diff --git a/rust/lancedb/src/database/listing.rs b/rust/lancedb/src/database/listing.rs index a4624112e..0ab3614e7 100644 --- a/rust/lancedb/src/database/listing.rs +++ b/rust/lancedb/src/database/listing.rs @@ -1294,9 +1294,11 @@ mod tests { use crate::connection::ConnectRequest; use crate::data::scannable::Scannable; use crate::database::{CreateTableMode, CreateTableRequest}; - use crate::table::WriteOptions; + use crate::query::QueryRequest; + use crate::table::{AnyQuery, WriteOptions}; use arrow_array::{Int32Array, RecordBatch, StringArray}; use arrow_schema::{DataType, Field, Schema}; + use futures::TryStreamExt; use std::path::PathBuf; use tempfile::tempdir; @@ -1438,6 +1440,94 @@ mod tests { assert!(after_open.hits >= before_open.hits + 3); } + /// Regression test for https://github.com/lancedb/lancedb/issues/3197. + #[cfg(unix)] + #[tokio::test] + async fn test_open_table_follows_hugging_face_symlinks() { + let (tempdir, db) = setup_database().await; + let schema = Arc::new(Schema::new(vec![Field::new("id", DataType::Int32, false)])); + db.create_table(CreateTableRequest { + name: "test".to_string(), + namespace_path: vec![], + data: Box::new( + RecordBatch::try_new(schema, vec![Arc::new(Int32Array::from(vec![1, 2, 3]))]) + .unwrap(), + ) as Box, + mode: CreateTableMode::Create, + write_options: Default::default(), + location: None, + namespace_client: None, + }) + .await + .unwrap(); + + let table_dir = tempdir.path().join("test.lance"); + let versions_dir = table_dir.join("_versions"); + let manifest_path = std::fs::read_dir(&versions_dir) + .unwrap() + .map(|entry| entry.unwrap().path()) + .find(|path| path.extension().is_some_and(|ext| ext == "manifest")) + .unwrap(); + let data_path = std::fs::read_dir(table_dir.join("data")) + .unwrap() + .map(|entry| entry.unwrap().path()) + .find(|path| path.extension().is_some_and(|ext| ext == "lance")) + .unwrap(); + + // Hugging Face snapshots keep dataset objects in a separate blob directory and + // expose them through relative symlinks. + let blobs_dir = tempdir.path().join("blobs"); + std::fs::create_dir(&blobs_dir).unwrap(); + let manifest_blob = "9b603c63d0e692e05d58be25605f2f2064cc781e5ff94fe983a405059547b816"; + let data_blob = "be64f20e5723bd0a27cfdbdb41cf7d6fad94cd572a71973b717fb8340f4310c5"; + std::fs::rename(&manifest_path, blobs_dir.join(manifest_blob)).unwrap(); + std::fs::rename(&data_path, blobs_dir.join(data_blob)).unwrap(); + std::os::unix::fs::symlink(Path::new("../../blobs").join(manifest_blob), &manifest_path) + .unwrap(); + std::os::unix::fs::symlink(Path::new("../../blobs").join(data_blob), &data_path).unwrap(); + let symlink_len = std::fs::symlink_metadata(&manifest_path).unwrap().len(); + let target_len = std::fs::metadata(&manifest_path).unwrap().len(); + assert_ne!(symlink_len, target_len); + + drop(db); + let db = ListingDatabase::connect_with_options(&ConnectRequest { + uri: tempdir.path().to_str().unwrap().to_string(), + #[cfg(feature = "remote")] + client_config: Default::default(), + options: Default::default(), + namespace_client_properties: Default::default(), + manifest_enabled: false, + read_consistency_interval: None, + session: None, + }) + .await + .unwrap(); + + let table = db + .open_table(OpenTableRequest { + name: "test".to_string(), + namespace_path: vec![], + index_cache_size: None, + lance_read_params: None, + location: None, + namespace_client: None, + managed_versioning: None, + }) + .await + .unwrap(); + let batches = table + .query( + &AnyQuery::Query(QueryRequest::default()), + Default::default(), + ) + .await + .unwrap() + .try_collect::>() + .await + .unwrap(); + assert_eq!(batches.iter().map(RecordBatch::num_rows).sum::(), 3); + } + #[tokio::test] async fn test_clone_table_basic() { let (_tempdir, db) = setup_database().await;