diff options
Diffstat (limited to 'submodule.c')
| -rw-r--r-- | submodule.c | 2601 |
1 files changed, 1941 insertions, 660 deletions
diff --git a/submodule.c b/submodule.c index 2f55436234..8e611fe1db 100644 --- a/submodule.c +++ b/submodule.c @@ -1,4 +1,8 @@ + #include "cache.h" +#include "repository.h" +#include "config.h" +#include "submodule-config.h" #include "submodule.h" #include "dir.h" #include "diff.h" @@ -8,65 +12,173 @@ #include "diffcore.h" #include "refs.h" #include "string-list.h" -#include "sha1-array.h" -#include "argv-array.h" - -static struct string_list config_name_for_path; -static struct string_list config_fetch_recurse_submodules_for_name; -static struct string_list config_ignore_for_name; -static int config_fetch_recurse_submodules = RECURSE_SUBMODULES_ON_DEMAND; -static struct string_list changed_submodule_paths; +#include "oid-array.h" +#include "strvec.h" +#include "blob.h" +#include "thread-utils.h" +#include "quote.h" +#include "remote.h" +#include "worktree.h" +#include "parse-options.h" +#include "object-store.h" +#include "commit-reach.h" + +static int config_update_recurse_submodules = RECURSE_SUBMODULES_OFF; static int initialized_fetch_ref_tips; -static struct sha1_array ref_tips_before_fetch; -static struct sha1_array ref_tips_after_fetch; +static struct oid_array ref_tips_before_fetch; +static struct oid_array ref_tips_after_fetch; + +/* + * Check if the .gitmodules file is unmerged. Parsing of the .gitmodules file + * will be disabled because we can't guess what might be configured in + * .gitmodules unless the user resolves the conflict. + */ +int is_gitmodules_unmerged(struct index_state *istate) +{ + int pos = index_name_pos(istate, GITMODULES_FILE, strlen(GITMODULES_FILE)); + if (pos < 0) { /* .gitmodules not found or isn't merged */ + pos = -1 - pos; + if (istate->cache_nr > pos) { /* there is a .gitmodules */ + const struct cache_entry *ce = istate->cache[pos]; + if (ce_namelen(ce) == strlen(GITMODULES_FILE) && + !strcmp(ce->name, GITMODULES_FILE)) + return 1; + } + } + + return 0; +} + +/* + * Check if the .gitmodules file is safe to write. + * + * Writing to the .gitmodules file requires that the file exists in the + * working tree or, if it doesn't, that a brand new .gitmodules file is going + * to be created (i.e. it's neither in the index nor in the current branch). + * + * It is not safe to write to .gitmodules if it's not in the working tree but + * it is in the index or in the current branch, because writing new values + * (and staging them) would blindly overwrite ALL the old content. + */ +int is_writing_gitmodules_ok(void) +{ + struct object_id oid; + return file_exists(GITMODULES_FILE) || + (get_oid(GITMODULES_INDEX, &oid) < 0 && get_oid(GITMODULES_HEAD, &oid) < 0); +} /* - * The following flag is set if the .gitmodules file is unmerged. We then - * disable recursion for all submodules where .git/config doesn't have a - * matching config entry because we can't guess what might be configured in - * .gitmodules unless the user resolves the conflict. When a command line - * option is given (which always overrides configuration) this flag will be - * ignored. + * Check if the .gitmodules file has unstaged modifications. This must be + * checked before allowing modifications to the .gitmodules file with the + * intention to stage them later, because when continuing we would stage the + * modifications the user didn't stage herself too. That might change in a + * future version when we learn to stage the changes we do ourselves without + * staging any previous modifications. */ -static int gitmodules_is_unmerged; +int is_staging_gitmodules_ok(struct index_state *istate) +{ + int pos = index_name_pos(istate, GITMODULES_FILE, strlen(GITMODULES_FILE)); + + if ((pos >= 0) && (pos < istate->cache_nr)) { + struct stat st; + if (lstat(GITMODULES_FILE, &st) == 0 && + ie_modified(istate, istate->cache[pos], &st, 0) & DATA_CHANGED) + return 0; + } + + return 1; +} + +static int for_each_remote_ref_submodule(const char *submodule, + each_ref_fn fn, void *cb_data) +{ + return refs_for_each_remote_ref(get_submodule_ref_store(submodule), + fn, cb_data); +} + +/* + * Try to update the "path" entry in the "submodule.<name>" section of the + * .gitmodules file. Return 0 only if a .gitmodules file was found, a section + * with the correct path=<oldpath> setting was found and we could update it. + */ +int update_path_in_gitmodules(const char *oldpath, const char *newpath) +{ + struct strbuf entry = STRBUF_INIT; + const struct submodule *submodule; + int ret; + + if (!file_exists(GITMODULES_FILE)) /* Do nothing without .gitmodules */ + return -1; + + if (is_gitmodules_unmerged(the_repository->index)) + die(_("Cannot change unmerged .gitmodules, resolve merge conflicts first")); + + submodule = submodule_from_path(the_repository, null_oid(), oldpath); + if (!submodule || !submodule->name) { + warning(_("Could not find section in .gitmodules where path=%s"), oldpath); + return -1; + } + strbuf_addstr(&entry, "submodule."); + strbuf_addstr(&entry, submodule->name); + strbuf_addstr(&entry, ".path"); + ret = config_set_in_gitmodules_file_gently(entry.buf, newpath); + strbuf_release(&entry); + return ret; +} + +/* + * Try to remove the "submodule.<name>" section from .gitmodules where the given + * path is configured. Return 0 only if a .gitmodules file was found, a section + * with the correct path=<path> setting was found and we could remove it. + */ +int remove_path_from_gitmodules(const char *path) +{ + struct strbuf sect = STRBUF_INIT; + const struct submodule *submodule; + + if (!file_exists(GITMODULES_FILE)) /* Do nothing without .gitmodules */ + return -1; + + if (is_gitmodules_unmerged(the_repository->index)) + die(_("Cannot change unmerged .gitmodules, resolve merge conflicts first")); + + submodule = submodule_from_path(the_repository, null_oid(), path); + if (!submodule || !submodule->name) { + warning(_("Could not find section in .gitmodules where path=%s"), path); + return -1; + } + strbuf_addstr(§, "submodule."); + strbuf_addstr(§, submodule->name); + if (git_config_rename_section_in_file(GITMODULES_FILE, sect.buf, NULL) < 0) { + /* Maybe the user already did that, don't error out here */ + warning(_("Could not remove .gitmodules entry for %s"), path); + strbuf_release(§); + return -1; + } + strbuf_release(§); + return 0; +} + +void stage_updated_gitmodules(struct index_state *istate) +{ + if (add_file_to_index(istate, GITMODULES_FILE, 0)) + die(_("staging updated .gitmodules failed")); +} -static int add_submodule_odb(const char *path) +/* TODO: remove this function, use repo_submodule_init instead. */ +int add_submodule_odb(const char *path) { struct strbuf objects_directory = STRBUF_INIT; - struct alternate_object_database *alt_odb; int ret = 0; - const char *git_dir; - strbuf_addf(&objects_directory, "%s/.git", path); - git_dir = read_gitfile(objects_directory.buf); - if (git_dir) { - strbuf_reset(&objects_directory); - strbuf_addstr(&objects_directory, git_dir); - } - strbuf_addstr(&objects_directory, "/objects/"); + ret = strbuf_git_path_submodule(&objects_directory, path, "objects/"); + if (ret) + goto done; if (!is_directory(objects_directory.buf)) { ret = -1; goto done; } - /* avoid adding it twice */ - for (alt_odb = alt_odb_list; alt_odb; alt_odb = alt_odb->next) - if (alt_odb->name - alt_odb->base == objects_directory.len && - !strncmp(alt_odb->base, objects_directory.buf, - objects_directory.len)) - goto done; - - alt_odb = xmalloc(objects_directory.len + 42 + sizeof(*alt_odb)); - alt_odb->next = alt_odb_list; - strcpy(alt_odb->base, objects_directory.buf); - alt_odb->name = alt_odb->base + objects_directory.len; - alt_odb->name[2] = '/'; - alt_odb->name[40] = '\0'; - alt_odb->name[41] = '\0'; - alt_odb_list = alt_odb; - - /* add possible alternates from the submodule */ - read_info_alternates(objects_directory.buf, 0); - prepare_alt_odb(); + add_to_alternates_memory(objects_directory.buf); done: strbuf_release(&objects_directory); return ret; @@ -75,149 +187,282 @@ done: void set_diffopt_flags_from_submodule_config(struct diff_options *diffopt, const char *path) { - struct string_list_item *path_option, *ignore_option; - path_option = unsorted_string_list_lookup(&config_name_for_path, path); - if (path_option) { - ignore_option = unsorted_string_list_lookup(&config_ignore_for_name, path_option->util); - if (ignore_option) - handle_ignore_submodules_arg(diffopt, ignore_option->util); - else if (gitmodules_is_unmerged) - DIFF_OPT_SET(diffopt, IGNORE_SUBMODULES); + const struct submodule *submodule = submodule_from_path(the_repository, + null_oid(), + path); + if (submodule) { + const char *ignore; + char *key; + + key = xstrfmt("submodule.%s.ignore", submodule->name); + if (repo_config_get_string_tmp(the_repository, key, &ignore)) + ignore = submodule->ignore; + free(key); + + if (ignore) + handle_ignore_submodules_arg(diffopt, ignore); + else if (is_gitmodules_unmerged(the_repository->index)) + diffopt->flags.ignore_submodules = 1; + } +} + +/* Cheap function that only determines if we're interested in submodules at all */ +int git_default_submodule_config(const char *var, const char *value, void *cb) +{ + if (!strcmp(var, "submodule.recurse")) { + int v = git_config_bool(var, value) ? + RECURSE_SUBMODULES_ON : RECURSE_SUBMODULES_OFF; + config_update_recurse_submodules = v; } + return 0; } -int submodule_config(const char *var, const char *value, void *cb) +int option_parse_recurse_submodules_worktree_updater(const struct option *opt, + const char *arg, int unset) { - if (!prefixcmp(var, "submodule.")) - return parse_submodule_config_option(var, value); - else if (!strcmp(var, "fetch.recursesubmodules")) { - config_fetch_recurse_submodules = parse_fetch_recurse_submodules_arg(var, value); + if (unset) { + config_update_recurse_submodules = RECURSE_SUBMODULES_OFF; return 0; } + if (arg) + config_update_recurse_submodules = + parse_update_recurse_submodules_arg(opt->long_name, + arg); + else + config_update_recurse_submodules = RECURSE_SUBMODULES_ON; + return 0; } -void gitmodules_config(void) -{ - const char *work_tree = get_git_work_tree(); - if (work_tree) { - struct strbuf gitmodules_path = STRBUF_INIT; - int pos; - strbuf_addstr(&gitmodules_path, work_tree); - strbuf_addstr(&gitmodules_path, "/.gitmodules"); - if (read_cache() < 0) - die("index file corrupt"); - pos = cache_name_pos(".gitmodules", 11); - if (pos < 0) { /* .gitmodules not found or isn't merged */ - pos = -1 - pos; - if (active_nr > pos) { /* there is a .gitmodules */ - const struct cache_entry *ce = active_cache[pos]; - if (ce_namelen(ce) == 11 && - !memcmp(ce->name, ".gitmodules", 11)) - gitmodules_is_unmerged = 1; - } +/* + * Determine if a submodule has been initialized at a given 'path' + */ +int is_submodule_active(struct repository *repo, const char *path) +{ + int ret = 0; + char *key = NULL; + char *value = NULL; + const struct string_list *sl; + const struct submodule *module; + + module = submodule_from_path(repo, null_oid(), path); + + /* early return if there isn't a path->module mapping */ + if (!module) + return 0; + + /* submodule.