threads / patch / 61692

patcht: port helper/test-hashmap.c to unit-tests/t-hashmap.c

Subject: [GSoC][PATCH] t: port helper/test-hashmap.c to unit-tests/t-hashmap.c

## tl;dr

20 messages between Jun 28, 2024 and Aug 7, 2024. Diffs are folded; open one to read it.

replies: 19people: 5as markdown or json

Ghanshyam Thakkar· Jun 28, 2024, 12:41 UTC · lore

helper/test-hashmap.c along with t0011-hashmap.sh test the hashmap.h library. Migrate them to the unit testing framework for better debugging, runtime performance and consice code.

Along with the migration, make 'add' tests from the shellscript order agnostic in unit tests, since they iterate over entries with the same keys and we do not guarantee the order.

The helper/test-hashmap.c is still not removed because it contains a performance test meant to be run by the user directly (not used in t/perf). And it makes sense for such a utility to be a helper.

Mentored-by: Christian Couder <chriscool@tuxfamily.org>
Mentored-by: Kaartic Sivaraam <kaartic.sivaraam@gmail.com>
Signed-off-by: Ghanshyam Thakkar <shyamthakkar001@gmail.com>
---
 Makefile                 |   1 +
 t/helper/test-hashmap.c  | 100 +-----------
 t/t0011-hashmap.sh       | 260 ------------------------------
 t/unit-tests/t-hashmap.c | 339 +++++++++++++++++++++++++++++++++++++++
 4 files changed, 342 insertions(+), 358 deletions(-)
 delete mode 100755 t/t0011-hashmap.sh
 create mode 100644 t/unit-tests/t-hashmap.c
Show changes to 4 files +342 −358

Makefile, t/helper/test-hashmap.c, t/t0011-hashmap.sh, t/unit-tests/t-hashmap.c

diff --git a/Makefile b/Makefile
index 3eab701b10..74bb026610 100644
--- a/Makefile
+++ b/Makefile
@@ -1336,6 +1336,7 @@ THIRD_PARTY_SOURCES += sha1dc/%
 UNIT_TEST_PROGRAMS += t-ctype
 UNIT_TEST_PROGRAMS += t-example-decorate
 UNIT_TEST_PROGRAMS += t-hash
+UNIT_TEST_PROGRAMS += t-hashmap
 UNIT_TEST_PROGRAMS += t-mem-pool
 UNIT_TEST_PROGRAMS += t-oidtree
 UNIT_TEST_PROGRAMS += t-prio-queue
diff --git a/t/helper/test-hashmap.c b/t/helper/test-hashmap.c
index 2912899558..7b854a7030 100644
--- a/t/helper/test-hashmap.c
+++ b/t/helper/test-hashmap.c
@@ -12,11 +12,6 @@ struct test_entry
 	char key[FLEX_ARRAY];
 };
 
-static const char *get_value(const struct test_entry *e)
-{
-	return e->key + strlen(e->key) + 1;
-}
-
 static int test_entry_cmp(const void *cmp_data,
 			  const struct hashmap_entry *eptr,
 			  const struct hashmap_entry *entry_or_key,
@@ -141,30 +136,16 @@ static void perf_hashmap(unsigned int method, unsigned int rounds)
 /*
  * Read stdin line by line and print result of commands to stdout:
  *
- * hash key -> strhash(key) memhash(key) strihash(key) memihash(key)
- * put key value -> NULL / old value
- * get key -> NULL / value
- * remove key -> NULL / old value
- * iterate -> key1 value1\nkey2 value2\n...
- * size -> tablesize numentries
- *
  * perfhashmap method rounds -> test hashmap.[ch] performance
  */
 int cmd__hashmap(int argc, const char **argv)
 {
 	struct string_list parts = STRING_LIST_INIT_NODUP;
 	struct strbuf line = STRBUF_INIT;
-	int icase;
-	struct hashmap map = HASHMAP_INIT(test_entry_cmp, &icase);
-
-	/* init hash map */
-	icase = argc > 1 && !strcmp("ignorecase", argv[1]);
 
 	/* process commands from stdin */
 	while (strbuf_getline(&line, stdin) != EOF) {
 		char *cmd, *p1, *p2;
-		unsigned int hash = 0;
-		struct test_entry *entry;
 
 		/* break line into command and up to two parameters */
 		string_list_setlen(&parts, 0);
@@ -180,84 +161,8 @@ int cmd__hashmap(int argc, const char **argv)
 		cmd = parts.items[0].string;
 		p1 = parts.nr >= 1 ? parts.items[1].string : NULL;
 		p2 = parts.nr >= 2 ? parts.items[2].string : NULL;
-		if (p1)
-			hash = icase ? strihash(p1) : strhash(p1);
-
-		if (!strcmp("add", cmd) && p1 && p2) {
-
-			/* create entry with key = p1, value = p2 */
-			entry = alloc_test_entry(hash, p1, p2);
-
-			/* add to hashmap */
-			hashmap_add(&map, &entry->ent);
-
-		} else if (!strcmp("put", cmd) && p1 && p2) {
-
-			/* create entry with key = p1, value = p2 */
-			entry = alloc_test_entry(hash, p1, p2);
-
-			/* add / replace entry */
-			entry = hashmap_put_entry(&map, entry, ent);
-
-			/* print and free replaced entry, if any */
-			puts(entry ? get_value(entry) : "NULL");
-			free(entry);
-
-		} else if (!strcmp("get", cmd) && p1) {
-			/* lookup entry in hashmap */
-			entry = hashmap_get_entry_from_hash(&map, hash, p1,
-							struct test_entry, ent);
-
-			/* print result */
-			if (!entry)
-				puts("NULL");
-			hashmap_for_each_entry_from(&map, entry, ent)
-				puts(get_value(entry));
-
-		} else if (!strcmp("remove", cmd) && p1) {
-
-			/* setup static key */
-			struct hashmap_entry key;
-			struct hashmap_entry *rm;
-			hashmap_entry_init(&key, hash);
-
-			/* remove entry from hashmap */
-			rm = hashmap_remove(&map, &key, p1);
-			entry = rm ? container_of(rm, struct test_entry, ent)
-					: NULL;
-
-			/* print result and free entry*/
-			puts(entry ? get_value(entry) : "NULL");
-			free(entry);
-
-		} else if (!strcmp("iterate", cmd)) {
-			struct hashmap_iter iter;
-
-			hashmap_for_each_entry(&map, &iter, entry,
-						ent /* member name */)
-				printf("%s %s\n", entry->key, get_value(entry));
-
-		} else if (!strcmp("size", cmd)) {
-
-			/* print table sizes */
-			printf("%u %u\n", map.tablesize,
-			       hashmap_get_size(&map));
-
-		} else if (!strcmp("intern", cmd) && p1) {
-
-			/* test that strintern works */
-			const char *i1 = strintern(p1);
-			const char *i2 = strintern(p1);
-			if (strcmp(i1, p1))
-				printf("strintern(%s) returns %s\n", p1, i1);
-			else if (i1 == p1)
-				printf("strintern(%s) returns input pointer\n", p1);
-			else if (i1 != i2)
-				printf("strintern(%s) != strintern(%s)", i1, i2);
-			else
-				printf("%s\n", i1);
-
-		} else if (!strcmp("perfhashmap", cmd) && p1 && p2) {
+	
+		if (!strcmp("perfhashmap", cmd) && p1 && p2) {
 
 			perf_hashmap(atoi(p1), atoi(p2));
 
@@ -270,6 +175,5 @@ int cmd__hashmap(int argc, const char **argv)
 
 	string_list_clear(&parts, 0);
 	strbuf_release(&line);
-	hashmap_clear_and_free(&map, struct test_entry, ent);
 	return 0;
 }
diff --git a/t/t0011-hashmap.sh b/t/t0011-hashmap.sh
deleted file mode 100755
index 46e74ad107..0000000000
--- a/t/t0011-hashmap.sh
+++ /dev/null
@@ -1,260 +0,0 @@
-#!/bin/sh
-
-test_description='test hashmap and string hash functions'
-
-TEST_PASSES_SANITIZE_LEAK=true
-. ./test-lib.sh
-
-test_hashmap() {
-	echo "$1" | test-tool hashmap $3 > actual &&
-	echo "$2" > expect &&
-	test_cmp expect actual
-}
-
-test_expect_success 'put' '
-
-test_hashmap "put key1 value1
-put key2 value2
-put fooBarFrotz value3
-put foobarfrotz value4
-size" "NULL
-NULL
-NULL
-NULL
-64 4"
-
-'
-
-test_expect_success 'put (case insensitive)' '
-
-test_hashmap "put key1 value1
-put key2 value2
-put fooBarFrotz value3
-size" "NULL
-NULL
-NULL
-64 3" ignorecase
-
-'
-
-test_expect_success 'replace' '
-
-test_hashmap "put key1 value1
-put key1 value2
-put fooBarFrotz value3
-put fooBarFrotz value4
-size" "NULL
-value1
-NULL
-value3
-64 2"
-
-'
-
-test_expect_success 'replace (case insensitive)' '
-
-test_hashmap "put key1 value1
-put Key1 value2
-put fooBarFrotz value3
-put foobarfrotz value4
-size" "NULL
-value1
-NULL
-value3
-64 2" ignorecase
-
-'
-
-test_expect_success 'get' '
-
-test_hashmap "put key1 value1
-put key2 value2
-put fooBarFrotz value3
-put foobarfrotz value4
-get key1
-get key2
-get fooBarFrotz
-get notInMap" "NULL
-NULL
-NULL
-NULL
-value1
-value2
-value3
-NULL"
-
-'
-
-test_expect_success 'get (case insensitive)' '
-
-test_hashmap "put key1 value1
-put key2 value2
-put fooBarFrotz value3
-get Key1
-get keY2
-get foobarfrotz
-get notInMap" "NULL
-NULL
-NULL
-value1
-value2
-value3
-NULL" ignorecase
-
-'
-
-test_expect_success 'add' '
-
-test_hashmap "add key1 value1
-add key1 value2
-add fooBarFrotz value3
-add fooBarFrotz value4
-get key1
-get fooBarFrotz
-get notInMap" "value2
-value1
-value4
-value3
-NULL"
-
-'
-
-test_expect_success 'add (case insensitive)' '
-
-test_hashmap "add key1 value1
-add Key1 value2
-add fooBarFrotz value3
-add foobarfrotz value4
-get key1
-get Foobarfrotz
-get notInMap" "value2
-value1
-value4
-value3
-NULL" ignorecase
-
-'
-
-test_expect_success 'remove' '
-
-test_hashmap "put key1 value1
-put key2 value2
-put fooBarFrotz value3
-remove key1
-remove key2
-remove notInMap
-size" "NULL
-NULL
-NULL
-value1
-value2
-NULL
-64 1"
-
-'
-
-test_expect_success 'remove (case insensitive)' '
-
-test_hashmap "put key1 value1
-put key2 value2
-put fooBarFrotz value3
-remove Key1
-remove keY2
-remove notInMap
-size" "NULL
-NULL
-NULL
-value1
-value2
-NULL
-64 1" ignorecase
-
-'
-
-test_expect_success 'iterate' '
-	test-tool hashmap >actual.raw <<-\EOF &&
-	put key1 value1
-	put key2 value2
-	put fooBarFrotz value3
-	iterate
-	EOF
-
-	cat >expect <<-\EOF &&
-	NULL
-	NULL
-	NULL
-	fooBarFrotz value3
-	key1 value1
-	key2 value2
-	EOF
-
-	sort <actual.raw >actual &&
-	test_cmp expect actual
-'
-
-test_expect_success 'iterate (case insensitive)' '
-	test-tool hashmap ignorecase >actual.raw <<-\EOF &&
-	put key1 value1
-	put key2 value2
-	put fooBarFrotz value3
-	iterate
-	EOF
-
-	cat >expect <<-\EOF &&
-	NULL
-	NULL
-	NULL
-	fooBarFrotz value3
-	key1 value1
-	key2 value2
-	EOF
-
-	sort <actual.raw >actual &&
-	test_cmp expect actual
-'
-
-test_expect_success 'grow / shrink' '
-
-	rm -f in &&
-	rm -f expect &&
-	for n in $(test_seq 51)
-	do
-		echo put key$n value$n >> in &&
-		echo NULL >> expect || return 1
-	done &&
-	echo size >> in &&
-	echo 64 51 >> expect &&
-	echo put key52 value52 >> in &&
-	echo NULL >> expect &&
-	echo size >> in &&
-	echo 256 52 >> expect &&
-	for n in $(test_seq 12)
-	do
-		echo remove key$n >> in &&
-		echo value$n >> expect || return 1
-	done &&
-	echo size >> in &&
-	echo 256 40 >> expect &&
-	echo remove key40 >> in &&
-	echo value40 >> expect &&
-	echo size >> in &&
-	echo 64 39 >> expect &&
-	test-tool hashmap <in >out &&
-	test_cmp expect out
-
-'
-
-test_expect_success 'string interning' '
-
-test_hashmap "intern value1
-intern Value1
-intern value2
-intern value2
-" "value1
-Value1
-value2
-value2"
-
-'
-
-test_done
diff --git a/t/unit-tests/t-hashmap.c b/t/unit-tests/t-hashmap.c
new file mode 100644
index 0000000000..628aba5231
--- /dev/null
+++ b/t/unit-tests/t-hashmap.c
@@ -0,0 +1,339 @@
+#include "test-lib.h"
+#include "hashmap.h"
+#include "strbuf.h"
+
+struct test_entry {
+	int padding; /* hashmap entry no longer needs to be the first member */
+	struct hashmap_entry ent;
+	/* key and value as two \0-terminated strings */
+	char key[FLEX_ARRAY];
+};
+
+static int test_entry_cmp(const void *cmp_data,
+			  const struct hashmap_entry *eptr,
+			  const struct hashmap_entry *entry_or_key,
+			  const void *keydata)
+{
+	const int ignore_case = cmp_data ? *((int *)cmp_data) : 0;
+	const struct test_entry *e1, *e2;
+	const char *key = keydata;
+
+	e1 = container_of(eptr, const struct test_entry, ent);
+	e2 = container_of(entry_or_key, const struct test_entry, ent);
+
+	if (ignore_case)
+		return strcasecmp(e1->key, key ? key : e2->key);
+	else
+		return strcmp(e1->key, key ? key : e2->key);
+}
+
+static const char *get_value(const struct test_entry *e)
+{
+	return e->key + strlen(e->key) + 1;
+}
+
+static struct test_entry *alloc_test_entry(unsigned int ignore_case,
+					   const char *key, const char *value)
+{
+	size_t klen = strlen(key);
+	size_t vlen = strlen(value);
+	unsigned int hash = ignore_case ? strihash(key) : strhash(key);
+	struct test_entry *entry = xmalloc(st_add4(sizeof(*entry), klen, vlen, 2));
+
+	hashmap_entry_init(&entry->ent, hash);
+	memcpy(entry->key, key, klen + 1);
+	memcpy(entry->key + klen + 1, value, vlen + 1);
+	return entry;
+}
+
+static struct test_entry *get_test_entry(struct hashmap *map,
+					 unsigned int ignore_case, const char *key)
+{
+	return hashmap_get_entry_from_hash(
+		map, ignore_case ? strihash(key) : strhash(key), key,
+		struct test_entry, ent);
+}
+
+static int key_val_contains(const char *key_val[][3], size_t n,
+			    struct test_entry *entry)
+{
+	for (size_t i = 0; i < n; i++) {
+		if (!strcmp(entry->key, key_val[i][0]) &&
+		    !strcmp(get_value(entry), key_val[i][1])) {
+			if (!strcmp(key_val[i][2], "USED"))
+				return 2;
+			key_val[i][2] = "USED";
+			return 0;
+		}
+	}
+	return 1;
+}
+
+static void setup(void (*f)(struct hashmap *map, int ignore_case),
+		  int ignore_case)
+{
+	struct hashmap map = HASHMAP_INIT(test_entry_cmp, &ignore_case);
+	f(&map, ignore_case);
+	hashmap_clear_and_free(&map, struct test_entry, ent);
+}
+
+static void t_put(struct hashmap *map, int ignore_case)
+{
+	struct test_entry *entry;
+	const char *key_val[][2] = { { "key1", "value1" },
+				   { "key2", "value2" },
+				   { "fooBarFrotz", "value3" } };
+
+	for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
+		entry = alloc_test_entry(ignore_case, key_val[i][0], key_val[i][1]);
+		check(hashmap_put_entry(map, entry, ent) == NULL);
+	}
+
+	entry = alloc_test_entry(ignore_case, "foobarfrotz", "value4");
+	entry = hashmap_put_entry(map, entry, ent);
+	check(ignore_case ? entry != NULL : entry == NULL);
+	free(entry);
+
+	check_int(map->tablesize, ==, 64);
+	check_int(hashmap_get_size(map), ==, ignore_case ? 3 : 4);
+}
+
+static void t_replace(struct hashmap *map, int ignore_case)
+{
+	struct test_entry *entry;
+
+	entry = alloc_test_entry(ignore_case, "key1", "value1");
+	check(hashmap_put_entry(map, entry, ent) == NULL);
+
+	entry = alloc_test_entry(ignore_case, ignore_case ? "Key1" : "key1",
+				 "value2");
+	entry = hashmap_put_entry(map, entry, ent);
+	if (check(entry != NULL))
+		check_str(get_value(entry), "value1");
+	free(entry);
+
+	entry = alloc_test_entry(ignore_case, "fooBarFrotz", "value3");
+	check(hashmap_put_entry(map, entry, ent) == NULL);
+
+	entry = alloc_test_entry(ignore_case,
+				 ignore_case ? "foobarfrotz" : "fooBarFrotz",
+				 "value4");
+	entry = hashmap_put_entry(map, entry, ent);
+	if (check(entry != NULL))
+		check_str(get_value(entry), "value3");
+	free(entry);
+}
+
+static void t_get(struct hashmap *map, int ignore_case)
+{
+	struct test_entry *entry;
+	const char *key_val[][2] = { { "key1", "value1" },
+				   { "key2", "value2" },
+				   { "fooBarFrotz", "value3" },
+				   { ignore_case ? "key4" : "foobarfrotz", "value4" } };
+	const char *query[][2] = {
+		{ ignore_case ? "Key1" : "key1", "value1" },
+		{ ignore_case ? "keY2" : "key2", "value2" },
+		{ ignore_case ? "foobarfrotz" : "fooBarFrotz", "value3" }
+	};
+
+	for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
+		entry = alloc_test_entry(ignore_case, key_val[i][0], key_val[i][1]);
+		check(hashmap_put_entry(map, entry, ent) == NULL);
+	}
+
+	for (size_t i = 0; i < ARRAY_SIZE(query); i++) {
+		entry = get_test_entry(map, ignore_case, query[i][0]);
+		if (check(entry != NULL))
+			check_str(get_value(entry), query[i][1]);
+	}
+
+	check(get_test_entry(map, ignore_case, "notInMap") == NULL);
+}
+
+static void t_add(struct hashmap *map, int ignore_case)
+{
+	struct test_entry *entry;
+	const char *key_val[][3] = {
+		{ "key1", "value2", "UNUSED" },
+		{ ignore_case ? "Key1" : "key1", "value2", "UNUSED" },
+		{ "fooBarFrotz", "value3", "UNUSED" },
+		{ ignore_case ? "Foobarfrotz" : "fooBarFrotz", "value4", "UNUSED" }
+	};
+
+	for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
+		entry = alloc_test_entry(ignore_case, key_val[i][0], key_val[i][1]);
+		hashmap_add(map, &entry->ent);
+	}
+
+	hashmap_for_each_entry_from(map, entry, ent)
+	{
+		int ret;
+		if (!check_int((ret = key_val_contains(key_val, ARRAY_SIZE(key_val),
+						       entry)), ==, 0)) {
+			switch (ret) {
+				case 1:
+					test_msg("found entry was not given in the input\n"
+						 "    key: %s\n  value: %s",
+						 entry->key, get_value(entry));
+					break;
+				case 2:
+					test_msg("duplicate entry detected\n"
+						 "    key: %s\n  value: %s",
+						 entry->key, get_value(entry));
+					break;
+			}
+		}
+	}
+
+	check(get_test_entry(map, ignore_case, "notInMap") == NULL);
+}
+
+static void t_remove(struct hashmap *map, int ignore_case)
+{
+	struct test_entry *entry, *removed;
+	const char *key_val[][2] = { { "key1", "value1" },
+				   { "key2", "value2" },
+				   { "fooBarFrotz", "value3" } };
+	const char *remove[][2] = { { ignore_case ? "Key1" : "key1", "value1" },
+				    { ignore_case ? "keY2" : "key2", "value2" } };
+
+	for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
+		entry = alloc_test_entry(ignore_case, key_val[i][0], key_val[i][1]);
+		check(hashmap_put_entry(map, entry, ent) == NULL);
+	}
+
+	for (size_t i = 0; i < ARRAY_SIZE(remove); i++) {
+		entry = alloc_test_entry(ignore_case, remove[i][0], "");
+		removed = hashmap_remove_entry(map, entry, ent, remove[i][0]);
+		if (check(removed != NULL))
+			check_str(get_value(removed), remove[i][1]);
+		free(entry);
+		free(removed);
+	}
+
+	entry = alloc_test_entry(ignore_case, "notInMap", "");
+	check(hashmap_remove_entry(map, entry, ent, "notInMap") == NULL);
+	free(entry);
+}
+
+static void t_iterate(struct hashmap *map, int ignore_case)
+{
+	struct test_entry *entry;
+	struct hashmap_iter iter;
+	const char *key_val[][3] = { { "key1", "value1", "UNUSED" },
+				     { "key2", "value2", "UNUSED" },
+				     { "fooBarFrotz", "value3", "UNUSED" } };
+
+	for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
+		entry = alloc_test_entry(ignore_case, key_val[i][0], key_val[i][1]);
+		check(hashmap_put_entry(map, entry, ent) == NULL);
+	}
+
+	hashmap_for_each_entry(map, &iter, entry, ent /* member name */)
+	{
+		int ret;
+		if (!check_int((ret = key_val_contains(key_val, ARRAY_SIZE(key_val),
+					      entry)), ==, 0)) {
+			switch (ret) {
+				case 1:
+					test_msg("found entry was not given in the input\n"
+						 "    key: %s\n  value: %s",
+						 entry->key, get_value(entry));
+					break;
+				case 2:
+					test_msg("duplicate entry detected\n"
+						 "    key: %s\n  value: %s",
+						 entry->key, get_value(entry));
+					break;
+			}
+		}
+	}
+	check_int(hashmap_get_size(map), ==, 3);
+}
+
+static void t_alloc(struct hashmap *map, int ignore_case)
+{
+	struct test_entry *entry, *removed;
+
+	for (int i = 1; i <= 51; i++) {
+		char *key = xstrfmt("key%d", i);
+		char *value = xstrfmt("value%d", i);
+		entry = alloc_test_entry(ignore_case, key, value);
+		check(hashmap_put_entry(map, entry, ent) == NULL);
+		free(key);
+		free(value);
+	}
+	check_int(map->tablesize, ==, 64);
+	check_int(hashmap_get_size(map), ==, 51);
+
+	entry = alloc_test_entry(ignore_case, "key52", "value52");
+	check(hashmap_put_entry(map, entry, ent) == NULL);
+	check_int(map->tablesize, ==, 256);
+	check_int(hashmap_get_size(map), ==, 52);
+
+	for (int i = 1; i <= 12; i++) {
+		char *key = xstrfmt("key%d", i);
+		char *value = xstrfmt("value%d", i);
+
+		entry = alloc_test_entry(ignore_case, key, "");
+		removed = hashmap_remove_entry(map, entry, ent, key);
+		if (check(removed != NULL))
+			check_str(value, get_value(removed));
+		free(key);
+		free(value);
+		free(entry);
+		free(removed);
+	}
+	check_int(map->tablesize, ==, 256);
+	check_int(hashmap_get_size(map), ==, 40);
+
+	entry = alloc_test_entry(ignore_case, "key40", "");
+	removed = hashmap_remove_entry(map, entry, ent, "key40");
+	if (check(removed != NULL))
+		check_str("value40", get_value(removed));
+	check_int(map->tablesize, ==, 64);
+	check_int(hashmap_get_size(map), ==, 39);
+	free(entry);
+	free(removed);
+}
+
+static void t_intern(struct hashmap *map, int ignore_case)
+{
+	const char *values[] = { "value1", "Value1", "value2", "value2" };
+
+	for (size_t i = 0; i < ARRAY_SIZE(values); i++) {
+		const char *i1 = strintern(values[i]);
+		const char *i2 = strintern(values[i]);
+
+		if (!check(!strcmp(i1, values[i])))
+			test_msg("strintern(%s) returns %s\n", values[i], i1);
+		else if (!check(i1 != values[i]))
+			test_msg("strintern(%s) returns input pointer\n",
+				 values[i]);
+		else if (!check(i1 == i2))
+			test_msg("address('%s') != address('%s'), so strintern('%s') != strintern('%s')",
+				 i1, i2, values[i], values[i]);
+		else
+			check_str(i1, values[i]);
+	}
+}
+
+int cmd_main(int argc UNUSED, const char **argv UNUSED)
+{
+	TEST(setup(t_put, 0), "put works");
+	TEST(setup(t_put, 1), "put (case insensitive) works");
+	TEST(setup(t_replace, 0), "replace works");
+	TEST(setup(t_replace, 1), "replace (case insensitive) works");
+	TEST(setup(t_get, 0), "get works");
+	TEST(setup(t_get, 1), "get (case insensitive) works");
+	TEST(setup(t_add, 0), "add works");
+	TEST(setup(t_add, 1), "add (case insensitive) works");
+	TEST(setup(t_remove, 0), "remove works");
+	TEST(setup(t_remove, 1), "remove (case insensitive) works");
+	TEST(setup(t_iterate, 0), "iterate works");
+	TEST(setup(t_iterate, 1), "iterate (case insensitive) works");
+	TEST(setup(t_alloc, 0), "grow / shrink works");
+	TEST(setup(t_intern, 0), "string interning works");
+	return test_done();
+}
-- 
2.45.2
Ghanshyam Thakkar· Jul 8, 2024, 16:15 UTC · re: Ghanshyam Thakkar · lore

[GSoC][PATCH v2] t: port helper/test-hashmap.c to unit-tests/t-hashmap.c

helper/test-hashmap.c along with t0011-hashmap.sh test the hashmap.h library. Migrate them to the unit testing framework for better debugging, runtime performance and consice code.

Along with the migration, make 'add' tests from the shellscript order agnostic in unit tests, since they iterate over entries with the same keys and we do not guarantee the order.

The helper/test-hashmap.c is still not removed because it contains a performance test meant to be run by the user directly (not used in t/perf). And it makes sense for such a utility to be a helper.

Mentored-by: Christian Couder <chriscool@tuxfamily.org>
Mentored-by: Kaartic Sivaraam <kaartic.sivaraam@gmail.com>
Signed-off-by: Ghanshyam Thakkar <shyamthakkar001@gmail.com>
---
The changes in v2 are inspired from the review of another similar
test t-oidmap: https://lore.kernel.org/git/16e06a6d-5fd0-4132-9d82-5c6f13b7f9ed@gmail.com/

The v2 also includes some formatting corrections and one of the testcases, t_add(), was changed to be more similar to the original.

Range-diff against v1:
1:  f095025d1b ! 1:  bbb4f2f23e t: port helper/test-hashmap.c to unit-tests/t-hashmap.c
    @@ t/unit-tests/t-hashmap.c (new)
     +		  int ignore_case)
     +{
     +	struct hashmap map = HASHMAP_INIT(test_entry_cmp, &ignore_case);
    ++
     +	f(&map, ignore_case);
     +	hashmap_clear_and_free(&map, struct test_entry, ent);
     +}
    @@ t/unit-tests/t-hashmap.c (new)
     +{
     +	struct test_entry *entry;
     +	const char *key_val[][2] = { { "key1", "value1" },
    -+				   { "key2", "value2" },
    -+				   { "fooBarFrotz", "value3" } };
    ++				     { "key2", "value2" },
    ++				     { "fooBarFrotz", "value3" } };
     +
     +	for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
     +		entry = alloc_test_entry(ignore_case, key_val[i][0], key_val[i][1]);
    @@ t/unit-tests/t-hashmap.c (new)
     +	free(entry);
     +
     +	check_int(map->tablesize, ==, 64);
    -+	check_int(hashmap_get_size(map), ==, ignore_case ? 3 : 4);
    ++	check_int(hashmap_get_size(map), ==,
    ++		  ignore_case ? ARRAY_SIZE(key_val) : ARRAY_SIZE(key_val) + 1);
     +}
     +
     +static void t_replace(struct hashmap *map, int ignore_case)
    @@ t/unit-tests/t-hashmap.c (new)
     +{
     +	struct test_entry *entry;
     +	const char *key_val[][2] = { { "key1", "value1" },
    -+				   { "key2", "value2" },
    -+				   { "fooBarFrotz", "value3" },
    -+				   { ignore_case ? "key4" : "foobarfrotz", "value4" } };
    ++				     { "key2", "value2" },
    ++				     { "fooBarFrotz", "value3" },
    ++				     { ignore_case ? "key4" : "foobarfrotz", "value4" } };
     +	const char *query[][2] = {
     +		{ ignore_case ? "Key1" : "key1", "value1" },
     +		{ ignore_case ? "keY2" : "key2", "value2" },
    @@ t/unit-tests/t-hashmap.c (new)
     +{
     +	struct test_entry *entry;
     +	const char *key_val[][3] = {
    -+		{ "key1", "value2", "UNUSED" },
    ++		{ "key1", "value1", "UNUSED" },
     +		{ ignore_case ? "Key1" : "key1", "value2", "UNUSED" },
     +		{ "fooBarFrotz", "value3", "UNUSED" },
     +		{ ignore_case ? "Foobarfrotz" : "fooBarFrotz", "value4", "UNUSED" }
     +	};
    ++	const char *queries[] = { "key1",
    ++				  ignore_case ? "Foobarfrotz" : "fooBarFrotz" };
     +
     +	for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
     +		entry = alloc_test_entry(ignore_case, key_val[i][0], key_val[i][1]);
     +		hashmap_add(map, &entry->ent);
     +	}
     +
    -+	hashmap_for_each_entry_from(map, entry, ent)
    -+	{
    -+		int ret;
    -+		if (!check_int((ret = key_val_contains(key_val, ARRAY_SIZE(key_val),
    -+						       entry)), ==, 0)) {
    -+			switch (ret) {
    ++	for (size_t i = 0; i < ARRAY_SIZE(queries); i++) {
    ++		int count = 0;
    ++		entry = hashmap_get_entry_from_hash(map,
    ++			ignore_case ? strihash(queries[i]) :
    ++				      strhash(queries[i]),
    ++			queries[i], struct test_entry, ent);
    ++
    ++		hashmap_for_each_entry_from(map, entry, ent)
    ++		{
    ++			int ret;
    ++			if (!check_int((ret = key_val_contains(
    ++						key_val, ARRAY_SIZE(key_val),
    ++						entry)), ==, 0)) {
    ++				switch (ret) {
     +				case 1:
     +					test_msg("found entry was not given in the input\n"
     +						 "    key: %s\n  value: %s",
    @@ t/unit-tests/t-hashmap.c (new)
     +						 "    key: %s\n  value: %s",
     +						 entry->key, get_value(entry));
     +					break;
    ++				}
    ++			} else {
    ++				count++;
     +			}
     +		}
    ++		check_int(count, ==, 2);
     +	}
    -+
    ++	check_int(hashmap_get_size(map), ==, ARRAY_SIZE(key_val));
     +	check(get_test_entry(map, ignore_case, "notInMap") == NULL);
     +}
     +
    @@ t/unit-tests/t-hashmap.c (new)
     +{
     +	struct test_entry *entry, *removed;
     +	const char *key_val[][2] = { { "key1", "value1" },
    -+				   { "key2", "value2" },
    -+				   { "fooBarFrotz", "value3" } };
    ++				     { "key2", "value2" },
    ++				     { "fooBarFrotz", "value3" } };
     +	const char *remove[][2] = { { ignore_case ? "Key1" : "key1", "value1" },
     +				    { ignore_case ? "keY2" : "key2", "value2" } };
     +
    @@ t/unit-tests/t-hashmap.c (new)
     +	const char *key_val[][3] = { { "key1", "value1", "UNUSED" },
     +				     { "key2", "value2", "UNUSED" },
     +				     { "fooBarFrotz", "value3", "UNUSED" } };
    ++	int count = 0;
     +
     +	for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
     +		entry = alloc_test_entry(ignore_case, key_val[i][0], key_val[i][1]);
    @@ t/unit-tests/t-hashmap.c (new)
     +	{
     +		int ret;
     +		if (!check_int((ret = key_val_contains(key_val, ARRAY_SIZE(key_val),
    -+					      entry)), ==, 0)) {
    ++						       entry)), ==, 0)) {
     +			switch (ret) {
    -+				case 1:
    -+					test_msg("found entry was not given in the input\n"
    -+						 "    key: %s\n  value: %s",
    -+						 entry->key, get_value(entry));
    -+					break;
    -+				case 2:
    -+					test_msg("duplicate entry detected\n"
    -+						 "    key: %s\n  value: %s",
    -+						 entry->key, get_value(entry));
    -+					break;
    ++			case 1:
    ++				test_msg("found entry was not given in the input\n"
    ++					 "    key: %s\n  value: %s",
    ++					 entry->key, get_value(entry));
    ++				break;
    ++			case 2:
    ++				test_msg("duplicate entry detected\n"
    ++					 "    key: %s\n  value: %s",
    ++					 entry->key, get_value(entry));
    ++				break;
     +			}
    ++		} else {
    ++			count++;
     +		}
     +	}
    -+	check_int(hashmap_get_size(map), ==, 3);
    ++	check_int(count, ==, ARRAY_SIZE(key_val));
    ++	check_int(hashmap_get_size(map), ==, ARRAY_SIZE(key_val));
     +}
     +
     +static void t_alloc(struct hashmap *map, int ignore_case)
 Makefile                 |   1 +
 t/helper/test-hashmap.c  | 100 +----------
 t/t0011-hashmap.sh       | 260 ----------------------------
 t/unit-tests/t-hashmap.c | 359 +++++++++++++++++++++++++++++++++++++++
 4 files changed, 362 insertions(+), 358 deletions(-)
 delete mode 100755 t/t0011-hashmap.sh
 create mode 100644 t/unit-tests/t-hashmap.c
Show changes to 4 files +362 −358

Makefile, t/helper/test-hashmap.c, t/t0011-hashmap.sh, t/unit-tests/t-hashmap.c

diff --git a/Makefile b/Makefile
index 3eab701b10..74bb026610 100644
--- a/Makefile
+++ b/Makefile
@@ -1336,6 +1336,7 @@ THIRD_PARTY_SOURCES += sha1dc/%
 UNIT_TEST_PROGRAMS += t-ctype
 UNIT_TEST_PROGRAMS += t-example-decorate
 UNIT_TEST_PROGRAMS += t-hash
+UNIT_TEST_PROGRAMS += t-hashmap
 UNIT_TEST_PROGRAMS += t-mem-pool
 UNIT_TEST_PROGRAMS += t-oidtree
 UNIT_TEST_PROGRAMS += t-prio-queue
diff --git a/t/helper/test-hashmap.c b/t/helper/test-hashmap.c
index 2912899558..7b854a7030 100644
--- a/t/helper/test-hashmap.c
+++ b/t/helper/test-hashmap.c
@@ -12,11 +12,6 @@ struct test_entry
 	char key[FLEX_ARRAY];
 };
 
