rust/lancedb
1
0
Fork 0
mirror of https://github.com/lancedb/lancedb.git synced 2026-01-07 04:12:59 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: list_indices can handle fts indexes (#1753)

Browse Source 
Fixes #1752
This commit is contained in:
Will Jones
2024-10-16 10:39:40 -07:00
committed by GitHub
parent f43cb8bba1
commit 46486d4d22
2 changed files with 47 additions and 27 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
rust/lancedb/src/index.rs
View File

@@ -144,7 +144,7 @@ impl std::str::FromStr for IndexType {
"BTREE" => Ok(Self::BTree),
"BITMAP" => Ok(Self::Bitmap),
"LABEL_LIST" | "LABELLIST" => Ok(Self::LabelList),
"FTS" => Ok(Self::FTS),
"FTS" | "INVERTED" => Ok(Self::FTS),
"IVF_PQ" => Ok(Self::IvfPq),
"IVF_HNSW_PQ" => Ok(Self::IvfHnswPq),
"IVF_HNSW_SQ" => Ok(Self::IvfHnswSq),

72
rust/lancedb/src/table.rs
View File

@@ -2110,7 +2110,6 @@ mod tests {
use arrow_schema::{DataType, Field, Schema, TimeUnit};
use futures::TryStreamExt;
use lance::dataset::{Dataset, WriteMode};
use lance::index::DatasetIndexInternalExt;
use lance::io::{ObjectStoreParams, WrappingObjectStore};
use rand::Rng;
use tempfile::tempdir;
@@ -3002,22 +3001,8 @@ mod tests {
let index_configs = table.list_indices().await.unwrap();
assert_eq!(index_configs.len(), 1);
let index = index_configs.into_iter().next().unwrap();
// TODO: Fix via https://github.com/lancedb/lance/issues/2039
// assert_eq!(index.index_type, crate::index::IndexType::Bitmap);
assert_eq!(index.index_type, crate::index::IndexType::Bitmap);
assert_eq!(index.columns, vec!["category".to_string()]);
// For now, just open the index to verify its type
let lance_dataset = table.as_native().unwrap().dataset.get().await.unwrap();
let indices = lance_dataset
.load_indices_by_name(&index.name)
.await
.unwrap();
let index_meta = &indices[0];
let idx = lance_dataset
.open_scalar_index("category", &index_meta.uuid.to_string())
.await
.unwrap();
assert_eq!(idx.index_type(), IndexType::Bitmap);
}
#[tokio::test]
@@ -3086,22 +3071,57 @@ mod tests {
let index_configs = table.list_indices().await.unwrap();
assert_eq!(index_configs.len(), 1);
let index = index_configs.into_iter().next().unwrap();
// TODO: Fix via https://github.com/lancedb/lance/issues/2039
// assert_eq!(index.index_type, crate::index::IndexType::LabelList);
assert_eq!(index.index_type, crate::index::IndexType::LabelList);
assert_eq!(index.columns, vec!["tags".to_string()]);
}
// For now, just open the index to verify its type
let lance_dataset = table.as_native().unwrap().dataset.get().await.unwrap();
let indices = lance_dataset
.load_indices_by_name(&index.name)
#[tokio::test]
async fn test_create_inverted_index() {
let tmp_dir = tempdir().unwrap();
let uri = tmp_dir.path().to_str().unwrap();
let conn = ConnectBuilder::new(uri).execute().await.unwrap();
const WORDS: [&str; 3] = ["cat", "dog", "fish"];
let mut text_builder = StringBuilder::new();
let num_rows = 120;
for i in 0..num_rows {
text_builder.append_value(WORDS[i % 3]);
}
let text = Arc::new(text_builder.finish());
let schema = Arc::new(Schema::new(vec![
Field::new("id", DataType::Int32, false),
Field::new("text", DataType::Utf8, true),
]));
let batch = RecordBatch::try_new(
schema.clone(),
vec![
Arc::new(Int32Array::from_iter_values(0..num_rows as i32)),
text,
],
)
.unwrap();
let table = conn
.create_table(
"test_bitmap",
RecordBatchIterator::new(vec![Ok(batch.clone())], batch.schema()),
)
.execute()
.await
.unwrap();
let index_meta = &indices[0];
let idx = lance_dataset
.open_scalar_index("tags", &index_meta.uuid.to_string())
table
.create_index(&["text"], Index::FTS(Default::default()))
.execute()
.await
.unwrap();
assert_eq!(idx.index_type(), IndexType::LabelList);
let index_configs = table.list_indices().await.unwrap();
assert_eq!(index_configs.len(), 1);
let index = index_configs.into_iter().next().unwrap();
assert_eq!(index.index_type, crate::index::IndexType::FTS);
assert_eq!(index.columns, vec!["text".to_string()]);
assert_eq!(index.name, "text_idx");
}
#[tokio::test]