<name>.active is set */ + key = xstrfmt("submodule.%s.active", module->name); + if (!repo_config_get_bool(repo, key, &ret)) { + free(key); + return ret; + } + free(key); + + /* submodule.active is set */ + sl = repo_config_get_value_multi(repo, "submodule.active"); + if (sl) { + struct pathspec ps; + struct strvec args = STRVEC_INIT; + const struct string_list_item *item; + + for_each_string_list_item(item, sl) { + strvec_push(&args, item->string); } - if (!gitmodules_is_unmerged) - git_config_from_file(submodule_config, gitmodules_path.buf, NULL); - strbuf_release(&gitmodules_path); + parse_pathspec(&ps, 0, 0, NULL, args.v); + ret = match_pathspec(repo->index, &ps, path, strlen(path), 0, NULL, 1); + + strvec_clear(&args); + clear_pathspec(&ps); + return ret; } + + /* fallback to checking if the URL is set */ + key = xstrfmt("submodule.%s.url", module->name); + ret = !repo_config_get_string(repo, key, &value); + + free(value); + free(key); + return ret; } -int parse_submodule_config_option(const char *var, const char *value) +int is_submodule_populated_gently(const char *path, int *return_error_code) { - int len; - struct string_list_item *config; - struct strbuf submodname = STRBUF_INIT; + int ret = 0; + char *gitdir = xstrfmt("%s/.git", path); - var += 10; /* Skip "submodule." */ + if (resolve_gitdir_gently(gitdir, return_error_code)) + ret = 1; - len = strlen(var); - if ((len > 5) && !strcmp(var + len - 5, ".path")) { - strbuf_add(&submodname, var, len - 5); - config = unsorted_string_list_lookup(&config_name_for_path, value); - if (config) - free(config->util); - else - config = string_list_append(&config_name_for_path, xstrdup(value)); - config->util = strbuf_detach(&submodname, NULL); - strbuf_release(&submodname); - } else if ((len > 23) && !strcmp(var + len - 23, ".fetchrecursesubmodules")) { - strbuf_add(&submodname, var, len - 23); - config = unsorted_string_list_lookup(&config_fetch_recurse_submodules_for_name, submodname.buf); - if (!config) - config = string_list_append(&config_fetch_recurse_submodules_for_name, - strbuf_detach(&submodname, NULL)); - config->util = (void *)(intptr_t)parse_fetch_recurse_submodules_arg(var, value); - strbuf_release(&submodname); - } else if ((len > 7) && !strcmp(var + len - 7, ".ignore")) { - if (strcmp(value, "untracked") && strcmp(value, "dirty") && - strcmp(value, "all") && strcmp(value, "none")) { - warning("Invalid parameter \"%s\" for config option \"submodule.%s.ignore\"", value, var); - return 0; - } + free(gitdir); + return ret; +} - strbuf_add(&submodname, var, len - 7); - config = unsorted_string_list_lookup(&config_ignore_for_name, submodname.buf); - if (config) - free(config->util); - else - config = string_list_append(&config_ignore_for_name, - strbuf_detach(&submodname, NULL)); - strbuf_release(&submodname); - config->util = xstrdup(value); - return 0; +/* + * Dies if the provided 'prefix' corresponds to an unpopulated submodule + */ +void die_in_unpopulated_submodule(struct index_state *istate, + const char *prefix) +{ + int i, prefixlen; + + if (!prefix) + return; + + prefixlen = strlen(prefix); + + for (i = 0; i < istate->cache_nr; i++) { + struct cache_entry *ce = istate->cache[i]; + int ce_len = ce_namelen(ce); + + if (!S_ISGITLINK(ce->ce_mode)) + continue; + if (prefixlen <= ce_len) + continue; + if (strncmp(ce->name, prefix, ce_len)) + continue; + if (prefix[ce_len] != '/') + continue; + + die(_("in unpopulated submodule '%s'"), ce->name); } +} + +/* + * Dies if any paths in the provided pathspec descends into a submodule + */ +void die_path_inside_submodule(struct index_state *istate, + const struct pathspec *ps) +{ + int i, j; + + for (i = 0; i < istate->cache_nr; i++) { + struct cache_entry *ce = istate->cache[i]; + int ce_len = ce_namelen(ce); + + if (!S_ISGITLINK(ce->ce_mode)) + continue; + + for (j = 0; j < ps->nr ; j++) { + const struct pathspec_item *item = &ps->items[j]; + + if (item->len <= ce_len) + continue; + if (item->match[ce_len] != '/') + continue; + if (strncmp(ce->name, item->match, ce_len)) + continue; + if (item->len == ce_len + 1) + continue; + + die(_("Pathspec '%s' is in submodule '%.*s'"), + item->original, ce_len, ce->name); + } + } +} + +enum submodule_update_type parse_submodule_update_type(const char *value) +{ + if (!strcmp(value, "none")) + return SM_UPDATE_NONE; + else if (!strcmp(value, "checkout")) + return SM_UPDATE_CHECKOUT; + else if (!strcmp(value, "rebase")) + return SM_UPDATE_REBASE; + else if (!strcmp(value, "merge")) + return SM_UPDATE_MERGE; + else if (*value == '!') + return SM_UPDATE_COMMAND; + else + return SM_UPDATE_UNSPECIFIED; +} + +int parse_submodule_update_strategy(const char *value, + struct submodule_update_strategy *dst) +{ + enum submodule_update_type type; + + free((void*)dst->command); + dst->command = NULL; + + type = parse_submodule_update_type(value); + if (type == SM_UPDATE_UNSPECIFIED) + return -1; + + dst->type = type; + if (type == SM_UPDATE_COMMAND) + dst->command = xstrdup(value + 1); + return 0; } +const char *submodule_strategy_to_string(const struct submodule_update_strategy *s) +{ + struct strbuf sb = STRBUF_INIT; + switch (s->type) { + case SM_UPDATE_CHECKOUT: + return "checkout"; + case SM_UPDATE_MERGE: + return "merge"; + case SM_UPDATE_REBASE: + return "rebase"; + case SM_UPDATE_NONE: + return "none"; + case SM_UPDATE_UNSPECIFIED: + return NULL; + case SM_UPDATE_COMMAND: + strbuf_addf(&sb, "!%s", s->command); + return strbuf_detach(&sb, NULL); + } + return NULL; +} + void handle_ignore_submodules_arg(struct diff_options *diffopt, const char *arg) { - DIFF_OPT_CLR(diffopt, IGNORE_SUBMODULES); - DIFF_OPT_CLR(diffopt, IGNORE_UNTRACKED_IN_SUBMODULES); - DIFF_OPT_CLR(diffopt, IGNORE_DIRTY_SUBMODULES); + diffopt->flags.ignore_submodule_set = 1; + diffopt->flags.ignore_submodules = 0; + diffopt->flags.ignore_untracked_in_submodules = 0; + diffopt->flags.ignore_dirty_submodules = 0; if (!strcmp(arg, "all")) - DIFF_OPT_SET(diffopt, IGNORE_SUBMODULES); + diffopt->flags.ignore_submodules = 1; else if (!strcmp(arg, "untracked")) - DIFF_OPT_SET(diffopt, IGNORE_UNTRACKED_IN_SUBMODULES); + diffopt->flags.ignore_untracked_in_submodules = 1; else if (!strcmp(arg, "dirty")) - DIFF_OPT_SET(diffopt, IGNORE_DIRTY_SUBMODULES); + diffopt->flags.ignore_dirty_submodules = 1; else if (strcmp(arg, "none")) - die("bad --ignore-submodules argument: %s", arg); + die(_("bad --ignore-submodules argument: %s"), arg); + /* + * Please update _git_status() in git-completion.bash when you + * add new options + */ } -static int prepare_submodule_summary(struct rev_info *rev, const char *path, - struct commit *left, struct commit *right, - int *fast_forward, int *fast_backward) +static int prepare_submodule_diff_summary(struct repository *r, struct rev_info *rev, + const char *path, + struct commit *left, struct commit *right, + struct commit_list *merge_bases) { - struct commit_list *merge_bases, *list; + struct commit_list *list; - init_revisions(rev, NULL); + repo_init_revisions(r, rev, NULL); setup_revisions(0, NULL, rev, NULL); rev->left_right = 1; rev->first_parent_only = 1; left->object.flags |= SYMMETRIC_LEFT; add_pending_object(rev, &left->object, path); add_pending_object(rev, &right->object, path); - merge_bases = get_merge_bases(left, right, 1); - if (merge_bases) { - if (merge_bases->item == left) - *fast_forward = 1; - else if (merge_bases->item == right) - *fast_backward = 1; - } for (list = merge_bases; list; list = list->next) { list->item->object.flags |= UNINTERESTING; add_pending_object(rev, &list->item->object, - sha1_to_hex(list->item->object.sha1)); + oid_to_hex(&list->item->object.oid)); } return prepare_revision_walk(rev); } -static void print_submodule_summary(struct rev_info *rev, FILE *f, - const char *del, const char *add, const char *reset) +static void print_submodule_diff_summary(struct repository *r, struct rev_info *rev, struct diff_options *o) { static const char format[] = " %m %s"; struct strbuf sb = STRBUF_INIT; @@ -226,125 +471,528 @@ static void print_submodule_summary(struct rev_info *rev, FILE *f, while ((commit = get_revision(rev))) { struct pretty_print_context ctx = {0}; ctx.date_mode = rev->date_mode; + ctx.output_encoding = get_log_output_encoding(); strbuf_setlen(&sb, 0); - if (commit->object.flags & SYMMETRIC_LEFT) { - if (del) - strbuf_addstr(&sb, del); - } - else if (add) - strbuf_addstr(&sb, add); - format_commit_message(commit, format, &sb, &ctx); - if (reset) - strbuf_addstr(&sb, reset); + repo_format_commit_message(r, commit, format, &sb, + &ctx); strbuf_addch(&sb, '\n'); - fprintf(f, "%s", sb.buf); + if (commit->object.flags & SYMMETRIC_LEFT) + diff_emit_submodule_del(o, sb.buf); + else + diff_emit_submodule_add(o, sb.buf); } strbuf_release(&sb); } -int parse_fetch_recurse_submodules_arg(const char *opt, const char *arg) +void prepare_submodule_repo_env(struct strvec *out) { - switch (git_config_maybe_bool(opt, arg)) { - case 1: - return RECURSE_SUBMODULES_ON; - case 0: - return RECURSE_SUBMODULES_OFF; - default: - if (!strcmp(arg, "on-demand")) - return RECURSE_SUBMODULES_ON_DEMAND; - die("bad %s argument: %s", opt, arg); + prepare_other_repo_env(out, DEFAULT_GIT_DIR_ENVIRONMENT); +} + +static void prepare_submodule_repo_env_in_gitdir(struct strvec *out) +{ + prepare_other_repo_env(out, "."); +} + +/* + * Initialize a repository struct for a submodule based on the provided 'path'. + * + * Unlike repo_submodule_init, this tolerates submodules not present + * in .gitmodules. This function exists only to preserve historical behavior, + * + * Returns the repository struct on success, + * NULL when the submodule is not present. + */ +static struct repository *open_submodule(const char *path) +{ + struct strbuf sb = STRBUF_INIT; + struct repository *out = xmalloc(sizeof(*out)); + + if (submodule_to_gitdir(&sb, path) || repo_init(out, sb.buf, NULL)) { + strbuf_release(&sb); + free(out); + return NULL; } + + /* Mark it as a submodule */ + out->submodule_prefix = xstrdup(path); + + strbuf_release(&sb); + return out; } -void show_submodule_summary(FILE *f, const char *path, - unsigned char one[20], unsigned char two[20], - unsigned dirty_submodule, const char *meta, - const char *del, const char *add, const char *reset) +/* + * Helper function to display the submodule header line prior to the full + * summary output. + * + * If it can locate the submodule git directory it will create a repository + * handle for the submodule and lookup both the left and right commits and + * put them into the left and right pointers. + */ +static void show_submodule_header(struct diff_options *o, + const char *path, + struct object_id *one, struct object_id *two, + unsigned dirty_submodule, + struct repository *sub, + struct commit **left, struct commit **right, + struct commit_list **merge_bases) { - struct rev_info rev; - struct commit *left = left, *right = right; const char *message = NULL; struct strbuf sb = STRBUF_INIT; int fast_forward = 0, fast_backward = 0; - if (is_null_sha1(two)) - message = "(submodule deleted)"; - else if (add_submodule_odb(path)) - message = "(not checked out)"; - else if (is_null_sha1(one)) + if (dirty_submodule & DIRTY_SUBMODULE_UNTRACKED) + diff_emit_submodule_untracked(o, path); + + if (dirty_submodule & DIRTY_SUBMODULE_MODIFIED) + diff_emit_submodule_modified(o, path); + + if (is_null_oid(one)) message = "(new submodule)"; - else if (!