Merge branch 'sb/diff-color-move-more'

"git diff --color-moved" feature has further been tweaked.

* sb/diff-color-move-more:
  diff.c: offer config option to control ws handling in move detection
  diff.c: add white space mode to move detection that allows indent changes
  diff.c: factor advance_or_nullify out of mark_color_as_moved
  diff.c: decouple white space treatment from move detection algorithm
  diff.c: add a blocks mode for moved code detection
  diff.c: adjust hash function signature to match hashmap expectation
  diff.c: do not pass diff options as keydata to hashmap
  t4015: avoid git as a pipe input
  xdiff/xdiffi.c: remove unneeded function declarations
  xdiff/xdiff.h: remove unused flags

Documentation/config.txt

@@ -1152,6 +1152,11 @@ diff.colorMoved::
 	true the default color mode will be used. When set to false,
 	moved lines are not colored.
 
+diff.colorMovedWS::
+	When moved lines are colored using e.g. the `diff.colorMoved` setting,
+	this option controls the `<mode>` how spaces are treated
+	for details of valid modes see '--color-moved-ws' in linkgit:git-diff[1].
+
 color.diff.<slot>::
 	Use customized color for diff colorization.  `<slot>` specifies
 	which part of the patch to use the specified color, and is one

Documentation/diff-options.txt

@@ -276,10 +276,14 @@ plain::
 	that are added somewhere else in the diff. This mode picks up any
 	moved line, but it is not very useful in a review to determine
 	if a block of code was moved without permutation.
-zebra::
+blocks::
 	Blocks of moved text of at least 20 alphanumeric characters
 	are detected greedily. The detected blocks are
-	painted using either the 'color.diff.{old,new}Moved' color or
+	painted using either the 'color.diff.{old,new}Moved' color.
+	Adjacent blocks cannot be told apart.
+zebra::
+	Blocks of moved text are detected as in 'blocks' mode. The blocks
+	are painted using either the 'color.diff.{old,new}Moved' color or
 	'color.diff.{old,new}MovedAlternative'. The change between
 	the two colors indicates that a new block was detected.
 dimmed_zebra::
@@ -288,6 +292,31 @@ dimmed_zebra::
 	blocks are considered interesting, the rest is uninteresting.
 --
 
+--color-moved-ws=<modes>::
+	This configures how white spaces are ignored when performing the
+	move detection for `--color-moved`.
+ifdef::git-diff[]
+	It can be set by the `diff.colorMovedWS` configuration setting.
+endif::git-diff[]
+	These modes can be given as a comma separated list:
++
+--
+ignore-space-at-eol::
+	Ignore changes in whitespace at EOL.
+ignore-space-change::
+	Ignore changes in amount of whitespace.  This ignores whitespace
+	at line end, and considers all other sequences of one or
+	more whitespace characters to be equivalent.
+ignore-all-space::
+	Ignore whitespace when comparing lines. This ignores differences
+	even if one line has whitespace where the other line has none.
+allow-indentation-change::
+	Initially ignore any white spaces in the move detection, then
+	group the moved code blocks only into a block if the change in
+	whitespace is the same per line. This is incompatible with the
+	other modes.
+--
+
 --word-diff[=<mode>]::
 	Show a word diff, using the <mode> to delimit changed words.
 	By default, words are delimited by whitespace; see

diff.c

@@ -37,6 +37,7 @@ static int diff_rename_limit_default = 400;
 static int diff_suppress_blank_empty;
 static int diff_use_color_default = -1;
 static int diff_color_moved_default;
+static int diff_color_moved_ws_default;
 static int diff_context_default = 3;
 static int diff_interhunk_context_default;
 static const char *diff_word_regex_cfg;
@@ -264,6 +265,8 @@ static int parse_color_moved(const char *arg)
 		return COLOR_MOVED_NO;
 	else if (!strcmp(arg, "plain"))
 		return COLOR_MOVED_PLAIN;
+	else if (!strcmp(arg, "blocks"))
+		return COLOR_MOVED_BLOCKS;
 	else if (!strcmp(arg, "zebra"))
 		return COLOR_MOVED_ZEBRA;
 	else if (!strcmp(arg, "default"))
@@ -271,7 +274,43 @@ static int parse_color_moved(const char *arg)
 	else if (!strcmp(arg, "dimmed_zebra"))
 		return COLOR_MOVED_ZEBRA_DIM;
 	else
-		return error(_("color moved setting must be one of 'no', 'default', 'zebra', 'dimmed_zebra', 'plain'"));
+		return error(_("color moved setting must be one of 'no', 'default', 'blocks', 'zebra', 'dimmed_zebra', 'plain'"));
+}
+
+static int parse_color_moved_ws(const char *arg)
+{
+	int ret = 0;
+	struct string_list l = STRING_LIST_INIT_DUP;
+	struct string_list_item *i;
+
+	string_list_split(&l, arg, ',', -1);
+
+	for_each_string_list_item(i, &l) {
+		struct strbuf sb = STRBUF_INIT;
+		strbuf_addstr(&sb, i->string);
+		strbuf_trim(&sb);
+
+		if (!strcmp(sb.buf, "ignore-space-change"))
+			ret |= XDF_IGNORE_WHITESPACE_CHANGE;
+		else if (!strcmp(sb.buf, "ignore-space-at-eol"))
+			ret |= XDF_IGNORE_WHITESPACE_AT_EOL;
+		else if (!strcmp(sb.buf, "ignore-all-space"))
+			ret |= XDF_IGNORE_WHITESPACE;
+		else if (!strcmp(sb.buf, "allow-indentation-change"))
+			ret |= COLOR_MOVED_WS_ALLOW_INDENTATION_CHANGE;
+		else
+			error(_("ignoring unknown color-moved-ws mode '%s'"), sb.buf);
+
+		strbuf_release(&sb);
+	}
+
+	if ((ret & COLOR_MOVED_WS_ALLOW_INDENTATION_CHANGE) &&
+	    (ret & XDF_WHITESPACE_FLAGS))
+		die(_("color-moved-ws: allow-indentation-change cannot be combined with other white space modes"));
+
+	string_list_clear(&l, 0);
+
+	return ret;
 }
 
