nostrdb

commit 6e9b1aa0f848292eb5a52b41bad48b0478ac0c07
parent 8813d9ebec3f6f8f0e74b960bae248d1e6b20aaf
Author: William Casarin <jb55@jb55.com>
Date:   Tue, 28 Nov 2023 10:51:12 -0800

search: make search case insensitive

Diffstat:
M
cursor.h
 | 
14
++++++++++++++
M
nostrdb.c
 | 
4
++--
M
test.c
 | 
12
+++++++++++-

3 files changed, 27 insertions(+), 3 deletions(-)
diff --git a/cursor.h b/cursor.h
@@ -50,6 +50,20 @@ static inline int cursor_push(struct cursor *cursor, unsigned char *data, int le
 	return 1;
 }
 
+static inline int cursor_push_lowercase(struct cursor *cur, const char *str, int len)
+{
+	int i;
+
+	if (unlikely(cur->p + len >= cur->end))
+		return 0;
+
+	for (i = 0; i < len; i++)
+		cur->p[i] = tolower(str[i]);
+
+	cur->p += len;
+	return 1;
+}
+
 static inline int cursor_push_str(struct cursor *cursor, const char *str)
 {
 	return cursor_push(cursor, (unsigned char*)str, (int)strlen(str));
diff --git a/nostrdb.c b/nostrdb.c
@@ -164,8 +164,8 @@ static int ndb_make_text_search_key(unsigned char *buf, int bufsize,
 	if (!push_varint(&cur, word_len))
 		return 0;
 
-	// non-null terminated string
-	if (!cursor_push(&cur, (unsigned char*)str, word_len))
+	// non-null terminated, lowercase string
+	if (!cursor_push_lowercase(&cur, str, word_len))
 		return 0;
 
 	// the index of the word in the content so that we can do more accurate
diff --git a/test.c b/test.c
@@ -948,16 +948,26 @@ static void test_fulltext()
 	size_t mapsize;
 	int ingester_threads;
 	struct ndb_txn txn;
+	int written;
+	static const int alloc_size = 2 << 18;
+	char *json = malloc(alloc_size);
 
 	mapsize = 1024 * 1024 * 100;
 	ingester_threads = 1;
 	assert(ndb_init(&ndb, test_dir, mapsize, ingester_threads, 0));
 
+	read_file("testdata/search.json", (unsigned char*)json, alloc_size, &written);
+	assert(ndb_process_client_events(ndb, json, written));
+	ndb_destroy(ndb);
+	assert(ndb_init(&ndb, test_dir, mapsize, ingester_threads, 0));
+
 	ndb_begin_query(ndb, &txn);
-	ndb_text_search(&txn, "bits after");
+	ndb_text_search(&txn, "Jumped Over");
 	ndb_end_query(&txn);
 
 	ndb_destroy(ndb);
+
+	free(json);
 }
 
 int main(int argc, const char *argv[]) {