rust/lancedb
1
0
Fork 0
mirror of https://github.com/lancedb/lancedb.git synced 2025-12-27 15:12:53 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: support to build FTS without positions (#1621)

Browse Source
This commit is contained in:
BubbleCal
2024-09-10 22:51:32 +08:00
committed by GitHub
parent a405847f9b
commit 2bde5401eb
11 changed files with 150 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files

41
python/python/tests/test_fts.py
View File

@@ -140,8 +140,11 @@ def test_create_index_with_stemming(tmp_path, table):
@pytest.mark.parametrize("use_tantivy", [True, False])
def test_create_inverted_index(table, use_tantivy):
table.create_fts_index("text", use_tantivy=use_tantivy)
@pytest.mark.parametrize("with_position", [True, False])
def test_create_inverted_index(table, use_tantivy, with_position):
if use_tantivy and not with_position:
pytest.skip("we don't support to build tantivy index without position")
table.create_fts_index("text", use_tantivy=use_tantivy, with_position=with_position)
def test_populate_index(tmp_path, table):
@@ -166,6 +169,40 @@ def test_search_fts(table, use_tantivy):
assert len(results) == 5
def test_search_fts_phrase_query(table):
table.create_fts_index("text", use_tantivy=False, with_position=False)
try:
phrase_results = table.search('"puppy runs"').limit(100).to_list()
assert False
except Exception:
pass
table.create_fts_index("text", use_tantivy=False, replace=True)
results = table.search("puppy").limit(100).to_list()
phrase_results = table.search('"puppy runs"').limit(100).to_list()
assert len(results) > len(phrase_results)
assert len(phrase_results) > 0
@pytest.mark.asyncio
async def test_search_fts_phrase_query_async(async_table):
async_table = await async_table
await async_table.create_index("text", config=FTS(with_position=False))
try:
phrase_results = (
await async_table.query().nearest_to_text("puppy runs").limit(100).to_list()
)
assert False
except Exception:
pass
await async_table.create_index("text", config=FTS())
results = await async_table.query().nearest_to_text("puppy").limit(100).to_list()
phrase_results = (
await async_table.query().nearest_to_text('"puppy runs"').limit(100).to_list()
)
assert len(results) > len(phrase_results)
assert len(phrase_results) > 0
def test_search_fts_specify_column(table):
table.create_fts_index("text", use_tantivy=False)
table.create_fts_index("text2", use_tantivy=False)