(left = lookup_commit_reference(one)) || - !(right = lookup_commit_reference(two))) - message = "(commits not present)"; + else if (is_null_oid(two)) + message = "(submodule deleted)"; - if (!message && - prepare_submodule_summary(&rev, path, left, right, - &fast_forward, &fast_backward)) - message = "(revision walker failed)"; + if (!sub) { + if (!message) + message = "(commits not present)"; + goto output_header; + } - if (dirty_submodule & DIRTY_SUBMODULE_UNTRACKED) - fprintf(f, "Submodule %s contains untracked content\n", path); - if (dirty_submodule & DIRTY_SUBMODULE_MODIFIED) - fprintf(f, "Submodule %s contains modified content\n", path); + /* + * Attempt to lookup the commit references, and determine if this is + * a fast forward or fast backwards update. + */ + *left = lookup_commit_reference(sub, one); + *right = lookup_commit_reference(sub, two); - if (!hashcmp(one, two)) { + /* + * Warn about missing commits in the submodule project, but only if + * they aren't null. + */ + if ((!is_null_oid(one) && !*left) || + (!is_null_oid(two) && !*right)) + message = "(commits not present)"; + + *merge_bases = repo_get_merge_bases(sub, *left, *right); + if (*merge_bases) { + if ((*merge_bases)->item == *left) + fast_forward = 1; + else if ((*merge_bases)->item == *right) + fast_backward = 1; + } + + if (oideq(one, two)) { strbuf_release(&sb); return; } - strbuf_addf(&sb, "%sSubmodule %s %s..", meta, path, - find_unique_abbrev(one, DEFAULT_ABBREV)); - if (!fast_backward && !fast_forward) - strbuf_addch(&sb, '.'); - strbuf_addf(&sb, "%s", find_unique_abbrev(two, DEFAULT_ABBREV)); +output_header: + strbuf_addf(&sb, "Submodule %s ", path); + strbuf_add_unique_abbrev(&sb, one, DEFAULT_ABBREV); + strbuf_addstr(&sb, (fast_backward || fast_forward) ? ".." : "..."); + strbuf_add_unique_abbrev(&sb, two, DEFAULT_ABBREV); if (message) - strbuf_addf(&sb, " %s%s\n", message, reset); + strbuf_addf(&sb, " %s\n", message); else - strbuf_addf(&sb, "%s:%s\n", fast_backward ? " (rewind)" : "", reset); - fwrite(sb.buf, sb.len, 1, f); + strbuf_addf(&sb, "%s:\n", fast_backward ? " (rewind)" : ""); + diff_emit_submodule_header(o, sb.buf); + + strbuf_release(&sb); +} + +void show_submodule_diff_summary(struct diff_options *o, const char *path, + struct object_id *one, struct object_id *two, + unsigned dirty_submodule) +{ + struct rev_info rev; + struct commit *left = NULL, *right = NULL; + struct commit_list *merge_bases = NULL; + struct repository *sub; + + sub = open_submodule(path); + show_submodule_header(o, path, one, two, dirty_submodule, + sub, &left, &right, &merge_bases); + + /* + * If we don't have both a left and a right pointer, there is no + * reason to try and display a summary. The header line should contain + * all the information the user needs. + */ + if (!left || !right || !sub) + goto out; + + /* Treat revision walker failure the same as missing commits */ + if (prepare_submodule_diff_summary(sub, &rev, path, left, right, merge_bases)) { + diff_emit_submodule_error(o, "(revision walker failed)\n"); + goto out; + } + + print_submodule_diff_summary(sub, &rev, o); + +out: + if (merge_bases) + free_commit_list(merge_bases); + clear_commit_marks(left, ~0); + clear_commit_marks(right, ~0); + if (sub) { + repo_clear(sub); + free(sub); + } +} + +void show_submodule_inline_diff(struct diff_options *o, const char *path, + struct object_id *one, struct object_id *two, + unsigned dirty_submodule) +{ + const struct object_id *old_oid = the_hash_algo->empty_tree, *new_oid = the_hash_algo->empty_tree; + struct commit *left = NULL, *right = NULL; + struct commit_list *merge_bases = NULL; + struct child_process cp = CHILD_PROCESS_INIT; + struct strbuf sb = STRBUF_INIT; + struct repository *sub; + + sub = open_submodule(path); + show_submodule_header(o, path, one, two, dirty_submodule, + sub, &left, &right, &merge_bases); + + /* We need a valid left and right commit to display a difference */ + if (!(left || is_null_oid(one)) || + !(right || is_null_oid(two))) + goto done; + + if (left) + old_oid = one; + if (right) + new_oid = two; + + cp.git_cmd = 1; + cp.dir = path; + cp.out = -1; + cp.no_stdin = 1; + + /* TODO: other options may need to be passed here. */ + strvec_pushl(&cp.args, "diff", "--submodule=diff", NULL); + strvec_pushf(&cp.args, "--color=%s", want_color(o->use_color) ? + "always" : "never"); + + if (o->flags.reverse_diff) { + strvec_pushf(&cp.args, "--src-prefix=%s%s/", + o->b_prefix, path); + strvec_pushf(&cp.args, "--dst-prefix=%s%s/", + o->a_prefix, path); + } else { + strvec_pushf(&cp.args, "--src-prefix=%s%s/", + o->a_prefix, path); + strvec_pushf(&cp.args, "--dst-prefix=%s%s/", + o->b_prefix, path); + } + strvec_push(&cp.args, oid_to_hex(old_oid)); + /* + * If the submodule has modified content, we will diff against the + * work tree, under the assumption that the user has asked for the + * diff format and wishes to actually see all differences even if they + * haven't yet been committed to the submodule yet. + */ + if (!(dirty_submodule & DIRTY_SUBMODULE_MODIFIED)) + strvec_push(&cp.args, oid_to_hex(new_oid)); + + prepare_submodule_repo_env(&cp.env_array); + if (start_command(&cp)) + diff_emit_submodule_error(o, "(diff failed)\n"); + + while (strbuf_getwholeline_fd(&sb, cp.out, '\n') != EOF) + diff_emit_submodule_pipethrough(o, sb.buf, sb.len); + + if (finish_command(&cp)) + diff_emit_submodule_error(o, "(diff failed)\n"); - if (!message) { - print_submodule_summary(&rev, f, del, add, reset); +done: + strbuf_release(&sb); + if (merge_bases) + free_commit_list(merge_bases); + if (left) clear_commit_marks(left, ~0); + if (right) clear_commit_marks(right, ~0); + if (sub) { + repo_clear(sub); + free(sub); } +} - strbuf_release(&sb); +int should_update_submodules(void) +{ + return config_update_recurse_submodules == RECURSE_SUBMODULES_ON; +} + +const struct submodule *submodule_from_ce(const struct cache_entry *ce) +{ + if (!S_ISGITLINK(ce->ce_mode)) + return NULL; + + if (!should_update_submodules()) + return NULL; + + return submodule_from_path(the_repository, null_oid(), ce->name); +} + +static struct oid_array *submodule_commits(struct string_list *submodules, + const char *name) +{ + struct string_list_item *item; + + item = string_list_insert(submodules, name); + if (item->util) + return (struct oid_array *) item->util; + + /* NEEDSWORK: should we have oid_array_init()? */ + item->util = xcalloc(1, sizeof(struct oid_array)); + return (struct oid_array *) item->util; +} + +struct collect_changed_submodules_cb_data { + struct repository *repo; + struct string_list *changed; + const struct object_id *commit_oid; +}; + +/* + * this would normally be two functions: default_name_from_path() and + * path_from_default_name(). Since the default name is the same as + * the submodule path we can get away with just one function which only + * checks whether there is a submodule in the working directory at that + * location. + */ +static const char *default_name_or_path(const char *path_or_name) +{ + int error_code; + + if (!is_submodule_populated_gently(path_or_name, &error_code)) + return NULL; + + return path_or_name; +} + +static void collect_changed_submodules_cb(struct diff_queue_struct *q, + struct diff_options *options, + void *data) +{ + struct collect_changed_submodules_cb_data *me = data; + struct string_list *changed = me->changed; + const struct object_id *commit_oid = me->commit_oid; + int i; + + for (i = 0; i < q->nr; i++) { + struct diff_filepair *p = q->queue[i]; + struct oid_array *commits; + const struct submodule *submodule; + const char *name; + + if (!S_ISGITLINK(p->two->mode)) + continue; + + submodule = submodule_from_path(me->repo, + commit_oid, p->two->path); + if (submodule) + name = submodule->name; + else { + name = default_name_or_path(p->two->path); + /* make sure name does not collide with existing one */ + if (name) + submodule = submodule_from_name(me->repo, + commit_oid, name); + if (submodule) { + warning(_("Submodule in commit %s at path: " + "'%s' collides with a submodule named " + "the same. Skipping it."), + oid_to_hex(commit_oid), p->two->path); + name = NULL; + } + } + + if (!name) + continue; + + commits = submodule_commits(changed, name); + oid_array_append(commits, &p->two->oid); + } +} + +/* + * Collect the paths of submodules in 'changed' which have changed based on + * the revisions as specified in 'argv'. Each entry in 'changed' will also + * have a corresponding 'struct oid_array' (in the 'util' field) which lists + * what the submodule pointers were updated to during the change. + */ +static void collect_changed_submodules(struct repository *r, + struct string_list *changed, + struct strvec *argv) +{ + struct rev_info rev; + const struct commit *commit; + int save_warning; + struct setup_revision_opt s_r_opt = { + .assume_dashdash = 1, + }; + + save_warning = warn_on_object_refname_ambiguity; + warn_on_object_refname_ambiguity = 0; + repo_init_revisions(r, &rev, NULL); + setup_revisions(argv->nr, argv->v, &rev, &s_r_opt); + warn_on_object_refname_ambiguity = save_warning; + if (prepare_revision_walk(&rev)) + die(_("revision walk setup failed")); + + while ((commit = get_revision(&rev))) { + struct rev_info diff_rev; + struct collect_changed_submodules_cb_data data; + data.repo = r; + data.changed = changed; + data.commit_oid = &commit->object.oid; + + repo_init_revisions(r, &diff_rev, NULL); + diff_rev.diffopt.output_format |= DIFF_FORMAT_CALLBACK; + diff_rev.diffopt.format_callback = collect_changed_submodules_cb; + diff_rev.diffopt.format_callback_data = &data; + diff_rev.dense_combined_merges = 1; + diff_tree_combined_merge(commit, &diff_rev); + } + + reset_revision_walk(); } -void set_config_fetch_recurse_submodules(int value) +static void free_submodules_oids(struct string_list *submodules) { - config_fetch_recurse_submodules = value; + struct string_list_item *item; + for_each_string_list_item(item, submodules) + oid_array_clear((struct oid_array *) item->util); + string_list_clear(submodules, 1); } -static int has_remote(const char *refname, const unsigned char *sha1, int flags, void *cb_data) +static int has_remote(const char *refname, const struct object_id *oid, + int flags, void *cb_data) { return 1; } -static int submodule_needs_pushing(const char *path, const unsigned char sha1[20]) +static int append_oid_to_argv(const struct object_id *oid, void *data) +{ + struct strvec *argv = data; + strvec_push(argv, oid_to_hex(oid)); + return 0; +} + +struct has_commit_data { + struct repository *repo; + int result; + const char *path; +}; + +static int check_has_commit(const struct object_id *oid, void *data) { - if (add_submodule_odb(path) || !lookup_commit_reference(sha1)) + struct has_commit_data *cb = data; + + enum object_type type = oid_object_info(cb->repo, oid, NULL); + + switch (type) { + case OBJ_COMMIT: + return 0; + case OBJ_BAD: + /* + * Object is missing or invalid. If invalid, an error message + * has already been printed. + */ + cb->result = 0; + return 0; + default: + die(_("submodule entry '%s' (%s) is a %s, not a commit"), + cb->path, oid_to_hex(oid), type_name(type)); + } +} + +static int submodule_has_commits(struct repository *r, + const char *path, + struct oid_array *commits) +{ + struct has_commit_data has_commit = { r, 1, path }; + + /* + * Perform a cheap, but incorrect check for the existence of 'commits'. + * This is done by adding the submodule's object store to the in-core + * object store, and then querying for each commit's existence. If we + * do not have the commit object anywhere, there is no chance we have + * it in the object store of the correct submodule and have it + * reachable from a ref, so we can fail early without spawning rev-list + * which is expensive. + */ + if (add_submodule_odb(path)) + return 0; + + oid_array_for_each_unique(commits, check_has_commit, &has_commit); + + if (has_commit.result) { + /* + * Even if the submodule is checked out and the commit is + * present, make sure it exists in the submodule's object store + * and that it is reachable from a ref. + */ + struct child_process cp = CHILD_PROCESS_INIT; + struct strbuf out = STRBUF_INIT; + + strvec_pushl(&cp.args, "rev-list", "-n", "1", NULL); + oid_array_for_each_unique(commits, append_oid_to_argv, &cp.args); + strvec_pushl(&cp.args, "--not", "--all", NULL); + + prepare_submodule_repo_env(&cp.env_array); + cp.git_cmd = 1; + cp.no_stdin = 1; + cp.dir = path; + + if (capture_command(&cp, &out, GIT_MAX_HEXSZ + 1) || out.len) + has_commit.result = 0; + + strbuf_release(&out); + } + + return has_commit.result; +} + +static int submodule_needs_pushing(struct repository *r, + const char *path, + struct oid_array *commits) +{ + if (!submodule_has_commits(r, path, commits)) + /* + * NOTE: We do consider it safe to return "no" here. The + * correct answer would be "We do not know" instead of + * "No push needed", but it is quite hard to change + * the submodule pointer without having the submodule + * around. If a user did however change the submodules + * without having the submodule around, this indicates + * an expert who knows what they are doing or a + * maintainer integrating work from other people. In + * both cases it should be safe to skip this check. + */ return 0; if (for_each_remote_ref_submodule(path, has_remote, NULL) > 0) { - struct child_process cp; - const char *argv[] = {"rev-list", NULL, "--not", "--remotes", "-n", "1" , NULL}; + struct child_process cp = CHILD_PROCESS_INIT; struct strbuf buf = STRBUF_INIT; int needs_pushing = 0; - argv[1] = sha1_to_hex(sha1); - memset(&cp, 0, sizeof(cp)); - cp.argv = argv; - cp.env = local_repo_env; + strvec_push(&cp.args, "rev-list"); + oid_array_for_each_unique(commits, append_oid_to_argv, &cp.args); + strvec_pushl(&cp.args, "--not", "--remotes", "-n", "1" , NULL); + + prepare_submodule_repo_env(&cp.env_array); cp.git_cmd = 1; cp.no_stdin = 1; cp.out = -1; cp.dir = path; if (start_command(&cp)) - die("Could not run 'git rev-list %s --not --remotes -n 1' command in submodule %s", - sha1_to_hex(sha1), path); - if (strbuf_read(&buf, cp.out, 41)) + die(_("Could not run 'git rev-list <commits> --not --remotes -n 1' command in submodule %s"), + path); + if (strbuf_read(&buf, cp.out, the_hash_algo->hexsz + 1)) needs_pushing = 1; finish_command(&cp); close(cp.out); @@ -355,76 +1003,74 @@ static int submodule_needs_pushing(const char *path, const unsigned char sha1[20 return 0; } -static void collect_submodules_from_diff(struct diff_queue_struct *q, - struct diff_options *options, - void *data) +int find_unpushed_submodules(struct repository *r, + struct oid_array *commits, + const char *remotes_name, + struct string_list *needs_pushing) { - int i; - struct string_list *needs_pushing = data; + struct string_list submodules = STRING_LIST_INIT_DUP; + struct string_list_item *name; + struct strvec argv = STRVEC_INIT; + + /* argv.v[0] will be ignored by setup_revisions */ + strvec_push(&argv, "find_unpushed_submodules"); + oid_array_for_each_unique(commits, append_oid_to_argv, &argv); + strvec_push(&argv, "--not"); + strvec_pushf(&argv, "--remotes=%s", remotes_name); + + collect_changed_submodules(r, &submodules, &argv); + + for_each_string_list_item(name, &submodules) { + struct oid_array *commits = name->util; + const struct submodule *submodule; + const char *path = NULL; + + submodule = submodule_from_name(r, null_oid(), name->string); + if (submodule) + path = submodule->path; + else + path = default_name_or_path(name->string); - for (i = 0; i < q->nr; i++) { - struct diff_filepair *p = q->queue[i]; - if (!S_ISGITLINK(p->two->mode)) + if (!path) continue; - if (submodule_needs_pushing(p->two->path, p->two->sha1)) - string_list_insert(needs_pushing, p->two->path); - } -} -static void find_unpushed_submodule_commits(struct commit *commit, - struct string_list *needs_pushing) -{ - struct rev_info rev; - - init_revisions(&rev, NULL); - rev.diffopt.output_format |= DIFF_FORMAT_CALLBACK; - rev.diffopt.format_callback = collect_submodules_from_diff; - rev.diffopt.format_callback_data = needs_pushing; - diff_tree_combined_merge(commit, 1, &rev); -} - -int find_unpushed_submodules(unsigned char new_sha1[20], - const char *remotes_name, struct string_list *needs_pushing) -{ - struct rev_info rev; - struct commit *commit; - const char *argv[] = {NULL, NULL, "--not", "NULL", NULL}; - int argc = ARRAY_SIZE(argv) - 1; - char *sha1_copy; - - struct strbuf remotes_arg = STRBUF_INIT; - - strbuf_addf(&remotes_arg, "--remotes=%s", remotes_name); - init_revisions(&rev, NULL); - sha1_copy = xstrdup(sha1_to_hex(new_sha1)); - argv[1] = sha1_copy; - argv[3] = remotes_arg.buf; - setup_revisions(argc, argv, &rev, NULL); - if (prepare_revision_walk(&rev)) - die("revision walk setup failed"); - - while ((commit = get_revision(&rev)) != NULL) - find_unpushed_submodule_commits(commit, needs_pushing); + if (submodule_needs_pushing(r, path, commits)) + string_list_insert(needs_pushing, path); + } - reset_revision_walk(); - free(sha1_copy); - strbuf_release(&remotes_arg); + free_submodules_oids(&submodules); + strvec_clear(&argv); return needs_pushing->nr; } -static int push_submodule(const char *path) +static int push_submodule(const char *path, + const struct remote *remote, + const struct refspec *rs, + const struct string_list *push_options, + int dry_run) { - if (add_submodule_odb(path)) - return 1; - if (for_each_remote_ref_submodule(path, has_remote, NULL) > 0) { - struct child_process cp; - const char *argv[] = {"push", NULL}; + struct child_process cp = CHILD_PROCESS_INIT; + strvec_push(&cp.args, "push"); + if (dry_run) + strvec_push(&cp.args, "--dry-run"); + + if (push_options && push_options->nr) { + const struct string_list_item *item; + for_each_string_list_item(item, push_options) + strvec_pushf(&cp.args, "--push-option=%s", + item->string); + } - memset(&cp, 0, sizeof(cp)); - cp.argv = argv; - cp.env = local_repo_env; + if (remote->origin != REMOTE_UNCONFIGURED) { + int i; + strvec_push(&cp.args, remote->name); + for (i = 0; i < rs->raw_nr; i++) + strvec_push(&cp.args, rs->raw[i]); + } + + prepare_submodule_repo_env(&cp.env_array); cp.git_cmd = 1; cp.no_stdin = 1; cp.dir = path; @@ -436,22 +1082,81 @@ static int push_submodule(const char *path) return 1; } -int push_unpushed_submodules(unsigned char new_sha1[20], const char *remotes_name) +/* + * Perform a check in the submodule to see if the remote and refspec work. + * Die if the submodule can't be pushed. + */ +static void submodule_push_check(const char *path, const char *head, + const struct remote *remote, + const struct refspec *rs) { - int i, ret = 1; - struct string_list needs_pushing; + struct child_process cp = CHILD_PROCESS_INIT; + int i; - memset(&needs_pushing, 0, sizeof(struct string_list)); - needs_pushing.strdup_strings = 1; + strvec_push(&cp.args, "submodule--helper"); + strvec_push(&cp.args, "push-check"); + strvec_push(&cp.args, head); + strvec_push(&cp.args, remote->name); - if (!find_unpushed_submodules(new_sha1, remotes_name, &needs_pushing)) + for (i = 0; i < rs->raw_nr; i++) + strvec_push(&cp.args, rs->raw[i]); + + prepare_submodule_repo_env(&cp.env_array); + cp.git_cmd = 1; + cp.no_stdin = 1; + cp.no_stdout = 1; + cp.dir = path; + + /* + * Simply indicate if 'submodule--helper push-check' failed. + * More detailed error information will be provided by the + * child process. + */ + if (run_command(&cp)) + die(_("process for submodule '%s' failed"), path); +} + +int push_unpushed_submodules(struct repository *r, + struct oid_array *commits, + const struct remote *remote, + const struct refspec *rs, + const struct string_list *push_options, + int dry_run) +{ + int i, ret = 1; + struct string_list needs_pushing = STRING_LIST_INIT_DUP; + + if (!find_unpushed_submodules(r, commits, + remote->name, &needs_pushing)) return 1; + /* + * Verify that the remote and refspec can be propagated to all + * submodules. This check can be skipped if the remote and refspec + * won't be propagated due to the