Merge branch 'en/strmap'

A specialization of hashmap that uses a string as key has been
introduced.  Hopefully it will see wider use over time.

* en/strmap:
  shortlog: use strset from strmap.h
  Use new HASHMAP_INIT macro to simplify hashmap initialization
  strmap: take advantage of FLEXPTR_ALLOC_STR when relevant
  strmap: enable allocations to come from a mem_pool
  strmap: add a strset sub-type
  strmap: split create_entry() out of strmap_put()
  strmap: add functions facilitating use as a string->int map
  strmap: enable faster clearing and reusing of strmaps
  strmap: add more utility functions
  strmap: new utility functions
  hashmap: provide deallocation function names
  hashmap: introduce a new hashmap_partial_clear()
  hashmap: allow re-use after hashmap_free()
  hashmap: adjust spacing to fix argument alignment
  hashmap: add usage documentation explaining hashmap_free[_entries]()

Author: gitster

Makefile

@@ -1004,6 +1004,7 @@ LIB_OBJS += stable-qsort.o
 LIB_OBJS += strbuf.o
 LIB_OBJS += streaming.o
 LIB_OBJS += string-list.o
+LIB_OBJS += strmap.o
 LIB_OBJS += strvec.o
 LIB_OBJS += sub-process.o
 LIB_OBJS += submodule-config.o

add-interactive.c

@@ -557,7 +557,7 @@ static int get_modified_files(struct repository *r,
 		if (ps)
 			clear_pathspec(&rev.prune_data);
 	}
-	hashmap_free_entries(&s.file_map, struct pathname_entry, ent);
+	hashmap_clear_and_free(&s.file_map, struct pathname_entry, ent);
 	if (unmerged_count)
 		*unmerged_count = s.unmerged_count;
 	if (binary_count)

attr.c

@@ -52,13 +52,6 @@ static inline void hashmap_unlock(struct attr_hashmap *map)
 	pthread_mutex_unlock(&map->mutex);
 }
 
-/*
- * The global dictionary of all interned attributes.  This
- * is a singleton object which is shared between threads.
- * Access to this dictionary must be surrounded with a mutex.
- */
-static struct attr_hashmap g_attr_hashmap;
-
 /* The container for objects stored in "struct attr_hashmap" */
 struct attr_hash_entry {
 	struct hashmap_entry ent;
@@ -80,11 +73,14 @@ static int attr_hash_entry_cmp(const void *unused_cmp_data,
 	return (a->keylen != b->keylen) || strncmp(a->key, b->key, a->keylen);
 }
 
-/* Initialize an 'attr_hashmap' object */
-static void attr_hashmap_init(struct attr_hashmap *map)
-{
-	hashmap_init(&map->map, attr_hash_entry_cmp, NULL, 0);
-}
+/*
+ * The global dictionary of all interned attributes.  This
+ * is a singleton object which is shared between threads.
+ * Access to this dictionary must be surrounded with a mutex.
+ */
+static struct attr_hashmap g_attr_hashmap = {
+	HASHMAP_INIT(attr_hash_entry_cmp, NULL)
+};
 
 /*
  * Retrieve the 'value' stored in a hashmap given the provided 'key'.
@@ -96,9 +92,6 @@ static void *attr_hashmap_get(struct attr_hashmap *map,
 	struct attr_hash_entry k;
 	struct attr_hash_entry *e;
 
-	if (!map->map.tablesize)
-		attr_hashmap_init(map);
-
 	hashmap_entry_init(&k.ent, memhash(key, keylen));
 	k.key = key;
 	k.keylen = keylen;
@@ -114,9 +107,6 @@ static void attr_hashmap_add(struct attr_hashmap *map,
 {
 	struct attr_hash_entry *e;
 
