Ali Zarinkolah
c9cf7b368b
Why: - Implements plan 001 Phase 3's upload orchestration. Changes: - ObjectStorage port and MinIO adapter, thread-offloaded per ADR-0017. - Tenant-scoped repositories for api_keys, source_files, ingestion_jobs. - upload_source_file implementing the two-transaction shape with (tenant_id, domain, content_sha256) idempotency. Impact: - This phase stores bytes only -- chunks_indexed is always 0 until Phase 4/5 add parsing/embedding.
59 lines
2.2 KiB
Python
59 lines
2.2 KiB
Python
import pytest
|
|
|
|
from src.application.files.errors import FileTooLargeError, InvalidUploadError
|
|
from src.application.files.validation import validate_and_hash_upload
|
|
from src.application.ingestion.errors import UnsupportedSourceTypeError
|
|
|
|
pytestmark = pytest.mark.unit
|
|
|
|
_DOCX_HEADER = b"PK\x03\x04" + b"\x00" * 20
|
|
_CSV_BYTES = b"name,value\nfirst,1\n"
|
|
|
|
|
|
def test_validate_and_hash_upload_accepts_matching_csv() -> None:
|
|
result = validate_and_hash_upload(filename="report.csv", data=_CSV_BYTES, max_size_bytes=1_000)
|
|
|
|
assert result.source_type == "csv"
|
|
assert result.content_type == "text/csv"
|
|
assert len(result.content_sha256) == 64
|
|
|
|
|
|
def test_validate_and_hash_upload_accepts_matching_docx() -> None:
|
|
result = validate_and_hash_upload(
|
|
filename="report.docx", data=_DOCX_HEADER, max_size_bytes=1_000
|
|
)
|
|
|
|
assert result.source_type == "docx"
|
|
|
|
|
|
def test_validate_and_hash_upload_rejects_doc_as_unsupported() -> None:
|
|
with pytest.raises(UnsupportedSourceTypeError):
|
|
validate_and_hash_upload(filename="legacy.doc", data=_CSV_BYTES, max_size_bytes=1_000)
|
|
|
|
|
|
def test_validate_and_hash_upload_rejects_unknown_extension() -> None:
|
|
with pytest.raises(UnsupportedSourceTypeError):
|
|
validate_and_hash_upload(filename="report.pdf", data=_CSV_BYTES, max_size_bytes=1_000)
|
|
|
|
|
|
def test_validate_and_hash_upload_rejects_empty_file() -> None:
|
|
with pytest.raises(InvalidUploadError):
|
|
validate_and_hash_upload(filename="report.csv", data=b"", max_size_bytes=1_000)
|
|
|
|
|
|
def test_validate_and_hash_upload_rejects_oversized_file() -> None:
|
|
with pytest.raises(FileTooLargeError):
|
|
validate_and_hash_upload(filename="report.csv", data=_CSV_BYTES, max_size_bytes=4)
|
|
|
|
|
|
def test_validate_and_hash_upload_rejects_spoofed_docx_extension() -> None:
|
|
"""Content is really CSV text, but the filename claims `.docx`."""
|
|
with pytest.raises(InvalidUploadError):
|
|
validate_and_hash_upload(filename="report.docx", data=_CSV_BYTES, max_size_bytes=1_000)
|
|
|
|
|
|
def test_validate_and_hash_upload_rejects_spoofed_csv_extension() -> None:
|
|
"""Content is really an OOXML zip, but the filename claims `.csv`."""
|
|
with pytest.raises(InvalidUploadError):
|
|
validate_and_hash_upload(filename="report.csv", data=_DOCX_HEADER, max_size_bytes=1_000)
|