diff options
Diffstat (limited to 'dir.c')
| -rw-r--r-- | dir.c | 1284 |
1 files changed, 864 insertions, 420 deletions
@@ -2,12 +2,9 @@ * 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 */ -#define NO_THE_INDEX_COMPATIBILITY_MACROS #include "cache.h" #include "config.h" #include "dir.h" @@ -44,7 +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; }; @@ -53,8 +51,8 @@ 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); int count_slashes(const char *s) { @@ -140,7 +138,7 @@ static size_t common_prefix_len(const struct pathspec *pathspec) * ":(icase)path" is treated as a pathspec full of * wildcard. In other words, only prefix is considered common * prefix. If the pathspec is abc/foo abc/bar, running in - * subdir xyz, the common prefix is still xyz, not xuz/abc as + * subdir xyz, the common prefix is still xyz, not xyz/abc as * in non-:(icase). */ GUARD_PATHSPEC(pathspec, @@ -274,50 +272,30 @@ static int do_read_blob(const struct object_id *oid, struct oid_stat *oid_stat, #define DO_MATCH_EXCLUDE (1<<0) #define DO_MATCH_DIRECTORY (1<<1) -#define DO_MATCH_SUBMODULE (1<<2) - -static int match_attrs(const struct index_state *istate, - const char *name, int namelen, - const struct pathspec_item *item) -{ - int i; - - git_check_attr(istate, name, item->attr_check); - for (i = 0; i < item->attr_match_nr; i++) { - const char *value; - int matched; - enum attr_match_mode match_mode; - - value = item->attr_check->items[i].value; - match_mode = item->attr_match[i].match_mode; - - if (ATTR_TRUE(value)) - matched = (match_mode == MATCH_SET); - else if (ATTR_FALSE(value)) - matched = (match_mode == MATCH_UNSET); - else if (ATTR_UNSET(value)) - matched = (match_mode == MATCH_UNSPECIFIED); - else - matched = (match_mode == MATCH_VALUE && - !strcmp(item->attr_match[i].value, value)); - if (!matched) - return 0; - } - - return 1; -} +#define DO_MATCH_LEADING_PATHSPEC (1<<2) /* - * Does 'match' match the given name? - * A match is found if + * Does the given pathspec match the given name? A match is found if + * + * (1) the pathspec string is leading directory of 'name' ("RECURSIVELY"), or + * (2) the pathspec string has a leading part matching 'name' ("LEADING"), or + * (3) the pathspec string is a wildcard and matches 'name' ("WILDCARD"), or + * (4) the pathspec string is exactly the same as 'name' ("EXACT"). * - * (1) the 'match' string is leading directory of 'name', or - * (2) the 'match' string is a wildcard and matches 'name', or - * (3) the 'match' string is exactly the same as 'name'. + * Return value tells which case it was (1-4), or 0 when there is no match. * - * and the return value tells which case it was. + * It may be instructive to look at a small table of concrete examples + * to understand the differences between 1, 2, and 4: * - * It returns 0 when there is no match. + * Pathspecs + * | a/b | a/b/ | a/b/c + * ------+-----------+-----------+------------ + * a/b | EXACT | EXACT[1] | LEADING[2] + * Names a/b/ | RECURSIVE | EXACT | LEADING[2] + * a/b/c | RECURSIVE | RECURSIVE | EXACT + * + * [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, const struct pathspec_item *item, int prefix, @@ -360,7 +338,8 @@ static int match_pathspec_item(const struct index_state *istate, strncmp(item->match, name - prefix, item->prefix)) return 0; - if (item->attr_match_nr && !match_attrs(istate, name, namelen, item)) + if (item->attr_match_nr && + !match_pathspec_attrs(istate, name, namelen, item)) return 0; /* If the match was just the prefix, we matched */ @@ -384,21 +363,29 @@ static int match_pathspec_item(const struct index_state *istate, item->nowildcard_len - prefix)) return MATCHED_FNMATCH; - /* Perform checks to see if "name" is a super set of the pathspec */ - if (flags & DO_MATCH_SUBMODULE) { + /* Perform checks to see if "name" is a leading string of the pathspec */ + if (flags & DO_MATCH_LEADING_PATHSPEC) { /* name is a literal prefix of the pathspec */ + int offset = name[namelen-1] == '/' ? 1 : 0; if ((namelen < matchlen) && - (match[namelen] == '/') && + (match[namelen-offset] == '/') && !ps_strncmp(item, match, name, namelen)) - return MATCHED_RECURSIVELY; + 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 @@ -407,7 +394,7 @@ static int match_pathspec_item(const struct index_state *istate, * The submodules themselves will be able to perform more * accurate matching to determine if the pathspec matches. */ - return MATCHED_RECURSIVELY; + return MATCHED_RECURSIVELY_LEADING_PATHSPEC; } return 0; @@ -528,13 +515,12 @@ int submodule_path_match(const struct index_state *istate, strlen(submodule_name), 0, seen, DO_MATCH_DIRECTORY | - DO_MATCH_SUBMODULE); + DO_MATCH_LEADING_PATHSPEC); return matched; } int report_path_error(const char *ps_matched, - const struct pathspec *pathspec, - const char *prefix) + const struct