-static const char *get_value(const struct test_entry *e)
-{
-	return e->key + strlen(e->key) + 1;
-}
-
 static int test_entry_cmp(const void *cmp_data,
 			  const struct hashmap_entry *eptr,
 			  const struct hashmap_entry *entry_or_key,
@@ -141,30 +136,16 @@ static void perf_hashmap(unsigned int method, unsigned int rounds)
 /*
  * Read stdin line by line and print result of commands to stdout:
  *
- * hash key -> strhash(key) memhash(key) strihash(key) memihash(key)
- * put key value -> NULL / old value
- * get key -> NULL / value
- * remove key -> NULL / old value
- * iterate -> key1 value1\nkey2 value2\n...
- * size -> tablesize numentries
- *
  * perfhashmap method rounds -> test hashmap.[ch] performance
  */
 int cmd__hashmap(int argc, const char **argv)
 {
 	struct string_list parts = STRING_LIST_INIT_NODUP;
 	struct strbuf line = STRBUF_INIT;
-	int icase;
-	struct hashmap map = HASHMAP_INIT(test_entry_cmp, &icase);
-
-	/* init hash map */
-	icase = argc > 1 && !strcmp("ignorecase", argv[1]);
 
 	/* process commands from stdin */
 	while (strbuf_getline(&line, stdin) != EOF) {
 		char *cmd, *p1, *p2;
-		unsigned int hash = 0;
-		struct test_entry *entry;
 
 		/* break line into command and up to two parameters */
 		string_list_setlen(&parts, 0);
@@ -180,84 +161,8 @@ int cmd__hashmap(int argc, const char **argv)
 		cmd = parts.items[0].string;
 		p1 = parts.nr >= 1 ? parts.items[1].string : NULL;
 		p2 = parts.nr >= 2 ? parts.items[2].string : NULL;
-		if (p1)
-			hash = icase ? strihash(p1) : strhash(p1);
-
-		if (!strcmp("add", cmd) && p1 && p2) {
-
-			/* create entry with key = p1, value = p2 */
-			entry = alloc_test_entry(hash, p1, p2);
-
-			/* add to hashmap */
-			hashmap_add(&map, &entry->ent);
-
-		} else if (!strcmp("put", cmd) && p1 && p2) {
-
-			/* create entry with key = p1, value = p2 */
-			entry = alloc_test_entry(hash, p1, p2);
-
-			/* add / replace entry */
-			entry = hashmap_put_entry(&map, entry, ent);
-
-			/* print and free replaced entry, if any */
-			puts(entry ? get_value(entry) : "NULL");
-			free(entry);
-
-		} else if (!strcmp("get", cmd) && p1) {
-			/* lookup entry in hashmap */
-			entry = hashmap_get_entry_from_hash(&map, hash, p1,
-							struct test_entry, ent);
-
-			/* print result */
-			if (!entry)
-				puts("NULL");
-			hashmap_for_each_entry_from(&map, entry, ent)
-				puts(get_value(entry));
-
-		} else if (!strcmp("remove", cmd) && p1) {
-
-			/* setup static key */
-			struct hashmap_entry key;
-			struct hashmap_entry *rm;
-			hashmap_entry_init(&key, hash);
-
-			/* remove entry from hashmap */
-			rm = hashmap_remove(&map, &key, p1);
-			entry = rm ? container_of(rm, struct test_entry, ent)
-					: NULL;
-
-			/* print result and free entry*/
-			puts(entry ? get_value(entry) : "NULL");
-			free(entry);
-
-		} else if (!strcmp("iterate", cmd)) {
-			struct hashmap_iter iter;
-
-			hashmap_for_each_entry(&map, &iter, entry,
-						ent /* member name */)
-				printf("%s %s\n", entry->key, get_value(entry));
-
-		} else if (!strcmp("size", cmd)) {
-
-			/* print table sizes */
-			printf("%u %u\n", map.tablesize,
-			       hashmap_get_size(&map));
-
-		} else if (!strcmp("intern", cmd) && p1) {
-
-			/* test that strintern works */
-			const char *i1 = strintern(p1);
-			const char *i2 = strintern(p1);
-			if (strcmp(i1, p1))
-				printf("strintern(%s) returns %s\n", p1, i1);
-			else if (i1 == p1)
-				printf("strintern(%s) returns input pointer\n", p1);
-			else if (i1 != i2)
-				printf("strintern(%s) != strintern(%s)", i1, i2);
-			else
-				printf("%s\n", i1);
-
-		} else if (!strcmp("perfhashmap", cmd) && p1 && p2) {
+	
+		if (!strcmp("perfhashmap", cmd) && p1 && p2) {
 
 			perf_hashmap(atoi(p1), atoi(p2));
 
@@ -270,6 +175,5 @@ int cmd__hashmap(int argc, const char **argv)
 
 	string_list_clear(&parts, 0);
 	strbuf_release(&line);
-	hashmap_clear_and_free(&map, struct test_entry, ent);
 	return 0;
 }
diff --git a/t/t0011-hashmap.sh b/t/t0011-hashmap.sh
deleted file mode 100755
index 46e74ad107..0000000000
--- a/t/t0011-hashmap.sh
+++ /dev/null
@@ -1,260 +0,0 @@
-#!/bin/sh
-
-test_description='test hashmap and string hash functions'
-
-TEST_PASSES_SANITIZE_LEAK=true
-. ./test-lib.sh
-
-test_hashmap() {
-	echo "$1" | test-tool hashmap $3 > actual &&
-	echo "$2" > expect &&
-	test_cmp expect actual
-}
-
-test_expect_success 'put' '
-
-test_hashmap "put key1 value1
-put key2 value2
-put fooBarFrotz value3
-put foobarfrotz value4
-size" "NULL
-NULL
-NULL
-NULL
-64 4"
-
-'
-
-test_expect_success 'put (case insensitive)' '
-
-test_hashmap "put key1 value1
-put key2 value2
-put fooBarFrotz value3
-size" "NULL
-NULL
-NULL
-64 3" ignorecase
-
-'
-
-test_expect_success 'replace' '
-
-test_hashmap "put key1 value1
-put key1 value2
-put fooBarFrotz value3
-put fooBarFrotz value4
-size" "NULL
-value1
-NULL
-value3
-64 2"
-
-'
-
-test_expect_success 'replace (case insensitive)' '
-
-test_hashmap "put key1 value1
-put Key1 value2
-put fooBarFrotz value3
-put foobarfrotz value4
-size" "NULL
-value1
-NULL
-value3
-64 2" ignorecase
-
-'
-
-test_expect_success 'get' '
-
-test_hashmap "put key1 value1
-put key2 value2
-put fooBarFrotz value3
-put foobarfrotz value4
-get key1
-get key2
-get fooBarFrotz
-get notInMap" "NULL
-NULL
-NULL
-NULL
-value1
-value2
-value3
-NULL"
-
-'
-
-test_expect_success 'get (case insensitive)' '
-
-test_hashmap "put key1 value1
-put key2 value2
-put fooBarFrotz value3
-get Key1
-get keY2
-get foobarfrotz
-get notInMap" "NULL
-NULL
-NULL
-value1
-value2
-value3
-NULL" ignorecase
-
-'
-
-test_expect_success 'add' '
-
-test_hashmap "add key1 value1
-add key1 value2
-add fooBarFrotz value3
-add fooBarFrotz value4
-get key1
-get fooBarFrotz
-get notInMap" "value2
-value1
-value4
-value3
-NULL"
-
-'
-
-test_expect_success 'add (case insensitive)' '
-
-test_hashmap "add key1 value1
-add Key1 value2
-add fooBarFrotz value3
-add foobarfrotz value4
-get key1
-get Foobarfrotz
-get notInMap" "value2
-value1
-value4
-value3
-NULL" ignorecase
-
-'
-
-test_expect_success 'remove' '
-
-test_hashmap "put key1 value1
-put key2 value2
-put fooBarFrotz value3
-remove key1
-remove key2
-remove notInMap
-size" "NULL
-NULL
-NULL
-value1
-value2
-NULL
-64 1"
-
-'
-
-test_expect_success 'remove (case insensitive)' '
-
-test_hashmap "put key1 value1
-put key2 value2
-put fooBarFrotz value3
-remove Key1
-remove keY2
-remove notInMap
-size" "NULL
-NULL
-NULL
-value1
-value2
-NULL
-64 1" ignorecase
-
-'
-
-test_expect_success 'iterate' '
-	test-tool hashmap >actual.raw <<-\EOF &&
-	put key1 value1
-	put key2 value2
-	put fooBarFrotz value3
-	iterate
-	EOF
-
-	cat >expect <<-\EOF &&
-	NULL
-	NULL
-	NULL
-	fooBarFrotz value3
-	key1 value1
-	key2 value2
-	EOF
-
-	sort <actual.raw >actual &&
-	test_cmp expect actual
-'
-
-test_expect_success 'iterate (case insensitive)' '
-	test-tool hashmap ignorecase >actual.raw <<-\EOF &&
-	put key1 value1
-	put key2 value2
-	put fooBarFrotz value3
-	iterate
-	EOF
-
-	cat >expect <<-\EOF &&
-	NULL
-	NULL
-	NULL
-	fooBarFrotz value3
-	key1 value1
-	key2 value2
-	EOF
-
-	sort <actual.raw >actual &&
-	test_cmp expect actual
-'
-
-test_expect_success 'grow / shrink' '
-
-	rm -f in &&
-	rm -f expect &&
-	for n in $(test_seq 51)
-	do
-		echo put key$n value$n >> in &&
-		echo NULL >> expect || return 1
-	done &&
-	echo size >> in &&
-	echo 64 51 >> expect &&
-	echo put key52 value52 >> in &&
-	echo NULL >> expect &&
-	echo size >> in &&
-	echo 256 52 >> expect &&
-	for n in $(test_seq 12)
-	do
-		echo remove key$n >> in &&
-		echo value$n >> expect || return 1
-	done &&
-	echo size >> in &&
-	echo 256 40 >> expect &&
-	echo remove key40 >> in &&
-	echo value40 >> expect &&
-	echo size >> in &&
-	echo 64 39 >> expect &&
-	test-tool hashmap <in >out &&
-	test_cmp expect out
-
-'
-
-test_expect_success 'string interning' '
-
-test_hashmap "intern value1
-intern Value1
-intern value2
-intern value2
-" "value1
-Value1
-value2
-value2"
-
-'
-
-test_done
diff --git a/t/unit-tests/t-hashmap.c b/t/unit-tests/t-hashmap.c
new file mode 100644
index 0000000000..1c951fcfd8
--- /dev/null
+++ b/t/unit-tests/t-hashmap.c
@@ -0,0 +1,359 @@
+#include "test-lib.h"
+#include "hashmap.h"
+#include "strbuf.h"
+
+struct test_entry {
+	int padding; /* hashmap entry no longer needs to be the first member */
+	struct hashmap_entry ent;
+	/* key and value as two \0-terminated strings */
+	char key[FLEX_ARRAY];
+};
+
+static int test_entry_cmp(const void *cmp_data,
+			  const struct hashmap_entry *eptr,
+			  const struct hashmap_entry *entry_or_key,
+			  const void *keydata)
+{
+	const int ignore_case = cmp_data ? *((int *)cmp_data) : 0;
+	const struct test_entry *e1, *e2;
+	const char *key = keydata;
+
+	e1 = container_of(eptr, const struct test_entry, ent);
+	e2 = container_of(entry_or_key, const struct test_entry, ent);
+
+	if (ignore_case)
+		return strcasecmp(e1->key, key ? key : e2->key);
+	else
+		return strcmp(e1->key, key ? key : e2->key);
+}
+
+static const char *get_value(const struct test_entry *e)
+{
+	return e->key + strlen(e->key) + 1;
+}
+
+static struct test_entry *alloc_test_entry(unsigned int ignore_case,
+					   const char *key, const char *value)
+{
+	size_t klen = strlen(key);
+	size_t vlen = strlen(value);
+	unsigned int hash = ignore_case ? strihash(key) : strhash(key);
+	struct test_entry *entry = xmalloc(st_add4(sizeof(*entry), klen, vlen, 2));
+
+	hashmap_entry_init(&entry->ent, hash);
+	memcpy(entry->key, key, klen + 1);
+	memcpy(entry->key + klen + 1, value, vlen + 1);
+	return entry;
+}
+
+static struct test_entry *get_test_entry(struct hashmap *map,
+					 unsigned int ignore_case, const char *key)
+{
+	return hashmap_get_entry_from_hash(
+		map, ignore_case ? strihash(key) : strhash(key), key,
+		struct test_entry, ent);
+}
+
+static int key_val_contains(const char *key_val[][3], size_t n,
+			    struct test_entry *entry)
+{
+	for (size_t i = 0; i < n; i++) {
+		if (!strcmp(entry->key, key_val[i][0]) &&
+		    !strcmp(get_value(entry), key_val[i][1])) {
+			if (!strcmp(key_val[i][2], "USED"))
+				return 2;
+			key_val[i][2] = "USED";
+			return 0;
+		}
+	}
+	return 1;
+}
+
+static void setup(void (*f)(struct hashmap *map, int ignore_case),
+		  int ignore_case)
+{
+	struct hashmap map = HASHMAP_INIT(test_entry_cmp, &ignore_case);
+
+	f(&map, ignore_case);
+	hashmap_clear_and_free(&map, struct test_entry, ent);
+}
+
+static void t_put(struct hashmap *map, int ignore_case)
+{
+	struct test_entry *entry;
+	const char *key_val[][2] = { { "key1", "value1" },
+				     { "key2", "value2" },
+				     { "fooBarFrotz", "value3" } };
+
+	for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
+		entry = alloc_test_entry(ignore_case, key_val[i][0], key_val[i][1]);
+		check(hashmap_put_entry(map, entry, ent) == NULL);
+	}
+
+	entry = alloc_test_entry(ignore_case, "foobarfrotz", "value4");
+	entry = hashmap_put_entry(map, entry, ent);
+	check(ignore_case ? entry != NULL : entry == NULL);
+	free(entry);
+
+	check_int(map->tablesize, ==, 64);
+	check_int(hashmap_get_size(map), ==,
+		  ignore_case ? ARRAY_SIZE(key_val) : ARRAY_SIZE(key_val) + 1);
+}
+
+static void t_replace(struct hashmap *map, int ignore_case)
+{
+	struct test_entry *entry;
+
+	entry = alloc_test_entry(ignore_case, "key1", "value1");
+	check(hashmap_put_entry(map, entry, ent) == NULL);
+
+	entry = alloc_test_entry(ignore_case, ignore_case ? "Key1" : "key1",
+				 "value2");
+	entry = hashmap_put_entry(map, entry, ent);
+	if (check(entry != NULL))
+		check_str(get_value(entry), "value1");
+	free(entry);
+
+	entry = alloc_test_entry(ignore_case, "fooBarFrotz", "value3");
+	check(hashmap_put_entry(map, entry, ent) == NULL);
+
+	entry = alloc_test_entry(ignore_case,
+				 ignore_case ? "foobarfrotz" : "fooBarFrotz",
+				 "value4");
+	entry = hashmap_put_entry(map, entry, ent);
+	if (check(entry != NULL))
+		check_str(get_value(entry), "value3");
+	free(entry);
+}
+
+static void t_get(struct hashmap *map, int ignore_case)
+{
+	struct test_entry *entry;
+	const char *key_val[][2] = { { "key1", "value1" },
+				     { "key2", "value2" },
+				     { "fooBarFrotz", "value3" },
+				     { ignore_case ? "key4" : "foobarfrotz", "value4" } };
+	const char *query[][2] = {
+		{ ignore_case ? "Key1" : "key1", "value1" },
+		{ ignore_case ? "keY2" : "key2", "value2" },
+		{ ignore_case ? "foobarfrotz" : "fooBarFrotz", "value3" }
+	};
+
+	for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
+		entry = alloc_test_entry(ignore_case, key_val[i][0], key_val[i][1]);
+		check(hashmap_put_entry(map, entry, ent) == NULL);
+	}
+
+	for (size_t i = 0; i < ARRAY_SIZE(query); i++) {
+		entry = get_test_entry(map, ignore_case, query[i][0]);
+		if (check(entry != NULL))
+			check_str(get_value(entry), query[i][1]);
+	}
+
+	check(get_test_entry(map, ignore_case, "notInMap") == NULL);
+}
+
+static void t_add(struct hashmap *map, int ignore_case)
+{
+	struct test_entry *entry;
+	const char *key_val[][3] = {
+		{ "key1", "value1", "UNUSED" },
+		{ ignore_case ? "Key1" : "key1", "value2", "UNUSED" },
+		{ "fooBarFrotz", "value3", "UNUSED" },
+		{ ignore_case ? "Foobarfrotz" : "fooBarFrotz", "value4", "UNUSED" }
+	};
+	const char *queries[] = { "key1",
+				  ignore_case ? "Foobarfrotz" : "fooBarFrotz" };
+
+	for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
+		entry = alloc_test_entry(ignore_case, key_val[i][0], key_val[i][1]);
+		hashmap_add(map, &entry->ent);
+	}
+
+	for (size_t i = 0; i < ARRAY_SIZE(queries); i++) {
+		int count = 0;
+		entry = hashmap_get_entry_from_hash(map,
+			ignore_case ? strihash(queries[i]) :
+				      strhash(queries[i]),
+			queries[i], struct test_entry, ent);
+
+		hashmap_for_each_entry_from(map, entry, ent)
+		{
+			int ret;
+			if (!check_int((ret = key_val_contains(
+						key_val, ARRAY_SIZE(key_val),
+						entry)), ==, 0)) {
+				switch (ret) {
+				case 1:
+					test_msg("found entry was not given in the input\n"
+						 "    key: %s\n  value: %s",
+						 entry->key, get_value(entry));
+					break;
+				case 2:
+					test_msg("duplicate entry detected\n"
+						 "    key: %s\n  value: %s",
+						 entry->key, get_value(entry));
+					break;
+				}
+			} else {
+				count++;
+			}
+		}
+		check_int(count, ==, 2);
+	}
+	check_int(hashmap_get_size(map), ==, ARRAY_SIZE(key_val));
+	check(get_test_entry(map, ignore_case, "notInMap") == NULL);
+}
+
+static void t_remove(struct hashmap *map, int ignore_case)
+{
+	struct test_entry *entry, *removed;
+	const char *key_val[][2] = { { "key1", "value1" },
+				     { "key2", "value2" },
+				     { "fooBarFrotz", "value3" } };
+	const char *remove[][2] = { { ignore_case ? "Key1" : "key1", "value1" },
+				    { ignore_case ? "keY2" : "key2", "value2" } };
+
+	for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
+		entry = alloc_test_entry(ignore_case, key_val[i][0], key_val[i][1]);
+		check(hashmap_put_entry(map, entry, ent) == NULL);
+	}
+
+	for (size_t i = 0; i < ARRAY_SIZE(remove); i++) {
+		entry = alloc_test_entry(ignore_case, remove[i][0], "");
+		removed = hashmap_remove_entry(map, entry, ent, remove[i][0]);
+		if (check(removed != NULL))
+			check_str(get_value(removed), remove[i][1]);
+		free(entry);
+		free(removed);
+	}
+
+	entry = alloc_test_entry(ignore_case, "notInMap", "");
+	check(hashmap_remove_entry(map, entry, ent, "notInMap") == NULL);
+	free(entry);
+}
+
+static void t_iterate(struct hashmap *map, int ignore_case)
+{
+	struct test_entry *entry;
+	struct hashmap_iter iter;
+	const char *key_val[][3] = { { "key1", "value1", "UNUSED" },
+				     { "key2", "value2", "UNUSED" },
+				     { "fooBarFrotz", "value3", "UNUSED" } };
+	int count = 0;
+
+	for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
+		entry = alloc_test_entry(ignore_case, key_val[i][0], key_val[i][1]);
+		check(hashmap_put_entry(map, entry, ent) == NULL);
+	}
+
+	hashmap_for_each_entry(map, &iter, entry, ent /* member name */)
+	{
+		int ret;
+		if (!check_int((ret = key_val_contains(key_val, ARRAY_SIZE(key_val),
+						       entry)), ==, 0)) {
+			switch (ret) {
+			case 1:
+				test_msg("found entry was not given in the input\n"
+					 "    key: %s\n  value: %s",
+					 entry->key, get_value(entry));
+				break;
+			case 2:
+				test_msg("duplicate entry detected\n"
+					 "    key: %s\n  value: %s",
+					 entry->key, get_value(entry));
+				break;
+			}
+		} else {
+			count++;
+		}
+	}
+	check_int(count, ==, ARRAY_SIZE(key_val));
+	check_int(hashmap_get_size(map), ==, ARRAY_SIZE(key_val));
+}
+
+static void t_alloc(struct hashmap *map, int ignore_case)
+{
+	struct test_entry *entry, *removed;
+
+	for (int i = 1; i <= 51; i++) {
+		char *key = xstrfmt("key%d", i);
+		char *value = xstrfmt("value%d", i);
+		entry = alloc_test_entry(ignore_case, key, value);
+		check(hashmap_put_entry(map, entry, ent) == NULL);
+		free(key);
+		free(value);
+	}
+	check_int(map->tablesize, ==, 64);
+	check_int(hashmap_get_size(map), ==, 51);
+
+	entry = alloc_test_entry(ignore_case, "key52", "value52");
+	check(hashmap_put_entry(map, entry, ent) == NULL);
+	check_int(map->tablesize, ==, 256);
+	check_int(hashmap_get_size(map), ==, 52);
+
+	for (int i = 1; i <= 12; i++) {
+		char *key = xstrfmt("key%d", i);
+		char *value = xstrfmt("value%d", i);
+
+		entry = alloc_test_entry(ignore_case, key, "");
+		removed = hashmap_remove_entry(map, entry, ent, key);
+		if (check(removed != NULL))
+			check_str(value, get_value(removed));
+		free(key);
+		free(value);
+		free(entry);
+		free(removed);
+	}
+	check_int(map->tablesize, ==, 256);
+	check_int(hashmap_get_size(map), ==, 40);
+
+	entry = alloc_test_entry(ignore_case, "key40", "");
+	removed = hashmap_remove_entry(map, entry, ent, "key40");
+	if (check(removed != NULL))
+		check_str("value40", get_value(removed));
+	check_int(map->tablesize, ==, 64);
+	check_int(hashmap_get_size(map), ==, 39);
+	free(entry);
+	free(removed);
+}
+
+static void t_intern(struct hashmap *map, int ignore_case)
+{
+	const char *values[] = { "value1", "Value1", "value2", "value2" };
+
+	for (size_t i = 0; i < ARRAY_SIZE(values); i++) {
+		const char *i1 = strintern(values[i]);
+		const char *i2 = strintern(values[i]);
+
+		if (!check(!strcmp(i1, values[i])))
+			test_msg("strintern(%s) returns %s\n", values[i], i1);
+		else if (!check(i1 != values[i]))
+			test_msg("strintern(%s) returns input pointer\n",
+				 values[i]);
+		else if (!check(i1 == i2))
+			test_msg("address('%s') != address('%s'), so strintern('%s') != strintern('%s')",
+				 i1, i2, values[i], values[i]);
+		else
+			check_str(i1, values[i]);
+	}
+}
+
+int cmd_main(int argc UNUSED, const char **argv UNUSED)
+{
+	TEST(setup(t_put, 0), "put works");
+	TEST(setup(t_put, 1), "put (case insensitive) works");
+	TEST(setup(t_replace, 0), "replace works");
+	TEST(setup(t_replace, 1), "replace (case insensitive) works");
+	TEST(setup(t_get, 0), "get works");
+	TEST(setup(t_get, 1), "get (case insensitive) works");
+	TEST(setup(t_add, 0), "add works");
+	TEST(setup(t_add, 1), "add (case insensitive) works");
+	TEST(setup(t_remove, 0), "remove works");
+	TEST(setup(t_remove, 1), "remove (case insensitive) works");
+	TEST(setup(t_iterate, 0), "iterate works");
+	TEST(setup(t_iterate, 1), "iterate (case insensitive) works");
+	TEST(setup(t_alloc, 0), "grow / shrink works");
+	TEST(setup(t_intern, 0), "string interning works");
+	return test_done();
+}
-- 
2.45.2
Josh Steadmon· Jul 9, 2024, 19:34 UTC · re: Ghanshyam Thakkar · lore

Re: [GSoC][PATCH v2] t: port helper/test-hashmap.c to unit-tests/t-hashmap.c

This looks like a good conversion to me. There are a few small improvements that could be made, but mostly LGTM. Comments are inline below.

On 2024.07.08 21:45, Ghanshyam Thakkar wrote:
> helper/test-hashmap.c along with t0011-hashmap.sh test the hashmap.h
> library. Migrate them to the unit testing framework for better
> debugging, runtime performance and consice code.
Typo: s/consice/concise/
Show 25 quoted lines
> Along with the migration, make 'add' tests from the shellscript order
> agnostic in unit tests, since they iterate over entries with the same
> keys and we do not guarantee the order.
> 
> The helper/test-hashmap.c is still not removed because it contains a
> performance test meant to be run by the user directly (not used in
> t/perf). And it makes sense for such a utility to be a helper.
> 
> Mentored-by: Christian Couder <chriscool@tuxfamily.org>
> Mentored-by: Kaartic Sivaraam <kaartic.sivaraam@gmail.com>
> Signed-off-by: Ghanshyam Thakkar <shyamthakkar001@gmail.com>
> ---
> The changes in v2 are inspired from the review of another similar
> test t-oidmap: https://lore.kernel.org/git/16e06a6d-5fd0-4132-9d82-5c6f13b7f9ed@gmail.com/
> 
> The v2 also includes some formatting corrections and one of the
> testcases, t_add(), was changed to be more similar to the original.
> 
>  Makefile                 |   1 +
>  t/helper/test-hashmap.c  | 100 +----------
>  t/t0011-hashmap.sh       | 260 ----------------------------
>  t/unit-tests/t-hashmap.c | 359 +++++++++++++++++++++++++++++++++++++++
>  4 files changed, 362 insertions(+), 358 deletions(-)
>  delete mode 100755 t/t0011-hashmap.sh
>  create mode 100644 t/unit-tests/t-hashmap.c
[snip]
Show 53 quoted lines
> diff --git a/t/unit-tests/t-hashmap.c b/t/unit-tests/t-hashmap.c
> new file mode 100644
> index 0000000000..1c951fcfd8
> --- /dev/null
> +++ b/t/unit-tests/t-hashmap.c
> @@ -0,0 +1,359 @@
> +#include "test-lib.h"
> +#include "hashmap.h"
> +#include "strbuf.h"
> +
> +struct test_entry {
> +	int padding; /* hashmap entry no longer needs to be the first member */
> +	struct hashmap_entry ent;
> +	/* key and value as two \0-terminated strings */
> +	char key[FLEX_ARRAY];
> +};
> +
> +static int test_entry_cmp(const void *cmp_data,
> +			  const struct hashmap_entry *eptr,
> +			  const struct hashmap_entry *entry_or_key,
> +			  const void *keydata)
> +{
> +	const int ignore_case = cmp_data ? *((int *)cmp_data) : 0;
> +	const struct test_entry *e1, *e2;
> +	const char *key = keydata;
> +
> +	e1 = container_of(eptr, const struct test_entry, ent);
> +	e2 = container_of(entry_or_key, const struct test_entry, ent);
> +
> +	if (ignore_case)
> +		return strcasecmp(e1->key, key ? key : e2->key);
> +	else
> +		return strcmp(e1->key, key ? key : e2->key);
> +}
> +
> +static const char *get_value(const struct test_entry *e)
> +{
> +	return e->key + strlen(e->key) + 1;
> +}
> +
> +static struct test_entry *alloc_test_entry(unsigned int ignore_case,
> +					   const char *key, const char *value)
> +{
> +	size_t klen = strlen(key);
> +	size_t vlen = strlen(value);
> +	unsigned int hash = ignore_case ? strihash(key) : strhash(key);
> +	struct test_entry *entry = xmalloc(st_add4(sizeof(*entry), klen, vlen, 2));
> +
> +	hashmap_entry_init(&entry->ent, hash);
> +	memcpy(entry->key, key, klen + 1);
> +	memcpy(entry->key + klen + 1, value, vlen + 1);
> +	return entry;
> +}

So we're duplicating `struct test_entry`, `test_entry_cmp()`, and `alloc_test_entry()`, which have (almost) identical definitions in t/helper/test-hashmap.c. I wonder if it's worth splitting these into a separate .c file. Maybe it's too much of a pain to add Makefile rules to share objects across the test helper and the unit tests. Something to keep in mind I guess, if we find that we want to share more code than this.

Show 31 quoted lines
> +static struct test_entry *get_test_entry(struct hashmap *map,
> +					 unsigned int ignore_case, const char *key)
> +{
> +	return hashmap_get_entry_from_hash(
> +		map, ignore_case ? strihash(key) : strhash(key), key,
> +		struct test_entry, ent);
> +}
> +
> +static int key_val_contains(const char *key_val[][3], size_t n,
> +			    struct test_entry *entry)
> +{
> +	for (size_t i = 0; i < n; i++) {
> +		if (!strcmp(entry->key, key_val[i][0]) &&
> +		    !strcmp(get_value(entry), key_val[i][1])) {
> +			if (!strcmp(key_val[i][2], "USED"))
> +				return 2;
> +			key_val[i][2] = "USED";
> +			return 0;
> +		}
> +	}
> +	return 1;
> +}
> +
> +static void setup(void (*f)(struct hashmap *map, int ignore_case),
> +		  int ignore_case)
> +{
> +	struct hashmap map = HASHMAP_INIT(test_entry_cmp, &ignore_case);
> +
> +	f(&map, ignore_case);
> +	hashmap_clear_and_free(&map, struct test_entry, ent);
> +}

As I mentioned in my review [1] on René's TEST_RUN series, I don't think we get much value out of having a setup + callback approach when the setup is minimal. Would you consider rewriting a v2 using TEST_RUN once that is ready in `next`?

[1] https://lore.kernel.org/git/tswyfparvchgi7qxrjxbx4eb7cohypzekjqzbnkbffsesaiazs@vtewtz7o6twi/
Show 21 quoted lines
> +static void t_put(struct hashmap *map, int ignore_case)
> +{
> +	struct test_entry *entry;
> +	const char *key_val[][2] = { { "key1", "value1" },
> +				     { "key2", "value2" },
> +				     { "fooBarFrotz", "value3" } };
> +
> +	for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
> +		entry = alloc_test_entry(ignore_case, key_val[i][0], key_val[i][1]);
> +		check(hashmap_put_entry(map, entry, ent) == NULL);
> +	}
> +
> +	entry = alloc_test_entry(ignore_case, "foobarfrotz", "value4");
> +	entry = hashmap_put_entry(map, entry, ent);
> +	check(ignore_case ? entry != NULL : entry == NULL);
> +	free(entry);
> +
> +	check_int(map->tablesize, ==, 64);
> +	check_int(hashmap_get_size(map), ==,
> +		  ignore_case ? ARRAY_SIZE(key_val) : ARRAY_SIZE(key_val) + 1);
> +}

Ahhh, so you're using the same function for both case-sensitive and -insensitive tests. So I guess TEST_RUN isn't useful here after all. Personally I'd still rather get rid of setup(), but I don't feel super strongly about it.

Show 71 quoted lines
> +static void t_replace(struct hashmap *map, int ignore_case)
> +{
> +	struct test_entry *entry;
> +
> +	entry = alloc_test_entry(ignore_case, "key1", "value1");
> +	check(hashmap_put_entry(map, entry, ent) == NULL);
> +
> +	entry = alloc_test_entry(ignore_case, ignore_case ? "Key1" : "key1",
> +				 "value2");
> +	entry = hashmap_put_entry(map, entry, ent);
> +	if (check(entry != NULL))
> +		check_str(get_value(entry), "value1");
> +	free(entry);
> +
> +	entry = alloc_test_entry(ignore_case, "fooBarFrotz", "value3");
> +	check(hashmap_put_entry(map, entry, ent) == NULL);
> +
> +	entry = alloc_test_entry(ignore_case,
> +				 ignore_case ? "foobarfrotz" : "fooBarFrotz",
> +				 "value4");
> +	entry = hashmap_put_entry(map, entry, ent);
> +	if (check(entry != NULL))
> +		check_str(get_value(entry), "value3");
> +	free(entry);
> +}
> +
> +static void t_get(struct hashmap *map, int ignore_case)
> +{
> +	struct test_entry *entry;
> +	const char *key_val[][2] = { { "key1", "value1" },
> +				     { "key2", "value2" },
> +				     { "fooBarFrotz", "value3" },
> +				     { ignore_case ? "key4" : "foobarfrotz", "value4" } };
> +	const char *query[][2] = {
> +		{ ignore_case ? "Key1" : "key1", "value1" },
> +		{ ignore_case ? "keY2" : "key2", "value2" },
> +		{ ignore_case ? "foobarfrotz" : "fooBarFrotz", "value3" }
> +	};
> +
> +	for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
> +		entry = alloc_test_entry(ignore_case, key_val[i][0], key_val[i][1]);
> +		check(hashmap_put_entry(map, entry, ent) == NULL);
> +	}
> +
> +	for (size_t i = 0; i < ARRAY_SIZE(query); i++) {
> +		entry = get_test_entry(map, ignore_case, query[i][0]);
> +		if (check(entry != NULL))
> +			check_str(get_value(entry), query[i][1]);
> +	}
> +
> +	check(get_test_entry(map, ignore_case, "notInMap") == NULL);
> +}
> +
> +static void t_add(struct hashmap *map, int ignore_case)
> +{
> +	struct test_entry *entry;
> +	const char *key_val[][3] = {
> +		{ "key1", "value1", "UNUSED" },
> +		{ ignore_case ? "Key1" : "key1", "value2", "UNUSED" },
> +		{ "fooBarFrotz", "value3", "UNUSED" },
> +		{ ignore_case ? "Foobarfrotz" : "fooBarFrotz", "value4", "UNUSED" }
> +	};
> +	const char *queries[] = { "key1",
> +				  ignore_case ? "Foobarfrotz" : "fooBarFrotz" };
> +
> +	for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
> +		entry = alloc_test_entry(ignore_case, key_val[i][0], key_val[i][1]);
> +		hashmap_add(map, &entry->ent);
> +	}
> +
> +	for (size_t i = 0; i < ARRAY_SIZE(queries); i++) {

Since we only have one query, can we remove the loop and simplify the following block of code?

Also (here and elsewhere), it might be less confusing to say "UNSEEN" / "SEEN" instead of "UNUSED" / "USED". The latter makes it sound to me like there's some API requirement to have a 3-item array that we don't actually need, but in this case those fields are actually used in key_val_contains() to track duplicates.

