feat(reader): добавить парсер RFC из RFC Editor и отдельную группу спецификаций на книжной полке

- Реализован парсер RFC в app/reader.py с авто-загрузкой с rfc-editor.org и datatracker.ietf.org
- Очистка пагинации ([Page X], \x0c) и разбиение спецификаций на структурированные главы (TOC, разделы)
- Эндпоинт POST /api/books/fetch-rfc с защитой от дублирования и поддержкой номеров/URL
- Визуальное разделение на книжной полке через hr-разделитель и блок спецификаций IETF & RFC
- Быстрые пресеты стандартов (HTTP/1.1, HTTP/2, TLS 1.3, OAuth 2.0, WebSocket, QUIC, TCP, DNS)
- Интеграция в интерактивную читалку (перевод по клику, авто-захват контекста, SRS карточки)
- Unit-тесты парсера и API (31/31 passed) и обновление Service Worker кэша

tests/test_api.py

@@ -1645,6 +1645,118 @@ def test_background_tasks_and_book_mining():
     assert cancel_resp.json()["cancelled"] is True
 
 
+def test_rfc_parser_and_api(monkeypatch):
+    from app.reader import extract_rfc_number, parse_rfc_text
+
+    # 1. Number extraction
+    assert extract_rfc_number("9110") == 9110
+    assert extract_rfc_number("RFC 8446") == 8446
+    assert extract_rfc_number("rfc-6749") == 6749
+    assert extract_rfc_number("https://www.rfc-editor.org/rfc/rfc7540.txt") == 7540
+    assert extract_rfc_number("https://datatracker.ietf.org/doc/rfc9000/") == 9000
+
+    with pytest.raises(ValueError):
+        extract_rfc_number("invalid-rfc-string-without-number")
+
+    with pytest.raises(ValueError):
+        extract_rfc_number("rfc -5")
+
+    # 2. Parsing raw text with pagination artifacts
+    sample_rfc = """Internet Engineering Task Force (IETF)
+Request for Comments: 9999
+Category: Standards Track
+
+             Test Protocol Specification
+
+Abstract
+
+   This is a test abstract for RFC 9999 demonstrating cleaning.
+
+Table of Contents
+
+   1. Introduction .................................................... 1
+   2. Protocol Framing ................................................ 2
+   Authors' Addresses ................................................. 3
+
+                 Standards Track                    [Page 1]
+\x0c
+RFC 9999                 Test Protocol Specification          June 2026
+
+1. Introduction
+
+   The Test Protocol is designed for testing RFC parsers.
+   It provides ultra-clean chapter segmentation.
+
+2. Protocol Framing
+
+   Framing uses standard binary encodings.
+
+Authors' Addresses
+
+   Jane Doe
+   Example Corp
+"""
+    clean_title, author, chapters, total_words = parse_rfc_text(sample_rfc, rfc_number=9999)
+    assert clean_title == "RFC 9999: Test Protocol Specification"
+    assert author == "IETF"
+    assert len(chapters) >= 3
+    # Check that pagination footer/header was stripped
+    for ch in chapters:
+        assert "[Page 1]" not in ch["content"]
+        assert "\x0c" not in ch["content"]
+    assert any("Introduction" in ch["title"] for ch in chapters)
+    assert any("Framing" in ch["title"] for ch in chapters)
+    assert any("Addresses" in ch["title"] for ch in chapters)
+    assert total_words > 20
+
+    # 3. Test API endpoint unauthenticated
+    anon_client = TestClient(app)
+    resp = anon_client.post("/api/books/fetch-rfc", json={"rfc": "9999"})
+    assert resp.status_code == 401
+
+    # 4. Test API endpoint authenticated with mock fetch
+    import app.main as main_mod
+
+    def mock_fetch_and_parse_rfc(query):
+        return ("RFC 9999: Test Protocol Specification", "IETF (Jane Doe)", chapters, 9999, total_words)
+
+    monkeypatch.setattr(main_mod, "fetch_and_parse_rfc", mock_fetch_and_parse_rfc)
+
+    # Login demo user
+    login_resp = client.post("/api/login", json={"username": "demo_user", "password": "demo_pass_999"})
+    assert login_resp.status_code == 200
+
+    # Invalid input
+    bad_resp = client.post("/api/books/fetch-rfc", json={"rfc": "no_number_here"})
+    assert bad_resp.status_code == 400
+
+    # Fetch valid RFC
+    fetch_resp = client.post("/api/books/fetch-rfc", json={"rfc": "9999"})
+    assert fetch_resp.status_code == 200
+    book_data = fetch_resp.json()
+    assert book_data["source_type"] == "rfc"
+    assert book_data["title"] == "RFC 9999: Test Protocol Specification"
+    assert book_data["already_existed"] is False
+    assert len(book_data["chapters"]) >= 3
+    book_id = book_data["id"]
+
+    # Fetch again without force -> should return existing book
+    fetch_again = client.post("/api/books/fetch-rfc", json={"rfc": "9999"})
+    assert fetch_again.status_code == 200
+    again_data = fetch_again.json()
+    assert again_data["id"] == book_id
+    assert again_data["already_existed"] is True
+
+    # Check bookshelf retrieval includes RFC book
+    shelf_resp = client.get("/api/books")
+    assert shelf_resp.status_code == 200
+    shelf_books = shelf_resp.json()
+    rfc_books = [b for b in shelf_books if b["source_type"] == "rfc"]
+    assert len(rfc_books) > 0
+    assert rfc_books[0]["id"] == book_id
+
+
+