postgres/typesense
1
0
Fork 0
mirror of https://github.com/typesense/typesense.git synced 2025-05-23 23:30:42 +08:00
Code Issues Actions 3 Packages Projects Releases Wiki Activity

Merge pull request #1052 from krunal1313/doc_count_with_grouping

Browse Source 
adding found documents in results when group_by is enabled
This commit is contained in:
Kishore Nallan 2023-06-08 20:37:14 +05:30 committed by GitHub
commit 6b418318b2
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 22 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
src/collection.cpp
View File

@ -1384,7 +1384,7 @@ Option<nlohmann::json> Collection::search(std::string raw_query,
std::vector<std::vector<KV*>> raw_result_kvs;
std::vector<std::vector<KV*>> override_result_kvs;
size_t total_found = 0;
size_t total = 0;
std::vector<uint32_t> excluded_ids;
std::vector<std::pair<uint32_t, uint32_t>> included_ids; // ID -> position
@ -1557,12 +1557,13 @@ Option<nlohmann::json> Collection::search(std::string raw_query,
// for grouping we have to aggregate group set sizes to a count value
if(group_limit) {
total_found = search_params->groups_processed.size() + override_result_kvs.size();
total = search_params->groups_processed.size() + override_result_kvs.size();
} else {
total_found = search_params->all_result_ids_len;
total = search_params->all_result_ids_len;
}
if(search_cutoff && total_found == 0) {
if(search_cutoff && total == 0) {
// this can happen if other requests stopped this request from being processed
// we should return an error so that request can be retried by client
return Option<nlohmann::json>(408, "Request Timeout");
@ -1683,7 +1684,10 @@ Option<nlohmann::json> Collection::search(std::string raw_query,
}
nlohmann::json result = nlohmann::json::object();
result["found"] = total_found;
result["found"] = total;
if(group_limit != 0) {
result["found_docs"] = search_params->all_result_ids_len;
}
if(exclude_fields.count("out_of") == 0) {
result["out_of"] = num_documents.load();

14
test/collection_grouping_test.cpp
View File

@ -69,6 +69,7 @@ TEST_F(CollectionGroupingTest, GroupingBasics) {
"", 10,
{}, {}, {"size"}, 2).get();
ASSERT_EQ(12, res["found_docs"].get<size_t>());
ASSERT_EQ(3, res["found"].get<size_t>());
ASSERT_EQ(3, res["grouped_hits"].size());
ASSERT_EQ(11, res["grouped_hits"][0]["group_key"][0].get<size_t>());
@ -116,6 +117,7 @@ TEST_F(CollectionGroupingTest, GroupingBasics) {
{}, {}, {"rating"}, 2).get();
// 7 unique ratings
ASSERT_EQ(12, res["found_docs"].get<size_t>());
ASSERT_EQ(7, res["found"].get<size_t>());
ASSERT_EQ(7, res["grouped_hits"].size());
ASSERT_FLOAT_EQ(4.4, res["grouped_hits"][0]["group_key"][0].get<float>());
@ -167,7 +169,7 @@ TEST_F(CollectionGroupingTest, GroupingCompoundKey) {
spp::sparse_hash_set<std::string>(), 10, "", 30, 5,
"", 10,
{}, {}, {"size", "brand"}, 2).get();
ASSERT_EQ(12, res["found_docs"].get<size_t>());
ASSERT_EQ(10, res["found"].get<size_t>());
ASSERT_EQ(10, res["grouped_hits"].size());
@ -227,6 +229,7 @@ TEST_F(CollectionGroupingTest, GroupingCompoundKey) {
ASSERT_STREQ("0", res["grouped_hits"][0]["hits"][1]["document"]["id"].get<std::string>().c_str());
// total count and facet counts should be the same
ASSERT_EQ(12, res["found_docs"].get<size_t>());
ASSERT_EQ(10, res["found"].get<size_t>());
ASSERT_EQ(2, res["grouped_hits"].size());
ASSERT_EQ(10, res["grouped_hits"][0]["group_key"][0].get<size_t>());
@ -313,6 +316,7 @@ TEST_F(CollectionGroupingTest, GroupingWithMultiFieldRelevance) {
"", 10,
{}, {}, {"genre"}, 2).get();
ASSERT_EQ(7, results["found_docs"].get<size_t>());
ASSERT_EQ(3, results["found"].get<size_t>());
ASSERT_EQ(3, results["grouped_hits"].size());
@ -345,6 +349,7 @@ TEST_F(CollectionGroupingTest, GroupingWithGropLimitOfOne) {
"", 10,
{}, {}, {"brand"}, 1).get();
ASSERT_EQ(12, res["found_docs"].get<size_t>());
ASSERT_EQ(5, res["found"].get<size_t>());
ASSERT_EQ(5, res["grouped_hits"].size());
@ -430,6 +435,7 @@ TEST_F(CollectionGroupingTest, GroupingWithArrayFieldAndOverride) {
"", 10,
{}, {}, {"colors"}, 2).get();
ASSERT_EQ(9, res["found_docs"].get<size_t>());
ASSERT_EQ(4, res["found"].get<size_t>());
ASSERT_EQ(4, res["grouped_hits"].size());
@ -611,6 +617,7 @@ TEST_F(CollectionGroupingTest, SortingOnGroupCount) {
"", 10,
{}, {}, {"size"}, 2).get();
ASSERT_EQ(12, res["found_docs"].get<size_t>());
ASSERT_EQ(3, res["found"].get<size_t>());
ASSERT_EQ(3, res["grouped_hits"].size());
@ -635,6 +642,7 @@ TEST_F(CollectionGroupingTest, SortingOnGroupCount) {
"", 10,
{}, {}, {"size"}, 2).get();
ASSERT_EQ(12, res2["found_docs"].get<size_t>());
ASSERT_EQ(3, res2["found"].get<size_t>());
ASSERT_EQ(3, res2["grouped_hits"].size());
@ -715,6 +723,7 @@ TEST_F(CollectionGroupingTest, SortingMoreThanMaxTopsterSize) {
"", 10,
{}, {}, {"size"}, 2).get();
ASSERT_EQ(1000, res["found_docs"].get<size_t>());
ASSERT_EQ(300, res["found"].get<size_t>());
ASSERT_EQ(100, res["grouped_hits"].size());
@ -734,6 +743,7 @@ TEST_F(CollectionGroupingTest, SortingMoreThanMaxTopsterSize) {
"", 10,
{}, {}, {"size"}, 2).get();
ASSERT_EQ(1000, res["found_docs"].get<size_t>());
ASSERT_EQ(300, res["found"].get<size_t>());
ASSERT_EQ(100, res["grouped_hits"].size());
@ -757,6 +767,7 @@ TEST_F(CollectionGroupingTest, SortingMoreThanMaxTopsterSize) {
"", 10,
{}, {}, {"size"}, 2).get();
ASSERT_EQ(1000, res2["found_docs"].get<size_t>());
ASSERT_EQ(300, res2["found"].get<size_t>());
ASSERT_EQ(100, res2["grouped_hits"].size());
@ -775,6 +786,7 @@ TEST_F(CollectionGroupingTest, SortingMoreThanMaxTopsterSize) {
"", 10,
{}, {}, {"size"}, 2).get();
ASSERT_EQ(1000, res2["found_docs"].get<size_t>());
ASSERT_EQ(300, res2["found"].get<size_t>());
ASSERT_EQ(100, res2["grouped_hits"].size());