diff options
Diffstat (limited to 'dir.c')
| -rw-r--r-- | dir.c | 1108 |
1 files changed, 832 insertions, 276 deletions
@@ -2,8 +2,6 @@ * This handles recursive filename detection with exclude * files, index knowledge etc.. * - * See Documentation/technical/api-directory-listing.txt - * * Copyright (C) Linus Torvalds, 2005-2006 * Junio Hamano, 2005-2006 */ @@ -43,7 +41,8 @@ struct cached_dir { int nr_files; int nr_dirs; - struct dirent *de; + const char *d_name; + int d_type; const char *file; struct untracked_cache_dir *ucd; }; @@ -52,8 +51,18 @@ static enum path_treatment read_directory_recursive(struct dir_struct *dir, struct index_state *istate, const char *path, int len, struct untracked_cache_dir *untracked, int check_only, int stop_at_first_file, const struct pathspec *pathspec); -static int get_dtype(struct dirent *de, struct index_state *istate, - const char *path, int len); +static int resolve_dtype(int dtype, struct index_state *istate, + const char *path, int len); +struct dirent *readdir_skip_dot_and_dotdot(DIR *dirp) +{ + struct dirent *e; + + while ((e = readdir(dirp)) != NULL) { + if (!is_dot_or_dotdot(e->d_name)) + break; + } + return e; +} int count_slashes(const char *s) { @@ -69,11 +78,21 @@ int fspathcmp(const char *a, const char *b) return ignore_case ? strcasecmp(a, b) : strcmp(a, b); } +int fspatheq(const char *a, const char *b) +{ + return !fspathcmp(a, b); +} + int fspathncmp(const char *a, const char *b, size_t count) { return ignore_case ? strncasecmp(a, b, count) : strncmp(a, b, count); } +unsigned int fspathhash(const char *str) +{ + return ignore_case ? strihash(str) : strhash(str); +} + int git_fnmatch(const struct pathspec_item *item, const char *pattern, const char *string, int prefix) @@ -194,6 +213,10 @@ int fill_directory(struct dir_struct *dir, const char *prefix; size_t prefix_len; + unsigned exclusive_flags = DIR_SHOW_IGNORED | DIR_SHOW_IGNORED_TOO; + if ((dir->flags & exclusive_flags) == exclusive_flags) + BUG("DIR_SHOW_IGNORED and DIR_SHOW_IGNORED_TOO are exclusive"); + /* * Calculate common prefix for the pathspec, and * use that to optimize the directory walk @@ -298,7 +321,7 @@ static int do_read_blob(const struct object_id *oid, struct oid_stat *oid_stat, * [1] Only if DO_MATCH_DIRECTORY is passed; otherwise, this is NOT a match. * [2] Only if DO_MATCH_LEADING_PATHSPEC is passed; otherwise, not a match. */ -static int match_pathspec_item(const struct index_state *istate, +static int match_pathspec_item(struct index_state *istate, const struct pathspec_item *item, int prefix, const char *name, int namelen, unsigned flags) { @@ -365,7 +388,8 @@ static int match_pathspec_item(const struct index_state *istate, return MATCHED_FNMATCH; /* Perform checks to see if "name" is a leading string of the pathspec */ - if (flags & DO_MATCH_LEADING_PATHSPEC) { + if ( (flags & DO_MATCH_LEADING_PATHSPEC) && + !(flags & DO_MATCH_EXCLUDE)) { /* name is a literal prefix of the pathspec */ int offset = name[namelen-1] == '/' ? 1 : 0; if ((namelen < matchlen) && @@ -373,13 +397,20 @@ static int match_pathspec_item(const struct index_state *istate, !ps_strncmp(item, match, name, namelen)) return MATCHED_RECURSIVELY_LEADING_PATHSPEC; - /* name" doesn't match up to the first wild character */ + /* name doesn't match up to the first wild character */ if (item->nowildcard_len < item->len && ps_strncmp(item, match, name, item->nowildcard_len - prefix)) return 0; /* + * name has no wildcard, and it didn't match as a leading + * pathspec so return. + */ + if (item->nowildcard_len == item->len) + return 0; + + /* * Here is where we would perform a wildmatch to check if * "name" can be matched as a directory (or a prefix) against * the pathspec. Since wildmatch doesn't have this capability @@ -395,6 +426,10 @@ static int match_pathspec_item(const struct index_state *istate, } /* + * do_match_pathspec() is meant to ONLY be called by + * match_pathspec_with_flags(); calling it directly risks pathspecs + * like ':!unwanted_path' being ignored. + * * Given a name and a list of pathspecs, returns the nature of the * closest (i.e. most specific) match of the name to any of the * pathspecs. @@ -409,7 +444,7 @@ static int match_pathspec_item(const struct index_state *istate, * pathspec did not match any names, which could indicate that the * user mistyped the nth pathspec. */ -static int do_match_pathspec(const struct index_state *istate, +static int do_match_pathspec(struct index_state *istate, const struct pathspec *ps, const char *name, int namelen, int prefix, char *seen, @@ -480,13 +515,12 @@ static int do_match_pathspec(const struct index_state *istate, return retval; } -int match_pathspec(const struct index_state *istate, - const struct pathspec *ps, - const char *name, int namelen, - int prefix, char *seen, int is_dir) +static int match_pathspec_with_flags(struct index_state *istate, + const struct pathspec *ps, + const char *name, int namelen, + int prefix, char *seen, unsigned flags) { int positive, negative; - unsigned flags = is_dir ? DO_MATCH_DIRECTORY : 0; positive = do_match_pathspec(istate, ps, name, namelen, prefix, seen, flags); if (!(ps->magic & PATHSPEC_EXCLUDE) || !positive) @@ -497,19 +531,29 @@ int match_pathspec(const struct index_state *istate, return negative ? 0 : positive; } +int match_pathspec(struct index_state *istate, + const struct pathspec *ps, + const char *name, int namelen, + int prefix, char *seen, int is_dir) +{ + unsigned flags = is_dir ? DO_MATCH_DIRECTORY : 0; + return match_pathspec_with_flags(istate, ps, name, namelen, + prefix, seen, flags); +} + /** * Check if a submodule is a superset of the pathspec */ -int submodule_path_match(const struct index_state *istate, +int submodule_path_match(struct index_state *istate, const struct pathspec *ps, const char *submodule_name, char *seen) { - int matched = do_match_pathspec(istate, ps, submodule_name, - strlen(submodule_name), - 0, seen, - DO_MATCH_DIRECTORY | - DO_MATCH_LEADING_PATHSPEC); + int matched = match_pathspec_with_flags(istate, ps, submodule_name, + strlen(submodule_name), + 0, seen, + DO_MATCH_DIRECTORY | + DO_MATCH_LEADING_PATHSPEC); return matched; } @@ -611,6 +655,223 @@ void parse_path_pattern(const char **pattern, *patternlen = len; } +int pl_hashmap_cmp(const void *unused_cmp_data, + const struct hashmap_entry *a, + const struct hashmap_entry *b, + const void *key) +{ + const struct pattern_entry *ee1 = + container_of(a, struct pattern_entry, ent); + const struct pattern_entry *ee2 = + container_of(b, struct pattern_entry, ent); + + size_t min_len = ee1->patternlen <= ee2->patternlen + ? ee1->patternlen + : ee2->patternlen; + + if (ignore_case) + return strncasecmp(ee1->pattern, ee2->pattern, min_len); + return strncmp(ee1->pattern, ee2->pattern, min_len); +} + +static char *dup_and_filter_pattern(const char *pattern) +{ + char *set, *read; + size_t count = 0; + char *result = xstrdup(pattern); + + set = result; + read = result; + + while (*read) { + /* skip escape characters (once) */ + if (*read == '\\') + read++; + + *set = *read; + + set++; + read++; + count++; + } + *set = 0; + + if (count > 2 && + *(set - 1) == '*' && + *(set - 2) == '/') + *(set - 2) = 0; + + return result; +} + +static void add_pattern_to_hashsets(struct pattern_list *pl, struct path_pattern *given) +{ + struct pattern_entry *translated; + char *truncated; + char *data = NULL; + const char *prev, *cur, *next; + + if (!pl->use_cone_patterns) + return; + + if (given->flags & PATTERN_FLAG_NEGATIVE && + given->flags & PATTERN_FLAG_MUSTBEDIR && + !strcmp(given->pattern, "/*")) { + pl->full_cone = 0; + return; + } + + if (!given->flags && !strcmp(given->pattern, "/*")) { + pl->full_cone = 1; + return; + } + + if (given->patternlen < 2 || + *given->pattern == '*' || + strstr(given->pattern, "**")) { + /* Not a cone pattern. */ + warning(_("unrecognized pattern: '%s'"), given->pattern); + goto clear_hashmaps; + } + + prev = given->pattern; + cur = given->pattern + 1; + next = given->pattern + 2; + + while (*cur) { + /* Watch for glob characters '*', '\', '[', '?' */ + if (!is_glob_special(*cur)) + goto increment; + + /* But only if *prev != '\\' */ + if (*prev == '\\') + goto increment; + + /* But allow the initial '\' */ + if (*cur == '\\' && + is_glob_special(*next)) + goto increment; + + /* But a trailing '/' then '*' is fine */ + if (*prev == '/' && + *cur == '*' && + *next == 0) + goto increment; + + /* Not a cone pattern. */ + warning(_("unrecognized pattern: '%s'"), given->pattern); + goto clear_hashmaps; + + increment: + prev++; + cur++; + next++; + } + + if (given->patternlen > 2 && + !strcmp(given->pattern + given->patternlen - 2, "/*")) { + if (!(given->flags & PATTERN_FLAG_NEGATIVE)) { + /* Not a cone pattern. */ + warning(_("unrecognized pattern: '%s'"), given->pattern); + goto clear_hashmaps; + } + + truncated = dup_and_filter_pattern(given->pattern); + + translated = xmalloc(sizeof(struct pattern_entry)); + translated->pattern = truncated; + translated->patternlen = given->patternlen - 2; + hashmap_entry_init(&translated->ent, + fspathhash(translated->pattern)); + + if (!hashmap_get_entry(&pl->recursive_hashmap, + translated, ent, NULL)) { + /* We did not see the "parent" included */ + warning(_("unrecognized negative pattern: '%s'"), + given->pattern); + free(truncated); + free(translated); + goto clear_hashmaps; + } + + hashmap_add(&pl->parent_hashmap, &translated->ent); + hashmap_remove(&pl->recursive_hashmap, &translated->ent, &data); + free(data); + return; + } + + if (given->flags & PATTERN_FLAG_NEGATIVE) { + warning(_("unrecognized negative pattern: '%s'"), + given->pattern); + goto clear_hashmaps; + } + + translated = xmalloc(sizeof(struct pattern_entry)); + + translated->pattern = dup_and_filter_pattern(given->pattern); + translated->patternlen = given->patternlen; + hashmap_entry_init(&translated->ent, + fspathhash(translated->pattern)); + + hashmap_add(&pl->recursive_hashmap, &translated->ent); + + if (hashmap_get_entry(&pl->parent_hashmap, translated, ent, NULL)) { + /* we already included this at the parent level */ + warning(_("your sparse-checkout file may have issues: pattern '%s' is repeated"), + given->pattern); + hashmap_remove(&pl->parent_hashmap, &translated->ent, &data); + free(data); + free(translated); + } + + return; + +clear_hashmaps: + warning(_("disabling cone pattern matching")); + hashmap_clear_and_free(&pl->parent_hashmap, struct pattern_entry, ent); + hashmap_clear_and_free(&pl->recursive_hashmap, struct pattern_entry, ent); + pl->use_cone_patterns = 0; +} + +static int hashmap_contains_path(struct hashmap *map, + struct strbuf *pattern) +{ + struct pattern_entry p; + + /* Check straight mapping */ + p.pattern = pattern->buf; + p.patternlen = pattern->len; + hashmap_entry_init(&p.ent, fspathhash(p.pattern)); + return !!hashmap_get_entry(map, &p, ent, NULL); +} + +int hashmap_contains_parent(struct hashmap *map, + const char *path, + struct strbuf *buffer) +{ + char *slash_pos; + + strbuf_setlen(buffer, 0); + + if (path[0] != '/') + strbuf_addch(buffer, '/'); + + strbuf_addstr(buffer, path); + + slash_pos = strrchr(buffer->buf, '/'); + + while (slash_pos > buffer->buf) { + strbuf_setlen(buffer, slash_pos - buffer->buf); + + if (hashmap_contains_path(map, buffer)) + return 1; + + slash_pos = strrchr(buffer->buf, '/'); + } + + return 0; +} + void add_pattern(const char *string, const char *base, int baselen, struct pattern_list *pl, int srcpos) { @@ -635,9 +896,11 @@ void add_pattern(const char *string, const char *base, ALLOC_GROW(pl->patterns, pl->nr + 1, pl->alloc); pl->patterns[pl->nr++] = pattern; pattern->pl = pl; + + add_pattern_to_hashsets(pl, pattern); } -static int read_skip_worktree_file_from_index(const struct index_state *istate, +static int read_skip_worktree_file_from_index(struct index_state *istate, const char *path, size_t *size_out, char **data_out, struct oid_stat *oid_stat) @@ -666,6 +929,8 @@ void clear_pattern_list(struct pattern_list *pl) free(pl->patterns[i]); free(pl->patterns); free(pl->filebuf); + hashmap_clear_and_free(&pl->recursive_hashmap, struct pattern_entry, ent); + hashmap_clear_and_free(&pl->parent_hashmap, struct pattern_entry, ent); memset(pl, 0, sizeof(*pl)); } @@ -778,18 +1043,21 @@ static int add_patterns_from_buffer(char *buf, size_t size, const char *base, int baselen, struct pattern_list *pl); +/* Flags for add_patterns() */ +#define PATTERN_NOFOLLOW (1<<0) + /* * Given a file with