 int git_diff_ui_config(const char *var, const char *value, void *cb)
@@ -287,6 +326,13 @@ int git_diff_ui_config(const char *var, const char *value, void *cb)
 		diff_color_moved_default = cm;
 		return 0;
 	}
+	if (!strcmp(var, "diff.colormovedws")) {
+		int cm = parse_color_moved_ws(value);
+		if (cm < 0)
+			return -1;
+		diff_color_moved_ws_default = cm;
+		return 0;
+	}
 	if (!strcmp(var, "diff.context")) {
 		diff_context_default = git_config_int(var, value);
 		if (diff_context_default < 0)
@@ -698,16 +744,116 @@ struct moved_entry {
 	struct hashmap_entry ent;
 	const struct emitted_diff_symbol *es;
 	struct moved_entry *next_line;
+	struct ws_delta *wsd;
 };
 
-static int moved_entry_cmp(const struct diff_options *diffopt,
+/**
-			   const struct moved_entry *a,
+ * The struct ws_delta holds white space differences between moved lines, i.e.
-			   const struct moved_entry *b,
+ * between '+' and '-' lines that have been detected to be a move.
+ * The string contains the difference in leading white spaces, before the
+ * rest of the line is compared using the white space config for move
+ * coloring. The current_longer indicates if the first string in the
+ * comparision is longer than the second.
+ */
+struct ws_delta {
+	char *string;
+	unsigned int current_longer : 1;
+};
+#define WS_DELTA_INIT { NULL, 0 }
+
+static int compute_ws_delta(const struct emitted_diff_symbol *a,
+			     const struct emitted_diff_symbol *b,
+			     struct ws_delta *out)
+{
+	const struct emitted_diff_symbol *longer =  a->len > b->len ? a : b;
+	const struct emitted_diff_symbol *shorter = a->len > b->len ? b : a;
+	int d = longer->len - shorter->len;
+
+	out->string = xmemdupz(longer->line, d);
+	out->current_longer = (a == longer);
+
+	return !strncmp(longer->line + d, shorter->line, shorter->len);
+}
+
+static int cmp_in_block_with_wsd(const struct diff_options *o,
+				 const struct moved_entry *cur,
+				 const struct moved_entry *match,
+				 struct moved_entry *pmb,
+				 int n)
+{
+	struct emitted_diff_symbol *l = &o->emitted_symbols->buf[n];
+	int al = cur->es->len, cl = l->len;
+	const char *a = cur->es->line,
+		   *b = match->es->line,
+		   *c = l->line;
+
+	int wslen;
+
+	/*
+	 * We need to check if 'cur' is equal to 'match'.
+	 * As those are from the same (+/-) side, we do not need to adjust for
+	 * indent changes. However these were found using fuzzy matching
+	 * so we do have to check if they are equal.
+	 */
+	if (strcmp(a, b))
+		return 1;
+
+	if (!pmb->wsd)
+		/*
+		 * No white space delta was carried forward? This can happen
+		 * when we exit early in this function and do not carry
+		 * forward ws.
+		 */
+		return 1;
+
+	/*
+	 * The indent changes of the block are known and carried forward in
+	 * pmb->wsd; however we need to check if the indent changes of the
+	 * current line are still the same as before.
+	 *
+	 * To do so we need to compare 'l' to 'cur', adjusting the
+	 * one of them for the white spaces, depending which was longer.
+	 */
+
+	wslen = strlen(pmb->wsd->string);
+	if (pmb->wsd->current_longer) {
+		c += wslen;
+		cl -= wslen;
+	} else {
+		a += wslen;
+		al -= wslen;
+	}
+
+	if (strcmp(a, c))
+		return 1;
+
+	return 0;
+}
+
+static int moved_entry_cmp(const void *hashmap_cmp_fn_data,
+			   const void *entry,
+			   const void *entry_or_key,
 			   const void *keydata)
 {
+	const struct diff_options *diffopt = hashmap_cmp_fn_data;
+	const struct moved_entry *a = entry;
+	const struct moved_entry *b = entry_or_key;
+	unsigned flags = diffopt->color_moved_ws_handling
+			 & XDF_WHITESPACE_FLAGS;
+
+	if (diffopt->color_moved_ws_handling &
+	    COLOR_MOVED_WS_ALLOW_INDENTATION_CHANGE)
+		/*
+		 * As there is not specific white space config given,
+		 * we'd need to check for a new block, so ignore all
+		 * white space. The setup of the white space
+		 * configuration for the next block is done else where
+		 */
+		flags |= XDF_IGNORE_WHITESPACE;
+
 	return !xdiff_compare_lines(a->es->line, a->es->len,
 				    b->es->line, b->es->len,
-				    diffopt->xdl_opts);
+				    flags);
 }
 
