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

tests/helpers.py

@@ -0,0 +1,141 @@
+"""Pure-function test helpers for the EPUB -> PDF converter suite.
+
+No pytest fixtures here: every function takes its dependencies explicitly so
+the helpers stay unit-testable and reusable.
+"""
+import io
+import time
+import zipfile
+
+from pypdf import PdfReader
+
+TERMINAL_STATUSES = ("done", "error")
+
+
+def wait_for_job(client, job_id, timeout=90.0):
+    """Poll GET /api/jobs/<job_id> until a terminal status; return snapshot."""
+    deadline = time.time() + timeout
+    last = None
+    while time.time() < deadline:
+        resp = client.get(f"/api/jobs/{job_id}")
+        assert resp.status_code == 200, f"job lookup failed: {resp.status_code}"
+        last = resp.get_json()
+        if last["status"] in TERMINAL_STATUSES:
+            return last
+        time.sleep(0.05)
+    raise TimeoutError(f"job {job_id} not terminal after {timeout}s: {last}")
+
+
+def download_bytes(client, filename):
+    """GET /download/<filename> and return the raw body (asserts 200)."""
+    resp = client.get(f"/download/{filename}")
+    assert resp.status_code == 200, (
+        f"download failed for {filename}: {resp.status_code}"
+    )
+    return resp.data
+
+
+def pdf_text(data_bytes):
+    """Extract all text from a PDF byte string (pypdf)."""
+    reader = PdfReader(io.BytesIO(data_bytes))
+    return "\n".join((page.extract_text() or "") for page in reader.pages)
+
+
+def pdf_page_count(data_bytes):
+    return len(PdfReader(io.BytesIO(data_bytes)).pages)
+
+
+def pdf_metadata_title(data_bytes):
+    reader = PdfReader(io.BytesIO(data_bytes))
+    meta = reader.metadata
+    return meta.get("/Title") if meta else None
+
+
+def make_zip_without_container():
+    """A valid zip that is not an EPUB (no META-INF/container.xml)."""
+    buf = io.BytesIO()
+    with zipfile.ZipFile(buf, "w") as zf:
+        zf.writestr("notes.txt", "hello, not an epub")
+    return buf.getvalue()
+
+
+_CONTAINER_XML = (
+    '<?xml version="1.0" encoding="utf-8"?>'
+    '<container version="1.0" xmlns="urn:oasis:names:tc:opendocument:xmlns:container">'
+    '<rootfiles><rootfile full-path="OEBPS/book.opf" '
+    'media-type="application/oebps-package+xml"/></rootfiles></container>'
+)
+
+
+def make_epub_zip(items, spine_ids, title="Synthetic", creator="Synth"):
+    """Build a minimal EPUB byte string from (id, href, media_type, props) items."""
+    manifest = "".join(
+        f'<item id="{i}" href="{h}" media-type="{m}"'
+        + (f' properties="{p}"' if p else "")
+        + "/>"
+        for i, h, m, p in items
+    )
+    refs = "".join(f'<itemref idref="{sid}"/>' for sid in spine_ids)
+    opf = (
+        '<?xml version="1.0" encoding="utf-8"?>'
+        '<package xmlns="http://www.idpf.org/2007/opf" version="3.0" '
+        'unique-identifier="uid">'
+        '<metadata xmlns:dc="http://purl.org/dc/elements/1.1/">'
+        f"<dc:title>{title}</dc:title><dc:creator>{creator}</dc:creator>"
+        "</metadata>"
+        f"<manifest>{manifest}</manifest>"
+        f"<spine>{refs}</spine>"
+        "</package>"
+    )
+    buf = io.BytesIO()
+    with zipfile.ZipFile(buf, "w") as zf:
+        zf.writestr("META-INF/container.xml", _CONTAINER_XML)
+        zf.writestr("OEBPS/book.opf", opf)
+    return buf.getvalue()
+
+
+def build_epub_tree(base, *, items=None, spine_ids=None, pdir=None):
+    """Materialize a minimal on-disk EPUB structure for parse_opf tests."""
+    items = items or [
+        ("ch1", "chapter1.xhtml", "application/xhtml+xml", ""),
+        ("ch2", "chapter2.xhtml", "application/xhtml+xml", ""),
+        ("img1", "img.png", "image/png", ""),
+    ]
+    spine_ids = (
+        list(spine_ids)
+        if spine_ids is not None
+        else [i for i, h, m, p in items if "html" in m]
+    )
+    pdir_attr = f' page-progression-direction="{pdir}"' if pdir else ""
+    manifest = "".join(
+        f'<item id="{i}" href="{h}" media-type="{m}"'
+        + (f' properties="{p}"' if p else "")
+        + "/>"
+        for i, h, m, p in items
+    )
+    refs = "".join(f'<itemref idref="{sid}"/>' for sid in spine_ids)
+    opf = (
+        '<?xml version="1.0" encoding="utf-8"?>'
+        f'<package xmlns="http://www.idpf.org/2007/opf" version="3.0" '
+        f'unique-identifier="uid"{pdir_attr}>'
+        '<metadata xmlns:dc="http://purl.org/dc/elements/1.1/">'
+        "<dc:title>Tree Book</dc:title>"
+        "<dc:creator>Tree Author</dc:creator>"
+        "<dc:language>en</dc:language>"
+        "</metadata>"
+        f"<manifest>{manifest}</manifest>"
+        f"<spine>{refs}</spine>"
+        "</package>"
+    )
+    (base / "META-INF").mkdir(parents=True, exist_ok=True)
+    (base / "META-INF" / "container.xml").write_text(_CONTAINER_XML, encoding="utf-8")
+    (base / "OEBPS").mkdir(parents=True, exist_ok=True)
+    (base / "OEBPS" / "book.opf").write_text(opf, encoding="utf-8")
+    for i, h, m, p in items:
+        if "html" in m:
+            (base / "OEBPS" / h).write_text(
+                '<?xml version="1.0" encoding="utf-8"?>'
+                "<html><body><p>chapter body</p></body></html>",
+                encoding="utf-8",
+            )
+    return base