name "fname", read it (either from disk, or from * an index if 'istate' is non-null), parse it and store the * exclude rules in "pl". * - * If "ss" is not NULL, compute SHA-1 of the exclude file and fill + * If "oid_stat" is not NULL, compute oid of the exclude file and fill * stat data from disk (only valid if add_patterns returns zero). If - * ss_valid is non-zero, "ss" must contain good value as input. + * oid_stat.valid is non-zero, "oid_stat" must contain good value as input. */ static int add_patterns(const char *fname, const char *base, int baselen, struct pattern_list *pl, struct index_state *istate, - struct oid_stat *oid_stat) + unsigned flags, struct oid_stat *oid_stat) { struct stat st; int r; @@ -797,7 +1065,11 @@ static int add_patterns(const char *fname, const char *base, int baselen, size_t size = 0; char *buf; - fd = open(fname, O_RDONLY); + if (flags & PATTERN_NOFOLLOW) + fd = open_nofollow(fname, O_RDONLY); + else + fd = open(fname, O_RDONLY); + if (fd < 0 || fstat(fd, &st) < 0) { if (fd < 0) warn_on_fopen_errors(fname); @@ -833,7 +1105,7 @@ static int add_patterns(const char *fname, const char *base, int baselen, int pos; if (oid_stat->valid && !match_stat_data_racy(istate, &oid_stat->stat, &st)) - ; /* no content change, ss->sha1 still good */ + ; /* no content change, oid_stat->oid still good */ else if (istate && (pos = index_name_pos(istate, fname, strlen(fname))) >= 0 && !ce_stage(istate->cache[pos]) && @@ -842,8 +1114,8 @@ static int add_patterns(const char *fname, const char *base, int baselen, oidcpy(&oid_stat->oid, &istate->cache[pos]->oid); else - hash_object_file(buf, size, "blob", - &oid_stat->oid); + hash_object_file(the_hash_algo, buf, size, + "blob", &oid_stat->oid); fill_stat_data(&oid_stat->stat, &st); oid_stat->valid = 1; } @@ -860,6 +1132,9 @@ static int add_patterns_from_buffer(char *buf, size_t size, int i, lineno = 1; char *entry; + hashmap_init(&pl->recursive_hashmap, pl_hashmap_cmp, NULL, 0); + hashmap_init(&pl->parent_hashmap, pl_hashmap_cmp, NULL, 0); + pl->filebuf = buf; if (skip_utf8_bom(&buf, size)) @@ -883,9 +1158,10 @@ static int add_patterns_from_buffer(char *buf, size_t size, int add_patterns_from_file_to_list(const char *fname, const char *base, int baselen, struct pattern_list *pl, - struct index_state *istate) + struct index_state *istate, + unsigned flags) { - return add_patterns(fname, base, baselen, pl, istate, NULL); + return add_patterns(fname, base, baselen, pl, istate, flags, NULL); } int add_patterns_from_blob_to_list( @@ -934,7 +1210,7 @@ static void add_patterns_from_file_1(struct dir_struct *dir, const char *fname, if (!dir->untracked) dir->unmanaged_exclude_files++; pl = add_pattern_list(dir, EXC_FILE, fname); - if (add_patterns(fname, "", 0, pl, NULL, oid_stat) < 0) + if (add_patterns(fname, "", 0, pl, NULL, 0, oid_stat) < 0) die(_("cannot use %s as an exclude file"), fname); } @@ -1052,8 +1328,7 @@ static struct path_pattern *last_matching_pattern_from_list(const char *pathname int prefix = pattern->nowildcardlen; if (pattern->flags & PATTERN_FLAG_MUSTBEDIR) { - if (*dtype == DT_UNKNOWN) - *dtype = get_dtype(NULL, istate, pathname, pathlen); + *dtype = resolve_dtype(*dtype, istate, pathname, pathlen); if (*dtype != DT_DIR) continue; } @@ -1096,16 +1371,72 @@ enum pattern_match_result path_matches_pattern_list( struct index_state *istate) { struct path_pattern *pattern; - pattern = last_matching_pattern_from_list(pathname, pathlen, basename, - dtype, pl, istate); - if (pattern) { - if (pattern->flags & PATTERN_FLAG_NEGATIVE) - return NOT_MATCHED; - else - return MATCHED; + struct strbuf parent_pathname = STRBUF_INIT; + int result = NOT_MATCHED; + size_t slash_pos; + + if (!pl->use_cone_patterns) { + pattern = last_matching_pattern_from_list(pathname, pathlen, basename, + dtype, pl, istate); + if (pattern) { + if (pattern->flags & PATTERN_FLAG_NEGATIVE) + return NOT_MATCHED; + else + return MATCHED; + } + + return UNDECIDED; } - return UNDECIDED; + if (pl->full_cone) + return MATCHED; + + strbuf_addch(&parent_pathname, '/'); + strbuf_add(&parent_pathname, pathname, pathlen); + + /* + * Directory entries are matched if and only if a file + * contained immediately within them is matched. For the + * case of a directory entry, modify the path to create + * a fake filename within this directory, allowing us to + * use the file-base matching logic in an equivalent way. + */ + if (parent_pathname.len > 0 && + parent_pathname.buf[parent_pathname.len - 1] == '/') { + slash_pos = parent_pathname.len - 1; + strbuf_add(&parent_pathname, "-", 1); + } else { + const char *slash_ptr = strrchr(parent_pathname.buf, '/'); + slash_pos = slash_ptr ? slash_ptr - parent_pathname.buf : 0; + } + + if (hashmap_contains_path(&pl->recursive_hashmap, + &parent_pathname)) { + result = MATCHED_RECURSIVE; + goto done; + } + + if (!slash_pos) { + /* include every file in root */ + result = MATCHED; + goto done; + } + + strbuf_setlen(&parent_pathname, slash_pos); + + if (hashmap_contains_path(&pl->parent_hashmap, &parent_pathname)) { + result = MATCHED; + goto done; + } + + if (hashmap_contains_parent(&pl->recursive_hashmap, + pathname, + &parent_pathname)) + result = MATCHED_RECURSIVE; + +done: + strbuf_release(&parent_pathname); + return result; } static struct path_pattern *last_matching_pattern_from_lists( @@ -1187,7 +1518,7 @@ static void prep_exclude(struct dir_struct *dir, const char *cp; struct oid_stat oid_stat; - stk = xcalloc(1, sizeof(*stk)); + CALLOC_ARRAY(stk, 1); if (current < 0) { cp = base; current = 0; @@ -1257,6 +1588,7 @@ static void prep_exclude(struct dir_struct *dir, strbuf_addstr(&sb, dir->exclude_per_dir); pl->src = strbuf_detach(&sb, NULL); add_patterns(pl->src, pl->src, stk->baselen, pl, istate, + PATTERN_NOFOLLOW, untracked ? &oid_stat : NULL); } /* @@ -1439,45 +1771,76 @@ static enum exist_status directory_exists_in_index(struct index_state *istate, * Case 3: if we didn't have it in the index previously, we * have a few sub-cases: * - * (a) if "show_other_directories" is true, we show it as - * just a directory, unless "hide_empty_directories" is + * (a) if DIR_SHOW_OTHER_DIRECTORIES flag is set, we show it as + * just a directory, unless DIR_HIDE_EMPTY_DIRECTORIES