 static struct moved_entry *prepare_entry(struct diff_options *o,
@@ -715,10 +861,12 @@ static struct moved_entry *prepare_entry(struct diff_options *o,
 {
 	struct moved_entry *ret = xmalloc(sizeof(*ret));
 	struct emitted_diff_symbol *l = &o->emitted_symbols->buf[line_no];
+	unsigned flags = o->color_moved_ws_handling & XDF_WHITESPACE_FLAGS;
 
-	ret->ent.hash = xdiff_hash_string(l->line, l->len, o->xdl_opts);
+	ret->ent.hash = xdiff_hash_string(l->line, l->len, flags);
 	ret->es = l;
 	ret->next_line = NULL;
+	ret->wsd = NULL;
 
 	return ret;
 }
@@ -755,6 +903,56 @@ static void add_lines_to_move_detection(struct diff_options *o,
 	}
 }
 
+static void pmb_advance_or_null(struct diff_options *o,
+				struct moved_entry *match,
+				struct hashmap *hm,
+				struct moved_entry **pmb,
+				int pmb_nr)
+{
+	int i;
+	for (i = 0; i < pmb_nr; i++) {
+		struct moved_entry *prev = pmb[i];
+		struct moved_entry *cur = (prev && prev->next_line) ?
+				prev->next_line : NULL;
+		if (cur && !hm->cmpfn(o, cur, match, NULL)) {
+			pmb[i] = cur;
+		} else {
+			pmb[i] = NULL;
+		}
+	}
+}
+
+static void pmb_advance_or_null_multi_match(struct diff_options *o,
+					    struct moved_entry *match,
+					    struct hashmap *hm,
+					    struct moved_entry **pmb,
+					    int pmb_nr, int n)
+{
+	int i;
+	char *got_match = xcalloc(1, pmb_nr);
+
+	for (; match; match = hashmap_get_next(hm, match)) {
+		for (i = 0; i < pmb_nr; i++) {
+			struct moved_entry *prev = pmb[i];
+			struct moved_entry *cur = (prev && prev->next_line) ?
+					prev->next_line : NULL;
+			if (!cur)
+				continue;
+			if (!cmp_in_block_with_wsd(o, cur, match, pmb[i], n))
+				got_match[i] |= 1;
+		}
+	}
+
+	for (i = 0; i < pmb_nr; i++) {
+		if (got_match[i]) {
+			/* Carry the white space delta forward */
+			pmb[i]->next_line->wsd = pmb[i]->wsd;
+			pmb[i] = pmb[i]->next_line;
+		} else
+			pmb[i] = NULL;
+	}
+}
+
 static int shrink_potential_moved_blocks(struct moved_entry **pmb,
 					 int pmb_nr)
 {
@@ -772,6 +970,10 @@ static int shrink_potential_moved_blocks(struct moved_entry **pmb,
 
 		if (lp < pmb_nr && rp > -1 && lp < rp) {
 			pmb[lp] = pmb[rp];
+			if (pmb[rp]->wsd) {
+				free(pmb[rp]->wsd->string);
+				FREE_AND_NULL(pmb[rp]->wsd);
+			}
 			pmb[rp] = NULL;
 			rp--;
 			lp++;
@@ -829,19 +1031,18 @@ static void mark_color_as_moved(struct diff_options *o,
 		struct moved_entry *key;
 		struct moved_entry *match = NULL;
 		struct emitted_diff_symbol *l = &o->emitted_symbols->buf[n];
-		int i;
 
 		switch (l->s) {
 		case DIFF_SYMBOL_PLUS:
 			hm = del_lines;
 			key = prepare_entry(o, n);
-			match = hashmap_get(hm, key, o);
+			match = hashmap_get(hm, key, NULL);
 			free(key);
 			break;
 		case DIFF_SYMBOL_MINUS:
 			hm = add_lines;
 			key = prepare_entry(o, n);
-			match = hashmap_get(hm, key, o);
+			match = hashmap_get(hm, key, NULL);
 			free(key);
 			break;
 		default:
@@ -860,17 +1061,11 @@ static void mark_color_as_moved(struct diff_options *o,
 		if (o->color_moved == COLOR_MOVED_PLAIN)
 			continue;
 
