Skip to content

test: Add more push down support #30

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

Merged
Xuanwo merged 2 commits into from
Dec 23, 2025
Merged

test: Add more push down support #30

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
87c652d
test: Add more push down support
Xuanwo Dec 23, 2025
6675488
Fix format check
Xuanwo Dec 23, 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
22 changes: 12 additions & 10 deletions src/lance_scan.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -90,7 +90,7 @@ struct LanceScanBindData : public TableFunctionData {
ArrowTableSchema arrow_table;
vector<string> names;
vector<LogicalType> types;
string lance_complex_filter_sql;
string lance_pushed_filter_sql;

~LanceScanBindData() override {
if (dataset) {
Expand Down Expand Up @@ -467,7 +467,7 @@ static bool TrySerializeLanceExpr(const LogicalGet &get,
}

static void
LancePushdownComplexFilter(ClientContext &, LogicalGet &get,
LancePushdownComplexFilter(ClientContext &context, LogicalGet &get,
FunctionData *bind_data,
vector<unique_ptr<Expression>> &filters) {
if (!bind_data || filters.empty()) {
Expand All @@ -493,11 +493,11 @@ LancePushdownComplexFilter(ClientContext &, LogicalGet &get,
return;
}
auto pushed_sql = StringUtil::Join(predicates, " AND ");
if (scan_bind.lance_complex_filter_sql.empty()) {
scan_bind.lance_complex_filter_sql = std::move(pushed_sql);
if (scan_bind.lance_pushed_filter_sql.empty()) {
scan_bind.lance_pushed_filter_sql = std::move(pushed_sql);
} else {
scan_bind.lance_complex_filter_sql =
"(" + scan_bind.lance_complex_filter_sql + ") AND (" + pushed_sql + ")";
scan_bind.lance_pushed_filter_sql =
"(" + scan_bind.lance_pushed_filter_sql + ") AND (" + pushed_sql + ")";
}
}

Expand Down Expand Up @@ -583,13 +583,15 @@ LanceScanInitGlobal(ClientContext &context, TableFunctionInitInput &input) {
}

auto table_filter_sql = BuildLanceFilterSQL(bind_data, input);
if (bind_data.lance_complex_filter_sql.empty()) {
auto pushed_filter_sql = bind_data.lance_pushed_filter_sql;

if (pushed_filter_sql.empty()) {
scan_state.lance_filter_sql = std::move(table_filter_sql);
} else if (table_filter_sql.empty()) {
scan_state.lance_filter_sql = bind_data.lance_complex_filter_sql;
scan_state.lance_filter_sql = std::move(pushed_filter_sql);
} else {
scan_state.lance_filter_sql = "(" + bind_data.lance_complex_filter_sql +
") AND (" + table_filter_sql + ")";
scan_state.lance_filter_sql =
"(" + pushed_filter_sql + ") AND (" + table_filter_sql + ")";
}
return state;
}
Expand Down
44 changes: 42 additions & 2 deletions test/sql/lance.test
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,7 +14,11 @@ SELECT 1
statement ok
SELECT * FROM lance_scan('test/test_data.lance') LIMIT 1

# Test parallel scan + filter pushdown
# Baseline: materialize once and evaluate filters in DuckDB
statement ok
CREATE TEMP TABLE baseline AS SELECT * FROM 'test/test_data.lance'

# Test parallel scan + filter pushdown correctness
statement ok
PRAGMA threads=4

Expand All @@ -33,7 +37,7 @@ SELECT count(*) FROM 'test/test_data.lance' WHERE age > 30 AND score < 90
----
2

# Test complex filter forms (OR across columns, NOT, BETWEEN, NOT IN)
# Test complex filter forms
query I
SELECT count(*) FROM 'test/test_data.lance' WHERE age > 30 OR score < 90
----
Expand Down Expand Up @@ -62,6 +66,42 @@ Charlie
David
Eve

# Equivalence: baseline table (DuckDB evaluation) matches expected results
query I
SELECT count(*) FROM baseline WHERE age > 30
----
3

query I
SELECT count(*) FROM baseline WHERE name IN ('Alice', 'Eve')
----
2

query I
SELECT count(*) FROM baseline WHERE age > 30 AND score < 90
----
2

query I
SELECT count(*) FROM baseline WHERE age > 30 OR score < 90
----
4

query I
SELECT count(*) FROM baseline WHERE NOT (age > 30)
----
2

query I
SELECT count(*) FROM baseline WHERE age BETWEEN 26 AND 40
----
3

query I
SELECT count(*) FROM baseline WHERE name NOT IN ('Alice', 'Eve')
----
3

# Test replacement scan for SELECT * FROM '.../dataset.lance'
statement ok
SELECT * FROM 'test/test_data.lance' LIMIT 1
Expand Down