Skip to content

feat(query): Enhanced Inverted Index for VARIANT Type to precise matching Object within Arrays #19096

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
b41sh wants to merge 3 commits into
base: main
Choose a base branch
from
Draft

feat(query): Enhanced Inverted Index for VARIANT Type to precise matching Object within Arrays #19096

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
0af6e5c
feat(query): Enhanced Inverted Index for VARIANT Type to precise matc…
b41sh Dec 10, 2025
74667ab
fix
b41sh Dec 12, 2025
be7a9cf
fix
b41sh Dec 15, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
20 changes: 10 additions & 10 deletions Cargo.lock
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

8 changes: 4 additions & 4 deletions Cargo.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -661,9 +661,9 @@ recursive = { git = "https://github.com/datafuse-extras/recursive.git", rev = "1
sled = { git = "https://github.com/datafuse-extras/sled", tag = "v0.34.7-datafuse.1" }
state-machine-api = { git = "https://github.com/databendlabs/state-machine-api.git", tag = "v0.3.4" }
sub-cache = { git = "https://github.com/databendlabs/sub-cache", tag = "v0.2.1" }
tantivy = { git = "https://github.com/datafuse-extras/tantivy", rev = "9065a4d" }
tantivy-common = { git = "https://github.com/datafuse-extras/tantivy", rev = "9065a4d", package = "tantivy-common" }
tantivy-jieba = { git = "https://github.com/datafuse-extras/tantivy-jieba", rev = "ac27464" }
tantivy-query-grammar = { git = "https://github.com/datafuse-extras/tantivy", rev = "9065a4d", package = "tantivy-query-grammar" }
tantivy = { git = "https://github.com/b41sh/tantivy", rev = "48fb0f7f3c393de67a0b46d8a3be50f085312fd4" }
tantivy-common = { git = "https://github.com/b41sh/tantivy", rev = "48fb0f7f3c393de67a0b46d8a3be50f085312fd4", package = "tantivy-common" }
tantivy-jieba = { git = "https://github.com/b41sh/tantivy-jieba", rev = "de314415bdcbf01ab10ab3f76b8eef7cdb6fadf1" }
tantivy-query-grammar = { git = "https://github.com/b41sh/tantivy", rev = "48fb0f7f3c393de67a0b46d8a3be50f085312fd4", package = "tantivy-query-grammar" }
watcher = { git = "https://github.com/databendlabs/watcher", tag = "v0.4.2" }
xorfilter-rs = { git = "https://github.com/datafuse-extras/xorfilter", tag = "databend-alpha.4" }
9 changes: 9 additions & 0 deletions src/query/storages/fuse/src/pruning/inverted_index_pruner.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,7 @@ use std::sync::Arc;
use databend_common_catalog::plan::InvertedIndexInfo;
use databend_common_catalog::plan::PushDownInfo;
use databend_common_exception::Result;
use databend_common_expression::types::DataType;
use databend_common_expression::types::F32;
use databend_storages_common_io::ReadSettings;
use opendal::Operator;
Expand Down Expand Up @@ -95,6 +96,14 @@ impl InvertedIndexPruner {
need_position = true;
}
});
for field_id in &field_ids {
let field = inverted_index_info.index_schema.field(*field_id as usize);
let data_type = field.data_type().remove_nullable();
if data_type == DataType::Variant {
need_position = true;
break;
}
}

// whether need to generate score internl column
let has_score = inverted_index_info.has_score;
Expand Down
28 changes: 28 additions & 0 deletions tests/sqllogictests/suites/query/index/04_inverted_index/04_0000_inverted_index_base.test
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -500,6 +500,33 @@ query IT
select * from t2 where query('body:test');
----


statement ok
CREATE TABLE t3 (id int, body variant, INVERTED INDEX idx (body))

statement ok
INSERT INTO t3 VALUES
(1, '{"videoInfo":{"extraData":[{ "name": "codecA", "type": "mp4" },{ "name": "codecB", "type": "jpg" }]}}'),
(2, '{"videoInfo":{"extraData":[{ "name": "codecA", "type": "jpg" },{ "name": "codecA", "type": "mp4" }]}}'),
(3, '{"videoInfo":{"extraData":[{ "name": "codecA", "type": "jpg" },{ "name": "codecB", "type": "mp4" }]}}');

query IT
select * from t3 where query('body.videoInfo.extraData.name:codecA AND body.videoInfo.extraData.type:jpg');
----
2 {"videoInfo":{"extraData":[{"name":"codecA","type":"jpg"},{"name":"codecA","type":"mp4"}]}}
3 {"videoInfo":{"extraData":[{"name":"codecA","type":"jpg"},{"name":"codecB","type":"mp4"}]}}

query IT
select * from t3 where query('body.videoInfo.extraData.name:codecA AND body.videoInfo.extraData.type:mp4');
----
1 {"videoInfo":{"extraData":[{"name":"codecA","type":"mp4"},{"name":"codecB","type":"jpg"}]}}
2 {"videoInfo":{"extraData":[{"name":"codecA","type":"jpg"},{"name":"codecA","type":"mp4"}]}}

query IT
select * from t3 where query('body.videoInfo.extraData.name:codecB AND body.videoInfo.extraData.type:jpg');
----
1 {"videoInfo":{"extraData":[{"name":"codecA","type":"mp4"},{"name":"codecB","type":"jpg"}]}}

statement ok
CREATE TABLE t_native (id int, content string, INVERTED INDEX idx1 (content)) storage_format = 'native' row_per_page = 2;

Expand Down Expand Up @@ -528,3 +555,4 @@ use default
statement ok
drop database test_inverted_index


Loading