feat: implement Stage 5 (Interactive Reader, EPUB/TXT parser, Bookshelf, Click-to-Translate) and Stage 4.3 (Strict CEFR level calculation)

tests/test_api.py

@@ -503,4 +503,290 @@ def test_change_password_flow():
     assert new_auth["username"] == "pwd_user"
 
 
+# ---------------------------------------------------------------------------
+# Stage 5: Bookshelf & Interactive Reader Tests
+# ---------------------------------------------------------------------------
+
+def make_mock_epub(title="The Time Machine", author="H. G. Wells", chapters=None):
+    import io, zipfile
+    if chapters is None:
+        chapters = [
+            ("Chapter 1: The Machine", "<p>The Time Traveller was expounding a recondite matter to us.</p>"),
+            ("Chapter 2: The Journey", "<p>I seemed to see the clock hands spin around.</p>")
+        ]
+    buf = io.BytesIO()
+    with zipfile.ZipFile(buf, "w") as z:
+        z.writestr("META-INF/container.xml", """<?xml version="1.0"?>
+<container version="1.0" xmlns="urn:oasis:names:tc:opendocument:xmlns:container">
+    <rootfiles>
+        <rootfile full-path="OEBPS/content.opf" media-type="application/oebps-package+xml"/>
+    </rootfiles>
+</container>""")
+        manifest_items = []
+        spine_items = []
+        for i, (ch_title, ch_body) in enumerate(chapters, 1):
+            manifest_items.append(f'<item id="c{i}" href="ch{i}.xhtml" media-type="application/xhtml+xml"/>')
+            spine_items.append(f'<itemref idref="c{i}"/>')
+            z.writestr(f"OEBPS/ch{i}.xhtml", f"""<!DOCTYPE html>
+<html>
+<head><title>{ch_title}</title></head>
+<body>
+<h1>{ch_title}</h1>
+{ch_body}
+</body>
+</html>""")
+
+        opf = f"""<?xml version="1.0" encoding="utf-8"?>
+<package xmlns="http://www.idpf.org/2007/opf" version="3.0" unique-identifier="id">
+  <metadata xmlns:dc="http://purl.org/dc/elements/1.1/">
+    <dc:title>{title}</dc:title>
+    <dc:creator>{author}</dc:creator>
+  </metadata>
+  <manifest>
+    {''.join(manifest_items)}
+  </manifest>
+  <spine>
+    {''.join(spine_items)}
+  </spine>
+</package>"""
+        z.writestr("OEBPS/content.opf", opf)
+    return buf.getvalue()
+
+
+def test_reader_unit():
+    from app.reader import count_words, parse_text, parse_epub
+
+    # 1. count_words
+    assert count_words("") == 0
+    assert count_words("   \n\t  ") == 0
+    assert count_words("Hello world!") == 2
+    assert count_words("Привет, мир! Это тест.") == 4
+    assert count_words("Don't stop believing") == 3
+
+    # 2. parse_text with Markdown headers
+    md_content = """# My Book
+Author: Arthur Dent
+
+## Chapter 1: Hitchhiker
+Far out in the uncharted backwaters.
+
+## Chapter 2: The Towel
+A towel is about the most useful thing.
+"""
+    t, a, chs = parse_text(md_content)
+    assert t == "My Book"
+    assert a == "Arthur Dent"
+    assert len(chs) == 2
+    assert "Chapter 1: Hitchhiker" in chs[0]["title"]
+    assert "Far out" in chs[0]["content"]
+
+    # 3. parse_text with Chapter X headings
+    txt_content = """Chapter 1. The Boy Who Lived
+Mr. and Mrs. Dursley of number four Privet Drive.
+
+Chapter 2 - The Vanishing Glass
+Nearly ten years had passed.
