71 lines
2.3 KiB
Python
71 lines
2.3 KiB
Python
from __future__ import annotations
|
|
|
|
from pathlib import Path
|
|
from types import SimpleNamespace
|
|
|
|
import pytest
|
|
|
|
from deerflow.utils import file_conversion
|
|
|
|
|
|
@pytest.fixture(autouse=True)
|
|
def local_parser(monkeypatch):
|
|
# Parser-selection unit tests inject readers locally. Production always
|
|
# sends this same top-level parser entry point to spawned worker processes.
|
|
monkeypatch.setattr(
|
|
file_conversion,
|
|
"_run_conversion_in_process",
|
|
lambda path, converter: file_conversion._convert_document_worker(str(path), converter),
|
|
)
|
|
|
|
|
|
def test_legacy_word_is_normalized_before_markitdown(monkeypatch, tmp_path: Path) -> None:
|
|
source = tmp_path / "legacy.doc"
|
|
source.write_bytes(b"legacy")
|
|
|
|
monkeypatch.setattr(file_conversion.shutil, "which", lambda _name: "/usr/bin/soffice")
|
|
monkeypatch.setattr(
|
|
file_conversion,
|
|
"_convert_with_markitdown",
|
|
lambda path: f"converted:{path.suffix}",
|
|
)
|
|
|
|
def fake_run(command, **_kwargs):
|
|
output_dir = Path(command[command.index("--outdir") + 1])
|
|
(output_dir / "legacy.docx").write_bytes(b"normalized")
|
|
return SimpleNamespace(returncode=0, stderr="")
|
|
|
|
monkeypatch.setattr(file_conversion.subprocess, "run", fake_run)
|
|
|
|
assert file_conversion._do_convert(source, "auto") == "converted:.docx"
|
|
|
|
|
|
def test_modern_office_file_does_not_start_libreoffice(monkeypatch, tmp_path: Path) -> None:
|
|
source = tmp_path / "modern.pptx"
|
|
source.write_bytes(b"modern")
|
|
monkeypatch.setattr(
|
|
file_conversion,
|
|
"_convert_with_markitdown",
|
|
lambda path: f"direct:{path.suffix}",
|
|
)
|
|
monkeypatch.setattr(
|
|
file_conversion.subprocess,
|
|
"run",
|
|
lambda *_args, **_kwargs: (_ for _ in ()).throw(AssertionError("unexpected LibreOffice call")),
|
|
)
|
|
|
|
assert file_conversion._do_convert(source, "auto") == "direct:.pptx"
|
|
|
|
|
|
def test_legacy_office_falls_back_when_libreoffice_is_missing(monkeypatch, tmp_path: Path) -> None:
|
|
source = tmp_path / "legacy.xls"
|
|
source.write_bytes(b"legacy")
|
|
monkeypatch.setattr(file_conversion.shutil, "which", lambda _name: None)
|
|
monkeypatch.setattr(
|
|
file_conversion,
|
|
"_convert_with_markitdown",
|
|
lambda path: f"fallback:{path.suffix}",
|
|
)
|
|
|
|
assert file_conversion._do_convert(source, "auto") == "fallback:.xls"
|