epub2pdf: title-based export names, .pdf download headers, security hardening (68 tests green)

tests/test_edge_cases.py

@@ -0,0 +1,101 @@
+"""Edge cases: bad uploads, size limits, unknown jobs, path traversal."""
+import io
+import zipfile
+
+import app
+from tests.helpers import make_epub_zip, make_zip_without_container, wait_for_job
+
+
+def test_wrong_extension_returns_400(client, fixture_epub_bytes):
+    files = {"file": (io.BytesIO(fixture_epub_bytes), "book.pdf")}
+    resp = client.post("/api/convert", data=files, content_type="multipart/form-data")
+    assert resp.status_code == 400
+    assert ".epub" in resp.get_json()["error"]
+
+
+def test_corrupt_zip_returns_202_then_job_error(client):
+    """Non-zip upload: accepted (202) but the job must end in error state."""
+    files = {"file": (io.BytesIO(b"this is not a zip at all"), "book.epub")}
+    resp = client.post("/api/convert", data=files, content_type="multipart/form-data")
+    assert resp.status_code == 202
+    job_id = resp.get_json()["job_id"]
+    job = wait_for_job(client, job_id)
+    assert job["status"] == "error"
+    assert "Not a valid EPUB" in job["error"]
+    # The failed upload must not linger on disk.
+    assert not (app.UPLOAD_DIR / f"{job_id}.epub").exists()
+
+
+def test_zip_without_container_xml_ends_in_job_error(client):
+    """Valid zip, not an EPUB: worker hits the missing-container.xml error."""
+    files = {
+        "file": (io.BytesIO(make_zip_without_container()), "book.epub"),
+    }
+    resp = client.post("/api/convert", data=files, content_type="multipart/form-data")
+    assert resp.status_code == 202
+    job = wait_for_job(client, resp.get_json()["job_id"])
+    assert job["status"] == "error", job
+    assert "container.xml" in job["error"]
+
+
+def test_epub_without_readable_content_ends_in_job_error(client):
+    """EPUB whose spine has no html items -> 'No readable content' error."""
+    content = make_epub_zip(
+        items=[("img1", "img.png", "image/png", "")],
+        spine_ids=["img1"],
+    )
+    files = {"file": (io.BytesIO(content), "empty.epub")}
+    resp = client.post("/api/convert", data=files, content_type="multipart/form-data")
+    assert resp.status_code == 202
+    job = wait_for_job(client, resp.get_json()["job_id"])
+    assert job["status"] == "error", job
+    assert "No readable content" in job["error"]
+
+
+def test_oversized_upload_returns_413_json(client, submit_epub, monkeypatch):
+    """Flask MAX_CONTENT_LENGTH path: 413 with a JSON error body."""
+    monkeypatch.setitem(app.app.config, "MAX_CONTENT_LENGTH", 1024)  # 1 KiB
+    resp = submit_epub(filename="book.epub")  # fixture is ~3.3 KB
+    assert resp.status_code == 413
+    body = resp.get_json()
+    assert body is not None, "413 body must be JSON, not the HTML error page"
+    assert "too large" in body["error"].lower()
+
+
+def test_app_side_size_check_returns_400(client, submit_epub, monkeypatch):
+    """app.py's own MAX_UPLOAD_MB check (distinct from Flask's 413)."""
+    monkeypatch.setattr(app, "MAX_UPLOAD_MB", 0)
+    monkeypatch.setitem(app.app.config, "MAX_CONTENT_LENGTH", 10**10)
+    resp = submit_epub(filename="book.epub")
+    assert resp.status_code == 400
+    assert "too large" in resp.get_json()["error"].lower()
+
+
+def test_unknown_job_returns_404(client):
+    resp = client.get("/api/jobs/doesnotexist12")
+    assert resp.status_code == 404
+    assert resp.get_json()["error"] == "unknown job"
+
+
+def test_download_unknown_file_returns_404(client):
+    assert client.get("/download/never-converted.pdf").status_code == 404
+
+
+def test_download_traversal_dotdot_returns_404(client):
+    """.. segments must be neutralized by Path(name).name, never resolve
+    outside OUTPUT_DIR."""
+    for name in ("../app.py", "../../etc/passwd", "..%2F..%2Fetc%2Fpasswd"):
+        resp = client.get(f"/download/{name}")
+        assert resp.status_code == 404, f"traversal not blocked for {name!r}"
+
+
+def test_download_traversal_cannot_read_app_source(client, monkeypatch, tmp_path):
+    """Prove the guard: even a file sitting next to OUTPUT_DIR is unreachable."""
+    secret = tmp_path / "secret.txt"
+    secret.write_text("top secret", encoding="utf-8")
+    # OUTPUT_DIR is DATA_DIR/output; the secret is one level up.
+    # Path('..').name == '' -> OUTPUT_DIR / '' -> OUTPUT_DIR itself (a dir)
+    # -> is_file() False -> 404 regardless.
+    resp = client.get("/download/..%2Fsecret.txt")
+    assert resp.status_code == 404
+    assert b"top secret" not in resp.data