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

PLAN.md

@@ -146,7 +146,7 @@
   - Процент точности запоминания (Retention Rate %).
 - [ ] **4.2. Быстрый захват из браузера**:
   - Букмарклет для выделения текста на любой странице и отправки в словарь.
-- [ ] **4.3. Честный и строгий расчёт уровня CEFR (Active Vocabulary & Retention Weighting)**:
+- [x] **4.3. Честный и строгий расчёт уровня CEFR (Active Vocabulary & Retention Weighting)**:
   - Расчёт уровня владения исключительно по **активным выученным словам** (стадии `Mastered` и `Review` в алгоритме SM-2), исключая пассивные добавленные карточки, которые ещё не прошли интервальные повторения.
   - Корректирующий коэффициент точности: учёт Retention Rate %, чтобы уровень отражал реальную память, а не просто количество выписанных слов.
   - Индикатор пути к следующему уровню (например: «*До уровня B2 осталось закрепить 142 слова*»).
@@ -156,19 +156,19 @@
 ### Этап 5: Интерактивная Читалка & Библиотека (Interactive Reader & Source-based Learning)
 *Цель: чтение живых книг, статей и документации с мгновенным клик-переводом и авто-тегированием источников.*
 
-- [ ] **5.1. Хранилище текстов и парсер форматов (Bookshelf & Document Engine)**:
+- [x] **5.1. Хранилище текстов и парсер форматов (Bookshelf & Document Engine)**:
   - Поддержка форматов: вставка текста из буфера, `.txt`, `.md`, электронные книги `.epub` (с разбивкой по главам и сохранением позиции чтения).
   - Умная очистка веб-статей от лишней верстки и рекламы (Reader view).
-- [ ] **5.2. Автоматическое тегирование источников (Source & Metadata Auto-tagging)**:
+- [x] **5.2. Автоматическое тегирование источников (Source & Metadata Auto-tagging)**:
   - Каждое слово, сохранённое из книги/статьи, автоматически получает теги источника:
     - Название произведения (например, `#fight-club`, `#the-martian`, `#designing-data-intensive-apps`).
     - Тип/жанр материала (например, `#novel`, `#tech-article`, `#documentation`, `#cybersecurity`).
     - Автор / Источник (например, `#author:chuck-palahniuk`, `#cloudflare-blog`).
   - Автоматический захват предложения-контекста, в котором слово встретилось в книге.
-- [ ] **5.3. Запуск тестов и тренировок по источникам и тегам (Tag-scoped SRS Quizzes)**:
+- [x] **5.3. Запуск тестов и тренировок по источникам и тегам (Tag-scoped SRS Quizzes)**:
   - Возможность запустить любую тренировку (Карточки, 4 варианта ответа, Набор слова, Диктант) **строго по словам конкретной книги, статьи или автора**.
   - Быстрый запуск из читалки: *«Повторить все 35 новых слов из Fight Club»* прямо во время или после прочтения главы.
-- [ ] **5.4. Интерактивный клик-перевод и подсветка (Interactive Reader Layer)**:
+- [x] **5.4. Интерактивный клик-перевод и подсветка (Interactive Reader Layer)**:
   - Клик по любому слову $\rightarrow$ моментальный перевод, транскрипция, нативное аудио и кнопка «+ В словарь» в 1 клик.
   - Выделение фраз/связок (chunks) мышкой или тапом с литературным переводом всего выражения.
   - Подсветка в тексте книги уже выученных (`mastered`) и изучаемых (`learning`) слов.

app/database.py

@@ -64,6 +64,25 @@ def _migrate(conn: sqlite3.Connection):
     conn.execute("CREATE INDEX IF NOT EXISTS idx_srs_user ON srs_logs(user_id);")
     conn.execute("CREATE INDEX IF NOT EXISTS idx_srs_reviewed ON srs_logs(user_id, reviewed_at);")
 