-		/* Check any potential block runs, advance each or nullify */
+		if (o->color_moved_ws_handling &
-		for (i = 0; i < pmb_nr; i++) {
+		    COLOR_MOVED_WS_ALLOW_INDENTATION_CHANGE)
-			struct moved_entry *p = pmb[i];
+			pmb_advance_or_null_multi_match(o, match, hm, pmb, pmb_nr, n);
-			struct moved_entry *pnext = (p && p->next_line) ?
+		else
-					p->next_line : NULL;
+			pmb_advance_or_null(o, match, hm, pmb, pmb_nr);
-			if (pnext && !hm->cmpfn(o, pnext, match, NULL)) {
-				pmb[i] = p->next_line;
-			} else {
-				pmb[i] = NULL;
-			}
-		}
 
 		pmb_nr = shrink_potential_moved_blocks(pmb, pmb_nr);
 
@@ -881,7 +1076,17 @@ static void mark_color_as_moved(struct diff_options *o,
 			 */
 			for (; match; match = hashmap_get_next(hm, match)) {
 				ALLOC_GROW(pmb, pmb_nr + 1, pmb_alloc);
+				if (o->color_moved_ws_handling &
+				    COLOR_MOVED_WS_ALLOW_INDENTATION_CHANGE) {
+					struct ws_delta *wsd = xmalloc(sizeof(*match->wsd));
+					if (compute_ws_delta(l, match->es, wsd)) {
+						match->wsd = wsd;
 						pmb[pmb_nr++] = match;
+					} else
+						free(wsd);
+				} else {
+					pmb[pmb_nr++] = match;
+				}
 			}
 
 			flipped_block = (flipped_block + 1) % 2;
@@ -892,7 +1097,7 @@ static void mark_color_as_moved(struct diff_options *o,
 
 		block_length++;
 
-		if (flipped_block)
+		if (flipped_block && o->color_moved != COLOR_MOVED_BLOCKS)
 			l->flags |= DIFF_SYMBOL_MOVED_LINE_ALT;
 	}
 	adjust_last_block(o, n, block_length);
@@ -4125,6 +4330,7 @@ void diff_setup(struct diff_options *options)
 	}
 
 	options->color_moved = diff_color_moved_default;
+	options->color_moved_ws_handling = diff_color_moved_ws_default;
 }
 
 void diff_setup_done(struct diff_options *options)
@@ -4704,6 +4910,8 @@ int diff_opt_parse(struct diff_options *options,
 		if (cm < 0)
 			die("bad --color-moved argument: %s", arg);
 		options->color_moved = cm;
+	} else if (skip_prefix(arg, "--color-moved-ws=", &arg)) {
+		options->color_moved_ws_handling = parse_color_moved_ws(arg);
 	} else if (skip_to_optional_arg_default(arg, "--color-words", &options->word_regex, NULL)) {
 		options->use_color = 1;
 		options->word_diff = DIFF_WORDS_COLOR;
@@ -5534,10 +5742,12 @@ static void diff_flush_patch_all_file_pairs(struct diff_options *o)
 		if (o->color_moved) {
 			struct hashmap add_lines, del_lines;
 
-			hashmap_init(&del_lines,
+			if (o->color_moved_ws_handling &
-				     (hashmap_cmp_fn)moved_entry_cmp, o, 0);
+			    COLOR_MOVED_WS_ALLOW_INDENTATION_CHANGE)
-			hashmap_init(&add_lines,
+				o->color_moved_ws_handling |= XDF_IGNORE_WHITESPACE;
-				     (hashmap_cmp_fn)moved_entry_cmp, o, 0);
+
+			hashmap_init(&del_lines, moved_entry_cmp, o, 0);
+			hashmap_init(&add_lines, moved_entry_cmp, o, 0);
 
 			add_lines_to_move_detection(o, &add_lines, &del_lines);
 			mark_color_as_moved(o, &add_lines, &del_lines);

