diff --git a/rust/lancedb/src/connection.rs b/rust/lancedb/src/connection.rs index 187e2df0e..5f66d9dee 100644 --- a/rust/lancedb/src/connection.rs +++ b/rust/lancedb/src/connection.rs @@ -1679,6 +1679,50 @@ mod tests { assert_eq!(tables, names[..7]); } + #[tokio::test] + async fn test_list_tables_walks_page_boundaries() { + let tc = new_test_connection().await.unwrap(); + if tc.is_remote { + // What resumes a page is the server's to decide, and asserting it here would be + // asserting the server's contract rather than this one. + return; + } + let db = tc.connection; + let schema = Arc::new(Schema::new(vec![Field::new("x", DataType::Int32, false)])); + let mut names = Vec::with_capacity(5); + for _ in 0..5 { + let name = uuid::Uuid::new_v4().to_string(); + names.push(name.clone()); + db.create_empty_table(name, schema.clone()) + .execute() + .await + .unwrap(); + } + names.sort(); + + // Walking in pages has to reach every table exactly once, with nothing lost at a + // page boundary. + let mut seen = Vec::with_capacity(names.len()); + let mut page_token = None; + loop { + let page = db + .list_tables(ListTablesRequest { + id: Some(Vec::new()), + limit: Some(2), + page_token, + ..Default::default() + }) + .await + .unwrap(); + seen.extend(page.tables); + page_token = page.page_token.filter(|token| !token.is_empty()); + if page_token.is_none() { + break; + } + } + assert_eq!(seen, names); + } + #[tokio::test] async fn test_open_table() { let tc = new_test_connection().await.unwrap(); diff --git a/rust/lancedb/src/database/listing.rs b/rust/lancedb/src/database/listing.rs index c9e9bcb22..17dc82756 100644 --- a/rust/lancedb/src/database/listing.rs +++ b/rust/lancedb/src/database/listing.rs @@ -974,17 +974,15 @@ impl Database for ListingDatabase { f.drain(0..index); } - // Determine if there's a next page - let next_page_token = if let Some(limit) = request.limit { - if f.len() > limit as usize { - let token = f[limit as usize].clone(); + // Determine if there's a next page. The token is the last name of this page, + // not the first of the next one: the next page resumes strictly after the + // token, so naming the next page's first entry would skip it. + let next_page_token = match request.limit { + Some(limit) if f.len() > limit as usize => { f.truncate(limit as usize); - Some(token) - } else { - None + f.last().cloned() } - } else { - None + _ => None, }; Ok(ListTablesResponse {