+    # Ensure books table exists
+    conn.execute("""
+    CREATE TABLE IF NOT EXISTS books (
+        id INTEGER PRIMARY KEY AUTOINCREMENT,
+        user_id INTEGER NOT NULL,
+        title TEXT NOT NULL,
+        author TEXT DEFAULT '',
+        source_type TEXT NOT NULL,
+        chapters_json TEXT NOT NULL,
+        current_chapter INTEGER DEFAULT 0,
+        current_position REAL DEFAULT 0,
+        total_words INTEGER DEFAULT 0,
+        created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
+        updated_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
+        FOREIGN KEY (user_id) REFERENCES users(id) ON DELETE CASCADE
+    );
+    """)
+    conn.execute("CREATE INDEX IF NOT EXISTS idx_books_user ON books(user_id);")
+
 
 def init_db():
     config.DB_PATH.parent.mkdir(parents=True, exist_ok=True)
@@ -138,6 +157,22 @@ def init_db():
             response_json TEXT NOT NULL,
             cached_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
         );
+
+        CREATE TABLE IF NOT EXISTS books (
+            id INTEGER PRIMARY KEY AUTOINCREMENT,
+            user_id INTEGER NOT NULL,
+            title TEXT NOT NULL,
+            author TEXT DEFAULT '',
+            source_type TEXT NOT NULL, -- 'epub', 'txt', 'md', 'text'
+            chapters_json TEXT NOT NULL, -- JSON array: [{"title": "Chapter 1", "content": "..."}]
+            current_chapter INTEGER DEFAULT 0,
+            current_position REAL DEFAULT 0,
+            total_words INTEGER DEFAULT 0,
+            created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
+            updated_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
+            FOREIGN KEY (user_id) REFERENCES users(id) ON DELETE CASCADE
+        );
+        CREATE INDEX IF NOT EXISTS idx_books_user ON books(user_id);
         """)
         # Apply migrations for pre-existing databases
         _migrate(conn)

app/main.py

@@ -1,5 +1,7 @@
 import os
+import json
 import urllib.parse
+from pathlib import Path
 from contextlib import asynccontextmanager
 from typing import Optional, List, Dict, Any
 from datetime import datetime, timezone, date
@@ -24,7 +26,8 @@ from app.auth import (
 )
 from app.dictionary import lookup_term, USER_AGENT
 from app.export import export_csv, export_json, export_anki_tsv, export_markdown
-from app.srs import calculate_sm2, generate_quiz_options, build_activity_heatmap
+from app.srs import calculate_sm2, generate_quiz_options, build_activity_heatmap, calculate_cefr_level
+from app.reader import parse_epub, parse_text, count_words
 
 
 @asynccontextmanager
@@ -131,6 +134,20 @@ class SrsReviewRequest(BaseModel):
     rating: int = Field(..., ge=1, le=4)
 
 
+class BookCreateRequest(BaseModel):
+    title: Optional[str] = "Untitled"
+    author: Optional[str] = ""
+    content: Optional[str] = ""
+    source_type: Optional[str] = "text"
+
+
+class BookProgressRequest(BaseModel):
+    current_chapter: Optional[int] = None
+    current_position: Optional[float] = None
+    chapter: Optional[int] = None
+    position: Optional[float] = None
+
+
 # ---------------------------------------------------------------------------
 # PWA Static Endpoints
 # ---------------------------------------------------------------------------
@@ -528,6 +545,7 @@ async def api_batch_action(req: BatchActionRequest, user: dict = Depends(require
 @app.get("/api/srs/due")
 async def api_srs_queue(
     collection: Optional[str] = None,
+    tag: Optional[str] = None,
     limit: int = 25,
     mix: bool = False,
     user: dict = Depends(require_user),
@@ -543,8 +561,14 @@ async def api_srs_queue(
     with get_db() as conn:
         now_str = datetime.now(timezone.utc).strftime("%Y-%m-%d %H:%M:%S")
 
