[pull] master from git:master

Documentation/RelNotes/2.56.0.adoc

@@ -298,6 +298,22 @@ Performance, Internal Implementation, Development Support etc.
    the image upgrade.
    (merge 1a1579c42d jk/ci-static-analysis-image-bump later to maint).
 
+ * The alias tests in 't/t0014-alias.sh' have been updated to dynamically
+   query the list of deprecated commands using 'git
+   --list-cmds=deprecated' to avoid test failures when running with
+   'WITH_BREAKING_CHANGES' in a build directory that contains stale
+   executables of formerly deprecated commands.
+   (merge bc57ecb915 jk/t0014-dynamic-deprecated-cmds later to maint).
+
+ * The code path that deals with relative paths in the diff-lib has
+   been cleaned up.
+
+ * The get_commit_action() function has been refactored to be a pure
+   predicate by moving the side-effecting line-level log range folding to
+   simplify_commit().  This ensures that evaluating a commit's action
+   before the walk reaches it does not prematurely mutate its tracked
+   line ranges, making it safer for potential lookahead evaluations.
+
 
 Fixes since v2.55
 -----------------
@@ -496,14 +512,26 @@ Fixes since v2.55
    and another prevented the editor from opening when the final command
    in a chain containing 'fixup -c' was skipped.
 
- * The alias tests in 't/t0014-alias.sh' have been updated to dynamically
-   query the list of deprecated commands using 'git
-   --list-cmds=deprecated' to avoid test failures when running with
-   'WITH_BREAKING_CHANGES' in a build directory that contains stale
-   executables of formerly deprecated commands.
-   (merge bc57ecb915 jk/t0014-dynamic-deprecated-cmds later to maint).
-
  * Git for Windows has been updated to avoid auto-detecting the symlink
    type if the target path starts with a slash, preventing NTLM
    credential leaks when checking out repositories with crafted
    symbolic links pointing to network shares.
+
+ * 'git cat-file --batch-command' that asked for 'contents' without
+   'type' segfaults, which has been corrected.
+   (merge 2abc7f0304 jk/cat-file-batch-wo-type-fix later to maint).
+
+ * A memory leak in 'git merge' when run without arguments (which
+   triggers the default-to-upstream path) has been fixed.  A test has
+   been added to cover this case.
+   (merge 68cce04a02 tc/merge-default-to-upstream-leakfix later to maint).
+
+ * A boundary case check in reachability bitmap traversal has been
+   corrected to properly handle the object at position zero, which was
+   previously skipped, leading to redundant bitmap loading.
+   (merge b56b48301e dl/pack-bitmap-position-zero later to maint).
+
+ * A crash in the 'sparse-index' collapse code when encountering an
+   invalidated cache-tree node (due to an intent-to-add path) has been
+   fixed by avoiding collapsing such subtrees.
+   (merge eede1e69fe ds/sparse-index-ita-crash later to maint).

builtin/cat-file.c

@@ -789,8 +789,11 @@ static void parse_cmd_contents(struct batch_options *opt,
 			     struct strbuf *output,
 			     struct expand_data *data)
 {
+	enum object_type *saved_typep = data->info.typep;
+	data->info.typep = &data->type;
 	opt->batch_mode = BATCH_MODE_CONTENTS;
 	batch_one_object(line, output, opt, data);
+	data->info.typep = saved_typep;
 }
 
 static void parse_cmd_info(struct batch_options *opt,

builtin/merge.c

@@ -1373,7 +1373,7 @@ int cmd_merge(int argc,
 	struct commit_list *common = NULL;
 	const char *best_strategy = NULL, *wt_strategy = NULL;
 	struct commit_list *remoteheads = NULL, *p;
-	void *branch_to_free;
+	void *branch_to_free, *argv_to_free = NULL;
 	int orig_argc = argc;
 	int merge_log_config = -1;
 
