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>

2 files changed, 49 insertions, 2 deletions

diff --git a/xdiff/xdiff.h b/xdiff/xdiff.h
index 032e3a9..7a04605 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 bd03513..380eb72 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) {