-        col_filter = " AND collection = ?" if collection else ""
-        col_params = [collection] if collection else []
+        col_filter = ""
+        col_params = []
+        if collection:
+            col_filter += " AND collection = ?"
+            col_params.append(collection.strip())
+        if tag:
+            col_filter += " AND tags LIKE ?"
+            col_params.append(f"%{tag.strip()}%")
 
         if mix:
             # 1. New cards (up to 10)
@@ -607,6 +631,7 @@ async def api_srs_queue(
 @app.get("/api/srs/quiz")
 async def api_srs_quiz(
     collection: Optional[str] = None,
+    tag: Optional[str] = None,
     count: int = 10,
     user: dict = Depends(require_user),
 ):
@@ -615,8 +640,15 @@ async def api_srs_quiz(
     """
     with get_db() as conn:
         # Fetch target cards for user
-        col_filter = " AND collection = ?" if collection else ""
-        col_params = [collection] if collection else []
+        col_filter = ""
+        col_params = []
+        if collection:
+            col_filter += " AND collection = ?"
+            col_params.append(collection.strip())
+        if tag:
+            col_filter += " AND tags LIKE ?"
+            col_params.append(f"%{tag.strip()}%")
+
         rows = conn.execute(
             f"SELECT * FROM vocabulary_cards WHERE user_id = ?{col_filter} ORDER BY RANDOM() LIMIT ?",
             [user["id"]] + col_params + [count],
@@ -798,6 +830,8 @@ async def api_srs_stats(user: dict = Depends(require_user)):
         ).fetchone()[0]
         today_reviewed = date_counts.get(today_str, 0)
 
+        cefr_info = calculate_cefr_level(mastered, review, retention_rate, total_cards)
+
         return {
             "total_cards": total_cards,
             "new_cards": new_cards,
@@ -812,6 +846,7 @@ async def api_srs_stats(user: dict = Depends(require_user)):
             "longest_streak": heatmap_info["longest_streak"],
             "today_added": today_added,
             "today_reviewed": today_reviewed,
+            "cefr": cefr_info,
         }
 
