Merge branch 'tc/diff-tree-max-depth' into jch

"git diff-tree" learned "--max-depth" option.

Comments?

* tc/diff-tree-max-depth:
  diff: teach tree-diff a max-depth parameter
  within_depth: fix return for empty path
  combine-diff: zero memory used for callback filepairs

Author: gitster

Documentation/diff-options.adoc

@@ -893,5 +893,33 @@ endif::git-format-patch[]
 	reverted with `--ita-visible-in-index`. Both options are
 	experimental and could be removed in future.
 
+--max-depth=<depth>::
+	For each pathspec given on command line, descend at most `<depth>`
+	levels of directories. A value of `-1` means no limit.
+	Cannot be combined with wildcards in the pathspec.
+	Given a tree containing `foo/bar/baz`, the following list shows the
+	matches generated by each set of options:
++
+--
+ - `--max-depth=0 -- foo`: `foo`
+
+ - `--max-depth=1 -- foo`: `foo/bar`
+
+ - `--max-depth=1 -- foo/bar`: `foo/bar/baz`
+
+ - `--max-depth=1 -- foo foo/bar`: `foo/bar/baz`
+
+ - `--max-depth=2 -- foo`: `foo/bar/baz`
+--
++
+If no pathspec is given, the depth is measured as if all
+top-level entries were specified. Note that this is different
+than measuring from the root, in that `--max-depth=0` would
+still return `foo`. This allows you to still limit depth while
+asking for a subset of the top-level entries.
++
+Note that this option is only supported for diffs between tree objects,
+not against the index or working tree.
+
 For more detailed explanation on these common options, see also
 linkgit:gitdiffcore[7].

Makefile

@@ -1354,6 +1354,7 @@ THIRD_PARTY_SOURCES += $(UNIT_TEST_DIR)/clar/%
 THIRD_PARTY_SOURCES += $(UNIT_TEST_DIR)/clar/clar/%
 
 CLAR_TEST_SUITES += u-ctype
+CLAR_TEST_SUITES += u-dir
 CLAR_TEST_SUITES += u-example-decorate
 CLAR_TEST_SUITES += u-hash
 CLAR_TEST_SUITES += u-hashmap

combine-diff.c

@@ -1315,7 +1315,7 @@ static struct diff_filepair *combined_pair(struct combine_diff_path *p,
 	struct diff_filepair *pair;
 	struct diff_filespec *pool;
 
-	pair = xmalloc(sizeof(*pair));
+	CALLOC_ARRAY(pair, 1);
 	CALLOC_ARRAY(pool, st_add(num_parent, 1));
 	pair->one = pool + 1;
 	pair->two = pool;

diff-lib.c

@@ -115,6 +115,9 @@ void run_diff_files(struct rev_info *revs, unsigned int option)
 	uint64_t start = getnanotime();
 	struct index_state *istate = revs->diffopt.repo->index;
 
+	if (revs->diffopt.max_depth_valid)
+		die(_("max-depth is not supported for worktree diffs"));
+
 	diff_set_mnemonic_prefix(&revs->diffopt, "i/", "w/");
 
 	refresh_fsmonitor(istate);
@@ -560,6 +563,8 @@ static int diff_cache(struct rev_info *revs,
 	opts.dst_index = NULL;
 	opts.pathspec = &revs->diffopt.pathspec;
 	opts.pathspec->recursive = 1;
+	if (revs->diffopt.max_depth_valid)
+		die(_("max-depth is not supported for index diffs"));
 
 	init_tree_desc(&t, &tree->object.oid, tree->buffer, tree->size);
 	return unpack_trees(1, &t, &opts);

diff.c

@@ -4982,6 +4982,9 @@ void diff_setup_done(struct diff_options *options)
 			options->filter = ~filter_bit[DIFF_STATUS_FILTER_AON];
 		options->filter &= ~options->filter_not;
 	}
+
+	if (options->pathspec.has_wildcard && options->max_depth_valid)
+		die("max-depth cannot be used with wildcard pathspecs");
 }
 
 int parse_long_opt(const char *opt, const char **argv,
@@ -5616,6 +5619,23 @@ static int diff_opt_rotate_to(const struct option *opt, const char *arg, int uns
 	return 0;
 }
 
