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: stabilize ZIP artifact fixture timestamps
myhlolid129c237fb8b
diff --git a/tests/unittest/test_file_parse.py b/tests/unittest/test_file_parse.pyindex 887a143f..b03a146f 100644--- a/tests/unittest/test_file_parse.py+++ b/tests/unittest/test_file_parse.py@@ -38,7 +38,9 @@ def artifact_bytes(formats: list[str]) -> bytes:return b"<!doctype html><html><body>file parse result</body></html>"output = io.BytesIO()with zipfile.ZipFile(output, "w") as archive:- archive.writestr("word/document.xml" if formats == ["docx"] else "markdown.md", "file parse result")+ name = "word/document.xml" if formats == ["docx"] else "markdown.md"+ # 固定 ZIP 时间戳,避免上游响应和预期附件跨两秒时间边界后产生不同字节。+ archive.writestr(zipfile.ZipInfo(name, date_time=(1980, 1, 1, 0, 0, 0)), "file parse result")return output.getvalue()