Show 61 quoted lines
> +		int count = 0;
> +		entry = hashmap_get_entry_from_hash(map,
> +			ignore_case ? strihash(queries[i]) :
> +				      strhash(queries[i]),
> +			queries[i], struct test_entry, ent);
> +
> +		hashmap_for_each_entry_from(map, entry, ent)
> +		{
> +			int ret;
> +			if (!check_int((ret = key_val_contains(
> +						key_val, ARRAY_SIZE(key_val),
> +						entry)), ==, 0)) {
> +				switch (ret) {
> +				case 1:
> +					test_msg("found entry was not given in the input\n"
> +						 "    key: %s\n  value: %s",
> +						 entry->key, get_value(entry));
> +					break;
> +				case 2:
> +					test_msg("duplicate entry detected\n"
> +						 "    key: %s\n  value: %s",
> +						 entry->key, get_value(entry));
> +					break;
> +				}
> +			} else {
> +				count++;
> +			}
> +		}
> +		check_int(count, ==, 2);
> +	}
> +	check_int(hashmap_get_size(map), ==, ARRAY_SIZE(key_val));
> +	check(get_test_entry(map, ignore_case, "notInMap") == NULL);
> +}
> +
> +static void t_remove(struct hashmap *map, int ignore_case)
> +{
> +	struct test_entry *entry, *removed;
> +	const char *key_val[][2] = { { "key1", "value1" },
> +				     { "key2", "value2" },
> +				     { "fooBarFrotz", "value3" } };
> +	const char *remove[][2] = { { ignore_case ? "Key1" : "key1", "value1" },
> +				    { ignore_case ? "keY2" : "key2", "value2" } };
> +
> +	for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
> +		entry = alloc_test_entry(ignore_case, key_val[i][0], key_val[i][1]);
> +		check(hashmap_put_entry(map, entry, ent) == NULL);
> +	}
> +
> +	for (size_t i = 0; i < ARRAY_SIZE(remove); i++) {
> +		entry = alloc_test_entry(ignore_case, remove[i][0], "");
> +		removed = hashmap_remove_entry(map, entry, ent, remove[i][0]);
> +		if (check(removed != NULL))
> +			check_str(get_value(removed), remove[i][1]);
> +		free(entry);
> +		free(removed);
> +	}
> +
> +	entry = alloc_test_entry(ignore_case, "notInMap", "");
> +	check(hashmap_remove_entry(map, entry, ent, "notInMap") == NULL);
> +	free(entry);
> +}

Is there a reason why you don't check the table size as the shell test did? (similar to what you have in t_put())

Show 94 quoted lines
> +static void t_iterate(struct hashmap *map, int ignore_case)
> +{
> +	struct test_entry *entry;
> +	struct hashmap_iter iter;
> +	const char *key_val[][3] = { { "key1", "value1", "UNUSED" },
> +				     { "key2", "value2", "UNUSED" },
> +				     { "fooBarFrotz", "value3", "UNUSED" } };
> +	int count = 0;
> +
> +	for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
> +		entry = alloc_test_entry(ignore_case, key_val[i][0], key_val[i][1]);
> +		check(hashmap_put_entry(map, entry, ent) == NULL);
> +	}
> +
> +	hashmap_for_each_entry(map, &iter, entry, ent /* member name */)
> +	{
> +		int ret;
> +		if (!check_int((ret = key_val_contains(key_val, ARRAY_SIZE(key_val),
> +						       entry)), ==, 0)) {
> +			switch (ret) {
> +			case 1:
> +				test_msg("found entry was not given in the input\n"
> +					 "    key: %s\n  value: %s",
> +					 entry->key, get_value(entry));
> +				break;
> +			case 2:
> +				test_msg("duplicate entry detected\n"
> +					 "    key: %s\n  value: %s",
> +					 entry->key, get_value(entry));
> +				break;
> +			}
> +		} else {
> +			count++;
> +		}
> +	}
> +	check_int(count, ==, ARRAY_SIZE(key_val));
> +	check_int(hashmap_get_size(map), ==, ARRAY_SIZE(key_val));
> +}
> +
> +static void t_alloc(struct hashmap *map, int ignore_case)
> +{
> +	struct test_entry *entry, *removed;
> +
> +	for (int i = 1; i <= 51; i++) {
> +		char *key = xstrfmt("key%d", i);
> +		char *value = xstrfmt("value%d", i);
> +		entry = alloc_test_entry(ignore_case, key, value);
> +		check(hashmap_put_entry(map, entry, ent) == NULL);
> +		free(key);
> +		free(value);
> +	}
> +	check_int(map->tablesize, ==, 64);
> +	check_int(hashmap_get_size(map), ==, 51);
> +
> +	entry = alloc_test_entry(ignore_case, "key52", "value52");
> +	check(hashmap_put_entry(map, entry, ent) == NULL);
> +	check_int(map->tablesize, ==, 256);
> +	check_int(hashmap_get_size(map), ==, 52);
> +
> +	for (int i = 1; i <= 12; i++) {
> +		char *key = xstrfmt("key%d", i);
> +		char *value = xstrfmt("value%d", i);
> +
> +		entry = alloc_test_entry(ignore_case, key, "");
> +		removed = hashmap_remove_entry(map, entry, ent, key);
> +		if (check(removed != NULL))
> +			check_str(value, get_value(removed));
> +		free(key);
> +		free(value);
> +		free(entry);
> +		free(removed);
> +	}
> +	check_int(map->tablesize, ==, 256);
> +	check_int(hashmap_get_size(map), ==, 40);
> +
> +	entry = alloc_test_entry(ignore_case, "key40", "");
> +	removed = hashmap_remove_entry(map, entry, ent, "key40");
> +	if (check(removed != NULL))
> +		check_str("value40", get_value(removed));
> +	check_int(map->tablesize, ==, 64);
> +	check_int(hashmap_get_size(map), ==, 39);
> +	free(entry);
> +	free(removed);
> +}
> +
> +static void t_intern(struct hashmap *map, int ignore_case)
> +{
> +	const char *values[] = { "value1", "Value1", "value2", "value2" };
> +
> +	for (size_t i = 0; i < ARRAY_SIZE(values); i++) {
> +		const char *i1 = strintern(values[i]);
> +		const char *i2 = strintern(values[i]);
> +
> +		if (!check(!strcmp(i1, values[i])))

Should we use check_str() here? Or does that add too much extraneous detail when the test_msg() below is what we really care about?

> +			test_msg("strintern(%s) returns %s\n", values[i], i1);
> +		else if (!check(i1 != values[i]))
Similarly, check_pointer_eq() here?
> +			test_msg("strintern(%s) returns input pointer\n",
> +				 values[i]);
> +		else if (!check(i1 == i2))
And check_pointer_eq() here as well.
Show 29 quoted lines
> +			test_msg("address('%s') != address('%s'), so strintern('%s') != strintern('%s')",
> +				 i1, i2, values[i], values[i]);
> +		else
> +			check_str(i1, values[i]);
> +	}
> +}
> +
> +int cmd_main(int argc UNUSED, const char **argv UNUSED)
> +{
> +	TEST(setup(t_put, 0), "put works");
> +	TEST(setup(t_put, 1), "put (case insensitive) works");
> +	TEST(setup(t_replace, 0), "replace works");
> +	TEST(setup(t_replace, 1), "replace (case insensitive) works");
> +	TEST(setup(t_get, 0), "get works");
> +	TEST(setup(t_get, 1), "get (case insensitive) works");
> +	TEST(setup(t_add, 0), "add works");
> +	TEST(setup(t_add, 1), "add (case insensitive) works");
> +	TEST(setup(t_remove, 0), "remove works");
> +	TEST(setup(t_remove, 1), "remove (case insensitive) works");
> +	TEST(setup(t_iterate, 0), "iterate works");
> +	TEST(setup(t_iterate, 1), "iterate (case insensitive) works");
> +	TEST(setup(t_alloc, 0), "grow / shrink works");
> +	TEST(setup(t_intern, 0), "string interning works");
> +	return test_done();
> +}
> -- 
> 2.45.2
> 
> 
Junio C Hamano· Jul 9, 2024, 21:42 UTC · re: Josh Steadmon · lore

Re: [GSoC][PATCH v2] t: port helper/test-hashmap.c to unit-tests/t-hashmap.c

Josh Steadmon <steadmon@google.com> writes:
Show 26 quoted lines
>> +static void t_put(struct hashmap *map, int ignore_case)
>> +{
>> +	struct test_entry *entry;
>> +	const char *key_val[][2] = { { "key1", "value1" },
>> +				     { "key2", "value2" },
>> +				     { "fooBarFrotz", "value3" } };
>> +
>> +	for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
>> +		entry = alloc_test_entry(ignore_case, key_val[i][0], key_val[i][1]);
>> +		check(hashmap_put_entry(map, entry, ent) == NULL);
>> +	}
>> +
>> +	entry = alloc_test_entry(ignore_case, "foobarfrotz", "value4");
>> +	entry = hashmap_put_entry(map, entry, ent);
>> +	check(ignore_case ? entry != NULL : entry == NULL);
>> +	free(entry);
>> +
>> +	check_int(map->tablesize, ==, 64);
>> +	check_int(hashmap_get_size(map), ==,
>> +		  ignore_case ? ARRAY_SIZE(key_val) : ARRAY_SIZE(key_val) + 1);
>> +}
>
> Ahhh, so you're using the same function for both case-sensitive and
> -insensitive tests. So I guess TEST_RUN isn't useful here after all.
> Personally I'd still rather get rid of setup(), but I don't feel super
> strongly about it.

Consulting the table with "fooBarFrotz" and checking what gets returned (expect "value3" for !icase, or "value4" for icase) is one of the things that are missing. In fact, the values stored are not even checked with the above test at all.

Show 20 quoted lines
>> +static void t_replace(struct hashmap *map, int ignore_case)
>> +{
>> +	struct test_entry *entry;
>> +
>> +	entry = alloc_test_entry(ignore_case, "key1", "value1");
>> +	check(hashmap_put_entry(map, entry, ent) == NULL);
>> +
>> +	entry = alloc_test_entry(ignore_case, ignore_case ? "Key1" : "key1",
>> +				 "value2");
>> +	entry = hashmap_put_entry(map, entry, ent);
>> +	if (check(entry != NULL))
>> +		check_str(get_value(entry), "value1");
>> +	free(entry);
>> +
>> +	entry = alloc_test_entry(ignore_case, "fooBarFrotz", "value3");
>> +	check(hashmap_put_entry(map, entry, ent) == NULL);
>> +
>> +	entry = alloc_test_entry(ignore_case,
>> +				 ignore_case ? "foobarfrotz" : "fooBarFrotz",
>> +				 "value4");

Curious. If the hashmap is set up for icase use, do callers still need to downcase the key? Shouldn't the library take care of that? After all, test_entry_cmp() when the hashmap is being used in icase mode does strcasecmp() anyway.

>> +	entry = hashmap_put_entry(map, entry, ent);
>> +	if (check(entry != NULL))
>> +		check_str(get_value(entry), "value3");
Here the stored value is checked, which is good.
Show 29 quoted lines
>> +	free(entry);
>> +}
>> +
>> +static void t_get(struct hashmap *map, int ignore_case)
>> +{
>> +	struct test_entry *entry;
>> +	const char *key_val[][2] = { { "key1", "value1" },
>> +				     { "key2", "value2" },
>> +				     { "fooBarFrotz", "value3" },
>> +				     { ignore_case ? "key4" : "foobarfrotz", "value4" } };
>> +	const char *query[][2] = {
>> +		{ ignore_case ? "Key1" : "key1", "value1" },
>> +		{ ignore_case ? "keY2" : "key2", "value2" },
>> +		{ ignore_case ? "foobarfrotz" : "fooBarFrotz", "value3" }
>> +	};
>> +
>> +	for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
>> +		entry = alloc_test_entry(ignore_case, key_val[i][0], key_val[i][1]);
>> +		check(hashmap_put_entry(map, entry, ent) == NULL);
>> +	}
>> +
>> +	for (size_t i = 0; i < ARRAY_SIZE(query); i++) {
>> +		entry = get_test_entry(map, ignore_case, query[i][0]);
>> +		if (check(entry != NULL))
>> +			check_str(get_value(entry), query[i][1]);
>> +	}
>> +
>> +	check(get_test_entry(map, ignore_case, "notInMap") == NULL);
>> +}

It is getting dubious if it is worth having t_put, when t_get does so similar things and more.

Same comment applies wrt icase, and not limited to t_get() but all the remaining test functions (elided).

Thanks.
Ghanshyam Thakkar· Jul 10, 2024, 19:41 UTC · re: Junio C Hamano · lore

Re: [GSoC][PATCH v2] t: port helper/test-hashmap.c to unit-tests/t-hashmap.c

Junio C Hamano <gitster@pobox.com> wrote:
Show 33 quoted lines
> Josh Steadmon <steadmon@google.com> writes:
>
> >> +static void t_put(struct hashmap *map, int ignore_case)
> >> +{
> >> +	struct test_entry *entry;
> >> +	const char *key_val[][2] = { { "key1", "value1" },
> >> +				     { "key2", "value2" },
> >> +				     { "fooBarFrotz", "value3" } };
> >> +
> >> +	for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
> >> +		entry = alloc_test_entry(ignore_case, key_val[i][0], key_val[i][1]);
> >> +		check(hashmap_put_entry(map, entry, ent) == NULL);
> >> +	}
> >> +
> >> +	entry = alloc_test_entry(ignore_case, "foobarfrotz", "value4");
> >> +	entry = hashmap_put_entry(map, entry, ent);
> >> +	check(ignore_case ? entry != NULL : entry == NULL);
> >> +	free(entry);
> >> +
> >> +	check_int(map->tablesize, ==, 64);
> >> +	check_int(hashmap_get_size(map), ==,
> >> +		  ignore_case ? ARRAY_SIZE(key_val) : ARRAY_SIZE(key_val) + 1);
> >> +}
> >
> > Ahhh, so you're using the same function for both case-sensitive and
> > -insensitive tests. So I guess TEST_RUN isn't useful here after all.
> > Personally I'd still rather get rid of setup(), but I don't feel super
> > strongly about it.
>
> Consulting the table with "fooBarFrotz" and checking what gets
> returned (expect "value3" for !icase, or "value4" for icase) is one
> of the things that are missing. In fact, the values stored are not
> even checked with the above test at all.

Yeah, I tried to replicate the 'put' tests from the shellscript. However, t_get() does the same thing as you mentioned below, so I'll just remove it and rename t_get() to t_put_get(), and add some missing checks from t_put() to t_put_get().

Show 26 quoted lines
>
> >> +static void t_replace(struct hashmap *map, int ignore_case)
> >> +{
> >> +	struct test_entry *entry;
> >> +
> >> +	entry = alloc_test_entry(ignore_case, "key1", "value1");
> >> +	check(hashmap_put_entry(map, entry, ent) == NULL);
> >> +
> >> +	entry = alloc_test_entry(ignore_case, ignore_case ? "Key1" : "key1",
> >> +				 "value2");
> >> +	entry = hashmap_put_entry(map, entry, ent);
> >> +	if (check(entry != NULL))
> >> +		check_str(get_value(entry), "value1");
> >> +	free(entry);
> >> +
> >> +	entry = alloc_test_entry(ignore_case, "fooBarFrotz", "value3");
> >> +	check(hashmap_put_entry(map, entry, ent) == NULL);
> >> +
> >> +	entry = alloc_test_entry(ignore_case,
> >> +				 ignore_case ? "foobarfrotz" : "fooBarFrotz",
> >> +				 "value4");
>
> Curious. If the hashmap is set up for icase use, do callers still
> need to downcase the key? Shouldn't the library take care of that?
> After all, test_entry_cmp() when the hashmap is being used in icase
> mode does strcasecmp() anyway.

Of course we don't need to downcase. But the idea is to insert "fooBarFrotz" then insert "foobarfrotz" to check if it is considered the same or not. In a way, it is also testing test_entry_cmp() and alloc_test_entry(). If we pass "fooBarFrotz" both the times we can't be sure if it downcases or not, as both are same, we'd pass even if it didn't downcase. After all, we are testing the library rather than using it.

Thanks.
Show 44 quoted lines
>
> >> +	entry = hashmap_put_entry(map, entry, ent);
> >> +	if (check(entry != NULL))
> >> +		check_str(get_value(entry), "value3");
>
> Here the stored value is checked, which is good.
>
> >> +	free(entry);
> >> +}
> >> +
> >> +static void t_get(struct hashmap *map, int ignore_case)
> >> +{
> >> +	struct test_entry *entry;
> >> +	const char *key_val[][2] = { { "key1", "value1" },
> >> +				     { "key2", "value2" },
> >> +				     { "fooBarFrotz", "value3" },
> >> +				     { ignore_case ? "key4" : "foobarfrotz", "value4" } };
> >> +	const char *query[][2] = {
> >> +		{ ignore_case ? "Key1" : "key1", "value1" },
> >> +		{ ignore_case ? "keY2" : "key2", "value2" },
> >> +		{ ignore_case ? "foobarfrotz" : "fooBarFrotz", "value3" }
> >> +	};
> >> +
> >> +	for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
> >> +		entry = alloc_test_entry(ignore_case, key_val[i][0], key_val[i][1]);
> >> +		check(hashmap_put_entry(map, entry, ent) == NULL);
> >> +	}
> >> +
> >> +	for (size_t i = 0; i < ARRAY_SIZE(query); i++) {
> >> +		entry = get_test_entry(map, ignore_case, query[i][0]);
> >> +		if (check(entry != NULL))
> >> +			check_str(get_value(entry), query[i][1]);
> >> +	}
> >> +
> >> +	check(get_test_entry(map, ignore_case, "notInMap") == NULL);
> >> +}
>
> It is getting dubious if it is worth having t_put, when t_get does
> so similar things and more.
>
> Same comment applies wrt icase, and not limited to t_get() but all
> the remaining test functions (elided).
>
> Thanks.
Ghanshyam Thakkar· Jul 9, 2024, 23:27 UTC · re: Josh Steadmon · lore

Re: [GSoC][PATCH v2] t: port helper/test-hashmap.c to unit-tests/t-hashmap.c

Josh Steadmon <steadmon@google.com> wrote:
Show 12 quoted lines
>
> This looks like a good conversion to me. There are a few small
> improvements that could be made, but mostly LGTM. Comments are inline
> below.
>
>
> On 2024.07.08 21:45, Ghanshyam Thakkar wrote:
> > helper/test-hashmap.c along with t0011-hashmap.sh test the hashmap.h
> > library. Migrate them to the unit testing framework for better
> > debugging, runtime performance and consice code.
>
> Typo: s/consice/concise/
Will update.
Show 159 quoted lines
>
> > Along with the migration, make 'add' tests from the shellscript order
> > agnostic in unit tests, since they iterate over entries with the same
> > keys and we do not guarantee the order.
> > 
> > The helper/test-hashmap.c is still not removed because it contains a
> > performance test meant to be run by the user directly (not used in
> > t/perf). And it makes sense for such a utility to be a helper.
> > 
> > Mentored-by: Christian Couder <chriscool@tuxfamily.org>
> > Mentored-by: Kaartic Sivaraam <kaartic.sivaraam@gmail.com>
> > Signed-off-by: Ghanshyam Thakkar <shyamthakkar001@gmail.com>
> > ---
> > The changes in v2 are inspired from the review of another similar
> > test t-oidmap: https://lore.kernel.org/git/16e06a6d-5fd0-4132-9d82-5c6f13b7f9ed@gmail.com/
> > 
> > The v2 also includes some formatting corrections and one of the
> > testcases, t_add(), was changed to be more similar to the original.
> > 
> >  Makefile                 |   1 +
> >  t/helper/test-hashmap.c  | 100 +----------
> >  t/t0011-hashmap.sh       | 260 ----------------------------
> >  t/unit-tests/t-hashmap.c | 359 +++++++++++++++++++++++++++++++++++++++
> >  4 files changed, 362 insertions(+), 358 deletions(-)
> >  delete mode 100755 t/t0011-hashmap.sh
> >  create mode 100644 t/unit-tests/t-hashmap.c
>
> [snip]
>
> > diff --git a/t/unit-tests/t-hashmap.c b/t/unit-tests/t-hashmap.c
> > new file mode 100644
> > index 0000000000..1c951fcfd8
> > --- /dev/null
> > +++ b/t/unit-tests/t-hashmap.c
> > @@ -0,0 +1,359 @@
> > +#include "test-lib.h"
> > +#include "hashmap.h"
> > +#include "strbuf.h"
> > +
> > +struct test_entry {
> > +	int padding; /* hashmap entry no longer needs to be the first member */
> > +	struct hashmap_entry ent;
> > +	/* key and value as two \0-terminated strings */
> > +	char key[FLEX_ARRAY];
> > +};
> > +
> > +static int test_entry_cmp(const void *cmp_data,
> > +			  const struct hashmap_entry *eptr,
> > +			  const struct hashmap_entry *entry_or_key,
> > +			  const void *keydata)
> > +{
> > +	const int ignore_case = cmp_data ? *((int *)cmp_data) : 0;
> > +	const struct test_entry *e1, *e2;
> > +	const char *key = keydata;
> > +
> > +	e1 = container_of(eptr, const struct test_entry, ent);
> > +	e2 = container_of(entry_or_key, const struct test_entry, ent);
> > +
> > +	if (ignore_case)
> > +		return strcasecmp(e1->key, key ? key : e2->key);
> > +	else
> > +		return strcmp(e1->key, key ? key : e2->key);
> > +}
> > +
> > +static const char *get_value(const struct test_entry *e)
> > +{
> > +	return e->key + strlen(e->key) + 1;
> > +}
> > +
> > +static struct test_entry *alloc_test_entry(unsigned int ignore_case,
> > +					   const char *key, const char *value)
> > +{
> > +	size_t klen = strlen(key);
> > +	size_t vlen = strlen(value);
> > +	unsigned int hash = ignore_case ? strihash(key) : strhash(key);
> > +	struct test_entry *entry = xmalloc(st_add4(sizeof(*entry), klen, vlen, 2));
> > +
> > +	hashmap_entry_init(&entry->ent, hash);
> > +	memcpy(entry->key, key, klen + 1);
> > +	memcpy(entry->key + klen + 1, value, vlen + 1);
> > +	return entry;
> > +}
>
> So we're duplicating `struct test_entry`, `test_entry_cmp()`, and
> `alloc_test_entry()`, which have (almost) identical definitions in
> t/helper/test-hashmap.c. I wonder if it's worth splitting these into a
> separate .c file. Maybe it's too much of a pain to add Makefile rules to
> share objects across the test helper and the unit tests. Something to
> keep in mind I guess, if we find that we want to share more code than
> this.
>
>
> > +static struct test_entry *get_test_entry(struct hashmap *map,
> > +					 unsigned int ignore_case, const char *key)
> > +{
> > +	return hashmap_get_entry_from_hash(
> > +		map, ignore_case ? strihash(key) : strhash(key), key,
> > +		struct test_entry, ent);
> > +}
> > +
> > +static int key_val_contains(const char *key_val[][3], size_t n,
> > +			    struct test_entry *entry)
> > +{
> > +	for (size_t i = 0; i < n; i++) {
> > +		if (!strcmp(entry->key, key_val[i][0]) &&
> > +		    !strcmp(get_value(entry), key_val[i][1])) {
> > +			if (!strcmp(key_val[i][2], "USED"))
> > +				return 2;
> > +			key_val[i][2] = "USED";
> > +			return 0;
> > +		}
> > +	}
> > +	return 1;
> > +}
> > +
> > +static void setup(void (*f)(struct hashmap *map, int ignore_case),
> > +		  int ignore_case)
> > +{
> > +	struct hashmap map = HASHMAP_INIT(test_entry_cmp, &ignore_case);
> > +
> > +	f(&map, ignore_case);
> > +	hashmap_clear_and_free(&map, struct test_entry, ent);
> > +}
>
> As I mentioned in my review [1] on René's TEST_RUN series, I don't
> think
> we get much value out of having a setup + callback approach when the
> setup is minimal. Would you consider rewriting a v2 using TEST_RUN once
> that is ready in `next`?
>
> [1]
> https://lore.kernel.org/git/tswyfparvchgi7qxrjxbx4eb7cohypzekjqzbnkbffsesaiazs@vtewtz7o6twi/
>
> > +static void t_put(struct hashmap *map, int ignore_case)
> > +{
> > +	struct test_entry *entry;
> > +	const char *key_val[][2] = { { "key1", "value1" },
> > +				     { "key2", "value2" },
> > +				     { "fooBarFrotz", "value3" } };
> > +
> > +	for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
> > +		entry = alloc_test_entry(ignore_case, key_val[i][0], key_val[i][1]);
> > +		check(hashmap_put_entry(map, entry, ent) == NULL);
> > +	}
> > +
> > +	entry = alloc_test_entry(ignore_case, "foobarfrotz", "value4");
> > +	entry = hashmap_put_entry(map, entry, ent);
> > +	check(ignore_case ? entry != NULL : entry == NULL);
> > +	free(entry);
> > +
> > +	check_int(map->tablesize, ==, 64);
> > +	check_int(hashmap_get_size(map), ==,
> > +		  ignore_case ? ARRAY_SIZE(key_val) : ARRAY_SIZE(key_val) + 1);
> > +}
>
> Ahhh, so you're using the same function for both case-sensitive and
> -insensitive tests. So I guess TEST_RUN isn't useful here after all.
> Personally I'd still rather get rid of setup(), but I don't feel super
> strongly about it.
Sure, I'll get rid of setup().
Show 75 quoted lines
>
> > +static void t_replace(struct hashmap *map, int ignore_case)
> > +{
> > +	struct test_entry *entry;
> > +
> > +	entry = alloc_test_entry(ignore_case, "key1", "value1");
> > +	check(hashmap_put_entry(map, entry, ent) == NULL);
> > +
> > +	entry = alloc_test_entry(ignore_case, ignore_case ? "Key1" : "key1",
> > +				 "value2");
> > +	entry = hashmap_put_entry(map, entry, ent);
> > +	if (check(entry != NULL))
> > +		check_str(get_value(entry), "value1");
> > +	free(entry);
> > +
> > +	entry = alloc_test_entry(ignore_case, "fooBarFrotz", "value3");
> > +	check(hashmap_put_entry(map, entry, ent) == NULL);
> > +
> > +	entry = alloc_test_entry(ignore_case,
> > +				 ignore_case ? "foobarfrotz" : "fooBarFrotz",
> > +				 "value4");
> > +	entry = hashmap_put_entry(map, entry, ent);
> > +	if (check(entry != NULL))
> > +		check_str(get_value(entry), "value3");
> > +	free(entry);
> > +}
> > +
> > +static void t_get(struct hashmap *map, int ignore_case)
> > +{
> > +	struct test_entry *entry;
> > +	const char *key_val[][2] = { { "key1", "value1" },
> > +				     { "key2", "value2" },
> > +				     { "fooBarFrotz", "value3" },
> > +				     { ignore_case ? "key4" : "foobarfrotz", "value4" } };
> > +	const char *query[][2] = {
> > +		{ ignore_case ? "Key1" : "key1", "value1" },
> > +		{ ignore_case ? "keY2" : "key2", "value2" },
> > +		{ ignore_case ? "foobarfrotz" : "fooBarFrotz", "value3" }
> > +	};
> > +
> > +	for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
> > +		entry = alloc_test_entry(ignore_case, key_val[i][0], key_val[i][1]);
> > +		check(hashmap_put_entry(map, entry, ent) == NULL);
> > +	}
> > +
> > +	for (size_t i = 0; i < ARRAY_SIZE(query); i++) {
> > +		entry = get_test_entry(map, ignore_case, query[i][0]);
> > +		if (check(entry != NULL))
> > +			check_str(get_value(entry), query[i][1]);
> > +	}
> > +
> > +	check(get_test_entry(map, ignore_case, "notInMap") == NULL);
> > +}
> > +
> > +static void t_add(struct hashmap *map, int ignore_case)
> > +{
> > +	struct test_entry *entry;
> > +	const char *key_val[][3] = {
> > +		{ "key1", "value1", "UNUSED" },
> > +		{ ignore_case ? "Key1" : "key1", "value2", "UNUSED" },
> > +		{ "fooBarFrotz", "value3", "UNUSED" },
> > +		{ ignore_case ? "Foobarfrotz" : "fooBarFrotz", "value4", "UNUSED" }
> > +	};
> > +	const char *queries[] = { "key1",
> > +				  ignore_case ? "Foobarfrotz" : "fooBarFrotz" };
> > +
> > +	for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
> > +		entry = alloc_test_entry(ignore_case, key_val[i][0], key_val[i][1]);
> > +		hashmap_add(map, &entry->ent);
> > +	}
> > +
> > +	for (size_t i = 0; i < ARRAY_SIZE(queries); i++) {
>
> Since we only have one query, can we remove the loop and simplify the
> following block of code?

We have two queries as can be seen above. One is "key1" and the other is "Foobarfrotz"/"fooBarFrotz".

Show 5 quoted lines
> Also (here and elsewhere), it might be less confusing to say "UNSEEN" /
> "SEEN" instead of "UNUSED" / "USED". The latter makes it sound to me
> like there's some API requirement to have a 3-item array that we don't
> actually need, but in this case those fields are actually used in
> key_val_contains() to track duplicates.
Yeah, "UNSEEN" is definitely less confusing. Will change.
Show 65 quoted lines
>
> > +		int count = 0;
> > +		entry = hashmap_get_entry_from_hash(map,
> > +			ignore_case ? strihash(queries[i]) :
> > +				      strhash(queries[i]),
> > +			queries[i], struct test_entry, ent);
> > +
> > +		hashmap_for_each_entry_from(map, entry, ent)
> > +		{
> > +			int ret;
> > +			if (!check_int((ret = key_val_contains(
> > +						key_val, ARRAY_SIZE(key_val),
> > +						entry)), ==, 0)) {
> > +				switch (ret) {
> > +				case 1:
> > +					test_msg("found entry was not given in the input\n"
> > +						 "    key: %s\n  value: %s",
> > +						 entry->key, get_value(entry));
> > +					break;
> > +				case 2:
> > +					test_msg("duplicate entry detected\n"
> > +						 "    key: %s\n  value: %s",
> > +						 entry->key, get_value(entry));
> > +					break;
> > +				}
> > +			} else {
> > +				count++;
> > +			}
> > +		}
> > +		check_int(count, ==, 2);
> > +	}
> > +	check_int(hashmap_get_size(map), ==, ARRAY_SIZE(key_val));
> > +	check(get_test_entry(map, ignore_case, "notInMap") == NULL);
> > +}
> > +
> > +static void t_remove(struct hashmap *map, int ignore_case)
> > +{
> > +	struct test_entry *entry, *removed;
> > +	const char *key_val[][2] = { { "key1", "value1" },
> > +				     { "key2", "value2" },
> > +				     { "fooBarFrotz", "value3" } };
> > +	const char *remove[][2] = { { ignore_case ? "Key1" : "key1", "value1" },
> > +				    { ignore_case ? "keY2" : "key2", "value2" } };
> > +
> > +	for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
> > +		entry = alloc_test_entry(ignore_case, key_val[i][0], key_val[i][1]);
> > +		check(hashmap_put_entry(map, entry, ent) == NULL);
> > +	}
> > +
> > +	for (size_t i = 0; i < ARRAY_SIZE(remove); i++) {
> > +		entry = alloc_test_entry(ignore_case, remove[i][0], "");
> > +		removed = hashmap_remove_entry(map, entry, ent, remove[i][0]);
> > +		if (check(removed != NULL))
> > +			check_str(get_value(removed), remove[i][1]);
> > +		free(entry);
> > +		free(removed);
> > +	}
> > +
> > +	entry = alloc_test_entry(ignore_case, "notInMap", "");
> > +	check(hashmap_remove_entry(map, entry, ent, "notInMap") == NULL);
> > +	free(entry);
> > +}
>
> Is there a reason why you don't check the table size as the shell test
> did? (similar to what you have in t_put())
Huh, I seem to have forgotten to put this snippet here:
  
	check_int(map->tablesize, ==, 64);
	check_int(hashmap_get_size(map), ==, ARRAY_SIZE(key_val) - ARRAY_SIZE(remove));
	
I'll add it in v3.
Show 98 quoted lines
>
> > +static void t_iterate(struct hashmap *map, int ignore_case)
> > +{
> > +	struct test_entry *entry;
> > +	struct hashmap_iter iter;
> > +	const char *key_val[][3] = { { "key1", "value1", "UNUSED" },
> > +				     { "key2", "value2", "UNUSED" },
> > +				     { "fooBarFrotz", "value3", "UNUSED" } };
> > +	int count = 0;
> > +
> > +	for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
> > +		entry = alloc_test_entry(ignore_case, key_val[i][0], key_val[i][1]);
> > +		check(hashmap_put_entry(map, entry, ent) == NULL);
> > +	}
> > +
> > +	hashmap_for_each_entry(map, &iter, entry, ent /* member name */)
> > +	{
> > +		int ret;
> > +		if (!check_int((ret = key_val_contains(key_val, ARRAY_SIZE(key_val),
> > +						       entry)), ==, 0)) {
> > +			switch (ret) {
> > +			case 1:
> > +				test_msg("found entry was not given in the input\n"
> > +					 "    key: %s\n  value: %s",
> > +					 entry->key, get_value(entry));
> > +				break;
> > +			case 2:
> > +				test_msg("duplicate entry detected\n"
> > +					 "    key: %s\n  value: %s",
> > +					 entry->key, get_value(entry));
> > +				break;
> > +			}
> > +		} else {
> > +			count++;
> > +		}
> > +	}
> > +	check_int(count, ==, ARRAY_SIZE(key_val));
> > +	check_int(hashmap_get_size(map), ==, ARRAY_SIZE(key_val));
> > +}
> > +
> > +static void t_alloc(struct hashmap *map, int ignore_case)
> > +{
> > +	struct test_entry *entry, *removed;
> > +
> > +	for (int i = 1; i <= 51; i++) {
> > +		char *key = xstrfmt("key%d", i);
> > +		char *value = xstrfmt("value%d", i);
> > +		entry = alloc_test_entry(ignore_case, key, value);
> > +		check(hashmap_put_entry(map, entry, ent) == NULL);
> > +		free(key);
> > +		free(value);
> > +	}
> > +	check_int(map->tablesize, ==, 64);
> > +	check_int(hashmap_get_size(map), ==, 51);
> > +
> > +	entry = alloc_test_entry(ignore_case, "key52", "value52");
> > +	check(hashmap_put_entry(map, entry, ent) == NULL);
> > +	check_int(map->tablesize, ==, 256);
> > +	check_int(hashmap_get_size(map), ==, 52);
> > +
> > +	for (int i = 1; i <= 12; i++) {
> > +		char *key = xstrfmt("key%d", i);
> > +		char *value = xstrfmt("value%d", i);
> > +
> > +		entry = alloc_test_entry(ignore_case, key, "");
> > +		removed = hashmap_remove_entry(map, entry, ent, key);
> > +		if (check(removed != NULL))
> > +			check_str(value, get_value(removed));
> > +		free(key);
> > +		free(value);
> > +		free(entry);
> > +		free(removed);
> > +	}
> > +	check_int(map->tablesize, ==, 256);
> > +	check_int(hashmap_get_size(map), ==, 40);
> > +
> > +	entry = alloc_test_entry(ignore_case, "key40", "");
> > +	removed = hashmap_remove_entry(map, entry, ent, "key40");
> > +	if (check(removed != NULL))
> > +		check_str("value40", get_value(removed));
> > +	check_int(map->tablesize, ==, 64);
> > +	check_int(hashmap_get_size(map), ==, 39);
> > +	free(entry);
> > +	free(removed);
> > +}
> > +
> > +static void t_intern(struct hashmap *map, int ignore_case)
> > +{
> > +	const char *values[] = { "value1", "Value1", "value2", "value2" };
> > +
> > +	for (size_t i = 0; i < ARRAY_SIZE(values); i++) {
> > +		const char *i1 = strintern(values[i]);
> > +		const char *i2 = strintern(values[i]);
> > +
> > +		if (!check(!strcmp(i1, values[i])))
>
> Should we use check_str() here? Or does that add too much extraneous
> detail when the test_msg() below is what we really care about?

It would repetitive as both print the same thing but test_msg() has more context.

> > +			test_msg("strintern(%s) returns %s\n", values[i], i1);
> > +		else if (!check(i1 != values[i]))
>
> Similarly, check_pointer_eq() here?

How would we use check_pointer_eq() here as we are checking to make sure they are not equal?