+static int diff_opt_max_depth(const struct option *opt,
+			      const char *arg, int unset)
+{
+	struct diff_options *options = opt->value;
+
+	BUG_ON_OPT_NEG(unset);
+
+	if (!git_parse_int(arg, &options->max_depth))
+		return error(_("invalid value for '%s': '%s'"),
+			     "--max-depth", arg);
+
+	options->flags.recursive = 1;
+	options->max_depth_valid = options->max_depth >= 0;
+
+	return 0;
+}
+
 /*
  * Consider adding new flags to __git_diff_common_options
  * in contrib/completion/git-completion.bash
@@ -5888,6 +5908,10 @@ struct option *add_diff_options(const struct option *opts,
 		OPT_CALLBACK_F(0, "diff-filter", options, N_("[(A|C|D|M|R|T|U|X|B)...[*]]"),
 			       N_("select files by diff type"),
 			       PARSE_OPT_NONEG, diff_opt_diff_filter),
+		OPT_CALLBACK_F(0, "max-depth", options, N_("<depth>"),
+			       N_("maximum tree depth to recurse"),
+			       PARSE_OPT_NONEG, diff_opt_max_depth),
+
 		{
 			.type = OPTION_CALLBACK,
 			.long_name = "output",

diff.h

@@ -404,6 +404,14 @@ struct diff_options {
 	struct strmap *additional_path_headers;
 
 	int no_free;
+
+	/*
+	 * The value '0' is a valid max-depth (for no recursion), and value '-1'
+	 * also (for unlimited recursion), so the extra "valid" flag is used to
+	 * determined whether the user specified option --max-depth.
+	 */
+	int max_depth;
+	int max_depth_valid;
 };
 
 unsigned diff_filter_bit(char status);

dir.c

@@ -277,7 +277,7 @@ int within_depth(const char *name, int namelen,
 		if (depth > max_depth)
 			return 0;
 	}
-	return 1;
+	return depth <= max_depth;
 }
 
 /*

t/meson.build

@@ -1,5 +1,6 @@
 clar_test_suites = [
   'unit-tests/u-ctype.c',
+  'unit-tests/u-dir.c',
   'unit-tests/u-example-decorate.c',
   'unit-tests/u-hash.c',
   'unit-tests/u-hashmap.c',
@@ -487,6 +488,7 @@ integration_tests = [
   't4069-remerge-diff.sh',
   't4070-diff-pairs.sh',
   't4071-diff-minimal.sh',
+  't4072-diff-max-depth.sh',
   't4100-apply-stat.sh',
   't4101-apply-nonl.sh',
   't4102-apply-rename.sh',

t/t4072-diff-max-depth.sh

@@ -0,0 +1,116 @@
+#!/bin/sh
+
+test_description='check that diff --max-depth will limit recursion'
+. ./test-lib.sh
+
+make_dir() {
+	mkdir -p "$1" &&
+	echo "$2" >"$1/file"
+}
+
+make_files() {
+	echo "$1" >file &&
+	make_dir one "$1" &&
+	make_dir one/two "$1" &&
+	make_dir one/two/three "$1"
+}
+
+test_expect_success 'setup' '
+	git commit --allow-empty -m empty &&
+	git tag empty &&
+	make_files added &&
+	git add . &&
+	git commit -m added &&
+	make_files modified &&
+	git add . &&
+	git commit -m modified &&
+	make_files index &&
+	git add . &&
+	make_files worktree
+'
+
+test_expect_success '--max-depth is disallowed with wildcard pathspecs' '
+	test_must_fail git diff-tree --max-depth=0 HEAD^ HEAD -- "f*"
+'
+
+check_one() {
+	type=$1; shift
+	args=$1; shift
+	path=$1; shift
+	depth=$1; shift
+	test_expect_${expect:-success} "diff-$type $args, path=$path, depth=$depth" "
+		for i in $*; do echo \$i; done >expect &&
+		git diff-$type --max-depth=$depth --name-only $args -- $path >actual &&
+		test_cmp expect actual
+	"
+}
+
+# For tree comparisons, we expect to see subtrees at the boundary
+# get their own entry.
+check_trees() {
+	check_one tree "$*" '' 0 file one
+	check_one tree "$*" '' 1 file one/file one/two
+	check_one tree "$*" '' 2 file one/file one/two/file one/two/three
+	check_one tree "$*" '' 3 file one/file one/two/file one/two/three/file
+	check_one tree "$*" '' -1 file one/file one/two/file one/two/three/file
+	check_one tree "$*" one 0 one
+	check_one tree "$*" one 1 one/file one/two
+	check_one tree "$*" one 2 one/file one/two/file one/two/three
+	check_one tree "$*" one 3 one/file one/two/file one/two/three/file
+	check_one tree "$*" one/two 0 one/two
+	check_one tree "$*" one/two 1 one/two/file one/two/three
+	check_one tree "$*" one/two 2 one/two/file one/two/three/file
+	check_one tree "$*" one/two 2 one/two/file one/two/three/file
+	check_one tree "$*" one/two/three 0 one/two/three
+	check_one tree "$*" one/two/three 1 one/two/three/file
+}
+
+# But for index comparisons, we do not store subtrees at all, so we do not
+# expect them.
+check_index() {
+	check_one "$@" '' 0 file
+	check_one "$@" '' 1 file one/file
+	check_one "$@" '' 2 file one/file one/two/file
+	check_one "$@" '' 3 file one/file one/two/file one/two/three/file
+	check_one "$@" one 0
+	check_one "$@" one 1 one/file
+	check_one "$@" one 2 one/file one/two/file
+	check_one "$@" one 3 one/file one/two/file one/two/three/file
+	check_one "$@" one/two 0
+	check_one "$@" one/two 1 one/two/file
+	check_one "$@" one/two 2 one/two/file one/two/three/file
+	check_one "$@" one/two/three 0
+	check_one "$@" one/two/three 1 one/two/three/file
+
+	# Value '-1' for '--max-depth is the same as recursion without limit,
+	# and thus should always succeed.
+	local expect=
+	check_one "$@" '' -1 file one/file one/two/file one/two/three/file
+}
+
+# Check as a modification...
+check_trees HEAD^ HEAD
+# ...and as an addition...
+check_trees empty HEAD
+# ...and as a deletion.
+check_trees HEAD empty
+
+# We currently only implement max-depth for trees.
+expect=failure
+# Check index against a tree
+check_index index "--cached HEAD"
+# and index against the worktree
+check_index files ""
+expect=
+
+test_expect_success 'find shortest path within embedded pathspecs' '
+	cat >expect <<-\EOF &&
+	one/file
+	one/two/file
+	one/two/three/file
+	EOF
+	git diff-tree --max-depth=2 --name-only HEAD^ HEAD -- one one/two >actual &&
+	test_cmp expect actual
+'
+
+test_done

