marked as oldMoved newMovedAlternate
+	unchanged
+	line 2A should be marked as oldMoved newMovedAlternate
+	line 2B should be marked as oldMoved newMovedAlternate
+	line 3A should be marked as oldMovedAlternate newMoved
+	line 3B should be marked as oldMovedAlternate newMoved
+	unchanged
+	line 4A should be marked as oldMoved newMovedAlternate
+	line 4B should be marked as oldMoved newMovedAlternate
+	line 5A should be marked as oldMovedAlternate newMoved
+	line 5B should be marked as oldMovedAlternate newMoved
+	line 6A should be marked as oldMoved newMoved
+	line 6B should be marked as oldMoved newMoved
+	EOF
+	cat >new.txt <<-\EOF &&
+	  line 1A should be marked as oldMoved newMovedAlternate
+	  line 1B should be marked as oldMoved newMovedAlternate
+	unchanged
+	  line 3A should be marked as oldMovedAlternate newMoved
+	  line 3B should be marked as oldMovedAlternate newMoved
+	  line 2A should be marked as oldMoved newMovedAlternate
+	  line 2B should be marked as oldMoved newMovedAlternate
+	unchanged
+	  line 6A should be marked as oldMoved newMoved
+	  line 6B should be marked as oldMoved newMoved
+	    line 4A should be marked as oldMoved newMovedAlternate
+	    line 4B should be marked as oldMoved newMovedAlternate
+	  line 5A should be marked as oldMovedAlternate newMoved
+	  line 5B should be marked as oldMovedAlternate newMoved
+	EOF
+	test_expect_code 1 git diff --no-index --color --color-moved=zebra \
+		 --color-moved-ws=allow-indentation-change \
+		 old.txt new.txt >output &&
+	grep -v index output | test_decode_color >actual &&
+	cat >expected <<-\EOF &&
+	<BOLD>diff --git a/old.txt b/new.txt<RESET>
+	<BOLD>--- a/old.txt<RESET>
+	<BOLD>+++ b/new.txt<RESET>
+	<CYAN>@@ -1,14 +1,14 @@<RESET>
+	<BOLD;MAGENTA>-line 1A should be marked as oldMoved newMovedAlternate<RESET>
+	<BOLD;MAGENTA>-line 1B should be marked as oldMoved newMovedAlternate<RESET>
+	<BOLD;CYAN>+<RESET><BOLD;CYAN>  line 1A should be marked as oldMoved newMovedAlternate<RESET>
+	<BOLD;CYAN>+<RESET><BOLD;CYAN>  line 1B should be marked as oldMoved newMovedAlternate<RESET>
+	 unchanged<RESET>
+	<BOLD;MAGENTA>-line 2A should be marked as oldMoved newMovedAlternate<RESET>
+	<BOLD;MAGENTA>-line 2B should be marked as oldMoved newMovedAlternate<RESET>
+	<BOLD;BLUE>-line 3A should be marked as oldMovedAlternate newMoved<RESET>
+	<BOLD;BLUE>-line 3B should be marked as oldMovedAlternate newMoved<RESET>
+	<BOLD;CYAN>+<RESET><BOLD;CYAN>  line 3A should be marked as oldMovedAlternate newMoved<RESET>
+	<BOLD;CYAN>+<RESET><BOLD;CYAN>  line 3B should be marked as oldMovedAlternate newMoved<RESET>
+	<BOLD;YELLOW>+<RESET><BOLD;YELLOW>  line 2A should be marked as oldMoved newMovedAlternate<RESET>
+	<BOLD;YELLOW>+<RESET><BOLD;YELLOW>  line 2B should be marked as oldMoved newMovedAlternate<RESET>
+	 unchanged<RESET>
+	<BOLD;MAGENTA>-line 4A should be marked as oldMoved newMovedAlternate<RESET>
+	<BOLD;MAGENTA>-line 4B should be marked as oldMoved newMovedAlternate<RESET>
+	<BOLD;BLUE>-line 5A should be marked as oldMovedAlternate newMoved<RESET>
+	<BOLD;BLUE>-line 5B should be marked as oldMovedAlternate newMoved<RESET>
+	<BOLD;MAGENTA>-line 6A should be marked as oldMoved newMoved<RESET>
+	<BOLD;MAGENTA>-line 6B should be marked as oldMoved newMoved<RESET>
+	<BOLD;CYAN>+<RESET><BOLD;CYAN>  line 6A should be marked as oldMoved newMoved<RESET>
+	<BOLD;CYAN>+<RESET><BOLD;CYAN>  line 6B should be marked as oldMoved newMoved<RESET>