-	if (!map->map.tablesize)
-		attr_hashmap_init(map);
-
 	e = xmalloc(sizeof(struct attr_hash_entry));
 	hashmap_entry_init(&e->ent, memhash(key, keylen));
 	e->key = key;

blame.c

@@ -435,7 +435,7 @@ static void get_fingerprint(struct fingerprint *result,
 
 static void free_fingerprint(struct fingerprint *f)
 {
-	hashmap_free(&f->map);
+	hashmap_clear(&f->map);
 	free(f->entries);
 }
 

bloom.c

@@ -229,10 +229,9 @@ struct bloom_filter *get_or_compute_bloom_filter(struct repository *r,
 	diffcore_std(&diffopt);
 
 	if (diff_queued_diff.nr <= settings->max_changed_paths) {
-		struct hashmap pathmap;
+		struct hashmap pathmap = HASHMAP_INIT(pathmap_cmp, NULL);
 		struct pathmap_hash_entry *e;
 		struct hashmap_iter iter;
-		hashmap_init(&pathmap, pathmap_cmp, NULL, 0);
 
 		for (i = 0; i < diff_queued_diff.nr; i++) {
 			const char *path = diff_queued_diff.queue[i]->two->path;
@@ -287,7 +286,7 @@ struct bloom_filter *get_or_compute_bloom_filter(struct repository *r,
 		}
 
 	cleanup:
-		hashmap_free_entries(&pathmap, struct pathmap_hash_entry, entry);
+		hashmap_clear_and_free(&pathmap, struct pathmap_hash_entry, entry);
 	} else {
 		for (i = 0; i < diff_queued_diff.nr; i++)
 			diff_free_filepair(diff_queued_diff.queue[i]);

builtin/difftool.c

@@ -342,7 +342,10 @@ static int run_dir_diff(const char *extcmd, int symlinks, const char *prefix,
 	const char *workdir, *tmp;
 	int ret = 0, i;
 	FILE *fp;
-	struct hashmap working_tree_dups, submodules, symlinks2;
+	struct hashmap working_tree_dups = HASHMAP_INIT(working_tree_entry_cmp,
+							NULL);
+	struct hashmap submodules = HASHMAP_INIT(pair_cmp, NULL);
+	struct hashmap symlinks2 = HASHMAP_INIT(pair_cmp, NULL);
 	struct hashmap_iter iter;
 	struct pair_entry *entry;
 	struct index_state wtindex;
@@ -383,10 +386,6 @@ static int run_dir_diff(const char *extcmd, int symlinks, const char *prefix,
 	rdir_len = rdir.len;
 	wtdir_len = wtdir.len;
 
-	hashmap_init(&working_tree_dups, working_tree_entry_cmp, NULL, 0);
-	hashmap_init(&submodules, pair_cmp, NULL, 0);
-	hashmap_init(&symlinks2, pair_cmp, NULL, 0);
-
 	child.no_stdin = 1;
 	child.git_cmd = 1;
 	child.use_shell = 0;

builtin/fetch.c

@@ -393,7 +393,7 @@ static void find_non_local_tags(const struct ref *refs,
 		item = refname_hash_add(&remote_refs, ref->name, &ref->old_oid);
 		string_list_insert(&remote_refs_list, ref->name);
 	}
-	hashmap_free_entries(&existing_refs, struct refname_hash_entry, ent);
+	hashmap_clear_and_free(&existing_refs, struct refname_hash_entry, ent);
 
 	/*
 	 * We may have a final lightweight tag that needs to be
@@ -428,7 +428,7 @@ static void find_non_local_tags(const struct ref *refs,
 		**tail = rm;
 		*tail = &rm->next;
 	}
-	hashmap_free_entries(&remote_refs, struct refname_hash_entry, ent);
+	hashmap_clear_and_free(&remote_refs, struct refname_hash_entry, ent);
 	string_list_clear(&remote_refs_list, 0);
 	oidset_clear(&fetch_oids);
 }
@@ -573,7 +573,7 @@ static struct ref *get_ref_map(struct remote *remote,
 		}
 	}
 	if (existing_refs_populated)
-		hashmap_free_entries(&existing_refs, struct refname_hash_entry, ent);
+		hashmap_clear_and_free(&existing_refs, struct refname_hash_entry, ent);
 
 	return ref_map;
 }

builtin/shortlog.c

@@ -10,6 +10,7 @@
 #include "shortlog.h"
 #include "parse-options.h"
 #include "trailer.h"
+#include "strmap.h"
 
 static char const * const shortlog_usage[] = {
 	N_("git shortlog [<options>] [<revision-range>] [[--] <path>...]"),
@@ -169,60 +170,6 @@ static void read_from_stdin(struct shortlog *log)
 	strbuf_release(&oneline);
 }
 