+"""
+    t, a, chs = parse_text(txt_content, title="Harry Potter", author="J.K. Rowling")
+    assert t == "Harry Potter"
+    assert a == "J.K. Rowling"
+    assert len(chs) == 2
+    assert "Chapter 1" in chs[0]["title"]
+    assert "Chapter 2" in chs[1]["title"]
+
+    # 4. parse_text chunking on long text
+    long_words = ["word"] * 7000
+    long_text = "\n\n".join([" ".join(long_words[i:i + 400]) for i in range(0, len(long_words), 400)])
+    t, a, chs = parse_text(long_text, title="Long Essay")
+    assert t == "Long Essay"
+    assert len(chs) >= 2
+
+    # 5. parse_epub
+    epub_bytes = make_mock_epub("Brave New World", "Aldous Huxley")
+    t, a, chs = parse_epub(epub_bytes)
+    assert t == "Brave New World"
+    assert a == "Aldous Huxley"
+    assert len(chs) == 2
+    assert "Chapter 1: The Machine" in chs[0]["title"]
+    assert "Time Traveller" in chs[0]["content"]
+
+    # 6. parse_epub invalid archive error
+    with pytest.raises(ValueError):
+        parse_epub(b"not a zip file")
+
+
+def test_books_unauthenticated_blocked():
+    unauth = TestClient(app)
+    resp = unauth.get("/api/books")
+    assert resp.status_code == 401
+
+    resp = unauth.post("/api/books", json={"title": "Test", "content": "Text"})
+    assert resp.status_code == 401
+
+    resp = unauth.get("/api/books/1")
+    assert resp.status_code == 401
+
+    resp = unauth.put("/api/books/1/progress", json={"current_chapter": 1, "current_position": 0.5})
+    assert resp.status_code == 401
+
+    resp = unauth.delete("/api/books/1")
+    assert resp.status_code == 401
+
+
+def test_books_crud_workflow():
+    # Login as admin
+    client.post("/api/login", json={"username": "testadmin", "password": "testpass12345"})
+
+    # 1. Create book via JSON
+    payload = {
+        "title": "Fight Club",
+        "author": "Chuck Palahniuk",
+        "content": "Chapter 1\nTyler gets me a job.\n\nChapter 2\nA guy had come to the club.",
+        "source_type": "text"
+    }
+    resp = client.post("/api/books", json=payload)
+    assert resp.status_code == 200
+    book = resp.json()
+    assert book["id"] > 0
+    book_id = book["id"]
+    assert book["title"] == "Fight Club"
+    assert book["author"] == "Chuck Palahniuk"
+    assert book["source_type"] == "text"
+    assert book["chapters_count"] == 2
+    assert book["total_words"] > 0
+    assert book["current_chapter"] == 0
+    assert book["current_position"] == 0.0
+
+    # 2. List books (ensure chapters_json is excluded from list)
+    resp = client.get("/api/books")
+    assert resp.status_code == 200
+    books = resp.json()
+    assert isinstance(books, list)
+    target = next((b for b in books if b["id"] == book_id), None)
+    assert target is not None
+    assert target["title"] == "Fight Club"
+    assert target["chapters_count"] == 2
+    assert "chapters_json" not in target
+
+    # 3. Get single book (includes chapters_json and chapters)
+    resp = client.get(f"/api/books/{book_id}")
+    assert resp.status_code == 200
+    detail = resp.json()
+    assert detail["id"] == book_id
+    assert "chapters_json" in detail
+    assert "chapters" in detail
+    assert len(detail["chapters"]) == 2
+    assert "Chapter 1" in detail["chapters"][0]["title"]
+
+    # 4. Update reading progress
+    resp = client.put(f"/api/books/{book_id}/progress", json={
+        "current_chapter": 1,
+        "current_position": 0.75
+    })
+    assert resp.status_code == 200
+    updated = resp.json()
+    assert updated["current_chapter"] == 1
+    assert updated["current_position"] == 0.75
+
+    # 5. Delete book
+    resp = client.delete(f"/api/books/{book_id}")
+    assert resp.status_code == 200
+    assert resp.json()["status"] == "ok"
+    assert resp.json()["deleted_id"] == book_id
+
+    # 6. Verify deleted (404)
+    resp = client.get(f"/api/books/{book_id}")
+    assert resp.status_code == 404
+
+
+def test_books_multipart_file_uploads():
+    # Login
+    client.post("/api/login", json={"username": "testadmin", "password": "testpass12345"})
+
+    # 1. Upload TXT file
+    txt_data = b"Chapter 1: The Start\nOnce upon a time in a distant land.\n\nChapter 2: The End\nThey lived happily ever after."
