diff: add -I<regex> that ignores matching changes

Add a new diff option that enables ignoring changes whose all lines
(changed, removed, and added) match a given regular expression.  This is
similar to the -I/--ignore-matching-lines option in standalone diff
utilities and can be used e.g. to ignore changes which only affect code
comments or to look for unrelated changes in commits containing a large
number of automatically applied modifications (e.g. a tree-wide string
replacement).  The difference between -G/-S and the new -I option is
that the latter filters output on a per-change basis.

Use the 'ignore' field of xdchange_t for marking a change as ignored or
not.  Since the same field is used by --ignore-blank-lines, identical
hunk emitting rules apply for --ignore-blank-lines and -I.  These two
options can also be used together in the same git invocation (they are
complementary to each other).

Rename xdl_mark_ignorable() to xdl_mark_ignorable_lines(), to indicate
that it is logically a "sibling" of xdl_mark_ignorable_regex() rather
than its "parent".

Signed-off-by: Michał Kępień <michal@isc.org>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

7 files changed, 221 insertions, 2 deletions

diff --git a/Documentation/diff-options.txt b/Documentation/diff-options.txt
index 7987d72b02..012daf9452 100644
--- a/Documentation/diff-options.txt
+++ b/Documentation/diff-options.txt
@@ -681,6 +681,11 @@ endif::git-format-patch[]
 --ignore-blank-lines::
 	Ignore changes whose lines are all blank.
 
+-I<regex>::
+--ignore-matching-lines=<regex>::
+	Ignore changes whose all lines match <regex>.  This option may
+	be specified more than once.
+
 --inter-hunk-context=<lines>::
 	Show the context between diff hunks, up to the specified number
 	of lines, thereby fusing hunks that are close to each other.
diff --git a/diff.c b/diff.c
index d24aaa3047..92e247fb83 100644
--- a/diff.c
+++ b/diff.c
@@ -3584,6 +3584,8 @@ static void builtin_diff(const char *name_a,
 		if (header.len && !o->flags.suppress_diff_headers)
 			ecbdata.header = &header;
 		xpp.flags = o->xdl_opts;
+		xpp.ignore_regex = o->ignore_regex;
+		xpp.ignore_regex_nr = o->ignore_regex_nr;
 		xpp.anchors = o->anchors;
 		xpp.anchors_nr = o->anchors_nr;
 		xecfg.ctxlen = o->context;
@@ -3711,6 +3713,8 @@ static void builtin_diffstat(const char *name_a, const char *name_b,
 		memset(&xpp, 0, sizeof(xpp));
 		memset(&xecfg, 0, sizeof(xecfg));
 		xpp.flags = o->xdl_opts;
+		xpp.ignore_regex = o->ignore_regex;
+		xpp.ignore_regex_nr = o->ignore_regex_nr;
 		xpp.anchors = o->anchors;
 		xpp.anchors_nr = o->anchors_nr;
 		xecfg.ctxlen = o->context;
@@ -5174,6 +5178,22 @@ static int diff_opt_patience(const struct option *opt,
 	return 0;
 }
 
+static int diff_opt_ignore_regex(const struct option *opt,
+				 const char *arg, int unset)
+{
+	struct diff_options *options = opt->value;
+	regex_t *regex;
+
+	BUG_ON_OPT_NEG(unset);
+	regex = xmalloc(sizeof(*regex));
+	if (regcomp(regex, arg, REG_EXTENDED | REG_NEWLINE))
+		return error(_("invalid regex given to -I: '%s'"), arg);
+	ALLOC_GROW(options->ignore_regex, options->ignore_regex_nr + 1,
+		   options->ignore_regex_alloc);
+	options->ignore_regex[options->ignore_regex_nr++] = regex;
+	return 0;
+}
+
 static int diff_opt_pickaxe_regex(const struct option *opt,
 				  const char *arg, int unset)
 {
@@ -5462,6 +5482,9 @@ static void prep_parse_options(struct diff_options *options)
 		OPT_BIT_F(0, "ignore-blank-lines", &options->xdl_opts,
 			  N_("ignore changes whose lines are all blank"),
 			  XDF_IGNORE_BLANK_LINES, PARSE_OPT_NONEG),
+		OPT_CALLBACK_F('I', "ignore-matching-lines", options, N_("<regex>"),
+			       N_("ignore changes whose all lines match <regex>"),
+			       0, diff_opt_ignore_regex),
 		OPT_BIT(0, "indent-heuristic", &options->xdl_opts,
 			N_("heuristic to shift diff hunk boundaries for easy reading"),
 			XDF_INDENT_HEURISTIC),
diff --git a/diff.h b/diff.h
index 9443dc1b00..976f83e031 100644
--- a/diff.h
+++ b/diff.h
@@ -234,6 +234,10 @@ struct diff_options {
 	 */
 	const char *pickaxe;
 
