From 2fb21751ec8f495aa35e479d73361d54c7765ee2 Mon Sep 17 00:00:00 2001 From: Derrick Stolee Date: Sun, 4 Jul 2021 17:06:12 -0400 Subject: [PATCH] sparse-checkout: clear tracked sparse dirs When changing the scope of a sparse-checkout using cone mode, we might have some tracked directories go out of scope. The current logic removes the tracked files from within those directories, but leaves the ignored files within those directories. This is a bit unexpected to users who have given input to Git saying they don't need those directories anymore. This is something that is new to the cone mode pattern type: the user has explicitly said "I want these directories and _not_ those directories." The typical sparse-checkout patterns more generally apply to "I want files with with these patterns" so it is natural to leave ignored files as they are. This focus on directories in cone mode provides us an opportunity to change the behavior. Leaving these ignored files in the sparse directories makes it impossible to gain performance benefits in the sparse index. When we track into these directories, we need to know if the files are ignored or not, which might depend on the _tracked_ .gitignore file(s) within the sparse directory. This depends on the indexed version of the file, so the sparse directory must be expanded. By deleting the sparse directories when changing scope (or running 'git sparse-checkout reapply') we regain these performance benefits as if the repository was in a clean state. Since these ignored files are frequently build output or helper files from IDEs, the users should not need the files now that the tracked files are removed. If the tracked files reappear, then they will have newer timestamps than the build artifacts, so the artifacts will need to be regenerated anyway. If users depend on ignored files within the sparse directories, then they have created a bad shape in their repository. Regardless, such shapes would create risk that changing the behavior for all cone mode users might be too risky to take on at the moment. Since this data shape makes it impossible to get performance benefits using the sparse index, we limit the change to only be enabled when the sparse index is enabled. Users can opt out of this behavior by disabline the sparse index. Depending on user feedback or real-world use, we might want to consider expanding the behavior change to all of cone mode. Since we are currently restricting to the sparse index case, we can use the existence of sparse directory entries in the index as indicators of which directories should be removed. The contained files are deleted by a 'git clean -dfx' subcommand while the directories themselves are deleted once they are empty. Signed-off-by: Derrick Stolee --- Documentation/git-sparse-checkout.txt | 6 +++ builtin/sparse-checkout.c | 78 +++++++++++++++++++++++++++ t/t1091-sparse-checkout-builtin.sh | 42 +++++++++++++++ 3 files changed, 126 insertions(+) diff --git a/Documentation/git-sparse-checkout.txt b/Documentation/git-sparse-checkout.txt index fdcf43f87cb373..c443189f418c92 100644 --- a/Documentation/git-sparse-checkout.txt +++ b/Documentation/git-sparse-checkout.txt @@ -210,6 +210,12 @@ case-insensitive check. This corrects for case mismatched filenames in the 'git sparse-checkout set' command to reflect the expected cone in the working directory. +When the sparse index is enabled through the `index.sparse` config option, +the cone mode sparse-checkout patterns will also remove ignored files that +are not within the sparse-checkout definition. This is important behavior +to preserve the performance of the sparse index, but also matches that +cone mode patterns care about directories, not files. + SUBMODULES ---------- diff --git a/builtin/sparse-checkout.c b/builtin/sparse-checkout.c index a4bdd7c4940260..4448daba27e0cb 100644 --- a/builtin/sparse-checkout.c +++ b/builtin/sparse-checkout.c @@ -15,6 +15,7 @@ #include "wt-status.h" #include "quote.h" #include "sparse-index.h" +#include "run-command.h" static const char *empty_base = ""; @@ -100,6 +101,76 @@ static int sparse_checkout_list(int argc, const char **argv) return 0; } +static void clean_tracked_sparse_directories(struct