diff --git a/builtin/reset.c b/builtin/reset.c index 4303a78029ada2..7b0d3169cf0424 100644 --- a/builtin/reset.c +++ b/builtin/reset.c @@ -196,6 +196,73 @@ static void update_index_from_diff(struct diff_queue_struct *q, } } +static int pathspec_needs_expanded_index(const struct pathspec *pathspec) +{ + unsigned int i, pos; + int res = 0; + char *skip_worktree_seen = NULL; + + /* + * When using a magic pathspec, assume for the sake of simplicity that + * the index needs to be expanded to match all matchable files. + */ + if (pathspec->magic) + return 1; + + for (i = 0; i < pathspec->nr; i++) { + struct pathspec_item item = pathspec->items[i]; + + /* + * If the pathspec item has a wildcard, the index should be expanded + * if the pathspec has the possibility of matching a subset of entries inside + * of a sparse directory (but not the entire directory). + * + * If the pathspec item is a literal path, the index only needs to be expanded + * if a) the pathspec isn't in the sparse checkout cone (to make sure we don't + * expand for in-cone files) and b) it doesn't match any sparse directories + * (since we can reset whole sparse directories without expanding them). + */ + if (item.nowildcard_len < item.len) { + for (pos = 0; pos < active_nr; pos++) { + struct cache_entry *ce = active_cache[pos]; + + if (!S_ISSPARSEDIR(ce->ce_mode)) + continue; + + /* + * If the pre-wildcard length is longer than the sparse + * directory name and the sparse directory is the first + * component of the pathspec, need to expand the index. + */ + if (item.nowildcard_len > ce_namelen(ce) && + !strncmp(item.original, ce->name, ce_namelen(ce))) { + res = 1; + break; + } + + /* + * If the pre-wildcard length is shorter than the sparse + * directory and the pathspec does not match the whole + * directory, need to expand the index. + */ + if (!strncmp(item.original, ce->name, item.nowildcard_len) && + wildmatch(item.original, ce->name, 0)) { + res = 1; + break; + } + } + } else if (!path_in_cone_mode_sparse_checkout(item.original, &the_index) && + !matches_skip_worktree(pathspec, i, &skip_worktree_seen)) + res = 1; + + if (res > 0) + break; + } + + free(skip_worktree_seen); + return res; +} + static int read_from_tree(const struct pathspec *pathspec, struct object_id *tree_oid, int intent_to_add) @@ -208,7 +275,13 @@ static int read_from_tree(const struct pathspec *pathspec, opt.format_callback = update_index_from_diff; opt.format_callback_data = &intent_to_add; opt.flags.override_submodule_config = 1; + opt.flags.recursive = 1; opt.repo = the_repository; + opt.change = diff_change; + opt.add_remove = diff_addremove; + + if (pathspec->nr && the_index.sparse_index && pathspec_needs_expanded_index(pathspec)) + ensure_full_index(&the_index); if (do_diff_cache(tree_oid, &opt)) return 1; @@ -287,9 +360,6 @@ static void parse_args(struct pathspec *pathspec, } *rev_ret = rev; - if (read_cache() < 0) - die(_("index file corrupt")); - parse_pathspec(pathspec, 0, PATHSPEC_PREFER_FULL | (patch_mode ? PATHSPEC_PREFIX_ORIGIN : 0), @@ -446,6 +516,12 @@ int cmd_reset(int argc, const char **argv, const char *prefix) if (intent_to_add && reset_type != MIXED) die(_("-N can only be used with --mixed")); + prepare_repo_settings(the_repository); + the_repository->settings.command_requires_full_index = 0; + + if (read_cache() < 0) + die(_("index file corrupt")); + /* Soft reset does not touch the index file nor the working tree * at all, but requires them in a good order. Other resets reset * the index file to the tree object we are switching to. */ diff --git a/cache-tree.c b/cache-tree.c index 848494496bf085..04d1a1f0f5efb1 100644 --- a/cache-tree.c +++ b/cache-tree.c @@ -801,15 +801,26 @@ int write_index_as_tree(struct object_id *oid, struct index_state *index_state, return ret; } +static void prime_cache_tree_sparse_dir(struct cache_tree *it, + struct tree *tree) +{ + + oidcpy(&it->oid, &tree->object.oid); + it->entry_count = 1; +} + static void prime_cache_tree_rec(struct repository *r, struct cache_tree *it, - struct tree *tree) + struct tree *tree, + struct strbuf *tree_path) { struct tree_desc desc; struct name_entry entry; int cnt; + int base_path_len = tree_path->len; oidcpy(&it->oid, &tree->object.oid); + init_tree_desc(&desc, tree->buffer, tree->size); cnt = 0; while (tree_entry(&desc, &entry)) { @@ -818,14 +829,40 @@ static void prime_cache_tree_rec(struct repository *r, else { struct cache_tree_sub *sub; struct tree *subtree = lookup_tree(r, &entry.oid); + if (!subtree->object.parsed) parse_tree(subtree); sub = cache_tree_sub(it, entry.path); sub->cache_tree = cache_tree(); - prime_cache_tree_rec(r, sub->cache_tree, subtree); + + /* + * Recursively-constructed subtree path is only needed when working + * in a sparse index (where it's used to determine whether the + * subtree is a sparse directory in the index). + */ + if (r->index->sparse_index) { + strbuf_setlen(tree_path, base_path_len); + strbuf_grow(tree_path, base_path_len + entry.pathlen + 1); + strbuf_add(tree_path, entry.path, entry.pathlen); + strbuf_addch(tree_path, '/'); + } + + /* + * If a sparse index is in use, the directory being processed may be + * sparse. To confirm that, we can check whether an entry with that + * exact name exists in the index. If it does, the created subtree + * should be sparse. Otherwise, cache tree expansion should continue + * as normal. + */ + if (r->index->sparse_index && + index_entry_exists(r->index, tree_path->buf, tree_path->len)) + prime_cache_tree_sparse_dir(sub->cache_tree, subtree); + else + prime_cache_tree_rec(r, sub->cache_tree, subtree, tree_path); cnt += sub->cache_tree->entry_count; } } + it->entry_count = cnt; } @@ -833,11 +870,14 @@ void prime_cache_tree(struct repository *r, struct index_state *istate, struct tree *tree) { + struct strbuf tree_path = STRBUF_INIT; + trace2_region_enter("cache-tree", "prime_cache_tree", r); cache_tree_free(&istate->cache_tree); istate->cache_tree = cache_tree(); - prime_cache_tree_rec(r, istate->cache_tree, tree); + prime_cache_tree_rec(r, istate->cache_tree, tree, &tree_path); + strbuf_release(&tree_path); istate->cache_changed |= CACHE_TREE_CHANGED; trace2_region_leave("cache-tree", "prime_cache_tree", r); } diff --git a/cache.h b/cache.h index 9f92bfebff3b4c..5bb484abb89bee 100644 --- a/cache.h +++ b/cache.h @@ -833,6 +833,16 @@ struct cache_entry *index_file_next_match(struct index_state *istate, struct cac */ int index_name_pos(struct index_state *, const char *name, int namelen); +/* + * Determines whether an entry with the given name exists within the + * given index. The return value is 1 if an exact match is found, otherwise + * it is 0. Note that, unlike index_name_pos, this function does not expand + * the index if it is sparse. If an item exists within the full index but it + * is contained within a sparse directory (and not in the sparse index), 0 is + * returned. + */ +int index_entry_exists(struct index_state *, const char *name, int namelen); + /* * Some functions return the negative complement of an insert position when a * precise match was not found but a position was found where the entry would diff --git a/read-cache.c b/read-cache.c index 141e7a1087f8e4..ee2831494bafac 100644 --- a/read-cache.c +++ b/read-cache.c @@ -70,6 +70,11 @@ */ #define CACHE_ENTRY_PATH_LENGTH 80 +enum index_search_mode { + NO_EXPAND_SPARSE = 0, + EXPAND_SPARSE = 1 +}; + static inline struct cache_entry *mem_pool__ce_alloc(struct mem_pool *mem_pool, size_t len) { struct cache_entry *ce; @@ -564,7 +569,10 @@ int cache_name_stage_compare(const char *name1, int len1, int stage1, const char return 0; } -static int index_name_stage_pos(struct index_state *istate, const char *name, int namelen, int stage) +static int index_name_stage_pos(struct index_state *istate, + const char *name, int namelen, + int stage, + enum index_search_mode search_mode) { int first, last; @@ -583,7 +591,7 @@ static int index_name_stage_pos(struct index_state *istate, const char *name, in first = next+1; } - if (istate->sparse_index && + if (search_mode == EXPAND_SPARSE && istate->sparse_index && first > 0) { /* Note: first <= istate->cache_nr */ struct cache_entry *ce = istate->cache[first - 1]; @@ -599,7 +607,7 @@ static int index_name_stage_pos(struct index_state *istate, const char *name, in ce_namelen(ce) < namelen && !strncmp(name, ce->name, ce_namelen(ce))) { ensure_full_index(istate); - return index_name_stage_pos(istate, name, namelen, stage); + return index_name_stage_pos(istate, name, namelen, stage, search_mode); } } @@ -608,7 +616,12 @@ static int index_name_stage_pos(struct index_state *istate, const char *name, in int index_name_pos(struct index_state *istate, const char *name, int namelen) { - return index_name_stage_pos(istate, name, namelen, 0); + return index_name_stage_pos(istate, name, namelen, 0, EXPAND_SPARSE); +} + +int index_entry_exists(struct index_state *istate, const char *name, int namelen) +{ + return index_name_stage_pos(istate, name, namelen, 0, NO_EXPAND_SPARSE) >= 0; } int remove_index_entry_at(struct index_state *istate, int pos) @@ -1250,7 +1263,7 @@ static int has_dir_name(struct index_state *istate, */ } - pos = index_name_stage_pos(istate, name, len, stage); + pos = index_name_stage_pos(istate, name, len, stage, EXPAND_SPARSE); if (pos >= 0) { /* * Found one, but not so fast. This could @@ -1350,7 +1363,7 @@ static int add_index_entry_with_check(struct index_state *istate, struct cache_e strcmp(ce->name, istate->cache[istate->cache_nr - 1]->name) > 0) pos = index_pos_to_insert_pos(istate->cache_nr); else - pos = index_name_stage_pos(istate, ce->name, ce_namelen(ce), ce_stage(ce)); + pos = index_name_stage_pos(istate, ce->name, ce_namelen(ce), ce_stage(ce), EXPAND_SPARSE); /* existing match? Just replace it. */ if (pos >= 0) { @@ -1385,7 +1398,7 @@ static int add_index_entry_with_check(struct index_state *istate, struct cache_e if (!ok_to_replace) return error(_("'%s' appears as both a file and as a directory"), ce->name); - pos = index_name_stage_pos(istate, ce->name, ce_namelen(ce), ce_stage(ce)); + pos = index_name_stage_pos(istate, ce->name, ce_namelen(ce), ce_stage(ce), EXPAND_SPARSE); pos = -pos-1; } return pos + 1; diff --git a/t/t1092-sparse-checkout-compatibility.sh b/t/t1092-sparse-checkout-compatibility.sh index e7ef6abe92a5b3..3e24c00140e810 100755 --- a/t/t1092-sparse-checkout-compatibility.sh +++ b/t/t1092-sparse-checkout-compatibility.sh @@ -511,6 +511,113 @@ test_expect_success 'checkout and reset (mixed) [sparse]' ' test_sparse_match git reset update-folder2 ' +# NEEDSWORK: with mixed reset, files with differences between HEAD and +# will be added to the work tree even if outside the sparse checkout +# definition, and even if the file is modified to a state of having no local +# changes. The file is "re-ignored" if a hard reset is executed. We may want to +# change this behavior in the future and enforce that files are not written +# outside of the sparse checkout definition. +test_expect_success 'checkout and mixed reset file tracking [sparse]' ' + init_repos && + + test_all_match git checkout -b reset-test update-deep && + test_all_match git reset update-folder1 && + test_all_match git reset update-deep && + + # At this point, there are no changes in the working tree. However, + # folder1/a now exists locally (even though it is outside of the sparse + # paths). + run_on_sparse test_path_exists folder1 && + + run_on_all rm folder1/a && + test_all_match git status --porcelain=v2 && + + test_all_match git reset --hard update-deep && + run_on_sparse test_path_is_missing folder1 && + test_path_exists full-checkout/folder1 +' + +test_expect_success 'checkout and reset (merge)' ' + init_repos && + + write_script edit-contents <<-\EOF && + echo text >>$1 + EOF + + test_all_match git checkout -b reset-test update-deep && + run_on_all ../edit-contents a && + test_all_match git reset --merge deepest && + test_all_match git status --porcelain=v2 && + + test_all_match git reset --hard update-deep && + run_on_all ../edit-contents deep/a && + test_all_match test_must_fail git reset --merge deepest +' + +test_expect_success 'checkout and reset (keep)' ' + init_repos && + + write_script edit-contents <<-\EOF && + echo text >>$1 + EOF + + test_all_match git checkout -b reset-test update-deep && + run_on_all ../edit-contents a && + test_all_match git reset --keep deepest && + test_all_match git status --porcelain=v2 && + + test_all_match git reset --hard update-deep && + run_on_all ../edit-contents deep/a && + test_all_match test_must_fail git reset --keep deepest +' + +test_expect_success 'reset with pathspecs inside sparse definition' ' + init_repos && + + write_script edit-contents <<-\EOF && + echo text >>$1 + EOF + + test_all_match git checkout -b reset-test update-deep && + run_on_all ../edit-contents deep/a && + + test_all_match git reset base -- deep/a && + test_all_match git status --porcelain=v2 && + + test_all_match git reset base -- nonexistent-file && + test_all_match git status --porcelain=v2 && + + test_all_match git reset deepest -- deep && + test_all_match git status --porcelain=v2 +' + +test_expect_success 'reset with sparse directory pathspec outside definition' ' + init_repos && + + test_all_match git checkout -b reset-test update-deep && + test_all_match git reset --hard update-folder1 && + test_all_match git reset base -- folder1 && + test_all_match git status --porcelain=v2 +' + +test_expect_success 'reset with pathspec match in sparse directory' ' + init_repos && + + test_all_match git checkout -b reset-test update-deep && + test_all_match git reset --hard update-folder1 && + test_all_match git reset base -- folder1/a && + test_all_match git status --porcelain=v2 +' + +test_expect_success 'reset with wildcard pathspec' ' + init_repos && + + test_all_match git checkout -b reset-test update-deep && + test_all_match git reset --hard update-folder1 && + test_all_match git reset base -- \*/a && + test_all_match git status --porcelain=v2 +' + test_expect_success 'merge, cherry-pick, and rebase' ' init_repos && @@ -685,11 +792,15 @@ test_expect_success 'submodule handling' ' grep "160000 commit $(git -C initial-repo rev-parse HEAD) modules/sub" cache ' +# When working with a sparse index, some commands will need to expand the +# index to operate properly. If those commands also write the index back +# to disk, they need to convert the index to sparse before writing. +# This test verifies that both of these events are logged in trace2 logs. test_expect_success 'sparse-index is expanded and converted back' ' init_repos && GIT_TRACE2_EVENT="$(pwd)/trace2.txt" GIT_TRACE2_EVENT_NESTING=10 \ - git -C sparse-index -c core.fsmonitor="" reset --hard && + git -C sparse-index reset -- folder1/a && test_region index convert_to_sparse trace2.txt && test_region index ensure_full_index trace2.txt ' @@ -726,9 +837,9 @@ test_expect_success 'sparse-index is not expanded' ' ensure_not_expanded checkout - && ensure_not_expanded switch rename-out-to-out && ensure_not_expanded switch - && - git -C sparse-index reset --hard && + ensure_not_expanded reset --hard && ensure_not_expanded checkout rename-out-to-out -- deep/deeper1 && - git -C sparse-index reset --hard && + ensure_not_expanded reset --hard && ensure_not_expanded restore -s rename-out-to-out -- deep/deeper1 && echo >>sparse-index/README.md && @@ -738,6 +849,45 @@ test_expect_success 'sparse-index is not expanded' ' echo >>sparse-index/untracked.txt && ensure_not_expanded add . && + for ref in update-deep update-folder1 update-folder2 update-deep + do + echo >>sparse-index/README.md && + ensure_not_expanded reset --hard $ref || return 1 + done && + + ensure_not_expanded reset --mixed base && + ensure_not_expanded reset --hard update-deep && + ensure_not_expanded reset --keep base && + ensure_not_expanded reset --merge update-deep && + + ensure_not_expanded reset base -- deep/a && + ensure_not_expanded reset base -- nonexistent-file && + ensure_not_expanded reset deepest -- deep && + + # Although folder1 is outside the sparse definition, it exists as a + # directory entry in the index, so it will be reset without needing to + # expand the full index. + ensure_not_expanded reset --hard update-folder1 && + ensure_not_expanded reset base -- folder1 && + + ensure_not_expanded reset --hard update-deep && + + ensure_not_expanded reset base -- deep/a && + ensure_not_expanded reset base -- nonexistent-file && + ensure_not_expanded reset deepest -- deep && + + # Although folder1 is outside the sparse definition, it exists as a + # directory entry in the index, so the pathspec will not force the + # index to be expanded. + ensure_not_expanded reset deepest -- folder1 && + ensure_not_expanded reset deepest -- folder1/ && + + # Wildcard identifies only in-cone files, no index expansion + ensure_not_expanded reset deepest -- deep/\* && + + # Wildcard identifies only full sparse directories, no index expansion + ensure_not_expanded reset deepest -- folder\* && + ensure_not_expanded checkout -f update-deep && test_config -C sparse-index pull.twohead ort && (