test(python): verify FTS build controls

python/Cargo.toml

@@ -26,7 +26,9 @@ lance-namespace-impls.workspace = true
 lance-io.workspace = true
 env_logger.workspace = true
 log.workspace = true
-pyo3 = { version = "0.28", features = ["extension-module", "abi3-py310", "chrono"] }
+# Maturin enables extension-module mode for Python builds. Keeping it out of
+# Cargo features lets Rust unit tests link against libpython.
+pyo3 = { version = "0.28", features = ["abi3-py310", "chrono"] }
 chrono = { version = "0.4", default-features = false, features = ["clock"] }
 pyo3-async-runtimes = { version = "0.28", features = [
     "attributes",
@@ -41,10 +43,7 @@ tokio = { version = "1.40", features = ["sync", "rt-multi-thread"] }
 libc = "0.2"
 
 [build-dependencies]
-pyo3-build-config = { version = "0.28", features = [
-    "extension-module",
-    "abi3-py310",
-] }
+pyo3-build-config = { version = "0.28", features = ["abi3-py310"] }
 
 [features]
 default = ["remote", "lancedb/aws", "lancedb/gcs", "lancedb/azure", "lancedb/dynamodb", "lancedb/oss", "lancedb/huggingface", "lancedb/cos", "lancedb/goosefs", "lancedb/metrics-otel"]

python/src/index.rs

@@ -452,3 +452,51 @@ impl IndexConfig {
         }
     }
 }
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use pyo3::types::{PyDict, PyDictMethods};
+    use serde_json::json;
+
+    #[test]
+    fn fts_build_controls_are_forwarded() {
+        Python::initialize();
+        Python::attach(|py| {
+            let locals = PyDict::new(py);
+            py.run(
+                c"class FTS:
+    with_position = True
+    base_tokenizer = 'simple'
+    language = 'English'
+    max_token_length = None
+    lower_case = True
+    stem = False
+    remove_stop_words = False
+    custom_stop_words = None
+    ascii_folding = False
+    ngram_min_length = 3
+    ngram_max_length = 3
+    prefix_only = False
+    block_size = 128
+    memory_limit = 2048
+    num_workers = 7
+
+config = FTS()",
+                None,
+                Some(&locals),
+            )
+            .unwrap();
+
+            let config = locals.get_item("config").unwrap().unwrap();
+            let index = extract_index_params(&Some(config)).unwrap();
+            let LanceDbIndex::FTS(params) = index else {
+                panic!("expected FTS index parameters");
+            };
+            let training_json = params.to_training_json().unwrap();
+
+            assert_eq!(training_json.get("memory_limit"), Some(&json!(2048)));
+            assert_eq!(training_json.get("num_workers"), Some(&json!(7)));
+        });
+    }
+}