Merge branch 'kb/fast-hashmap'

Improvements to our hash table to get it to meet the needs of the
msysgit fscache project, with some nice performance improvements.

* kb/fast-hashmap:
  name-hash: retire unused index_name_exists()
  hashmap.h: use 'unsigned int' for hash-codes everywhere
  test-hashmap.c: drop unnecessary #includes
  .gitignore: test-hashmap is a generated file
  read-cache.c: fix memory leaks caused by removed cache entries
  builtin/update-index.c: cleanup update_one
  fix 'git update-index --verbose --again' output
  remove old hash.[ch] implementation
  name-hash.c: remove cache entries instead of marking them CE_UNHASHED
  name-hash.c: use new hash map implementation for cache entries
  name-hash.c: remove unreferenced directory entries
  name-hash.c: use new hash map implementation for directories
  diffcore-rename.c: use new hash map implementation
  diffcore-rename.c: simplify finding exact renames
  diffcore-rename.c: move code around to prepare for the next patch
  buitin/describe.c: use new hash map implementation
  add a hashtable implementation that supports O(1) removal
  submodule: don't access the .gitmodules cache entry after removing it

3 files changed, 43 insertions, 51 deletions

diff --git a/builtin/describe.c b/builtin/describe.c
index 7db43dae1b..dadd999c41 100644
--- a/builtin/describe.c
+++ b/builtin/describe.c
@@ -6,7 +6,7 @@
 #include "exec_cmd.h"
 #include "parse-options.h"
 #include "diff.h"
-#include "hash.h"
+#include "hashmap.h"
 #include "argv-array.h"
 
 #define SEEN		(1u << 0)
@@ -25,7 +25,7 @@ static int longformat;
 static int first_parent;
 static int abbrev = -1; /* unspecified */
 static int max_candidates = 10;
-static struct hash_table names;
+static struct hashmap names;
 static int have_util;
 static const char *pattern;
 static int always;
@@ -37,7 +37,7 @@ static const char *diff_index_args[] = {
 };
 
 struct commit_name {
-	struct commit_name *next;
+	struct hashmap_entry entry;
 	unsigned char peeled[20];
 	struct tag *tag;
 	unsigned prio:2; /* annotated tag = 2, tag = 1, head = 0 */
@@ -50,6 +50,12 @@ static const char *prio_names[] = {
 	"head", "lightweight", "annotated",
 };
 
+static int commit_name_cmp(const struct commit_name *cn1,
+		const struct commit_name *cn2, const void *peeled)
+{
+	return hashcmp(cn1->peeled, peeled ? peeled : cn2->peeled);
+}
+
 static inline unsigned int hash_sha1(const unsigned char *sha1)
 {
 	unsigned int hash;
@@ -59,21 +65,9 @@ static inline unsigned int hash_sha1(const unsigned char *sha1)
 
 static inline struct commit_name *find_commit_name(const unsigned char *peeled)
 {
-	struct commit_name *n = lookup_hash(hash_sha1(peeled), &names);
-	while (n && !!hashcmp(peeled, n->peeled))
-		n = n->next;
-	return n;
-}
-
-static int set_util(void *chain, void *data)
-{
-	struct commit_name *n;
-	for (n = chain; n; n = n->next) {
-		struct commit *c = lookup_commit_reference_gently(n->peeled, 1);
-		if (c)
-			c->util = n;
-	}
-	return 0;
+	struct commit_name key;
+	hashmap_entry_init(&key, hash_sha1(peeled));
+	return hashmap_get(&names, &key, peeled);
 }
 
 static int replace_name(struct commit_name *e,
@@ -118,16 +112,10 @@ static void add_to_known_names(const char *path,
 	struct tag *tag = NULL;
 	if (replace_name(e, prio, sha1, &tag)) {
 		if (!e) {
-			void **pos;
 			e = xmalloc(sizeof(struct commit_name));
 			hashcpy(e->peeled, peeled);
-			pos = insert_hash(hash_sha1(peeled), e, &names);
-			if (pos) {
-				e->next = *pos;
-				*pos = e;
-			} else {
-				e->next = NULL;
-			}
+			hashmap_entry_init(e, hash_sha1(peeled));
+			hashmap_add(&names, e);
 			e->path = NULL;
 		}
 		e->tag = tag;
@@ -292,7 +280,14 @@ static void describe(const char *arg, int last_one)
 		fprintf(stderr, _("searching to describe %s\n"), arg);
 
 	if (!have_util) {
-		for_each_hash(&names, set_util, NULL);
+		struct hashmap_iter iter;
+		struct commit *c;
+		struct commit_name *n = hashmap_iter_first(&names, &iter);
+		for (; n; n = hashmap_iter_next(&iter)) {
+			c = lookup_commit_reference_gently(n->peeled, 1);
+			if (c)
+				c->util = n;
+		}
 		have_util = 1;
 	}
 
@@ -463,9 +458,9 @@ int cmd_describe(int argc, const char **argv, const char *prefix)
 		return cmd_name_rev(args.argc, args.argv, prefix);
 	}
 
