diff: Teach diff to read attribute diff-algorithm

It can be useful to specify diff algorithms per file type. For example,
one may want to use the minimal diff algorithm for .json files, another
for .c files, etc.

Teach the diff machinery to check attributes for a diff algorithm.
Enforce precedence by favoring the command line option, then looking at
attributes, then finally the config.

To enforce precedence order, swap out options parsing for "minimal" and
"histogram" into `OPT_CALLBACK_F` so we can set the
`xdl_opts_command_line` member.

Signed-off-by: John Cai <johncai86@gmail.com>

Documentation/gitattributes.txt

@@ -736,6 +736,29 @@ String::
 	by the configuration variables in the "diff.foo" section of the
 	Git config file.
 
+`diff-algorithm`
+^^^^^^^^^^^^^^^^
+
+The attribute `diff-algorithm` affects which algorithm Git uses to generate
+diffs. This allows defining diff algorithms per file extension. Precedence rules
+are as follows, in order from highest to lowest:
+
+*Command line option*
+
+Pass in the `--diff-algorithm` command line option int git-diff(1)
+
+*Git attributes*
+
+------------------------
+*.json	diff-algorithm=histogram
+------------------------
+
+*Git config*
+
+----------------------------------------------------------------
+[diff]
+	algorithm = histogram
+----------------------------------------------------------------
 
 Defining an external diff driver
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

builtin/diff.c

@@ -13,6 +13,7 @@
 #include "blob.h"
 #include "tag.h"
 #include "diff.h"
+#include "xdiff-interface.h"
 #include "diff-merges.h"
 #include "diffcore.h"
 #include "revision.h"

diff-no-index.c

@@ -10,6 +10,7 @@
 #include "blob.h"
 #include "tag.h"
 #include "diff.h"
+#include "xdiff-interface.h"
 #include "diffcore.h"
 #include "revision.h"
 #include "log-tree.h"

diff.c

@@ -3652,6 +3652,27 @@ static void builtin_diff(const char *name_a,
 		ecbdata.opt = o;
 		if (header.len && !o->flags.suppress_diff_headers)
 			ecbdata.header = &header;
+
+		if (!o->xdl_opts_command_line) {
+			static struct attr_check *check;
+			const char *one_diff_algo;
+			const char *two_diff_algo;
+
+			check = attr_check_alloc();
+			attr_check_append(check, git_attr("diff-algorithm"));
+
+			git_check_attr(the_repository->index, NULL, one->path, check);
+			one_diff_algo = check->items[0].value;
+			git_check_attr(the_repository->index, NULL, two->path, check);
+			two_diff_algo = check->items[0].value;
+
+			if (!ATTR_UNSET(one_diff_algo) && !ATTR_UNSET(two_diff_algo) &&
+				!strcmp(one_diff_algo, two_diff_algo))
+				set_diff_algorithm(o, one_diff_algo);
+
+			attr_check_free(check);
+		}
+
 		xpp.flags = o->xdl_opts;
 		xpp.ignore_regex = o->ignore_regex;
 		xpp.ignore_regex_nr = o->ignore_regex_nr;
@@ -5122,9 +5143,13 @@ static int diff_opt_compact_summary(const struct option *opt,
 static int diff_opt_diff_algorithm(const struct option *opt,
 				   const char *arg, int unset)
 {
+	struct diff_options *options = opt->value;
+
 	BUG_ON_OPT_NEG(unset);
 
-	return set_diff_algorithm(opt->value, arg);
+	options->xdl_opts_command_line = 1;
+
+	return set_diff_algorithm(options, arg);
 }
 
 static int diff_opt_dirstat(const struct option *opt,
@@ -5256,7 +5281,6 @@ static int diff_opt_patience(const struct option *opt,
 
 	BUG_ON_OPT_NEG(unset);
 	BUG_ON_OPT_ARG(arg);
-	options->xdl_opts = DIFF_WITH_ALG(options, PATIENCE_DIFF);
 	/*
 	 * Both --patience and --anchored use PATIENCE_DIFF
 	 * internally, so remove any anchors previously
@@ -5265,7 +5289,36 @@ static int diff_opt_patience(const struct option *opt,
 	for (i = 0; i < options->anchors_nr; i++)
 		free(options->anchors[i]);
 	options->anchors_nr = 0;
-	return 0;
+
+	options->xdl_opts_command_line = 1;
+
+	return set_diff_algorithm(options, "patience");
+}
+
+static int diff_opt_histogram(const struct option *opt,
+			     const char *arg, int unset)
+{
+	struct diff_options *options = opt->value;
+
+	BUG_ON_OPT_NEG(unset);
+	BUG_ON_OPT_ARG(arg);
+
+	options->xdl_opts_command_line = 1;
+
+	return set_diff_algorithm(options, "histogram");
+}
+
+static int diff_opt_minimal(const struct option *opt,
+			     const char *arg, int unset)
+{
+	struct diff_options *options = opt->value;
+
+	BUG_ON_OPT_NEG(unset);
+	BUG_ON_OPT_ARG(arg);
+
+	options->xdl_opts_command_line = 1;
+
+	return set_diff_algorithm(options, "minimal");
 }
 
