strmap: new utility functions

Add strmap as a new struct and associated utility functions,
specifically for hashmaps that map strings to some value.  The API is
taken directly from Peff's proposal at
https://lore.kernel.org/git/20180906191203.GA26184@sigill.intra.peff.net/

Note that similar string-list, I have a strdup_strings setting.
However, unlike string-list, strmap_init() does not take a parameter for
this setting and instead automatically sets it to 1; callers who want to
control this detail need to instead call strmap_init_with_options().
(Future patches will add additional parameters to
strmap_init_with_options()).

Signed-off-by: Elijah Newren <newren@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

3 files changed, 165 insertions, 0 deletions

diff --git a/Makefile b/Makefile
index 95571ee3fc..777a34c01c 100644
--- a/Makefile
+++ b/Makefile
@@ -1000,6 +1000,7 @@ LIB_OBJS += stable-qsort.o
 LIB_OBJS += strbuf.o
 LIB_OBJS += streaming.o
 LIB_OBJS += string-list.o
+LIB_OBJS += strmap.o
 LIB_OBJS += strvec.o
 LIB_OBJS += sub-process.o
 LIB_OBJS += submodule-config.o
diff --git a/strmap.c b/strmap.c
new file mode 100644
index 0000000000..53f284eb20
--- /dev/null
+++ b/strmap.c
@@ -0,0 +1,99 @@
+#include "git-compat-util.h"
+#include "strmap.h"
+
+int cmp_strmap_entry(const void *hashmap_cmp_fn_data,
+		     const struct hashmap_entry *entry1,
+		     const struct hashmap_entry *entry2,
+		     const void *keydata)
+{
+	const struct strmap_entry *e1, *e2;
+
+	e1 = container_of(entry1, const struct strmap_entry, ent);
+	e2 = container_of(entry2, const struct strmap_entry, ent);
+	return strcmp(e1->key, e2->key);
+}
+
+static struct strmap_entry *find_strmap_entry(struct strmap *map,
+					      const char *str)
+{
+	struct strmap_entry entry;
+	hashmap_entry_init(&entry.ent, strhash(str));
+	entry.key = str;
+	return hashmap_get_entry(&map->map, &entry, ent, NULL);
+}
+
+void strmap_init(struct strmap *map)
+{
+	strmap_init_with_options(map, 1);
+}
+
+void strmap_init_with_options(struct strmap *map,
+			      int strdup_strings)
+{
+	hashmap_init(&map->map, cmp_strmap_entry, NULL, 0);
+	map->strdup_strings = strdup_strings;
+}
+
+static void strmap_free_entries_(struct strmap *map, int free_values)
+{
+	struct hashmap_iter iter;
+	struct strmap_entry *e;
+
+	if (!map)
+		return;
+
+	/*
+	 * We need to iterate over the hashmap entries and free
+	 * e->key and e->value ourselves; hashmap has no API to
+	 * take care of that for us.  Since we're already iterating over
+	 * the hashmap, though, might as well free e too and avoid the need
+	 * to make some call into the hashmap API to do that.
+	 */
+	hashmap_for_each_entry(&map->map, &iter, e, ent) {
+		if (free_values)
+			free(e->value);
+		if (map->strdup_strings)
+			free((char*)e->key);
+		free(e);
+	}
+}
+
+void strmap_clear(struct strmap *map, int free_values)
+{
+	strmap_free_entries_(map, free_values);
+	hashmap_clear(&map->map);
+}
+
+void *strmap_put(struct strmap *map, const char *str, void *data)
+{
+	struct strmap_entry *entry = find_strmap_entry(map, str);
+	void *old = NULL;
+
+	if (entry) {
+		old = entry->value;
+		entry->value = data;
+	} else {
+		const char *key = str;
+
+		entry = xmalloc(sizeof(*entry));
+		hashmap_entry_init(&entry->ent, strhash(str));
+
+		if (map->strdup_strings)
+			key = xstrdup(str);
+		entry->key = key;
+		entry->value = data;
+		hashmap_add(&map->map, &entry->ent);
+	}
+	return old;
+}
+
+void *strmap_get(struct strmap *map, const char *str)
+{
+	struct strmap_entry *entry = find_strmap_entry(map, str);
+	return entry ? entry->value : NULL;
+}
+
+int strmap_contains(struct strmap *map, const char *str)
+{
+	return find_strmap_entry(map, str) != NULL;
+}
diff --git a/strmap.h b/strmap.h
new file mode 100644
index 0000000000..96888c23ad
--- /dev/null
+++ b/strmap.h
@@ -0,0 +1,65 @@
+#ifndef STRMAP_H
+#define STRMAP_H
+
+#include "hashmap.h"
+
+struct strmap {
+	struct hashmap map;
+	unsigned int strdup_strings:1;
+};
+
+struct strmap_entry {
+	struct hashmap_entry ent;
+	const char *key;
+	void *value;
+};
+
+int cmp_strmap_entry(const void *hashmap_cmp_fn_data,
+		     const struct hashmap_entry *entry1,
+		     const struct hashmap_entry *entry2,
+		     const void *keydata);
+
+#define STRMAP_INIT { \
+			.map = HASHMAP_INIT(cmp_strmap_entry, NULL),  \
+			.strdup_strings = 1,                          \
+		    }
+
+/*
+ * Initialize the members of the strmap.  Any keys added to the strmap will
+ * be strdup'ed with their memory managed by the strmap.
+ */
+void strmap_init(struct strmap *map);
+
+/*
+ * Same as strmap_init, but for those who want to control the memory management
+ * carefully instead of using the default of strdup_strings=1.
+ */
+void strmap_init_with_options(struct strmap *map,
+			      int strdup_strings);
+
+/*
+ * Remove all entries from the map, releasing any allocated resources.
+ */
+void strmap_clear(struct strmap *map, int free_values);
+
+/*
+ * Insert "str" into the map, pointing to "data".
+ *
+ * If an entry for "str" already exists, its data pointer is overwritten, and
+ * the original data pointer returned. Otherwise, returns NULL.
+ */
+void *strmap_put(struct strmap *map, const char *str, void *data);
+
+/*
+ * Return the data pointer mapped by "str", or NULL if the entry does not
+ * exist.
+ */
+void *strmap_get(struct strmap *map, const char *str);
+
+/*
+ * Return non-zero iff "str" is present in the map. This differs from
+ * strmap_get() in that it can distinguish entries with a NULL data pointer.
+ */
+int strmap_contains(struct strmap *map, const char *str);
+
+#endif /* STRMAP_H */