-	init_hash(&names);
+	hashmap_init(&names, (hashmap_cmp_fn) commit_name_cmp, 0);
 	for_each_rawref(get_name, NULL);
-	if (!names.nr && !always)
+	if (!names.size && !always)
 		die(_("No names found, cannot describe anything."));
 
 	if (argc == 0) {
diff --git a/builtin/rm.c b/builtin/rm.c
index 3a0e0eaab7..171f37c1cc 100644
--- a/builtin/rm.c
+++ b/builtin/rm.c
@@ -311,7 +311,7 @@ int cmd_rm(int argc, const char **argv, const char *prefix)
 		if (!match_pathspec_depth(&pathspec, ce->name, ce_namelen(ce), 0, seen))
 			continue;
 		ALLOC_GROW(list.entry, list.nr + 1, list.alloc);
-		list.entry[list.nr].name = ce->name;
+		list.entry[list.nr].name = xstrdup(ce->name);
 		list.entry[list.nr].is_submodule = S_ISGITLINK(ce->ce_mode);
 		if (list.entry[list.nr++].is_submodule &&
 		    !is_staging_gitmodules_ok())
diff --git a/builtin/update-index.c b/builtin/update-index.c
index e3a10d706d..00313f373a 100644
--- a/builtin/update-index.c
+++ b/builtin/update-index.c
@@ -274,36 +274,32 @@ static void chmod_path(int flip, const char *path)
 	die("git update-index: cannot chmod %cx '%s'", flip, path);
 }
 
-static void update_one(const char *path, const char *prefix, int prefix_length)
+static void update_one(const char *path)
 {
-	const char *p = prefix_path(prefix, prefix_length, path);
-	if (!verify_path(p)) {
+	if (!verify_path(path)) {
 		fprintf(stderr, "Ignoring path %s\n", path);
-		goto free_return;
+		return;
 	}
 	if (mark_valid_only) {
-		if (mark_ce_flags(p, CE_VALID, mark_valid_only == MARK_FLAG))
+		if (mark_ce_flags(path, CE_VALID, mark_valid_only == MARK_FLAG))
 			die("Unable to mark file %s", path);
-		goto free_return;
+		return;
 	}
 	if (mark_skip_worktree_only) {
-		if (mark_ce_flags(p, CE_SKIP_WORKTREE, mark_skip_worktree_only == MARK_FLAG))
+		if (mark_ce_flags(path, CE_SKIP_WORKTREE, mark_skip_worktree_only == MARK_FLAG))
 			die("Unable to mark file %s", path);
-		goto free_return;
+		return;
 	}
 
 	if (force_remove) {
-		if (remove_file_from_cache(p))
+		if (remove_file_from_cache(path))
 			die("git update-index: unable to remove %s", path);
 		report("remove '%s'", path);
-		goto free_return;
+		return;
 	}
-	if (process_path(p))
+	if (process_path(path))
 		die("Unable to process path %s", path);
 	report("add '%s'", path);
- free_return:
-	if (p < path || p > path + strlen(path))
-		free((char *)p);
 }
 
 static void read_index_info(int line_termination)
@@ -563,6 +559,7 @@ static int do_reupdate(int ac, const char **av,
 		const struct cache_entry *ce = active_cache[pos];
 		struct cache_entry *old = NULL;
 		int save_nr;
+		char *path;
 
 		if (ce_stage(ce) || !ce_path_match(ce, &pathspec))
 			continue;
@@ -579,7 +576,9 @@ static int do_reupdate(int ac, const char **av,
 		 * or worse yet 'allow_replace', active_nr may decrease.
 		 */
 		save_nr = active_nr;
-		update_one(ce->name + prefix_length, prefix, prefix_length);
+		path = xstrdup(ce->name);
+		update_one(path);
+		free(path);
 		if (save_nr != active_nr)
 			goto redo;
 	}
@@ -836,11 +835,10 @@ int cmd_update_index(int argc, const char **argv, const char *prefix)
 
 			setup_work_tree();
 			p = prefix_path(prefix, prefix_length, path);
-			update_one(p, NULL, 0);
+			update_one(p);
 			if (set_executable_bit)
 				chmod_path(set_executable_bit, p);
-			if (p < path || p > path + strlen(path))
-				free((char *)p);
+			free((char *)p);
 			ctx.argc--;
 			ctx.argv++;
 			break;
@@ -879,11 +877,10 @@ int cmd_update_index(int argc, const char **argv, const char *prefix)
 				strbuf_swap(&buf, &nbuf);
 			}
 			p = prefix_path(prefix, prefix_length, buf.buf);
-			update_one(p, NULL, 0);
+			update_one(p);
 			if (set_executable_bit)
 				chmod_path(set_executable_bit, p);
-			if (p < buf.buf || p > buf.buf + buf.len)
-				free((char *)p);
+			free((char *)p);
 		}
 		strbuf_release(&nbuf);
 		strbuf_release(&buf);