Show 6 quoted lines
>
> > +			test_msg("strintern(%s) returns input pointer\n",
> > +				 values[i]);
> > +		else if (!check(i1 == i2))
>
> And check_pointer_eq() here as well.
Will update here.
Thanks for the review.
Phillip Wood· Jul 10, 2024, 10:19 UTC · re: Josh Steadmon · lore

Re: [GSoC][PATCH v2] t: port helper/test-hashmap.c to unit-tests/t-hashmap.c

On 09/07/2024 20:34, Josh Steadmon wrote:
> On 2024.07.08 21:45, Ghanshyam Thakkar wrote:
Show 26 quoted lines
>> +static void t_put(struct hashmap *map, int ignore_case)
>> +{
>> +	struct test_entry *entry;
>> +	const char *key_val[][2] = { { "key1", "value1" },
>> +				     { "key2", "value2" },
>> +				     { "fooBarFrotz", "value3" } };
>> +
>> +	for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
>> +		entry = alloc_test_entry(ignore_case, key_val[i][0], key_val[i][1]);
>> +		check(hashmap_put_entry(map, entry, ent) == NULL);
>> +	}
>> +
>> +	entry = alloc_test_entry(ignore_case, "foobarfrotz", "value4");
>> +	entry = hashmap_put_entry(map, entry, ent);
>> +	check(ignore_case ? entry != NULL : entry == NULL);
>> +	free(entry);
>> +
>> +	check_int(map->tablesize, ==, 64);
>> +	check_int(hashmap_get_size(map), ==,
>> +		  ignore_case ? ARRAY_SIZE(key_val) : ARRAY_SIZE(key_val) + 1);
>> +}
> 
> Ahhh, so you're using the same function for both case-sensitive and
> -insensitive tests. So I guess TEST_RUN isn't useful here after all.
> Personally I'd still rather get rid of setup(), but I don't feel super
> strongly about it.

I'm not sure - we have to pass ignore_case to HASHMAP_INIT and the test function so using setup() means we cannot pass different values to the two different functions.

For parameterized tests where we calling the same function with 
different inputs using a setup function allows us to
  - write more concise test code
  - easily change the setup of all the tests if the api changes in the
    future.
  - consistently free resources at the end of a test making it easier to
    write leak-free tests
  - assert pre- and post- conditions on all tests

Using TEST_RUN is useful to declare the different inputs for each test. For example in the oid-array tests it allows us to write

     TEST_RUN("ordered enumeration") {
         const char *input[] = { "88", "44", "aa", "55" };
         const char *expected[] = { "44", "55", "88", "aa" };
         TEST_ENUMERATION(input, expected)
     }

rather than declaring a bunch of variables up front a long way from where they are used.

Show 27 quoted lines
>> +static void t_add(struct hashmap *map, int ignore_case)
>> +{
>> +	struct test_entry *entry;
>> +	const char *key_val[][3] = {
>> +		{ "key1", "value1", "UNUSED" },
>> +		{ ignore_case ? "Key1" : "key1", "value2", "UNUSED" },
>> +		{ "fooBarFrotz", "value3", "UNUSED" },
>> +		{ ignore_case ? "Foobarfrotz" : "fooBarFrotz", "value4", "UNUSED" }
>> +	};
>> +	const char *queries[] = { "key1",
>> +				  ignore_case ? "Foobarfrotz" : "fooBarFrotz" };
>> +
>> +	for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
>> +		entry = alloc_test_entry(ignore_case, key_val[i][0], key_val[i][1]);
>> +		hashmap_add(map, &entry->ent);
>> +	}
>> +
>> +	for (size_t i = 0; i < ARRAY_SIZE(queries); i++) {
> 
> Since we only have one query, can we remove the loop and simplify the
> following block of code?
> 
> Also (here and elsewhere), it might be less confusing to say "UNSEEN" /
> "SEEN" instead of "UNUSED" / "USED". The latter makes it sound to me
> like there's some API requirement to have a 3-item array that we don't
> actually need, but in this case those fields are actually used in
> key_val_contains() to track duplicates.

The third element just needs to be a boolean flag so it might be better to use a struct

	const struct {
		char *key;
		char *val;
		char seen;
	} key_val[] = {
		{ .key = "key1", .val = "value1" },
		{ .key = ignore_case ? "Key1" : "key1" .val = "value2" },		{ .key = 
"fooBarFrotz" .val = "value3" },
		{ .key = ignore_case ? "Foobarfrotz" : "fooBarFrotz", .value = "value4" }
	};
Best Wishes
Phillip
Ghanshyam Thakkar· Jul 11, 2024, 18:54 UTC · re: Phillip Wood · lore

Re: [GSoC][PATCH v2] t: port helper/test-hashmap.c to unit-tests/t-hashmap.c

Phillip Wood <phillip.wood123@gmail.com> wrote:
Show 55 quoted lines
> On 09/07/2024 20:34, Josh Steadmon wrote:
> > On 2024.07.08 21:45, Ghanshyam Thakkar wrote:
>
> >> +static void t_put(struct hashmap *map, int ignore_case)
> >> +{
> >> +	struct test_entry *entry;
> >> +	const char *key_val[][2] = { { "key1", "value1" },
> >> +				     { "key2", "value2" },
> >> +				     { "fooBarFrotz", "value3" } };
> >> +
> >> +	for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
> >> +		entry = alloc_test_entry(ignore_case, key_val[i][0], key_val[i][1]);
> >> +		check(hashmap_put_entry(map, entry, ent) == NULL);
> >> +	}
> >> +
> >> +	entry = alloc_test_entry(ignore_case, "foobarfrotz", "value4");
> >> +	entry = hashmap_put_entry(map, entry, ent);
> >> +	check(ignore_case ? entry != NULL : entry == NULL);
> >> +	free(entry);
> >> +
> >> +	check_int(map->tablesize, ==, 64);
> >> +	check_int(hashmap_get_size(map), ==,
> >> +		  ignore_case ? ARRAY_SIZE(key_val) : ARRAY_SIZE(key_val) + 1);
> >> +}
> > 
> > Ahhh, so you're using the same function for both case-sensitive and
> > -insensitive tests. So I guess TEST_RUN isn't useful here after all.
> > Personally I'd still rather get rid of setup(), but I don't feel super
> > strongly about it.
>
> I'm not sure - we have to pass ignore_case to HASHMAP_INIT and the test
> function so using setup() means we cannot pass different values to the
> two different functions.
>
> For parameterized tests where we calling the same function with
> different inputs using a setup function allows us to
> - write more concise test code
> - easily change the setup of all the tests if the api changes in the
> future.
> - consistently free resources at the end of a test making it easier to
> write leak-free tests
> - assert pre- and post- conditions on all tests
>
> Using TEST_RUN is useful to declare the different inputs for each test.
> For example in the oid-array tests it allows us to write
>
> TEST_RUN("ordered enumeration") {
> const char *input[] = { "88", "44", "aa", "55" };
> const char *expected[] = { "44", "55", "88", "aa" };
>
> TEST_ENUMERATION(input, expected)
> }
>
> rather than declaring a bunch of variables up front a long way from
> where they are used.

Yeah, I changed my mind from removing setup(). I'll keep it as it does not have anything complex to make manual verifying harder. Also, since this test does not have any variable inputs, we can just use TEST(), although TEST_RUN() with variable inputs is very useful in other tests.

Show 42 quoted lines
> >> +static void t_add(struct hashmap *map, int ignore_case)
> >> +{
> >> +	struct test_entry *entry;
> >> +	const char *key_val[][3] = {
> >> +		{ "key1", "value1", "UNUSED" },
> >> +		{ ignore_case ? "Key1" : "key1", "value2", "UNUSED" },
> >> +		{ "fooBarFrotz", "value3", "UNUSED" },
> >> +		{ ignore_case ? "Foobarfrotz" : "fooBarFrotz", "value4", "UNUSED" }
> >> +	};
> >> +	const char *queries[] = { "key1",
> >> +				  ignore_case ? "Foobarfrotz" : "fooBarFrotz" };
> >> +
> >> +	for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
> >> +		entry = alloc_test_entry(ignore_case, key_val[i][0], key_val[i][1]);
> >> +		hashmap_add(map, &entry->ent);
> >> +	}
> >> +
> >> +	for (size_t i = 0; i < ARRAY_SIZE(queries); i++) {
> > 
> > Since we only have one query, can we remove the loop and simplify the
> > following block of code?
> > 
> > Also (here and elsewhere), it might be less confusing to say "UNSEEN" /
> > "SEEN" instead of "UNUSED" / "USED". The latter makes it sound to me
> > like there's some API requirement to have a 3-item array that we don't
> > actually need, but in this case those fields are actually used in
> > key_val_contains() to track duplicates.
>
> The third element just needs to be a boolean flag so it might be better
> to use a struct
>
> const struct {
> char *key;
> char *val;
> char seen;
> } key_val[] = {
> { .key = "key1", .val = "value1" },
> { .key = ignore_case ? "Key1" : "key1" .val = "value2" }, { .key =
> "fooBarFrotz" .val = "value3" },
> { .key = ignore_case ? "Foobarfrotz" : "fooBarFrotz", .value = "value4"
> }
> };

I think we can just use an extra 'char seen[]' for markings and modify key_val_contains() to have this parameter, instead of having it as a struct.

Thanks.
Ghanshyam Thakkar· Jul 11, 2024, 23:51 UTC · re: Ghanshyam Thakkar · lore

[GSoC][PATCH v3] t: port helper/test-hashmap.c to unit-tests/t-hashmap.c

helper/test-hashmap.c along with t0011-hashmap.sh test the hashmap.h library. Migrate them to the unit testing framework for better debugging, runtime performance and concise code.

Along with the migration, make 'add' tests from the shellscript order agnostic in unit tests, since they iterate over entries with the same keys and we do not guarantee the order.

The helper/test-hashmap.c is still not removed because it contains a performance test meant to be run by the user directly (not used in t/perf). And it makes sense for such a utility to be a helper.

Mentored-by: Christian Couder <chriscool@tuxfamily.org>
Mentored-by: Kaartic Sivaraam <kaartic.sivaraam@gmail.com>
Helped-by: Josh Steadmon <steadmon@google.com>
Helped-by: Phillip Wood <phillip.wood123@gmail.com>
Signed-off-by: Ghanshyam Thakkar <shyamthakkar001@gmail.com>
---
Range-diff against v2:
1:  bbb4f2f23e ! 1:  03ba77665e t: port helper/test-hashmap.c to unit-tests/t-hashmap.c
    @@ Commit message
     
         helper/test-hashmap.c along with t0011-hashmap.sh test the hashmap.h
         library. Migrate them to the unit testing framework for better
    -    debugging, runtime performance and consice code.
    +    debugging, runtime performance and concise code.
     
         Along with the migration, make 'add' tests from the shellscript order
         agnostic in unit tests, since they iterate over entries with the same
    @@ Commit message
     
         Mentored-by: Christian Couder <chriscool@tuxfamily.org>
         Mentored-by: Kaartic Sivaraam <kaartic.sivaraam@gmail.com>
    +    Helped-by: Josh Steadmon <steadmon@google.com>
    +    Helped-by: Phillip Wood <phillip.wood123@gmail.com>
         Signed-off-by: Ghanshyam Thakkar <shyamthakkar001@gmail.com>
     
      ## Makefile ##
    @@ t/unit-tests/t-hashmap.c (new)
     +		struct test_entry, ent);
     +}
     +
    -+static int key_val_contains(const char *key_val[][3], size_t n,
    ++static int key_val_contains(const char *key_val[][2], char seen[], size_t n,
     +			    struct test_entry *entry)
     +{
     +	for (size_t i = 0; i < n; i++) {
     +		if (!strcmp(entry->key, key_val[i][0]) &&
     +		    !strcmp(get_value(entry), key_val[i][1])) {
    -+			if (!strcmp(key_val[i][2], "USED"))
    ++			if (seen[i])
     +				return 2;
    -+			key_val[i][2] = "USED";
    ++			seen[i] = 1;
     +			return 0;
     +		}
     +	}
    @@ t/unit-tests/t-hashmap.c (new)
     +	hashmap_clear_and_free(&map, struct test_entry, ent);
     +}
     +
    -+static void t_put(struct hashmap *map, int ignore_case)
    -+{
    -+	struct test_entry *entry;
    -+	const char *key_val[][2] = { { "key1", "value1" },
    -+				     { "key2", "value2" },
    -+				     { "fooBarFrotz", "value3" } };
    -+
    -+	for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
    -+		entry = alloc_test_entry(ignore_case, key_val[i][0], key_val[i][1]);
    -+		check(hashmap_put_entry(map, entry, ent) == NULL);
    -+	}
    -+
    -+	entry = alloc_test_entry(ignore_case, "foobarfrotz", "value4");
    -+	entry = hashmap_put_entry(map, entry, ent);
    -+	check(ignore_case ? entry != NULL : entry == NULL);
    -+	free(entry);
    -+
    -+	check_int(map->tablesize, ==, 64);
    -+	check_int(hashmap_get_size(map), ==,
    -+		  ignore_case ? ARRAY_SIZE(key_val) : ARRAY_SIZE(key_val) + 1);
    -+}
    -+
     +static void t_replace(struct hashmap *map, int ignore_case)
     +{
     +	struct test_entry *entry;
     +
     +	entry = alloc_test_entry(ignore_case, "key1", "value1");
    -+	check(hashmap_put_entry(map, entry, ent) == NULL);
    ++	check_pointer_eq(hashmap_put_entry(map, entry, ent), NULL);
     +
     +	entry = alloc_test_entry(ignore_case, ignore_case ? "Key1" : "key1",
     +				 "value2");
    @@ t/unit-tests/t-hashmap.c (new)
     +	free(entry);
     +
     +	entry = alloc_test_entry(ignore_case, "fooBarFrotz", "value3");
    -+	check(hashmap_put_entry(map, entry, ent) == NULL);
    ++	check_pointer_eq(hashmap_put_entry(map, entry, ent), NULL);
     +
     +	entry = alloc_test_entry(ignore_case,
     +				 ignore_case ? "foobarfrotz" : "fooBarFrotz",
    @@ t/unit-tests/t-hashmap.c (new)
     +
     +	for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
     +		entry = alloc_test_entry(ignore_case, key_val[i][0], key_val[i][1]);
    -+		check(hashmap_put_entry(map, entry, ent) == NULL);
    ++		check_pointer_eq(hashmap_put_entry(map, entry, ent), NULL);
     +	}
     +
     +	for (size_t i = 0; i < ARRAY_SIZE(query); i++) {
     +		entry = get_test_entry(map, ignore_case, query[i][0]);
     +		if (check(entry != NULL))
     +			check_str(get_value(entry), query[i][1]);
    ++		else
    ++			test_msg("query key: %s", query[i][0]);
     +	}
     +
    -+	check(get_test_entry(map, ignore_case, "notInMap") == NULL);
    ++	check_pointer_eq(get_test_entry(map, ignore_case, "notInMap"), NULL);
    ++	check_int(map->tablesize, ==, 64);
    ++	check_int(hashmap_get_size(map), ==, ARRAY_SIZE(key_val));
     +}
     +
     +static void t_add(struct hashmap *map, int ignore_case)
     +{
     +	struct test_entry *entry;
    -+	const char *key_val[][3] = {
    -+		{ "key1", "value1", "UNUSED" },
    -+		{ ignore_case ? "Key1" : "key1", "value2", "UNUSED" },
    -+		{ "fooBarFrotz", "value3", "UNUSED" },
    -+		{ ignore_case ? "Foobarfrotz" : "fooBarFrotz", "value4", "UNUSED" }
    ++	const char *key_val[][2] = {
    ++		{ "key1", "value1" },
    ++		{ ignore_case ? "Key1" : "key1", "value2" },
    ++		{ "fooBarFrotz", "value3" },
    ++		{ ignore_case ? "Foobarfrotz" : "fooBarFrotz", "value4" }
     +	};
     +	const char *queries[] = { "key1",
     +				  ignore_case ? "Foobarfrotz" : "fooBarFrotz" };
    ++	char seen[ARRAY_SIZE(key_val)] = { 0 };
     +
     +	for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
     +		entry = alloc_test_entry(ignore_case, key_val[i][0], key_val[i][1]);
    @@ t/unit-tests/t-hashmap.c (new)
     +		{
     +			int ret;
     +			if (!check_int((ret = key_val_contains(
    -+						key_val, ARRAY_SIZE(key_val),
    -+						entry)), ==, 0)) {
    ++						key_val, seen,
    ++						ARRAY_SIZE(key_val), entry)),
    ++				       ==, 0)) {
     +				switch (ret) {
     +				case 1:
     +					test_msg("found entry was not given in the input\n"
    @@ t/unit-tests/t-hashmap.c (new)
     +		}
     +		check_int(count, ==, 2);
     +	}
    ++
    ++	for (size_t i = 0; i < ARRAY_SIZE(seen); i++) {
    ++		if (!check_int(seen[i], ==, 1))
    ++			test_msg("following key-val pair was not iterated over:\n"
    ++				 "    key: %s\n  value: %s",
    ++				 key_val[i][0], key_val[i][1]);
    ++	}
    ++
     +	check_int(hashmap_get_size(map), ==, ARRAY_SIZE(key_val));
    -+	check(get_test_entry(map, ignore_case, "notInMap") == NULL);
    ++	check_pointer_eq(get_test_entry(map, ignore_case, "notInMap"), NULL);
     +}
     +
     +static void t_remove(struct hashmap *map, int ignore_case)
    @@ t/unit-tests/t-hashmap.c (new)
     +
     +	for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
     +		entry = alloc_test_entry(ignore_case, key_val[i][0], key_val[i][1]);
    -+		check(hashmap_put_entry(map, entry, ent) == NULL);
    ++		check_pointer_eq(hashmap_put_entry(map, entry, ent), NULL);
     +	}
     +
     +	for (size_t i = 0; i < ARRAY_SIZE(remove); i++) {
    @@ t/unit-tests/t-hashmap.c (new)
     +	}
     +
     +	entry = alloc_test_entry(ignore_case, "notInMap", "");
    -+	check(hashmap_remove_entry(map, entry, ent, "notInMap") == NULL);
    ++	check_pointer_eq(hashmap_remove_entry(map, entry, ent, "notInMap"), NULL);
     +	free(entry);
    ++
    ++	check_int(map->tablesize, ==, 64);
    ++	check_int(hashmap_get_size(map), ==, ARRAY_SIZE(key_val) - ARRAY_SIZE(remove));
     +}
     +
     +static void t_iterate(struct hashmap *map, int ignore_case)
     +{
     +	struct test_entry *entry;
     +	struct hashmap_iter iter;
    -+	const char *key_val[][3] = { { "key1", "value1", "UNUSED" },
    -+				     { "key2", "value2", "UNUSED" },
    -+				     { "fooBarFrotz", "value3", "UNUSED" } };
    -+	int count = 0;
    ++	const char *key_val[][2] = { { "key1", "value1" },
    ++				     { "key2", "value2" },
    ++				     { "fooBarFrotz", "value3" } };
    ++	char seen[ARRAY_SIZE(key_val)] = { 0 };
     +
     +	for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
     +		entry = alloc_test_entry(ignore_case, key_val[i][0], key_val[i][1]);
    -+		check(hashmap_put_entry(map, entry, ent) == NULL);
    ++		check_pointer_eq(hashmap_put_entry(map, entry, ent), NULL);
     +	}
     +
     +	hashmap_for_each_entry(map, &iter, entry, ent /* member name */)
     +	{
     +		int ret;
    -+		if (!check_int((ret = key_val_contains(key_val, ARRAY_SIZE(key_val),
    ++		if (!check_int((ret = key_val_contains(key_val, seen,
    ++						       ARRAY_SIZE(key_val),
     +						       entry)), ==, 0)) {
     +			switch (ret) {
     +			case 1:
    @@ t/unit-tests/t-hashmap.c (new)
     +					 entry->key, get_value(entry));
     +				break;
     +			}
    -+		} else {
    -+			count++;
     +		}
     +	}
    -+	check_int(count, ==, ARRAY_SIZE(key_val));
    ++
    ++	for (size_t i = 0; i < ARRAY_SIZE(seen); i++) {
    ++		if (!check_int(seen[i], ==, 1))
    ++			test_msg("following key-val pair was not iterated over:\n"
    ++				 "    key: %s\n  value: %s",
    ++				 key_val[i][0], key_val[i][1]);
    ++	}
    ++
     +	check_int(hashmap_get_size(map), ==, ARRAY_SIZE(key_val));
     +}
     +
    @@ t/unit-tests/t-hashmap.c (new)
     +		char *key = xstrfmt("key%d", i);
     +		char *value = xstrfmt("value%d", i);
     +		entry = alloc_test_entry(ignore_case, key, value);
    -+		check(hashmap_put_entry(map, entry, ent) == NULL);
    ++		check_pointer_eq(hashmap_put_entry(map, entry, ent), NULL);
     +		free(key);
     +		free(value);
     +	}
    @@ t/unit-tests/t-hashmap.c (new)
     +	check_int(hashmap_get_size(map), ==, 51);
     +
     +	entry = alloc_test_entry(ignore_case, "key52", "value52");
    -+	check(hashmap_put_entry(map, entry, ent) == NULL);
    ++	check_pointer_eq(hashmap_put_entry(map, entry, ent), NULL);
     +	check_int(map->tablesize, ==, 256);
     +	check_int(hashmap_get_size(map), ==, 52);
     +
    @@ t/unit-tests/t-hashmap.c (new)
     +		else if (!check(i1 != values[i]))
     +			test_msg("strintern(%s) returns input pointer\n",
     +				 values[i]);
    -+		else if (!check(i1 == i2))
    ++		else if (!check_pointer_eq(i1, i2))
     +			test_msg("address('%s') != address('%s'), so strintern('%s') != strintern('%s')",
     +				 i1, i2, values[i], values[i]);
     +		else
    @@ t/unit-tests/t-hashmap.c (new)
     +
     +int cmd_main(int argc UNUSED, const char **argv UNUSED)
     +{
    -+	TEST(setup(t_put, 0), "put works");
    -+	TEST(setup(t_put, 1), "put (case insensitive) works");
     +	TEST(setup(t_replace, 0), "replace works");
     +	TEST(setup(t_replace, 1), "replace (case insensitive) works");
     +	TEST(setup(t_get, 0), "get works");
 Makefile                 |   1 +
 t/helper/test-hashmap.c  | 100 +----------
 t/t0011-hashmap.sh       | 260 ----------------------------
 t/unit-tests/t-hashmap.c | 358 +++++++++++++++++++++++++++++++++++++++
 4 files changed, 361 insertions(+), 358 deletions(-)
 delete mode 100755 t/t0011-hashmap.sh
 create mode 100644 t/unit-tests/t-hashmap.c
Show changes to 4 files +361 −358

Makefile, t/helper/test-hashmap.c, t/t0011-hashmap.sh, t/unit-tests/t-hashmap.c

diff --git a/Makefile b/Makefile
index 3eab701b10..74bb026610 100644
--- a/Makefile
+++ b/Makefile
@@ -1336,6 +1336,7 @@ THIRD_PARTY_SOURCES += sha1dc/%
 UNIT_TEST_PROGRAMS += t-ctype
 UNIT_TEST_PROGRAMS += t-example-decorate
 UNIT_TEST_PROGRAMS += t-hash
+UNIT_TEST_PROGRAMS += t-hashmap
 UNIT_TEST_PROGRAMS += t-mem-pool
 UNIT_TEST_PROGRAMS += t-oidtree
 UNIT_TEST_PROGRAMS += t-prio-queue
diff --git a/t/helper/test-hashmap.c b/t/helper/test-hashmap.c
index 2912899558..7b854a7030 100644
--- a/t/helper/test-hashmap.c
+++ b/t/helper/test-hashmap.c
@@ -12,11 +12,6 @@ struct test_entry
 	char key[FLEX_ARRAY];
 };
 
-static const char *get_value(const struct test_entry *e)
-{
-	return e->key + strlen(e->key) + 1;
-}
-
 static int test_entry_cmp(const void *cmp_data,
 			  const struct hashmap_entry *eptr,
 			  const struct hashmap_entry *entry_or_key,
@@ -141,30 +136,16 @@ static void perf_hashmap(unsigned int method, unsigned int rounds)
 /*
  * Read stdin line by line and print result of commands to stdout:
  *
- * hash key -> strhash(key) memhash(key) strihash(key) memihash(key)
- * put key value -> NULL / old value
- * get key -> NULL / value
- * remove key -> NULL / old value
- * iterate -> key1 value1\nkey2 value2\n...
- * size -> tablesize numentries
- *
  * perfhashmap method rounds -> test hashmap.[ch] performance
  */
 int cmd__hashmap(int argc, const char **argv)
 {
 	struct string_list parts = STRING_LIST_INIT_NODUP;
 	struct strbuf line = STRBUF_INIT;
-	int icase;
-	struct hashmap map = HASHMAP_INIT(test_entry_cmp, &icase);
-
-	/* init hash map */
-	icase = argc > 1 && !strcmp("ignorecase", argv[1]);
 
 	/* process commands from stdin */
 	while (strbuf_getline(&line, stdin) != EOF) {
 		char *cmd, *p1, *p2;
-		unsigned int hash = 0;
-		struct test_entry *entry;
 
 		/* break line into command and up to two parameters */
 		string_list_setlen(&parts, 0);
@@ -180,84 +161,8 @@ int cmd__hashmap(int argc, const char **argv)
 		cmd = parts.items[0].string;
 		p1 = parts.nr >= 1 ? parts.items[1].string : NULL;
 		p2 = parts.nr >= 2 ? parts.items[2].string : NULL;
-		if (p1)
-			hash = icase ? strihash(p1) : strhash(p1);
-
-		if (!strcmp("add", cmd) && p1 && p2) {
-
-			/* create entry with key = p1, value = p2 */
-			entry = alloc_test_entry(hash, p1, p2);
-
-			/* add to hashmap */
-			hashmap_add(&map, &entry->ent);
-
-		} else if (!strcmp("put", cmd) && p1 && p2) {
-
-			/* create entry with key = p1, value = p2 */
-			entry = alloc_test_entry(hash, p1, p2);
-
-			/* add / replace entry */
-			entry = hashmap_put_entry(&map, entry, ent);
-
-			/* print and free replaced entry, if any */
-			puts(entry ? get_value(entry) : "NULL");
-			free(entry);
-
-		} else if (!strcmp("get", cmd) && p1) {
-			/* lookup entry in hashmap */
-			entry = hashmap_get_entry_from_hash(&map, hash, p1,
-							struct test_entry, ent);
-
-			/* print result */
-			if (!entry)
-				puts("NULL");
-			hashmap_for_each_entry_from(&map, entry, ent)
-				puts(get_value(entry));
-
-		} else if (!strcmp("remove", cmd) && p1) {
-
-			/* setup static key */
-			struct hashmap_entry key;
-			struct hashmap_entry *rm;
-			hashmap_entry_init(&key, hash);
-
-			/* remove entry from hashmap */
-			rm = hashmap_remove(&map, &key, p1);
-			entry = rm ? container_of(rm, struct test_entry, ent)
-					: NULL;
-
-			/* print result and free entry*/
-			puts(entry ? get_value(entry) : "NULL");
-			free(entry);
-
-		} else if (!strcmp("iterate", cmd)) {
-			struct hashmap_iter iter;
-
-			hashmap_for_each_entry(&map, &iter, entry,
-						ent /* member name */)
-				printf("%s %s\n", entry->key, get_value(entry));
-
-		} else if (!strcmp("size", cmd)) {
-
-			/* print table sizes */
-			printf("%u %u\n", map.tablesize,
-			       hashmap_get_size(&map));
-
-		} else if (!strcmp("intern", cmd) && p1) {
-
-			/* test that strintern works */
-			const char *i1 = strintern(p1);
-			const char *i2 = strintern(p1);
-			if (strcmp(i1, p1))
-				printf("strintern(%s) returns %s\n", p1, i1);
-			else if (i1 == p1)
-				printf("strintern(%s) returns input pointer\n", p1);
-			else if (i1 != i2)
-				printf("strintern(%s) != strintern(%s)", i1, i2);
-			else
-				printf("%s\n", i1);
-
-		} else if (!strcmp("perfhashmap", cmd) && p1 && p2) {
+	
+		if (!strcmp("perfhashmap", cmd) && p1 && p2) {
 
 			perf_hashmap(atoi(p1), atoi(p2));
 
@@ -270,6 +175,5 @@ int cmd__hashmap(int argc, const char **argv)
 
