{
unsigned int hash = 0x123;
- do {
+ while (namelen--) {
unsigned char c = *name++;
c = icase_hash(c);
hash = hash*101 + c;
- } while (--namelen);
+ }
return hash;
}
+struct dir_entry {
+ struct dir_entry *next;
+ struct dir_entry *parent;
+ struct cache_entry *ce;
+ int nr;
+ unsigned int namelen;
+};
+
+static struct dir_entry *find_dir_entry(struct index_state *istate,
+ const char *name, unsigned int namelen)
+{
+ unsigned int hash = hash_name(name, namelen);
+ struct dir_entry *dir;
+
+ for (dir = lookup_hash(hash, &istate->dir_hash); dir; dir = dir->next)
+ if (dir->namelen == namelen &&
+ !strncasecmp(dir->ce->name, name, namelen))
+ return dir;
+ return NULL;
+}
+
+static struct dir_entry *hash_dir_entry(struct index_state *istate,
+ struct cache_entry *ce, int namelen)
+{
+ /*
+ * Throw each directory component in the hash for quick lookup
+ * during a git status. Directory components are stored with their
+ * closing slash. Despite submodules being a directory, they never
+ * reach this point, because they are stored without a closing slash
+ * in index_state.name_hash (as ordinary cache_entries).
+ *
+ * Note that the cache_entry stored with the dir_entry merely
+ * supplies the name of the directory (up to dir_entry.namelen). We
+ * track the number of 'active' files in a directory in dir_entry.nr,
+ * so we can tell if the directory is still relevant, e.g. for git
+ * status. However, if cache_entries are removed, we cannot pinpoint
+ * an exact cache_entry that's still active. It is very possible that
+ * multiple dir_entries point to the same cache_entry.
+ */
+ struct dir_entry *dir;
+
+ /* get length of parent directory */
+ while (namelen > 0 && !is_dir_sep(ce->name[namelen - 1]))
+ namelen--;
+ if (namelen <= 0)
+ return NULL;
+
+ /* lookup existing entry for that directory */
+ dir = find_dir_entry(istate, ce->name, namelen);
+ if (!dir) {
+ /* not found, create it and add to hash table */
+ void **pdir;
+ unsigned int hash = hash_name(ce->name, namelen);
+
+ dir = xcalloc(1, sizeof(struct dir_entry));
+ dir->namelen = namelen;
+ dir->ce = ce;
+
+ pdir = insert_hash(hash, dir, &istate->dir_hash);
+ if (pdir) {
+ dir->next = *pdir;
+ *pdir = dir;
+ }
+
+ /* recursively add missing parent directories */
+ dir->parent = hash_dir_entry(istate, ce, namelen - 1);
+ }
+ return dir;
+}
+
+static void add_dir_entry(struct index_state *istate, struct cache_entry *ce)
+{
+ /* Add reference to the directory entry (and parents if 0). */
+ struct dir_entry *dir = hash_dir_entry(istate, ce, ce_namelen(ce));
+ while (dir && !(dir->nr++))
+ dir = dir->parent;
+}
+
+static void remove_dir_entry(struct index_state *istate, struct cache_entry *ce)
+{
+ /*
+ * Release reference to the directory entry (and parents if 0).
+ *
+ * Note: we do not remove / free the entry because there's no
+ * hash.[ch]::remove_hash and dir->next may point to other entries
+ * that are still valid, so we must not free the memory.
+ */
+ struct dir_entry *dir = hash_dir_entry(istate, ce, ce_namelen(ce));
+ while (dir && dir->nr && !(--dir->nr))
+ dir = dir->parent;
+}
+
static void hash_index_entry(struct index_state *istate, struct cache_entry *ce)
{
void **pos;
ce->next = *pos;
*pos = ce;
}
+
+ if (ignore_case && !(ce->ce_flags & CE_UNHASHED))
+ add_dir_entry(istate, ce);
}
static void lazy_init_name_hash(struct index_state *istate)
if (istate->name_hash_initialized)
return;
+ if (istate->cache_nr)
+ preallocate_hash(&istate->name_hash, istate->cache_nr);
for (nr = 0; nr < istate->cache_nr; nr++)
hash_index_entry(istate, istate->cache[nr]);
istate->name_hash_initialized = 1;
void add_name_hash(struct index_state *istate, struct cache_entry *ce)
{
+ /* if already hashed, add reference to directory entries */
+ if (ignore_case && (ce->ce_flags & CE_STATE_MASK) == CE_STATE_MASK)
+ add_dir_entry(istate, ce);
+
ce->ce_flags &= ~CE_UNHASHED;
if (istate->name_hash_initialized)
hash_index_entry(istate, ce);
}
+/*
+ * We don't actually *remove* it, we can just mark it invalid so that
+ * we won't find it in lookups.
+ *
+ * Not only would we have to search the lists (simple enough), but
+ * we'd also have to rehash other hash buckets in case this makes the
+ * hash bucket empty (common). So it's much better to just mark
+ * it.
+ */
+void remove_name_hash(struct index_state *istate, struct cache_entry *ce)
+{
+ /* if already hashed, release reference to directory entries */
+ if (ignore_case && (ce->ce_flags & CE_STATE_MASK) == CE_HASHED)
+ remove_dir_entry(istate, ce);
+
+ ce->ce_flags |= CE_UNHASHED;
+}
+
static int slow_same_name(const char *name1, int len1, const char *name2, int len2)
{
if (len1 != len2)
if (len == namelen && !cache_name_compare(name, namelen, ce->name, len))
return 1;
- return icase && slow_same_name(name, namelen, ce->name, len);
+ if (!icase)
+ return 0;
+
+ return slow_same_name(name, namelen, ce->name, len);
}
struct cache_entry *index_name_exists(struct index_state *istate, const char *name, int namelen, int icase)
}
ce = ce->next;
}
+
+ /*
+ * When looking for a directory (trailing '/'), it might be a
+ * submodule or a directory. Despite submodules being directories,
+ * they are stored in the name hash without a closing slash.
+ * When ignore_case is 1, directories are stored in a separate hash
+ * table *with* their closing slash.
+ *
+ * The side effect of this storage technique is we have need to
+ * lookup the directory in a separate hash table, and if not found
+ * remove the slash from name and perform the lookup again without
+ * the slash. If a match is made, S_ISGITLINK(ce->mode) will be
+ * true.
+ */
+ if (icase && name[namelen - 1] == '/') {
+ struct dir_entry *dir = find_dir_entry(istate, name, namelen);
+ if (dir && dir->nr)
+ return dir->ce;
+
+ ce = index_name_exists(istate, name, namelen - 1, icase);
+ if (ce && S_ISGITLINK(ce->ce_mode))
+ return ce;
+ }
return NULL;
}
+
+static int free_dir_entry(void *entry, void *unused)
+{
+ struct dir_entry *dir = entry;
+ while (dir) {
+ struct dir_entry *next = dir->next;
+ free(dir);
+ dir = next;
+ }
+ return 0;
+}
+
+void free_name_hash(struct index_state *istate)
+{
+ if (!istate->name_hash_initialized)
+ return;
+ istate->name_hash_initialized = 0;
+ if (ignore_case)
+ /* free directory entries */
+ for_each_hash(&istate->dir_hash, free_dir_entry, NULL);
+
+ free_hash(&istate->name_hash);
+ free_hash(&istate->dir_hash);
+}