merge-file: add --diff-algorithm option

Make it possible to use other diff algorithms than the 'myers'
default algorithm, when using the 'git merge-file' command, to help
avoid spurious conflicts by selecting a more recent algorithm such
as 'histogram', for instance when using 'git merge-file' as part of
a custom merge driver.

Signed-off-by: Antonin Delpeuch <antonin@delpeuch.eu>
Reviewed-by: Phillip Wood <phillip.wood@dunelm.org.uk>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

Documentation/git-merge-file.txt

@@ -92,6 +92,12 @@ object store and the object ID of its blob is written to standard output.
 	Instead of leaving conflicts in the file, resolve conflicts
 	favouring our (or their or both) side of the lines.
 
+--diff-algorithm={patience|minimal|histogram|myers}::
+	Use a different diff algorithm while merging. The current default is "myers",
+	but selecting more recent algorithm such as "histogram" can help
+	avoid mismerges that occur due to unimportant matching lines
+	(such as braces from distinct functions). See also
+	linkgit:git-diff[1] `--diff-algorithm`.
 
 EXAMPLES
 --------

builtin/merge-file.c

@@ -1,5 +1,6 @@
 #include "builtin.h"
 #include "abspath.h"
+#include "diff.h"
 #include "hex.h"
 #include "object-name.h"
 #include "object-store.h"
@@ -28,6 +29,30 @@ static int label_cb(const struct option *opt, const char *arg, int unset)
 	return 0;
 }
 
+static int set_diff_algorithm(xpparam_t *xpp,
+			      const char *alg)
+{
+	long diff_algorithm = parse_algorithm_value(alg);
+	if (diff_algorithm < 0)
+		return -1;
+	xpp->flags = (xpp->flags & ~XDF_DIFF_ALGORITHM_MASK) | diff_algorithm;
+	return 0;
+}
+
+static int diff_algorithm_cb(const struct option *opt,
+				const char *arg, int unset)
+{
+	xpparam_t *xpp = opt->value;
+
+	BUG_ON_OPT_NEG(unset);
+
+	if (set_diff_algorithm(xpp, arg))
+		return error(_("option diff-algorithm accepts \"myers\", "
+			       "\"minimal\", \"patience\" and \"histogram\""));
+
+	return 0;
+}
+
 int cmd_merge_file(int argc, const char **argv, const char *prefix)
 {
 	const char *names[3] = { 0 };
@@ -48,6 +73,9 @@ int cmd_merge_file(int argc, const char **argv, const char *prefix)
 			    XDL_MERGE_FAVOR_THEIRS),
 		OPT_SET_INT(0, "union", &xmp.favor, N_("for conflicts, use a union version"),
 			    XDL_MERGE_FAVOR_UNION),
+		OPT_CALLBACK_F(0, "diff-algorithm", &xmp.xpp, N_("<algorithm>"),
+			     N_("choose a diff algorithm"),
+			     PARSE_OPT_NONEG, diff_algorithm_cb),
 		OPT_INTEGER(0, "marker-size", &xmp.marker_size,
 			    N_("for conflicts, use this marker size")),
 		OPT__QUIET(&quiet, N_("do not warn about conflicts")),

t/t6403-merge-file.sh

@@ -56,7 +56,67 @@ test_expect_success 'setup' '
 	deduxit me super semitas jusitiae,
 	EOF
 
-	printf "propter nomen suum." >>new4.txt
+	printf "propter nomen suum." >>new4.txt &&
+
+	cat >base.c <<-\EOF &&
+	int f(int x, int y)
+	{
+		if (x == 0)
+		{
+			return y;
+		}
+		return x;
+	}
+
+	int g(size_t u)
+	{
+		while (u < 30)
+		{
+			u++;
+		}
+		return u;
+	}
+	EOF
+
+	cat >ours.c <<-\EOF &&
+	int g(size_t u)
+	{
+		while (u < 30)
+		{
+			u++;
+		}
+		return u;
+	}
+
+	int h(int x, int y, int z)
+	{
+		if (z == 0)
+		{
+			return x;
+		}
+		return y;
+	}
+	EOF
+
+	cat >theirs.c <<-\EOF
+	int f(int x, int y)
+	{
+		if (x == 0)
+		{
+			return y;
+		}
+		return x;
+	}
+
+	int g(size_t u)
+	{
+		while (u > 34)
+		{
+			u--;
+		}
+		return u;
+	}
+	EOF
 '
 
 test_expect_success 'merge with no changes' '
@@ -447,4 +507,66 @@ test_expect_success '--object-id fails without repository' '
 	grep "not a git repository" err
 '
 
+test_expect_success 'merging C files with "myers" diff algorithm creates some spurious conflicts' '
+	cat >expect.c <<-\EOF &&
+	int g(size_t u)
+	{
+		while (u < 30)
+		{
+			u++;
+		}
+		return u;
+	}
+
+	int h(int x, int y, int z)
+	{
+	<<<<<<< ours.c
+		if (z == 0)
+	||||||| base.c
+		while (u < 30)
+	=======
+		while (u > 34)
+	>>>>>>> theirs.c
+		{
+	<<<<<<< ours.c
+			return x;
+	||||||| base.c
+			u++;
+	=======
+			u--;
+	>>>>>>> theirs.c
+		}
+		return y;
+	}
+	EOF
+
+	test_must_fail git merge-file -p --diff3 --diff-algorithm myers ours.c base.c theirs.c >myers_output.c &&
+	test_cmp expect.c myers_output.c
+'
+
+test_expect_success 'merging C files with "histogram" diff algorithm avoids some spurious conflicts' '
+	cat >expect.c <<-\EOF &&
+	int g(size_t u)
+	{
+		while (u > 34)
+		{
+			u--;
+		}
+		return u;
+	}
+
+	int h(int x, int y, int z)
+	{
+		if (z == 0)
+		{
+			return x;
+		}
+		return y;
+	}
+	EOF
+
+	git merge-file -p --diff3 --diff-algorithm histogram ours.c base.c theirs.c >histogram_output.c &&
+	test_cmp expect.c histogram_output.c
+'
+
 test_done