is * also true, in which case we need to check if it contains any * untracked and / or ignored files. - * (b) if it looks like a git directory, and we don't have - * 'no_gitlinks' set we treat it as a gitlink, and show it - * as a directory. + * (b) if it looks like a git directory and we don't have the + * DIR_NO_GITLINKS flag, then we treat it as a gitlink, and + * show it as a directory. * (c) otherwise, we recurse into it. */ static enum path_treatment treat_directory(struct dir_struct *dir, struct index_state *istate, struct untracked_cache_dir *untracked, - const char *dirname, int len, int baselen, int exclude, + const char *dirname, int len, int baselen, int excluded, const struct pathspec *pathspec) { + /* + * WARNING: From this function, you can return path_recurse or you + * can call read_directory_recursive() (or neither), but + * you CAN'T DO BOTH. + */ + enum path_treatment state; + int matches_how = 0; + int nested_repo = 0, check_only, stop_early; + int old_ignored_nr, old_untracked_nr; /* The "len-1" is to strip the final '/' */ - switch (directory_exists_in_index(istate, dirname, len-1)) { - case index_directory: - return path_recurse; + enum exist_status status = directory_exists_in_index(istate, dirname, len-1); - case index_gitdir: + if (status == index_directory) + return path_recurse; + if (status == index_gitdir) return path_none; + if (status != index_nonexistent) + BUG("Unhandled value for directory_exists_in_index: %d\n", status); - case index_nonexistent: - if (dir->flags & DIR_SKIP_NESTED_GIT) { - int nested_repo; - struct strbuf sb = STRBUF_INIT; - strbuf_addstr(&sb, dirname); - nested_repo = is_nonbare_repository_dir(&sb); - strbuf_release(&sb); - if (nested_repo) - return path_none; - } + /* + * We don't want to descend into paths that don't match the necessary + * patterns. Clearly, if we don't have a pathspec, then we can't check + * for matching patterns. Also, if (excluded) then we know we matched + * the exclusion patterns so as an optimization we can skip checking + * for matching patterns. + */ + if (pathspec && !excluded) { + matches_how = match_pathspec_with_flags(istate, pathspec, + dirname, len, + 0 /* prefix */, + NULL /* seen */, + DO_MATCH_LEADING_PATHSPEC); + if (!matches_how) + return path_none; + } - if (dir->flags & DIR_SHOW_OTHER_DIRECTORIES) - break; - if (exclude && - (dir->flags & DIR_SHOW_IGNORED_TOO) && - (dir->flags & DIR_SHOW_IGNORED_TOO_MODE_MATCHING)) { + + if ((dir->flags & DIR_SKIP_NESTED_GIT) || + !(dir->flags & DIR_NO_GITLINKS)) { + struct strbuf sb = STRBUF_INIT; + strbuf_addstr(&sb, dirname); + nested_repo = is_nonbare_repository_dir(&sb); + strbuf_release(&sb); + } + if (nested_repo) { + if ((dir->flags & DIR_SKIP_NESTED_GIT) || + (matches_how == MATCHED_RECURSIVELY_LEADING_PATHSPEC)) + return path_none; + return excluded ? path_excluded : path_untracked; + } + + if (!(dir->flags & DIR_SHOW_OTHER_DIRECTORIES)) { + if (excluded && + (dir->flags & DIR_SHOW_IGNORED_TOO) && + (dir->flags & DIR_SHOW_IGNORED_TOO_MODE_MATCHING)) { /* * This is an excluded directory and we are @@ -1499,30 +1862,155 @@ static enum path_treatment treat_directory(struct dir_struct *dir, return path_none; } - if (!(dir->flags & DIR_NO_GITLINKS)) { - struct strbuf sb = STRBUF_INIT; - strbuf_addstr(&sb, dirname); - if (is_nonbare_repository_dir(&sb)) - return exclude ? path_excluded : path_untracked; - strbuf_release(&sb); - } return path_recurse; } - /* This is the "show_other_directories" case */ + assert(dir->flags & DIR_SHOW_OTHER_DIRECTORIES); - if (!(dir->flags & DIR_HIDE_EMPTY_DIRECTORIES)) - return exclude ? path_excluded : path_untracked; + /* + * If we have a pathspec which could match something _below_ this + * directory (e.g. when checking 'subdir/' having a pathspec like + * 'subdir/some/deep/path/file' or 'subdir/widget-*.c'), then we + * need to recurse. + */ + if (matches_how == MATCHED_RECURSIVELY_LEADING_PATHSPEC) + return path_recurse; + /* Special cases for where this directory is excluded/ignored */ + if (excluded) { + /* + * If DIR_SHOW_OTHER_DIRECTORIES is set and we're not + * hiding empty directories, there is no need to + * recurse into an ignored directory. + */ + if (!(dir->flags & DIR_HIDE_EMPTY_DIRECTORIES)) + return path_excluded; + + /* + * Even if we are hiding empty directories, we can still avoid + * recursing into ignored directories for DIR_SHOW_IGNORED_TOO + * if DIR_SHOW_IGNORED_TOO_MODE_MATCHING is also set. + */ + if ((dir->flags & DIR_SHOW_IGNORED_TOO) && + (dir->flags & DIR_SHOW_IGNORED_TOO_MODE_MATCHING)) + return path_excluded; + } + + /* + * Other than the path_recurse case above, we only need to + * recurse into untracked directories if any of the following + * bits is set: + * - DIR_SHOW_IGNORED (because then we need to determine if + * there are ignored entries below) + * - DIR_SHOW_IGNORED_TOO (same as above) + * - DIR_HIDE_EMPTY_DIRECTORIES (because we have to determine if + * the directory is empty) + */ + if (!excluded && + !(dir->flags & (DIR_SHOW_IGNORED | + DIR_SHOW_IGNORED_TOO | + DIR_HIDE_EMPTY_DIRECTORIES))) { + return path_untracked; + } + + /* + * Even if we don't want to know all the paths under an untracked or + * ignored directory, we may still need to go into the directory to + * determine if it is empty (because with DIR_HIDE_EMPTY_DIRECTORIES, + * an empty directory should be path_none instead of path_excluded or + * path_untracked). + */ + check_only = ((dir->flags & DIR_HIDE_EMPTY_DIRECTORIES) && + !