mirror of
https://github.com/lancedb/lancedb.git
synced 2025-12-26 14:49:57 +00:00
fix(python): make sure explain_plan works with FTS queries (#2466)
## Summary Fixes issue #2465 where FTS explain plans only showed basic `LanceScan` instead of detailed execution plans with FTS query details, limits, and offsets. ## Root Cause The `FTSQuery::explain_plan()` and `analyze_plan()` methods were missing the `.full_text_search()` call before calling explain/analyze plan, causing them to operate on the base query without FTS context. ## Changes - **Fixed** `explain_plan()` and `analyze_plan()` in `src/query.rs` to call `.full_text_search()` - **Added comprehensive test coverage** for FTS explain plans with limits, offsets, and filters - **Updated existing tests** to expect correct behavior instead of buggy behavior ## Before/After **Before (broken):** ``` LanceScan: uri=..., projection=[...], row_id=false, row_addr=false, ordered=true ``` **After (fixed):** ``` ProjectionExec: expr=[id@2 as id, text@3 as text, _score@1 as _score] Take: columns="_rowid, _score, (id), (text)" CoalesceBatchesExec: target_batch_size=1024 GlobalLimitExec: skip=2, fetch=4 MatchQuery: query=test ``` ## Test Plan - [x] All new FTS explain plan tests pass - [x] Existing tests continue to pass - [x] FTS queries now show proper execution plans with MatchQuery, limits, filters Closes #2465 🤖 Generated with [Claude Code](https://claude.ai/code) <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit * **Tests** * Added new test cases to verify explain plan output for full-text search, vector queries with pagination, and queries with filters. * **Bug Fixes** * Improved the accuracy of explain plan and analysis output for full-text search queries, ensuring the correct query details are reflected. * **Refactor** * Enhanced the formatting and hierarchical structure of execution plans for hybrid queries, providing clearer and more detailed plan representations. <!-- end of auto-generated comment: release notes by coderabbit.ai --> --------- Co-authored-by: Claude <noreply@anthropic.com>
This commit is contained in:
@@ -775,6 +775,82 @@ async def test_explain_plan_async(table_async: AsyncTable):
|
||||
assert "KNN" in plan
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_explain_plan_fts(table_async: AsyncTable):
|
||||
"""Test explain plan for FTS queries"""
|
||||
# Create FTS index
|
||||
from lancedb.index import FTS
|
||||
|
||||
await table_async.create_index("text", config=FTS())
|
||||
|
||||
# Test pure FTS query
|
||||
query = await table_async.search("dog", query_type="fts", fts_columns="text")
|
||||
plan = await query.explain_plan()
|
||||
# Should show FTS details (issue #2465 is now fixed)
|
||||
assert "MatchQuery: query=dog" in plan
|
||||
assert "GlobalLimitExec" in plan # Default limit
|
||||
|
||||
# Test FTS query with limit
|
||||
query_with_limit = await table_async.search(
|
||||
"dog", query_type="fts", fts_columns="text"
|
||||
)
|
||||
plan_with_limit = await query_with_limit.limit(1).explain_plan()
|
||||
assert "MatchQuery: query=dog" in plan_with_limit
|
||||
assert "GlobalLimitExec: skip=0, fetch=1" in plan_with_limit
|
||||
|
||||
# Test FTS query with offset and limit
|
||||
query_with_offset = await table_async.search(
|
||||
"dog", query_type="fts", fts_columns="text"
|
||||
)
|
||||
plan_with_offset = await query_with_offset.offset(1).limit(1).explain_plan()
|
||||
assert "MatchQuery: query=dog" in plan_with_offset
|
||||
assert "GlobalLimitExec: skip=1, fetch=1" in plan_with_offset
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_explain_plan_vector_with_limit_offset(table_async: AsyncTable):
|
||||
"""Test explain plan for vector queries with limit and offset"""
|
||||
# Test vector query with limit
|
||||
plan_with_limit = await (
|
||||
table_async.query().nearest_to(pa.array([1, 2])).limit(1).explain_plan()
|
||||
)
|
||||
assert "KNN" in plan_with_limit
|
||||
assert "GlobalLimitExec: skip=0, fetch=1" in plan_with_limit
|
||||
|
||||
# Test vector query with offset and limit
|
||||
plan_with_offset = await (
|
||||
table_async.query()
|
||||
.nearest_to(pa.array([1, 2]))
|
||||
.offset(1)
|
||||
.limit(1)
|
||||
.explain_plan()
|
||||
)
|
||||
assert "KNN" in plan_with_offset
|
||||
assert "GlobalLimitExec: skip=1, fetch=1" in plan_with_offset
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_explain_plan_with_filters(table_async: AsyncTable):
|
||||
"""Test explain plan for queries with filters"""
|
||||
# Test vector query with filter
|
||||
plan_with_filter = await (
|
||||
table_async.query().nearest_to(pa.array([1, 2])).where("id = 1").explain_plan()
|
||||
)
|
||||
assert "KNN" in plan_with_filter
|
||||
assert "FilterExec" in plan_with_filter
|
||||
|
||||
# Test FTS query with filter
|
||||
from lancedb.index import FTS
|
||||
|
||||
await table_async.create_index("text", config=FTS())
|
||||
query_fts_filter = await table_async.search(
|
||||
"dog", query_type="fts", fts_columns="text"
|
||||
)
|
||||
plan_fts_filter = await query_fts_filter.where("id = 1").explain_plan()
|
||||
assert "MatchQuery: query=dog" in plan_fts_filter
|
||||
assert "FilterExec: id@" in plan_fts_filter # Should show filter details
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_query_camelcase_async(tmp_path):
|
||||
db = await lancedb.connect_async(tmp_path)
|
||||
|
||||
Reference in New Issue
Block a user