Skip to content

Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

feat: add upload size mismatch validation and error handling

myhloliec7b96333896
diff --git a/mineru/parser/api_server.py b/mineru/parser/api_server.py
index 077882e7..2cc9be05 100644
--- a/mineru/parser/api_server.py
+++ b/mineru/parser/api_server.py
@@ -769,6 +769,13 @@ class FileStore:
# compute sha256 from uploaded data if not provided
data = self._read_upload_data(upload_id)
+ if len(data) != rec.bytes:
+ _raise_api_error(
+ 413,
+ error_type="invalid_request_error",
+ code="upload_size_mismatch",
+ message=f"Upload expects {rec.bytes} bytes, received {len(data)}",
+ )
actual_sha = hashlib.sha256(data).hexdigest()
if sha256hex and sha256hex != actual_sha:
@@ -832,6 +839,13 @@ class FileStore:
code="upload_already_terminal",
message=f"Upload is {rec.status}",
)
+ if len(data) != rec.bytes:
+ _raise_api_error(
+ 413,
+ error_type="invalid_request_error",
+ code="upload_size_mismatch",
+ message=f"Upload expects {rec.bytes} bytes, received {len(data)}",
+ )
# store temporarily under upload_id in blobs dir
p = self._blobs / "_uploads" / upload_id
p.parent.mkdir(parents=True, exist_ok=True)
@@ -1509,7 +1523,6 @@ async def _run_job(
duration_ms=int((time.monotonic() - file_started) * 1000),
parser_version=__version__,
)
- fr.file_id = file_store.create_file_for_output(fr.name, data)
rec.progress.completed += 1
except Exception as exc:
@@ -1694,7 +1707,7 @@ async def get_upload(
"/uploads/{upload_id}/content",
response_model=None,
status_code=status.HTTP_200_OK,
- responses={**_ERR_404, **_ERR_409},
+ responses={**_ERR_404, **_ERR_409, **_ERR_413},
tags=["Uploads"],
)
async def upload_content(
@@ -1711,7 +1724,7 @@ async def upload_content(
"/uploads/{upload_id}/complete",
response_model=UploadResponse,
status_code=status.HTTP_200_OK,
- responses={**_ERR_400, **_ERR_404, **_ERR_409},
+ responses={**_ERR_400, **_ERR_404, **_ERR_409, **_ERR_413},
tags=["Uploads"],
)
async def complete_upload(
diff --git a/tests/unittest/test_parser_api_contract.py b/tests/unittest/test_parser_api_contract.py
index 3c106c6c..488f7bd9 100644
--- a/tests/unittest/test_parser_api_contract.py
+++ b/tests/unittest/test_parser_api_contract.py
@@ -30,6 +30,7 @@ from mineru.parser.api_client import MinerUApiParser, _pages_from_middle_json, _
from mineru.parser.api_server import (
_API_SERVER_LANGUAGES,
CreateJobRequest,
+ CreateUploadRequest,
FileParseInfo,
FileStore,
HealthResponse,
@@ -1978,6 +1979,86 @@ def test_api_server_run_job_normalizes_lightweight_file_tier_to_flash(
assert rec.files[0].status == "completed"
+def test_store_upload_data_rejects_declared_size_mismatch(tmp_path: Path) -> None:
+ """声明 bytes 与 PUT 实际大小不一致时在落盘前拒绝。"""
+ file_store = FileStore(tmp_path / "api-files")
+ upload = file_store.create_upload(
+ CreateUploadRequest.model_validate({"filename": "demo.pdf", "bytes": 4, "mime_type": "application/pdf"})
+ )
+
+ with pytest.raises(api_server.ApiServerError) as exc_info:
+ file_store.store_upload_data(upload.id, b"too-many-bytes")
+
+ assert exc_info.value.status_code == 413
+ assert exc_info.value.error.code == "upload_size_mismatch"
+ assert not (tmp_path / "api-files" / "blobs" / "_uploads" / upload.id).is_file()
+
+
+def test_complete_upload_rejects_size_mismatch(tmp_path: Path) -> None:
+ """complete 阶段复核实际大小,防止绕过 store_upload_data 的写入路径。"""
+ file_store = FileStore(tmp_path / "api-files")
+ upload = file_store.create_upload(
+ CreateUploadRequest.model_validate({"filename": "demo.pdf", "bytes": 4, "mime_type": "application/pdf"})
+ )
+ blob = file_store._blobs / "_uploads" / upload.id
+ blob.parent.mkdir(parents=True, exist_ok=True)
+ blob.write_bytes(b"0123456789")
+
+ with pytest.raises(api_server.ApiServerError) as exc_info:
+ file_store.complete_upload(upload.id, None)
+
+ assert exc_info.value.status_code == 413
+ assert exc_info.value.error.code == "upload_size_mismatch"
+
+
+def test_run_job_preserves_input_file_id_and_keeps_source_undownloadable(
+ monkeypatch: pytest.MonkeyPatch,
+ tmp_path: Path,
+) -> None:
+ """完成的 job 保留输入 file_id,不为源文件创建可下载的 parse_output 副本。"""
+
+ async def fake_parse_async(*args: object, **kwargs: object) -> ParseResult:
+ return ParseResult(middle_json=_full_middle_json(PageInfo(page_idx=0)))
+
+ monkeypatch.setattr("mineru.parser.api_server.parse_async", fake_parse_async)
+ file_store = FileStore(tmp_path / "api-files")
+ payload = b"%PDF-1.7 demo"
+ upload = file_store.create_upload(
+ CreateUploadRequest.model_validate({"filename": "demo.pdf", "bytes": len(payload), "mime_type": "application/pdf"})
+ )
+ file_store.store_upload_data(upload.id, payload)
+ completed = file_store.complete_upload(upload.id, None)
+ assert completed.file is not None
+ input_file_id = completed.file.id
+
+ request = CreateJobRequest.model_validate(
+ {
+ "files": [{"source": {"type": "file_id", "file_id": input_file_id}}],
+ "tier": "standard",
+ "output_formats": ["middle_json"],
+ }
+ )
+ rec = api_server.JobStore().create(request, file_store)
+
+ asyncio.run(
+ api_server._run_job(
+ rec,
+ request,
+ file_store,
+ image_analysis=True,
+ )
+ )
+
+ assert rec.files[0].status == "completed"
+ assert rec.files[0].file_id == input_file_id
+ output_files = file_store.list_files(after=None, limit=1000, order="asc", purpose="parse_output").data
+ assert input_file_id not in [item.id for item in output_files]
+ assert [item.filename for item in output_files] == ["demo.pdf.middle.json"]
+ with pytest.raises(api_server.ApiServerError) as exc_info:
+ file_store.read_file_data(input_file_id)
+ assert exc_info.value.status_code == 403
+
+
@pytest.mark.parametrize(("request_tier", "response_tier"), [("standard", "standard"), (None, "flash")])
def test_api_server_accepts_lightweight_job_without_requested_quality_runtime(
monkeypatch: pytest.MonkeyPatch,