+	/* -I<regex> */
+	regex_t **ignore_regex;
+	size_t ignore_regex_nr, ignore_regex_alloc;
+
 	const char *single_follow;
 	const char *a_prefix, *b_prefix;
 	const char *line_prefix;
diff --git a/t/t4013-diff-various.sh b/t/t4013-diff-various.sh
index 43267d6024..585ceedb13 100755
--- a/t/t4013-diff-various.sh
+++ b/t/t4013-diff-various.sh
@@ -6,6 +6,7 @@
 test_description='Various diff formatting options'
 
 . ./test-lib.sh
+. "$TEST_DIRECTORY"/diff-lib.sh
 
 test_expect_success setup '
 
@@ -309,6 +310,7 @@ log -SF master --max-count=2
 log -GF master
 log -GF -p master
 log -GF -p --pickaxe-all master
+log -IA -IB -I1 -I2 -p master
 log --decorate --all
 log --decorate=full --all
 
@@ -449,4 +451,43 @@ test_expect_success 'diff-tree --stdin with log formatting' '
 	test_cmp expect actual
 '
 
+test_expect_success 'diff -I<regex>: setup' '
+	git checkout master &&
+	test_seq 50 >file0 &&
+	git commit -m "Set up -I<regex> test file" file0 &&
+	test_seq 50 | sed -e "s/13/ten and three/" -e "/7\$/d" >file0 &&
+	echo >>file0
+'
+test_expect_success 'diff -I<regex>' '
+	git diff --ignore-blank-lines -I"ten.*e" -I"^[124-9]" >actual &&
+	cat >expect <<-\EOF &&
+	diff --git a/file0 b/file0
+	--- a/file0
+	+++ b/file0
+	@@ -34,7 +31,6 @@
+	 34
+	 35
+	 36
+	-37
+	 38
+	 39
+	 40
+	EOF
+	compare_diff_patch expect actual
+'
+
+test_expect_success 'diff -I<regex> --stat' '
+	git diff --stat --ignore-blank-lines -I"ten.*e" -I"^[124-9]" >actual &&
+	cat >expect <<-\EOF &&
+	 file0 | 1 -
+	 1 file changed, 1 deletion(-)
+	EOF
+	test_cmp expect actual
+'
+
+test_expect_success 'diff -I<regex>: detect malformed regex' '
+	test_expect_code 129 git diff --ignore-matching-lines="^[124-9" 2>error &&
+	test_i18ngrep "invalid regex given to -I: " error
+'
+
 test_done
diff --git a/t/t4013/diff.log_-IA_-IB_-I1_-I2_-p_master b/t/t4013/diff.log_-IA_-IB_-I1_-I2_-p_master
new file mode 100644
index 0000000000..929f35a05b
--- /dev/null
+++ b/t/t4013/diff.log_-IA_-IB_-I1_-I2_-p_master
@@ -0,0 +1,99 @@
+$ git log -IA -IB -I1 -I2 -p master
+commit 59d314ad6f356dd08601a4cd5e530381da3e3c64
+Merge: 9a6d494 c7a2ab9
+Author: A U Thor <author@example.com>
+Date:   Mon Jun 26 00:04:00 2006 +0000
+
+    Merge branch 'side'
+
+commit c7a2ab9e8eac7b117442a607d5a9b3950ae34d5a
+Author: A U Thor <author@example.com>
+Date:   Mon Jun 26 00:03:00 2006 +0000
+
+    Side
+
+diff --git a/file0 b/file0
+index 01e79c3..f4615da 100644
+--- a/file0
++++ b/file0
+@@ -1,3 +1,6 @@
+ 1
+ 2
+ 3
++A
++B
++C
+diff --git a/file3 b/file3
+new file mode 100644
+index 0000000..7289e35
+
+commit 9a6d4949b6b76956d9d5e26f2791ec2ceff5fdc0
+Author: A U Thor <author@example.com>
+Date:   Mon Jun 26 00:02:00 2006 +0000
+
+    Third
+
+diff --git a/dir/sub b/dir/sub
+index 8422d40..cead32e 100644
+--- a/dir/sub
++++ b/dir/sub
+@@ -2,3 +2,5 @@ A
+ B
+ C
+ D
++E
++F
+diff --git a/file1 b/file1
+new file mode 100644
+index 0000000..b1e6722
+--- /dev/null
++++ b/file1
+@@ -0,0 +1,3 @@
++A
++B
++C
+
+commit 1bde4ae5f36c8d9abe3a0fce0c6aab3c4a12fe44
+Author: A U Thor <author@example.com>
+Date:   Mon Jun 26 00:01:00 2006 +0000
+
+    Second
+    
+    This is the second commit.
+
+diff --git a/dir/sub b/dir/sub
+index 35d242b..8422d40 100644
+--- a/dir/sub
++++ b/dir/sub
+@@ -1,2 +1,4 @@
+ A
+ B
++C
++D
+diff --git a/file0 b/file0
+index 01e79c3..b414108 100644
+--- a/file0
++++ b/file0
+@@ -1,3 +1,6 @@
+ 1
+ 2
+ 3
++4
++5
++6
+diff --git a/file2 b/file2
+deleted file mode 100644
+index 01e79c3..0000000
+--- a/file2
++++ /dev/null
+@@ -1,3 +0,0 @@
+-1
+-2
+-3
+
+commit 444ac553ac7612cc88969031b02b3767fb8a353a
+Author: A U Thor <author@example.com>
+Date:   Mon Jun 26 00:00:00 2006 +0000
+
+    Initial
+$
diff --git a/xdiff/xdiff.h b/xdiff/xdiff.h
index 032e3a9f41..7a04605146 100644
--- a/xdiff/xdiff.h
+++ b/xdiff/xdiff.h
@@ -79,6 +79,10 @@ typedef struct s_mmbuffer {
 typedef struct s_xpparam {
 	unsigned long flags;
 
