diff: teach diff to display submodule difference with an inline diff

Teach git-diff and friends a new format for displaying the difference
of a submodule. The new format is an inline diff of the contents of the
submodule between the commit range of the update. This allows the user
to see the actual code change caused by a submodule update.

Add tests for the new format and option.

Signed-off-by: Jacob Keller <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: jacob-keller

Documentation/diff-config.txt

@@ -122,10 +122,11 @@ diff.suppressBlankEmpty::
 
 diff.submodule::
 	Specify the format in which differences in submodules are
-	shown.  The "log" format lists the commits in the range like
-	linkgit:git-submodule[1] `summary` does.  The "short" format
-	format just shows the names of the commits at the beginning
-	and end of the range.  Defaults to short.
+	shown.  The "short" format just shows the names of the commits
+	at the beginning and end of the range. The "log" format lists
+	the commits in the range like linkgit:git-submodule[1] `summary`
+	does. The "diff" format shows an inline diff of the changed
+	contents of the submodule. Defaults to "short".
 
 diff.wordRegex::
 	A POSIX Extended Regular Expression used to determine what is a "word"

Documentation/diff-options.txt

@@ -210,13 +210,16 @@ any of those replacements occurred.
 	of the `--diff-filter` option on what the status letters mean.
 
 --submodule[=<format>]::
-	Specify how differences in submodules are shown.  When `--submodule`
-	or `--submodule=log` is given, the 'log' format is used.  This format lists
-	the commits in the range like linkgit:git-submodule[1] `summary` does.
-	Omitting the `--submodule` option or specifying `--submodule=short`,
-	uses the 'short' format. This format just shows the names of the commits
-	at the beginning and end of the range.  Can be tweaked via the
-	`diff.submodule` configuration variable.
+	Specify how differences in submodules are shown.  When specifying
+	`--submodule=short` the 'short' format is used.  This format just
+	shows the names of the commits at the beginning and end of the range.
+	When `--submodule` or `--submodule=log` is specified, the 'log'
+	format is used.  This format lists the commits in the range like
+	linkgit:git-submodule[1] `summary` does.  When `--submodule=diff`
+	is specified, the 'diff' format is used.  This format shows an
+	inline diff of the changes in the submodule contents between the
+	commit range.  Defaults to `diff.submodule` or the 'short' format
+	if the config option is unset.
 
 --color[=<when>]::
 	Show colored diff.

diff.c

@@ -135,6 +135,8 @@ static int parse_submodule_params(struct diff_options *options, const char *valu
 		options->submodule_format = DIFF_SUBMODULE_LOG;
 	else if (!strcmp(value, "short"))
 		options->submodule_format = DIFF_SUBMODULE_SHORT;
+	else if (!strcmp(value, "diff"))
+		options->submodule_format = DIFF_SUBMODULE_INLINE_DIFF;
 	else
 		return -1;
 	return 0;
@@ -2300,6 +2302,15 @@ static void builtin_diff(const char *name_a,
 	struct strbuf header = STRBUF_INIT;
 	const char *line_prefix = diff_line_prefix(o);
 
+	diff_set_mnemonic_prefix(o, "a/", "b/");
+	if (DIFF_OPT_TST(o, REVERSE_DIFF)) {
+		a_prefix = o->b_prefix;
+		b_prefix = o->a_prefix;
+	} else {
+		a_prefix = o->a_prefix;
+		b_prefix = o->b_prefix;
+	}
+
 	if (o->submodule_format == DIFF_SUBMODULE_LOG &&
 	    (!one->mode || S_ISGITLINK(one->mode)) &&
 	    (!two->mode || S_ISGITLINK(two->mode))) {
@@ -2311,22 +2322,24 @@ static void builtin_diff(const char *name_a,
 				two->dirty_submodule,
 				meta, del, add, reset);
 		return;
+	} else if (o->submodule_format == DIFF_SUBMODULE_INLINE_DIFF &&
+		   (!one->mode || S_ISGITLINK(one->mode)) &&
+		   (!two->mode || S_ISGITLINK(two->mode))) {
+		const char *del = diff_get_color_opt(o, DIFF_FILE_OLD);
+		const char *add = diff_get_color_opt(o, DIFF_FILE_NEW);
+		show_submodule_inline_diff(o->file, one->path ? one->path : two->path,
+				line_prefix,
+				&one->oid, &two->oid,
+				two->dirty_submodule,
+				meta, del, add, reset, o);
+		return;
 	}
 
 	if (DIFF_OPT_TST(o, ALLOW_TEXTCONV)) {
 		textconv_one = get_textconv(one);
 		textconv_two = get_textconv(two);
 	}
 