diff.h

@@ -208,11 +208,16 @@ struct diff_options {
 	enum {
 		COLOR_MOVED_NO = 0,
 		COLOR_MOVED_PLAIN = 1,
-		COLOR_MOVED_ZEBRA = 2,
+		COLOR_MOVED_BLOCKS = 2,
-		COLOR_MOVED_ZEBRA_DIM = 3,
+		COLOR_MOVED_ZEBRA = 3,
+		COLOR_MOVED_ZEBRA_DIM = 4,
 	} color_moved;
 	#define COLOR_MOVED_DEFAULT COLOR_MOVED_ZEBRA
 	#define COLOR_MOVED_MIN_ALNUM_COUNT 20
+
+	/* XDF_WHITESPACE_FLAGS regarding block detection are set at 2, 3, 4 */
+	#define COLOR_MOVED_WS_ALLOW_INDENTATION_CHANGE (1<<5)
+	int color_moved_ws_handling;
 };
 
 void diff_emit_submodule_del(struct diff_options *o, const char *line);

t/t4015-diff-whitespace.sh

@@ -1223,7 +1223,7 @@ test_expect_success 'plain moved code, inside file' '
 	test_cmp expected actual
 '
 
-test_expect_success 'detect permutations inside moved code -- dimmed_zebra' '
+test_expect_success 'detect blocks of moved code' '
 	git reset --hard &&
 	cat <<-\EOF >lines.txt &&
 		long line 1
@@ -1271,9 +1271,52 @@ test_expect_success 'detect permutations inside moved code -- dimmed_zebra' '
 	test_config color.diff.newMovedDimmed "normal cyan" &&
 	test_config color.diff.oldMovedAlternativeDimmed "normal blue" &&
 	test_config color.diff.newMovedAlternativeDimmed "normal yellow" &&
-	git diff HEAD --no-renames --color-moved=dimmed_zebra --color |
+	git diff HEAD --no-renames --color-moved=blocks --color >actual.raw &&
-		grep -v "index" |
+	grep -v "index" actual.raw | test_decode_color >actual &&
-		test_decode_color >actual &&
+	cat <<-\EOF >expected &&
+	<BOLD>diff --git a/lines.txt b/lines.txt<RESET>
+	<BOLD>--- a/lines.txt<RESET>
+	<BOLD>+++ b/lines.txt<RESET>
+	<CYAN>@@ -1,16 +1,16 @@<RESET>
+	<MAGENTA>-long line 1<RESET>
+	<MAGENTA>-long line 2<RESET>
+	<MAGENTA>-long line 3<RESET>
+	 line 4<RESET>
+	 line 5<RESET>
+	 line 6<RESET>
+	 line 7<RESET>
+	 line 8<RESET>
+	 line 9<RESET>
+	<CYAN>+<RESET><CYAN>long line 1<RESET>
+	<CYAN>+<RESET><CYAN>long line 2<RESET>
+	<CYAN>+<RESET><CYAN>long line 3<RESET>
+	<CYAN>+<RESET><CYAN>long line 14<RESET>
+	<CYAN>+<RESET><CYAN>long line 15<RESET>
+	<CYAN>+<RESET><CYAN>long line 16<RESET>
+	 line 10<RESET>
+	 line 11<RESET>
+	 line 12<RESET>
+	 line 13<RESET>
+	<MAGENTA>-long line 14<RESET>
+	<MAGENTA>-long line 15<RESET>
+	<MAGENTA>-long line 16<RESET>
+	EOF
+	test_cmp expected actual
+
+'
+
+test_expect_success 'detect permutations inside moved code -- dimmed_zebra' '
+	# reuse setup from test before!
+	test_config color.diff.oldMoved "magenta" &&
+	test_config color.diff.newMoved "cyan" &&
+	test_config color.diff.oldMovedAlternative "blue" &&
+	test_config color.diff.newMovedAlternative "yellow" &&
+	test_config color.diff.oldMovedDimmed "normal magenta" &&
+	test_config color.diff.newMovedDimmed "normal cyan" &&
+	test_config color.diff.oldMovedAlternativeDimmed "normal blue" &&
+	test_config color.diff.newMovedAlternativeDimmed "normal yellow" &&
+	git diff HEAD --no-renames --color-moved=dimmed_zebra --color >actual.raw &&
+	grep -v "index" actual.raw | test_decode_color >actual &&
 	cat <<-\EOF >expected &&
 	<BOLD>diff --git a/lines.txt b/lines.txt<RESET>
 	<BOLD>--- a/lines.txt<RESET>
@@ -1315,9 +1358,8 @@ test_expect_success 'cmd option assumes configured colored-moved' '
 	test_config color.diff.oldMovedAlternativeDimmed "normal blue" &&
 	test_config color.diff.newMovedAlternativeDimmed "normal yellow" &&
 	test_config diff.colorMoved zebra &&
-	git diff HEAD --no-renames --color-moved --color |
+	git diff HEAD --no-renames --color-moved --color >actual.raw &&
-		grep -v "index" |
+	grep -v "index" actual.raw | test_decode_color >actual &&
-		test_decode_color >actual &&
 	cat <<-\EOF >expected &&
 	<BOLD>diff --git a/lines.txt b/lines.txt<RESET>
 	<BOLD>--- a/lines.txt<RESET>
@@ -1395,9 +1437,8 @@ test_expect_success 'move detection ignoring whitespace ' '
 	line 4
 	line 5
 	EOF
-	git diff HEAD --no-renames --color-moved --color |
+	git diff HEAD --no-renames --color-moved --color >actual.raw &&
-		grep -v "index" |
+	grep -v "index" actual.raw | test_decode_color >actual &&
-		test_decode_color >actual &&
 	cat <<-\EOF >expected &&
 	<BOLD>diff --git a/lines.txt b/lines.txt<RESET>
 	<BOLD>--- a/lines.txt<RESET>
@@ -1419,9 +1460,9 @@ test_expect_success 'move detection ignoring whitespace ' '
 	EOF
 	test_cmp expected actual &&
 