pathspec *pathspec) { /* * Make sure all pathspec matched; otherwise it is an error. @@ -593,7 +579,7 @@ int no_wildcard(const char *string) return string[simple_length(string)] == '\0'; } -void parse_exclude_pattern(const char **pattern, +void parse_path_pattern(const char **pattern, int *patternlen, unsigned *flags, int *nowildcardlen) @@ -603,20 +589,20 @@ void parse_exclude_pattern(const char **pattern, *flags = 0; if (*p == '!') { - *flags |= EXC_FLAG_NEGATIVE; + *flags |= PATTERN_FLAG_NEGATIVE; p++; } len = strlen(p); if (len && p[len - 1] == '/') { len--; - *flags |= EXC_FLAG_MUSTBEDIR; + *flags |= PATTERN_FLAG_MUSTBEDIR; } for (i = 0; i < len; i++) { if (p[i] == '/') break; } if (i == len) - *flags |= EXC_FLAG_NODIR; + *flags |= PATTERN_FLAG_NODIR; *nowildcardlen = simple_length(p); /* * we should have excluded the trailing slash from 'p' too, @@ -626,35 +612,261 @@ void parse_exclude_pattern(const char **pattern, if (*nowildcardlen > len) *nowildcardlen = len; if (*p == '*' && no_wildcard(p + 1)) - *flags |= EXC_FLAG_ENDSWITH; + *flags |= PATTERN_FLAG_ENDSWITH; *pattern = p; *patternlen = len; } -void add_exclude(const char *string, const char *base, - int baselen, struct exclude_list *el, int srcpos) +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, + ignore_case ? + strihash(translated->pattern) : + strhash(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, + ignore_case ? + strihash(translated->pattern) : + strhash(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_free_entries(&pl->parent_hashmap, struct pattern_entry, ent); + hashmap_free_entries(&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, + ignore_case ? + strihash(p.pattern) : + strhash(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) { - struct exclude *x; + struct path_pattern *pattern; int patternlen; unsigned flags; int nowildcardlen; - parse_exclude_pattern(&string, &patternlen, &flags, &nowildcardlen); - if (flags & EXC_FLAG_MUSTBEDIR) { - FLEXPTR_ALLOC_MEM(x, pattern, string, patternlen); + parse_path_pattern(&string, &patternlen, &flags, &nowildcardlen); + if (flags & PATTERN_FLAG_MUSTBEDIR) { + FLEXPTR_ALLOC_MEM(pattern, pattern, string, patternlen); } else { - x = xmalloc(sizeof(*x)); - x->pattern = string; + pattern = xmalloc(sizeof(*pattern)); + pattern->pattern = string; } - x->patternlen = patternlen; - x->nowildcardlen = nowildcardlen; - x->base = base; - x->baselen = baselen; - x->flags = flags; - x->srcpos = srcpos; - ALLOC_GROW(el->excludes, el->nr + 1, el->alloc); - el->excludes[el->nr++] = x; - x->el = el; + pattern->patternlen = patternlen; + pattern->nowildcardlen = nowildcardlen; + pattern->base = base; + pattern->baselen = baselen; + pattern->flags = flags; + pattern->srcpos = srcpos; + 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, @@ -675,19 +887,19 @@ static int read_skip_worktree_file_from_index(const struct index_state *istate, } /* - * Frees memory within el which was allocated for exclude patterns and - * the file buffer. Does not free el itself. + * Frees memory within pl which was allocated for exclude patterns and + * the file buffer. Does not free pl itself. */ -void clear_exclude_list(struct exclude_list *el) +void clear_pattern_list(struct pattern_list *pl) { int i; - for (i = 0; i < el->nr; i++) - free(el->excludes[i]); - free(el->excludes); - free(el->filebuf); + for (i = 0; i < pl->nr; i++) + free(pl->patterns[i]); + free(pl->patterns); + free(pl->filebuf); - memset(el, 0, sizeof(*el)); + memset(pl, 0, sizeof(*pl)); } static void trim_trailing_spaces(char *buf) @@ -733,7 +945,7 @@ static struct untracked_cache_dir *lookup_untracked(struct untracked_cache *uc, first = 0; last = dir->dirs_nr; while (last > first) { - int cmp, next = (last + first) >> 1; + int cmp, next = first + ((last - first) >> 1); d = dir->dirs[next]; cmp = strncmp(name, d->name, len); if (!cmp && strlen(d->name) > len) @@ -794,21 +1006,21 @@ static void invalidate_directory(struct untracked_cache *uc, dir->dirs[i]->recurse = 0; } -static int add_excludes_from_buffer(char *buf, size_t size, +static int add_patterns_from_buffer(char *buf, size_t size, const char *base, int baselen, - struct exclude_list *el); + struct pattern_list *pl); /* * 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 "el". + * exclude rules in "pl". * * If "ss" is not NULL, compute SHA-1 of the exclude file and fill - * stat data from disk (only valid if add_excludes returns zero). If + * stat data from disk (only valid if add_patterns returns zero). If * ss_valid is non-zero, "ss" must contain good value as input. */ -static int add_excludes(const char *fname, const char *base, int baselen, - struct exclude_list *el, struct index_state *istate, +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) { struct stat st; @@ -862,28 +1074,31 @@ static int add_excludes(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; } } - add_excludes_from_buffer(buf, size, base, baselen, el); + add_patterns_from_buffer(buf, size, base, baselen, pl); return 0; } -static int add_excludes_from_buffer(char *buf, size_t size, +static int add_patterns_from_buffer(char *buf, size_t size, const char *base, int baselen, - struct exclude_list *el) + struct pattern_list *pl) { int i, lineno = 1; char *entry; - el->filebuf = buf; + 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)) - size -= buf - el->filebuf; + size -= buf - pl->filebuf; entry = buf; @@ -892,7 +1107,7 @@ static int add_excludes_from_buffer(char *buf, size_t size, if (entry != buf + i && entry[0] != '#') { buf[i - (i && buf[i-1] == '\r')] = 0; trim_trailing_spaces(entry); - add_exclude(entry, base, baselen, el, lineno); + add_pattern(entry, base, baselen, pl, lineno); } lineno++; entry = buf + i + 1; @@ -901,17 +1116,17 @@ static int add_excludes_from_buffer(char *buf, size_t size, return 0; } -int add_excludes_from_file_to_list(const char *fname, const char *base, - int baselen, struct exclude_list *el, +int add_patterns_from_file_to_list(const char *fname, const char *base, + int baselen, struct pattern_list *pl, struct index_state *istate) { - return add_excludes(fname, base, baselen, el, istate, NULL); + return add_patterns(fname, base, baselen, pl, istate, NULL); } -int add_excludes_from_blob_to_list( +int add_patterns_from_blob_to_list( struct object_id *oid, const char *base, int baselen, - struct exclude_list *el) + struct pattern_list *pl) { char *buf; size_t size; @@ -921,31 +1136,31 @@ int add_excludes_from_blob_to_list( if (r != 1) return r; - add_excludes_from_buffer(buf, size, base, baselen, el); + add_patterns_from_buffer(buf, size, base, baselen, pl); return 0; } -struct exclude_list *add_exclude_list(struct dir_struct *dir, +struct pattern_list *add_pattern_list(struct dir_struct *dir, int group_type, const char *src) { - struct exclude_list *el; + struct pattern_list *pl; struct exclude_list_group *group; group = &dir->exclude_list_group[group_type]; - ALLOC_GROW(group->el, group->nr + 1, group->alloc); - el = &group->el[group->nr++]; - memset(el, 0, sizeof(*el)); - el->src = src; - return el; + ALLOC_GROW(group->pl, group->nr + 1, group->alloc); + pl = &group->pl[group->nr++]; + memset(pl, 0, sizeof(*pl)); + pl->src = src; + return pl; } /* * Used to set up core.excludesfile and .git/info/exclude lists. */ -static void add_excludes_from_file_1(struct dir_struct *dir, const char *fname, +static void add_patterns_from_file_1(struct dir_struct *dir, const char *fname, struct oid_stat *oid_stat) { - struct exclude_list *el; + struct pattern_list *pl; /* * catch setup_standard_excludes() that's called before * dir->untracked is assigned. That function behaves @@ -953,15 +1168,15 @@ static void add_excludes_from_file_1(struct dir_struct *dir, const char *fname, */ if (!dir->untracked) dir->unmanaged_exclude_files++; - el = add_exclude_list(dir, EXC_FILE, fname); - if (add_excludes(fname, "", 0, el, NULL, oid_stat) < 0) + pl = add_pattern_list(dir, EXC_FILE, fname); + if (add_patterns(fname, "", 0, pl, NULL, oid_stat) < 0) die(_("cannot use %s as an exclude file"), fname); } -void add_excludes_from_file(struct dir_struct *dir, const char *fname) +void add_patterns_from_file(struct dir_struct *dir, const char *fname) { dir->unmanaged_exclude_files++; /* see validate_untracked_cache() */ - add_excludes_from_file_1(dir, fname, NULL); + add_patterns_from_file_1(dir, fname, NULL); } int match_basename(const char *basename, int basenamelen, @@ -972,7 +1187,7 @@ int match_basename(const char *basename, int basenamelen, if (patternlen == basenamelen && !fspathncmp(pattern, basename, basenamelen)) return 1; - } else if (flags & EXC_FLAG_ENDSWITH) { + } else if (flags & PATTERN_FLAG_ENDSWITH) { /* "*literal" matching against "fooliteral" */ if (patternlen - 1 <= basenamelen && !fspathncmp(pattern + 1, @@ -1053,85 +1268,138 @@ int match_pathname(const char *pathname, int pathlen, * any, determines the fate. Returns the exclude_list element which * matched, or NULL for undecided. */ -static struct exclude *last_exclude_matching_from_list(const char *pathname, +static struct path_pattern *last_matching_pattern_from_list(const char *pathname, int pathlen, const char *basename, int *dtype, - struct exclude_list *el, + struct pattern_list *pl, struct index_state *istate) { - struct exclude *exc = NULL; /* undecided */ + struct path_pattern *res = NULL; /* undecided */ int i; - if (!el->nr) + if (!pl->nr) return NULL; /* undefined */ - for (i = el->nr - 1; 0 <= i; i--) { - struct exclude *x = el->excludes[i]; - const char *exclude = x->pattern; - int prefix = x->nowildcardlen; + for (i = pl->nr - 1; 0 <= i; i--) { + struct