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

tests/test_parse_opf.py

@@ -0,0 +1,75 @@
+"""Unit tests for EPUB structure parsing (no rendering involved)."""
+import pytest
+
+import app
+from tests.helpers import build_epub_tree
+
+
+def test_missing_container_xml_raises(tmp_path):
+    (tmp_path / "META-INF").mkdir()
+    with pytest.raises(ValueError, match="missing META-INF/container.xml"):
+        app.parse_opf(tmp_path)
+
+
+def test_container_xml_without_rootfile_raises(tmp_path):
+    (tmp_path / "META-INF").mkdir()
+    (tmp_path / "META-INF" / "container.xml").write_text(
+        '<?xml version="1.0"?><container version="1.0"><rootfiles/></container>',
+        encoding="utf-8",
+    )
+    with pytest.raises(ValueError, match="no rootfile"):
+        app.parse_opf(tmp_path)
+
+
+def test_parse_opf_returns_meta_spine_and_pdir_ltr(tmp_path):
+    build_epub_tree(tmp_path)
+    meta, opf_dir, spine, pdir = app.parse_opf(tmp_path)
+    assert meta["title"] == "Tree Book"
+    assert meta["creator"] == "Tree Author"
+    assert meta["language"] == "en"
+    assert str(opf_dir).endswith("OEBPS")
+    assert [i["href"] for i in spine] == ["chapter1.xhtml", "chapter2.xhtml"]  # img filtered out
+    assert pdir == "ltr"  # unset defaults to ltr
+
+
+def test_parse_opf_rtl_page_progression(tmp_path):
+    build_epub_tree(tmp_path, pdir="rtl")
+    _, _, _, pdir = app.parse_opf(tmp_path)
+    assert pdir == "rtl"
+
+
+def test_nonlinear_spine_items_are_skipped(tmp_path):
+    items = [
+        ("front", "front.xhtml", "application/xhtml+xml", ""),
+        ("ch1", "chapter1.xhtml", "application/xhtml+xml", ""),
+    ]
+    build_epub_tree(tmp_path, items=items, spine_ids=["ch1"])
+    # Add a non-linear itemref for 'front' via raw OPF edit
+    opf_path = tmp_path / "OEBPS" / "book.opf"
+    text = opf_path.read_text(encoding="utf-8")
+    text = text.replace(
+        '<spine><itemref idref="ch1"/></spine>',
+        '<spine><itemref idref="front" linear="no"/>'
+        '<itemref idref="ch1"/></spine>',
+    )
+    opf_path.write_text(text, encoding="utf-8")
+    _, _, spine, _ = app.parse_opf(tmp_path)
+    assert [i["href"] for i in spine] == ["chapter1.xhtml"]
+
+
+def test_empty_spine_falls_back_to_non_nav_html(tmp_path):
+    items = [
+        ("nav", "nav.xhtml", "application/xhtml+xml", "nav"),
+        ("ch1", "chapter1.xhtml", "application/xhtml+xml", ""),
+        ("img1", "img.png", "image/png", ""),
+    ]
+    build_epub_tree(tmp_path, items=items, spine_ids=[])  # spine refs: none
+    _, _, spine, _ = app.parse_opf(tmp_path)
+    assert [i["href"] for i in spine] == ["chapter1.xhtml"]  # nav + image excluded
+
+
+def test_no_readable_content_raises(tmp_path):
+    items = [("img1", "img.png", "image/png", "")]
+    build_epub_tree(tmp_path, items=items, spine_ids=["img1"])
+    with pytest.raises(ValueError, match="No readable content"):
+        app.parse_opf(tmp_path)