 	string_list_clear(&parts, 0);
 	strbuf_release(&line);
-	hashmap_clear_and_free(&map, struct test_entry, ent);
 	return 0;
 }
diff --git a/t/t0011-hashmap.sh b/t/t0011-hashmap.sh
deleted file mode 100755
index 46e74ad107..0000000000
--- a/t/t0011-hashmap.sh
+++ /dev/null
@@ -1,260 +0,0 @@
-#!/bin/sh
-
-test_description='test hashmap and string hash functions'
-
-TEST_PASSES_SANITIZE_LEAK=true
-. ./test-lib.sh
-
-test_hashmap() {
-	echo "$1" | test-tool hashmap $3 > actual &&
-	echo "$2" > expect &&
-	test_cmp expect actual
-}
-
-test_expect_success 'put' '
-
-test_hashmap "put key1 value1
-put key2 value2
-put fooBarFrotz value3
-put foobarfrotz value4
-size" "NULL
-NULL
-NULL
-NULL
-64 4"
-
-'
-
-test_expect_success 'put (case insensitive)' '
-
-test_hashmap "put key1 value1
-put key2 value2
-put fooBarFrotz value3
-size" "NULL
-NULL
-NULL
-64 3" ignorecase
-
-'
-
-test_expect_success 'replace' '
-
-test_hashmap "put key1 value1
-put key1 value2
-put fooBarFrotz value3
-put fooBarFrotz value4
-size" "NULL
-value1
-NULL
-value3
-64 2"
-
-'
-
-test_expect_success 'replace (case insensitive)' '
-
-test_hashmap "put key1 value1
-put Key1 value2
-put fooBarFrotz value3
-put foobarfrotz value4
-size" "NULL
-value1
-NULL
-value3
-64 2" ignorecase
-
-'
-
-test_expect_success 'get' '
-
-test_hashmap "put key1 value1
-put key2 value2
-put fooBarFrotz value3
-put foobarfrotz value4
-get key1
-get key2
-get fooBarFrotz
-get notInMap" "NULL
-NULL
-NULL
-NULL
-value1
-value2
-value3
-NULL"
-
-'
-
-test_expect_success 'get (case insensitive)' '
-
-test_hashmap "put key1 value1
-put key2 value2
-put fooBarFrotz value3
-get Key1
-get keY2
-get foobarfrotz
-get notInMap" "NULL
-NULL
-NULL
-value1
-value2
-value3
-NULL" ignorecase
-
-'
-
-test_expect_success 'add' '
-
-test_hashmap "add key1 value1
-add key1 value2
-add fooBarFrotz value3
-add fooBarFrotz value4
-get key1
-get fooBarFrotz
-get notInMap" "value2
-value1
-value4
-value3
-NULL"
-
-'
-
-test_expect_success 'add (case insensitive)' '
-
-test_hashmap "add key1 value1
-add Key1 value2
-add fooBarFrotz value3
-add foobarfrotz value4
-get key1
-get Foobarfrotz
-get notInMap" "value2
-value1
-value4
-value3
-NULL" ignorecase
-
-'
-
-test_expect_success 'remove' '
-
-test_hashmap "put key1 value1
-put key2 value2
-put fooBarFrotz value3
-remove key1
-remove key2
-remove notInMap
-size" "NULL
-NULL
-NULL
-value1
-value2
-NULL
-64 1"
-
-'
-
-test_expect_success 'remove (case insensitive)' '
-
-test_hashmap "put key1 value1
-put key2 value2
-put fooBarFrotz value3
-remove Key1
-remove keY2
-remove notInMap
-size" "NULL
-NULL
-NULL
-value1
-value2
-NULL
-64 1" ignorecase
-
-'
-
-test_expect_success 'iterate' '
-	test-tool hashmap >actual.raw <<-\EOF &&
-	put key1 value1
-	put key2 value2
-	put fooBarFrotz value3
-	iterate
-	EOF
-
-	cat >expect <<-\EOF &&
-	NULL
-	NULL
-	NULL
-	fooBarFrotz value3
-	key1 value1
-	key2 value2
-	EOF
-
-	sort <actual.raw >actual &&
-	test_cmp expect actual
-'
-
-test_expect_success 'iterate (case insensitive)' '
-	test-tool hashmap ignorecase >actual.raw <<-\EOF &&
-	put key1 value1
-	put key2 value2
-	put fooBarFrotz value3
-	iterate
-	EOF
-
-	cat >expect <<-\EOF &&
-	NULL
-	NULL
-	NULL
-	fooBarFrotz value3
-	key1 value1
-	key2 value2
-	EOF
-
-	sort <actual.raw >actual &&
-	test_cmp expect actual
-'
-
-test_expect_success 'grow / shrink' '
-
-	rm -f in &&
-	rm -f expect &&
-	for n in $(test_seq 51)
-	do
-		echo put key$n value$n >> in &&
-		echo NULL >> expect || return 1
-	done &&
-	echo size >> in &&
-	echo 64 51 >> expect &&
-	echo put key52 value52 >> in &&
-	echo NULL >> expect &&
-	echo size >> in &&
-	echo 256 52 >> expect &&
-	for n in $(test_seq 12)
-	do
-		echo remove key$n >> in &&
-		echo value$n >> expect || return 1
-	done &&
-	echo size >> in &&
-	echo 256 40 >> expect &&
-	echo remove key40 >> in &&
-	echo value40 >> expect &&
-	echo size >> in &&
-	echo 64 39 >> expect &&
-	test-tool hashmap <in >out &&
-	test_cmp expect out
-
-'
-
-test_expect_success 'string interning' '
-
-test_hashmap "intern value1
-intern Value1
-intern value2
-intern value2
-" "value1
-Value1
-value2
-value2"
-
-'
-
-test_done
diff --git a/t/unit-tests/t-hashmap.c b/t/unit-tests/t-hashmap.c
new file mode 100644
index 0000000000..3112b10b33
--- /dev/null
+++ b/t/unit-tests/t-hashmap.c
@@ -0,0 +1,358 @@
+#include "test-lib.h"
+#include "hashmap.h"
+#include "strbuf.h"
+
+struct test_entry {
+	int padding; /* hashmap entry no longer needs to be the first member */
+	struct hashmap_entry ent;
+	/* key and value as two \0-terminated strings */
+	char key[FLEX_ARRAY];
+};
+
+static int test_entry_cmp(const void *cmp_data,
+			  const struct hashmap_entry *eptr,
+			  const struct hashmap_entry *entry_or_key,
+			  const void *keydata)
+{
+	const int ignore_case = cmp_data ? *((int *)cmp_data) : 0;
+	const struct test_entry *e1, *e2;
+	const char *key = keydata;
+
+	e1 = container_of(eptr, const struct test_entry, ent);
+	e2 = container_of(entry_or_key, const struct test_entry, ent);
+
+	if (ignore_case)
+		return strcasecmp(e1->key, key ? key : e2->key);
+	else
+		return strcmp(e1->key, key ? key : e2->key);
+}
+
+static const char *get_value(const struct test_entry *e)
+{
+	return e->key + strlen(e->key) + 1;
+}
+
+static struct test_entry *alloc_test_entry(unsigned int ignore_case,
+					   const char *key, const char *value)
+{
+	size_t klen = strlen(key);
+	size_t vlen = strlen(value);
+	unsigned int hash = ignore_case ? strihash(key) : strhash(key);
+	struct test_entry *entry = xmalloc(st_add4(sizeof(*entry), klen, vlen, 2));
+
+	hashmap_entry_init(&entry->ent, hash);
+	memcpy(entry->key, key, klen + 1);
+	memcpy(entry->key + klen + 1, value, vlen + 1);
+	return entry;
+}
+
+static struct test_entry *get_test_entry(struct hashmap *map,
+					 unsigned int ignore_case, const char *key)
+{
+	return hashmap_get_entry_from_hash(
+		map, ignore_case ? strihash(key) : strhash(key), key,
+		struct test_entry, ent);
+}
+
+static int key_val_contains(const char *key_val[][2], char seen[], size_t n,
+			    struct test_entry *entry)
+{
+	for (size_t i = 0; i < n; i++) {
+		if (!strcmp(entry->key, key_val[i][0]) &&
+		    !strcmp(get_value(entry), key_val[i][1])) {
+			if (seen[i])
+				return 2;
+			seen[i] = 1;
+			return 0;
+		}
+	}
+	return 1;
+}
+
+static void setup(void (*f)(struct hashmap *map, int ignore_case),
+		  int ignore_case)
+{
+	struct hashmap map = HASHMAP_INIT(test_entry_cmp, &ignore_case);
+
+	f(&map, ignore_case);
+	hashmap_clear_and_free(&map, struct test_entry, ent);
+}
+
+static void t_replace(struct hashmap *map, int ignore_case)
+{
+	struct test_entry *entry;
+
+	entry = alloc_test_entry(ignore_case, "key1", "value1");
+	check_pointer_eq(hashmap_put_entry(map, entry, ent), NULL);
+
+	entry = alloc_test_entry(ignore_case, ignore_case ? "Key1" : "key1",
+				 "value2");
+	entry = hashmap_put_entry(map, entry, ent);
+	if (check(entry != NULL))
+		check_str(get_value(entry), "value1");
+	free(entry);
+
+	entry = alloc_test_entry(ignore_case, "fooBarFrotz", "value3");
+	check_pointer_eq(hashmap_put_entry(map, entry, ent), NULL);
+
+	entry = alloc_test_entry(ignore_case,
+				 ignore_case ? "foobarfrotz" : "fooBarFrotz",
+				 "value4");
+	entry = hashmap_put_entry(map, entry, ent);
+	if (check(entry != NULL))
+		check_str(get_value(entry), "value3");
+	free(entry);
+}
+
+static void t_get(struct hashmap *map, int ignore_case)
+{
+	struct test_entry *entry;
+	const char *key_val[][2] = { { "key1", "value1" },
+				     { "key2", "value2" },
+				     { "fooBarFrotz", "value3" },
+				     { ignore_case ? "key4" : "foobarfrotz", "value4" } };
+	const char *query[][2] = {
+		{ ignore_case ? "Key1" : "key1", "value1" },
+		{ ignore_case ? "keY2" : "key2", "value2" },
+		{ ignore_case ? "foobarfrotz" : "fooBarFrotz", "value3" }
+	};
+
+	for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
+		entry = alloc_test_entry(ignore_case, key_val[i][0], key_val[i][1]);
+		check_pointer_eq(hashmap_put_entry(map, entry, ent), NULL);
+	}
+
+	for (size_t i = 0; i < ARRAY_SIZE(query); i++) {
+		entry = get_test_entry(map, ignore_case, query[i][0]);
+		if (check(entry != NULL))
+			check_str(get_value(entry), query[i][1]);
+		else
+			test_msg("query key: %s", query[i][0]);
+	}
+
+	check_pointer_eq(get_test_entry(map, ignore_case, "notInMap"), NULL);
+	check_int(map->tablesize, ==, 64);
+	check_int(hashmap_get_size(map), ==, ARRAY_SIZE(key_val));
+}
+
+static void t_add(struct hashmap *map, int ignore_case)
+{
+	struct test_entry *entry;
+	const char *key_val[][2] = {
+		{ "key1", "value1" },
+		{ ignore_case ? "Key1" : "key1", "value2" },
+		{ "fooBarFrotz", "value3" },
+		{ ignore_case ? "Foobarfrotz" : "fooBarFrotz", "value4" }
+	};
+	const char *queries[] = { "key1",
+				  ignore_case ? "Foobarfrotz" : "fooBarFrotz" };
+	char seen[ARRAY_SIZE(key_val)] = { 0 };
+
+	for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
+		entry = alloc_test_entry(ignore_case, key_val[i][0], key_val[i][1]);
+		hashmap_add(map, &entry->ent);
+	}
+
+	for (size_t i = 0; i < ARRAY_SIZE(queries); i++) {
+		int count = 0;
+		entry = hashmap_get_entry_from_hash(map,
+			ignore_case ? strihash(queries[i]) :
+				      strhash(queries[i]),
+			queries[i], struct test_entry, ent);
+
+		hashmap_for_each_entry_from(map, entry, ent)
+		{
+			int ret;
+			if (!check_int((ret = key_val_contains(
+						key_val, seen,
+						ARRAY_SIZE(key_val), entry)),
+				       ==, 0)) {
+				switch (ret) {
+				case 1:
+					test_msg("found entry was not given in the input\n"
+						 "    key: %s\n  value: %s",
+						 entry->key, get_value(entry));
+					break;
+				case 2:
+					test_msg("duplicate entry detected\n"
+						 "    key: %s\n  value: %s",
+						 entry->key, get_value(entry));
+					break;
+				}
+			} else {
+				count++;
+			}
+		}
+		check_int(count, ==, 2);
+	}
+
+	for (size_t i = 0; i < ARRAY_SIZE(seen); i++) {
+		if (!check_int(seen[i], ==, 1))
+			test_msg("following key-val pair was not iterated over:\n"
+				 "    key: %s\n  value: %s",
+				 key_val[i][0], key_val[i][1]);
+	}
+
+	check_int(hashmap_get_size(map), ==, ARRAY_SIZE(key_val));
+	check_pointer_eq(get_test_entry(map, ignore_case, "notInMap"), NULL);
+}
+
+static void t_remove(struct hashmap *map, int ignore_case)
+{
+	struct test_entry *entry, *removed;
+	const char *key_val[][2] = { { "key1", "value1" },
+				     { "key2", "value2" },
+				     { "fooBarFrotz", "value3" } };
+	const char *remove[][2] = { { ignore_case ? "Key1" : "key1", "value1" },
+				    { ignore_case ? "keY2" : "key2", "value2" } };
+
+	for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
+		entry = alloc_test_entry(ignore_case, key_val[i][0], key_val[i][1]);
+		check_pointer_eq(hashmap_put_entry(map, entry, ent), NULL);
+	}
+
+	for (size_t i = 0; i < ARRAY_SIZE(remove); i++) {
+		entry = alloc_test_entry(ignore_case, remove[i][0], "");
+		removed = hashmap_remove_entry(map, entry, ent, remove[i][0]);
+		if (check(removed != NULL))
+			check_str(get_value(removed), remove[i][1]);
+		free(entry);
+		free(removed);
+	}
+
+	entry = alloc_test_entry(ignore_case, "notInMap", "");
+	check_pointer_eq(hashmap_remove_entry(map, entry, ent, "notInMap"), NULL);
+	free(entry);
+
+	check_int(map->tablesize, ==, 64);
+	check_int(hashmap_get_size(map), ==, ARRAY_SIZE(key_val) - ARRAY_SIZE(remove));
+}
+
+static void t_iterate(struct hashmap *map, int ignore_case)
+{
+	struct test_entry *entry;
+	struct hashmap_iter iter;
+	const char *key_val[][2] = { { "key1", "value1" },
+				     { "key2", "value2" },
+				     { "fooBarFrotz", "value3" } };
+	char seen[ARRAY_SIZE(key_val)] = { 0 };
+
+	for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
+		entry = alloc_test_entry(ignore_case, key_val[i][0], key_val[i][1]);
+		check_pointer_eq(hashmap_put_entry(map, entry, ent), NULL);
+	}
+
+	hashmap_for_each_entry(map, &iter, entry, ent /* member name */)
+	{
+		int ret;
+		if (!check_int((ret = key_val_contains(key_val, seen,
+						       ARRAY_SIZE(key_val),
+						       entry)), ==, 0)) {
+			switch (ret) {
+			case 1:
+				test_msg("found entry was not given in the input\n"
+					 "    key: %s\n  value: %s",
+					 entry->key, get_value(entry));
+				break;
+			case 2:
+				test_msg("duplicate entry detected\n"
+					 "    key: %s\n  value: %s",
+					 entry->key, get_value(entry));
+				break;
+			}
+		}
+	}
+
+	for (size_t i = 0; i < ARRAY_SIZE(seen); i++) {
+		if (!check_int(seen[i], ==, 1))
+			test_msg("following key-val pair was not iterated over:\n"
+				 "    key: %s\n  value: %s",
+				 key_val[i][0], key_val[i][1]);
+	}
+
+	check_int(hashmap_get_size(map), ==, ARRAY_SIZE(key_val));
+}
+
+static void t_alloc(struct hashmap *map, int ignore_case)
+{
+	struct test_entry *entry, *removed;
+
+	for (int i = 1; i <= 51; i++) {
+		char *key = xstrfmt("key%d", i);
+		char *value = xstrfmt("value%d", i);
+		entry = alloc_test_entry(ignore_case, key, value);
+		check_pointer_eq(hashmap_put_entry(map, entry, ent), NULL);
+		free(key);
+		free(value);
+	}
+	check_int(map->tablesize, ==, 64);
+	check_int(hashmap_get_size(map), ==, 51);
+
+	entry = alloc_test_entry(ignore_case, "key52", "value52");
+	check_pointer_eq(hashmap_put_entry(map, entry, ent), NULL);
+	check_int(map->tablesize, ==, 256);
+	check_int(hashmap_get_size(map), ==, 52);
+
+	for (int i = 1; i <= 12; i++) {
+		char *key = xstrfmt("key%d", i);
+		char *value = xstrfmt("value%d", i);
+
+		entry = alloc_test_entry(ignore_case, key, "");
+		removed = hashmap_remove_entry(map, entry, ent, key);
+		if (check(removed != NULL))
+			check_str(value, get_value(removed));
+		free(key);
+		free(value);
+		free(entry);
+		free(removed);
+	}
+	check_int(map->tablesize, ==, 256);
+	check_int(hashmap_get_size(map), ==, 40);
+
+	entry = alloc_test_entry(ignore_case, "key40", "");
+	removed = hashmap_remove_entry(map, entry, ent, "key40");
+	if (check(removed != NULL))
+		check_str("value40", get_value(removed));
+	check_int(map->tablesize, ==, 64);
+	check_int(hashmap_get_size(map), ==, 39);
+	free(entry);
+	free(removed);
+}
+
+static void t_intern(struct hashmap *map, int ignore_case)
+{
+	const char *values[] = { "value1", "Value1", "value2", "value2" };
+
+	for (size_t i = 0; i < ARRAY_SIZE(values); i++) {
+		const char *i1 = strintern(values[i]);
+		const char *i2 = strintern(values[i]);
+
+		if (!check(!strcmp(i1, values[i])))
+			test_msg("strintern(%s) returns %s\n", values[i], i1);
+		else if (!check(i1 != values[i]))
+			test_msg("strintern(%s) returns input pointer\n",
+				 values[i]);
+		else if (!check_pointer_eq(i1, i2))
+			test_msg("address('%s') != address('%s'), so strintern('%s') != strintern('%s')",
+				 i1, i2, values[i], values[i]);
+		else
+			check_str(i1, values[i]);
+	}
+}
+
+int cmd_main(int argc UNUSED, const char **argv UNUSED)
+{
+	TEST(setup(t_replace, 0), "replace works");
+	TEST(setup(t_replace, 1), "replace (case insensitive) works");
+	TEST(setup(t_get, 0), "get works");
+	TEST(setup(t_get, 1), "get (case insensitive) works");
+	TEST(setup(t_add, 0), "add works");
+	TEST(setup(t_add, 1), "add (case insensitive) works");
+	TEST(setup(t_remove, 0), "remove works");
+	TEST(setup(t_remove, 1), "remove (case insensitive) works");
+	TEST(setup(t_iterate, 0), "iterate works");
+	TEST(setup(t_iterate, 1), "iterate (case insensitive) works");
+	TEST(setup(t_alloc, 0), "grow / shrink works");
+	TEST(setup(t_intern, 0), "string interning works");
+	return test_done();
+}
-- 
2.45.2
Ghanshyam Thakkar· Jul 12, 2024, 00:00 UTC · re: Ghanshyam Thakkar · lore

Re: [GSoC][PATCH v3] t: port helper/test-hashmap.c to unit-tests/t-hashmap.c

Ghanshyam Thakkar <shyamthakkar001@gmail.com> wrote:
Show 18 quoted lines
> helper/test-hashmap.c along with t0011-hashmap.sh test the hashmap.h
> library. Migrate them to the unit testing framework for better
> debugging, runtime performance and concise code.
>
> Along with the migration, make 'add' tests from the shellscript order
> agnostic in unit tests, since they iterate over entries with the same
> keys and we do not guarantee the order.
>
> The helper/test-hashmap.c is still not removed because it contains a
> performance test meant to be run by the user directly (not used in
> t/perf). And it makes sense for such a utility to be a helper.
>
> Mentored-by: Christian Couder <chriscool@tuxfamily.org>
> Mentored-by: Kaartic Sivaraam <kaartic.sivaraam@gmail.com>
> Helped-by: Josh Steadmon <steadmon@google.com>
> Helped-by: Phillip Wood <phillip.wood123@gmail.com>
> Signed-off-by: Ghanshyam Thakkar <shyamthakkar001@gmail.com>
> ---
Changes in v3:
- I have removed the t_put() tests as they were identical to
  t_get() minus the size checks at the end. So, I've added those size
  checks to t_get().
- Besides that I've replaced check() with check_pointer_eq() where ever
  applicable.
  
- And replaced the third elements of key_val[] which recorded
  the presence of certain key-val pair with 'char seen[]'.
- Added some test_msg() statements for better debugging.
- Fixed typo in commit message.
Thanks.
Show 1068 quoted lines
> Range-diff against v2:
> 1: bbb4f2f23e ! 1: 03ba77665e t: port helper/test-hashmap.c to
> unit-tests/t-hashmap.c
> @@ Commit message
>      
> helper/test-hashmap.c along with t0011-hashmap.sh test the hashmap.h
> library. Migrate them to the unit testing framework for better
> - debugging, runtime performance and consice code.
> + debugging, runtime performance and concise code.
>      
> Along with the migration, make 'add' tests from the shellscript order
> agnostic in unit tests, since they iterate over entries with the same
> @@ Commit message
>      
> Mentored-by: Christian Couder <chriscool@tuxfamily.org>
> Mentored-by: Kaartic Sivaraam <kaartic.sivaraam@gmail.com>
> + Helped-by: Josh Steadmon <steadmon@google.com>
> + Helped-by: Phillip Wood <phillip.wood123@gmail.com>
> Signed-off-by: Ghanshyam Thakkar <shyamthakkar001@gmail.com>
>      
> ## Makefile ##
> @@ t/unit-tests/t-hashmap.c (new)
> + struct test_entry, ent);
> +}
> +
> -+static int key_val_contains(const char *key_val[][3], size_t n,
> ++static int key_val_contains(const char *key_val[][2], char seen[],
> size_t n,
> + struct test_entry *entry)
> +{
> + for (size_t i = 0; i < n; i++) {
> + if (!strcmp(entry->key, key_val[i][0]) &&
> + !strcmp(get_value(entry), key_val[i][1])) {
> -+ if (!strcmp(key_val[i][2], "USED"))
> ++ if (seen[i])
> + return 2;
> -+ key_val[i][2] = "USED";
> ++ seen[i] = 1;
> + return 0;
> + }
> + }
> @@ t/unit-tests/t-hashmap.c (new)
> + hashmap_clear_and_free(&map, struct test_entry, ent);
> +}
> +
> -+static void t_put(struct hashmap *map, int ignore_case)
> -+{
> -+ struct test_entry *entry;
> -+ const char *key_val[][2] = { { "key1", "value1" },
> -+ { "key2", "value2" },
> -+ { "fooBarFrotz", "value3" } };
> -+
> -+ for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
> -+ entry = alloc_test_entry(ignore_case, key_val[i][0], key_val[i][1]);
> -+ check(hashmap_put_entry(map, entry, ent) == NULL);
> -+ }
> -+
> -+ entry = alloc_test_entry(ignore_case, "foobarfrotz", "value4");
> -+ entry = hashmap_put_entry(map, entry, ent);
> -+ check(ignore_case ? entry != NULL : entry == NULL);
> -+ free(entry);
> -+
> -+ check_int(map->tablesize, ==, 64);
> -+ check_int(hashmap_get_size(map), ==,
> -+ ignore_case ? ARRAY_SIZE(key_val) : ARRAY_SIZE(key_val) + 1);
> -+}
> -+
> +static void t_replace(struct hashmap *map, int ignore_case)
> +{
> + struct test_entry *entry;
> +
> + entry = alloc_test_entry(ignore_case, "key1", "value1");
> -+ check(hashmap_put_entry(map, entry, ent) == NULL);
> ++ check_pointer_eq(hashmap_put_entry(map, entry, ent), NULL);
> +
> + entry = alloc_test_entry(ignore_case, ignore_case ? "Key1" : "key1",
> + "value2");
> @@ t/unit-tests/t-hashmap.c (new)
> + free(entry);
> +
> + entry = alloc_test_entry(ignore_case, "fooBarFrotz", "value3");
> -+ check(hashmap_put_entry(map, entry, ent) == NULL);
> ++ check_pointer_eq(hashmap_put_entry(map, entry, ent), NULL);
> +
> + entry = alloc_test_entry(ignore_case,
> + ignore_case ? "foobarfrotz" : "fooBarFrotz",
> @@ t/unit-tests/t-hashmap.c (new)
> +
> + for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
> + entry = alloc_test_entry(ignore_case, key_val[i][0], key_val[i][1]);
> -+ check(hashmap_put_entry(map, entry, ent) == NULL);
> ++ check_pointer_eq(hashmap_put_entry(map, entry, ent), NULL);
> + }
> +
> + for (size_t i = 0; i < ARRAY_SIZE(query); i++) {
> + entry = get_test_entry(map, ignore_case, query[i][0]);
> + if (check(entry != NULL))
> + check_str(get_value(entry), query[i][1]);
> ++ else
> ++ test_msg("query key: %s", query[i][0]);
> + }
> +
> -+ check(get_test_entry(map, ignore_case, "notInMap") == NULL);
> ++ check_pointer_eq(get_test_entry(map, ignore_case, "notInMap"), NULL);
> ++ check_int(map->tablesize, ==, 64);
> ++ check_int(hashmap_get_size(map), ==, ARRAY_SIZE(key_val));
> +}
> +
> +static void t_add(struct hashmap *map, int ignore_case)
> +{
> + struct test_entry *entry;
> -+ const char *key_val[][3] = {
> -+ { "key1", "value1", "UNUSED" },
> -+ { ignore_case ? "Key1" : "key1", "value2", "UNUSED" },
> -+ { "fooBarFrotz", "value3", "UNUSED" },
> -+ { ignore_case ? "Foobarfrotz" : "fooBarFrotz", "value4", "UNUSED" }
> ++ const char *key_val[][2] = {
> ++ { "key1", "value1" },
> ++ { ignore_case ? "Key1" : "key1", "value2" },
> ++ { "fooBarFrotz", "value3" },
> ++ { ignore_case ? "Foobarfrotz" : "fooBarFrotz", "value4" }
> + };
> + const char *queries[] = { "key1",
> + ignore_case ? "Foobarfrotz" : "fooBarFrotz" };
> ++ char seen[ARRAY_SIZE(key_val)] = { 0 };
> +
> + for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
> + entry = alloc_test_entry(ignore_case, key_val[i][0], key_val[i][1]);
> @@ t/unit-tests/t-hashmap.c (new)
> + {
> + int ret;
> + if (!check_int((ret = key_val_contains(
> -+ key_val, ARRAY_SIZE(key_val),
> -+ entry)), ==, 0)) {
> ++ key_val, seen,
> ++ ARRAY_SIZE(key_val), entry)),
> ++ ==, 0)) {
> + switch (ret) {
> + case 1:
> + test_msg("found entry was not given in the input\n"
> @@ t/unit-tests/t-hashmap.c (new)
> + }
> + check_int(count, ==, 2);
> + }
> ++
> ++ for (size_t i = 0; i < ARRAY_SIZE(seen); i++) {
> ++ if (!check_int(seen[i], ==, 1))
> ++ test_msg("following key-val pair was not iterated over:\n"
> ++ " key: %s\n value: %s",
> ++ key_val[i][0], key_val[i][1]);
> ++ }
> ++
> + check_int(hashmap_get_size(map), ==, ARRAY_SIZE(key_val));
> -+ check(get_test_entry(map, ignore_case, "notInMap") == NULL);
> ++ check_pointer_eq(get_test_entry(map, ignore_case, "notInMap"), NULL);
> +}
> +
> +static void t_remove(struct hashmap *map, int ignore_case)
> @@ t/unit-tests/t-hashmap.c (new)
> +
> + for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
> + entry = alloc_test_entry(ignore_case, key_val[i][0], key_val[i][1]);
> -+ check(hashmap_put_entry(map, entry, ent) == NULL);
> ++ check_pointer_eq(hashmap_put_entry(map, entry, ent), NULL);
> + }
> +
> + for (size_t i = 0; i < ARRAY_SIZE(remove); i++) {
> @@ t/unit-tests/t-hashmap.c (new)
> + }
> +
> + entry = alloc_test_entry(ignore_case, "notInMap", "");
> -+ check(hashmap_remove_entry(map, entry, ent, "notInMap") == NULL);
> ++ check_pointer_eq(hashmap_remove_entry(map, entry, ent, "notInMap"),
> NULL);
> + free(entry);
> ++
> ++ check_int(map->tablesize, ==, 64);
> ++ check_int(hashmap_get_size(map), ==, ARRAY_SIZE(key_val) -
> ARRAY_SIZE(remove));
> +}
> +
> +static void t_iterate(struct hashmap *map, int ignore_case)
> +{
> + struct test_entry *entry;
> + struct hashmap_iter iter;
> -+ const char *key_val[][3] = { { "key1", "value1", "UNUSED" },
> -+ { "key2", "value2", "UNUSED" },
> -+ { "fooBarFrotz", "value3", "UNUSED" } };
> -+ int count = 0;
> ++ const char *key_val[][2] = { { "key1", "value1" },
> ++ { "key2", "value2" },
> ++ { "fooBarFrotz", "value3" } };
> ++ char seen[ARRAY_SIZE(key_val)] = { 0 };
> +
> + for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
> + entry = alloc_test_entry(ignore_case, key_val[i][0], key_val[i][1]);
> -+ check(hashmap_put_entry(map, entry, ent) == NULL);
> ++ check_pointer_eq(hashmap_put_entry(map, entry, ent), NULL);
> + }
> +
> + hashmap_for_each_entry(map, &iter, entry, ent /* member name */)
> + {
> + int ret;
> -+ if (!check_int((ret = key_val_contains(key_val, ARRAY_SIZE(key_val),
> ++ if (!check_int((ret = key_val_contains(key_val, seen,
> ++ ARRAY_SIZE(key_val),
> + entry)), ==, 0)) {
> + switch (ret) {
> + case 1:
> @@ t/unit-tests/t-hashmap.c (new)
> + entry->key, get_value(entry));
> + break;
> + }
> -+ } else {
> -+ count++;
> + }
> + }
> -+ check_int(count, ==, ARRAY_SIZE(key_val));
> ++
> ++ for (size_t i = 0; i < ARRAY_SIZE(seen); i++) {
> ++ if (!check_int(seen[i], ==, 1))
> ++ test_msg("following key-val pair was not iterated over:\n"
> ++ " key: %s\n value: %s",
> ++ key_val[i][0], key_val[i][1]);
> ++ }
> ++
> + check_int(hashmap_get_size(map), ==, ARRAY_SIZE(key_val));
> +}
> +
> @@ t/unit-tests/t-hashmap.c (new)
> + char *key = xstrfmt("key%d", i);
> + char *value = xstrfmt("value%d", i);
> + entry = alloc_test_entry(ignore_case, key, value);
> -+ check(hashmap_put_entry(map, entry, ent) == NULL);
> ++ check_pointer_eq(hashmap_put_entry(map, entry, ent), NULL);
> + free(key);
> + free(value);
> + }
> @@ t/unit-tests/t-hashmap.c (new)
> + check_int(hashmap_get_size(map), ==, 51);
> +
> + entry = alloc_test_entry(ignore_case, "key52", "value52");
> -+ check(hashmap_put_entry(map, entry, ent) == NULL);
> ++ check_pointer_eq(hashmap_put_entry(map, entry, ent), NULL);
> + check_int(map->tablesize, ==, 256);
> + check_int(hashmap_get_size(map), ==, 52);
> +
> @@ t/unit-tests/t-hashmap.c (new)
> + else if (!check(i1 != values[i]))
> + test_msg("strintern(%s) returns input pointer\n",
> + values[i]);
> -+ else if (!check(i1 == i2))
> ++ else if (!check_pointer_eq(i1, i2))
> + test_msg("address('%s') != address('%s'), so strintern('%s') !=
> strintern('%s')",
> + i1, i2, values[i], values[i]);
> + else
> @@ t/unit-tests/t-hashmap.c (new)
> +
> +int cmd_main(int argc UNUSED, const char **argv UNUSED)
> +{
> -+ TEST(setup(t_put, 0), "put works");
> -+ TEST(setup(t_put, 1), "put (case insensitive) works");
> + TEST(setup(t_replace, 0), "replace works");
> + TEST(setup(t_replace, 1), "replace (case insensitive) works");
> + TEST(setup(t_get, 0), "get works");
>
> Makefile | 1 +
> t/helper/test-hashmap.c | 100 +----------
> t/t0011-hashmap.sh | 260 ----------------------------
> t/unit-tests/t-hashmap.c | 358 +++++++++++++++++++++++++++++++++++++++
> 4 files changed, 361 insertions(+), 358 deletions(-)
> delete mode 100755 t/t0011-hashmap.sh
> create mode 100644 t/unit-tests/t-hashmap.c
>
> diff --git a/Makefile b/Makefile
> index 3eab701b10..74bb026610 100644
> --- a/Makefile
> +++ b/Makefile
> @@ -1336,6 +1336,7 @@ THIRD_PARTY_SOURCES += sha1dc/%
> UNIT_TEST_PROGRAMS += t-ctype
> UNIT_TEST_PROGRAMS += t-example-decorate
> UNIT_TEST_PROGRAMS += t-hash
> +UNIT_TEST_PROGRAMS += t-hashmap
> UNIT_TEST_PROGRAMS += t-mem-pool
> UNIT_TEST_PROGRAMS += t-oidtree
> UNIT_TEST_PROGRAMS += t-prio-queue
> diff --git a/t/helper/test-hashmap.c b/t/helper/test-hashmap.c
> index 2912899558..7b854a7030 100644
> --- a/t/helper/test-hashmap.c
> +++ b/t/helper/test-hashmap.c
> @@ -12,11 +12,6 @@ struct test_entry
> char key[FLEX_ARRAY];
> };
>  
> -static const char *get_value(const struct test_entry *e)
> -{
> - return e->key + strlen(e->key) + 1;
> -}
> -
> static int test_entry_cmp(const void *cmp_data,
> const struct hashmap_entry *eptr,
> const struct hashmap_entry *entry_or_key,
> @@ -141,30 +136,16 @@ static void perf_hashmap(unsigned int method,
> unsigned int rounds)
> /*
> * Read stdin line by line and print result of commands to stdout:
> *
> - * hash key -> strhash(key) memhash(key) strihash(key) memihash(key)
> - * put key value -> NULL / old value
> - * get key -> NULL / value
> - * remove key -> NULL / old value
> - * iterate -> key1 value1\nkey2 value2\n...
> - * size -> tablesize numentries
> - *
> * perfhashmap method rounds -> test hashmap.[ch] performance
> */
> int cmd__hashmap(int argc, const char **argv)
> {
> struct string_list parts = STRING_LIST_INIT_NODUP;
> struct strbuf line = STRBUF_INIT;
> - int icase;
> - struct hashmap map = HASHMAP_INIT(test_entry_cmp, &icase);
> -
> - /* init hash map */
> - icase = argc > 1 && !strcmp("ignorecase", argv[1]);
>  
> /* process commands from stdin */
> while (strbuf_getline(&line, stdin) != EOF) {
> char *cmd, *p1, *p2;
> - unsigned int hash = 0;
> - struct test_entry *entry;
>  
> /* break line into command and up to two parameters */
> string_list_setlen(&parts, 0);
> @@ -180,84 +161,8 @@ int cmd__hashmap(int argc, const char **argv)
> cmd = parts.items[0].string;
> p1 = parts.nr >= 1 ? parts.items[1].string : NULL;
> p2 = parts.nr >= 2 ? parts.items[2].string : NULL;
> - if (p1)
> - hash = icase ? strihash(p1) : strhash(p1);
> -
> - if (!strcmp("add", cmd) && p1 && p2) {
> -
> - /* create entry with key = p1, value = p2 */
> - entry = alloc_test_entry(hash, p1, p2);
> -
> - /* add to hashmap */
> - hashmap_add(&map, &entry->ent);
> -
> - } else if (!strcmp("put", cmd) && p1 && p2) {
> -
> - /* create entry with key = p1, value = p2 */
> - entry = alloc_test_entry(hash, p1, p2);
> -
> - /* add / replace entry */
> - entry = hashmap_put_entry(&map, entry, ent);
> -
> - /* print and free replaced entry, if any */
> - puts(entry ? get_value(entry) : "NULL");
> - free(entry);
> -
> - } else if (!strcmp("get", cmd) && p1) {
> - /* lookup entry in hashmap */
> - entry = hashmap_get_entry_from_hash(&map, hash, p1,
> - struct test_entry, ent);
> -
> - /* print result */
> - if (!entry)
> - puts("NULL");
> - hashmap_for_each_entry_from(&map, entry, ent)
> - puts(get_value(entry));
> -
> - } else if (!strcmp("remove", cmd) && p1) {
> -
> - /* setup static key */
> - struct hashmap_entry key;
> - struct hashmap_entry *rm;
> - hashmap_entry_init(&key, hash);
> -
> - /* remove entry from hashmap */
> - rm = hashmap_remove(&map, &key, p1);
> - entry = rm ? container_of(rm, struct test_entry, ent)
> - : NULL;
> -
> - /* print result and free entry*/
> - puts(entry ? get_value(entry) : "NULL");
> - free(entry);
> -
> - } else if (!strcmp("iterate", cmd)) {
> - struct hashmap_iter iter;
> -
> - hashmap_for_each_entry(&map, &iter, entry,
> - ent /* member name */)
> - printf("%s %s\n", entry->key, get_value(entry));
> -
> - } else if (!strcmp("size", cmd)) {
> -
> - /* print table sizes */
> - printf("%u %u\n", map.tablesize,
> - hashmap_get_size(&map));
> -
> - } else if (!strcmp("intern", cmd) && p1) {
> -
> - /* test that strintern works */
> - const char *i1 = strintern(p1);
> - const char *i2 = strintern(p1);
> - if (strcmp(i1, p1))
> - printf("strintern(%s) returns %s\n", p1, i1);
> - else if (i1 == p1)
> - printf("strintern(%s) returns input pointer\n", p1);
> - else if (i1 != i2)
> - printf("strintern(%s) != strintern(%s)", i1, i2);
> - else
> - printf("%s\n", i1);
> -
> - } else if (!strcmp("perfhashmap", cmd) && p1 && p2) {
> +
> + if (!strcmp("perfhashmap", cmd) && p1 && p2) {
>  
> perf_hashmap(atoi(p1), atoi(p2));
>  
> @@ -270,6 +175,5 @@ int cmd__hashmap(int argc, const char **argv)
>  
> string_list_clear(&parts, 0);
> strbuf_release(&line);
> - hashmap_clear_and_free(&map, struct test_entry, ent);
> return 0;
> }
> diff --git a/t/t0011-hashmap.sh b/t/t0011-hashmap.sh
> deleted file mode 100755
> index 46e74ad107..0000000000
> --- a/t/t0011-hashmap.sh
> +++ /dev/null
> @@ -1,260 +0,0 @@
> -#!/bin/sh
> -
> -test_description='test hashmap and string hash functions'
> -
> -TEST_PASSES_SANITIZE_LEAK=true
> -. ./test-lib.sh
> -
> -test_hashmap() {
> - echo "$1" | test-tool hashmap $3 > actual &&
> - echo "$2" > expect &&
> - test_cmp expect actual
> -}
> -
> -test_expect_success 'put' '
> -
> -test_hashmap "put key1 value1
> -put key2 value2
> -put fooBarFrotz value3
> -put foobarfrotz value4
> -size" "NULL
> -NULL
> -NULL
> -NULL
> -64 4"
> -
> -'
> -
> -test_expect_success 'put (case insensitive)' '
> -
> -test_hashmap "put key1 value1
> -put key2 value2
> -put fooBarFrotz value3
> -size" "NULL
> -NULL
> -NULL
> -64 3" ignorecase
> -
> -'
> -
> -test_expect_success 'replace' '
> -
> -test_hashmap "put key1 value1
> -put key1 value2
> -put fooBarFrotz value3
> -put fooBarFrotz value4
> -size" "NULL
> -value1
> -NULL
> -value3
> -64 2"
> -
> -'
> -
> -test_expect_success 'replace (case insensitive)' '
> -
> -test_hashmap "put key1 value1
> -put Key1 value2
> -put fooBarFrotz value3
> -put foobarfrotz value4
> -size" "NULL
> -value1
> -NULL
> -value3
> -64 2" ignorecase
> -
> -'
> -
> -test_expect_success 'get' '
> -
> -test_hashmap "put key1 value1
> -put key2 value2
> -put fooBarFrotz value3
> -put foobarfrotz value4
> -get key1
> -get key2
> -get fooBarFrotz
> -get notInMap" "NULL
> -NULL
> -NULL
> -NULL
> -value1
> -value2
> -value3
> -NULL"
> -
> -'
> -
> -test_expect_success 'get (case insensitive)' '
> -
> -test_hashmap "put key1 value1
> -put key2 value2
> -put fooBarFrotz value3
> -get Key1
> -get keY2
> -get foobarfrotz
> -get notInMap" "NULL
> -NULL
> -NULL
> -value1
> -value2
> -value3
> -NULL" ignorecase
> -
> -'
> -
> -test_expect_success 'add' '
> -
> -test_hashmap "add key1 value1
> -add key1 value2
> -add fooBarFrotz value3
> -add fooBarFrotz value4
> -get key1
> -get fooBarFrotz
> -get notInMap" "value2
> -value1
> -value4
> -value3
> -NULL"
> -
> -'
> -
> -test_expect_success 'add (case insensitive)' '
> -
> -test_hashmap "add key1 value1
> -add Key1 value2
> -add fooBarFrotz value3
> -add foobarfrotz value4
> -get key1
> -get Foobarfrotz
> -get notInMap" "value2
> -value1
> -value4
> -value3
> -NULL" ignorecase
> -
> -'
> -
> -test_expect_success 'remove' '
> -
> -test_hashmap "put key1 value1
> -put key2 value2
> -put fooBarFrotz value3
> -remove key1
> -remove key2
> -remove notInMap
> -size" "NULL
> -NULL
> -NULL
> -value1
> -value2
> -NULL
> -64 1"
> -
> -'
> -
> -test_expect_success 'remove (case insensitive)' '
> -
> -test_hashmap "put key1 value1
> -put key2 value2
> -put fooBarFrotz value3
> -remove Key1
> -remove keY2
> -remove notInMap
> -size" "NULL
> -NULL
> -NULL
> -value1
> -value2
> -NULL
> -64 1" ignorecase
> -
> -'
> -
> -test_expect_success 'iterate' '
> - test-tool hashmap >actual.raw <<-\EOF &&
> - put key1 value1
> - put key2 value2
> - put fooBarFrotz value3
> - iterate
> - EOF
> -
> - cat >expect <<-\EOF &&
> - NULL
> - NULL
> - NULL
> - fooBarFrotz value3
> - key1 value1
> - key2 value2
> - EOF
> -
> - sort <actual.raw >actual &&
> - test_cmp expect actual
> -'
> -
> -test_expect_success 'iterate (case insensitive)' '
> - test-tool hashmap ignorecase >actual.raw <<-\EOF &&
> - put key1 value1
> - put key2 value2
> - put fooBarFrotz value3
> - iterate
> - EOF
> -
> - cat >expect <<-\EOF &&
> - NULL
> - NULL
> - NULL
> - fooBarFrotz value3
> - key1 value1
> - key2 value2
> - EOF
> -
> - sort <actual.raw >actual &&
> - test_cmp expect actual
> -'
> -
> -test_expect_success 'grow / shrink' '
> -
> - rm -f in &&
> - rm -f expect &&
> - for n in $(test_seq 51)
> - do
> - echo put key$n value$n >> in &&
> - echo NULL >> expect || return 1
> - done &&
> - echo size >> in &&
> - echo 64 51 >> expect &&
> - echo put key52 value52 >> in &&
> - echo NULL >> expect &&
> - echo size >> in &&
> - echo 256 52 >> expect &&
> - for n in $(test_seq 12)
> - do
> - echo remove key$n >> in &&
> - echo value$n >> expect || return 1
> - done &&
> - echo size >> in &&
> - echo 256 40 >> expect &&
> - echo remove key40 >> in &&
> - echo value40 >> expect &&
> - echo size >> in &&
> - echo 64 39 >> expect &&
> - test-tool hashmap <in >out &&
> - test_cmp expect out
> -
> -'
> -
> -test_expect_success 'string interning' '
> -
> -test_hashmap "intern value1
> -intern Value1
> -intern value2
> -intern value2
> -" "value1
> -Value1
> -value2
> -value2"
> -
> -'
> -
> -test_done
> diff --git a/t/unit-tests/t-hashmap.c b/t/unit-tests/t-hashmap.c
> new file mode 100644
> index 0000000000..3112b10b33
> --- /dev/null
> +++ b/t/unit-tests/t-hashmap.c
> @@ -0,0 +1,358 @@
> +#include "test-lib.h"
> +#include "hashmap.h"
> +#include "strbuf.h"
> +
> +struct test_entry {
> + int padding; /* hashmap entry no longer needs to be the first member
> */
> + struct hashmap_entry ent;
> + /* key and value as two \0-terminated strings */
> + char key[FLEX_ARRAY];
> +};
> +
> +static int test_entry_cmp(const void *cmp_data,
> + const struct hashmap_entry *eptr,
> + const struct hashmap_entry *entry_or_key,
> + const void *keydata)
> +{
> + const int ignore_case = cmp_data ? *((int *)cmp_data) : 0;
> + const struct test_entry *e1, *e2;
> + const char *key = keydata;
> +
> + e1 = container_of(eptr, const struct test_entry, ent);
> + e2 = container_of(entry_or_key, const struct test_entry, ent);
> +
> + if (ignore_case)
> + return strcasecmp(e1->key, key ? key : e2->key);
> + else
> + return strcmp(e1->key, key ? key : e2->key);
> +}
> +
> +static const char *get_value(const struct test_entry *e)
> +{
> + return e->key + strlen(e->key) + 1;
> +}
> +
> +static struct test_entry *alloc_test_entry(unsigned int ignore_case,
> + const char *key, const char *value)
> +{
> + size_t klen = strlen(key);
> + size_t vlen = strlen(value);
> + unsigned int hash = ignore_case ? strihash(key) : strhash(key);
> + struct test_entry *entry = xmalloc(st_add4(sizeof(*entry), klen, vlen,
> 2));
> +
> + hashmap_entry_init(&entry->ent, hash);
> + memcpy(entry->key, key, klen + 1);
> + memcpy(entry->key + klen + 1, value, vlen + 1);
> + return entry;
> +}
> +
> +static struct test_entry *get_test_entry(struct hashmap *map,
> + unsigned int ignore_case, const char *key)
> +{
> + return hashmap_get_entry_from_hash(
> + map, ignore_case ? strihash(key) : strhash(key), key,
> + struct test_entry, ent);
> +}
> +
> +static int key_val_contains(const char *key_val[][2], char seen[],
> size_t n,
> + struct test_entry *entry)
> +{
> + for (size_t i = 0; i < n; i++) {
> + if (!strcmp(entry->key, key_val[i][0]) &&
> + !strcmp(get_value(entry), key_val[i][1])) {
> + if (seen[i])
> + return 2;
> + seen[i] = 1;
> + return 0;
> + }
> + }
> + return 1;
> +}
> +
> +static void setup(void (*f)(struct hashmap *map, int ignore_case),
> + int ignore_case)
> +{
> + struct hashmap map = HASHMAP_INIT(test_entry_cmp, &ignore_case);
> +
> + f(&map, ignore_case);
> + hashmap_clear_and_free(&map, struct test_entry, ent);
> +}
> +
> +static void t_replace(struct hashmap *map, int ignore_case)
> +{
> + struct test_entry *entry;
> +
> + entry = alloc_test_entry(ignore_case, "key1", "value1");
> + check_pointer_eq(hashmap_put_entry(map, entry, ent), NULL);
> +
> + entry = alloc_test_entry(ignore_case, ignore_case ? "Key1" : "key1",
> + "value2");
> + entry = hashmap_put_entry(map, entry, ent);
> + if (check(entry != NULL))
> + check_str(get_value(entry), "value1");
> + free(entry);
> +
> + entry = alloc_test_entry(ignore_case, "fooBarFrotz", "value3");
> + check_pointer_eq(hashmap_put_entry(map, entry, ent), NULL);
> +
> + entry = alloc_test_entry(ignore_case,
> + ignore_case ? "foobarfrotz" : "fooBarFrotz",
> + "value4");
> + entry = hashmap_put_entry(map, entry, ent);
> + if (check(entry != NULL))
> + check_str(get_value(entry), "value3");
> + free(entry);
> +}
> +
> +static void t_get(struct hashmap *map, int ignore_case)
> +{
> + struct test_entry *entry;
> + const char *key_val[][2] = { { "key1", "value1" },
> + { "key2", "value2" },
> + { "fooBarFrotz", "value3" },
> + { ignore_case ? "key4" : "foobarfrotz", "value4" } };
> + const char *query[][2] = {
> + { ignore_case ? "Key1" : "key1", "value1" },
> + { ignore_case ? "keY2" : "key2", "value2" },
> + { ignore_case ? "foobarfrotz" : "fooBarFrotz", "value3" }
> + };
> +
> + for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
> + entry = alloc_test_entry(ignore_case, key_val[i][0], key_val[i][1]);
> + check_pointer_eq(hashmap_put_entry(map, entry, ent), NULL);
> + }
> +
> + for (size_t i = 0; i < ARRAY_SIZE(query); i++) {
> + entry = get_test_entry(map, ignore_case, query[i][0]);
> + if (check(entry != NULL))
> + check_str(get_value(entry), query[i][1]);
> + else
> + test_msg("query key: %s", query[i][0]);
> + }
> +
> + check_pointer_eq(get_test_entry(map, ignore_case, "notInMap"), NULL);
> + check_int(map->tablesize, ==, 64);
> + check_int(hashmap_get_size(map), ==, ARRAY_SIZE(key_val));
> +}
> +
> +static void t_add(struct hashmap *map, int ignore_case)
> +{
> + struct test_entry *entry;
> + const char *key_val[][2] = {
> + { "key1", "value1" },
> + { ignore_case ? "Key1" : "key1", "value2" },
> + { "fooBarFrotz", "value3" },
> + { ignore_case ? "Foobarfrotz" : "fooBarFrotz", "value4" }
> + };
> + const char *queries[] = { "key1",
> + ignore_case ? "Foobarfrotz" : "fooBarFrotz" };
> + char seen[ARRAY_SIZE(key_val)] = { 0 };
> +
> + for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
> + entry = alloc_test_entry(ignore_case, key_val[i][0], key_val[i][1]);
> + hashmap_add(map, &entry->ent);
> + }
> +
> + for (size_t i = 0; i < ARRAY_SIZE(queries); i++) {
> + int count = 0;
> + entry = hashmap_get_entry_from_hash(map,
> + ignore_case ? strihash(queries[i]) :
> + strhash(queries[i]),
> + queries[i], struct test_entry, ent);
> +
> + hashmap_for_each_entry_from(map, entry, ent)
> + {
> + int ret;
> + if (!check_int((ret = key_val_contains(
> + key_val, seen,
> + ARRAY_SIZE(key_val), entry)),
> + ==, 0)) {
> + switch (ret) {
> + case 1:
> + test_msg("found entry was not given in the input\n"
> + " key: %s\n value: %s",
> + entry->key, get_value(entry));
> + break;
> + case 2:
> + test_msg("duplicate entry detected\n"
> + " key: %s\n value: %s",
> + entry->key, get_value(entry));
> + break;
> + }
> + } else {
> + count++;
> + }
> + }
> + check_int(count, ==, 2);
> + }
> +
> + for (size_t i = 0; i < ARRAY_SIZE(seen); i++) {
> + if (!check_int(seen[i], ==, 1))
> + test_msg("following key-val pair was not iterated over:\n"
> + " key: %s\n value: %s",
> + key_val[i][0], key_val[i][1]);
> + }
> +
> + check_int(hashmap_get_size(map), ==, ARRAY_SIZE(key_val));
> + check_pointer_eq(get_test_entry(map, ignore_case, "notInMap"), NULL);
> +}
> +
> +static void t_remove(struct hashmap *map, int ignore_case)
> +{
> + struct test_entry *entry, *removed;
> + const char *key_val[][2] = { { "key1", "value1" },
> + { "key2", "value2" },
> + { "fooBarFrotz", "value3" } };
> + const char *remove[][2] = { { ignore_case ? "Key1" : "key1", "value1"
> },
> + { ignore_case ? "keY2" : "key2", "value2" } };
> +
> + for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
> + entry = alloc_test_entry(ignore_case, key_val[i][0], key_val[i][1]);
> + check_pointer_eq(hashmap_put_entry(map, entry, ent), NULL);
> + }
> +
> + for (size_t i = 0; i < ARRAY_SIZE(remove); i++) {
> + entry = alloc_test_entry(ignore_case, remove[i][0], "");
> + removed = hashmap_remove_entry(map, entry, ent, remove[i][0]);
> + if (check(removed != NULL))
> + check_str(get_value(removed), remove[i][1]);
> + free(entry);
> + free(removed);
> + }
> +
> + entry = alloc_test_entry(ignore_case, "notInMap", "");
> + check_pointer_eq(hashmap_remove_entry(map, entry, ent, "notInMap"),
> NULL);
> + free(entry);
> +
> + check_int(map->tablesize, ==, 64);
> + check_int(hashmap_get_size(map), ==, ARRAY_SIZE(key_val) -
> ARRAY_SIZE(remove));
> +}
> +
> +static void t_iterate(struct hashmap *map, int ignore_case)
> +{
> + struct test_entry *entry;
> + struct hashmap_iter iter;
> + const char *key_val[][2] = { { "key1", "value1" },
> + { "key2", "value2" },
> + { "fooBarFrotz", "value3" } };
> + char seen[ARRAY_SIZE(key_val)] = { 0 };
> +
> + for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
> + entry = alloc_test_entry(ignore_case, key_val[i][0], key_val[i][1]);
> + check_pointer_eq(hashmap_put_entry(map, entry, ent), NULL);
> + }
> +
> + hashmap_for_each_entry(map, &iter, entry, ent /* member name */)
> + {
> + int ret;
> + if (!check_int((ret = key_val_contains(key_val, seen,
> + ARRAY_SIZE(key_val),
> + entry)), ==, 0)) {
> + switch (ret) {
> + case 1:
> + test_msg("found entry was not given in the input\n"
> + " key: %s\n value: %s",
> + entry->key, get_value(entry));
> + break;
> + case 2:
> + test_msg("duplicate entry detected\n"
> + " key: %s\n value: %s",
> + entry->key, get_value(entry));
> + break;
> + }
> + }
> + }
> +
> + for (size_t i = 0; i < ARRAY_SIZE(seen); i++) {
> + if (!check_int(seen[i], ==, 1))
> + test_msg("following key-val pair was not iterated over:\n"
> + " key: %s\n value: %s",
> + key_val[i][0], key_val[i][1]);
> + }
> +
> + check_int(hashmap_get_size(map), ==, ARRAY_SIZE(key_val));
> +}
> +
> +static void t_alloc(struct hashmap *map, int ignore_case)
> +{
> + struct test_entry *entry, *removed;
> +
> + for (int i = 1; i <= 51; i++) {
> + char *key = xstrfmt("key%d", i);
> + char *value = xstrfmt("value%d", i);
> + entry = alloc_test_entry(ignore_case, key, value);
> + check_pointer_eq(hashmap_put_entry(map, entry, ent), NULL);
> + free(key);
> + free(value);
> + }
> + check_int(map->tablesize, ==, 64);
> + check_int(hashmap_get_size(map), ==, 51);
> +
> + entry = alloc_test_entry(ignore_case, "key52", "value52");
> + check_pointer_eq(hashmap_put_entry(map, entry, ent), NULL);
> + check_int(map->tablesize, ==, 256);
> + check_int(hashmap_get_size(map), ==, 52);
> +
> + for (int i = 1; i <= 12; i++) {
> + char *key = xstrfmt("key%d", i);
> + char *value = xstrfmt("value%d", i);
> +
> + entry = alloc_test_entry(ignore_case, key, "");
> + removed = hashmap_remove_entry(map, entry, ent, key);
> + if (check(removed != NULL))
> + check_str(value, get_value(removed));
> + free(key);
> + free(value);
> + free(entry);
> + free(removed);
> + }
> + check_int(map->tablesize, ==, 256);
> + check_int(hashmap_get_size(map), ==, 40);
> +
> + entry = alloc_test_entry(ignore_case, "key40", "");
> + removed = hashmap_remove_entry(map, entry, ent, "key40");
> + if (check(removed != NULL))
> + check_str("value40", get_value(removed));
> + check_int(map->tablesize, ==, 64);
> + check_int(hashmap_get_size(map), ==, 39);
> + free(entry);
> + free(removed);
> +}
> +
> +static void t_intern(struct hashmap *map, int ignore_case)
> +{
> + const char *values[] = { "value1", "Value1", "value2", "value2" };
> +
> + for (size_t i = 0; i < ARRAY_SIZE(values); i++) {
> + const char *i1 = strintern(values[i]);
> + const char *i2 = strintern(values[i]);
> +
> + if (!check(!strcmp(i1, values[i])))
> + test_msg("strintern(%s) returns %s\n", values[i], i1);
> + else if (!check(i1 != values[i]))
> + test_msg("strintern(%s) returns input pointer\n",
> + values[i]);
> + else if (!check_pointer_eq(i1, i2))
> + test_msg("address('%s') != address('%s'), so strintern('%s') !=
> strintern('%s')",
> + i1, i2, values[i], values[i]);
> + else
> + check_str(i1, values[i]);
> + }
> +}
> +
> +int cmd_main(int argc UNUSED, const char **argv UNUSED)
> +{
> + TEST(setup(t_replace, 0), "replace works");
> + TEST(setup(t_replace, 1), "replace (case insensitive) works");
> + TEST(setup(t_get, 0), "get works");
> + TEST(setup(t_get, 1), "get (case insensitive) works");
> + TEST(setup(t_add, 0), "add works");
> + TEST(setup(t_add, 1), "add (case insensitive) works");
> + TEST(setup(t_remove, 0), "remove works");
> + TEST(setup(t_remove, 1), "remove (case insensitive) works");
> + TEST(setup(t_iterate, 0), "iterate works");
> + TEST(setup(t_iterate, 1), "iterate (case insensitive) works");
> + TEST(setup(t_alloc, 0), "grow / shrink works");
> + TEST(setup(t_intern, 0), "string interning works");
> + return test_done();
> +}
> --
> 2.45.2
Junio C Hamano· Jul 12, 2024, 17:14 UTC · re: Ghanshyam Thakkar · lore