path_pattern *pattern = pl->patterns[i]; + const char *exclude = pattern->pattern; + int prefix = pattern->nowildcardlen; - if (x->flags & EXC_FLAG_MUSTBEDIR) { - if (*dtype == DT_UNKNOWN) - *dtype = get_dtype(NULL, istate, pathname, pathlen); + if (pattern->flags & PATTERN_FLAG_MUSTBEDIR) { + *dtype = resolve_dtype(*dtype, istate, pathname, pathlen); if (*dtype != DT_DIR) continue; } - if (x->flags & EXC_FLAG_NODIR) { + if (pattern->flags & PATTERN_FLAG_NODIR) { if (match_basename(basename, pathlen - (basename - pathname), - exclude, prefix, x->patternlen, - x->flags)) { - exc = x; + exclude, prefix, pattern->patternlen, + pattern->flags)) { + res = pattern; break; } continue; } - assert(x->baselen == 0 || x->base[x->baselen - 1] == '/'); + assert(pattern->baselen == 0 || + pattern->base[pattern->baselen - 1] == '/'); if (match_pathname(pathname, pathlen, - x->base, x->baselen ? x->baselen - 1 : 0, - exclude, prefix, x->patternlen, x->flags)) { - exc = x; + pattern->base, + pattern->baselen ? pattern->baselen - 1 : 0, + exclude, prefix, pattern->patternlen, + pattern->flags)) { + res = pattern; break; } } - return exc; + return res; } /* - * Scan the list and let the last match determine the fate. - * Return 1 for exclude, 0 for include and -1 for undecided. + * Scan the list of patterns to determine if the ordered list + * of patterns matches on 'pathname'. + * + * Return 1 for a match, 0 for not matched and -1 for undecided. */ -int is_excluded_from_list(const char *pathname, - int pathlen, const char *basename, int *dtype, - struct exclude_list *el, struct index_state *istate) -{ - struct exclude *exclude; - exclude = last_exclude_matching_from_list(pathname, pathlen, basename, - dtype, el, istate); - if (exclude) - return exclude->flags & EXC_FLAG_NEGATIVE ? 0 : 1; - return -1; /* undecided */ +enum pattern_match_result path_matches_pattern_list( + const char *pathname, int pathlen, + const char *basename, int *dtype, + struct pattern_list *pl, + struct index_state *istate) +{ + struct path_pattern *pattern; + struct strbuf parent_pathname = STRBUF_INIT; + int result = NOT_MATCHED; + const char *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; + } + + if (pl->full_cone) + return MATCHED; + + strbuf_addch(&parent_pathname, '/'); + strbuf_add(&parent_pathname, pathname, pathlen); + + if (hashmap_contains_path(&pl->recursive_hashmap, + &parent_pathname)) { + result = MATCHED_RECURSIVE; + goto done; + } + + slash_pos = strrchr(parent_pathname.buf, '/'); + + if (slash_pos == parent_pathname.buf) { + /* include every file in root */ + result = MATCHED; + goto done; + } + + strbuf_setlen(&parent_pathname, slash_pos - parent_pathname.buf); + + 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 exclude *last_exclude_matching_from_lists(struct dir_struct *dir, - struct index_state *istate, - const char *pathname, int pathlen, const char *basename, - int *dtype_p) +static struct path_pattern *last_matching_pattern_from_lists( + struct dir_struct *dir, struct index_state *istate, + const char *pathname, int pathlen, + const char *basename, int *dtype_p) { int i, j; struct exclude_list_group *group; - struct exclude *exclude; + struct path_pattern *pattern; for (i = EXC_CMDL; i <= EXC_FILE; i++) { group = &dir->exclude_list_group[i]; for (j = group->nr - 1; j >= 0; j--) { - exclude = last_exclude_matching_from_list( + pattern = last_matching_pattern_from_list( pathname, pathlen, basename, dtype_p, - &group->el[j], istate); - if (exclude) - return exclude; + &group->pl[j], istate); + if (pattern) + return pattern; } } return NULL; @@ -1146,7 +1414,7 @@ static void prep_exclude(struct dir_struct *dir, const char *base, int baselen) { struct exclude_list_group *group; - struct exclude_list *el; + struct pattern_list *pl; struct exclude_stack *stk = NULL; struct untracked_cache_dir *untracked; int current; @@ -1162,17 +1430,17 @@ static void prep_exclude(struct dir_struct *dir, if (stk->baselen <= baselen && !strncmp(dir->basebuf.buf, base, stk->baselen)) break; - el = &group->el[dir->exclude_stack->exclude_ix]; + pl = &group->pl[dir->exclude_stack->exclude_ix]; dir->exclude_stack = stk->prev; - dir->exclude = NULL; - free((char *)el->src); /* see strbuf_detach() below */ - clear_exclude_list(el); + dir->pattern = NULL; + free((char *)pl->src); /* see strbuf_detach() below */ + clear_pattern_list(pl); free(stk); group->nr--; } /* Skip traversing into sub directories if the parent is excluded */ - if (dir->exclude) + if (dir->pattern) return; /* @@ -1213,7 +1481,7 @@ static void prep_exclude(struct dir_struct *dir, stk->baselen = cp - base; stk->exclude_ix = group->nr; stk->ucd = untracked; - el = add_exclude_list(dir, EXC_DIRS, NULL); + pl = add_pattern_list(dir, EXC_DIRS, NULL); strbuf_add(&dir->basebuf, base + current, stk->baselen - current); assert(stk->baselen == dir->basebuf.len); @@ -1221,15 +1489,15 @@ static void prep_exclude(struct dir_struct *dir, if (stk->baselen) { int dt = DT_DIR; dir->basebuf.buf[stk->baselen - 1] = 0; - dir->exclude = last_exclude_matching_from_lists(dir, + dir->pattern = last_matching_pattern_from_lists(dir, istate, dir->basebuf.buf, stk->baselen - 1, dir->basebuf.buf + current, &dt); dir->basebuf.buf[stk->baselen - 1] = '/'; - if (dir->exclude && - dir->exclude->flags & EXC_FLAG_NEGATIVE) - dir->exclude = NULL; - if (dir->exclude) { + if (dir->pattern && + dir->pattern->flags & PATTERN_FLAG_NEGATIVE) + dir->pattern = NULL; + if (dir->pattern) { dir->exclude_stack = stk; return; } @@ -1255,34 +1523,34 @@ static void prep_exclude(struct dir_struct *dir, /* * dir->basebuf gets reused by the traversal, but we * need fname to remain unchanged to ensure the src - * member of each struct exclude correctly + * member of each struct path_pattern correctly * back-references its source file. Other invocations - * of add_exclude_list provide stable strings, so we + * of add_pattern_list provide stable strings, so we * strbuf_detach() and free() here in the caller. */ struct strbuf sb = STRBUF_INIT; strbuf_addbuf(&sb, &dir->basebuf); strbuf_addstr(&sb, dir->exclude_per_dir); - el->src = strbuf_detach(&sb, NULL); - add_excludes(el->src, el->src, stk->baselen, el, istate, + pl->src = strbuf_detach(&sb, NULL); + add_patterns(pl->src, pl->src, stk->baselen, pl, istate, untracked ? &oid_stat : NULL); } /* * NEEDSWORK: when untracked cache is enabled, prep_exclude() * will first be called in valid_cached_dir() then maybe many - * times more in last_exclude_matching(). When the cache is - * used, last_exclude_matching() will not be called and + * times more in last_matching_pattern(). When the cache is + * used, last_matching_pattern() will not be called and * reading .gitignore content will be a waste. * * So when it's called by valid_cached_dir() and we can get * .gitignore SHA-1 from the index (i.e. .gitignore is not * modified on work tree), we could delay reading the * .gitignore content until we absolutely need it in - * last_exclude_matching(). Be careful about ignore rule + * last_matching_pattern(). Be careful about ignore rule * order, though, if you do that. */ if (untracked && - oidcmp(&oid_stat.oid, &untracked->exclude_oid)) { + !oideq(&oid_stat.oid, &untracked->exclude_oid)) { invalidate_gitignore(dir->untracked, untracked); oidcpy(&untracked->exclude_oid, &oid_stat.oid); } @@ -1298,7 +1566,7 @@ static void prep_exclude(struct dir_struct *dir, * Returns the exclude_list element which matched, or NULL for * undecided. */ -struct exclude *last_exclude_matching(struct dir_struct *dir, +struct path_pattern *last_matching_pattern(struct dir_struct *dir, struct index_state *istate, const char *pathname, int *dtype_p) @@ -1309,10 +1577,10 @@ struct exclude *last_exclude_matching(struct dir_struct *dir, prep_exclude(dir, istate, pathname, basename-pathname); - if (dir->exclude) - return dir->exclude; + if (dir->pattern) + return dir->pattern; - return last_exclude_matching_from_lists(dir, istate, pathname, pathlen, + return last_matching_pattern_from_lists(dir, istate, pathname, pathlen, basename, dtype_p); } @@ -1324,10 +1592,10 @@ struct exclude *last_exclude_matching(struct dir_struct *dir, int is_excluded(struct dir_struct *dir, struct index_state *istate, const char *pathname, int *dtype_p) { - struct exclude *exclude = - last_exclude_matching(dir, istate, pathname, dtype_p); - if (exclude) - return exclude->flags & EXC_FLAG_NEGATIVE ? 0 : 1; + struct path_pattern *pattern = + last_matching_pattern(dir, istate, pathname, dtype_p); + if (pattern) + return pattern->flags & PATTERN_FLAG_NEGATIVE ? 0 : 1; return 0; } @@ -1459,23 +1727,59 @@ static enum exist_status directory_exists_in_index(struct index_state *istate, 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_SHOW_OTHER_DIRECTORIES) - break; - if (exclude && - (dir->flags & DIR_SHOW_IGNORED_TOO) && - (dir->flags & DIR_SHOW_IGNORED_TOO_MODE_MATCHING)) { + /* + * 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 = do_match_pathspec(istate, pathspec, dirname, len, + 0 /* prefix */, NULL /* seen */, + DO_MATCH_LEADING_PATHSPEC); + if (!matches_how) + return path_none; + } + + + 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) + return ((dir->flags & DIR_SKIP_NESTED_GIT) ? path_none : + (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 @@ -1497,28 +1801,139 @@ static enum path_treatment treat_directory(struct dir_struct *dir, return path_none; } - if (!(dir->flags & DIR_NO_GITLINKS)) { - struct object_id oid; - if (resolve_gitlink_ref(dirname, "HEAD", &oid) == 0) - return exclude ? path_excluded : path_untracked; - } return path_recurse; } /* This is the "show_other_directories" case */ - 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; + + /* + * 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. 