+    resp = client.post(
+        "/api/books",
+        files={"file": ("fairytale.txt", txt_data, "text/plain")},
+        data={"title": "Fairy Tale", "author": "Brothers Grimm"}
+    )
+    assert resp.status_code == 200
+    book_txt = resp.json()
+    assert book_txt["title"] == "Fairy Tale"
+    assert book_txt["author"] == "Brothers Grimm"
+    assert book_txt["source_type"] == "txt"
+    assert book_txt["chapters_count"] == 2
+
+    # 2. Upload Markdown file
+    md_data = b"# The Cyberpunk Guide\nBy: Anonymous\n\n## Section 1\nWelcome to the matrix.\n\n## Section 2\nJack into cyberspace."
+    resp = client.post(
+        "/api/books",
+        files={"file": ("cyberpunk.md", md_data, "text/markdown")},
+    )
+    assert resp.status_code == 200
+    book_md = resp.json()
+    assert book_md["title"] == "The Cyberpunk Guide"
+    assert book_md["author"] == "Anonymous"
+    assert book_md["source_type"] == "md"
+    assert book_md["chapters_count"] == 2
+
+    # 3. Upload EPUB file
+    epub_bytes = make_mock_epub("The Invisible Man", "H. G. Wells")
+    resp = client.post(
+        "/api/books",
+        files={"file": ("invisible_man.epub", epub_bytes, "application/epub+zip")},
+    )
+    assert resp.status_code == 200
+    book_epub = resp.json()
+    assert book_epub["title"] == "The Invisible Man"
+    assert book_epub["author"] == "H. G. Wells"
+    assert book_epub["source_type"] == "epub"
+    assert book_epub["chapters_count"] == 2
+
+
+def test_srs_queue_and_quiz_tag_filtering():
+    # Login
+    client.post("/api/login", json={"username": "testadmin", "password": "testpass12345"})
+
+    # Create distinct tagged cards for book-scoped testing
+    c1 = client.post("/api/cards", json={
+        "term": "recondite",
+        "translation": "малопонятный, глубокий",
+        "tags": "book:time-machine, scifi",
+        "collection": "Literature"
+    }).json()
+
+    c2 = client.post("/api/cards", json={
+        "term": "invisible",
+        "translation": "невидимый",
+        "tags": "book:invisible-man, scifi",
+        "collection": "Literature"
+    }).json()
+
+    c3 = client.post("/api/cards", json={
+        "term": "soap",
+        "translation": "мыло",
+        "tags": "book:fight-club",
+        "collection": "Fiction"
+    }).json()
+
+    # 1. Filter queue by tag
+    resp = client.get("/api/srs/queue?tag=book:time-machine")
+    assert resp.status_code == 200
+    queue_cards = resp.json()["cards"]
+    card_ids = [c["id"] for c in queue_cards]
+    assert c1["id"] in card_ids
+    assert c2["id"] not in card_ids
+    assert c3["id"] not in card_ids
+
+    # 2. Filter quiz by tag
+    resp = client.get("/api/srs/quiz?tag=book:fight-club")
+    assert resp.status_code == 200
+    quiz_items = resp.json()["quiz"]
+    assert any(q["card"]["id"] == c3["id"] for q in quiz_items)
+    assert not any(q["card"]["id"] == c1["id"] for q in quiz_items)
+    assert not any(q["card"]["id"] == c2["id"] for q in quiz_items)
+
+
+