-struct strset_item {
-	struct hashmap_entry ent;
-	char value[FLEX_ARRAY];
-};
-
-struct strset {
-	struct hashmap map;
-};
-
-#define STRSET_INIT { { NULL } }
-
-static int strset_item_hashcmp(const void *hash_data,
-			       const struct hashmap_entry *entry,
-			       const struct hashmap_entry *entry_or_key,
-			       const void *keydata)
-{
-	const struct strset_item *a, *b;
-
-	a = container_of(entry, const struct strset_item, ent);
-	if (keydata)
-		return strcmp(a->value, keydata);
-
-	b = container_of(entry_or_key, const struct strset_item, ent);
-	return strcmp(a->value, b->value);
-}
-
-/*
- * Adds "str" to the set if it was not already present; returns true if it was
- * already there.
- */
-static int strset_check_and_add(struct strset *ss, const char *str)
-{
-	unsigned int hash = strhash(str);
-	struct strset_item *item;
-
-	if (!ss->map.table)
-		hashmap_init(&ss->map, strset_item_hashcmp, NULL, 0);
-
-	if (hashmap_get_from_hash(&ss->map, hash, str))
-		return 1;
-
-	FLEX_ALLOC_STR(item, value, str);
-	hashmap_entry_init(&item->ent, hash);
-	hashmap_add(&ss->map, &item->ent);
-	return 0;
-}
-
-static void strset_clear(struct strset *ss)
-{
-	if (!ss->map.table)
-		return;
-	hashmap_free_entries(&ss->map, struct strset_item, ent);
-}
-
 static void insert_records_from_trailers(struct shortlog *log,
 					 struct strset *dups,
 					 struct commit *commit,
@@ -253,7 +200,7 @@ static void insert_records_from_trailers(struct shortlog *log,
 		if (!parse_ident(log, &ident, value))
 			value = ident.buf;
 
-		if (strset_check_and_add(dups, value))
+		if (!strset_add(dups, value))
 			continue;
 		insert_one_record(log, value, oneline);
 	}
@@ -291,7 +238,7 @@ void shortlog_add_commit(struct shortlog *log, struct commit *commit)
 				      log->email ? "%aN <%aE>" : "%aN",
 				      &ident, &ctx);
 		if (!HAS_MULTI_BITS(log->groups) ||
-		    !strset_check_and_add(&dups, ident.buf))
+		    strset_add(&dups, ident.buf))
 			insert_one_record(log, ident.buf, oneline_str);
 	}
 	if (log->groups & SHORTLOG_GROUP_COMMITTER) {
@@ -300,7 +247,7 @@ void shortlog_add_commit(struct shortlog *log, struct commit *commit)
 				      log->email ? "%cN <%cE>" : "%cN",
 				      &ident, &ctx);
 		if (!HAS_MULTI_BITS(log->groups) ||
-		    !strset_check_and_add(&dups, ident.buf))
+		    strset_add(&dups, ident.buf))
 			insert_one_record(log, ident.buf, oneline_str);
 	}
 	if (log->groups & SHORTLOG_GROUP_TRAILER) {

config.c

@@ -1963,7 +1963,7 @@ void git_configset_clear(struct config_set *cs)
 		free(entry->key);
 		string_list_clear(&entry->value_list, 1);
 	}
-	hashmap_free_entries(&cs->config_hash, struct config_set_element, ent);
+	hashmap_clear_and_free(&cs->config_hash, struct config_set_element, ent);
 	cs->hash_initialized = 0;
 	free(cs->list.items);
 	cs->list.nr = 0;

diff.c

@@ -6315,9 +6315,9 @@ static void diff_flush_patch_all_file_pairs(struct diff_options *o)
 			if (o->color_moved == COLOR_MOVED_ZEBRA_DIM)
 				dim_moved_lines(o);
 
-			hashmap_free_entries(&add_lines, struct moved_entry,
+			hashmap_clear_and_free(&add_lines, struct moved_entry,
 						ent);
-			hashmap_free_entries(&del_lines, struct moved_entry,
+			hashmap_clear_and_free(&del_lines, struct moved_entry,
 						ent);
 		}