 
@@ -944,3 +979,255 @@ async def api_export_markdown(collection: Optional[str] = None, user: dict = Dep
         media_type="text/markdown; charset=utf-8",
         headers={"Content-Disposition": "attachment; filename=\"vocabulary.md\""},
     )
+
+
+# ---------------------------------------------------------------------------
+# Bookshelf & Interactive Reader Endpoints (Stage 5)
+# ---------------------------------------------------------------------------
+
+@app.get("/api/books")
+async def api_get_books(user: dict = Depends(require_user)):
+    """
+    Lists books for current user (id, title, author, source_type, chapters_count,
+    total_words, current_chapter, current_position, created_at, updated_at).
+    Excludes full chapters_json for efficiency.
+    """
+    with get_db() as conn:
+        rows = conn.execute(
+            """
+            SELECT id, user_id, title, author, source_type,
+                   json_array_length(chapters_json) AS chapters_count,
+                   total_words, current_chapter, current_position,
+                   created_at, updated_at
+            FROM books
+            WHERE user_id = ?
+            ORDER BY updated_at DESC, id DESC
+            """,
+            (user["id"],),
+        ).fetchall()
+        return [dict(r) for r in rows]
+
+
+@app.post("/api/books")
+async def api_create_book(
+    request: Request,
+    user: dict = Depends(require_user),
+):
+    """
+    Creates or uploads a book.
+    Accepts:
+      - JSON: {"title": "...", "author": "...", "content": "...", "source_type": "text"}
+      - Multipart file upload: file (UploadFile for .epub, .txt, .md) and optional title, author
+    """
+    content_type = request.headers.get("content-type", "")
+
+    title = "Untitled"
+    author = ""
+    source_type = "text"
+    chapters = []
+
+    if "multipart/form-data" in content_type:
+        form = await request.form()
+        file_obj = form.get("file")
+        if not file_obj or not hasattr(file_obj, "filename") or not file_obj.filename:
+            raise HTTPException(status_code=400, detail="No file uploaded")
+
+        filename = file_obj.filename
+        file_bytes = await file_obj.read()
+        if not file_bytes:
+            raise HTTPException(status_code=400, detail="Uploaded file is empty")
+
+        form_title = (form.get("title") or "").strip()
+        form_author = (form.get("author") or "").strip()
+        stem = Path(filename).stem
+
+        lower_name = filename.lower()
+        if lower_name.endswith(".epub"):
+            source_type = "epub"
+            parsed_title, parsed_author, chapters = parse_epub(file_bytes)
+            title = form_title or (parsed_title if parsed_title != "Untitled" else "") or stem
+            author = form_author or parsed_author
+        elif lower_name.endswith(".md"):
+            source_type = "md"
+            text_str = file_bytes.decode("utf-8", errors="replace")
+            parsed_title, parsed_author, chapters = parse_text(text_str, title=form_title or "Untitled", author=form_author)
+            title = form_title or (parsed_title if parsed_title != "Untitled" else "") or stem
+            author = form_author or parsed_author
+        elif lower_name.endswith(".txt"):
+            source_type = "txt"
+            text_str = file_bytes.decode("utf-8", errors="replace")
+            parsed_title, parsed_author, chapters = parse_text(text_str, title=form_title or "Untitled", author=form_author)
+            title = form_title or (parsed_title if parsed_title != "Untitled" else "") or stem
+            author = form_author or parsed_author
+        else:
+            source_type = "text"
+            text_str = file_bytes.decode("utf-8", errors="replace")
+            parsed_title, parsed_author, chapters = parse_text(text_str, title=form_title or "Untitled", author=form_author)
+            title = form_title or (parsed_title if parsed_title != "Untitled" else "") or stem
+            author = form_author or parsed_author
+
+    else:
+        try:
+            body = await request.json()
+        except Exception:
+            raise HTTPException(status_code=400, detail="Invalid JSON or missing body")
+
+        raw_content = body.get("content") or ""
+        title_in = (body.get("title") or "").strip()
+        author_in = (body.get("author") or "").strip()
+        source_type = body.get("source_type") or "text"
+
+        if not raw_content and not title_in:
+            raise HTTPException(status_code=400, detail="Book content is required")
+
+        parsed_title, parsed_author, chapters = parse_text(
+            raw_content, title=title_in or "Untitled", author=author_in
+        )
+        title = title_in or parsed_title
+        author = author_in or parsed_author
+
+    total_words = sum(count_words(ch.get("content", "")) for ch in chapters)
+    chapters_json = json.dumps(chapters, ensure_ascii=False)
+
+    with get_db() as conn:
+        cursor = conn.execute(
+            """