@@ -1517,8 +1517,10 @@ int cmd_merge(int argc,
 		option_commit = 1;
 
 	if (!argc) {
-		if (default_to_upstream)
+		if (default_to_upstream) {
 			argc = setup_with_upstream(&argv);
+			argv_to_free = argv;
+		}
 		else
 			die(_("No commit specified and merge.defaultToUpstream not set."));
 	} else if (argc == 1 && !strcmp(argv[0], "-")) {
@@ -1880,6 +1882,7 @@ int cmd_merge(int argc,
 	}
 	strbuf_release(&buf);
 	free(branch_to_free);
+	free(argv_to_free);
 	free(pull_twohead);
 	free(pull_octopus);
 	discard_index(the_repository->index);

diff-lib.c

@@ -508,11 +508,9 @@ static void do_oneway_diff(struct unpack_trees_options *o,
  * For diffing, the index is more important, and we only have a
  * single tree.
  *
- * We're supposed to advance o->pos to skip what we have already processed.
- *
  * This wrapper makes it all more readable, and takes care of all
  * the fairly complex unpack_trees() semantic requirements, including
- * the skipping, the path matching, the type conflict cases etc.
+ * the path matching, the type conflict cases etc.
  */
 static int oneway_diff(const struct cache_entry * const *src,
 		       struct unpack_trees_options *o)
@@ -540,6 +538,11 @@ static int oneway_diff(const struct cache_entry * const *src,
 	if (!idx && !tree)
 		BUG("oneway_diff with neither idx nor tree");
 
+	if (revs->diffopt.prefix &&
+	    strncmp((idx ? idx : tree)->name, revs->diffopt.prefix,
+		    revs->diffopt.prefix_length))
+		return 0;
+
 	if (ce_path_match(revs->diffopt.repo->index,
 			  idx ? idx : tree,
 			  &revs->prune_data, NULL)) {

pack-bitmap.c

@@ -1569,7 +1569,7 @@ static struct bitmap *find_objects(struct bitmap_index *bitmap_git,
 
 		if (base) {
 			int pos = bitmap_position(bitmap_git, &object->oid);
-			if (pos > 0 && bitmap_get(base, pos)) {
+			if (pos >= 0 && bitmap_get(base, pos)) {
 				object->flags |= SEEN;
 				continue;
 			}

revision.c

@@ -4196,37 +4196,39 @@ static timestamp_t comparison_date(const struct rev_info *revs,
 		commit->date;
 }
 
-enum commit_action get_commit_action(struct rev_info *revs, struct commit *commit)
+/*
+ * Whether the commit is ignored by the cheap checks that read only its
+ * traversal flags and pack membership (e.g. already shown, or marked
+ * uninteresting), before any check that examines the commit's date,
+ * parents, message, or diff.
+ */
+static int commit_early_ignore(struct rev_info *revs, struct commit *commit)
 {
 	if (commit->object.flags & SHOWN)
-		return commit_ignore;
+		return 1;
 	if (revs->maximal_only && (commit->object.flags & CHILD_VISITED))
-		return commit_ignore;
+		return 1;
 	if (revs->unpacked && has_object_pack(revs->repo, &commit->object.oid))
-		return commit_ignore;
-	if (revs->no_kept_objects) {
-		if (has_object_kept_pack(revs->repo, &commit->object.oid,
-					 revs->keep_pack_cache_flags))
-			return commit_ignore;
-	}
+		return 1;
+	if (revs->no_kept_objects &&
+	    has_object_kept_pack(revs->repo, &commit->object.oid,
+				 revs->keep_pack_cache_flags))
+		return 1;
 	if (commit->object.flags & UNINTERESTING)
+		return 1;
+	return 0;
+}
+
+/*
+ * Decide whether this commit is shown or ignored.  Keep it a pure
+ * predicate: callers such as the commit graph depend on it having no
+ * side effects, so per-commit mutations (such as -L range tracking)
+ * belong in the caller, simplify_commit(), not here.
+ */
+enum commit_action get_commit_action(struct rev_info *revs, struct commit *commit)
+{
+	if (commit_early_ignore(revs, commit))
 		return commit_ignore;
-	if (revs->line_level_traverse && !want_ancestry(revs)) {
-		/*
-		 * In case of line-level log with parent rewriting
-		 * prepare_revision_walk() already took care of all line-level
-		 * log filtering, and there is nothing left to do here.
-		 *
-		 * If parent rewriting was not requested, then this is the
-		 * place to perform the line-level log filtering.  Notably,
-		 * this check, though expensive, must come before the other,
-		 * cheaper filtering conditions, because the tracked line
-		 * ranges must be adjusted even when the commit will end up
-		 * being ignored based on other conditions.
-		 */
-		if (!line_log_process_ranges_arbitrary_commit(revs, commit))
-			return commit_ignore;
-	}
 	if (revs->min_age != -1 &&
 	    comparison_date(revs, commit) > revs->min_age)
 			return commit_ignore;
@@ -4335,7 +4337,23 @@ struct commit_list *get_saved_parents(struct rev_info *revs, const struct commit
 
