Open Source alternative to Algolia + Pinecone and an Easier-to-Use alternative to ElasticSearch ⚡ 🔍 ✨ Fast, typo tolerant, in-memory fuzzy Search Engine for building delightful search experiences
C++ algoliadatastoreelasticsearchenterprise-searchfacetingfull-text-searchfuzzy-searchgeosearchin-memoryinstantsearchmerchandisingpineconesearchsearch-enginesemantic-searchsimilarity-searchsite-searchsynonymstypo-tolerancevector-search
Speed up wildcard searches further.
kishorenc14faa3af4e69
diff --git a/TODO.md b/TODO.mdindex 8c3bed2d..0c5afdb8 100644--- a/TODO.md+++ b/TODO.md@@ -2,6 +2,13 @@## Pre-alpha+a) ~~Fix memory ratio (decreasing with indexing)~~+b) ~~Speed up wildcard searches further~~+c) Allow int64 in default sorting field+d) Use connection timeout for CURL rather than request timeout+e) Update role to set max memory ration at 0.80+f) Async import+**Search index**- ~~Proper JSON as input~~diff --git a/src/collection.cpp b/src/collection.cppindex e5495630..a3955d00 100644--- a/src/collection.cpp+++ b/src/collection.cpp@@ -619,15 +619,6 @@ Option<nlohmann::json> Collection::search(const std::string & query, const std::filters.push_back(f);}- // for a wildcard query, if filter is not specified, use default_sorting_field as a catch-all- if(query == "*" && filters.empty()) {- field f = search_schema.at(default_sorting_field);- std::string max_value = f.is_float() ? std::to_string(std::numeric_limits<float>::max()) :- std::to_string(std::numeric_limits<int32_t>::max());- filter catch_all_filter = {f.name, {max_value}, LESS_THAN_EQUALS};- filters.push_back(catch_all_filter);- }-// validate facet fieldsfor(const std::string & field_name: facet_fields) {if(facet_schema.count(field_name) == 0) {diff --git a/src/index.cpp b/src/index.cppindex 6613e572..2fcc048d 100644--- a/src/index.cpp+++ b/src/index.cpp@@ -1164,11 +1164,32 @@ void Index::search(Option<uint32_t> & outcome,const uint8_t field_id = (uint8_t)(FIELD_LIMIT_NUM - 0);const std::string & field = search_fields[0];+ // if a filter is not specified, use the sorting index to generate the list of all document ids+ if(filters.empty()) {+ std::string all_records_field;++ // get the first non-optional field+ for(const auto& kv: sort_schema) {+ if(!kv.second.optional && kv.first != sort_field_const::text_match) {+ all_records_field = kv.first;+ break;+ }+ }++ const spp::sparse_hash_map<uint32_t, int64_t> *kvs = sort_index[all_records_field];+ filter_ids_length = kvs->size();+ filter_ids = new uint32_t[filter_ids_length];++ size_t i = 0;+ for(const auto& kv: *kvs) {+ filter_ids[i++] = kv.first;+ }+ }+if(!curated_ids.empty()) {uint32_t *excluded_result_ids = nullptr;filter_ids_length = ArrayUtils::exclude_scalar(filter_ids, filter_ids_length, &curated_ids_sorted[0],curated_ids.size(), &excluded_result_ids);-delete [] filter_ids;filter_ids = excluded_result_ids;}diff --git a/test/collection_test.cpp b/test/collection_test.cppindex f22a5068..29ecd996 100644--- a/test/collection_test.cpp+++ b/test/collection_test.cpp@@ -2259,7 +2259,7 @@ TEST_F(CollectionTest, OptionalFields) {infile.close();- // first must be able to fetch all records (i.e. all must have been index)+ // first must be able to fetch all records (i.e. all must have been indexed)auto res = coll1->search("*", {"title"}, "", {}, {}, 0, 10, 1, FREQUENCY, false).get();ASSERT_EQ(6, res["found"].get<size_t>());