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; + } + } + + /* + * We may need to ignore some of the untracked paths we found while + * traversing subdirectories. + */ + 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 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, exclude, pathspec); + if (state == path_none && !(dir->flags & DIR_HIDE_EMPTY_DIRECTORIES)) + state = excluded ? path_excluded : path_untracked; + + return state; } /* @@ -1637,10 +2052,9 @@ 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) @@ -1659,86 +2073,6 @@ 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) -{ - int exclude; - int has_path_in_index = !!index_file_exists(istate, path->buf, path->len, ignore_case); - enum path_treatment path_treatment; - - if (dtype == DT_UNKNOWN) - dtype = get_dtype(de, istate, path->buf, path->len); - - /* Always exclude indexed files */ - if (dtype != DT_DIR && has_path_in_index) - return path_none; - - /* - * When we are looking at a directory P in the working tree, - * there are three cases: - * - * (1) P exists in the index. Everything inside the directory P in - * the working tree needs to go when P is checked out from the - * index. - * - * (2) P does not exist in the index, but there is P/Q in the index. - * We know P will stay a directory when we check out the contents - * of the index, but we do not know yet if there is a directory - * P/Q in the working tree to be killed, so we need to recurse. - * - * (3) P does not exist in the index, and there is no P/Q in the index - * to require P to be a directory, either. Only in this case, we - * know that everything inside P will not be killed without - * recursing. - */ - if ((dir->flags & DIR_COLLECT_KILLED_ONLY) && - (dtype == DT_DIR) && - !has_path_in_index && - (directory_exists_in_index(istate, path->buf, path->len) == index_nonexistent)) - return path_none; - - exclude = 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))) - 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). - */ - 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; - 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, @@ -1747,6 +2081,11 @@ 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); @@ -1780,21 +2119,84 @@ static enum path_treatment treat_path(struct dir_struct *dir, int baselen, const struct pathspec *pathspec) { - int dtype; - struct dirent *de = cdir->de; + int has_path_in_index, dtype, excluded; - if (!de) + if (!cdir->d_name) return treat_path_fast(dir, untracked, cdir, istate, path, baselen, pathspec); - if (is_dot_or_dotdot(de->d_name) || !fspathcmp(de->d_name, ".git")) + if (is_dot_or_dotdot(cdir->d_name) || !fspathcmp(cdir->d_name, ".git")) return path_none; strbuf_setlen(path, baselen); - strbuf_addstr(path, de->d_name); + strbuf_addstr(path, cdir->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); + 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; + + /* + * When we are looking at a directory P in the working tree, + * there are three cases: + * + * (1) P exists in the index. Everything inside the directory P in + * the working tree needs to go when P is checked out from the + * index. + * + * (2) P does not exist in the index, but there is P/Q in the index. + * We know P will stay a directory when we check out the contents + * of the index, but we do not know yet if there is a directory + * P/Q in the working tree to be killed, so we need to recurse. + * + * (3) P does not exist in the index, and there is no P/Q in the index + * to require P to be a directory, either. Only in this case, we + * know that everything inside P will not be killed without + * recursing. + */ + if ((dir->flags & DIR_COLLECT_KILLED_ONLY) && + (dtype == DT_DIR) && + !has_path_in_index && + (directory_exists_in_index(istate, path->buf, path->len) == index_nonexistent)) + return path_none; + + excluded = is_excluded(dir, istate, path->buf, &dtype); + + /* + * Excluded? If we don't explicitly want to show + * ignored files, ignore it + */ + if (excluded && !