 enum commit_action simplify_commit(struct rev_info *revs, struct commit *commit)
 {
-	enum commit_action action = get_commit_action(revs, commit);
+	enum commit_action action;
+
+	/*
+	 * For a line-level log without parent rewriting, fold each commit's
+	 * ranges as the walk reaches it (parent rewriting does this eagerly in
+	 * prepare_revision_walk()).  Fold before get_commit_action() so the
+	 * ranges carry across a commit that a later, cheaper check ignores;
+	 * the commit_early_ignore() guard skips a commit get_commit_action()
+	 * would ignore outright.
+	 */
+	if (revs->line_level_traverse && !want_ancestry(revs) &&
+	    !commit_early_ignore(revs, commit)) {
+		if (!line_log_process_ranges_arbitrary_commit(revs, commit))
+			return commit_ignore;
+	}
+
+	action = get_commit_action(revs, commit);
 
 	if (action == commit_show &&
 	    revs->prune && revs->dense && want_ancestry(revs)) {

sparse-index.c

@@ -113,10 +113,17 @@ static int convert_to_sparse_rec(struct index_state *istate,
 			continue;
 		}
 
+		span = ct->down[pos]->cache_tree->entry_count;
+		if (span < 0) {
+			/* cache-tree entry is invalidated, cannot collapse. */
+			istate->cache[num_converted++] = ce;
+			i++;
+			continue;
+		}
+
 		strbuf_setlen(&child_path, 0);
 		strbuf_add(&child_path, ce->name, slash - ce->name + 1);
 
-		span = ct->down[pos]->cache_tree->entry_count;
 		count = convert_to_sparse_rec(istate,
 					      num_converted, i, i + span,
 					      child_path.buf, child_path.len,

t/helper/test-revision-walking.c

@@ -13,9 +13,12 @@
 #include "test-tool.h"
 #include "commit.h"
 #include "diff.h"
+#include "line-log.h"
+#include "object-name.h"
 #include "repository.h"
 #include "revision.h"
 #include "setup.h"
+#include "string-list.h"
 
 static void print_commit(struct commit *commit)
 {
@@ -51,6 +54,60 @@ static int run_revision_walk(void)
 	return got_revision;
 }
 
+/*
+ * Check that get_commit_action() is a pure predicate by evaluating it on a
+ * commit the walk has not reached yet.  No git command makes that out-of-order
+ * call, so this probe does it deliberately, and reports whether the call
+ * mutated the peeked commit: a pure get_commit_action() leaves it untouched.
+ * We compare the commit's flags rather than the emitted commit list because
+ * range merges are idempotent, so a side effect would not change which commits
+ * are shown.  Only meaningful for a plain "-L" walk with no parent rewriting.
+ */
+static int line_log_peek(const char **argv)
+{
+	struct repository *repo = the_repository;
+	struct rev_info rev;
+	struct string_list range_args = STRING_LIST_INIT_DUP;
+	struct object_id oid;
+	struct commit *peek;
+	const char *rev_argv[3];
+	unsigned before, after;
+
+	if (repo_get_oid(repo, argv[0], &oid))
+		die("bad peek commit: %s", argv[0]);
+	peek = lookup_commit_reference(repo, &oid);
+	if (!peek || repo_parse_commit(repo, peek))
+		die("cannot parse peek commit: %s", argv[0]);
+
+	repo_init_revisions(repo, &rev, NULL);
+	rev.diffopt.flags.recursive = 1;
+	rev.line_level_traverse = 1;
+	string_list_append(&range_args, argv[1]);
+
+	rev_argv[0] = "line-log-peek";
+	rev_argv[1] = argv[2];
+	rev_argv[2] = NULL;
+	setup_revisions(2, rev_argv, &rev, NULL);
+
+	line_log_init(&rev, NULL, &range_args);
+
+	if (rev.rewrite_parents || rev.children.name)
+		die("line-log-peek requires a non-ancestry (-L, no --graph) walk");
+
+	if (prepare_revision_walk(&rev))
+		die("prepare_revision_walk failed");
+
+	before = peek->object.flags;
+	get_commit_action(&rev, peek);
+	after = peek->object.flags;
+
+	printf("mutated %d\n", before != after);
+
+	release_revisions(&rev);
+	string_list_clear(&range_args, 0);
+	return 0;
+}
+
 int cmd__revision_walking(int argc, const char **argv)
 {
 	if (argc < 2)
@@ -69,6 +126,12 @@ int cmd__revision_walking(int argc, const char **argv)
 		return 0;
 	}
 