-	git diff HEAD --no-renames -w --color-moved --color |
+	git diff HEAD --no-renames --color-moved --color \
-		grep -v "index" |
+		--color-moved-ws=ignore-all-space >actual.raw &&
-		test_decode_color >actual &&
+	grep -v "index" actual.raw | test_decode_color >actual &&
 	cat <<-\EOF >expected &&
 	<BOLD>diff --git a/lines.txt b/lines.txt<RESET>
 	<BOLD>--- a/lines.txt<RESET>
@@ -1459,9 +1500,8 @@ test_expect_success 'move detection ignoring whitespace changes' '
 	line 5
 	EOF
 
-	git diff HEAD --no-renames --color-moved --color |
+	git diff HEAD --no-renames --color-moved --color >actual.raw &&
-		grep -v "index" |
+	grep -v "index" actual.raw | test_decode_color >actual &&
-		test_decode_color >actual &&
 	cat <<-\EOF >expected &&
 	<BOLD>diff --git a/lines.txt b/lines.txt<RESET>
 	<BOLD>--- a/lines.txt<RESET>
@@ -1483,9 +1523,9 @@ test_expect_success 'move detection ignoring whitespace changes' '
 	EOF
 	test_cmp expected actual &&
 
-	git diff HEAD --no-renames -b --color-moved --color |
+	git diff HEAD --no-renames --color-moved --color \
-		grep -v "index" |
+		--color-moved-ws=ignore-space-change >actual.raw &&
-		test_decode_color >actual &&
+	grep -v "index" actual.raw | test_decode_color >actual &&
 	cat <<-\EOF >expected &&
 	<BOLD>diff --git a/lines.txt b/lines.txt<RESET>
 	<BOLD>--- a/lines.txt<RESET>
@@ -1526,9 +1566,8 @@ test_expect_success 'move detection ignoring whitespace at eol' '
 	# avoid cluttering the output with complaints about our eol whitespace
 	test_config core.whitespace -blank-at-eol &&
 
-	git diff HEAD --no-renames --color-moved --color |
+	git diff HEAD --no-renames --color-moved --color >actual.raw &&
-		grep -v "index" |
+	grep -v "index" actual.raw | test_decode_color >actual &&
-		test_decode_color >actual &&
 	cat <<-\EOF >expected &&
 	<BOLD>diff --git a/lines.txt b/lines.txt<RESET>
 	<BOLD>--- a/lines.txt<RESET>
@@ -1550,9 +1589,9 @@ test_expect_success 'move detection ignoring whitespace at eol' '
 	EOF
 	test_cmp expected actual &&
 
-	git diff HEAD --no-renames --ignore-space-at-eol --color-moved --color |
+	git diff HEAD --no-renames --color-moved --color \
-		grep -v "index" |
+		--color-moved-ws=ignore-space-at-eol >actual.raw &&
-		test_decode_color >actual &&
+	grep -v "index" actual.raw | test_decode_color >actual &&
 	cat <<-\EOF >expected &&
 	<BOLD>diff --git a/lines.txt b/lines.txt<RESET>
 	<BOLD>--- a/lines.txt<RESET>
@@ -1597,9 +1636,8 @@ test_expect_success '--color-moved block at end of diff output respects MIN_ALNU
 	irrelevant_line
 	EOF
 
-	git diff HEAD --color-moved=zebra --color --no-renames |
+	git diff HEAD --color-moved=zebra --color --no-renames >actual.raw &&
-		grep -v "index" |
+	grep -v "index" actual.raw | test_decode_color >actual &&
-		test_decode_color >actual &&
 	cat >expected <<-\EOF &&
 	<BOLD>diff --git a/bar b/bar<RESET>
 	<BOLD>--- a/bar<RESET>
@@ -1636,9 +1674,8 @@ test_expect_success '--color-moved respects MIN_ALNUM_COUNT' '
 	nineteen chars 456789
 	EOF
 
