tyiu/damus
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

nostrdb/search: phrase searching working

Browse Source 
This changes the search algorithm to be much smarter and more efficient
at searching phrases.

It is also much simpler, using less intermediate data structures.

Signed-off-by: William Casarin <jb55@jb55.com>
This commit is contained in:
William Casarin
2023-11-30 13:00:04 -08:00
parent 213a26cd01
commit 9d208284c6
2 changed files with 261 additions and 167 deletions
Download Patch File Download Diff File Expand all files Collapse all files

43
nostrdb/nostrdb.h
View File

@@ -163,6 +163,30 @@ struct ndb_keypair {
unsigned char pair[96];
};
#define MAX_TEXT_SEARCH_RESULTS 128
#define MAX_TEXT_SEARCH_WORDS 8
// unpacked form of the actual lmdb fulltext search key
// see `ndb_make_text_search_key` for how the packed version is constructed
struct ndb_text_search_key
{
int str_len;
const char *str;
uint64_t timestamp;
uint64_t note_id;
int word_index;
};
struct ndb_text_search_result {
struct ndb_text_search_key key;
int prefix_chars;
};
struct ndb_text_search_results {
struct ndb_text_search_result results[MAX_TEXT_SEARCH_RESULTS];
int num_results;
};
// these must be byte-aligned, they are directly accessing the serialized data
// representation
#pragma pack(push, 1)
@@ -271,25 +295,6 @@ struct ndb_filter {
struct ndb_filter_elements *elements[NDB_NUM_FILTERS];
};
// unpacked form of the actual lmdb fulltext search key
// see `ndb_make_text_search_key` for how the packed version is constructed
struct ndb_text_search_key
{
int str_len;
const char *str;
int word_index;
uint64_t timestamp;
};
// contains note ids of the searched notes from ndb_text_search
struct ndb_text_search_results {
uint64_t phrase_results[32];
int num_phrase_results;
uint64_t other_results[32];
int num_other_results;
};
// HELPERS
int ndb_calculate_id(struct ndb_note *note, unsigned char *buf, int buflen);