(dir->flags & DIR_SHOW_IGNORED_TOO)); + + /* + * However, there's another optimization possible as a subset of + * check_only, based on the cases we have to consider: + * A) Directory matches no exclude patterns: + * * Directory is empty => path_none + * * Directory has an untracked file under it => path_untracked + * * Directory has only ignored files under it => path_excluded + * B) Directory matches an exclude pattern: + * * Directory is empty => path_none + * * Directory has an untracked file under it => path_excluded + * * Directory has only ignored files under it => path_excluded + * In case A, we can exit as soon as we've found an untracked + * file but otherwise have to walk all files. In case B, though, + * we can stop at the first file we find under the directory. + */ + stop_early = check_only && excluded; + + /* + * If /every/ file within an untracked directory is ignored, then + * we want to treat the directory as ignored (for e.g. status + * --porcelain), without listing the individual ignored files + * underneath. To do so, we'll save the current ignored_nr, and + * pop all the ones added after it if it turns out the entire + * directory is ignored. Also, when DIR_SHOW_IGNORED_TOO and + * !DIR_KEEP_UNTRACKED_CONTENTS then we don't want to show + * untracked paths so will need to pop all those off the last + * after we traverse. + */ + old_ignored_nr = dir->ignored_nr; + old_untracked_nr = dir->nr; + + /* Actually recurse into dirname now, we'll fixup the state later. */ untracked = lookup_untracked(dir->untracked, untracked, dirname + baselen, len - baselen); + state = read_directory_recursive(dir, istate, dirname, len, untracked, + check_only, stop_early, pathspec); + + /* There are a variety of reasons we may need to fixup the state... */ + if (state == path_excluded) { + /* state == path_excluded implies all paths under + * dirname were ignored... + * + * if running e.g. `git status --porcelain --ignored=matching`, + * then we want to see the subpaths that are ignored. + * + * if running e.g. just `git status --porcelain`, then + * we just want the directory itself to be listed as ignored + * and not the individual paths underneath. + */ + int want_ignored_subpaths = + ((dir->flags & DIR_SHOW_IGNORED_TOO) && + (dir->flags & DIR_SHOW_IGNORED_TOO_MODE_MATCHING)); + + if (want_ignored_subpaths) { + /* + * with --ignored=matching, we want the subpaths + * INSTEAD of the directory itself. + */ + state = path_none; + } else { + int i; + for (i = old_ignored_nr + 1; i<dir->ignored_nr; ++i) + FREE_AND_NULL(dir->ignored[i]); + dir->ignored_nr = old_ignored_nr; + } + } /* - * If this is an excluded directory, then we only need to check if - * the directory contains any files. + * We may need to ignore some of the untracked paths we found while + * traversing subdirectories. */ - return read_directory_recursive(dir, istate, dirname, len, - untracked, 1, exclude, pathspec); + if ((dir->flags & DIR_SHOW_IGNORED_TOO) && + !(dir->flags & DIR_KEEP_UNTRACKED_CONTENTS)) { + int i; + for (i = old_untracked_nr + 1; i<dir->nr; ++i) + FREE_AND_NULL(dir->entries[i]); + dir->nr = old_untracked_nr; + } + + /* + * If there is nothing under the current directory and we are not + * hiding empty directories, then we need to report on the + * untracked or ignored status of the directory itself. + */ + if (state == path_none && !(dir->flags & DIR_HIDE_EMPTY_DIRECTORIES)) + state = excluded ? path_excluded : path_untracked; + + return state; } /* @@ -1641,10 +2129,9 @@ static int get_index_dtype(struct index_state *istate, return DT_UNKNOWN; } -static int get_dtype(struct dirent *de, struct index_state *istate, - const char *path, int len) +static int resolve_dtype(int dtype, struct index_state *istate, + const char *path, int len) { - int dtype = de ? DTYPE(de) : DT_UNKNOWN; struct stat st; if (dtype != DT_UNKNOWN) @@ -1663,22 +2150,68 @@ static int get_dtype(struct dirent *de, struct index_state *istate, return dtype; } -static enum path_treatment treat_one_path(struct dir_struct *dir, - struct untracked_cache_dir *untracked, - struct index_state *istate, - struct strbuf *path, - int baselen, - const struct pathspec *pathspec, - int dtype, struct dirent *de) +static enum path_treatment treat_path_fast(struct dir_struct *dir, + struct cached_dir *cdir, + struct index_state *istate, + struct strbuf *path, + int baselen, + const struct pathspec *pathspec) +{ + /* + * WARNING: From this function, you can return path_recurse or you + * can call read_directory_recursive() (or neither), but + * you CAN'T DO BOTH. + */ + strbuf_setlen(path, baselen); + if (!cdir->ucd) { + strbuf_addstr(path, cdir->file); + return path_untracked; + } + strbuf_addstr(path, cdir->ucd->name); + /* treat_one_path() does this before it calls treat_directory() */ + strbuf_complete(path, '/'); + if (cdir->ucd->check_only) + /* + * check_only is set as a result of treat_directory() getting + * to its bottom. Verify again the same set of directories + * with check_only set. + */ + return read_directory_recursive(dir, istate, path->buf, path->len, + cdir->ucd, 1, 0, pathspec); + /* + * We get path_recurse in the first run when + * directory_exists_in_index() returns index_nonexistent. We + * are sure that new changes in the index does not impact the + * outcome. Return now. + */ + return path_recurse; +} + +static enum path_treatment treat_path(struct dir_struct *dir, + struct untracked_cache_dir *untracked, + struct cached_dir *cdir, + struct index_state *istate, + struct strbuf *path, + int baselen, + const struct pathspec *pathspec) { - int exclude; - int has_path_in_index = !!index_file_exists(istate, path->buf, path->len, ignore_case); - enum path_treatment path_treatment; + int has_path_in_index, dtype, excluded; - if (dtype == DT_UNKNOWN) - dtype = get_dtype(de, istate, path->buf, path->len); + if (!cdir->d_name) + return treat_path_fast(dir, cdir, istate, path, + baselen, pathspec); + if (is_dot_or_dotdot(cdir->d_name) || !fspathcmp(cdir->d_name, ".git")) + return path_none; + strbuf_setlen(path, baselen); + strbuf_addstr(path, cdir->d_name); + if (simplify_away(path->buf, path->len, pathspec)) + return path_none; + + dtype = resolve_dtype(cdir->d_type, istate, path->buf, path->len); /* Always exclude indexed files */ + has_path_in_index = !!index_file_exists(istate, path->buf, path->len, + ignore_case); if (dtype != DT_DIR && has_path_in_index) return path_none; @@ -1706,99 +2239,40 @@ static enum path_treatment treat_one_path(struct dir_struct *dir, (directory_exists_in_index(istate, path->buf, path->len) == index_nonexistent)) return path_none; - exclude = is_excluded(dir, istate, path->buf, &dtype); + excluded = is_excluded(dir, istate, path->buf, &dtype); /* * Excluded? If we don't explicitly want to show * ignored files, ignore it */ - if (exclude && !(dir->flags & (DIR_SHOW_IGNORED|DIR_SHOW_IGNORED_TOO))) + if (excluded && !