-	git diff HEAD --color-moved=zebra --color --no-renames |
+	git diff HEAD --color-moved=zebra --color --no-renames >actual.raw &&
-		grep -v "index" |
+	grep -v "index" actual.raw | test_decode_color >actual &&
-		test_decode_color >actual &&
 	cat >expected <<-\EOF &&
 	<BOLD>diff --git a/bar b/bar<RESET>
 	<BOLD>--- a/bar<RESET>
@@ -1679,7 +1716,8 @@ test_expect_success '--color-moved treats adjacent blocks as separate for MIN_AL
 	7charsA
 	EOF
 
-	git diff HEAD --color-moved=zebra --color --no-renames | grep -v "index" | test_decode_color >actual &&
+	git diff HEAD --color-moved=zebra --color --no-renames >actual.raw &&
+	grep -v "index" actual.raw | test_decode_color >actual &&
 	cat >expected <<-\EOF &&
 	<BOLD>diff --git a/bar b/bar<RESET>
 	<BOLD>--- a/bar<RESET>
@@ -1722,7 +1760,146 @@ test_expect_success 'move detection with submodules' '
 
 	# nor did we mess with it another way
 	git diff --submodule=diff --color | test_decode_color >expect &&
-	test_cmp expect decoded_actual
+	test_cmp expect decoded_actual &&
+	rm -rf bananas &&
+	git submodule deinit bananas
+'
+
+test_expect_success 'only move detection ignores white spaces' '
+	git reset --hard &&
+	q_to_tab <<-\EOF >text.txt &&
+		a long line to exceed per-line minimum
+		another long line to exceed per-line minimum
+		original file
+	EOF
+	git add text.txt &&
+	git commit -m "add text" &&
+	q_to_tab <<-\EOF >text.txt &&
+		Qa long line to exceed per-line minimum
+		Qanother long line to exceed per-line minimum
+		new file
+	EOF
+
+	# Make sure we get a different diff using -w
+	git diff --color --color-moved -w >actual.raw &&
+	grep -v "index" actual.raw | test_decode_color >actual &&
+	q_to_tab <<-\EOF >expected &&
+	<BOLD>diff --git a/text.txt b/text.txt<RESET>
+	<BOLD>--- a/text.txt<RESET>
+	<BOLD>+++ b/text.txt<RESET>
+	<CYAN>@@ -1,3 +1,3 @@<RESET>
+	 Qa long line to exceed per-line minimum<RESET>
+	 Qanother long line to exceed per-line minimum<RESET>
+	<RED>-original file<RESET>
+	<GREEN>+<RESET><GREEN>new file<RESET>
+	EOF
+	test_cmp expected actual &&
+
+	# And now ignoring white space only in the move detection
+	git diff --color --color-moved \
+		--color-moved-ws=ignore-all-space,ignore-space-change,ignore-space-at-eol >actual.raw &&
+	grep -v "index" actual.raw | test_decode_color >actual &&
+	q_to_tab <<-\EOF >expected &&
+	<BOLD>diff --git a/text.txt b/text.txt<RESET>
+	<BOLD>--- a/text.txt<RESET>
+	<BOLD>+++ b/text.txt<RESET>
+	<CYAN>@@ -1,3 +1,3 @@<RESET>
+	<BOLD;MAGENTA>-a long line to exceed per-line minimum<RESET>
+	<BOLD;MAGENTA>-another long line to exceed per-line minimum<RESET>
+	<RED>-original file<RESET>
+	<BOLD;YELLOW>+<RESET>Q<BOLD;YELLOW>a long line to exceed per-line minimum<RESET>
+	<BOLD;YELLOW>+<RESET>Q<BOLD;YELLOW>another long line to exceed per-line minimum<RESET>
+	<GREEN>+<RESET><GREEN>new file<RESET>
+	EOF
+	test_cmp expected actual
+'
+
+test_expect_success 'compare whitespace delta across moved blocks' '
+
+	git reset --hard &&
+	q_to_tab <<-\EOF >text.txt &&
+	QIndented
+	QText across
+	Qsome lines
+	QBut! <- this stands out
+	QAdjusting with
+	QQdifferent starting
+	Qwhite spaces
+	QAnother outlier
+	QQQIndented
+	QQQText across
+	QQQfive lines
+	QQQthat has similar lines
+	QQQto previous blocks, but with different indent
+	QQQYetQAnotherQoutlierQ
+	EOF
+
+	git add text.txt &&
+	git commit -m "add text.txt" &&
+
+	q_to_tab <<-\EOF >text.txt &&
+	QQIndented
+	QQText across
+	QQsome lines
+	QQQBut! <- this stands out
+	Adjusting with
+	Qdifferent starting
+	white spaces
+	AnotherQoutlier
+	QQIndented
+	QQText across
+	QQfive lines
+	QQthat has similar lines
+	QQto previous blocks, but with different indent
+	QQYetQAnotherQoutlier
+	EOF
+
+	git diff --color --color-moved --color-moved-ws=allow-indentation-change >actual.raw &&
+	grep -v "index" actual.raw | test_decode_color >actual &&
+
+	q_to_tab <<-\EOF >expected &&
+		<BOLD>diff --git a/text.txt b/text.txt<RESET>
+		<BOLD>--- a/text.txt<RESET>
+		<BOLD>+++ b/text.txt<RESET>
+		<CYAN>@@ -1,14 +1,14 @@<RESET>
+		<BOLD;MAGENTA>-QIndented<RESET>
+		<BOLD;MAGENTA>-QText across<RESET>
+		<BOLD;MAGENTA>-Qsome lines<RESET>
+		<RED>-QBut! <- this stands out<RESET>
+		<BOLD;MAGENTA>-QAdjusting with<RESET>
+		<BOLD;MAGENTA>-QQdifferent starting<RESET>
+		<BOLD;MAGENTA>-Qwhite spaces<RESET>
+		<RED>-QAnother outlier<RESET>
+		<BOLD;MAGENTA>-QQQIndented<RESET>
+		<BOLD;MAGENTA>-QQQText across<RESET>
+		<BOLD;MAGENTA>-QQQfive lines<RESET>
+		<BOLD;MAGENTA>-QQQthat has similar lines<RESET>
+		<BOLD;MAGENTA>-QQQto previous blocks, but with different indent<RESET>
+		<RED>-QQQYetQAnotherQoutlierQ<RESET>
+		<BOLD;CYAN>+<RESET>QQ<BOLD;CYAN>Indented<RESET>
+		<BOLD;CYAN>+<RESET>QQ<BOLD;CYAN>Text across<RESET>
+		<BOLD;CYAN>+<RESET>QQ<BOLD;CYAN>some lines<RESET>
+		<GREEN>+<RESET>QQQ<GREEN>But! <- this stands out<RESET>
+		<BOLD;CYAN>+<RESET><BOLD;CYAN>Adjusting with<RESET>
+		<BOLD;CYAN>+<RESET>Q<BOLD;CYAN>different starting<RESET>
+		<BOLD;CYAN>+<RESET><BOLD;CYAN>white spaces<RESET>
+		<GREEN>+<RESET><GREEN>AnotherQoutlier<RESET>
+		<BOLD;CYAN>+<RESET>QQ<BOLD;CYAN>Indented<RESET>
+		<BOLD;CYAN>+<RESET>QQ<BOLD;CYAN>Text across<RESET>
+		<BOLD;CYAN>+<RESET>QQ<BOLD;CYAN>five lines<RESET>
+		<BOLD;CYAN>+<RESET>QQ<BOLD;CYAN>that has similar lines<RESET>
+		<BOLD;CYAN>+<RESET>QQ<BOLD;CYAN>to previous blocks, but with different indent<RESET>
+		<GREEN>+<RESET>QQ<GREEN>YetQAnotherQoutlier<RESET>
+	EOF
+
+	test_cmp expected actual
+'
+
+test_expect_success 'compare whitespace delta incompatible with other space options' '
+	test_must_fail git diff \
+		--color-moved-ws=allow-indentation-change,ignore-all-space \
+		2>err &&
+	test_i18ngrep allow-indentation-change err
 '
 
