Merge branch 'ee/clean-remove-dirs'

Replace "is this subdirectory a separate repository that should not
be touched?" check "git clean" does by checking if it has .git/HEAD
using the submodule-related code with a more optimized check.

* ee/clean-remove-dirs:
  read_gitfile_gently: fix use-after-free
  clean: improve performance when removing lots of directories
  p7300: add performance tests for clean
  t7300: add tests to document behavior of clean and nested git
  setup: sanity check file size in read_gitfile_gently
  setup: add gentle version of read_gitfile

2 files changed, 171 insertions, 0 deletions

diff --git a/t/perf/p7300-clean.sh b/t/perf/p7300-clean.sh
new file mode 100755
index 0000000000..ec94cdd657
--- /dev/null
+++ b/t/perf/p7300-clean.sh
@@ -0,0 +1,31 @@
+#!/bin/sh
+
+test_description="Test git-clean performance"
+
+. ./perf-lib.sh
+
+test_perf_default_repo
+test_checkout_worktree
+
+test_expect_success 'setup untracked directory with many sub dirs' '
+	rm -rf 500_sub_dirs 100000_sub_dirs clean_test_dir &&
+	mkdir 500_sub_dirs 100000_sub_dirs clean_test_dir &&
+	for i in $(test_seq 1 500)
+	do
+		mkdir 500_sub_dirs/dir$i || return $?
+	done &&
+	for i in $(test_seq 1 200)
+	do
+		cp -r 500_sub_dirs 100000_sub_dirs/dir$i || return $?
+	done
+'
+
+test_perf 'clean many untracked sub dirs, check for nested git' '
+	git clean -n -q -f -d 100000_sub_dirs/
+'
+
+test_perf 'clean many untracked sub dirs, ignore nested git' '
+	git clean -n -q -f -f -d 100000_sub_dirs/
+'
+
+test_done
diff --git a/t/t7300-clean.sh b/t/t7300-clean.sh
index 99be5d95d0..32e96da7e3 100755
--- a/t/t7300-clean.sh
+++ b/t/t7300-clean.sh
@@ -455,6 +455,146 @@ test_expect_success 'nested git work tree' '
 	! test -d bar
 '
 
+test_expect_success 'should clean things that almost look like git but are not' '
+	rm -fr almost_git almost_bare_git almost_submodule &&
+	mkdir -p almost_git/.git/objects &&
+	mkdir -p almost_git/.git/refs &&
+	cat >almost_git/.git/HEAD <<-\EOF &&
+	garbage
+	EOF
+	cp -r almost_git/.git/ almost_bare_git &&
+	mkdir almost_submodule/ &&
+	cat >almost_submodule/.git <<-\EOF &&
+	garbage
+	EOF
+	test_when_finished "rm -rf almost_*" &&
+	git clean -f -d &&
+	test_path_is_missing almost_git &&
+	test_path_is_missing almost_bare_git &&
+	test_path_is_missing almost_submodule
+'
+
+test_expect_success 'should not clean submodules' '
+	rm -fr repo to_clean sub1 sub2 &&
+	mkdir repo to_clean &&
+	(
+		cd repo &&
+		git init &&
+		test_commit msg hello.world
+	) &&
+	git submodule add ./repo/.git sub1 &&
+	git commit -m "sub1" &&
+	git branch before_sub2 &&
+	git submodule add ./repo/.git sub2 &&
+	git commit -m "sub2" &&
+	git checkout before_sub2 &&
+	>to_clean/should_clean.this &&
+	git clean -f -d &&
+	test_path_is_file repo/.git/index &&
+	test_path_is_file repo/hello.world &&
+	test_path_is_file sub1/.git &&
+	test_path_is_file sub1/hello.world &&
+	test_path_is_file sub2/.git &&
+	test_path_is_file sub2/hello.world &&
+	test_path_is_missing to_clean
+'
+
+test_expect_success 'should avoid cleaning possible submodules' '
+	rm -fr to_clean possible_sub1 &&
+	mkdir to_clean possible_sub1 &&
+	test_when_finished "rm -rf possible_sub*" &&
+	echo "gitdir: foo" >possible_sub1/.git &&
+	>possible_sub1/hello.world &&
+	chmod 0 possible_sub1/.git &&
+	>to_clean/should_clean.this &&
+	git clean -f -d &&
+	test_path_is_file possible_sub1/.git &&
+	test_path_is_file possible_sub1/hello.world &&
+	test_path_is_missing to_clean
+'
+
+test_expect_success 'nested (empty) git should be kept' '
+	rm -fr empty_repo to_clean &&
+	git init empty_repo &&
+	mkdir to_clean &&
+	>to_clean/should_clean.this &&
+	git clean -f -d &&
+	test_path_is_file empty_repo/.git/HEAD &&
+	test_path_is_missing to_clean
+'
+
+test_expect_success 'nested bare repositories should be cleaned' '
+	rm -fr bare1 bare2 subdir &&
+	git init --bare bare1 &&
+	git clone --local --bare . bare2 &&
+	mkdir subdir &&
+	cp -r bare2 subdir/bare3 &&
+	git clean -f -d &&
+	test_path_is_missing bare1 &&
+	test_path_is_missing bare2 &&
+	test_path_is_missing subdir
+'
+
+test_expect_failure 'nested (empty) bare repositories should be cleaned even when in .git' '
+	rm -fr strange_bare &&
+	mkdir strange_bare &&
+	git init --bare strange_bare/.git &&
+	git clean -f -d &&
+	test_path_is_missing strange_bare
+'
+
+test_expect_failure 'nested (non-empty) bare repositories should be cleaned even when in .git' '
+	rm -fr strange_bare &&
+	mkdir strange_bare &&
+	git clone --local --bare . strange_bare/.git &&
+	git clean -f -d &&
+	test_path_is_missing strange_bare
+'
+
+test_expect_success 'giving path in nested git work tree will remove it' '
+	rm -fr repo &&
+	mkdir repo &&
+	(
+		cd repo &&
+		git init &&
+		mkdir -p bar/baz &&
+		test_commit msg bar/baz/hello.world
+	) &&
+	git clean -f -d repo/bar/baz &&
+	test_path_is_file repo/.git/HEAD &&
+	test_path_is_dir repo/bar/ &&
+	test_path_is_missing repo/bar/baz
+'
+
+test_expect_success 'giving path to nested .git will not remove it' '
+	rm -fr repo &&
+	mkdir repo untracked &&
+	(
+		cd repo &&
+		git init &&
+		test_commit msg hello.world
+	) &&
+	git clean -f -d repo/.git &&
+	test_path_is_file repo/.git/HEAD &&
+	test_path_is_dir repo/.git/refs &&
+	test_path_is_dir repo/.git/objects &&
+	test_path_is_dir untracked/
+'
+
+test_expect_success 'giving path to nested .git/ will remove contents' '
+	rm -fr repo untracked &&
+	mkdir repo untracked &&
+	(
+		cd repo &&
+		git init &&
+		test_commit msg hello.world
+	) &&
+	git clean -f -d repo/.git/ &&
+	test_path_is_dir repo/.git &&
+	test_dir_is_empty repo/.git &&
+	test_path_is_dir untracked/
+'
+
 test_expect_success 'force removal of nested git work tree' '
 	rm -fr foo bar baz &&
 	mkdir -p foo bar baz/boo &&