+            INSERT INTO books (
+                user_id, title, author, source_type, chapters_json,
+                current_chapter, current_position, total_words
+            ) VALUES (?, ?, ?, ?, ?, 0, 0.0, ?)
+            """,
+            (user["id"], title, author, source_type, chapters_json, total_words),
+        )
+        new_id = cursor.lastrowid
+        row = conn.execute(
+            """
+            SELECT id, user_id, title, author, source_type, chapters_json,
+                   json_array_length(chapters_json) AS chapters_count,
+                   current_chapter, current_position, total_words,
+                   created_at, updated_at
+            FROM books WHERE id = ?
+            """,
+            (new_id,),
+        ).fetchone()
+
+        res = dict(row)
+        res["chapters"] = chapters
+        return res
+
+
+@app.get("/api/books/{book_id}")
+async def api_get_book(book_id: int, user: dict = Depends(require_user)):
+    """
+    Returns full book details including chapters_json.
+    """
+    with get_db() as conn:
+        row = conn.execute(
+            """
+            SELECT id, user_id, title, author, source_type, chapters_json,
+                   json_array_length(chapters_json) AS chapters_count,
+                   current_chapter, current_position, total_words,
+                   created_at, updated_at
+            FROM books
+            WHERE id = ? AND user_id = ?
+            """,
+            (book_id, user["id"]),
+        ).fetchone()
+        if not row:
+            raise HTTPException(status_code=404, detail="Book not found")
+        data = dict(row)
+        try:
+            data["chapters"] = json.loads(data["chapters_json"])
+        except Exception:
+            data["chapters"] = []
+        return data
+
+
+@app.put("/api/books/{book_id}/progress")
+@app.patch("/api/books/{book_id}/progress")
+async def api_update_book_progress(
+    book_id: int,
+    req: Optional[BookProgressRequest] = None,
+    current_chapter: Optional[int] = Query(None),
+    current_position: Optional[float] = Query(None),
+    request: Request = None,
+    user: dict = Depends(require_user),
+):
+    """
+    Updates reading progress (current_chapter, current_position) for a book.
+    """
+    ch = None
+    pos = None
+    if req is not None:
+        ch = req.current_chapter if req.current_chapter is not None else req.chapter
+        pos = req.current_position if req.current_position is not None else req.position
+    if ch is None:
+        ch = current_chapter
+    if pos is None:
+        pos = current_position
+    if ch is None or pos is None:
+        if request:
+            try:
+                body = await request.json()
+                if ch is None:
+                    ch = body.get("current_chapter", body.get("chapter"))
+                if pos is None:
+                    pos = body.get("current_position", body.get("position"))
+            except Exception:
+                pass
+
+    if ch is None and pos is None:
+        raise HTTPException(status_code=400, detail="Missing current_chapter or current_position")
+
+    with get_db() as conn:
+        row = conn.execute(
+            "SELECT id, current_chapter, current_position FROM books WHERE id = ? AND user_id = ?",
+            (book_id, user["id"]),
+        ).fetchone()
+        if not row:
+            raise HTTPException(status_code=404, detail="Book not found")
+
+        new_ch = int(ch) if ch is not None else row["current_chapter"]
+        new_pos = float(pos) if pos is not None else row["current_position"]
+
+        conn.execute(
+            """
+            UPDATE books
+            SET current_chapter = ?, current_position = ?, updated_at = CURRENT_TIMESTAMP
+            WHERE id = ? AND user_id = ?
+            """,
+            (new_ch, new_pos, book_id, user["id"]),
+        )
+
+        updated_row = conn.execute(
+            """
+            SELECT id, user_id, title, author, source_type, chapters_json,
+                   json_array_length(chapters_json) AS chapters_count,
+                   current_chapter, current_position, total_words,
+                   created_at, updated_at
+            FROM books
+            WHERE id = ?
+            """,
+            (book_id,),
+        ).fetchone()
+        res = dict(updated_row)
+        try:
+            res["chapters"] = json.loads(res["chapters_json"])
+        except Exception:
+            res["chapters"] = []
+        return res
+
+
+@app.delete("/api/books/{book_id}")
+async def api_delete_book(book_id: int, user: dict = Depends(require_user)):
+    """
+    Deletes a book for the current user.
+    """
+    with get_db() as conn:
+        cursor = conn.execute(
+            "DELETE FROM books WHERE id = ? AND user_id = ?",
+            (book_id, user["id"]),
+        )
+        if cursor.rowcount == 0:
+            raise HTTPException(status_code=404, detail="Book not found")
+        return {"status": "ok", "deleted_id": book_id}