 test_done

xdiff/xdiff.h

@@ -52,14 +52,6 @@ extern "C" {
 #define XDL_EMIT_FUNCNAMES (1 << 0)
 #define XDL_EMIT_FUNCCONTEXT (1 << 2)
 
-#define XDL_MMB_READONLY (1 << 0)
-
-#define XDL_MMF_ATOMIC (1 << 0)
-
-#define XDL_BDOP_INS 1
-#define XDL_BDOP_CPY 2
-#define XDL_BDOP_INSB 3
-
 /* merge simplification levels */
 #define XDL_MERGE_MINIMAL 0
 #define XDL_MERGE_EAGER 1

xdiff/xdiffi.c

@@ -22,34 +22,17 @@
 
 #include "xinclude.h"
 
-
-
 #define XDL_MAX_COST_MIN 256
 #define XDL_HEUR_MIN_COST 256
 #define XDL_LINE_MAX (long)((1UL << (CHAR_BIT * sizeof(long) - 1)) - 1)
 #define XDL_SNAKE_CNT 20
 #define XDL_K_HEUR 4
 
-
-
 typedef struct s_xdpsplit {
 	long i1, i2;
 	int min_lo, min_hi;
 } xdpsplit_t;
 
-
-
-
-static long xdl_split(unsigned long const *ha1, long off1, long lim1,
-		      unsigned long const *ha2, long off2, long lim2,
-		      long *kvdf, long *kvdb, int need_min, xdpsplit_t *spl,
-		      xdalgoenv_t *xenv);
-static xdchange_t *xdl_add_change(xdchange_t *xscr, long i1, long i2, long chg1, long chg2);
-
-
-
-
-
 /*
  * See "An O(ND) Difference Algorithm and its Variations", by Eugene Myers.
  * Basically considers a "box" (off1, off2, lim1, lim2) and scan from both