(dir->flags & (DIR_SHOW_IGNORED|DIR_SHOW_IGNORED_TOO))) return path_excluded; switch (dtype) { default: return path_none; case DT_DIR: - strbuf_addch(path, '/'); - path_treatment = treat_directory(dir, istate, untracked, - path->buf, path->len, - baselen, exclude, pathspec); /* - * If 1) we only want to return directories that - * match an exclude pattern and 2) this directory does - * not match an exclude pattern but all of its - * contents are excluded, then indicate that we should - * recurse into this directory (instead of marking the - * directory itself as an ignored path). + * WARNING: Do not ignore/amend the return value from + * treat_directory(), and especially do not change it to return + * path_recurse as that can cause exponential slowdown. + * Instead, modify treat_directory() to return the right value. */ - if (!exclude && - path_treatment == path_excluded && - (dir->flags & DIR_SHOW_IGNORED_TOO) && - (dir->flags & DIR_SHOW_IGNORED_TOO_MODE_MATCHING)) - return path_recurse; - return path_treatment; + strbuf_addch(path, '/'); + return treat_directory(dir, istate, untracked, + path->buf, path->len, + baselen, excluded, pathspec); case DT_REG: case DT_LNK: - return exclude ? path_excluded : path_untracked; - } -} - -static enum path_treatment treat_path_fast(struct dir_struct *dir, - struct untracked_cache_dir *untracked, - struct cached_dir *cdir, - struct index_state *istate, - struct strbuf *path, - int baselen, - const struct pathspec *pathspec) -{ - strbuf_setlen(path, baselen); - if (!cdir->ucd) { - strbuf_addstr(path, cdir->file); + if (pathspec && + !match_pathspec(istate, pathspec, path->buf, path->len, + 0 /* prefix */, NULL /* seen */, + 0 /* is_dir */)) + return path_none; + if (excluded) + return path_excluded; return path_untracked; } - strbuf_addstr(path, cdir->ucd->name); - /* treat_one_path() does this before it calls treat_directory() */ - strbuf_complete(path, '/'); - if (cdir->ucd->check_only) - /* - * check_only is set as a result of treat_directory() getting - * to its bottom. Verify again the same set of directories - * with check_only set. - */ - return read_directory_recursive(dir, istate, path->buf, path->len, - cdir->ucd, 1, 0, pathspec); - /* - * We get path_recurse in the first run when - * directory_exists_in_index() returns index_nonexistent. We - * are sure that new changes in the index does not impact the - * outcome. Return now. - */ - return path_recurse; -} - -static enum path_treatment treat_path(struct dir_struct *dir, - struct untracked_cache_dir *untracked, - struct cached_dir *cdir, - struct index_state *istate, - struct strbuf *path, - int baselen, - const struct pathspec *pathspec) -{ - int dtype; - struct dirent *de = cdir->de; - - if (!de) - return treat_path_fast(dir, untracked, cdir, istate, path, - baselen, pathspec); - if (is_dot_or_dotdot(de->d_name) || !fspathcmp(de->d_name, ".git")) - return path_none; - strbuf_setlen(path, baselen); - strbuf_addstr(path, de->d_name); - if (simplify_away(path->buf, path->len, pathspec)) - return path_none; - - dtype = DTYPE(de); - return treat_one_path(dir, untracked, istate, path, baselen, pathspec, dtype, de); } static void add_untracked(struct untracked_cache_dir *dir, const char *name) @@ -1886,10 +2360,17 @@ static int open_cached_dir(struct cached_dir *cdir, static int read_cached_dir(struct cached_dir *cdir) { + struct dirent *de; + if (cdir->fdir) { - cdir->de = readdir(cdir->fdir); - if (!cdir->de) + de = readdir_skip_dot_and_dotdot(cdir->fdir); + if (!de) { + cdir->d_name = NULL; + cdir->d_type = DT_UNKNOWN; return -1; + } + cdir->d_name = de->d_name; + cdir->d_type = DTYPE(de); return 0; } while (cdir->nr_dirs < cdir->untracked->dirs_nr) { @@ -1925,6 +2406,40 @@ static void close_cached_dir(struct cached_dir *cdir) } } +static void add_path_to_appropriate_result_list(struct dir_struct *dir, + struct untracked_cache_dir *untracked, + struct cached_dir *cdir, + struct index_state *istate, + struct strbuf *path, + int baselen, + const struct pathspec *pathspec, + enum path_treatment state) +{ + /* add the path to the appropriate result list */ + switch (state) { + case path_excluded: + if (dir->flags & DIR_SHOW_IGNORED) + dir_add_name(dir, istate, path->buf, path->len); + else if ((dir->flags & DIR_SHOW_IGNORED_TOO) || + ((dir->flags & DIR_COLLECT_IGNORED) && + exclude_matches_pathspec(path->buf, path->len, + pathspec))) + dir_add_ignored(dir, istate, path->buf, path->len); + break; + + case path_untracked: + if (dir->flags & DIR_SHOW_IGNORED) + break; + dir_add_name(dir, istate, path->buf, path->len); + if (cdir->fdir) + add_untracked(untracked, path->buf + baselen); + break; + + default: + break; + } +} + /* * Read a directory tree. We currently ignore anything but * directories, regular files and symlinks. That's because git @@ -1937,7 +2452,7 @@ static void close_cached_dir(struct cached_dir *cdir) * If 'stop_at_first_file' is specified, 'path_excluded' is returned * to signal that a file was found. This is the least significant value that * indicates that a file was encountered that does not depend on the order of - * whether an untracked or exluded path was encountered first. + * whether an untracked or excluded path was encountered first. * * Returns the most significant path_treatment value encountered in the scan. * If 'stop_at_first_file' is specified, `path_excluded` is the most @@ -1949,6 +2464,11 @@ static enum path_treatment read_directory_recursive(struct dir_struct *dir, struct untracked_cache_dir *untracked, int check_only, int stop_at_first_file, const struct pathspec *pathspec) { + /* + * WARNING: Do NOT recurse unless path_recurse is returned from + * treat_path(). Recursing on any other return value + * can result in exponential slowdown. + */ struct cached_dir cdir; enum path_treatment state, subdir_state, dir_state = path_none; struct strbuf path = STRBUF_INIT; @@ -1957,6 +2477,7 @@ static enum path_treatment read_directory_recursive(struct dir_struct *dir, if (open_cached_dir(&cdir, dir, untracked, istate, &path, check_only)) goto out; + dir->visited_directories++; if (untracked) untracked->check_only = !!check_only; @@ -1965,18 +2486,13 @@ static enum path_treatment read_directory_recursive(struct dir_struct *dir, /* check how the file or directory should