Hypergraph is more powerful. Transform unstructured text into structured knowledge with LLMs. Graphs, hypergraphs, and spatio-temporal extractions — with one command.
test: cover batch merge with an empty first chunk
dex0shubham9eb414470931
diff --git a/tests/types/test_graph_dangling.py b/tests/types/test_graph_dangling.pyindex 164af64..c180c0f 100644--- a/tests/types/test_graph_dangling.py+++ b/tests/types/test_graph_dangling.py@@ -72,3 +72,34 @@ class TestAutoGraphMerge:])assert len(graph.nodes) == 1++ def test_merge_batch_data_empty_first_chunk(self, llm_client, embedder):+ """merge_batch_data tolerates a chunk that produced no nodes/edges.++ Previously the first sublist being empty raised IndexError via+ nodes_lists[0][0] / edges_lists[0][0].+ """+ graph = AutoGraph(+ node_schema=Entity,+ edge_schema=Relation,+ node_key_extractor=lambda x: x.name,+ edge_key_extractor=lambda x: f"{x.source}-{x.relation_type}-{x.target}",+ nodes_in_edge_extractor=lambda x: (x.source, x.target),+ llm_client=llm_client,+ embedder=embedder,+ )++ # First chunk produced nothing; the second carries the real data.+ nodes_lists = [+ [],+ [Entity(name="Apple", type="ORGANIZATION", properties={})],+ ]+ edges_lists = [+ [],+ [Relation(source="Apple", target="Steve", relation_type="founded_by")],+ ]++ result = graph.merge_batch_data((nodes_lists, edges_lists))++ assert {n.name for n in result.nodes} == {"Apple"}+ assert len(result.edges) == 1diff --git a/tests/types/test_hypergraph_merge.py b/tests/types/test_hypergraph_merge.pynew file mode 100644index 0000000..dce4343--- /dev/null+++ b/tests/types/test_hypergraph_merge.py@@ -0,0 +1,60 @@+"""Unit tests for AutoHypergraph batch merge."""++from typing import List++from pydantic import BaseModel, Field++from hyperextract.types import AutoHypergraph+++class Entity(BaseModel):+ """Simple node schema for testing."""++ name: str+ type: str+ properties: dict = Field(default_factory=dict)+++class HyperRelation(BaseModel):+ """Simple hyperedge schema for testing."""++ participants: List[str]+ relation_type: str+++class TestAutoHypergraphMerge:+ """Test cases for AutoHypergraph merge functionality."""++ def _make_graph(self, llm_client, embedder):+ return AutoHypergraph(+ node_schema=Entity,+ edge_schema=HyperRelation,+ node_key_extractor=lambda x: x.name,+ edge_key_extractor=lambda x: f"{x.relation_type}_{sorted(x.participants)}",+ nodes_in_edge_extractor=lambda x: tuple(x.participants),+ llm_client=llm_client,+ embedder=embedder,+ )++ def test_merge_batch_data_empty_first_chunk(self, llm_client, embedder):+ """merge_batch_data tolerates a chunk that produced no nodes/edges.++ Previously the first sublist being empty raised IndexError via+ nodes_lists[0][0] / edges_lists[0][0].+ """+ graph = self._make_graph(llm_client, embedder)++ # First chunk produced nothing; the second carries the real data.+ nodes_lists = [+ [],+ [Entity(name="Apple", type="ORGANIZATION", properties={})],+ ]+ edges_lists = [+ [],+ [HyperRelation(participants=["Apple", "Steve"], relation_type="founded_by")],+ ]++ result = graph.merge_batch_data((nodes_lists, edges_lists))++ assert {n.name for n in result.nodes} == {"Apple"}+ assert len(result.edges) == 1