* 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
*/
*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 void add_pattern_to_hashsets(struct pattern_list *pl, struct path_pattern *given)
+{
+ struct pattern_entry *translated;
+ char *truncated;
+ char *data = NULL;
+
+ 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 &&
+ !strcmp(given->pattern + given->patternlen - 2, "/*")) {
+ if (!(given->flags & PATTERN_FLAG_NEGATIVE)) {
+ /* Not a cone pattern. */
+ pl->use_cone_patterns = 0;
+ warning(_("unrecognized pattern: '%s'"), given->pattern);
+ goto clear_hashmaps;
+ }
+
+ truncated = xstrdup(given->pattern);
+ truncated[given->patternlen - 2] = 0;
+
+ 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 = xstrdup(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)
{
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,
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))
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;
+ 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;
}
- return UNDECIDED;
+ 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 path_pattern *last_matching_pattern_from_lists(
const char *dirname, int len, int baselen, int exclude,
const struct pathspec *pathspec)
{
+ int nested_repo = 0;
+
/* The "len-1" is to strip the final '/' */
switch (directory_exists_in_index(istate, dirname, len-1)) {
case index_directory:
return path_none;
case index_nonexistent:
- if (dir->flags & DIR_SKIP_NESTED_GIT) {
- int nested_repo;
+ 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 path_none;
}
+ if (nested_repo)
+ return ((dir->flags & DIR_SKIP_NESTED_GIT) ? path_none :
+ (exclude ? path_excluded : path_untracked));
if (dir->flags & DIR_SHOW_OTHER_DIRECTORIES)
break;
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;
}
struct untracked_cache_dir *untracked, int check_only,
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.
+ */
+
struct cached_dir cdir;
enum path_treatment state, subdir_state, dir_state = path_none;
struct strbuf path = STRBUF_INIT;
const char *path, int len,
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.
+ */
+
struct strbuf sb = STRBUF_INIT;
- int baselen, rc = 0;
+ int prevlen, baselen;
const char *cp;
+ struct cached_dir cdir;
+ struct dirent *de;
+ 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;
+
+ /*
+ * We need a manufactured dirent with sufficient space to store a
+ * leading directory component of path in its d_name. Here, we
+ * assume that the dirent's d_name is either declared as
+ * char d_name[BIG_ENOUGH]
+ * or that it is declared at the end of the struct as
+ * char d_name[]
+ * For either case, padding with len+1 bytes at the end will ensure
+ * sufficient storage space.
+ */
+ de = xcalloc(1, st_add3(sizeof(struct dirent), len, 1));
+ memset(&cdir, 0, sizeof(cdir));
+ cdir.de = de;
+#if defined(DT_UNKNOWN) && !defined(NO_D_TYPE_IN_DIRENT)
+ de->d_type = DT_DIR;
+#endif
baselen = 0;
+ 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);
+ memcpy(de->d_name, path+prevlen, baselen-prevlen);
+ de->d_name[baselen-prevlen] = '\0';
+ state = treat_path(dir, NULL, &cdir, istate, &sb, prevlen,
+ pathspec);
+ if (state == path_untracked &&
+ get_dtype(cdir.de, 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)) {
+ add_path_to_appropriate_result_list(dir, NULL, &cdir,
+ istate,
+ &sb, baselen,
+ pathspec, state);
+ state = path_recurse;
+ }
+
+ 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);
+
+ free(de);
strbuf_release(&sb);
- return rc;
+ return state == path_recurse;
}
static const char *get_ident_string(void)
* wanted anyway
*/
continue;
- /* fall thru */
+ /* fall through */
} else if (S_ISDIR(st.st_mode)) {
if (!remove_dir_recurse(path, flag, &kept_down))
continue; /* happy */
projects / thirdparty / git.git / blobdiff