Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
Python ai4sciencedocument-analysisdocxextract-datalayout-analysisocrparserpdfpdf-converterpdf-extractor-llmpdf-extractor-pretrainpdf-extractor-ragpdf-parserpptxpythonxlsx
test: allow instrumented PDF task completion
myhloli968ee71a6bfc
diff --git a/tests/unittest/test_pdf_page_id.py b/tests/unittest/test_pdf_page_id.pyindex 7fb671f1..b3a9ae4f 100644--- a/tests/unittest/test_pdf_page_id.py+++ b/tests/unittest/test_pdf_page_id.py@@ -280,7 +280,8 @@ def test_async_job_resolves_relative_ranges_and_reports_file_errors(tmp_path: Pafor item in created["files"]:upload = item["upload"]assert client.put(upload["url"], content=data, headers=upload["headers"]).status_code == 200- ready = wait_task(client, created)+ # 真实解析还包含产物打包,覆盖率插桩下沿用端到端用例的 20 秒等待预算。+ ready = wait_task(client, created, timeout=20)assert ready["status"] == "partial"succeeded, failed = app.state.task_store._records[created["task_id"]].file_statesassert succeeded.execution.page_range == "1,4-5"