remote being unconfigured (e.g. a URL + * instead of a remote name). + */ + if (remote->origin != REMOTE_UNCONFIGURED) { + char *head; + struct object_id head_oid; + + head = resolve_refdup("HEAD", 0, &head_oid, NULL); + if (!head) + die(_("Failed to resolve HEAD as a valid ref.")); + + for (i = 0; i < needs_pushing.nr; i++) + submodule_push_check(needs_pushing.items[i].string, + head, remote, rs); + free(head); + } + + /* Actually push the submodules */ for (i = 0; i < needs_pushing.nr; i++) { const char *path = needs_pushing.items[i].string; - fprintf(stderr, "Pushing submodule '%s'\n", path); - if (!push_submodule(path)) { - fprintf(stderr, "Unable to push submodule '%s'\n", path); + fprintf(stderr, _("Pushing submodule '%s'\n"), path); + if (!push_submodule(path, remote, rs, + push_options, dry_run)) { + fprintf(stderr, _("Unable to push submodule '%s'\n"), path); ret = 0; } } @@ -461,299 +1166,561 @@ int push_unpushed_submodules(unsigned char new_sha1[20], const char *remotes_nam return ret; } -static int is_submodule_commit_present(const char *path, unsigned char sha1[20]) +static int append_oid_to_array(const char *ref, const struct object_id *oid, + int flags, void *data) { - int is_present = 0; - if (!add_submodule_odb(path) && lookup_commit_reference(sha1)) { - /* Even if the submodule is checked out and the commit is - * present, make sure it is reachable from a ref. */ - struct child_process cp; - const char *argv[] = {"rev-list", "-n", "1", NULL, "--not", "--all", NULL}; - struct strbuf buf = STRBUF_INIT; - - argv[3] = sha1_to_hex(sha1); - memset(&cp, 0, sizeof(cp)); - cp.argv = argv; - cp.env = local_repo_env; - cp.git_cmd = 1; - cp.no_stdin = 1; - cp.out = -1; - cp.dir = path; - if (!run_command(&cp) && !strbuf_read(&buf, cp.out, 1024)) - is_present = 1; + struct oid_array *array = data; + oid_array_append(array, oid); + return 0; +} - close(cp.out); - strbuf_release(&buf); +void check_for_new_submodule_commits(struct object_id *oid) +{ + if (!initialized_fetch_ref_tips) { + for_each_ref(append_oid_to_array, &ref_tips_before_fetch); + initialized_fetch_ref_tips = 1; } - return is_present; + + oid_array_append(&ref_tips_after_fetch, oid); } -static void submodule_collect_changed_cb(struct diff_queue_struct *q, - struct diff_options *options, - void *data) +static void calculate_changed_submodule_paths(struct repository *r, + struct string_list *changed_submodule_names) { - int i; - for (i = 0; i < q->nr; i++) { - struct diff_filepair *p = q->queue[i]; - if (!S_ISGITLINK(p->two->mode)) - continue; + struct strvec argv = STRVEC_INIT; + struct string_list_item *name; - if (S_ISGITLINK(p->one->mode)) { - /* NEEDSWORK: We should honor the name configured in - * the .gitmodules file of the commit we are examining - * here to be able to correctly follow submodules - * being moved around. */ - struct string_list_item *path; - path = unsorted_string_list_lookup(&changed_submodule_paths, p->two->path); - if (!path && !is_submodule_commit_present(p->two->path, p->two->sha1)) - string_list_append(&changed_submodule_paths, xstrdup(p->two->path)); - } else { - /* Submodule is new or was moved here */ - /* NEEDSWORK: When the .git directories of submodules - * live inside the superprojects .git directory some - * day we should fetch new submodules directly into - * that location too when config or options request - * that so they can be checked out from there. */ + /* No need to check if there are no submodules configured */ + if (!submodule_from_path(r, NULL, NULL)) + return; + + strvec_push(&argv, "--"); /* argv[0] program name */ + oid_array_for_each_unique(&ref_tips_after_fetch, + append_oid_to_argv, &argv); + strvec_push(&argv, "--not"); + oid_array_for_each_unique(&ref_tips_before_fetch, + append_oid_to_argv, &argv); + + /* + * Collect all submodules (whether checked out or not) for which new + * commits have been recorded upstream in "changed_submodule_names". + */ + collect_changed_submodules(r, changed_submodule_names, &argv); + + for_each_string_list_item(name, changed_submodule_names) { + struct oid_array *commits = name->util; + const struct submodule *submodule; + const char *path = NULL; + + submodule = submodule_from_name(r, null_oid(), name->string); + if (submodule) + path = submodule->path; + else + path = default_name_or_path(name->string); + + if (!path) continue; + + if (submodule_has_commits(r, path, commits)) { + oid_array_clear(commits); + *name->string = '\0'; } } -} -static int add_sha1_to_array(const char *ref, const unsigned char *sha1, - int flags, void *data) -{ - sha1_array_append(data, sha1); - return 0; + string_list_remove_empty_items(changed_submodule_names, 1); + + strvec_clear(&argv); + oid_array_clear(&ref_tips_before_fetch); + oid_array_clear(&ref_tips_after_fetch); + initialized_fetch_ref_tips = 0; } -void check_for_new_submodule_commits(unsigned char new_sha1[20]) +int submodule_touches_in_range(struct repository *r, + struct object_id *excl_oid, + struct object_id *incl_oid) { - if (!initialized_fetch_ref_tips) { - for_each_ref(add_sha1_to_array, &ref_tips_before_fetch); - initialized_fetch_ref_tips = 1; + struct string_list subs = STRING_LIST_INIT_DUP; + struct strvec args = STRVEC_INIT; + int ret; + + /* No need to check if there are no submodules configured */ + if (!submodule_from_path(r, NULL, NULL)) + return 0; + + strvec_push(&args, "--"); /* args[0] program name */ + strvec_push(&args, oid_to_hex(incl_oid)); + if (!is_null_oid(excl_oid)) { + strvec_push(&args, "--not"); + strvec_push(&args, oid_to_hex(excl_oid)); } - sha1_array_append(&ref_tips_after_fetch, new_sha1); + collect_changed_submodules(r, &subs, &args); + ret = subs.nr; + + strvec_clear(&args); + + free_submodules_oids(&subs); + return ret; } -static void add_sha1_to_argv(const unsigned char sha1[20], void *data) +struct submodule_parallel_fetch { + int count; + struct strvec args; + struct repository *r; + const char *prefix; + int command_line_option; + int default_option; + int quiet; + int result; + + struct string_list changed_submodule_names; + + /* Pending fetches by OIDs */ + struct fetch_task **oid_fetch_tasks; + int oid_fetch_tasks_nr, oid_fetch_tasks_alloc; + + struct strbuf submodules_with_errors; +}; +#define SPF_INIT {0, STRVEC_INIT, NULL, NULL, 0, 0, 0, 0, \ + STRING_LIST_INIT_DUP, \ + NULL, 0, 0, STRBUF_INIT} + +static int get_fetch_recurse_config(const struct submodule *submodule, + struct submodule_parallel_fetch *spf) { - argv_array_push(data, sha1_to_hex(sha1)); + if (spf->command_line_option != RECURSE_SUBMODULES_DEFAULT) + return spf->command_line_option; + + if (submodule) { + char *key; + const char *value; + + int fetch_recurse = submodule->fetch_recurse; + key = xstrfmt("submodule.%s.fetchRecurseSubmodules", submodule->name); + if (!repo_config_get_string_tmp(spf->r, key, &value)) { + fetch_recurse = parse_fetch_recurse_submodules_arg(key, value); + } + free(key); + + if (fetch_recurse != RECURSE_SUBMODULES_NONE) + /* local config overrules everything except commandline */ + return fetch_recurse; + } + + return spf->default_option; } -static void calculate_changed_submodule_paths(void) +/* + * Fetch in progress (if callback data) or + * pending (if in oid_fetch_tasks in struct submodule_parallel_fetch) + */ +struct fetch_task { + struct repository *repo; + const struct submodule *sub; + unsigned free_sub : 1; /* Do we need to free the submodule? */ + + struct oid_array *commits; /* Ensure these commits are fetched */ +}; + +/** + * When a submodule is not defined in .gitmodules, we cannot access it + * via the regular submodule-config. Create a fake submodule, which we can + * work on. + */ +static const struct submodule *get_non_gitmodules_submodule(const char *path) { - struct rev_info rev; - struct commit *commit; - struct argv_array argv = ARGV_ARRAY_INIT; + struct submodule *ret = NULL; + const char *name = default_name_or_path(path); - /* No need to check if there are no submodules configured */ - if (!config_name_for_path.nr) - return; + if (!name) + return NULL; - init_revisions(&rev, NULL); - argv_array_push(&argv, "--"); /* argv[0] program name */ - sha1_array_for_each_unique(&ref_tips_after_fetch, - add_sha1_to_argv, &argv); - argv_array_push(&argv, "--not"); - sha1_array_for_each_unique(&ref_tips_before_fetch, - add_sha1_to_argv, &argv); - setup_revisions(argv.argc, argv.argv, &rev, NULL); - if (prepare_revision_walk(&rev)) - die("revision walk setup failed"); + ret = xmalloc(sizeof(*ret)); + memset(ret, 0, sizeof(*ret)); + ret->path = name; + ret->name = name; - /* - * Collect all submodules (whether checked out or not) for which new - * commits have been recorded upstream in "changed_submodule_paths". - */ - while ((commit = get_revision(&rev))) { - struct commit_list *parent = commit->parents; - while (parent) { - struct diff_options diff_opts; - diff_setup(&diff_opts); - DIFF_OPT_SET(&diff_opts, RECURSIVE); - diff_opts.output_format |= DIFF_FORMAT_CALLBACK; - diff_opts.format_callback = submodule_collect_changed_cb; - diff_setup_done(&diff_opts); - diff_tree_sha1(parent->item->object.sha1, commit->object.sha1, "", &diff_opts); - diffcore_std(&diff_opts); - diff_flush(&diff_opts); - parent = parent->next; + return (const struct submodule *) ret; +} + +static struct fetch_task *fetch_task_create(struct repository *r, + const char *path) +{ + struct fetch_task *task = xmalloc(sizeof(*task)); + memset(task, 0, sizeof(*task)); + + task->sub = submodule_from_path(r, null_oid(), path); + if (!task->sub) { + /* + * No entry in .gitmodules? Technically not a submodule, + * but historically we supported repositories that happen to be + * in-place where a gitlink is. Keep supporting them. + */ + task->sub = get_non_gitmodules_submodule(path); + if (!task->sub) { + free(task); + return NULL; } + + task->free_sub = 1; } - argv_array_clear(&argv); - sha1_array_clear(&ref_tips_before_fetch); - sha1_array_clear(&ref_tips_after_fetch); - initialized_fetch_ref_tips = 0; + return task; } -int fetch_populated_submodules(const struct argv_array *options, - const char *prefix, int command_line_option, - int quiet) -{ - int i, result = 0; - struct child_process cp; - struct argv_array argv = ARGV_ARRAY_INIT; - struct string_list_item *name_for_path; - const char *work_tree = get_git_work_tree(); - if (!work_tree) - goto out; - - if (!the_index.initialized) - if (read_cache() < 0) - die("index file corrupt"); +static void fetch_task_release(struct fetch_task *p) +{ + if (p->free_sub) + free((void*)p->sub); + p->free_sub = 0; + p->sub = NULL; + + if (p->repo) + repo_clear(p->repo); + FREE_AND_NULL(p->repo); +} - argv_array_push(&argv, "fetch"); - for (i = 0; i < options->argc; i++) - argv_array_push(&argv, options->argv[i]); - argv_array_push(&argv, "--recurse-submodules-default"); - /* default value, "--submodule-prefix" and its value are added later */ +static struct repository *get_submodule_repo_for(struct repository *r, + const struct submodule *sub) +{ + struct repository *ret = xmalloc(sizeof(*ret)); + + if (repo_submodule_init(ret, r, sub)) { + /* + * No entry in .gitmodules? Technically not a submodule, + * but historically we supported repositories that happen to be + * in-place where a gitlink is. Keep supporting them. + */ + struct strbuf gitdir = STRBUF_INIT; + strbuf_repo_worktree_path(&gitdir, r, "%s/.git", sub->path); + if (repo_init(ret, gitdir.buf, NULL)) { + strbuf_release(&gitdir); + free(ret); + return NULL; + } + strbuf_release(&gitdir); + } - memset(&cp, 0, sizeof(cp)); - cp.env = local_repo_env; - cp.git_cmd = 1; - cp.no_stdin = 1; + return ret; +} - calculate_changed_submodule_paths(); +static int get_next_submodule(struct child_process *cp, + struct strbuf *err, void *data, void **task_cb) +{ + struct submodule_parallel_fetch *spf = data; - for (i = 0; i < active_nr; i++) { - struct strbuf submodule_path = STRBUF_INIT; - struct strbuf submodule_git_dir = STRBUF_INIT; - struct strbuf submodule_prefix = STRBUF_INIT; - struct cache_entry *ce = active_cache[i]; - const char *git_dir, *name, *default_argv; + for (; spf->count < spf->r->index->cache_nr; spf->count++) { + const struct cache_entry *ce = spf->r->index->cache[spf->count]; + const char *default_argv; + struct fetch_task *task; if (!S_ISGITLINK(ce->ce_mode)) continue; - name = ce->name; - name_for_path = unsorted_string_list_lookup(&config_name_for_path, ce->name); - if (name_for_path) - name = name_for_path->util; - - default_argv = "yes"; - if (command_line_option == RECURSE_SUBMODULES_DEFAULT) { - struct string_list_item *fetch_recurse_submodules_option; - fetch_recurse_submodules_option = unsorted_string_list_lookup(&config_fetch_recurse_submodules_for_name, name); - if (fetch_recurse_submodules_option) { - if ((intptr_t)fetch_recurse_submodules_option->util == RECURSE_SUBMODULES_OFF) - continue; - if ((intptr_t)fetch_recurse_submodules_option->util == RECURSE_SUBMODULES_ON_DEMAND) { - if (!unsorted_string_list_lookup(&changed_submodule_paths, ce->name)) - continue; - default_argv = "on-demand"; - } - } else { - if ((config_fetch_recurse_submodules == RECURSE_SUBMODULES_OFF) || - gitmodules_is_unmerged) - continue; - if (config_fetch_recurse_submodules == RECURSE_SUBMODULES_ON_DEMAND) { - if (!unsorted_string_list_lookup(&changed_submodule_paths, ce->name)) - continue; - default_argv = "on-demand"; - } - } - } else if (command_line_option == RECURSE_SUBMODULES_ON_DEMAND) { - if (!unsorted_string_list_lookup(&changed_submodule_paths, ce->name)) + task = fetch_task_create(spf->r, ce->name); + if (!task) + continue; + + switch (get_fetch_recurse_config(task->sub, spf)) + { + default: + case RECURSE_SUBMODULES_DEFAULT: + case RECURSE_SUBMODULES_ON_DEMAND: + if (!task->sub || + !string_list_lookup( + &spf->changed_submodule_names, + task->sub->name)) continue; default_argv = "on-demand"; + break; + case RECURSE_SUBMODULES_ON: + default_argv = "yes"; + break; + case RECURSE_SUBMODULES_OFF: + continue; } - strbuf_addf(&submodule_path, "%s/%s", work_tree, ce->name); - strbuf_addf(&submodule_git_dir, "%s/.git", submodule_path.buf); - strbuf_addf(&submodule_prefix, "%s%s/", prefix, ce->name); - git_dir = read_gitfile(submodule_git_dir.buf); - if (!git_dir) - git_dir = submodule_git_dir.buf; - if (is_directory(git_dir)) { - if (!quiet) - printf("Fetching submodule %s%s\n", prefix, ce->name); - cp.dir = submodule_path.buf; - argv_array_push(&argv, default_argv); - argv_array_push(&argv, "--submodule-prefix"); - argv_array_push(&argv, submodule_prefix.buf); - cp.argv = argv.argv; - if (run_command(&cp)) - result = 1; - argv_array_pop(&argv); - argv_array_pop(&argv); - argv_array_pop(&argv); + task->repo = get_submodule_repo_for(spf->r, task->sub); + if (task->repo) { + struct strbuf submodule_prefix = STRBUF_INIT; + child_process_init(cp); + cp->dir = task->repo->gitdir; + prepare_submodule_repo_env_in_gitdir(&cp->env_array); + cp->git_cmd = 1; + if (!spf->quiet) + strbuf_addf(err, _("Fetching submodule %s%s\n"), + spf->prefix, ce->name); + strvec_init(&cp->args); + strvec_pushv(&cp->args, spf->args.v); + strvec_push(&cp->args, default_argv); + strvec_push(&cp->args, "--submodule-prefix"); + + strbuf_addf(&submodule_prefix, "%s%s/", + spf->prefix, + task->sub->path); + strvec_push(&cp->args, submodule_prefix.buf); + + spf->count++; + *task_cb = task; + + strbuf_release(&submodule_prefix); + return 1; + } else { + struct strbuf empty_submodule_path = STRBUF_INIT; + + fetch_task_release(task); + free(task); + + /* + * An empty directory is normal, + * the submodule is not initialized + */ + strbuf_addf(&empty_submodule_path, "%s/%s/", + spf->r->worktree, + ce->name); + if (S_ISGITLINK(ce->ce_mode) && + !is_empty_dir(empty_submodule_path.buf)) { + spf->result = 1; + strbuf_addf(err, + _("Could not access submodule '%s'\n"), + ce->name); + } + strbuf_release(&empty_submodule_path); } - strbuf_release(&submodule_path); - strbuf_release(&submodule_git_dir); + } + + if (spf->oid_fetch_tasks_nr) { + struct fetch_task *task = + spf->oid_fetch_tasks[spf->oid_fetch_tasks_nr - 1]; + struct strbuf submodule_prefix = STRBUF_INIT; + spf->oid_fetch_tasks_nr--; + + strbuf_addf(&submodule_prefix, "%s%s/", + spf->prefix, task->sub->path); + + child_process_init(cp); + prepare_submodule_repo_env_in_gitdir(&cp->env_array); + cp->git_cmd = 1; + cp->dir = task->repo->gitdir; + + strvec_init(&cp->args); + strvec_pushv(&cp->args, spf->args.v); + strvec_push(&cp->args, "on-demand"); + strvec_push(&cp->args, "--submodule-prefix"); + strvec_push(&cp->args, submodule_prefix.buf); + + /* NEEDSWORK: have get_default_remote from submodule--helper */ + strvec_push(&cp->args, "origin"); + oid_array_for_each_unique(task->commits, + append_oid_to_argv, &cp->args); + + *task_cb = task; strbuf_release(&submodule_prefix); + return 1; } - argv_array_clear(&argv); + + return 0; +} + +static int fetch_start_failure(struct strbuf *err, + void *cb, void *task_cb) +{ + struct submodule_parallel_fetch *spf = cb; + struct fetch_task *task = task_cb; + + spf->result = 1; + + fetch_task_release(task); + return 0; +} + +static int commit_missing_in_sub(const struct object_id *oid, void *data) +{ + struct repository *subrepo = data; + + enum object_type type = oid_object_info(subrepo, oid, NULL); + + return type != OBJ_COMMIT; +} + +static int fetch_finish(int retvalue, struct strbuf *err, + void *cb, void *task_cb) +{ + struct submodule_parallel_fetch *spf = cb; + struct fetch_task *task = task_cb; + + struct string_list_item *it; + struct oid_array *commits; + + if (!task || !task->sub) + BUG("callback cookie bogus"); + + if (retvalue) { + /* + * NEEDSWORK: This indicates that the overall fetch + * failed, even though there may be a subsequent fetch + * by commit hash that might work. It may be a good + * idea to not indicate failure in this case, and only + * indicate failure if the subsequent fetch fails. + */ + spf->result = 1; + + strbuf_addf(&spf->submodules_with_errors, "\t%s\n", + task->sub->name); + } + + /* Is this the second time we process this submodule? */ + if (task->commits) + goto out; + + it = string_list_lookup(&spf->changed_submodule_names, task->sub->name); + if (!it) + /* Could be an unchanged submodule, not contained in the list */ + goto out; + + commits = it->util; + oid_array_filter(commits, + commit_missing_in_sub, + task->repo); + + /* Are there commits we want, but do not exist? */ + if (commits->nr) { + task->commits = commits; + ALLOC_GROW(spf->oid_fetch_tasks, + spf->oid_fetch_tasks_nr + 1, + spf->oid_fetch_tasks_alloc); + spf->oid_fetch_tasks[spf->oid_fetch_tasks_nr] = task; + spf->oid_fetch_tasks_nr++; + return 0; + } + +out: + fetch_task_release(task); + + return 0; +} + +int fetch_populated_submodules(struct repository *r, + const struct strvec *options, + const char *prefix, int command_line_option, + int default_option, + int quiet, int max_parallel_jobs) +{ + int i; + struct submodule_parallel_fetch spf = SPF_INIT; + + spf.r = r; + spf.command_line_option = command_line_option; + spf.default_option = default_option; + spf.quiet = quiet; + spf.prefix = prefix; + + if (!r->worktree) + goto out; + + if (repo_read_index(r) < 0) + die(_("index file corrupt")); + + strvec_push(&spf.args, "fetch"); + for (i = 0; i < options->nr; i++) + strvec_push(&spf.args, options->v[i]); + strvec_push(&spf.args, "--recurse-submodules-default"); + /* default value, "--submodule-prefix" and its value are added later */ + + calculate_changed_submodule_paths(r, &spf.changed_submodule_names); + string_list_sort(&spf.changed_submodule_names); + run_processes_parallel_tr2(max_parallel_jobs, + get_next_submodule, + fetch_start_failure, + fetch_finish, + &spf, + "submodule", "parallel/fetch"); + + if (spf.submodules_with_errors.len > 0) + fprintf(stderr, _("Errors during submodule fetch:\n%s"), + spf.submodules_with_errors.buf); + + + strvec_clear(&spf.args); out: - string_list_clear(&changed_submodule_paths, 1); - return result; + free_submodules_oids(&spf.changed_submodule_names); + return spf.result; } unsigned is_submodule_modified(const char *path, int ignore_untracked) { - ssize_t len; - struct child_process cp; - const char *argv[] = { - "status", - "--porcelain", - NULL, - NULL, - }; + struct child_process cp = CHILD_PROCESS_INIT; struct strbuf buf = STRBUF_INIT; + FILE *fp; unsigned dirty_submodule = 0; - const char *line, *next_line; const char *git_dir; + int ignore_cp_exit_code = 0; strbuf_addf(&buf, "%s/.git", path); git_dir = read_gitfile(buf.buf); if (!git_dir) git_dir = buf.buf; - if (!is_directory(git_dir)) { + if (!is_git_directory(git_dir)) { + if (is_directory(git_dir)) + die(_("'%s' not recognized as a git repository"), git_dir); strbuf_release(&buf); /* The submodule is not checked out, so it is not modified */ return 0; - } strbuf_reset(&buf); + strvec_pushl(&cp.args, "status", "--porcelain=2", NULL); if (ignore_untracked) - argv[2] = "-uno"; + strvec_push(&cp.args, "-uno"); - memset(&cp, 0, sizeof(cp)); - cp.argv = argv; - cp.env = local_repo_env; + prepare_submodule_repo_env(&cp.env_array); cp.git_cmd = 1; cp.no_stdin = 1; cp.out = -1; cp.dir = path; if (start_command(&cp)) - die("Could not run 'git status --porcelain' in submodule %s", path); + die(_("Could not run 'git status --porcelain=2' in submodule %s"), path); - len = strbuf_read(&buf, cp.out, 1024); - line = buf.buf; - while (len > 2) { - if ((line[0] == '?') && (line[1] == '?')) { + fp = xfdopen(cp.out, "r"); + while (strbuf_getwholeline(&buf, fp, '\n') != EOF) { + /* regular untracked files */ + if (buf.buf[0] == '?') dirty_submodule |= DIRTY_SUBMODULE_UNTRACKED; - if (dirty_submodule & DIRTY_SUBMODULE_MODIFIED) - break; - } else { - dirty_submodule |= DIRTY_SUBMODULE_MODIFIED; - if (ignore_untracked || - (dirty_submodule & DIRTY_SUBMODULE_UNTRACKED)) - break; + + if (buf.buf[0] == 'u' || + buf.buf[0] == '1' || + buf.buf[0] == '2') { + /* T = line type, XY = status, SSSS = submodule state */ + if (buf.len < strlen("T XY SSSS")) + BUG("invalid status --porcelain=2 line %s", + buf.buf); + + if (buf.buf[5] == 'S' && buf.buf[8] == 'U') + /* nested untracked file */ + dirty_submodule |= DIRTY_SUBMODULE_UNTRACKED; + + if (buf.buf[0] == 'u' || + buf.buf[0] == '2' || + memcmp(buf.buf + 5, "S..U", 4)) + /* other change */ + dirty_submodule |= DIRTY_SUBMODULE_MODIFIED; } - next_line = strchr(line, '\n'); - if (!next_line) + + if ((dirty_submodule & DIRTY_SUBMODULE_MODIFIED) && + ((dirty_submodule & DIRTY_SUBMODULE_UNTRACKED) || + ignore_untracked)) { + /* + * We're not interested in any further information from + * the child any more, neither output nor its exit code. + */ + ignore_cp_exit_code = 1; break; - next_line++; - len -= (next_line - line); - line = next_line; + } } - close(cp.out); + fclose(fp); - if (finish_command(&cp)) - die("'git status --porcelain' failed in submodule %s", path); + if (finish_command(&cp) && !ignore_cp_exit_code) + die(_("'git status --porcelain=2' failed in submodule %s"), path); strbuf_release(&buf); return dirty_submodule; @@ -761,15 +1728,7 @@ unsigned is_submodule_modified(const char *path, int ignore_untracked) int submodule_uses_gitfile(const char *path) { - struct child_process cp; - const char *argv[] = { - "submodule", - "foreach", - "--quiet", - "--recursive", - "test -f .git", - NULL, - }; + struct child_process cp = CHILD_PROCESS_INIT; struct strbuf buf = STRBUF_INIT; const char *git_dir; @@ -782,9 +1741,11 @@ int submodule_uses_gitfile(const char *path) strbuf_release(&buf); /* Now test that all nested submodules use a gitfile too */ - memset(&cp, 0, sizeof(cp)); - cp.argv = argv; - cp.env = local_repo_env; + strvec_pushl(&cp.args, + "submodule", "foreach", "--quiet", "--recursive", + "test -f .git", NULL); + + prepare_submodule_repo_env(&cp.env_array); cp.git_cmd = 1; cp.no_stdin = 1; cp.no_stderr = 1; @@ -796,210 +1757,530 @@ int submodule_uses_gitfile(const char *path) return 1; } -int ok_to_remove_submodule(const char *path) +/* + * Check if it is a bad idea to remove a submodule, i.e. if we'd lose data + * when doing so. + * + * Return 1 if we'd lose data, return 0 if the removal is fine, + * and negative values for errors. + */ +int bad_to_remove_submodule(const char *path, unsigned flags) { - struct stat st; ssize_t len; - struct child_process cp; - const char *argv[] = { - "status", - "--porcelain", - "-u", - "--ignore-submodules=none", - NULL, - }; + struct child_process cp = CHILD_PROCESS_INIT; struct strbuf buf = STRBUF_INIT; - int ok_to_remove = 1; + int ret = 0; - if ((lstat(path, &st) < 0) || is_empty_dir(path)) - return 1; + if (!file_exists(path) || is_empty_dir(path)) + return 0; if (!submodule_uses_gitfile(path)) - return 0; + return 1; + + strvec_pushl(&cp.args, "status", "--porcelain", + "--ignore-submodules=none", NULL); + + if (flags & SUBMODULE_REMOVAL_IGNORE_UNTRACKED) + strvec_push(&cp.args, "-uno"); + else + strvec_push(&cp.args, "-uall"); + + if (!(flags & SUBMODULE_REMOVAL_IGNORE_IGNORED_UNTRACKED)) + strvec_push(&cp.args, "--ignored"); - memset(&cp, 0, sizeof(cp)); - cp.argv = argv; - cp.env = local_repo_env; + prepare_submodule_repo_env(&cp.env_array); cp.git_cmd = 1; cp.no_stdin = 1; cp.out = -1; cp.dir = path; - if (start_command(&cp)) - die("Could not run 'git status --porcelain -uall --ignore-submodules=none' in submodule %s", path); + if (start_command(&cp)) { + if (flags & SUBMODULE_REMOVAL_DIE_ON_ERROR) + die(_("could not start 'git status' in submodule '%s'"), + path); + ret = -1; + goto out; + } len = strbuf_read(&buf, cp.out, 1024); if (len > 2) - ok_to_remove = 0; + ret = 1; close(cp.out); - if (finish_command(&cp)) - die("'git status --porcelain -uall --ignore-submodules=none' failed in submodule %s", path); - + if (finish_command(&cp)) { + if (flags & SUBMODULE_REMOVAL_DIE_ON_ERROR) + die(_("could not run 'git status' in submodule '%s'"), + path); + ret = -1; + } +out: strbuf_release(&buf); - return ok_to_remove; + return ret; } -static int find_first_merges(struct object_array *result, const char *path, - struct commit *a, struct commit *b) +void submodule_unset_core_worktree(const struct submodule *sub) { - int i, j; - struct object_array merges; - struct commit *commit; - int contains_another; - - char merged_revision[42]; - const char *rev_args[] = { "rev-list", "--merges", "--ancestry-path", - "--all", merged_revision, NULL }; - struct rev_info revs; - struct setup_revision_opt rev_opts; - - memset(&merges, 0, sizeof(merges)); - memset(result, 0, sizeof(struct object_array)); - memset(&rev_opts, 0, sizeof(rev_opts)); - - /* get all revisions that merge commit a */ - snprintf(merged_revision, sizeof(merged_revision), "^%s", - sha1_to_hex(a->object.sha1)); - init_revisions(&revs, NULL); - rev_opts.submodule = path; - setup_revisions(sizeof(rev_args)/sizeof(char *)-1, rev_args, &revs, &rev_opts); - - /* save all revisions from the above list that contain b */ - if (prepare_revision_walk(&revs)) - die("revision walk setup failed"); - while ((commit = get_revision(&revs)) != NULL) { - struct object *o = &(commit->object); - if (in_merge_bases(b, commit)) - add_object_array(o, NULL, &merges); - } - reset_revision_walk(); + char *config_path = xstrfmt("%s/modules/%s/config", + get_git_dir(), sub->name); - /* Now we've got all merges that contain a and b. Prune all - * merges that contain another found merge and save them in - * result. - */ - for (i = 0; i < merges.nr; i++) { - struct commit *m1 = (struct commit *) merges.objects[i].item; - - contains_another = 0; - for (j = 0; j < merges.nr; j++) { - struct commit *m2 = (struct commit *) merges.objects[j].item; - if (i != j && in_merge_bases(m2, m1)) { - contains_another = 1; - break; - } - } - - if (!contains_another) - add_object_array(merges.objects[i].item, - merges.objects[i].name, result); - } + if (git_config_set_in_file_gently(config_path, "core.worktree", NULL)) + warning(_("Could not unset core.worktree setting in submodule '%s'"), + sub->path); - free(merges.objects); - return result->nr; + free(config_path); } -static void print_commit(struct commit *commit) +static const char *get_super_prefix_or_empty(void) { - struct strbuf sb = STRBUF_INIT; - struct pretty_print_context ctx = {0}; - ctx.date_mode = DATE_NORMAL; - format_commit_message(commit, " %h: %m %s", &sb, &ctx); - fprintf(stderr, "%s\n", sb.buf); - strbuf_release(&sb); + const char *s = get_super_prefix(); + if (!s) + s = ""; + return s; } -#define MERGE_WARNING(path, msg) \ - warning("Failed to merge submodule %s (%s)", path, msg); +static int submodule_has_dirty_index(const struct submodule *sub) +{ + struct child_process cp = CHILD_PROCESS_INIT; -int merge_submodule(unsigned char result[20], const char *path, - const unsigned char base[20], const unsigned char a[20], - const unsigned char b[20], int search) + prepare_submodule_repo_env(&cp.env_array); + + cp.git_cmd = 1; + strvec_pushl(&cp.args, "diff-index", "--quiet", + "--cached", "HEAD", NULL); + cp.no_stdin = 1; + cp.no_stdout = 1; + cp.dir = sub->path; + if (start_command(&cp)) + die(_("could not recurse into submodule '%s'"), sub->path); + + return finish_command(&cp); +} + +static void submodule_reset_index(const char *path) { - struct commit *commit_base, *commit_a, *commit_b; - int parent_count; - struct object_array merges; + struct child_process cp = CHILD_PROCESS_INIT; + prepare_submodule_repo_env(&cp.env_array); - int i; + cp.git_cmd = 1; + cp.no_stdin = 1; + cp.dir = path; - /* store a in result in case we fail */ - hashcpy(result, a); + strvec_pushf(&cp.args, "--super-prefix=%s%s/", + get_super_prefix_or_empty(), path); + strvec_pushl(&cp.args, "read-tree", "-u", "--reset", NULL); - /* we can not handle deletion conflicts */ - if (is_null_sha1(base)) - return 0; - if (is_null_sha1(a)) - return 0; - if (is_null_sha1(b)) - return 0; + strvec_push(&cp.args, empty_tree_oid_hex()); - if (add_submodule_odb(path)) { - MERGE_WARNING(path, "not checked out"); + if (run_command(&cp)) + die(_("could not reset submodule index")); +} + +/** + * Moves a submodule at a given path from a given head to another new head. + * For edge cases (a submodule coming into existence or removing a submodule) + * pass NULL for old or new respectively. + */ +int submodule_move_head(const char *path, + const char *old_head, + const char *new_head, + unsigned flags) +{ + int ret = 0; + struct child_process cp = CHILD_PROCESS_INIT; + const struct submodule *sub; + int *error_code_ptr, error_code; + + if (!is_submodule_active(the_repository, path)) return 0; - } - if (!(commit_base = lookup_commit_reference(base)) || - !(commit_a = lookup_commit_reference(a)) || - !(commit_b = lookup_commit_reference(b))) { - MERGE_WARNING(path, "commits not present"); + if (flags & SUBMODULE_MOVE_HEAD_FORCE) + /* + * Pass non NULL pointer to is_submodule_populated_gently + * to prevent die()-ing. We'll use connect_work_tree_and_git_dir + * to fixup the submodule in the force case later. + */ + error_code_ptr = &error_code; + else + error_code_ptr = NULL; + + if (old_head && !is_submodule_populated_gently(path, error_code_ptr)) return 0; + + sub = submodule_from_path(the_repository, null_oid(), path); + + if (!sub) + BUG("could not get submodule information for '%s'", path); + + if (old_head && !(flags & SUBMODULE_MOVE_HEAD_FORCE)) { + /* Check if the submodule has a dirty index. */ + if (submodule_has_dirty_index(sub)) + return error(_("submodule '%s' has dirty index"), path); } - /* check whether both changes are forward */ - if (!in_merge_bases(commit_base, commit_a) || - !in_merge_bases(commit_base, commit_b)) { - MERGE_WARNING(path, "commits don't follow merge-base"); - return 0; + if (!