Re: [GSoC][PATCH v3] t: port helper/test-hashmap.c to unit-tests/t-hashmap.c

"Ghanshyam Thakkar" <shyamthakkar001@gmail.com> writes:
> - And replaced the third elements of key_val[] which recorded
>   the presence of certain key-val pair with 'char seen[]'.
It makes it in-line with the oidmap test, which is good.
Christian Couder· Jul 25, 2024, 12:48 UTC · re: Ghanshyam Thakkar · lore

Re: [GSoC][PATCH v3] t: port helper/test-hashmap.c to unit-tests/t-hashmap.c

On Fri, Jul 12, 2024 at 1:52 AM Ghanshyam Thakkar <shyamthakkar001@gmail.com> wrote:

Show 6 quoted lines
>
> helper/test-hashmap.c along with t0011-hashmap.sh test the hashmap.h
> library. Migrate them to the unit testing framework for better
> debugging, runtime performance and concise code.
>
> Along with the migration, make 'add' tests from the shellscript order
Nit: s/shellscript/shell script/
> agnostic in unit tests, since they iterate over entries with the same
> keys and we do not guarantee the order.

The above is not very clear. Maybe rephrasing a bit and adding an example could help.

> The helper/test-hashmap.c is still not removed because it contains a
> performance test meant to be run by the user directly (not used in
> t/perf). And it makes sense for such a utility to be a helper.
Show 42 quoted lines
> diff --git a/t/unit-tests/t-hashmap.c b/t/unit-tests/t-hashmap.c
> new file mode 100644
> index 0000000000..3112b10b33
> --- /dev/null
> +++ b/t/unit-tests/t-hashmap.c
> @@ -0,0 +1,358 @@
> +#include "test-lib.h"
> +#include "hashmap.h"
> +#include "strbuf.h"
> +
> +struct test_entry {
> +       int padding; /* hashmap entry no longer needs to be the first member */
> +       struct hashmap_entry ent;
> +       /* key and value as two \0-terminated strings */
> +       char key[FLEX_ARRAY];
> +};
> +
> +static int test_entry_cmp(const void *cmp_data,
> +                         const struct hashmap_entry *eptr,
> +                         const struct hashmap_entry *entry_or_key,
> +                         const void *keydata)
> +{
> +       const int ignore_case = cmp_data ? *((int *)cmp_data) : 0;
> +       const struct test_entry *e1, *e2;
> +       const char *key = keydata;
> +
> +       e1 = container_of(eptr, const struct test_entry, ent);
> +       e2 = container_of(entry_or_key, const struct test_entry, ent);
> +
> +       if (ignore_case)
> +               return strcasecmp(e1->key, key ? key : e2->key);
> +       else
> +               return strcmp(e1->key, key ? key : e2->key);
> +}
> +
> +static const char *get_value(const struct test_entry *e)
> +{
> +       return e->key + strlen(e->key) + 1;
> +}
> +
> +static struct test_entry *alloc_test_entry(unsigned int ignore_case,
> +                                          const char *key, const char *value)
Nit: `unsigned int ignore_case` is a bool flag argument which we often
put at the end of function arguments, so perhaps:
static struct test_entry *alloc_test_entry(const char *key, const char *value,
                                          unsigned int ignore_case)
Show 14 quoted lines
> +{
> +       size_t klen = strlen(key);
> +       size_t vlen = strlen(value);
> +       unsigned int hash = ignore_case ? strihash(key) : strhash(key);
> +       struct test_entry *entry = xmalloc(st_add4(sizeof(*entry), klen, vlen, 2));
> +
> +       hashmap_entry_init(&entry->ent, hash);
> +       memcpy(entry->key, key, klen + 1);
> +       memcpy(entry->key + klen + 1, value, vlen + 1);
> +       return entry;
> +}
> +
> +static struct test_entry *get_test_entry(struct hashmap *map,
> +                                        unsigned int ignore_case, const char *key)
Here also `unsigned int ignore_case` might want to be the last argument.
Show 23 quoted lines
> +{
> +       return hashmap_get_entry_from_hash(
> +               map, ignore_case ? strihash(key) : strhash(key), key,
> +               struct test_entry, ent);
> +}
> +
> +static int key_val_contains(const char *key_val[][2], char seen[], size_t n,
> +                           struct test_entry *entry)
> +{
> +       for (size_t i = 0; i < n; i++) {
> +               if (!strcmp(entry->key, key_val[i][0]) &&
> +                   !strcmp(get_value(entry), key_val[i][1])) {
> +                       if (seen[i])
> +                               return 2;
> +                       seen[i] = 1;
> +                       return 0;
> +               }
> +       }
> +       return 1;
> +}
> +
> +static void setup(void (*f)(struct hashmap *map, int ignore_case),
> +                 int ignore_case)
Why `int ignore_case` here, instead of `unsigned int ignore_case` above?
It's nice that the `ignore_case` argument is the last argument though.
Show 8 quoted lines
> +{
> +       struct hashmap map = HASHMAP_INIT(test_entry_cmp, &ignore_case);
> +
> +       f(&map, ignore_case);
> +       hashmap_clear_and_free(&map, struct test_entry, ent);
> +}
> +
> +static void t_replace(struct hashmap *map, int ignore_case)

Here also, why `int ignore_case` here, instead of `unsigned int ignore_case` towards the top of this file?

I won't mention it anymore below, but I think it might be better to have `unsigned int ignore_case` everywhere.

Show 19 quoted lines
> +{
> +       struct test_entry *entry;
> +
> +       entry = alloc_test_entry(ignore_case, "key1", "value1");
> +       check_pointer_eq(hashmap_put_entry(map, entry, ent), NULL);
> +
> +       entry = alloc_test_entry(ignore_case, ignore_case ? "Key1" : "key1",
> +                                "value2");
> +       entry = hashmap_put_entry(map, entry, ent);
> +       if (check(entry != NULL))
> +               check_str(get_value(entry), "value1");
> +       free(entry);
> +
> +       entry = alloc_test_entry(ignore_case, "fooBarFrotz", "value3");
> +       check_pointer_eq(hashmap_put_entry(map, entry, ent), NULL);
> +
> +       entry = alloc_test_entry(ignore_case,
> +                                ignore_case ? "foobarfrotz" : "fooBarFrotz",
> +                                "value4");

Maybe using something like "FOObarFrotZ" instead of "foobarfrotz" would make it clear that we don't need to downcase in case we ignore case.

Show 18 quoted lines
> +       entry = hashmap_put_entry(map, entry, ent);
> +       if (check(entry != NULL))
> +               check_str(get_value(entry), "value3");
> +       free(entry);
> +}
> +
> +static void t_get(struct hashmap *map, int ignore_case)
> +{
> +       struct test_entry *entry;
> +       const char *key_val[][2] = { { "key1", "value1" },
> +                                    { "key2", "value2" },
> +                                    { "fooBarFrotz", "value3" },
> +                                    { ignore_case ? "key4" : "foobarfrotz", "value4" } };
> +       const char *query[][2] = {
> +               { ignore_case ? "Key1" : "key1", "value1" },
> +               { ignore_case ? "keY2" : "key2", "value2" },
> +               { ignore_case ? "foobarfrotz" : "fooBarFrotz", "value3" }
> +       };
I think adding a test case like:
               { ignore_case ? "FOOBarFrotZ" : "foobarfrotz",
                 ignore_case ? : "value3" : "value4" }

which is a bit similar to what Junio suggested, could help a bit check that things work well especially when not ignoring the case.

Show 29 quoted lines
> +       for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
> +               entry = alloc_test_entry(ignore_case, key_val[i][0], key_val[i][1]);
> +               check_pointer_eq(hashmap_put_entry(map, entry, ent), NULL);
> +       }
> +
> +       for (size_t i = 0; i < ARRAY_SIZE(query); i++) {
> +               entry = get_test_entry(map, ignore_case, query[i][0]);
> +               if (check(entry != NULL))
> +                       check_str(get_value(entry), query[i][1]);
> +               else
> +                       test_msg("query key: %s", query[i][0]);
> +       }
> +
> +       check_pointer_eq(get_test_entry(map, ignore_case, "notInMap"), NULL);
> +       check_int(map->tablesize, ==, 64);
> +       check_int(hashmap_get_size(map), ==, ARRAY_SIZE(key_val));
> +}
> +
> +static void t_add(struct hashmap *map, int ignore_case)
> +{
> +       struct test_entry *entry;
> +       const char *key_val[][2] = {
> +               { "key1", "value1" },
> +               { ignore_case ? "Key1" : "key1", "value2" },
> +               { "fooBarFrotz", "value3" },
> +               { ignore_case ? "Foobarfrotz" : "fooBarFrotz", "value4" }
> +       };
> +       const char *queries[] = { "key1",
> +                                 ignore_case ? "Foobarfrotz" : "fooBarFrotz" };

It is tricky that here `queries` is not defined and doesn't contain the same things as in the other functions above:

const char *queries[][2] = ...

Maybe changing the name to something like `query_keys` would help make people aware that here it contains only keys.

Show 50 quoted lines
> +       char seen[ARRAY_SIZE(key_val)] = { 0 };
> +
> +       for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
> +               entry = alloc_test_entry(ignore_case, key_val[i][0], key_val[i][1]);
> +               hashmap_add(map, &entry->ent);
> +       }
> +
> +       for (size_t i = 0; i < ARRAY_SIZE(queries); i++) {
> +               int count = 0;
> +               entry = hashmap_get_entry_from_hash(map,
> +                       ignore_case ? strihash(queries[i]) :
> +                                     strhash(queries[i]),
> +                       queries[i], struct test_entry, ent);
> +
> +               hashmap_for_each_entry_from(map, entry, ent)
> +               {
> +                       int ret;
> +                       if (!check_int((ret = key_val_contains(
> +                                               key_val, seen,
> +                                               ARRAY_SIZE(key_val), entry)),
> +                                      ==, 0)) {
> +                               switch (ret) {
> +                               case 1:
> +                                       test_msg("found entry was not given in the input\n"
> +                                                "    key: %s\n  value: %s",
> +                                                entry->key, get_value(entry));
> +                                       break;
> +                               case 2:
> +                                       test_msg("duplicate entry detected\n"
> +                                                "    key: %s\n  value: %s",
> +                                                entry->key, get_value(entry));
> +                                       break;
> +                               }
> +                       } else {
> +                               count++;
> +                       }
> +               }
> +               check_int(count, ==, 2);
> +       }
> +
> +       for (size_t i = 0; i < ARRAY_SIZE(seen); i++) {
> +               if (!check_int(seen[i], ==, 1))
> +                       test_msg("following key-val pair was not iterated over:\n"
> +                                "    key: %s\n  value: %s",
> +                                key_val[i][0], key_val[i][1]);
> +       }
> +
> +       check_int(hashmap_get_size(map), ==, ARRAY_SIZE(key_val));
> +       check_pointer_eq(get_test_entry(map, ignore_case, "notInMap"), NULL);
> +}
Thanks!
A U Thor· Jul 30, 2024, 11:50 UTC · re: Ghanshyam Thakkar · lore

[PATCH v4] t: port helper/test-hashmap.c to unit-tests/t-hashmap.c

From: Ghanshyam Thakkar <shyamthakkar001@gmail.com>

helper/test-hashmap.c along with t0011-hashmap.sh test the hashmap.h library. Migrate them to the unit testing framework for better debugging, runtime performance and concise code.

Along with the migration, make 'add' tests from the shell script order agnostic in unit tests, since they iterate over entries with the same keys and we do not guarantee the order. This was already done for the 'iterate' tests[1].

The helper/test-hashmap.c is still not removed because it contains a performance test meant to be run by the user directly (not used in t/perf). And it makes sense for such a utility to be a helper.

[1]: e1e7a77141 (t: sort output of hashmap iteration, 2019-07-30)
Mentored-by: Christian Couder <chriscool@tuxfamily.org>
Mentored-by: Kaartic Sivaraam <kaartic.sivaraam@gmail.com>
Helped-by: Josh Steadmon <steadmon@google.com>
Helped-by: Junio C Hamano <gitster@pobox.com>
Helped-by: Phillip Wood <phillip.wood123@gmail.com>
Signed-off-by: Ghanshyam Thakkar <shyamthakkar001@gmail.com>
---
Changes in v4:
- update commit message to add a reference and fix typo
- change 'int ignore_case' to 'unsigned int ignore_case'
- make 'ignore_case' the last parameter in all the functions
- update t_get() to add a testcase query for better ignore-case
  checking
Range-diff against v3:
1:  03ba77665e ! 1:  04022c4cb9 t: port helper/test-hashmap.c to unit-tests/t-hashmap.c
    @@ Commit message
         library. Migrate them to the unit testing framework for better
         debugging, runtime performance and concise code.
     
    -    Along with the migration, make 'add' tests from the shellscript order
    +    Along with the migration, make 'add' tests from the shell script order
         agnostic in unit tests, since they iterate over entries with the same
    -    keys and we do not guarantee the order.
    +    keys and we do not guarantee the order. This was already done for the
    +    'iterate' tests[1].
     
         The helper/test-hashmap.c is still not removed because it contains a
         performance test meant to be run by the user directly (not used in
         t/perf). And it makes sense for such a utility to be a helper.
     
    +    [1]: e1e7a77141 (t: sort output of hashmap iteration, 2019-07-30)
    +
         Mentored-by: Christian Couder <chriscool@tuxfamily.org>
         Mentored-by: Kaartic Sivaraam <kaartic.sivaraam@gmail.com>
         Helped-by: Josh Steadmon <steadmon@google.com>
    +    Helped-by: Junio C Hamano <gitster@pobox.com>
         Helped-by: Phillip Wood <phillip.wood123@gmail.com>
         Signed-off-by: Ghanshyam Thakkar <shyamthakkar001@gmail.com>
     
    @@ t/unit-tests/t-hashmap.c (new)
     +			  const struct hashmap_entry *entry_or_key,
     +			  const void *keydata)
     +{
    -+	const int ignore_case = cmp_data ? *((int *)cmp_data) : 0;
    ++	const unsigned int ignore_case = cmp_data ? *((int *)cmp_data) : 0;
     +	const struct test_entry *e1, *e2;
     +	const char *key = keydata;
     +
    @@ t/unit-tests/t-hashmap.c (new)
     +	return e->key + strlen(e->key) + 1;
     +}
     +
    -+static struct test_entry *alloc_test_entry(unsigned int ignore_case,
    -+					   const char *key, const char *value)
    ++static struct test_entry *alloc_test_entry(const char *key, const char *value,
    ++					   unsigned int ignore_case)
     +{
     +	size_t klen = strlen(key);
     +	size_t vlen = strlen(value);
    @@ t/unit-tests/t-hashmap.c (new)
     +	return entry;
     +}
     +
    -+static struct test_entry *get_test_entry(struct hashmap *map,
    -+					 unsigned int ignore_case, const char *key)
    ++static struct test_entry *get_test_entry(struct hashmap *map, const char *key,
    ++					 unsigned int ignore_case)
     +{
     +	return hashmap_get_entry_from_hash(
     +		map, ignore_case ? strihash(key) : strhash(key), key,
    @@ t/unit-tests/t-hashmap.c (new)
     +	return 1;
     +}
     +
    -+static void setup(void (*f)(struct hashmap *map, int ignore_case),
    -+		  int ignore_case)
    ++static void setup(void (*f)(struct hashmap *map, unsigned int ignore_case),
    ++		  unsigned int ignore_case)
     +{
     +	struct hashmap map = HASHMAP_INIT(test_entry_cmp, &ignore_case);
     +
    @@ t/unit-tests/t-hashmap.c (new)
     +	hashmap_clear_and_free(&map, struct test_entry, ent);
     +}
     +
    -+static void t_replace(struct hashmap *map, int ignore_case)
    ++static void t_replace(struct hashmap *map, unsigned int ignore_case)
     +{
     +	struct test_entry *entry;
     +
    -+	entry = alloc_test_entry(ignore_case, "key1", "value1");
    ++	entry = alloc_test_entry("key1", "value1", ignore_case);
     +	check_pointer_eq(hashmap_put_entry(map, entry, ent), NULL);
     +
    -+	entry = alloc_test_entry(ignore_case, ignore_case ? "Key1" : "key1",
    -+				 "value2");
    ++	entry = alloc_test_entry(ignore_case ? "Key1" : "key1", "value2",
    ++				 ignore_case);
     +	entry = hashmap_put_entry(map, entry, ent);
     +	if (check(entry != NULL))
     +		check_str(get_value(entry), "value1");
     +	free(entry);
     +
    -+	entry = alloc_test_entry(ignore_case, "fooBarFrotz", "value3");
    ++	entry = alloc_test_entry("fooBarFrotz", "value3", ignore_case);
     +	check_pointer_eq(hashmap_put_entry(map, entry, ent), NULL);
     +
    -+	entry = alloc_test_entry(ignore_case,
    -+				 ignore_case ? "foobarfrotz" : "fooBarFrotz",
    -+				 "value4");
    ++	entry = alloc_test_entry(ignore_case ? "FOObarFrotz" : "fooBarFrotz",
    ++				 "value4", ignore_case);
     +	entry = hashmap_put_entry(map, entry, ent);
     +	if (check(entry != NULL))
     +		check_str(get_value(entry), "value3");
     +	free(entry);
     +}
     +
    -+static void t_get(struct hashmap *map, int ignore_case)
    ++static void t_get(struct hashmap *map, unsigned int ignore_case)
     +{
     +	struct test_entry *entry;
     +	const char *key_val[][2] = { { "key1", "value1" },
     +				     { "key2", "value2" },
     +				     { "fooBarFrotz", "value3" },
    -+				     { ignore_case ? "key4" : "foobarfrotz", "value4" } };
    ++				     { ignore_case ? "TeNor" : "tenor",
    ++				       ignore_case ? "value4" : "value5" } };
     +	const char *query[][2] = {
     +		{ ignore_case ? "Key1" : "key1", "value1" },
     +		{ ignore_case ? "keY2" : "key2", "value2" },
    -+		{ ignore_case ? "foobarfrotz" : "fooBarFrotz", "value3" }
    ++		{ ignore_case ? "FOObarFrotz" : "fooBarFrotz", "value3" },
    ++		{ ignore_case ? "TENOR" : "tenor",
    ++		  ignore_case ? "value4" : "value5" }
     +	};
     +
     +	for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
    -+		entry = alloc_test_entry(ignore_case, key_val[i][0], key_val[i][1]);
    ++		entry = alloc_test_entry(key_val[i][0], key_val[i][1],
    ++					 ignore_case);
     +		check_pointer_eq(hashmap_put_entry(map, entry, ent), NULL);
     +	}
     +
     +	for (size_t i = 0; i < ARRAY_SIZE(query); i++) {
    -+		entry = get_test_entry(map, ignore_case, query[i][0]);
    ++		entry = get_test_entry(map, query[i][0], ignore_case);
     +		if (check(entry != NULL))
     +			check_str(get_value(entry), query[i][1]);
     +		else
     +			test_msg("query key: %s", query[i][0]);
     +	}
     +
    -+	check_pointer_eq(get_test_entry(map, ignore_case, "notInMap"), NULL);
    ++	check_pointer_eq(get_test_entry(map, "notInMap", ignore_case), NULL);
     +	check_int(map->tablesize, ==, 64);
     +	check_int(hashmap_get_size(map), ==, ARRAY_SIZE(key_val));
     +}
     +
    -+static void t_add(struct hashmap *map, int ignore_case)
    ++static void t_add(struct hashmap *map, unsigned int ignore_case)
     +{
     +	struct test_entry *entry;
     +	const char *key_val[][2] = {
     +		{ "key1", "value1" },
     +		{ ignore_case ? "Key1" : "key1", "value2" },
     +		{ "fooBarFrotz", "value3" },
    -+		{ ignore_case ? "Foobarfrotz" : "fooBarFrotz", "value4" }
    ++		{ ignore_case ? "FOObarFrotz" : "fooBarFrotz", "value4" }
     +	};
    -+	const char *queries[] = { "key1",
    -+				  ignore_case ? "Foobarfrotz" : "fooBarFrotz" };
    ++	const char *query_keys[] = { "key1", ignore_case ? "FOObarFrotz" :
    ++							   "fooBarFrotz" };
     +	char seen[ARRAY_SIZE(key_val)] = { 0 };
     +
     +	for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
    -+		entry = alloc_test_entry(ignore_case, key_val[i][0], key_val[i][1]);
    ++		entry = alloc_test_entry(key_val[i][0], key_val[i][1], ignore_case);
     +		hashmap_add(map, &entry->ent);
     +	}
     +
    -+	for (size_t i = 0; i < ARRAY_SIZE(queries); i++) {
    ++	for (size_t i = 0; i < ARRAY_SIZE(query_keys); i++) {
     +		int count = 0;
     +		entry = hashmap_get_entry_from_hash(map,
    -+			ignore_case ? strihash(queries[i]) :
    -+				      strhash(queries[i]),
    -+			queries[i], struct test_entry, ent);
    ++			ignore_case ? strihash(query_keys[i]) :
    ++				      strhash(query_keys[i]),
    ++			query_keys[i], struct test_entry, ent);
     +
     +		hashmap_for_each_entry_from(map, entry, ent)
     +		{
    @@ t/unit-tests/t-hashmap.c (new)
     +	}
     +
     +	check_int(hashmap_get_size(map), ==, ARRAY_SIZE(key_val));
    -+	check_pointer_eq(get_test_entry(map, ignore_case, "notInMap"), NULL);
    ++	check_pointer_eq(get_test_entry(map, "notInMap", ignore_case), NULL);
     +}
     +
    -+static void t_remove(struct hashmap *map, int ignore_case)
    ++static void t_remove(struct hashmap *map, unsigned int ignore_case)
     +{
     +	struct test_entry *entry, *removed;
     +	const char *key_val[][2] = { { "key1", "value1" },
    @@ t/unit-tests/t-hashmap.c (new)
     +				    { ignore_case ? "keY2" : "key2", "value2" } };
     +
     +	for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
    -+		entry = alloc_test_entry(ignore_case, key_val[i][0], key_val[i][1]);
    ++		entry = alloc_test_entry(key_val[i][0], key_val[i][1], ignore_case);
     +		check_pointer_eq(hashmap_put_entry(map, entry, ent), NULL);
     +	}
     +
     +	for (size_t i = 0; i < ARRAY_SIZE(remove); i++) {
    -+		entry = alloc_test_entry(ignore_case, remove[i][0], "");
    ++		entry = alloc_test_entry(remove[i][0], "", ignore_case);
     +		removed = hashmap_remove_entry(map, entry, ent, remove[i][0]);
     +		if (check(removed != NULL))
     +			check_str(get_value(removed), remove[i][1]);
    @@ t/unit-tests/t-hashmap.c (new)
     +		free(removed);
     +	}
     +
    -+	entry = alloc_test_entry(ignore_case, "notInMap", "");
    ++	entry = alloc_test_entry("notInMap", "", ignore_case);
     +	check_pointer_eq(hashmap_remove_entry(map, entry, ent, "notInMap"), NULL);
     +	free(entry);
     +
    @@ t/unit-tests/t-hashmap.c (new)
     +	check_int(hashmap_get_size(map), ==, ARRAY_SIZE(key_val) - ARRAY_SIZE(remove));
     +}
     +
    -+static void t_iterate(struct hashmap *map, int ignore_case)
    ++static void t_iterate(struct hashmap *map, unsigned int ignore_case)
     +{
     +	struct test_entry *entry;
     +	struct hashmap_iter iter;
    @@ t/unit-tests/t-hashmap.c (new)
     +	char seen[ARRAY_SIZE(key_val)] = { 0 };
     +
     +	for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
    -+		entry = alloc_test_entry(ignore_case, key_val[i][0], key_val[i][1]);
    ++		entry = alloc_test_entry(key_val[i][0], key_val[i][1], ignore_case);
     +		check_pointer_eq(hashmap_put_entry(map, entry, ent), NULL);
     +	}
     +
    @@ t/unit-tests/t-hashmap.c (new)
     +	check_int(hashmap_get_size(map), ==, ARRAY_SIZE(key_val));
     +}
     +
    -+static void t_alloc(struct hashmap *map, int ignore_case)
    ++static void t_alloc(struct hashmap *map, unsigned int ignore_case)
     +{
     +	struct test_entry *entry, *removed;
     +
     +	for (int i = 1; i <= 51; i++) {
     +		char *key = xstrfmt("key%d", i);
     +		char *value = xstrfmt("value%d", i);
    -+		entry = alloc_test_entry(ignore_case, key, value);
    ++		entry = alloc_test_entry(key, value, ignore_case);
     +		check_pointer_eq(hashmap_put_entry(map, entry, ent), NULL);
     +		free(key);
     +		free(value);
    @@ t/unit-tests/t-hashmap.c (new)
     +	check_int(map->tablesize, ==, 64);
     +	check_int(hashmap_get_size(map), ==, 51);
     +
    -+	entry = alloc_test_entry(ignore_case, "key52", "value52");
    ++	entry = alloc_test_entry("key52", "value52", ignore_case);
     +	check_pointer_eq(hashmap_put_entry(map, entry, ent), NULL);
     +	check_int(map->tablesize, ==, 256);
     +	check_int(hashmap_get_size(map), ==, 52);
    @@ t/unit-tests/t-hashmap.c (new)
     +		char *key = xstrfmt("key%d", i);
     +		char *value = xstrfmt("value%d", i);
     +
    -+		entry = alloc_test_entry(ignore_case, key, "");
    ++		entry = alloc_test_entry(key, "", ignore_case);
     +		removed = hashmap_remove_entry(map, entry, ent, key);
     +		if (check(removed != NULL))
     +			check_str(value, get_value(removed));
    @@ t/unit-tests/t-hashmap.c (new)
     +	check_int(map->tablesize, ==, 256);
     +	check_int(hashmap_get_size(map), ==, 40);
     +
    -+	entry = alloc_test_entry(ignore_case, "key40", "");
    ++	entry = alloc_test_entry("key40", "", ignore_case);
     +	removed = hashmap_remove_entry(map, entry, ent, "key40");
     +	if (check(removed != NULL))
     +		check_str("value40", get_value(removed));
    @@ t/unit-tests/t-hashmap.c (new)
     +	free(removed);
     +}
     +
    -+static void t_intern(struct hashmap *map, int ignore_case)
    ++static void t_intern(struct hashmap *map, unsigned int ignore_case)
     +{
     +	const char *values[] = { "value1", "Value1", "value2", "value2" };
     +
 Makefile                 |   1 +
 t/helper/test-hashmap.c  | 100 +----------
 t/t0011-hashmap.sh       | 260 ----------------------------
 t/unit-tests/t-hashmap.c | 361 +++++++++++++++++++++++++++++++++++++++
 4 files changed, 364 insertions(+), 358 deletions(-)
 delete mode 100755 t/t0011-hashmap.sh
 create mode 100644 t/unit-tests/t-hashmap.c
Show changes to 4 files +364 −358