be treated */ state = treat_path(dir, untracked, &cdir, istate, &path, baselen, pathspec); + dir->visited_paths++; if (state > dir_state) dir_state = state; /* recurse into subdir if instructed by treat_path */ - if ((state == path_recurse) || - ((state == path_untracked) && - (get_dtype(cdir.de, istate, path.buf, path.len) == DT_DIR) && - ((dir->flags & DIR_SHOW_IGNORED_TOO) || - (pathspec && - do_match_pathspec(istate, pathspec, path.buf, path.len, - baselen, NULL, DO_MATCH_LEADING_PATHSPEC) == MATCHED_RECURSIVELY_LEADING_PATHSPEC)))) { + if (state == path_recurse) { struct untracked_cache_dir *ud; ud = lookup_untracked(dir->untracked, untracked, path.buf + baselen, @@ -2024,33 +2540,13 @@ static enum path_treatment read_directory_recursive(struct dir_struct *dir, add_untracked(untracked, path.buf + baselen); break; } - /* skip the dir_add_* part */ + /* skip the add_path_to_appropriate_result_list() */ continue; } - /* add the path to the appropriate result list */ - switch (state) { - case path_excluded: - if (dir->flags & DIR_SHOW_IGNORED) - dir_add_name(dir, istate, path.buf, path.len); - else if ((dir->flags & DIR_SHOW_IGNORED_TOO) || - ((dir->flags & DIR_COLLECT_IGNORED) && - exclude_matches_pathspec(path.buf, path.len, - pathspec))) - dir_add_ignored(dir, istate, path.buf, path.len); - break; - - case path_untracked: - if (dir->flags & DIR_SHOW_IGNORED) - break; - dir_add_name(dir, istate, path.buf, path.len); - if (cdir.fdir) - add_untracked(untracked, path.buf + baselen); - break; - - default: - break; - } + add_path_to_appropriate_result_list(dir, untracked, &cdir, + istate, &path, baselen, + pathspec, state); } close_cached_dir(&cdir); out: @@ -2081,40 +2577,69 @@ static int treat_leading_path(struct dir_struct *dir, const struct pathspec *pathspec) { struct strbuf sb = STRBUF_INIT; - int baselen, rc = 0; + struct strbuf subdir = STRBUF_INIT; + int prevlen, baselen; const char *cp; - int old_flags = dir->flags; + struct cached_dir cdir; + enum path_treatment state = path_none; + + /* + * For each directory component of path, we are going to check whether + * that path is relevant given the pathspec. For example, if path is + * foo/bar/baz/ + * then we will ask treat_path() whether we should go into foo, then + * whether we should go into bar, then whether baz is relevant. + * Checking each is important because e.g. if path is + * .git/info/ + * then we need to check .git to know we shouldn't traverse it. + * If the return from treat_path() is: + * * path_none, for any path, we return false. + * * path_recurse, for all path components, we return true + * * <anything else> for some intermediate component, we make sure + * to add that path to the relevant list but return false + * signifying that we shouldn't recurse into it. + */ while (len && path[len - 1] == '/') len--; if (!len) return 1; + + memset(&cdir, 0, sizeof(cdir)); + cdir.d_type = DT_DIR; baselen = 0; - dir->flags &= ~DIR_SHOW_OTHER_DIRECTORIES; + prevlen = 0; while (1) { - cp = path + baselen + !!baselen; + prevlen = baselen + !!baselen; + cp = path + prevlen; cp = memchr(cp, '/', path + len - cp); if (!cp) baselen = len; else baselen = cp - path; - strbuf_setlen(&sb, 0); + strbuf_reset(&sb); strbuf_add(&sb, path, baselen); if (!is_directory(sb.buf)) break; - if (simplify_away(sb.buf, sb.len, pathspec)) - break; - if (treat_one_path(dir, NULL, istate, &sb, baselen, pathspec, - DT_DIR, NULL) == path_none) + strbuf_reset(&sb); + strbuf_add(&sb, path, prevlen); + strbuf_reset(&subdir); + strbuf_add(&subdir, path+prevlen, baselen-prevlen); + cdir.d_name = subdir.buf; + state = treat_path(dir, NULL, &cdir, istate, &sb, prevlen, pathspec); + + if (state != path_recurse) break; /* do not recurse into it */ - if (len <= baselen) { - rc = 1; + if (len <= baselen) break; /* finished checking */ - } } + add_path_to_appropriate_result_list(dir, NULL, &cdir, istate, + &sb, baselen, pathspec, + state); + + strbuf_release(&subdir); strbuf_release(&sb); - dir->flags = old_flags; - return rc; + return state == path_recurse; } static const char *get_ident_string(void) @@ -2253,11 +2778,8 @@ static struct untracked_cache_dir *validate_untracked_cache(struct dir_struct *d return NULL; } - if (!dir->untracked->root) { - const int len = sizeof(*dir->untracked->root); - dir->untracked->root = xmalloc(len); - memset(dir->untracked->root, 0, len); - } + if (!dir->untracked->root) + FLEX_ALLOC_STR(dir->untracked->root, name, ""); /* Validate $GIT_DIR/info/exclude and core.excludesfile */ root = dir->untracked->root; @@ -2277,15 +2799,53 @@ static struct untracked_cache_dir *validate_untracked_cache(struct dir_struct *d return root; } +static void emit_traversal_statistics(struct dir_struct *dir, + struct repository *repo, + const char *path, + int path_len) +{ + if (!trace2_is_enabled()) + return; + + if (!path_len) { + trace2_data_string("read_directory", repo, "path", ""); + } else { + struct strbuf tmp = STRBUF_INIT; + strbuf_add(&tmp, path, path_len); + trace2_data_string("read_directory", repo, "path", tmp.buf); + strbuf_release(&tmp); + } + + trace2_data_intmax("read_directory", repo, + "directories-visited", dir->visited_directories); + trace2_data_intmax("read_directory", repo, + "paths-visited", dir->visited_paths); + + if (!dir->untracked) + return; + trace2_data_intmax("read_directory", repo, + "node-creation", dir->untracked->dir_created); + trace2_data_intmax("read_directory", repo, + "gitignore-invalidation", + dir->untracked->gitignore_invalidated); + trace2_data_intmax("read_directory", repo, + "directory-invalidation", + dir->untracked->dir_invalidated); + trace2_data_intmax("read_directory", repo, + "opendir", dir->untracked->dir_opened); +} + int read_directory(struct dir_struct *dir, struct index_state *istate, const char *path, int len, const struct pathspec *pathspec) { struct untracked_cache_dir *untracked; - trace_performance_enter(); + trace2_region_enter("dir", "read_directory", istate->repo); + dir->visited_paths = 0; + dir->visited_directories = 0; if (has_symlink_leading_path(path, len)) { - trace_performance_leave("read directory %.