(flags & SUBMODULE_MOVE_HEAD_DRY_RUN)) { + if (old_head) { + if (!submodule_uses_gitfile(path)) + absorb_git_dir_into_superproject(path, + ABSORB_GITDIR_RECURSE_SUBMODULES); + } else { + char *gitdir = xstrfmt("%s/modules/%s", + get_git_dir(), sub->name); + connect_work_tree_and_git_dir(path, gitdir, 0); + free(gitdir); + + /* make sure the index is clean as well */ + submodule_reset_index(path); + } + + if (old_head && (flags & SUBMODULE_MOVE_HEAD_FORCE)) { + char *gitdir = xstrfmt("%s/modules/%s", + get_git_dir(), sub->name); + connect_work_tree_and_git_dir(path, gitdir, 1); + free(gitdir); + } } - /* Case #1: a is contained in b or vice versa */ - if (in_merge_bases(commit_a, commit_b)) { - hashcpy(result, b); - return 1; + prepare_submodule_repo_env(&cp.env_array); + + cp.git_cmd = 1; + cp.no_stdin = 1; + cp.dir = path; + + strvec_pushf(&cp.args, "--super-prefix=%s%s/", + get_super_prefix_or_empty(), path); + strvec_pushl(&cp.args, "read-tree", "--recurse-submodules", NULL); + + if (flags & SUBMODULE_MOVE_HEAD_DRY_RUN) + strvec_push(&cp.args, "-n"); + else + strvec_push(&cp.args, "-u"); + + if (flags & SUBMODULE_MOVE_HEAD_FORCE) + strvec_push(&cp.args, "--reset"); + else + strvec_push(&cp.args, "-m"); + + if (!(flags & SUBMODULE_MOVE_HEAD_FORCE)) + strvec_push(&cp.args, old_head ? old_head : empty_tree_oid_hex()); + + strvec_push(&cp.args, new_head ? new_head : empty_tree_oid_hex()); + + if (run_command(&cp)) { + ret = error(_("Submodule '%s' could not be updated."), path); + goto out; } - if (in_merge_bases(commit_b, commit_a)) { - hashcpy(result, a); - return 1; + + if (!(flags & SUBMODULE_MOVE_HEAD_DRY_RUN)) { + if (new_head) { + child_process_init(&cp); + /* also set the HEAD accordingly */ + cp.git_cmd = 1; + cp.no_stdin = 1; + cp.dir = path; + + prepare_submodule_repo_env(&cp.env_array); + strvec_pushl(&cp.args, "update-ref", "HEAD", + "--no-deref", new_head, NULL); + + if (run_command(&cp)) { + ret = -1; + goto out; + } + } else { + struct strbuf sb = STRBUF_INIT; + + strbuf_addf(&sb, "%s/.git", path); + unlink_or_warn(sb.buf); + strbuf_release(&sb); + + if (is_empty_dir(path)) + rmdir_or_warn(path); + + submodule_unset_core_worktree(sub); + } } +out: + return ret; +} + +int validate_submodule_git_dir(char *git_dir, const char *submodule_name) +{ + size_t len = strlen(git_dir), suffix_len = strlen(submodule_name); + char *p; + int ret = 0; + + if (len <= suffix_len || (p = git_dir + len - suffix_len)[-1] != '/' || + strcmp(p, submodule_name)) + BUG("submodule name '%s' not a suffix of git dir '%s'", + submodule_name, git_dir); /* - * Case #2: There are one or more merges that contain a and b in - * the submodule. If there is only one, then present it as a - * suggestion to the user, but leave it marked unmerged so the - * user needs to confirm the resolution. + * We prevent the contents of sibling submodules' git directories to + * clash. + * + * Example: having a submodule named `hippo` and another one named + * `hippo/hooks` would result in the git directories + * `.git/modules/hippo/` and `.git/modules/hippo/hooks/`, respectively, + * but the latter directory is already designated to contain the hooks + * of the former. */ + for (; *p; p++) { + if (is_dir_sep(*p)) { + char c = *p; + + *p = '\0'; + if (is_git_directory(git_dir)) + ret = -1; + *p = c; + + if (ret < 0) + return error(_("submodule git dir '%s' is " + "inside git dir '%.*s'"), + git_dir, + (int)(p - git_dir), git_dir); + } + } + + return 0; +} + +/* + * Embeds a single submodules git directory into the superprojects git dir, + * non recursively. + */ +static void relocate_single_git_dir_into_superproject(const char *path) +{ + char *old_git_dir = NULL, *real_old_git_dir = NULL, *real_new_git_dir = NULL; + char *new_git_dir; + const struct submodule *sub; + + if (submodule_uses_worktrees(path)) + die(_("relocate_gitdir for submodule '%s' with " + "more than one worktree not supported"), path); + + old_git_dir = xstrfmt("%s/.git", path); + if (read_gitfile(old_git_dir)) + /* If it is an actual gitfile, it doesn't need migration. */ + return; + + real_old_git_dir = real_pathdup(old_git_dir, 1); + + sub = submodule_from_path(the_repository, null_oid(), path); + if (!sub) + die(_("could not lookup name for submodule '%s'"), path); + + new_git_dir = git_pathdup("modules/%s", sub->name); + if (validate_submodule_git_dir(new_git_dir, sub->name) < 0) + die(_("refusing to move '%s' into an existing git dir"), + real_old_git_dir); + if (safe_create_leading_directories_const(new_git_dir) < 0) + die(_("could not create directory '%s'"), new_git_dir); + real_new_git_dir = real_pathdup(new_git_dir, 1); + free(new_git_dir); + + fprintf(stderr, _("Migrating git directory of '%s%s' from\n'%s' to\n'%s'\n"), + get_super_prefix_or_empty(), path, + real_old_git_dir, real_new_git_dir); - /* Skip the search if makes no sense to the calling context. */ - if (!search) + relocate_gitdir(path, real_old_git_dir, real_new_git_dir); + + free(old_git_dir); + free(real_old_git_dir); + free(real_new_git_dir); +} + +/* + * Migrate the git directory of the submodule given by path from + * having its git directory within the working tree to the git dir nested + * in its superprojects git dir under modules/. + */ +void absorb_git_dir_into_superproject(const char *path, + unsigned flags) +{ + int err_code; + const char *sub_git_dir; + struct strbuf gitdir = STRBUF_INIT; + strbuf_addf(&gitdir, "%s/.git", path); + sub_git_dir = resolve_gitdir_gently(gitdir.buf, &err_code); + + /* Not populated? */ + if (!sub_git_dir) { + const struct submodule *sub; + + if (err_code == READ_GITFILE_ERR_STAT_FAILED) { + /* unpopulated as expected */ + strbuf_release(&gitdir); + return; + } + + if (err_code != READ_GITFILE_ERR_NOT_A_REPO) + /* We don't know what broke here. */ + read_gitfile_error_die(err_code, path, NULL); + + /* + * Maybe populated, but no git directory was found? + * This can happen if the superproject is a submodule + * itself and was just absorbed. The absorption of the + * superproject did not rewrite the git file links yet, + * fix it now. + */ + sub = submodule_from_path(the_repository, null_oid(), path); + if (!sub) + die(_("could not lookup name for submodule '%s'"), path); + connect_work_tree_and_git_dir(path, + git_path("modules/%s", sub->name), 0); + } else { + /* Is it already absorbed into the superprojects git dir? */ + char *real_sub_git_dir = real_pathdup(sub_git_dir, 1); + char *real_common_git_dir = real_pathdup(get_git_common_dir(), 1); + + if (!starts_with(real_sub_git_dir, real_common_git_dir)) + relocate_single_git_dir_into_superproject(path); + + free(real_sub_git_dir); + free(real_common_git_dir); + } + strbuf_release(&gitdir); + + if (flags & ABSORB_GITDIR_RECURSE_SUBMODULES) { + struct child_process cp = CHILD_PROCESS_INIT; + struct strbuf sb = STRBUF_INIT; + + if (flags & ~ABSORB_GITDIR_RECURSE_SUBMODULES) + BUG("we don't know how to pass the flags down?"); + + strbuf_addstr(&sb, get_super_prefix_or_empty()); + strbuf_addstr(&sb, path); + strbuf_addch(&sb, '/'); + + cp.dir = path; + cp.git_cmd = 1; + cp.no_stdin = 1; + strvec_pushl(&cp.args, "--super-prefix", sb.buf, + "submodule--helper", + "absorb-git-dirs", NULL); + prepare_submodule_repo_env(&cp.env_array); + if (run_command(&cp)) + die(_("could not recurse into submodule '%s'"), path); + + strbuf_release(&sb); + } +} + +int get_superproject_working_tree(struct strbuf *buf) +{ + struct child_process cp = CHILD_PROCESS_INIT; + struct strbuf sb = STRBUF_INIT; + struct strbuf one_up = STRBUF_INIT; + const char *cwd = xgetcwd(); + int ret = 0; + const char *subpath; + int code; + ssize_t len; + + if (!is_inside_work_tree()) + /* + * FIXME: + * We might have a superproject, but it is harder + * to determine. + */ return 0; - /* find commit which merges them */ - parent_count = find_first_merges(&merges, path, commit_a, commit_b); - switch (parent_count) { - case 0: - MERGE_WARNING(path, "merge following commits not found"); - break; - - case 1: - MERGE_WARNING(path, "not fast-forward"); - fprintf(stderr, "Found a possible merge resolution " - "for the submodule:\n"); - print_commit((struct commit *) merges.objects[0].item); - fprintf(stderr, - "If this is correct simply add it to the index " - "for example\n" - "by using:\n\n" - " git update-index --cacheinfo 160000 %s \"%s\"\n\n" - "which will accept this suggestion.\n", - sha1_to_hex(merges.objects[0].item->sha1), path); - break; + if (!strbuf_realpath(&one_up, "../", 0)) + return 0; - default: - MERGE_WARNING(path, "multiple merges found"); - for (i = 0; i < merges.nr; i++) - print_commit((struct commit *) merges.objects[i].item); + subpath = relative_path(cwd, one_up.buf, &sb); + strbuf_release(&one_up); + + prepare_submodule_repo_env(&cp.env_array); + strvec_pop(&cp.env_array); + + strvec_pushl(&cp.args, "--literal-pathspecs", "-C", "..", + "ls-files", "-z", "--stage", "--full-name", "--", + subpath, NULL); + strbuf_reset(&sb); + + cp.no_stdin = 1; + cp.no_stderr = 1; + cp.out = -1; + cp.git_cmd = 1; + + if (start_command(&cp)) + die(_("could not start ls-files in ..")); + + len = strbuf_read(&sb, cp.out, PATH_MAX); + close(cp.out); + + if (starts_with(sb.buf, "160000")) { + int super_sub_len; + int cwd_len = strlen(cwd); + char *super_sub, *super_wt; + + /* + * There is a superproject having this repo as a submodule. + * The format is <mode> SP <hash> SP <stage> TAB <full name> \0, + * We're only interested in the name after the tab. + */ + super_sub = strchr(sb.buf, '\t') + 1; + super_sub_len = strlen(super_sub); + + if (super_sub_len > cwd_len || + strcmp(&cwd[cwd_len - super_sub_len], super_sub)) + BUG("returned path string doesn't match cwd?"); + + super_wt = xstrdup(cwd); + super_wt[cwd_len - super_sub_len] = '\0'; + + strbuf_realpath(buf, super_wt, 1); + ret = 1; + free(super_wt); + } + strbuf_release(&sb); + + code = finish_command(&cp); + + if (code == 128) + /* '../' is not a git repository */ + return 0; + if (code == 0 && len == 0) + /* There is an unrelated git repository at '../' */ + return 0; + if (code) + die(_("ls-tree returned unexpected return code %d"), code); + + return ret; +} + +/* + * Put the gitdir for a submodule (given relative to the main + * repository worktree) into `buf`, or return -1 on error. + */ +int submodule_to_gitdir(struct strbuf *buf, const char *submodule) +{ + const struct submodule *sub; + const char *git_dir; + int ret = 0; + + strbuf_reset(buf); + strbuf_addstr(buf, submodule); + strbuf_complete(buf, '/'); + strbuf_addstr(buf, ".git"); + + git_dir = read_gitfile(buf->buf); + if (git_dir) { + strbuf_reset(buf); + strbuf_addstr(buf, git_dir); + } + if (!is_git_directory(buf->buf)) { + sub = submodule_from_path(the_repository, null_oid(), + submodule); + if (!sub) { + ret = -1; + goto cleanup; + } + strbuf_reset(buf); + strbuf_git_path(buf, "%s/%s", "modules", sub->name); } - free(merges.objects); - return 0; +cleanup: + return ret; } |