test: address PR review feedback for sparse vector tests

- Add SPECIAL_FIELDS validation test

- Add custom_mapping injection test

- Add legacy from_dict backward compat test

- Fix async test to use async_client for index deletion

- Add retrieval reconstruction assertions to sync and async sparse tests

Author: GunaPalanivel

integrations/elasticsearch/tests/test_document_store.py

@@ -24,6 +24,18 @@ def test_init_is_lazy(_mock_es_client):
     _mock_es_client.assert_not_called()
 
 
+def test_init_with_special_fields_raises_error():
+    with pytest.raises(ValueError, match=r"sparse_vector_field 'content' conflicts with a reserved field name\."):
+        ElasticsearchDocumentStore(sparse_vector_field="content")
+
+
+def test_init_with_custom_mapping_injects_sparse_vector():
+    custom_mapping = {"properties": {"some_field": {"type": "text"}}}
+    store = ElasticsearchDocumentStore(custom_mapping=custom_mapping, sparse_vector_field="my_sparse_vec")
+    assert "my_sparse_vec" in store._custom_mapping["properties"]
+    assert store._custom_mapping["properties"]["my_sparse_vec"] == {"type": "sparse_vector"}
+
+
 @patch("haystack_integrations.document_stores.elasticsearch.document_store.Elasticsearch")
 def test_headers_are_supported(_mock_es_client):
     _ = ElasticsearchDocumentStore(
@@ -159,6 +171,23 @@ def test_from_dict_with_api_keys_str():
     assert document_store._api_key_id == "my_api_key_id"
 
 
+def test_from_dict_without_sparse_vector_field():
+    data = {
+        "type": "haystack_integrations.document_stores.elasticsearch.document_store.ElasticsearchDocumentStore",
+        "init_parameters": {
+            "hosts": "some hosts",
+            "custom_mapping": None,
+            "index": "default",
+            "api_key": "my_api_key",
+            "api_key_id": "my_api_key_id",
+            "embedding_similarity_function": "cosine",
+        },
+    }
+
+    document_store = ElasticsearchDocumentStore.from_dict(data)
+    assert document_store._sparse_vector_field is None
+
+
 def test_api_key_validation_only_api_key():
     api_key = Secret.from_token("test_api_key")
     document_store = ElasticsearchDocumentStore(hosts="https://localhost:9200", api_key=api_key)
@@ -306,6 +335,13 @@ def test_write_documents_with_sparse_vectors(self):
         raw_doc = store.client.get(index="test_sync_sparse", id="1")
         assert raw_doc["_source"]["sparse_vec"] == {"0": 0.5, "1": 0.5}
 
+        # check retrieval reconstruction
+        results = store.filter_documents()
+        assert len(results) == 1
+        assert results[0].sparse_embedding is not None
+        assert results[0].sparse_embedding.indices == [0, 1]
+        assert results[0].sparse_embedding.values == [0.5, 0.5]
+
         store.client.indices.delete(index="test_sync_sparse")
 
     def test_write_documents_with_sparse_embedding_warning(self, document_store, caplog):

integrations/elasticsearch/tests/test_document_store_async.py

@@ -165,7 +165,7 @@ async def test_write_documents_async_with_sparse_vectors(self):
         store = ElasticsearchDocumentStore(
             hosts=["http://localhost:9200"], index="test_async_sparse", sparse_vector_field="sparse_vec"
         )
-        store.client.options(ignore_status=[400, 404]).indices.delete(index="test_async_sparse")
+        await store.async_client.options(ignore_status=[400, 404]).indices.delete(index="test_async_sparse")
 
         doc = Document(id="1", content="test", sparse_embedding=SparseEmbedding(indices=[0, 1], values=[0.5, 0.5]))
         await store.write_documents_async([doc])
@@ -174,7 +174,14 @@ async def test_write_documents_async_with_sparse_vectors(self):
         raw_doc = await store.async_client.get(index="test_async_sparse", id="1")
         assert raw_doc["_source"]["sparse_vec"] == {"0": 0.5, "1": 0.5}
 
-        store.client.indices.delete(index="test_async_sparse")
+        # check retrieval
+        results = await store.filter_documents_async()
+        assert len(results) == 1
+        assert results[0].sparse_embedding is not None
+        assert results[0].sparse_embedding.indices == [0, 1]
+        assert results[0].sparse_embedding.values == [0.5, 0.5]
+
+        await store.async_client.indices.delete(index="test_async_sparse")
 
     @pytest.mark.asyncio
     async def test_delete_all_documents_async(self, document_store):