Makefile, t/helper/test-hashmap.c, t/t0011-hashmap.sh, t/unit-tests/t-hashmap.c

diff --git a/Makefile b/Makefile
index 3eab701b10..74bb026610 100644
--- a/Makefile
+++ b/Makefile
@@ -1336,6 +1336,7 @@ THIRD_PARTY_SOURCES += sha1dc/%
 UNIT_TEST_PROGRAMS += t-ctype
 UNIT_TEST_PROGRAMS += t-example-decorate
 UNIT_TEST_PROGRAMS += t-hash
+UNIT_TEST_PROGRAMS += t-hashmap
 UNIT_TEST_PROGRAMS += t-mem-pool
 UNIT_TEST_PROGRAMS += t-oidtree
 UNIT_TEST_PROGRAMS += t-prio-queue
diff --git a/t/helper/test-hashmap.c b/t/helper/test-hashmap.c
index 2912899558..7b854a7030 100644
--- a/t/helper/test-hashmap.c
+++ b/t/helper/test-hashmap.c
@@ -12,11 +12,6 @@ struct test_entry
 	char key[FLEX_ARRAY];
 };
 
-static const char *get_value(const struct test_entry *e)
-{
-	return e->key + strlen(e->key) + 1;
-}
-
 static int test_entry_cmp(const void *cmp_data,
 			  const struct hashmap_entry *eptr,
 			  const struct hashmap_entry *entry_or_key,
@@ -141,30 +136,16 @@ static void perf_hashmap(unsigned int method, unsigned int rounds)
 /*
  * Read stdin line by line and print result of commands to stdout:
  *
- * hash key -> strhash(key) memhash(key) strihash(key) memihash(key)
- * put key value -> NULL / old value
- * get key -> NULL / value
- * remove key -> NULL / old value
- * iterate -> key1 value1\nkey2 value2\n...
- * size -> tablesize numentries
- *
  * perfhashmap method rounds -> test hashmap.[ch] performance
  */
 int cmd__hashmap(int argc, const char **argv)
 {
 	struct string_list parts = STRING_LIST_INIT_NODUP;
 	struct strbuf line = STRBUF_INIT;
-	int icase;
-	struct hashmap map = HASHMAP_INIT(test_entry_cmp, &icase);
-
-	/* init hash map */
-	icase = argc > 1 && !strcmp("ignorecase", argv[1]);
 
 	/* process commands from stdin */
 	while (strbuf_getline(&line, stdin) != EOF) {
 		char *cmd, *p1, *p2;
-		unsigned int hash = 0;
-		struct test_entry *entry;
 
 		/* break line into command and up to two parameters */
 		string_list_setlen(&parts, 0);
@@ -180,84 +161,8 @@ int cmd__hashmap(int argc, const char **argv)
 		cmd = parts.items[0].string;
 		p1 = parts.nr >= 1 ? parts.items[1].string : NULL;
 		p2 = parts.nr >= 2 ? parts.items[2].string : NULL;
-		if (p1)
-			hash = icase ? strihash(p1) : strhash(p1);
-
-		if (!strcmp("add", cmd) && p1 && p2) {
-
-			/* create entry with key = p1, value = p2 */
-			entry = alloc_test_entry(hash, p1, p2);
-
-			/* add to hashmap */
-			hashmap_add(&map, &entry->ent);
-
-		} else if (!strcmp("put", cmd) && p1 && p2) {
-
-			/* create entry with key = p1, value = p2 */
-			entry = alloc_test_entry(hash, p1, p2);
-
-			/* add / replace entry */
-			entry = hashmap_put_entry(&map, entry, ent);
-
-			/* print and free replaced entry, if any */
-			puts(entry ? get_value(entry) : "NULL");
-			free(entry);
-
-		} else if (!strcmp("get", cmd) && p1) {
-			/* lookup entry in hashmap */
-			entry = hashmap_get_entry_from_hash(&map, hash, p1,
-							struct test_entry, ent);
-
-			/* print result */
-			if (!entry)
-				puts("NULL");
-			hashmap_for_each_entry_from(&map, entry, ent)
-				puts(get_value(entry));
-
-		} else if (!strcmp("remove", cmd) && p1) {
-
-			/* setup static key */
-			struct hashmap_entry key;
-			struct hashmap_entry *rm;
-			hashmap_entry_init(&key, hash);
-
-			/* remove entry from hashmap */
-			rm = hashmap_remove(&map, &key, p1);
-			entry = rm ? container_of(rm, struct test_entry, ent)
-					: NULL;
-
-			/* print result and free entry*/
-			puts(entry ? get_value(entry) : "NULL");
-			free(entry);
-
-		} else if (!strcmp("iterate", cmd)) {
-			struct hashmap_iter iter;
-
-			hashmap_for_each_entry(&map, &iter, entry,
-						ent /* member name */)
-				printf("%s %s\n", entry->key, get_value(entry));
-
-		} else if (!strcmp("size", cmd)) {
-
-			/* print table sizes */
-			printf("%u %u\n", map.tablesize,
-			       hashmap_get_size(&map));
-
-		} else if (!strcmp("intern", cmd) && p1) {
-
-			/* test that strintern works */
-			const char *i1 = strintern(p1);
-			const char *i2 = strintern(p1);
-			if (strcmp(i1, p1))
-				printf("strintern(%s) returns %s\n", p1, i1);
-			else if (i1 == p1)
-				printf("strintern(%s) returns input pointer\n", p1);
-			else if (i1 != i2)
-				printf("strintern(%s) != strintern(%s)", i1, i2);
-			else
-				printf("%s\n", i1);
-
-		} else if (!strcmp("perfhashmap", cmd) && p1 && p2) {
+	
+		if (!strcmp("perfhashmap", cmd) && p1 && p2) {
 
 			perf_hashmap(atoi(p1), atoi(p2));
 
@@ -270,6 +175,5 @@ int cmd__hashmap(int argc, const char **argv)
 
 	string_list_clear(&parts, 0);
 	strbuf_release(&line);
-	hashmap_clear_and_free(&map, struct test_entry, ent);
 	return 0;
 }
diff --git a/t/t0011-hashmap.sh b/t/t0011-hashmap.sh
deleted file mode 100755
index 46e74ad107..0000000000
--- a/t/t0011-hashmap.sh
+++ /dev/null
@@ -1,260 +0,0 @@
-#!/bin/sh
-
-test_description='test hashmap and string hash functions'
-
-TEST_PASSES_SANITIZE_LEAK=true
-. ./test-lib.sh
-
-test_hashmap() {
-	echo "$1" | test-tool hashmap $3 > actual &&
-	echo "$2" > expect &&
-	test_cmp expect actual
-}
-
-test_expect_success 'put' '
-
-test_hashmap "put key1 value1
-put key2 value2
-put fooBarFrotz value3
-put foobarfrotz value4
-size" "NULL
-NULL
-NULL
-NULL
-64 4"
-
-'
-
-test_expect_success 'put (case insensitive)' '
-
-test_hashmap "put key1 value1
-put key2 value2
-put fooBarFrotz value3
-size" "NULL
-NULL
-NULL
-64 3" ignorecase
-
-'
-
-test_expect_success 'replace' '
-
-test_hashmap "put key1 value1
-put key1 value2
-put fooBarFrotz value3
-put fooBarFrotz value4
-size" "NULL
-value1
-NULL
-value3
-64 2"
-
-'
-
-test_expect_success 'replace (case insensitive)' '
-
-test_hashmap "put key1 value1
-put Key1 value2
-put fooBarFrotz value3
-put foobarfrotz value4
-size" "NULL
-value1
-NULL
-value3
-64 2" ignorecase
-
-'
-
-test_expect_success 'get' '
-
-test_hashmap "put key1 value1
-put key2 value2
-put fooBarFrotz value3
-put foobarfrotz value4
-get key1
-get key2
-get fooBarFrotz
-get notInMap" "NULL
-NULL
-NULL
-NULL
-value1
-value2
-value3
-NULL"
-
-'
-
-test_expect_success 'get (case insensitive)' '
-
-test_hashmap "put key1 value1
-put key2 value2
-put fooBarFrotz value3
-get Key1
-get keY2
-get foobarfrotz
-get notInMap" "NULL
-NULL
-NULL
-value1
-value2
-value3
-NULL" ignorecase
-
-'
-
-test_expect_success 'add' '
-
-test_hashmap "add key1 value1
-add key1 value2
-add fooBarFrotz value3
-add fooBarFrotz value4
-get key1
-get fooBarFrotz
-get notInMap" "value2
-value1
-value4
-value3
-NULL"
-
-'
-
-test_expect_success 'add (case insensitive)' '
-
-test_hashmap "add key1 value1
-add Key1 value2
-add fooBarFrotz value3
-add foobarfrotz value4
-get key1
-get Foobarfrotz
-get notInMap" "value2
-value1
-value4
-value3
-NULL" ignorecase
-
-'
-
-test_expect_success 'remove' '
-
-test_hashmap "put key1 value1
-put key2 value2
-put fooBarFrotz value3
-remove key1
-remove key2
-remove notInMap
-size" "NULL
-NULL
-NULL
-value1
-value2
-NULL
-64 1"
-
-'
-
-test_expect_success 'remove (case insensitive)' '
-
-test_hashmap "put key1 value1
-put key2 value2
-put fooBarFrotz value3
-remove Key1
-remove keY2
-remove notInMap
-size" "NULL
-NULL
-NULL
-value1
-value2
-NULL
-64 1" ignorecase
-
-'
-
-test_expect_success 'iterate' '
-	test-tool hashmap >actual.raw <<-\EOF &&
-	put key1 value1
-	put key2 value2
-	put fooBarFrotz value3
-	iterate
-	EOF
-
-	cat >expect <<-\EOF &&
-	NULL
-	NULL
-	NULL
-	fooBarFrotz value3
-	key1 value1
-	key2 value2
-	EOF
-
-	sort <actual.raw >actual &&
-	test_cmp expect actual
-'
-
-test_expect_success 'iterate (case insensitive)' '
-	test-tool hashmap ignorecase >actual.raw <<-\EOF &&
-	put key1 value1
-	put key2 value2
-	put fooBarFrotz value3
-	iterate
-	EOF
-
-	cat >expect <<-\EOF &&
-	NULL
-	NULL
-	NULL
-	fooBarFrotz value3
-	key1 value1
-	key2 value2
-	EOF
-
-	sort <actual.raw >actual &&
-	test_cmp expect actual
-'
-
-test_expect_success 'grow / shrink' '
-
-	rm -f in &&
-	rm -f expect &&
-	for n in $(test_seq 51)
-	do
-		echo put key$n value$n >> in &&
-		echo NULL >> expect || return 1
-	done &&
-	echo size >> in &&
-	echo 64 51 >> expect &&
-	echo put key52 value52 >> in &&
-	echo NULL >> expect &&
-	echo size >> in &&
-	echo 256 52 >> expect &&
-	for n in $(test_seq 12)
-	do
-		echo remove key$n >> in &&
-		echo value$n >> expect || return 1
-	done &&
-	echo size >> in &&
-	echo 256 40 >> expect &&
-	echo remove key40 >> in &&
-	echo value40 >> expect &&
-	echo size >> in &&
-	echo 64 39 >> expect &&
-	test-tool hashmap <in >out &&
-	test_cmp expect out
-
-'
-
-test_expect_success 'string interning' '
-
-test_hashmap "intern value1
-intern Value1
-intern value2
-intern value2
-" "value1
-Value1
-value2
-value2"
-
-'
-
-test_done
diff --git a/t/unit-tests/t-hashmap.c b/t/unit-tests/t-hashmap.c
new file mode 100644
index 0000000000..7c9b239eca
--- /dev/null
+++ b/t/unit-tests/t-hashmap.c
@@ -0,0 +1,361 @@
+#include "test-lib.h"
+#include "hashmap.h"
+#include "strbuf.h"
+
+struct test_entry {
+	int padding; /* hashmap entry no longer needs to be the first member */
+	struct hashmap_entry ent;
+	/* key and value as two \0-terminated strings */
+	char key[FLEX_ARRAY];
+};
+
+static int test_entry_cmp(const void *cmp_data,
+			  const struct hashmap_entry *eptr,
+			  const struct hashmap_entry *entry_or_key,
+			  const void *keydata)
+{
+	const unsigned int ignore_case = cmp_data ? *((int *)cmp_data) : 0;
+	const struct test_entry *e1, *e2;
+	const char *key = keydata;
+
+	e1 = container_of(eptr, const struct test_entry, ent);
+	e2 = container_of(entry_or_key, const struct test_entry, ent);
+
+	if (ignore_case)
+		return strcasecmp(e1->key, key ? key : e2->key);
+	else
+		return strcmp(e1->key, key ? key : e2->key);
+}
+
+static const char *get_value(const struct test_entry *e)
+{
+	return e->key + strlen(e->key) + 1;
+}
+
+static struct test_entry *alloc_test_entry(const char *key, const char *value,
+					   unsigned int ignore_case)
+{
+	size_t klen = strlen(key);
+	size_t vlen = strlen(value);
+	unsigned int hash = ignore_case ? strihash(key) : strhash(key);
+	struct test_entry *entry = xmalloc(st_add4(sizeof(*entry), klen, vlen, 2));
+
+	hashmap_entry_init(&entry->ent, hash);
+	memcpy(entry->key, key, klen + 1);
+	memcpy(entry->key + klen + 1, value, vlen + 1);
+	return entry;
+}
+
+static struct test_entry *get_test_entry(struct hashmap *map, const char *key,
+					 unsigned int ignore_case)
+{
+	return hashmap_get_entry_from_hash(
+		map, ignore_case ? strihash(key) : strhash(key), key,
+		struct test_entry, ent);
+}
+
+static int key_val_contains(const char *key_val[][2], char seen[], size_t n,
+			    struct test_entry *entry)
+{
+	for (size_t i = 0; i < n; i++) {
+		if (!strcmp(entry->key, key_val[i][0]) &&
+		    !strcmp(get_value(entry), key_val[i][1])) {
+			if (seen[i])
+				return 2;
+			seen[i] = 1;
+			return 0;
+		}
+	}
+	return 1;
+}
+
+static void setup(void (*f)(struct hashmap *map, unsigned int ignore_case),
+		  unsigned int ignore_case)
+{
+	struct hashmap map = HASHMAP_INIT(test_entry_cmp, &ignore_case);
+
+	f(&map, ignore_case);
+	hashmap_clear_and_free(&map, struct test_entry, ent);
+}
+
+static void t_replace(struct hashmap *map, unsigned int ignore_case)
+{
+	struct test_entry *entry;
+
+	entry = alloc_test_entry("key1", "value1", ignore_case);
+	check_pointer_eq(hashmap_put_entry(map, entry, ent), NULL);
+
+	entry = alloc_test_entry(ignore_case ? "Key1" : "key1", "value2",
+				 ignore_case);
+	entry = hashmap_put_entry(map, entry, ent);
+	if (check(entry != NULL))
+		check_str(get_value(entry), "value1");
+	free(entry);
+
+	entry = alloc_test_entry("fooBarFrotz", "value3", ignore_case);
+	check_pointer_eq(hashmap_put_entry(map, entry, ent), NULL);
+
+	entry = alloc_test_entry(ignore_case ? "FOObarFrotz" : "fooBarFrotz",
+				 "value4", ignore_case);
+	entry = hashmap_put_entry(map, entry, ent);
+	if (check(entry != NULL))
+		check_str(get_value(entry), "value3");
+	free(entry);
+}
+
+static void t_get(struct hashmap *map, unsigned int ignore_case)
+{
+	struct test_entry *entry;
+	const char *key_val[][2] = { { "key1", "value1" },
+				     { "key2", "value2" },
+				     { "fooBarFrotz", "value3" },
+				     { ignore_case ? "TeNor" : "tenor",
+				       ignore_case ? "value4" : "value5" } };
+	const char *query[][2] = {
+		{ ignore_case ? "Key1" : "key1", "value1" },
+		{ ignore_case ? "keY2" : "key2", "value2" },
+		{ ignore_case ? "FOObarFrotz" : "fooBarFrotz", "value3" },
+		{ ignore_case ? "TENOR" : "tenor",
+		  ignore_case ? "value4" : "value5" }
+	};
+
+	for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
+		entry = alloc_test_entry(key_val[i][0], key_val[i][1],
+					 ignore_case);
+		check_pointer_eq(hashmap_put_entry(map, entry, ent), NULL);
+	}
+
+	for (size_t i = 0; i < ARRAY_SIZE(query); i++) {
+		entry = get_test_entry(map, query[i][0], ignore_case);
+		if (check(entry != NULL))
+			check_str(get_value(entry), query[i][1]);
+		else
+			test_msg("query key: %s", query[i][0]);
+	}
+
+	check_pointer_eq(get_test_entry(map, "notInMap", ignore_case), NULL);
+	check_int(map->tablesize, ==, 64);
+	check_int(hashmap_get_size(map), ==, ARRAY_SIZE(key_val));
+}
+
+static void t_add(struct hashmap *map, unsigned int ignore_case)
+{
+	struct test_entry *entry;
+	const char *key_val[][2] = {
+		{ "key1", "value1" },
+		{ ignore_case ? "Key1" : "key1", "value2" },
+		{ "fooBarFrotz", "value3" },
+		{ ignore_case ? "FOObarFrotz" : "fooBarFrotz", "value4" }
+	};
+	const char *query_keys[] = { "key1", ignore_case ? "FOObarFrotz" :
+							   "fooBarFrotz" };
+	char seen[ARRAY_SIZE(key_val)] = { 0 };
+
+	for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
+		entry = alloc_test_entry(key_val[i][0], key_val[i][1], ignore_case);
+		hashmap_add(map, &entry->ent);
+	}
+
+	for (size_t i = 0; i < ARRAY_SIZE(query_keys); i++) {
+		int count = 0;
+		entry = hashmap_get_entry_from_hash(map,
+			ignore_case ? strihash(query_keys[i]) :
+				      strhash(query_keys[i]),
+			query_keys[i], struct test_entry, ent);
+
+		hashmap_for_each_entry_from(map, entry, ent)
+		{
+			int ret;
+			if (!check_int((ret = key_val_contains(
+						key_val, seen,
+						ARRAY_SIZE(key_val), entry)),
+				       ==, 0)) {
+				switch (ret) {
+				case 1:
+					test_msg("found entry was not given in the input\n"
+						 "    key: %s\n  value: %s",
+						 entry->key, get_value(entry));
+					break;
+				case 2:
+					test_msg("duplicate entry detected\n"
+						 "    key: %s\n  value: %s",
+						 entry->key, get_value(entry));
+					break;
+				}
+			} else {
+				count++;
+			}
+		}
+		check_int(count, ==, 2);
+	}
+
+	for (size_t i = 0; i < ARRAY_SIZE(seen); i++) {
+		if (!check_int(seen[i], ==, 1))
+			test_msg("following key-val pair was not iterated over:\n"
+				 "    key: %s\n  value: %s",
+				 key_val[i][0], key_val[i][1]);
+	}
+
+	check_int(hashmap_get_size(map), ==, ARRAY_SIZE(key_val));
+	check_pointer_eq(get_test_entry(map, "notInMap", ignore_case), NULL);
+}
+
+static void t_remove(struct hashmap *map, unsigned int ignore_case)
+{
+	struct test_entry *entry, *removed;
+	const char *key_val[][2] = { { "key1", "value1" },
+				     { "key2", "value2" },
+				     { "fooBarFrotz", "value3" } };
+	const char *remove[][2] = { { ignore_case ? "Key1" : "key1", "value1" },
+				    { ignore_case ? "keY2" : "key2", "value2" } };
+
+	for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
+		entry = alloc_test_entry(key_val[i][0], key_val[i][1], ignore_case);
+		check_pointer_eq(hashmap_put_entry(map, entry, ent), NULL);
+	}
+
+	for (size_t i = 0; i < ARRAY_SIZE(remove); i++) {
+		entry = alloc_test_entry(remove[i][0], "", ignore_case);
+		removed = hashmap_remove_entry(map, entry, ent, remove[i][0]);
+		if (check(removed != NULL))
+			check_str(get_value(removed), remove[i][1]);
+		free(entry);
+		free(removed);
+	}
+
+	entry = alloc_test_entry("notInMap", "", ignore_case);
+	check_pointer_eq(hashmap_remove_entry(map, entry, ent, "notInMap"), NULL);
+	free(entry);
+
+	check_int(map->tablesize, ==, 64);
+	check_int(hashmap_get_size(map), ==, ARRAY_SIZE(key_val) - ARRAY_SIZE(remove));
+}
+
+static void t_iterate(struct hashmap *map, unsigned int ignore_case)
+{
+	struct test_entry *entry;
+	struct hashmap_iter iter;
+	const char *key_val[][2] = { { "key1", "value1" },
+				     { "key2", "value2" },
+				     { "fooBarFrotz", "value3" } };
+	char seen[ARRAY_SIZE(key_val)] = { 0 };
+
+	for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
+		entry = alloc_test_entry(key_val[i][0], key_val[i][1], ignore_case);
+		check_pointer_eq(hashmap_put_entry(map, entry, ent), NULL);
+	}
+
+	hashmap_for_each_entry(map, &iter, entry, ent /* member name */)
+	{
+		int ret;
+		if (!check_int((ret = key_val_contains(key_val, seen,
+						       ARRAY_SIZE(key_val),
+						       entry)), ==, 0)) {
+			switch (ret) {
+			case 1:
+				test_msg("found entry was not given in the input\n"
+					 "    key: %s\n  value: %s",
+					 entry->key, get_value(entry));
+				break;
+			case 2:
+				test_msg("duplicate entry detected\n"
+					 "    key: %s\n  value: %s",
+					 entry->key, get_value(entry));
+				break;
+			}
+		}
+	}
+
+	for (size_t i = 0; i < ARRAY_SIZE(seen); i++) {
+		if (!check_int(seen[i], ==, 1))
+			test_msg("following key-val pair was not iterated over:\n"
+				 "    key: %s\n  value: %s",
+				 key_val[i][0], key_val[i][1]);
+	}
+
+	check_int(hashmap_get_size(map), ==, ARRAY_SIZE(key_val));
+}
+
+static void t_alloc(struct hashmap *map, unsigned int ignore_case)
+{
+	struct test_entry *entry, *removed;
+
+	for (int i = 1; i <= 51; i++) {
+		char *key = xstrfmt("key%d", i);
+		char *value = xstrfmt("value%d", i);
+		entry = alloc_test_entry(key, value, ignore_case);
+		check_pointer_eq(hashmap_put_entry(map, entry, ent), NULL);
+		free(key);
+		free(value);
+	}
+	check_int(map->tablesize, ==, 64);
+	check_int(hashmap_get_size(map), ==, 51);
+
+	entry = alloc_test_entry("key52", "value52", ignore_case);
+	check_pointer_eq(hashmap_put_entry(map, entry, ent), NULL);
+	check_int(map->tablesize, ==, 256);
+	check_int(hashmap_get_size(map), ==, 52);
+
+	for (int i = 1; i <= 12; i++) {
+		char *key = xstrfmt("key%d", i);
+		char *value = xstrfmt("value%d", i);
+
+		entry = alloc_test_entry(key, "", ignore_case);
+		removed = hashmap_remove_entry(map, entry, ent, key);
+		if (check(removed != NULL))
+			check_str(value, get_value(removed));
+		free(key);
+		free(value);
+		free(entry);
+		free(removed);
+	}
+	check_int(map->tablesize, ==, 256);
+	check_int(hashmap_get_size(map), ==, 40);
+
+	entry = alloc_test_entry("key40", "", ignore_case);
+	removed = hashmap_remove_entry(map, entry, ent, "key40");
+	if (check(removed != NULL))
+		check_str("value40", get_value(removed));
+	check_int(map->tablesize, ==, 64);
+	check_int(hashmap_get_size(map), ==, 39);
+	free(entry);
+	free(removed);
+}
+
+static void t_intern(struct hashmap *map, unsigned int ignore_case)
+{
+	const char *values[] = { "value1", "Value1", "value2", "value2" };
+
+	for (size_t i = 0; i < ARRAY_SIZE(values); i++) {
+		const char *i1 = strintern(values[i]);
+		const char *i2 = strintern(values[i]);
+
+		if (!check(!strcmp(i1, values[i])))
+			test_msg("strintern(%s) returns %s\n", values[i], i1);
+		else if (!check(i1 != values[i]))
+			test_msg("strintern(%s) returns input pointer\n",
+				 values[i]);
+		else if (!check_pointer_eq(i1, i2))
+			test_msg("address('%s') != address('%s'), so strintern('%s') != strintern('%s')",
+				 i1, i2, values[i], values[i]);
+		else
+			check_str(i1, values[i]);
+	}
+}
+
+int cmd_main(int argc UNUSED, const char **argv UNUSED)
+{
+	TEST(setup(t_replace, 0), "replace works");
+	TEST(setup(t_replace, 1), "replace (case insensitive) works");
+	TEST(setup(t_get, 0), "get works");
+	TEST(setup(t_get, 1), "get (case insensitive) works");
+	TEST(setup(t_add, 0), "add works");
+	TEST(setup(t_add, 1), "add (case insensitive) works");
+	TEST(setup(t_remove, 0), "remove works");
+	TEST(setup(t_remove, 1), "remove (case insensitive) works");
+	TEST(setup(t_iterate, 0), "iterate works");
+	TEST(setup(t_iterate, 1), "iterate (case insensitive) works");
+	TEST(setup(t_alloc, 0), "grow / shrink works");
+	TEST(setup(t_intern, 0), "string interning works");
+	return test_done();
+}
-- 
2.45.2
Christian Couder· Jul 31, 2024, 17:18 UTC · re: A U Thor · lore

Re: [PATCH v4] t: port helper/test-hashmap.c to unit-tests/t-hashmap.c

Hi Ghanshyam,
Not sure why the "From:" header of this email says:
"From: A U Thor <shyamthakkar001@gmail.com>"
Did you make changes to your config or something?
On Tue, Jul 30, 2024 at 1:52 PM A U Thor <shyamthakkar001@gmail.com> wrote:
>
> From: Ghanshyam Thakkar <shyamthakkar001@gmail.com>
Show 8 quoted lines
> Changes in v4:
> - update commit message to add a reference and fix typo
> - change 'int ignore_case' to 'unsigned int ignore_case'
> - make 'ignore_case' the last parameter in all the functions
> - update t_get() to add a testcase query for better ignore-case
>   checking
>
> Range-diff against v3:
Show 18 quoted lines
>     -+static void t_get(struct hashmap *map, int ignore_case)
>     ++static void t_get(struct hashmap *map, unsigned int ignore_case)
>      +{
>      +  struct test_entry *entry;
>      +  const char *key_val[][2] = { { "key1", "value1" },
>      +                               { "key2", "value2" },
>      +                               { "fooBarFrotz", "value3" },
>     -+                               { ignore_case ? "key4" : "foobarfrotz", "value4" } };
>     ++                               { ignore_case ? "TeNor" : "tenor",
>     ++                                 ignore_case ? "value4" : "value5" } };
>      +  const char *query[][2] = {
>      +          { ignore_case ? "Key1" : "key1", "value1" },
>      +          { ignore_case ? "keY2" : "key2", "value2" },
>     -+          { ignore_case ? "foobarfrotz" : "fooBarFrotz", "value3" }
>     ++          { ignore_case ? "FOObarFrotz" : "fooBarFrotz", "value3" },
>     ++          { ignore_case ? "TENOR" : "tenor",
>     ++            ignore_case ? "value4" : "value5" }
>      +  };
I suggested adding the following test case:
               { ignore_case ? "FOOBarFrotZ" : "foobarfrotz",
                 ignore_case ? : "value3" : "value4" }
to better check that things work well especially when not ignoring the case.

This is because, when not ignoring the case, there used to be a choice between { "fooBarFrotz", "value3" } and { "foobarfrotz", "value4" } that can be decided only by the case of the key in 'query'. But instead you removed that choice from 'key_val'.

And it seems to me that the new test case you added doesn't bring much value.
Maybe there was something wrong in what I suggested, but then please explain it.

The other changes look good to me and seem to address the suggestions made by others and me.

Thanks!
Junio C Hamano· Jul 31, 2024, 18:50 UTC · re: Christian Couder · lore

Re: [PATCH v4] t: port helper/test-hashmap.c to unit-tests/t-hashmap.c

Christian Couder <christian.couder@gmail.com> writes:
Show 29 quoted lines
>>      +  const char *query[][2] = {
>>      +          { ignore_case ? "Key1" : "key1", "value1" },
>>      +          { ignore_case ? "keY2" : "key2", "value2" },
>>     -+          { ignore_case ? "foobarfrotz" : "fooBarFrotz", "value3" }
>>     ++          { ignore_case ? "FOObarFrotz" : "fooBarFrotz", "value3" },
>>     ++          { ignore_case ? "TENOR" : "tenor",
>>     ++            ignore_case ? "value4" : "value5" }
>>      +  };
>
> I suggested adding the following test case:
>
>                { ignore_case ? "FOOBarFrotZ" : "foobarfrotz",
>                  ignore_case ? : "value3" : "value4" }
>
> to better check that things work well especially when not ignoring the case.
>
> This is because, when not ignoring the case, there used to be a choice
> between { "fooBarFrotz", "value3" } and { "foobarfrotz", "value4" }
> that can be decided only by the case of the key in 'query'. But
> instead you removed that choice from 'key_val'.
>
> And it seems to me that the new test case you added doesn't bring much value.
>
> Maybe there was something wrong in what I suggested, but then please explain it.
>
> The other changes look good to me and seem to address the suggestions
> made by others and me.
>
> Thanks!