+	if (!strcmp(argv[1], "line-log-peek")) {
+		if (argc != 5)
+			die("usage: test-tool revision-walking line-log-peek <peek-commit> <start,end:file> <rev>");
+		return line_log_peek(argv + 2);
+	}
+
 	fprintf(stderr, "check usage\n");
 	return 1;
 }

t/t1006-cat-file.sh

@@ -1340,6 +1340,14 @@ test_expect_success 'batch-command flush without --buffer' '
 	test_grep "^fatal:.*flush is only for --buffer mode.*" err
 '
 
+test_expect_success 'batch-command contents auto-handles type' '
+	echo "HEAD" |
+		git cat-file --batch="%(objectname)" >expect &&
+	echo "contents HEAD" |
+		git cat-file --batch-command="%(objectname)" >actual &&
+	test_cmp expect actual
+'
+
 perl_script='
 use warnings;
 use strict;

t/t1092-sparse-checkout-compatibility.sh

@@ -384,6 +384,54 @@ test_expect_success 'add, commit, checkout' '
 	test_all_match git checkout -
 '
 
+test_expect_success 'intent-to-add entries outside sparse-checkout' '
+	init_repos &&
+
+	write_script edit-contents <<-\EOF &&
+	echo text >>$1
+	EOF
+
+	test_sparse_match git sparse-checkout set deep folder1 &&
+	run_on_sparse mkdir -p folder1 &&
+	run_on_all ../edit-contents folder1/newita &&
+	test_sparse_match git add -N folder1/newita &&
+
+	test_sparse_match git sparse-checkout set deep &&
+	test_sparse_match git status --porcelain=v2 &&
+	test_sparse_match git ls-files --stage
+'
+
+test_expect_success 'intent-to-add with --sparse outside sparse-checkout' '
+	init_repos &&
+
+	write_script edit-contents <<-\EOF &&
+	echo text >>$1
+	EOF
+
+	run_on_all mkdir -p folder1 &&
+	run_on_all ../edit-contents folder1/newita &&
+	test_all_match git add --sparse --intent-to-add folder1/newita &&
+
+	test_all_match git status --porcelain=v2 &&
+	test_all_match git ls-files --stage &&
+	test_all_match git diff --cached --stat &&
+
+	# Ensure sparse index stores correct sparse directories and
+	# intent-to-add path.
+	git -C sparse-index ls-files --format="%(path)" --sparse >out &&
+
+	# These paths should be present in index as-is.
+	test_grep "^before/\$" out &&
+	test_grep "^folder1/newita\$" out &&
+	test_grep "^folder2/\$" out &&
+	test_grep "^x/\$" out &&
+
+	# folder/0/ could theoretically be collapsed to a sparse
+	# directory entry, but the current implementation avoids the
+	# reduction because of folder1/newita
+	test_grep "^folder1/0/0/0\$" out
+'
+
 test_expect_success 'git add, checkout, and reset with -p' '
 	init_repos &&