(dir->flags & (DIR_SHOW_IGNORED|DIR_SHOW_IGNORED_TOO))) + return path_excluded; + + switch (dtype) { + default: + return path_none; + case DT_DIR: + /* + * 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. + */ + strbuf_addch(path, '/'); + return treat_directory(dir, istate, untracked, + path->buf, path->len, + baselen, excluded, pathspec); + case DT_REG: + case DT_LNK: + if (excluded) + return path_excluded; + if (pathspec && + !do_match_pathspec(istate, pathspec, path->buf, path->len, + 0 /* prefix */, NULL /* seen */, + 0 /* flags */)) + return path_none; + return path_untracked; + } } static void add_untracked(struct untracked_cache_dir *dir, const char *name) @@ -1838,7 +2240,7 @@ static int valid_cached_dir(struct dir_struct *dir, /* * prep_exclude will be called eventually on this directory, - * but it's called much later in last_exclude_matching(). We + * but it's called much later in last_matching_pattern(). We * need it now to determine the validity of the cache for this * path. The next calls will be nearly no-op, the way * prep_exclude() is designed. @@ -1882,10 +2284,17 @@ 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(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) { @@ -1921,6 +2330,40 @@ 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 @@ -1933,7 +2376,7 @@ 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 @@ -1945,6 +2388,11 @@ 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; @@ -1966,10 +2414,7 @@ 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) && - (dir->flags & DIR_SHOW_IGNORED_TOO) && - (get_dtype(cdir.de, istate, path.buf, path.len) == DT_DIR))) { + if (state == path_recurse) { struct untracked_cache_dir *ud; ud = lookup_untracked(dir->untracked, untracked, path.buf + baselen, @@ -1980,6 +2425,12 @@ static enum path_treatment read_directory_recursive(struct dir_struct *dir, check_only, stop_at_first_file, pathspec); if (subdir_state > dir_state) dir_state = subdir_state; + + if (pathspec && + !match_pathspec(istate, pathspec, path.buf, path.len, + 0 /* prefix */, NULL, + 0 /* do NOT special case dirs */)) + state = path_none; } if (check_only) { @@ -2011,33 +2462,13 @@ 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: @@ -2068,40 +2499,69 @@ 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) @@ -2248,12 +2708,12 @@ static struct untracked_cache_dir *validate_untracked_cache(struct dir_struct *d /* Validate $GIT_DIR/info/exclude and core.excludesfile */ root = dir->untracked->root; - if (oidcmp(&dir->ss_info_exclude.oid, + if (!oideq(&dir->ss_info_exclude.oid, &dir->untracked->ss_info_exclude.oid)) { invalidate_gitignore(dir->untracked, root); dir->untracked->ss_info_exclude = dir->ss_info_exclude; } - if (oidcmp(&dir->ss_excludes_file.oid, + if (!oideq(&dir->ss_excludes_file.oid, &dir->untracked->ss_excludes_file.oid)) { invalidate_gitignore(dir->untracked, root); dir->untracked->ss_excludes_file = dir->ss_excludes_file; @@ -2268,10 +2728,13 @@ 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; - uint64_t start = getnanotime(); - if (has_symlink_leading_path(path, len)) + trace_performance_enter(); + + if (has_symlink_leading_path(path, len)) { + trace_performance_leave("read directory %.*s", len, path); return dir->nr; + } untracked = validate_untracked_cache(dir, len, pathspec); if (!untracked) @@ -2285,29 +2748,7 @@ 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]; - } - } - - dir->nr = i; - } - - trace_performance_since(start, "read directory %.*s", len, path); + trace_performance_leave("read directory %.*s", len, path); if (dir->untracked) { static int force_untracked_cache = -1; static struct trace_key trace_untracked_stats = TRACE_KEY_INIT(UNTRACKED_STATS); @@ -2343,6 +2784,14 @@ int file_exists(const char *f) return lstat(f, &sb) == 0; } +int repo_file_exists(struct repository *repo, const char *path) +{ + if (repo != the_repository) + BUG("do not know how to check file existence in arbitrary repo"); + + return file_exists(path); +} + static int cmp_icase(char a, char b) { if (a == b) @@ -2465,7 +2914,7 @@ 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 */ @@ -2507,14 +2956,14 @@ void setup_standard_excludes(struct dir_struct *dir) if (!excludes_file) excludes_file = xdg_config_home("ignore"); if (excludes_file && !access_or_warn(excludes_file, R_OK, 0)) - add_excludes_from_file_1(dir, excludes_file, + add_patterns_from_file_1(dir, excludes_file, dir->untracked ? &dir->ss_excludes_file : NULL); /* per repository user preference */ if (startup_info->have_repository) { const char *path = git_path_info_exclude(); if (!access_or_warn(path, R_OK, 0)) - add_excludes_from_file_1(dir, path, + add_patterns_from_file_1(dir, path, dir->untracked ? &dir->ss_info_exclude : NULL); } } @@ -2546,18 +2995,18 @@ void clear_directory(struct dir_struct *dir) { int i, j; struct exclude_list_group *group; - struct exclude_list *el; + struct pattern_list *pl; struct exclude_stack *stk; for (i = EXC_CMDL; i <= EXC_FILE; i++) { group = &dir->exclude_list_group[i]; for (j = 0; j < group->nr; j++) { - el = &group->el[j]; + pl = &group->pl[j]; if (i == EXC_DIRS) - free((char *)el->src); - clear_exclude_list(el); + free((char *)pl->src); + clear_pattern_list(pl); } - free(group->el); + free(group->pl); } stk = dir->exclude_stack; @@ -2573,13 +3022,9 @@ struct ondisk_untracked_cache { struct stat_data info_exclude_stat; struct stat_data excludes_file_stat; uint32_t dir_flags; - unsigned char info_exclude_sha1[20]; - unsigned