+	/* -I<regex> */
+	regex_t **ignore_regex;
+	size_t ignore_regex_nr;
+
 	/* See Documentation/diff-options.txt. */
 	char **anchors;
 	size_t anchors_nr;
diff --git a/xdiff/xdiffi.c b/xdiff/xdiffi.c
index bd035139f9..380eb728ed 100644
--- a/xdiff/xdiffi.c
+++ b/xdiff/xdiffi.c
@@ -998,7 +998,7 @@ static int xdl_call_hunk_func(xdfenv_t *xe, xdchange_t *xscr, xdemitcb_t *ecb,
 	return 0;
 }
 
-static void xdl_mark_ignorable(xdchange_t *xscr, xdfenv_t *xe, long flags)
+static void xdl_mark_ignorable_lines(xdchange_t *xscr, xdfenv_t *xe, long flags)
 {
 	xdchange_t *xch;
 
@@ -1019,6 +1019,46 @@ static void xdl_mark_ignorable(xdchange_t *xscr, xdfenv_t *xe, long flags)
 	}
 }
 
+static int record_matches_regex(xrecord_t *rec, xpparam_t const *xpp) {
+	regmatch_t regmatch;
+	int i;
+
+	for (i = 0; i < xpp->ignore_regex_nr; i++)
+		if (!regexec_buf(xpp->ignore_regex[i], rec->ptr, rec->size, 1,
+				 &regmatch, 0))
+			return 1;
+
+	return 0;
+}
+
+static void xdl_mark_ignorable_regex(xdchange_t *xscr, const xdfenv_t *xe,
+				     xpparam_t const *xpp)
+{
+	xdchange_t *xch;
+
+	for (xch = xscr; xch; xch = xch->next) {
+		xrecord_t **rec;
+		int ignore = 1;
+		long i;
+
+		/*
+		 * Do not override --ignore-blank-lines.
+		 */
+		if (xch->ignore)
+			continue;
+
+		rec = &xe->xdf1.recs[xch->i1];
+		for (i = 0; i < xch->chg1 && ignore; i++)
+			ignore = record_matches_regex(rec[i], xpp);
+
+		rec = &xe->xdf2.recs[xch->i2];
+		for (i = 0; i < xch->chg2 && ignore; i++)
+			ignore = record_matches_regex(rec[i], xpp);
+
+		xch->ignore = ignore;
+	}
+}
+
 int xdl_diff(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp,
 	     xdemitconf_t const *xecfg, xdemitcb_t *ecb) {
 	xdchange_t *xscr;
@@ -1038,7 +1078,10 @@ int xdl_diff(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp,
 	}
 	if (xscr) {
 		if (xpp->flags & XDF_IGNORE_BLANK_LINES)
-			xdl_mark_ignorable(xscr, &xe, xpp->flags);
+			xdl_mark_ignorable_lines(xscr, &xe, xpp->flags);
+
+		if (xpp->ignore_regex)
+			xdl_mark_ignorable_regex(xscr, &xe, xpp);
 
 		if (ef(&xe, xscr, ecb, xecfg) < 0) {