+	<BOLD;YELLOW>+<RESET><BOLD;YELLOW>    line 4A should be marked as oldMoved newMovedAlternate<RESET>
+	<BOLD;YELLOW>+<RESET><BOLD;YELLOW>    line 4B should be marked as oldMoved newMovedAlternate<RESET>
+	<BOLD;CYAN>+<RESET><BOLD;CYAN>  line 5A should be marked as oldMovedAlternate newMoved<RESET>
+	<BOLD;CYAN>+<RESET><BOLD;CYAN>  line 5B should be marked as oldMovedAlternate newMoved<RESET>
+	EOF
+	test_cmp expected actual
+'
+
+test_expect_success 'short lines of opposite sign do not get marked as moved' '
+	cat >old.txt <<-\EOF &&
+	this line should be marked as moved
+	unchanged
+	unchanged
+	unchanged
+	unchanged
+	too short
+	this line should be marked as oldMoved newMoved
+	this line should be marked as oldMovedAlternate newMoved
+	unchanged 1
+	unchanged 2
+	unchanged 3
+	unchanged 4
+	this line should be marked as oldMoved newMoved/newMovedAlternate
+	EOF
+	cat >new.txt <<-\EOF &&
+	too short
+	unchanged
+	unchanged
+	this line should be marked as moved
+	too short
+	unchanged
+	unchanged
+	this line should be marked as oldMoved newMoved/newMovedAlternate
+	unchanged 1
+	unchanged 2
+	this line should be marked as oldMovedAlternate newMoved
+	this line should be marked as oldMoved newMoved/newMovedAlternate
+	unchanged 3
+	this line should be marked as oldMoved newMoved
+	unchanged 4
+	EOF
+	test_expect_code 1 git diff --no-index --color --color-moved=zebra \
+		old.txt new.txt >output && cat output &&
+	grep -v index output | test_decode_color >actual &&
+	cat >expect <<-\EOF &&
+	<BOLD>diff --git a/old.txt b/new.txt<RESET>
+	<BOLD>--- a/old.txt<RESET>
+	<BOLD>+++ b/new.txt<RESET>
+	<CYAN>@@ -1,13 +1,15 @@<RESET>
+	<BOLD;MAGENTA>-this line should be marked as moved<RESET>
+	<GREEN>+<RESET><GREEN>too short<RESET>
+	 unchanged<RESET>
+	 unchanged<RESET>
+	<BOLD;CYAN>+<RESET><BOLD;CYAN>this line should be marked as moved<RESET>
+	<GREEN>+<RESET><GREEN>too short<RESET>
+	 unchanged<RESET>
+	 unchanged<RESET>
+	<RED>-too short<RESET>
+	<BOLD;MAGENTA>-this line should be marked as oldMoved newMoved<RESET>
+	<BOLD;BLUE>-this line should be marked as oldMovedAlternate newMoved<RESET>
+	<BOLD;CYAN>+<RESET><BOLD;CYAN>this line should be marked as oldMoved newMoved/newMovedAlternate<RESET>
+	 unchanged 1<RESET>
+	 unchanged 2<RESET>
+	<BOLD;CYAN>+<RESET><BOLD;CYAN>this line should be marked as oldMovedAlternate newMoved<RESET>
+	<BOLD;YELLOW>+<RESET><BOLD;YELLOW>this line should be marked as oldMoved newMoved/newMovedAlternate<RESET>
+	 unchanged 3<RESET>
+	<BOLD;CYAN>+<RESET><BOLD;CYAN>this line should be marked as oldMoved newMoved<RESET>
+	 unchanged 4<RESET>
+	<BOLD;MAGENTA>-this line should be marked as oldMoved newMoved/newMovedAlternate<RESET>
+	EOF
+	test_cmp expect actual
+'
+
 test_expect_success 'cmd option assumes configured colored-moved' '
 	test_config color.diff.oldMoved "magenta" &&
 	test_config color.diff.newMoved "cyan" &&
@@ -1833,6 +1970,52 @@ test_expect_success '--color-moved treats adjacent blocks as separate for MIN_AL
 	test_cmp expected actual
 '
 
+test_expect_success '--color-moved rewinds for MIN_ALNUM_COUNT' '
+	git reset --hard &&
+	test_write_lines >file \
+		A B C one two three four five six seven D E F G H I J &&
+	git add file &&
+	test_write_lines >file \
+		one two A B C D E F G H I J two three four five six seven &&
+	git diff --color-moved=zebra -- file &&
+
+	git diff --color-moved=zebra --color -- file >actual.raw &&
+	grep -v "index" actual.raw | test_decode_color >actual &&