char excludes_file_sha1[20]; - char exclude_per_dir[FLEX_ARRAY]; }; #define ouc_offset(x) offsetof(struct ondisk_untracked_cache, x) -#define ouc_size(len) (ouc_offset(exclude_per_dir) + len + 1) struct write_data { int index; /* number of written untracked_cache_dir */ @@ -2662,20 +3107,21 @@ void write_untracked_extension(struct strbuf *out, struct untracked_cache *untra struct write_data wd; unsigned char varbuf[16]; int varint_len; - size_t len = strlen(untracked->exclude_per_dir); + const unsigned hashsz = the_hash_algo->rawsz; - FLEX_ALLOC_MEM(ouc, exclude_per_dir, untracked->exclude_per_dir, len); + ouc = xcalloc(1, sizeof(*ouc)); 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); - hashcpy(ouc->info_exclude_sha1, untracked->ss_info_exclude.oid.hash); - hashcpy(ouc->excludes_file_sha1, untracked->ss_excludes_file.oid.hash); ouc->dir_flags = htonl(untracked->dir_flags); varint_len = encode_varint(untracked->ident.len, varbuf); strbuf_add(out, varbuf, varint_len); strbuf_addbuf(out, &untracked->ident); - strbuf_add(out, ouc, ouc_size(len)); + strbuf_add(out, ouc, sizeof(*ouc)); + strbuf_add(out, untracked->ss_info_exclude.oid.hash, hashsz); + strbuf_add(out, untracked->ss_excludes_file.oid.hash, hashsz); + strbuf_add(out, untracked->exclude_per_dir, strlen(untracked->exclude_per_dir) + 1); FREE_AND_NULL(ouc); if (!untracked->root) { @@ -2760,54 +3206,49 @@ static int read_one_dir(struct untracked_cache_dir **untracked_, struct read_data *rd) { struct untracked_cache_dir ud, *untracked; - const unsigned char *next, *data = rd->data, *end = rd->end; + const unsigned char *data = rd->data, *end = rd->end; + const unsigned char *eos; unsigned int value; - int i, len; + int i; memset(&ud, 0, sizeof(ud)); - next = data; - value = decode_varint(&next); - if (next > end) + value = decode_varint(&data); + if (data > end) return -1; ud.recurse = 1; ud.untracked_alloc = value; ud.untracked_nr = value; if (ud.untracked_nr) ALLOC_ARRAY(ud.untracked, ud.untracked_nr); - data = next; - next = data; - ud.dirs_alloc = ud.dirs_nr = decode_varint(&next); - if (next > end) + ud.dirs_alloc = ud.dirs_nr = decode_varint(&data); + if (data > end) return -1; ALLOC_ARRAY(ud.dirs, ud.dirs_nr); - data = next; - len = strlen((const char *)data); - next = data + len + 1; - if (next > rd->end) + eos = memchr(data, '\0', end - data); + if (!eos || eos == end) return -1; - *untracked_ = untracked = xmalloc(st_add(sizeof(*untracked), len)); + + *untracked_ = untracked = xmalloc(st_add3(sizeof(*untracked), eos - data, 1)); memcpy(untracked, &ud, sizeof(ud)); - memcpy(untracked->name, data, len + 1); - data = next; + memcpy(untracked->name, data, eos - data + 1); + data = eos + 1; for (i = 0; i < untracked->untracked_nr; i++) { - len = strlen((const char *)data); - next = data + len + 1; - if (next > rd->end) + eos = memchr(data, '\0', end - data); + if (!eos || eos == end) return -1; - untracked->untracked[i] = xstrdup((const char*)data); - data = next; + untracked->untracked[i] = xmemdupz(data, eos - data); + data = eos + 1; } rd->ucd[rd->index++] = untracked; rd->data = data; for (i = 0; i < untracked->dirs_nr; i++) { - len = read_one_dir(untracked->dirs + i, rd); - if (len < 0) + if (read_one_dir(untracked->dirs + i, rd) < 0) return -1; } return 0; @@ -2862,6 +3303,9 @@ struct untracked_cache *read_untracked_extension(const void *data, unsigned long int ident_len; ssize_t len; const char *exclude_per_dir; + const unsigned hashsz = the_hash_algo->rawsz; + const unsigned offset = sizeof(struct ondisk_untracked_cache); + const unsigned exclude_per_dir_offset = offset + 2 * hashsz; if (sz <= 1 || end[-1] != '\0') return NULL; @@ -2873,7 +3317,7 @@ struct untracked_cache *read_untracked_extension(const void *data, unsigned long ident = (const char *)next; next += ident_len; - if (next + ouc_size(0) > end) + if (next + exclude_per_dir_offset + 1 > end) return NULL; uc = xcalloc(1, sizeof(*uc)); @@ -2881,15 +3325,15 @@ struct untracked_cache *read_untracked_extension(const void *data, unsigned long strbuf_add(&uc->ident, ident, ident_len); load_oid_stat(&uc->ss_info_exclude, next + ouc_offset(info_exclude_stat), - next + ouc_offset(info_exclude_sha1)); + next + offset); load_oid_stat(&uc->ss_excludes_file, next + ouc_offset(excludes_file_stat), - next + ouc_offset(excludes_file_sha1)); + next + offset + hashsz); uc->dir_flags = get_be32(next + ouc_offset(dir_flags)); - exclude_per_dir = (const char *)next + ouc_offset(exclude_per_dir); + exclude_per_dir = (const char *)next + exclude_per_dir_offset; uc->exclude_per_dir = xstrdup(exclude_per_dir); /* NUL after exclude_per_dir is covered by sizeof(*ouc) */ - next += ouc_size(strlen(exclude_per_dir)); + next += exclude_per_dir_offset + strlen(exclude_per_dir) + 1; if (next >= end) goto done2; |