diff --git a/tests/unit/test_decoding/test_pdf_decoder.py b/tests/unit/test_decoding/test_pdf_decoder.py index 1b6e219f..a3ca3514 100644 --- a/tests/unit/test_decoding/test_pdf_decoder.py +++ b/tests/unit/test_decoding/test_pdf_decoder.py @@ -171,7 +171,9 @@ class TestPdfDecoderProcessor(IsolatedAsyncioTestCase): mock_output_flow.send.assert_called_once() call_args = mock_output_flow.send.call_args[0][0] - assert call_args.text == "Page with unicode: 你好世界 🌍".encode('utf-8') + # PDF decoder now forwards document_id, chunker fetches content from librarian + assert call_args.document_id == "test-doc/p1" + assert call_args.text == b"" # Content stored in librarian, not inline @patch('trustgraph.base.flow_processor.FlowProcessor.add_args') def test_add_args(self, mock_parent_add_args):