Thanks for a careful review, and of course thanks for working on the patch, A U Thor ;-)

Ghanshyam Thakkar· Aug 2, 2024, 02:28 UTC · re: Christian Couder · lore

Re: [PATCH v4] t: port helper/test-hashmap.c to unit-tests/t-hashmap.c

Christian Couder <christian.couder@gmail.com> wrote:
Show 7 quoted lines
> Hi Ghanshyam,
>
> Not sure why the "From:" header of this email says:
>
> "From: A U Thor <shyamthakkar001@gmail.com>"
>
> Did you make changes to your config or something?

I think I must have changed the user to "A U Thor <author@exmaple.com>" in the repo config while testing something, but don't consciously remember doing so.

Show 48 quoted lines
>
> On Tue, Jul 30, 2024 at 1:52 PM A U Thor <shyamthakkar001@gmail.com>
> wrote:
> >
> > From: Ghanshyam Thakkar <shyamthakkar001@gmail.com>
>
>
> > Changes in v4:
> > - update commit message to add a reference and fix typo
> > - change 'int ignore_case' to 'unsigned int ignore_case'
> > - make 'ignore_case' the last parameter in all the functions
> > - update t_get() to add a testcase query for better ignore-case
> >   checking
> >
> > Range-diff against v3:
>
>
> >     -+static void t_get(struct hashmap *map, int ignore_case)
> >     ++static void t_get(struct hashmap *map, unsigned int ignore_case)
> >      +{
> >      +  struct test_entry *entry;
> >      +  const char *key_val[][2] = { { "key1", "value1" },
> >      +                               { "key2", "value2" },
> >      +                               { "fooBarFrotz", "value3" },
> >     -+                               { ignore_case ? "key4" : "foobarfrotz", "value4" } };
> >     ++                               { ignore_case ? "TeNor" : "tenor",
> >     ++                                 ignore_case ? "value4" : "value5" } };
> >      +  const char *query[][2] = {
> >      +          { ignore_case ? "Key1" : "key1", "value1" },
> >      +          { ignore_case ? "keY2" : "key2", "value2" },
> >     -+          { ignore_case ? "foobarfrotz" : "fooBarFrotz", "value3" }
> >     ++          { ignore_case ? "FOObarFrotz" : "fooBarFrotz", "value3" },
> >     ++          { ignore_case ? "TENOR" : "tenor",
> >     ++            ignore_case ? "value4" : "value5" }
> >      +  };
>
> I suggested adding the following test case:
>
> { ignore_case ? "FOOBarFrotZ" : "foobarfrotz",
> ignore_case ? : "value3" : "value4" }
>
> to better check that things work well especially when not ignoring the
> case.
>
> This is because, when not ignoring the case, there used to be a choice
> between { "fooBarFrotz", "value3" } and { "foobarfrotz", "value4" }
> that can be decided only by the case of the key in 'query'. But
> instead you removed that choice from 'key_val'.

Yeah, you're correct about the choice thing. I think I misunderstood your comments from the previous version. Will update.

Thanks.
Ghanshyam Thakkar· Aug 3, 2024, 13:34 UTC · re: A U Thor · lore

[GSoC][PATCH v5] t: port helper/test-hashmap.c to unit-tests/t-hashmap.c

helper/test-hashmap.c along with t0011-hashmap.sh test the hashmap.h library. Migrate them to the unit testing framework for better debugging, runtime performance and concise code.

Along with the migration, make 'add' tests from the shell script order agnostic in unit tests, since they iterate over entries with the same keys and we do not guarantee the order. This was already done for the 'iterate' tests[1].

The helper/test-hashmap.c is still not removed because it contains a performance test meant to be run by the user directly (not used in t/perf). And it makes sense for such a utility to be a helper.

[1]: e1e7a77141 (t: sort output of hashmap iteration, 2019-07-30)
Mentored-by: Christian Couder <chriscool@tuxfamily.org>
Mentored-by: Kaartic Sivaraam <kaartic.sivaraam@gmail.com>
Helped-by: Josh Steadmon <steadmon@google.com>
Helped-by: Junio C Hamano <gitster@pobox.com>
Helped-by: Phillip Wood <phillip.wood123@gmail.com>
Signed-off-by: Ghanshyam Thakkar <shyamthakkar001@gmail.com>
---
Changes in v5:
- modify one of the inputs and queries inside t_get() to better check
  ignore-case scenario. This should address the comments from
  Christian in v4.
 Makefile                 |   1 +
 t/helper/test-hashmap.c  | 100 +----------
 t/t0011-hashmap.sh       | 260 ----------------------------
 t/unit-tests/t-hashmap.c | 361 +++++++++++++++++++++++++++++++++++++++
 4 files changed, 364 insertions(+), 358 deletions(-)
 delete mode 100755 t/t0011-hashmap.sh
 create mode 100644 t/unit-tests/t-hashmap.c
Show changes to 4 files +364 −358

Makefile, t/helper/test-hashmap.c, t/t0011-hashmap.sh, t/unit-tests/t-hashmap.c

diff --git a/Makefile b/Makefile
index 3eab701b10..74bb026610 100644
--- a/Makefile
+++ b/Makefile
@@ -1336,6 +1336,7 @@ THIRD_PARTY_SOURCES += sha1dc/%
 UNIT_TEST_PROGRAMS += t-ctype
 UNIT_TEST_PROGRAMS += t-example-decorate
 UNIT_TEST_PROGRAMS += t-hash
+UNIT_TEST_PROGRAMS += t-hashmap
 UNIT_TEST_PROGRAMS += t-mem-pool
 UNIT_TEST_PROGRAMS += t-oidtree
 UNIT_TEST_PROGRAMS += t-prio-queue
diff --git a/t/helper/test-hashmap.c b/t/helper/test-hashmap.c
index 2912899558..7b854a7030 100644
--- a/t/helper/test-hashmap.c
+++ b/t/helper/test-hashmap.c
@@ -12,11 +12,6 @@ struct test_entry
 	char key[FLEX_ARRAY];
 };
 
-static const char *get_value(const struct test_entry *e)
-{
-	return e->key + strlen(e->key) + 1;
-}
-
 static int test_entry_cmp(const void *cmp_data,
 			  const struct hashmap_entry *eptr,
 			  const struct hashmap_entry *entry_or_key,
@@ -141,30 +136,16 @@ static void perf_hashmap(unsigned int method, unsigned int rounds)
 /*
  * Read stdin line by line and print result of commands to stdout:
  *
- * hash key -> strhash(key) memhash(key) strihash(key) memihash(key)
- * put key value -> NULL / old value
- * get key -> NULL / value
- * remove key -> NULL / old value
- * iterate -> key1 value1\nkey2 value2\n...
- * size -> tablesize numentries
- *
  * perfhashmap method rounds -> test hashmap.[ch] performance
  */
 int cmd__hashmap(int argc, const char **argv)
 {
 	struct string_list parts = STRING_LIST_INIT_NODUP;
 	struct strbuf line = STRBUF_INIT;
-	int icase;
-	struct hashmap map = HASHMAP_INIT(test_entry_cmp, &icase);
-
-	/* init hash map */
-	icase = argc > 1 && !strcmp("ignorecase", argv[1]);
 
 	/* process commands from stdin */
 	while (strbuf_getline(&line, stdin) != EOF) {
 		char *cmd, *p1, *p2;
-		unsigned int hash = 0;
-		struct test_entry *entry;
 
 		/* break line into command and up to two parameters */
 		string_list_setlen(&parts, 0);
@@ -180,84 +161,8 @@ int cmd__hashmap(int argc, const char **argv)
 		cmd = parts.items[0].string;
 		p1 = parts.nr >= 1 ? parts.items[1].string : NULL;
 		p2 = parts.nr >= 2 ? parts.items[2].string : NULL;
-		if (p1)
-			hash = icase ? strihash(p1) : strhash(p1);
-
-		if (!strcmp("add", cmd) && p1 && p2) {
-
-			/* create entry with key = p1, value = p2 */
-			entry = alloc_test_entry(hash, p1, p2);
-
-			/* add to hashmap */
-			hashmap_add(&map, &entry->ent);
-
-		} else if (!strcmp("put", cmd) && p1 && p2) {
-
-			/* create entry with key = p1, value = p2 */
-			entry = alloc_test_entry(hash, p1, p2);
-
-			/* add / replace entry */
-			entry = hashmap_put_entry(&map, entry, ent);
-
-			/* print and free replaced entry, if any */
-			puts(entry ? get_value(entry) : "NULL");
-			free(entry);
-
-		} else if (!strcmp("get", cmd) && p1) {
-			/* lookup entry in hashmap */
-			entry = hashmap_get_entry_from_hash(&map, hash, p1,
-							struct test_entry, ent);
-
-			/* print result */
-			if (!entry)
-				puts("NULL");
-			hashmap_for_each_entry_from(&map, entry, ent)
-				puts(get_value(entry));
-
-		} else if (!strcmp("remove", cmd) && p1) {
-
-			/* setup static key */
-			struct hashmap_entry key;
-			struct hashmap_entry *rm;
-			hashmap_entry_init(&key, hash);
-
-			/* remove entry from hashmap */
-			rm = hashmap_remove(&map, &key, p1);
-			entry = rm ? container_of(rm, struct test_entry, ent)
-					: NULL;
-
-			/* print result and free entry*/
-			puts(entry ? get_value(entry) : "NULL");
-			free(entry);
-
-		} else if (!strcmp("iterate", cmd)) {
-			struct hashmap_iter iter;
-
-			hashmap_for_each_entry(&map, &iter, entry,
-						ent /* member name */)
-				printf("%s %s\n", entry->key, get_value(entry));
-
-		} else if (!strcmp("size", cmd)) {
-
-			/* print table sizes */
-			printf("%u %u\n", map.tablesize,
-			       hashmap_get_size(&map));
-
-		} else if (!strcmp("intern", cmd) && p1) {
-
-			/* test that strintern works */
-			const char *i1 = strintern(p1);
-			const char *i2 = strintern(p1);
-			if (strcmp(i1, p1))
-				printf("strintern(%s) returns %s\n", p1, i1);
-			else if (i1 == p1)
-				printf("strintern(%s) returns input pointer\n", p1);
-			else if (i1 != i2)
-				printf("strintern(%s) != strintern(%s)", i1, i2);
-			else
-				printf("%s\n", i1);
-
-		} else if (!strcmp("perfhashmap", cmd) && p1 && p2) {
+	
+		if (!strcmp("perfhashmap", cmd) && p1 && p2) {
 
 			perf_hashmap(atoi(p1), atoi(p2));
 
@@ -270,6 +175,5 @@ int cmd__hashmap(int argc, const char **argv)
 
 	string_list_clear(&parts, 0);
 	strbuf_release(&line);
-	hashmap_clear_and_free(&map, struct test_entry, ent);
 	return 0;
 }
diff --git a/t/t0011-hashmap.sh b/t/t0011-hashmap.sh
deleted file mode 100755
index 46e74ad107..0000000000
--- a/t/t0011-hashmap.sh
+++ /dev/null
@@ -1,260 +0,0 @@
-#!/bin/sh
-
-test_description='test hashmap and string hash functions'
-
-TEST_PASSES_SANITIZE_LEAK=true
-. ./test-lib.sh
-
-test_hashmap() {
-	echo "$1" | test-tool hashmap $3 > actual &&
-	echo "$2" > expect &&
-	test_cmp expect actual
-}
-
-test_expect_success 'put' '
-
-test_hashmap "put key1 value1
-put key2 value2
-put fooBarFrotz value3
-put foobarfrotz value4
-size" "NULL
-NULL
-NULL
-NULL
-64 4"
-
-'
-
-test_expect_success 'put (case insensitive)' '
-
-test_hashmap "put key1 value1
-put key2 value2
-put fooBarFrotz value3
-size" "NULL
-NULL
-NULL
-64 3" ignorecase
-
-'
-
-test_expect_success 'replace' '
-
-test_hashmap "put key1 value1
-put key1 value2
-put fooBarFrotz value3
-put fooBarFrotz value4
-size" "NULL
-value1
-NULL
-value3
-64 2"
-
-'
-
-test_expect_success 'replace (case insensitive)' '
-
-test_hashmap "put key1 value1
-put Key1 value2
-put fooBarFrotz value3
-put foobarfrotz value4
-size" "NULL
-value1
-NULL
-value3
-64 2" ignorecase
-
-'
-
-test_expect_success 'get' '
-
-test_hashmap "put key1 value1
-put key2 value2
-put fooBarFrotz value3
-put foobarfrotz value4
-get key1
-get key2
-get fooBarFrotz
-get notInMap" "NULL
-NULL
-NULL
-NULL
-value1
-value2
-value3
-NULL"
-
-'
-
-test_expect_success 'get (case insensitive)' '
-
-test_hashmap "put key1 value1
-put key2 value2
-put fooBarFrotz value3
-get Key1
-get keY2
-get foobarfrotz
-get notInMap" "NULL
-NULL
-NULL
-value1
-value2
-value3
-NULL" ignorecase
-
-'
-
-test_expect_success 'add' '
-
-test_hashmap "add key1 value1
-add key1 value2
-add fooBarFrotz value3
-add fooBarFrotz value4
-get key1
-get fooBarFrotz
-get notInMap" "value2
-value1
-value4
-value3
-NULL"
-
-'
-
-test_expect_success 'add (case insensitive)' '
-
-test_hashmap "add key1 value1
-add Key1 value2
-add fooBarFrotz value3
-add foobarfrotz value4
-get key1
-get Foobarfrotz
-get notInMap" "value2
-value1
-value4
-value3
-NULL" ignorecase
-
-'
-
-test_expect_success 'remove' '
-
-test_hashmap "put key1 value1
-put key2 value2
-put fooBarFrotz value3
-remove key1
-remove key2
-remove notInMap
-size" "NULL
-NULL
-NULL
-value1
-value2
-NULL
-64 1"
-
-'
-
-test_expect_success 'remove (case insensitive)' '
-
-test_hashmap "put key1 value1
-put key2 value2
-put fooBarFrotz value3
-remove Key1
-remove keY2
-remove notInMap
-size" "NULL
-NULL
-NULL
-value1
-value2
-NULL
-64 1" ignorecase
-
-'
-
-test_expect_success 'iterate' '
-	test-tool hashmap >actual.raw <<-\EOF &&
-	put key1 value1
-	put key2 value2
-	put fooBarFrotz value3
-	iterate
-	EOF
-
-	cat >expect <<-\EOF &&
-	NULL
-	NULL
-	NULL
-	fooBarFrotz value3
-	key1 value1
-	key2 value2
-	EOF
-
-	sort <actual.raw >actual &&
-	test_cmp expect actual
-'
-
-test_expect_success 'iterate (case insensitive)' '
-	test-tool hashmap ignorecase >actual.raw <<-\EOF &&
-	put key1 value1
-	put key2 value2
-	put fooBarFrotz value3
-	iterate
-	EOF
-
-	cat >expect <<-\EOF &&
-	NULL
-	NULL
-	NULL
-	fooBarFrotz value3
-	key1 value1
-	key2 value2
-	EOF
-
-	sort <actual.raw >actual &&
-	test_cmp expect actual
-'
-
-test_expect_success 'grow / shrink' '
-
-	rm -f in &&
-	rm -f expect &&
-	for n in $(test_seq 51)
-	do
-		echo put key$n value$n >> in &&
-		echo NULL >> expect || return 1
-	done &&
-	echo size >> in &&
-	echo 64 51 >> expect &&
-	echo put key52 value52 >> in &&
-	echo NULL >> expect &&
-	echo size >> in &&
-	echo 256 52 >> expect &&
-	for n in $(test_seq 12)
-	do
-		echo remove key$n >> in &&
-		echo value$n >> expect || return 1
-	done &&
-	echo size >> in &&
-	echo 256 40 >> expect &&
-	echo remove key40 >> in &&
-	echo value40 >> expect &&
-	echo size >> in &&
-	echo 64 39 >> expect &&
-	test-tool hashmap <in >out &&
-	test_cmp expect out
-
-'
-
-test_expect_success 'string interning' '
-
-test_hashmap "intern value1
-intern Value1
-intern value2
-intern value2
-" "value1
-Value1
-value2
-value2"
-
-'
-
-test_done
diff --git a/t/unit-tests/t-hashmap.c b/t/unit-tests/t-hashmap.c
new file mode 100644
index 0000000000..09a48c2c4e
--- /dev/null
+++ b/t/unit-tests/t-hashmap.c
@@ -0,0 +1,361 @@
+#include "test-lib.h"
+#include "hashmap.h"
+#include "strbuf.h"
+
+struct test_entry {
+	int padding; /* hashmap entry no longer needs to be the first member */
+	struct hashmap_entry ent;
+	/* key and value as two \0-terminated strings */
+	char key[FLEX_ARRAY];
+};
+
+static int test_entry_cmp(const void *cmp_data,
+			  const struct hashmap_entry *eptr,
+			  const struct hashmap_entry *entry_or_key,
+			  const void *keydata)
+{
+	const unsigned int ignore_case = cmp_data ? *((int *)cmp_data) : 0;
+	const struct test_entry *e1, *e2;
+	const char *key = keydata;
+
+	e1 = container_of(eptr, const struct test_entry, ent);
+	e2 = container_of(entry_or_key, const struct test_entry, ent);
+
+	if (ignore_case)
+		return strcasecmp(e1->key, key ? key : e2->key);
+	else
+		return strcmp(e1->key, key ? key : e2->key);
+}
+
+static const char *get_value(const struct test_entry *e)
+{
+	return e->key + strlen(e->key) + 1;
+}
+
+static struct test_entry *alloc_test_entry(const char *key, const char *value,
+					   unsigned int ignore_case)
+{
+	size_t klen = strlen(key);
+	size_t vlen = strlen(value);
+	unsigned int hash = ignore_case ? strihash(key) : strhash(key);
+	struct test_entry *entry = xmalloc(st_add4(sizeof(*entry), klen, vlen, 2));
+
+	hashmap_entry_init(&entry->ent, hash);
+	memcpy(entry->key, key, klen + 1);
+	memcpy(entry->key + klen + 1, value, vlen + 1);
+	return entry;
+}
+
+static struct test_entry *get_test_entry(struct hashmap *map, const char *key,
+					 unsigned int ignore_case)
+{
+	return hashmap_get_entry_from_hash(
+		map, ignore_case ? strihash(key) : strhash(key), key,
+		struct test_entry, ent);
+}
+
+static int key_val_contains(const char *key_val[][2], char seen[], size_t n,
+			    struct test_entry *entry)
+{
+	for (size_t i = 0; i < n; i++) {
+		if (!strcmp(entry->key, key_val[i][0]) &&
+		    !strcmp(get_value(entry), key_val[i][1])) {
+			if (seen[i])
+				return 2;
+			seen[i] = 1;
+			return 0;
+		}
+	}
+	return 1;
+}
+
+static void setup(void (*f)(struct hashmap *map, unsigned int ignore_case),
+		  unsigned int ignore_case)
+{
+	struct hashmap map = HASHMAP_INIT(test_entry_cmp, &ignore_case);
+
+	f(&map, ignore_case);
+	hashmap_clear_and_free(&map, struct test_entry, ent);
+}
+
+static void t_replace(struct hashmap *map, unsigned int ignore_case)
+{
+	struct test_entry *entry;
+
+	entry = alloc_test_entry("key1", "value1", ignore_case);
+	check_pointer_eq(hashmap_put_entry(map, entry, ent), NULL);
+
+	entry = alloc_test_entry(ignore_case ? "Key1" : "key1", "value2",
+				 ignore_case);
+	entry = hashmap_put_entry(map, entry, ent);
+	if (check(entry != NULL))
+		check_str(get_value(entry), "value1");
+	free(entry);
+
+	entry = alloc_test_entry("fooBarFrotz", "value3", ignore_case);
+	check_pointer_eq(hashmap_put_entry(map, entry, ent), NULL);
+
+	entry = alloc_test_entry(ignore_case ? "FOObarFrotz" : "fooBarFrotz",
+				 "value4", ignore_case);
+	entry = hashmap_put_entry(map, entry, ent);
+	if (check(entry != NULL))
+		check_str(get_value(entry), "value3");
+	free(entry);
+}
+
+static void t_get(struct hashmap *map, unsigned int ignore_case)
+{
+	struct test_entry *entry;
+	const char *key_val[][2] = { { "key1", "value1" },
+				     { "key2", "value2" },
+				     { "fooBarFrotz", "value3" },
+				     { ignore_case ? "key4" : "foobarfrotz",
+				       "value4" } };
+	const char *query[][2] = {
+		{ ignore_case ? "Key1" : "key1", "value1" },
+		{ ignore_case ? "keY2" : "key2", "value2" },
+		{ ignore_case ? "FOObarFrotz" : "fooBarFrotz", "value3" },
+		{ ignore_case ? "FOObarFrotz" : "foobarfrotz",
+		  ignore_case ? "value3" : "value4" }
+	};
+
+	for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
+		entry = alloc_test_entry(key_val[i][0], key_val[i][1],
+					 ignore_case);
+		check_pointer_eq(hashmap_put_entry(map, entry, ent), NULL);
+	}
+
+	for (size_t i = 0; i < ARRAY_SIZE(query); i++) {
+		entry = get_test_entry(map, query[i][0], ignore_case);
+		if (check(entry != NULL))
+			check_str(get_value(entry), query[i][1]);
+		else
+			test_msg("query key: %s", query[i][0]);
+	}
+
+	check_pointer_eq(get_test_entry(map, "notInMap", ignore_case), NULL);
+	check_int(map->tablesize, ==, 64);
+	check_int(hashmap_get_size(map), ==, ARRAY_SIZE(key_val));
+}
+
+static void t_add(struct hashmap *map, unsigned int ignore_case)
+{
+	struct test_entry *entry;
+	const char *key_val[][2] = {
+		{ "key1", "value1" },
+		{ ignore_case ? "Key1" : "key1", "value2" },
+		{ "fooBarFrotz", "value3" },
+		{ ignore_case ? "FOObarFrotz" : "fooBarFrotz", "value4" }
+	};
+	const char *query_keys[] = { "key1", ignore_case ? "FOObarFrotz" :
+							   "fooBarFrotz" };
+	char seen[ARRAY_SIZE(key_val)] = { 0 };
+
+	for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
+		entry = alloc_test_entry(key_val[i][0], key_val[i][1], ignore_case);
+		hashmap_add(map, &entry->ent);
+	}
+
+	for (size_t i = 0; i < ARRAY_SIZE(query_keys); i++) {
+		int count = 0;
+		entry = hashmap_get_entry_from_hash(map,
+			ignore_case ? strihash(query_keys[i]) :
+				      strhash(query_keys[i]),
+			query_keys[i], struct test_entry, ent);
+
+		hashmap_for_each_entry_from(map, entry, ent)
+		{
+			int ret;
+			if (!check_int((ret = key_val_contains(
+						key_val, seen,
+						ARRAY_SIZE(key_val), entry)),
+				       ==, 0)) {
+				switch (ret) {
+				case 1:
+					test_msg("found entry was not given in the input\n"
+						 "    key: %s\n  value: %s",
+						 entry->key, get_value(entry));
+					break;
+				case 2:
+					test_msg("duplicate entry detected\n"
+						 "    key: %s\n  value: %s",
+						 entry->key, get_value(entry));
+					break;
+				}
+			} else {
+				count++;
+			}
+		}
+		check_int(count, ==, 2);
+	}
+
+	for (size_t i = 0; i < ARRAY_SIZE(seen); i++) {
+		if (!check_int(seen[i], ==, 1))
+			test_msg("following key-val pair was not iterated over:\n"
+				 "    key: %s\n  value: %s",
+				 key_val[i][0], key_val[i][1]);
+	}
+
+	check_int(hashmap_get_size(map), ==, ARRAY_SIZE(key_val));
+	check_pointer_eq(get_test_entry(map, "notInMap", ignore_case), NULL);
+}
+
+static void t_remove(struct hashmap *map, unsigned int ignore_case)
+{
+	struct test_entry *entry, *removed;
+	const char *key_val[][2] = { { "key1", "value1" },
+				     { "key2", "value2" },
+				     { "fooBarFrotz", "value3" } };
+	const char *remove[][2] = { { ignore_case ? "Key1" : "key1", "value1" },
+				    { ignore_case ? "keY2" : "key2", "value2" } };
+
+	for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
+		entry = alloc_test_entry(key_val[i][0], key_val[i][1], ignore_case);
+		check_pointer_eq(hashmap_put_entry(map, entry, ent), NULL);
+	}
+
+	for (size_t i = 0; i < ARRAY_SIZE(remove); i++) {
+		entry = alloc_test_entry(remove[i][0], "", ignore_case);
+		removed = hashmap_remove_entry(map, entry, ent, remove[i][0]);
+		if (check(removed != NULL))
+			check_str(get_value(removed), remove[i][1]);
+		free(entry);
+		free(removed);
+	}
+
+	entry = alloc_test_entry("notInMap", "", ignore_case);
+	check_pointer_eq(hashmap_remove_entry(map, entry, ent, "notInMap"), NULL);
+	free(entry);
+
+	check_int(map->tablesize, ==, 64);
+	check_int(hashmap_get_size(map), ==, ARRAY_SIZE(key_val) - ARRAY_SIZE(remove));
+}
+
+static void t_iterate(struct hashmap *map, unsigned int ignore_case)
+{
+	struct test_entry *entry;
+	struct hashmap_iter iter;
+	const char *key_val[][2] = { { "key1", "value1" },
+				     { "key2", "value2" },
+				     { "fooBarFrotz", "value3" } };
+	char seen[ARRAY_SIZE(key_val)] = { 0 };
+
+	for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
+		entry = alloc_test_entry(key_val[i][0], key_val[i][1], ignore_case);
+		check_pointer_eq(hashmap_put_entry(map, entry, ent), NULL);
+	}
+
+	hashmap_for_each_entry(map, &iter, entry, ent /* member name */)
+	{
+		int ret;
+		if (!check_int((ret = key_val_contains(key_val, seen,
+						       ARRAY_SIZE(key_val),
+						       entry)), ==, 0)) {
+			switch (ret) {
+			case 1:
+				test_msg("found entry was not given in the input\n"
+					 "    key: %s\n  value: %s",
+					 entry->key, get_value(entry));
+				break;
+			case 2:
+				test_msg("duplicate entry detected\n"
+					 "    key: %s\n  value: %s",
+					 entry->key, get_value(entry));
+				break;
+			}
+		}
+	}
+
+	for (size_t i = 0; i < ARRAY_SIZE(seen); i++) {
+		if (!check_int(seen[i], ==, 1))
+			test_msg("following key-val pair was not iterated over:\n"
+				 "    key: %s\n  value: %s",
+				 key_val[i][0], key_val[i][1]);
+	}
+
+	check_int(hashmap_get_size(map), ==, ARRAY_SIZE(key_val));
+}
+
+static void t_alloc(struct hashmap *map, unsigned int ignore_case)
+{
+	struct test_entry *entry, *removed;
+
+	for (int i = 1; i <= 51; i++) {
+		char *key = xstrfmt("key%d", i);
+		char *value = xstrfmt("value%d", i);
+		entry = alloc_test_entry(key, value, ignore_case);
+		check_pointer_eq(hashmap_put_entry(map, entry, ent), NULL);
+		free(key);
+		free(value);
+	}
+	check_int(map->tablesize, ==, 64);
+	check_int(hashmap_get_size(map), ==, 51);
+
+	entry = alloc_test_entry("key52", "value52", ignore_case);
+	check_pointer_eq(hashmap_put_entry(map, entry, ent), NULL);
+	check_int(map->tablesize, ==, 256);
+	check_int(hashmap_get_size(map), ==, 52);
+
+	for (int i = 1; i <= 12; i++) {
+		char *key = xstrfmt("key%d", i);
+		char *value = xstrfmt("value%d", i);
+
+		entry = alloc_test_entry(key, "", ignore_case);
+		removed = hashmap_remove_entry(map, entry, ent, key);
+		if (check(removed != NULL))
+			check_str(value, get_value(removed));
+		free(key);
+		free(value);
+		free(entry);
+		free(removed);
+	}
+	check_int(map->tablesize, ==, 256);
+	check_int(hashmap_get_size(map), ==, 40);
+
+	entry = alloc_test_entry("key40", "", ignore_case);
+	removed = hashmap_remove_entry(map, entry, ent, "key40");
+	if (check(removed != NULL))
+		check_str("value40", get_value(removed));
+	check_int(map->tablesize, ==, 64);
+	check_int(hashmap_get_size(map), ==, 39);
+	free(entry);
+	free(removed);
+}
+
+static void t_intern(struct hashmap *map, unsigned int ignore_case)
+{
+	const char *values[] = { "value1", "Value1", "value2", "value2" };
+
+	for (size_t i = 0; i < ARRAY_SIZE(values); i++) {
+		const char *i1 = strintern(values[i]);
+		const char *i2 = strintern(values[i]);
+
+		if (!check(!strcmp(i1, values[i])))
+			test_msg("strintern(%s) returns %s\n", values[i], i1);
+		else if (!check(i1 != values[i]))
+			test_msg("strintern(%s) returns input pointer\n",
+				 values[i]);
+		else if (!check_pointer_eq(i1, i2))
+			test_msg("address('%s') != address('%s'), so strintern('%s') != strintern('%s')",
+				 i1, i2, values[i], values[i]);
+		else
+			check_str(i1, values[i]);
+	}
+}
+
+int cmd_main(int argc UNUSED, const char **argv UNUSED)
+{
+	TEST(setup(t_replace, 0), "replace works");
+	TEST(setup(t_replace, 1), "replace (case insensitive) works");
+	TEST(setup(t_get, 0), "get works");
+	TEST(setup(t_get, 1), "get (case insensitive) works");
+	TEST(setup(t_add, 0), "add works");
+	TEST(setup(t_add, 1), "add (case insensitive) works");
+	TEST(setup(t_remove, 0), "remove works");
+	TEST(setup(t_remove, 1), "remove (case insensitive) works");
+	TEST(setup(t_iterate, 0), "iterate works");
+	TEST(setup(t_iterate, 1), "iterate (case insensitive) works");
+	TEST(setup(t_alloc, 0), "grow / shrink works");
+	TEST(setup(t_intern, 0), "string interning works");
+	return test_done();
+}

Range-diff against v4:
1:  04022c4cb9 ! 1:  49cb2db9c8 t: port helper/test-hashmap.c to unit-tests/t-hashmap.c
    @@ t/unit-tests/t-hashmap.c (new)
     +	const char *key_val[][2] = { { "key1", "value1" },
     +				     { "key2", "value2" },
     +				     { "fooBarFrotz", "value3" },
    -+				     { ignore_case ? "TeNor" : "tenor",
    -+				       ignore_case ? "value4" : "value5" } };
    ++				     { ignore_case ? "key4" : "foobarfrotz",
    ++				       "value4" } };
     +	const char *query[][2] = {
     +		{ ignore_case ? "Key1" : "key1", "value1" },
     +		{ ignore_case ? "keY2" : "key2", "value2" },
     +		{ ignore_case ? "FOObarFrotz" : "fooBarFrotz", "value3" },
    -+		{ ignore_case ? "TENOR" : "tenor",
    -+		  ignore_case ? "value4" : "value5" }
    ++		{ ignore_case ? "FOObarFrotz" : "foobarfrotz",
    ++		  ignore_case ? "value3" : "value4" }
     +	};
     +
     +	for (size_t i = 0; i < ARRAY_SIZE(key_val); i++) {
-- 
2.46.0
Christian Couder· Aug 7, 2024, 14:33 UTC · re: Ghanshyam Thakkar · lore

Re: [GSoC][PATCH v5] t: port helper/test-hashmap.c to unit-tests/t-hashmap.c

On Sat, Aug 3, 2024 at 3:35 PM Ghanshyam Thakkar <shyamthakkar001@gmail.com> wrote:

Show 27 quoted lines
>
> helper/test-hashmap.c along with t0011-hashmap.sh test the hashmap.h
> library. Migrate them to the unit testing framework for better
> debugging, runtime performance and concise code.
>
> Along with the migration, make 'add' tests from the shell script order
> agnostic in unit tests, since they iterate over entries with the same
> keys and we do not guarantee the order. This was already done for the
> 'iterate' tests[1].
>
> The helper/test-hashmap.c is still not removed because it contains a
> performance test meant to be run by the user directly (not used in
> t/perf). And it makes sense for such a utility to be a helper.
>
> [1]: e1e7a77141 (t: sort output of hashmap iteration, 2019-07-30)
>
> Mentored-by: Christian Couder <chriscool@tuxfamily.org>
> Mentored-by: Kaartic Sivaraam <kaartic.sivaraam@gmail.com>
> Helped-by: Josh Steadmon <steadmon@google.com>
> Helped-by: Junio C Hamano <gitster@pobox.com>
> Helped-by: Phillip Wood <phillip.wood123@gmail.com>
> Signed-off-by: Ghanshyam Thakkar <shyamthakkar001@gmail.com>
> ---
> Changes in v5:
> - modify one of the inputs and queries inside t_get() to better check
>   ignore-case scenario. This should address the comments from
>   Christian in v4.

Yes, the only comment I had about the patch itself is addressed. There were also comments about the email author, but that is fixed too.

> Range-diff against v4:

Nit (not worth a reroll): the range-diff usually goes before the actual patch in the section starting with a line containing only 3 dashes

Show 18 quoted lines
> 1:  04022c4cb9 ! 1:  49cb2db9c8 t: port helper/test-hashmap.c to unit-tests/t-hashmap.c
>     @@ t/unit-tests/t-hashmap.c (new)
>      +  const char *key_val[][2] = { { "key1", "value1" },
>      +                               { "key2", "value2" },
>      +                               { "fooBarFrotz", "value3" },
>     -+                               { ignore_case ? "TeNor" : "tenor",
>     -+                                 ignore_case ? "value4" : "value5" } };
>     ++                               { ignore_case ? "key4" : "foobarfrotz",
>     ++                                 "value4" } };
>      +  const char *query[][2] = {
>      +          { ignore_case ? "Key1" : "key1", "value1" },
>      +          { ignore_case ? "keY2" : "key2", "value2" },
>      +          { ignore_case ? "FOObarFrotz" : "fooBarFrotz", "value3" },
>     -+          { ignore_case ? "TENOR" : "tenor",
>     -+            ignore_case ? "value4" : "value5" }
>     ++          { ignore_case ? "FOObarFrotz" : "foobarfrotz",
>     ++            ignore_case ? "value3" : "value4" }
>      +  };
Yeah, the above are the changes I suggested.

With this all the suggestions made by others and me have been taken into account and this patch should be good to go.

Thanks.
Ghanshyam Thakkar· Aug 7, 2024, 14:44 UTC · re: Christian Couder · lore

Re: [GSoC][PATCH v5] t: port helper/test-hashmap.c to unit-tests/t-hashmap.c

Christian Couder <christian.couder@gmail.com> wrote:
Show 8 quoted lines
> On Sat, Aug 3, 2024 at 3:35 PM Ghanshyam Thakkar
> <shyamthakkar001@gmail.com> wrote:
>
> > Range-diff against v4:
>
> Nit (not worth a reroll): the range-diff usually goes before the
> actual patch in the section starting with a line containing only 3
> dashes

'format-patch' placed it here by itself. Looking at the release notes for 2.46 I found this:

 * The inter/range-diff output has been moved to the end of the patch
   when format-patch adds it to a single patch, instead of writing it
   before the patch text, to be consistent with what is done for a
   cover letter for a multi-patch series.
Thanks.
Junio C Hamano· Aug 7, 2024, 16:20 UTC · re: Christian Couder · lore

Re: [GSoC][PATCH v5] t: port helper/test-hashmap.c to unit-tests/t-hashmap.c

Christian Couder <christian.couder@gmail.com> writes:
Show 5 quoted lines
>> Range-diff against v4:
>
> Nit (not worth a reroll): the range-diff usually goes before the
> actual patch in the section starting with a line containing only 3
> dashes

This comes from https://lore.kernel.org/git/Zk7UsJjhY_FV2z8C@tanuki/ that eventually became 2fa04ceb (format-patch: move range/inter diff at the end of a single patch output, 2024-05-24).

← back to recent threads