repository *r) +{ + int i; + struct strvec args = STRVEC_INIT; + + /* + * If we are not using cone mode patterns, then we cannot + * delete directories outside of the sparse cone. + */ + if (!r || !r->index || !r->index->sparse_checkout_patterns || + !r->index->sparse_checkout_patterns->use_cone_patterns) + return; + /* + * NEEDSWORK: For now, only use this behavior when index.sparse + * is enabled. We may want this behavior enabled whenever using + * cone mode patterns. + */ + prepare_repo_settings(r); + if (!r->settings.sparse_index) + return; + + strvec_pushl(&args, "clean", "-dfx", "--", NULL); + + /* + * Since we now depend on the sparse index to enable this + * behavior, use it to our advantage. This process is more + * complicated without it. + */ + convert_to_sparse(r->index); + + for (i = 0; i < r->index->cache_nr; i++) { + struct cache_entry *ce = r->index->cache[i]; + + /* + * Is this a sparse directory? If so, then definitely + * include it. All contained content is outside of the + * patterns. + */ + if (S_ISSPARSEDIR(ce->ce_mode) && + repo_file_exists(r, ce->name)) { + strvec_push(&args, ce->name); + continue; + } + } + + /* + * Only run if we found an existing sparse directory, otherwise + * the clean will be across the entire worktree! + */ + if (args.nr > 3) + run_command_v_opt(args.v, RUN_GIT_CMD); + + /* + * The 'git clean -dfx -- ...' command empties the + * tracked directories outside of the sparse cone, but does not + * delete the directories themselves. Remove them now. + */ + for (i = 3; i < args.nr; i++) + rmdir_or_warn(args.v[i]); + + strvec_clear(&args); + + /* + * This is temporary: the sparse-checkout builtin is not + * integrated with the sparse-index yet, so we need to keep + * it full during the process. + */ + ensure_full_index(r->index); +} + static int update_working_directory(struct pattern_list *pl) { enum update_sparsity_result result; @@ -141,6 +212,8 @@ static int update_working_directory(struct pattern_list *pl) else rollback_lock_file(&lock_file); + clean_tracked_sparse_directories(r); + r->index->sparse_checkout_patterns = NULL; return result; } @@ -540,8 +613,11 @@ static int modify_pattern_list(int argc, const char **argv, enum modify_type m) { int result; int changed_config = 0; + struct pattern_list *old_pl = xcalloc(1, sizeof(*old_pl)); struct pattern_list *pl = xcalloc(1, sizeof(*pl)); + get_sparse_checkout_patterns(old_pl); + switch (m) { case ADD: if (core_sparse_checkout_cone) @@ -567,7 +643,9 @@ static int modify_pattern_list(int argc, const char **argv, enum modify_type m) set_config(MODE_NO_PATTERNS); clear_pattern_list(pl); + clear_pattern_list(old_pl); free(pl); + free(old_pl); return result; } diff --git a/t/t1091-sparse-checkout-builtin.sh b/t/t1091-sparse-checkout-builtin.sh index 38fc8340f5c9b7..43eb314c94a5cb 100755 --- a/t/t1091-sparse-checkout-builtin.sh +++ b/t/t1091-sparse-checkout-builtin.sh @@ -642,4 +642,46 @@ test_expect_success MINGW 'cone mode replaces backslashes with slashes' ' check_files repo/deep a deeper1 ' +test_expect_success 'cone mode clears ignored subdirectories' ' + rm repo/.git/info/sparse-checkout && + + # NEEDSWORK: --sparse-index is required for now + git -C repo sparse-checkout init --cone --sparse-index && + git -C repo sparse-checkout set deep/deeper1 && + + cat >repo/.gitignore <<-\EOF && + obj/ + *.o + EOF + + git -C repo add .gitignore && + git -C repo commit -m ".gitignore" && + + mkdir -p repo/obj repo/folder1/obj repo/deep/deeper2/obj && + for file in folder1/obj/a obj/a folder1/file.o folder1.o \ + deep/deeper2/obj/a deep/deeper2/file.o file.o + do + echo ignored >repo/$file || return 1 + done && + + git -C repo status --porcelain=v2 >out && + test_must_be_empty out && + + git -C repo sparse-checkout reapply && + test_path_is_missing repo/folder1 && + test_path_is_missing repo/deep/deeper2 && + test_path_is_dir repo/obj && + test_path_is_file repo/file.o && + + git -C repo status --porcelain=v2 >out && + test_must_be_empty out && + + git -C repo sparse-checkout set deep/deeper2 && + test_path_is_missing repo/deep/deeper1 && + test_path_is_dir repo/deep/deeper2 && + + git -C repo status --porcelain=v2 >out && + test_must_be_empty out +' + test_done