*s", len, path); + trace2_region_leave("dir", "read_directory", istate->repo); return dir->nr; } @@ -2301,45 +2861,15 @@ int read_directory(struct dir_struct *dir, struct index_state *istate, QSORT(dir->entries, dir->nr, cmp_dir_entry); QSORT(dir->ignored, dir->ignored_nr, cmp_dir_entry); - /* - * If DIR_SHOW_IGNORED_TOO is set, read_directory_recursive() will - * also pick up untracked contents of untracked dirs; by default - * we discard these, but given DIR_KEEP_UNTRACKED_CONTENTS we do not. - */ - if ((dir->flags & DIR_SHOW_IGNORED_TOO) && - !(dir->flags & DIR_KEEP_UNTRACKED_CONTENTS)) { - int i, j; - - /* remove from dir->entries untracked contents of untracked dirs */ - for (i = j = 0; j < dir->nr; j++) { - if (i && - check_dir_entry_contains(dir->entries[i - 1], dir->entries[j])) { - FREE_AND_NULL(dir->entries[j]); - } else { - dir->entries[i++] = dir->entries[j]; - } - } + emit_traversal_statistics(dir, istate->repo, path, len); - dir->nr = i; - } - - trace_performance_leave("read directory %.*s", len, path); + trace2_region_leave("dir", "read_directory", istate->repo); if (dir->untracked) { static int force_untracked_cache = -1; - static struct trace_key trace_untracked_stats = TRACE_KEY_INIT(UNTRACKED_STATS); if (force_untracked_cache < 0) force_untracked_cache = git_env_bool("GIT_FORCE_UNTRACKED_CACHE", 0); - trace_printf_key(&trace_untracked_stats, - "node creation: %u\n" - "gitignore invalidation: %u\n" - "directory invalidation: %u\n" - "opendir: %u\n", - dir->untracked->dir_created, - dir->untracked->gitignore_invalidated, - dir->untracked->dir_invalidated, - dir->untracked->dir_opened); if (force_untracked_cache && dir->untracked == istate->untracked && (dir->untracked->dir_opened || @@ -2350,6 +2880,7 @@ int read_directory(struct dir_struct *dir, struct index_state *istate, FREE_AND_NULL(dir->untracked); } } + return dir->nr; } @@ -2431,11 +2962,9 @@ int is_empty_dir(const char *path) if (!dir) return 0; - while ((e = readdir(dir)) != NULL) - if (!is_dot_or_dotdot(e->d_name)) { - ret = 0; - break; - } + e = readdir_skip_dot_and_dotdot(dir); + if (e) + ret = 0; closedir(dir); return ret; @@ -2475,10 +3004,8 @@ static int remove_dir_recurse(struct strbuf *path, int flag, int *kept_up) strbuf_complete(path, '/'); len = path->len; - while ((e = readdir(dir)) != NULL) { + while ((e = readdir_skip_dot_and_dotdot(dir)) != NULL) { struct stat st; - if (is_dot_or_dotdot(e->d_name)) - continue; strbuf_setlen(path, len); strbuf_addstr(path, e->d_name); @@ -2489,7 +3016,7 @@ static int remove_dir_recurse(struct strbuf *path, int flag, int *kept_up) * wanted anyway */ continue; - /* fall thru */ + /* fall through */ } else if (S_ISDIR(st.st_mode)) { if (!remove_dir_recurse(path, flag, &kept_down)) continue; /* happy */ @@ -2543,6 +3070,23 @@ void setup_standard_excludes(struct dir_struct *dir) } } +char *get_sparse_checkout_filename(void) +{ + return git_pathdup("info/sparse-checkout"); +} + +int get_sparse_checkout_patterns(struct pattern_list *pl) +{ + int res; + char *sparse_filename = get_sparse_checkout_filename(); + + pl->use_cone_patterns = core_sparse_checkout_cone; + res = add_patterns_from_file_to_list(sparse_filename, "", 0, pl, NULL, 0); + + free(sparse_filename); + return res; +} + int remove_path(const char *name) { char *slash; @@ -2563,15 +3107,16 @@ int remove_path(const char *name) } /* - * Frees memory within dir which was allocated for exclude lists and - * the exclude_stack. Does not free dir itself. + * Frees memory within dir which was allocated, and resets fields for further + * use. Does not free dir itself. */ -void clear_directory(struct dir_struct *dir) +void dir_clear(struct dir_struct *dir) { int i, j; struct exclude_list_group *group; struct pattern_list *pl; struct exclude_stack *stk; + struct dir_struct new = DIR_INIT; for (i = EXC_CMDL; i <= EXC_FILE; i++) { group = &dir->exclude_list_group[i]; @@ -2584,6 +3129,13 @@ void clear_directory(struct dir_struct *dir) free(group->pl); } + for (i = 0; i < dir->ignored_nr; i++) + free(dir->ignored[i]); + for (i = 0; i < dir->nr; i++) + free(dir->entries[i]); + free(dir->ignored); + free(dir->entries); + stk = dir->exclude_stack; while (stk) { struct exclude_stack *prev = stk->prev; @@ -2591,6 +3143,8 @@ void clear_directory(struct dir_struct *dir) stk = prev; } strbuf_release(&dir->basebuf); + + memcpy(dir, &new, sizeof(*dir)); } struct ondisk_untracked_cache { @@ -2684,7 +3238,7 @@ void write_untracked_extension(struct strbuf *out, struct untracked_cache *untra int varint_len; const unsigned hashsz = the_hash_algo->rawsz; - ouc = xcalloc(1, sizeof(*ouc)); + CALLOC_ARRAY(ouc, 1); stat_data_to_disk(&ouc->info_exclude_stat, &untracked->ss_info_exclude.stat); stat_data_to_disk(&ouc->excludes_file_stat, &untracked->ss_excludes_file.stat); ouc->dir_flags = htonl(untracked->dir_flags); @@ -2857,7 +3411,7 @@ static void read_oid(size_t pos, void *cb) rd->data = rd->end + 1; return; } - hashcpy(ud->exclude_oid.hash, rd->data); + oidread(&ud->exclude_oid, rd->data); rd->data += the_hash_algo->rawsz; } @@ -2865,7 +3419,7 @@ static void load_oid_stat(struct oid_stat *oid_stat, const unsigned char *data, const unsigned char *sha1) { stat_data_from_disk(&oid_stat->stat, data); - hashcpy(oid_stat->oid.hash, sha1); + oidread(&oid_stat->oid, sha1); oid_stat->valid = 1; } @@ -2895,7 +3449,7 @@ struct untracked_cache *read_untracked_extension(const void *data, unsigned long if (next + exclude_per_dir_offset + 1 > end) return NULL; - uc = xcalloc(1, sizeof(*uc)); + CALLOC_ARRAY(uc, 1); strbuf_init(&uc->ident, ident_len); strbuf_add(&uc->ident, ident, ident_len); load_oid_stat(&uc->ss_info_exclude, @@ -3055,6 +3609,8 @@ static void connect_wt_gitdir_in_nested(const char *sub_worktree, if (repo_read_index(&subrepo) < 0) die(_("index file corrupt in repo %s"), subrepo.gitdir); + /* TODO: audit for interaction with sparse-index. */ + ensure_full_index(subrepo.index); for (i = 0; i < subrepo.index->cache_nr; i++) { const struct cache_entry *ce = subrepo.index->cache[i]; @@ -3069,7 +3625,7 @@ static void connect_wt_gitdir_in_nested(const char *sub_worktree, */ i++; - sub = submodule_from_path(&subrepo, &null_oid, ce->name); + sub = submodule_from_path(&subrepo, null_oid(), ce->name); if (!sub || !is_submodule_active(&subrepo, ce->name)) /* .gitmodules broken or inactive sub */ continue; |