[PATCH v2 2/3] diff: add -I<regex> that ignores matching changes

["Michał Kępień" <michal@isc.org>]

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 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>
---
 Documentation/diff-options.txt |  4 +++
 diff.c                         | 23 +++++++++++++++++
 diff.h                         |  4 +++
 xdiff/xdiff.h                  |  4 +++
 xdiff/xdiffi.c                 | 47 ++++++++++++++++++++++++++++++++--
 5 files changed, 80 insertions(+), 2 deletions(-)

diff --git a/Documentation/diff-options.txt b/Documentation/diff-options.txt
index 573fb9bb71..f8ccf85173 100644
--- a/Documentation/diff-options.txt
+++ b/Documentation/diff-options.txt
@@ -687,6 +687,10 @@ endif::git-format-patch[]
 --ignore-blank-lines::
 	Ignore changes whose lines are all blank.
 
+-I<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 2bb2f8f57e..c5d4920fee 100644
--- a/diff.c
+++ b/diff.c
@@ -3587,6 +3587,8 @@ 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;
@@ -3716,6 +3718,8 @@ 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;
@@ -5203,6 +5207,22 @@ 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 = xcalloc(1, sizeof(*regex));
+	if (regcomp(regex, arg, REG_EXTENDED | REG_NEWLINE))
+		die("invalid regex: %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)
 {
@@ -5491,6 +5511,9 @@ 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', NULL, 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 11de52e9e9..80dbd3dfdc 100644
--- a/diff.h
+++ b/diff.h
@@ -234,6 +234,10 @@ struct diff_options {
 	 */
 	const char *pickaxe;
 
+	/* see Documentation/diff-options.txt */
+	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/xdiff/xdiff.h b/xdiff/xdiff.h
index 032e3a9f41..883a0d770e 100644
--- a/xdiff/xdiff.h
+++ b/xdiff/xdiff.h
@@ -79,6 +79,10 @@ typedef struct s_mmbuffer {
 typedef struct s_xpparam {
 	unsigned long flags;
 
+	/* See Documentation/diff-options.txt. */
+	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) {
 
-- 
2.28.0