t/unit-tests/u-dir.c

@@ -0,0 +1,47 @@
+#include "unit-test.h"
+#include "dir.h"
+
+#define TEST_WITHIN_DEPTH(path, depth, max_depth, expect) do { \
+		int actual = within_depth(path, strlen(path), \
+					  depth, max_depth); \
+		if (actual != expect) \
+			cl_failf("path '%s' with depth '%d' and max-depth '%d': expected %d, got %d", \
+				 path, depth, max_depth, expect, actual); \
+	} while (0)
+
+void test_dir__within_depth(void)
+{
+	/* depth = 0; max_depth = 0 */
+	TEST_WITHIN_DEPTH("",         0, 0, 1);
+	TEST_WITHIN_DEPTH("file",     0, 0, 1);
+	TEST_WITHIN_DEPTH("a",        0, 0, 1);
+	TEST_WITHIN_DEPTH("a/file",   0, 0, 0);
+	TEST_WITHIN_DEPTH("a/b",      0, 0, 0);
+	TEST_WITHIN_DEPTH("a/b/file", 0, 0, 0);
+
+	/* depth = 0; max_depth = 1 */
+	TEST_WITHIN_DEPTH("",         0, 1, 1);
+	TEST_WITHIN_DEPTH("file",     0, 1, 1);
+	TEST_WITHIN_DEPTH("a",        0, 1, 1);
+	TEST_WITHIN_DEPTH("a/file",   0, 1, 1);
+	TEST_WITHIN_DEPTH("a/b",      0, 1, 1);
+	TEST_WITHIN_DEPTH("a/b/file", 0, 1, 0);
+
+	/* depth = 1; max_depth = 1 */
+	TEST_WITHIN_DEPTH("",         1, 1, 1);
+	TEST_WITHIN_DEPTH("file",     1, 1, 1);
+	TEST_WITHIN_DEPTH("a",        1, 1, 1);
+	TEST_WITHIN_DEPTH("a/file",   1, 1, 0);
+	TEST_WITHIN_DEPTH("a/b",      1, 1, 0);
+	TEST_WITHIN_DEPTH("a/b/file", 1, 1, 0);
+
+	/* depth = 1; max_depth = 0 */
+	TEST_WITHIN_DEPTH("",         1, 0, 0);
+	TEST_WITHIN_DEPTH("file",     1, 0, 0);
+	TEST_WITHIN_DEPTH("a",        1, 0, 0);
+	TEST_WITHIN_DEPTH("a/file",   1, 0, 0);
+	TEST_WITHIN_DEPTH("a/b",      1, 0, 0);
+	TEST_WITHIN_DEPTH("a/b/file", 1, 0, 0);
+
+
+}