diff options
| -rw-r--r-- | dir.c | 210 |
1 files changed, 147 insertions, 63 deletions
@@ -1659,7 +1659,13 @@ static enum path_treatment treat_directory(struct dir_struct *dir, const char *dirname, int len, int baselen, int excluded, const struct pathspec *pathspec) { - int nested_repo = 0; + /* + * 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 nested_repo = 0, old_ignored_nr, check_only, stop_early; /* The "len-1" is to strip the final '/' */ enum exist_status status = directory_exists_in_index(istate, dirname, len-1); @@ -1711,18 +1717,135 @@ static enum path_treatment treat_directory(struct dir_struct *dir, /* This is the "show_other_directories" case */ - if (!(dir->flags & DIR_HIDE_EMPTY_DIRECTORIES)) + /* + * 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 (pathspec) { + int ret = do_match_pathspec(istate, pathspec, dirname, len, + 0 /* prefix */, NULL /* seen */, + DO_MATCH_LEADING_PATHSPEC); + if (ret == MATCHED_RECURSIVELY_LEADING_PATHSPEC) + return path_recurse; + } + + /* + * Other than the path_recurse case immediately above, we only need + * to recurse into untracked/ignored directories if either of the + * following bits is set: + * - DIR_SHOW_IGNORED_TOO (because then we need to determine if + * there are ignored directories below) + * - DIR_HIDE_EMPTY_DIRECTORIES (because we have to determine if + * the directory is empty) + */ + if (!(dir->flags & (DIR_SHOW_IGNORED_TOO | DIR_HIDE_EMPTY_DIRECTORIES))) return excluded ? path_excluded : path_untracked; + /* + * ...and even if DIR_SHOW_IGNORED_TOO is set, we can still avoid + * recursing into ignored directories if the path is excluded and + * DIR_SHOW_IGNORED_TOO_MODE_MATCHING is also set. + */ + if (excluded && + (dir->flags & DIR_SHOW_IGNORED_TOO) && + (dir->flags & DIR_SHOW_IGNORED_TOO_MODE_MATCHING)) + return path_excluded; + + /* + * If we have we don't want to know the all the paths under an + * untracked or ignored directory, we still need to go into the + * directory to determine if it is empty (because 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. + */ + old_ignored_nr = dir->ignored_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. + * 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. */ - return read_directory_recursive(dir, istate, dirname, len, - untracked, 1, excluded, pathspec); + if (state == path_none && !(dir->flags & DIR_HIDE_EMPTY_DIRECTORIES)) + state = excluded ? path_excluded : path_untracked; + + /* + * We can recurse into untracked directories that don't match any + * of the given pathspecs when some file underneath the directory + * might match one of the pathspecs. If so, we should make sure + * to note that the directory itself did not match. + */ + if (pathspec && + !match_pathspec(istate, pathspec, dirname, len, + 0 /* prefix */, NULL, + 0 /* do NOT special case dirs */)) + state = path_none; + + return state; } /* @@ -1870,6 +1993,11 @@ static enum path_treatment treat_path_fast(struct dir_struct *dir, 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); @@ -1904,7 +2032,6 @@ static enum path_treatment treat_path(struct dir_struct *dir, const struct pathspec *pathspec) { int has_path_in_index, dtype, excluded; - enum path_treatment path_treatment; if (!cdir->d_name) return treat_path_fast(dir, untracked, cdir, istate, path, @@ -1961,24 +2088,16 @@ static enum path_treatment treat_path(struct dir_struct *dir, default: return path_none; case DT_DIR: - strbuf_addch(path, '/'); - path_treatment = treat_directory(dir, istate, untracked, - path->buf, path->len, - baselen, excluded, 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 (!excluded && - 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 excluded ? path_excluded : path_untracked; @@ -2175,14 +2294,10 @@ static enum path_treatment read_directory_recursive(struct dir_struct *dir, int stop_at_first_file, const struct pathspec *pathspec) { /* - * WARNING WARNING WARNING: - * - * Any updates to the traversal logic here may need corresponding - * updates in treat_leading_path(). See the commit message for the - * commit adding this warning as well as the commit preceding it - * for details. + * 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; @@ -2204,13 +2319,7 @@ static enum path_treatment read_directory_recursive(struct dir_struct *dir, dir_state = state; /* recurse into subdir if instructed by treat_path */ - if ((state == path_recurse) || - ((state == path_untracked) && - (resolve_dtype(cdir.d_type, 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, @@ -2294,15 +2403,6 @@ static int treat_leading_path(struct dir_struct *dir, const char *path, int len, const struct pathspec *pathspec) { - /* - * WARNING WARNING WARNING: - * - * Any updates to the traversal logic here may need corresponding - * updates in read_directory_recursive(). See 777b420347 (dir: - * synchronize treat_leading_path() and read_directory_recursive(), - * 2019-12-19) and its parent commit for details. - */ - struct strbuf sb = STRBUF_INIT; struct strbuf subdir = STRBUF_INIT; int prevlen, baselen; @@ -2353,23 +2453,7 @@ static int treat_leading_path(struct dir_struct *dir, 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_untracked && - resolve_dtype(cdir.d_type, istate, sb.buf, sb.len) == DT_DIR && - (dir->flags & DIR_SHOW_IGNORED_TOO || - do_match_pathspec(istate, pathspec, sb.buf, sb.len, - baselen, NULL, DO_MATCH_LEADING_PATHSPEC) == MATCHED_RECURSIVELY_LEADING_PATHSPEC)) { - if (!match_pathspec(istate, pathspec, sb.buf, sb.len, - 0 /* prefix */, NULL, - 0 /* do NOT special case dirs */)) - state = path_none; - add_path_to_appropriate_result_list(dir, NULL, &cdir, - istate, - &sb, baselen, - pathspec, state); - state = path_recurse; - } + state = treat_path(dir, NULL, &cdir, istate, &sb, prevlen, pathspec); if (state != path_recurse) break; /* do not recurse into it */ |