-	diff_set_mnemonic_prefix(o, "a/", "b/");
-	if (DIFF_OPT_TST(o, REVERSE_DIFF)) {
-		a_prefix = o->b_prefix;
-		b_prefix = o->a_prefix;
-	} else {
-		a_prefix = o->a_prefix;
-		b_prefix = o->b_prefix;
-	}
-
 	/* Never use a non-valid filename anywhere if at all possible */
 	name_a = DIFF_FILE_VALID(one) ? name_a : name_b;
 	name_b = DIFF_FILE_VALID(two) ? name_b : name_a;

diff.h

@@ -111,7 +111,8 @@ enum diff_words_type {
 
 enum diff_submodule_format {
 	DIFF_SUBMODULE_SHORT = 0,
-	DIFF_SUBMODULE_LOG
+	DIFF_SUBMODULE_LOG,
+	DIFF_SUBMODULE_INLINE_DIFF
 };
 
 struct diff_options {

submodule.c

@@ -442,6 +442,75 @@ void show_submodule_summary(FILE *f, const char *path,
 	clear_commit_marks(right, ~0);
 }
 
+void show_submodule_inline_diff(FILE *f, const char *path,
+		const char *line_prefix,
+		struct object_id *one, struct object_id *two,
+		unsigned dirty_submodule, const char *meta,
+		const char *del, const char *add, const char *reset,
+		const struct diff_options *o)
+{
+	const struct object_id *old = &empty_tree_oid, *new = &empty_tree_oid;
+	struct commit *left = NULL, *right = NULL;
+	struct commit_list *merge_bases = NULL;
+	struct strbuf submodule_dir = STRBUF_INIT;
+	struct child_process cp = CHILD_PROCESS_INIT;
+
+	show_submodule_header(f, path, line_prefix, one, two, dirty_submodule,
+			      meta, reset, &left, &right, &merge_bases);
+
+	/* We need a valid left and right commit to display a difference */
+	if (!(left || is_null_oid(one)) ||
+	    !(right || is_null_oid(two)))
+		goto done;
+
+	if (left)
+		old = one;
+	if (right)
+		new = two;
+
+	fflush(f);
+	cp.git_cmd = 1;
+	cp.dir = path;
+	cp.out = dup(fileno(f));
+	cp.no_stdin = 1;
+
+	/* TODO: other options may need to be passed here. */
+	argv_array_push(&cp.args, "diff");
+	argv_array_pushf(&cp.args, "--line-prefix=%s", line_prefix);
+	if (DIFF_OPT_TST(o, REVERSE_DIFF)) {
+		argv_array_pushf(&cp.args, "--src-prefix=%s%s/",
+				 o->b_prefix, path);
+		argv_array_pushf(&cp.args, "--dst-prefix=%s%s/",
+				 o->a_prefix, path);
+	} else {
+		argv_array_pushf(&cp.args, "--src-prefix=%s%s/",
+				 o->a_prefix, path);
+		argv_array_pushf(&cp.args, "--dst-prefix=%s%s/",
+				 o->b_prefix, path);
+	}
+	argv_array_push(&cp.args, oid_to_hex(old));
+	/*
+	 * If the submodule has modified content, we will diff against the
+	 * work tree, under the assumption that the user has asked for the
+	 * diff format and wishes to actually see all differences even if they
+	 * haven't yet been committed to the submodule yet.
+	 */
+	if (!(dirty_submodule & DIRTY_SUBMODULE_MODIFIED))
+		argv_array_push(&cp.args, oid_to_hex(new));
+
+	if (run_command(&cp))
+		fprintf(f, "(diff failed)\n");
+
+done:
+	strbuf_release(&submodule_dir);
+	if (merge_bases)
+		free_commit_list(merge_bases);
+	if (left)
+		clear_commit_marks(left, ~0);
+	if (right)
+		clear_commit_marks(right, ~0);
+}
+
 void set_config_fetch_recurse_submodules(int value)
 {
 	config_fetch_recurse_submodules = value;

submodule.h

@@ -46,6 +46,12 @@ void show_submodule_summary(FILE *f, const char *path,
 		struct object_id *one, struct object_id *two,
 		unsigned dirty_submodule, const char *meta,
 		const char *del, const char *add, const char *reset);
+void show_submodule_inline_diff(FILE *f, const char *path,
+		const char *line_prefix,
+		struct object_id *one, struct object_id *two,
+		unsigned dirty_submodule, const char *meta,
+		const char *del, const char *add, const char *reset,
+		const struct diff_options *opt);
 void set_config_fetch_recurse_submodules(int value);
 void check_for_new_submodule_commits(unsigned char new_sha1[20]);
 int fetch_populated_submodules(const struct argv_array *options,