 static int diff_opt_ignore_regex(const struct option *opt,
@@ -5568,9 +5621,10 @@ struct option *add_diff_options(const struct option *opts,
 			    N_("prevent rename/copy detection if the number of rename/copy targets exceeds given limit")),
 
 		OPT_GROUP(N_("Diff algorithm options")),
-		OPT_BIT(0, "minimal", &options->xdl_opts,
-			N_("produce the smallest possible diff"),
-			XDF_NEED_MINIMAL),
+		OPT_CALLBACK_F(0, "minimal", options, NULL,
+			       N_("produce the smallest possible diff"),
+			       PARSE_OPT_NONEG | PARSE_OPT_NOARG,
+			       diff_opt_minimal),
 		OPT_BIT_F('w', "ignore-all-space", &options->xdl_opts,
 			  N_("ignore whitespace when comparing lines"),
 			  XDF_IGNORE_WHITESPACE, PARSE_OPT_NONEG),
@@ -5596,9 +5650,10 @@ struct option *add_diff_options(const struct option *opts,
 			       N_("generate diff using the \"patience diff\" algorithm"),
 			       PARSE_OPT_NONEG | PARSE_OPT_NOARG,
 			       diff_opt_patience),
-		OPT_BITOP(0, "histogram", &options->xdl_opts,
-			  N_("generate diff using the \"histogram diff\" algorithm"),
-			  XDF_HISTOGRAM_DIFF, XDF_DIFF_ALGORITHM_MASK),
+		OPT_CALLBACK_F(0, "histogram", options, NULL,
+			       N_("generate diff using the \"histogram diff\" algorithm"),
+			       PARSE_OPT_NONEG | PARSE_OPT_NOARG,
+			       diff_opt_histogram),
 		OPT_CALLBACK_F(0, "diff-algorithm", options, N_("<algorithm>"),
 			       N_("choose a diff algorithm"),
 			       PARSE_OPT_NONEG, diff_opt_diff_algorithm),

diff.h

@@ -333,6 +333,8 @@ struct diff_options {
 	int prefix_length;
 	const char *stat_sep;
 	int xdl_opts;
+	/* If xdl_opts has been set via the command line. */
+	int xdl_opts_command_line;
 
 	/* see Documentation/diff-options.txt */
 	char **anchors;

t/lib-diff-alternative.sh

@@ -107,8 +107,27 @@ EOF
 
 	STRATEGY=$1
 
+	test_expect_success "$STRATEGY diff from attributes" '
+		echo "file* diff-algorithm=$STRATEGY" >.gitattributes &&
+		test_must_fail git diff --no-index file1 file2 > output &&
+		test_cmp expect output
+	'
+
 	test_expect_success "$STRATEGY diff" '
-		test_must_fail git diff --no-index "--$STRATEGY" file1 file2 > output &&
+		test_must_fail git diff --no-index "--diff-algorithm=$STRATEGY" file1 file2 > output &&
+		test_cmp expect output
+	'
+
+	test_expect_success "$STRATEGY diff command line precedence before attributes" '
+		echo "file* diff-algorithm=meyers" >.gitattributes &&
+		test_must_fail git diff --no-index "--diff-algorithm=$STRATEGY" file1 file2 > output &&
+		test_cmp expect output
+	'
+
+	test_expect_success "$STRATEGY diff attributes precedence before config" '
+		git config diff.algorithm default &&
+		echo "file* diff-algorithm=$STRATEGY" >.gitattributes &&
+		test_must_fail git diff --no-index "--diff-algorithm=$STRATEGY" file1 file2 > output &&
 		test_cmp expect output
 	'
 
@@ -166,5 +185,11 @@ EOF
 		test_must_fail git diff --no-index "--$STRATEGY" uniq1 uniq2 > output &&
 		test_cmp expect output
 	'
+
+	test_expect_success "$STRATEGY diff from attributes" '
+		echo "file* diff-algorithm=$STRATEGY" >.gitattributes &&
+		test_must_fail git diff --no-index uniq1 uniq2 > output &&
+		test_cmp expect output
+	'
 }