+	cat >expected <<-\EOF &&
+	<BOLD>diff --git a/file b/file<RESET>
+	<BOLD>--- a/file<RESET>
+	<BOLD>+++ b/file<RESET>
+	<CYAN>@@ -1,13 +1,8 @@<RESET>
+	<GREEN>+<RESET><GREEN>one<RESET>
+	<GREEN>+<RESET><GREEN>two<RESET>
+	 A<RESET>
+	 B<RESET>
+	 C<RESET>
+	<RED>-one<RESET>
+	<BOLD;MAGENTA>-two<RESET>
+	<BOLD;MAGENTA>-three<RESET>
+	<BOLD;MAGENTA>-four<RESET>
+	<BOLD;MAGENTA>-five<RESET>
+	<BOLD;MAGENTA>-six<RESET>
+	<BOLD;MAGENTA>-seven<RESET>
+	 D<RESET>
+	 E<RESET>
+	 F<RESET>
+	<CYAN>@@ -15,3 +10,9 @@<RESET> <RESET>G<RESET>
+	 H<RESET>
+	 I<RESET>
+	 J<RESET>
+	<BOLD;CYAN>+<RESET><BOLD;CYAN>two<RESET>
+	<BOLD;CYAN>+<RESET><BOLD;CYAN>three<RESET>
+	<BOLD;CYAN>+<RESET><BOLD;CYAN>four<RESET>
+	<BOLD;CYAN>+<RESET><BOLD;CYAN>five<RESET>
+	<BOLD;CYAN>+<RESET><BOLD;CYAN>six<RESET>
+	<BOLD;CYAN>+<RESET><BOLD;CYAN>seven<RESET>
+	EOF
+
+	test_cmp expected actual
+'
+
 test_expect_success 'move detection with submodules' '
 	test_create_repo bananas &&
 	echo ripe >bananas/recipe &&
@@ -2023,10 +2206,10 @@ EMPTY=''
 test_expect_success 'compare mixed whitespace delta across moved blocks' '
 
 	git reset --hard &&
-	tr Q_ "\t " <<-EOF >text.txt &&
-	${EMPTY}
-	____too short without
-	${EMPTY}
+	tr "^|Q_" "\f\v\t " <<-EOF >text.txt &&
+	^__
+	|____too short without
+	^
 	___being grouped across blank line
 	${EMPTY}
 	context
@@ -2045,7 +2228,7 @@ test_expect_success 'compare mixed whitespace delta across moved blocks' '
 	git add text.txt &&
 	git commit -m "add text.txt" &&
 
-	tr Q_ "\t " <<-EOF >text.txt &&
+	tr "^|Q_" "\f\v\t " <<-EOF >text.txt &&
 	context
 	lines
 	to
@@ -2056,7 +2239,7 @@ test_expect_success 'compare mixed whitespace delta across moved blocks' '
 	${EMPTY}
 	QQtoo short without
 	${EMPTY}
-	Q_______being grouped across blank line
+	^Q_______being grouped across blank line
 	${EMPTY}
 	Q_QThese two lines have had their
 	indentation reduced by four spaces
@@ -2068,16 +2251,16 @@ test_expect_success 'compare mixed whitespace delta across moved blocks' '
 		-c core.whitespace=space-before-tab \
 		diff --color --color-moved --ws-error-highlight=all \
 		--color-moved-ws=allow-indentation-change >actual.raw &&
-	grep -v "index" actual.raw | test_decode_color >actual &&
+	grep -v "index" actual.raw | tr "\f\v" "^|" | test_decode_color >actual &&
 
 	cat <<-\EOF >expected &&
 	<BOLD>diff --git a/text.txt b/text.txt<RESET>
 	<BOLD>--- a/text.txt<RESET>
 	<BOLD>+++ b/text.txt<RESET>
 	<CYAN>@@ -1,16 +1,16 @@<RESET>
-	<BOLD;MAGENTA>-<RESET>
-	<BOLD;MAGENTA>-<RESET><BOLD;MAGENTA>    too short without<RESET>
-	<BOLD;MAGENTA>-<RESET>
+	<BOLD;MAGENTA>-<RESET><BOLD;MAGENTA>^<RESET><BRED>  <RESET>
+	<BOLD;MAGENTA>-<RESET><BOLD;MAGENTA>|    too short without<RESET>
+	<BOLD;MAGENTA>-<RESET><BOLD;MAGENTA>^<RESET>
 	<BOLD;MAGENTA>-<RESET><BOLD;MAGENTA>   being grouped across blank line<RESET>
 	<BOLD;MAGENTA>-<RESET>
 	 <RESET>context<RESET>
@@ -2097,7 +2280,7 @@ test_expect_success 'compare mixed whitespace delta across moved blocks' '
 	<BOLD;YELLOW>+<RESET>
 	<BOLD;YELLOW>+<RESET>		<BOLD;YELLOW>too short without<RESET>
 	<BOLD;YELLOW>+<RESET>
-	<BOLD;YELLOW>+<RESET>	<BOLD;YELLOW>       being grouped across blank line<RESET>
+	<BOLD;YELLOW>+<RESET><BOLD;YELLOW>^	       being grouped across blank line<RESET>
 	<BOLD;YELLOW>+<RESET>
 	<BOLD;CYAN>+<RESET>	<BRED> <RESET>	<BOLD;CYAN>These two lines have had their<RESET>
 	<BOLD;CYAN>+<RESET><BOLD;CYAN>indentation reduced by four spaces<RESET>