app/reader.py

@@ -0,0 +1,350 @@
+import io
+import re
+import html
+import zipfile
+import posixpath
+import urllib.parse
+import xml.etree.ElementTree as ET
+from html.parser import HTMLParser
+from typing import Tuple, List, Dict
+
+
+def count_words(text: str) -> int:
+    """
+    Counts words in text across multiple languages, ignoring isolated punctuation.
+    """
+    if not text:
+        return 0
+    return len(re.findall(r"\b[\w]+(?:['’][\w]+)?\b", text))
+
+
+class HTMLTextExtractor(HTMLParser):
+    """
+    Strips HTML tags cleanly while preserving paragraph and heading breaks with newlines.
+    Also extracts the first heading and/or <title> tag for chapter naming.
+    """
+    def __init__(self):
+        super().__init__()
+        self.text_parts: List[str] = []
+        self.ignore_tags = {"style", "script", "noscript"}
+        self.ignore_depth = 0
+        self.heading: str | None = None
+        self.in_heading = False
+        self.heading_parts: List[str] = []
+        self.title: str | None = None
+        self.in_title = False
+        self.title_parts: List[str] = []
+
+    def handle_starttag(self, tag: str, attrs):
+        t = tag.lower()
+        if t in self.ignore_tags:
+            self.ignore_depth += 1
+        elif t == "title":
+            self.in_title = True
+            self.title_parts = []
+        elif t in {"h1", "h2", "h3", "h4", "h5", "h6"}:
+            self.text_parts.append("\n\n")
+            if not self.heading:
+                self.in_heading = True
+                self.heading_parts = []
+        elif t in {"p", "div", "section", "article", "blockquote", "header", "footer"}:
+            self.text_parts.append("\n\n")
+        elif t in {"br", "hr", "li", "tr"}:
+            self.text_parts.append("\n")
+
+    def handle_endtag(self, tag: str):
+        t = tag.lower()
+        if t in self.ignore_tags:
+            self.ignore_depth = max(0, self.ignore_depth - 1)
+        elif t == "title":
+            self.in_title = False
+            self.title = "".join(self.title_parts).strip()
+        elif t in {"h1", "h2", "h3", "h4", "h5", "h6"}:
+            self.text_parts.append("\n\n")
+            if self.in_heading:
+                self.in_heading = False
+                if not self.heading:
+                    self.heading = "".join(self.heading_parts).strip()
+        elif t in {"p", "div", "section", "article", "blockquote", "header", "footer"}:
+            self.text_parts.append("\n\n")
+        elif t in {"li", "tr"}:
+            self.text_parts.append("\n")
+
+    def handle_data(self, data: str):
+        if self.in_title:
+            self.title_parts.append(data)
+        if self.ignore_depth == 0 and not self.in_title:
+            # Replace non-breaking spaces with standard space
+            cleaned_data = data.replace("\xa0", " ")
+            self.text_parts.append(cleaned_data)
+            if self.in_heading:
+                self.heading_parts.append(cleaned_data)
+
+    def get_text(self) -> str:
+        raw = "".join(self.text_parts)
+        lines = [line.strip() for line in raw.split("\n")]
+        clean = "\n".join(lines)
+        return re.sub(r"\n{3,}", "\n\n", clean).strip()
+
+
+def parse_epub(file_bytes: bytes) -> Tuple[str, str, List[Dict[str, str]]]:
+    """
+    Parses an EPUB file archive and extracts:
+      - title: book title
+      - author: creator/author
+      - chapters: list of {"title": str, "content": str}
+    """
+    try:
+        z = zipfile.ZipFile(io.BytesIO(file_bytes))
+    except Exception as e:
+        raise ValueError(f"Invalid EPUB archive: {e}")
+
+    # 1. Locate root OPF file from META-INF/container.xml
+    opf_path = None
+    try:
+        container_data = z.read("META-INF/container.xml")
+        root = ET.fromstring(container_data)
+        rootfile = root.find(".//{*}rootfile")
+        if rootfile is not None:
+            opf_path = rootfile.attrib.get("full-path")
+    except Exception:
+        pass
+
+    if not opf_path:
+        for name in z.namelist():
+            if name.lower().endswith(".opf"):
+                opf_path = name
+                break
+
+    if not opf_path:
+        raise ValueError("Invalid EPUB: no OPF file found")
+
+    opf_path = opf_path.replace("\\", "/").lstrip("/")
+    opf_dir = posixpath.dirname(opf_path)
+
+    try:
+        opf_content = z.read(opf_path)
+    except KeyError:
+        # Try lowercase matching
+        name_map = {n.lower(): n for n in z.namelist()}
+        if opf_path.lower() in name_map:
+            opf_content = z.read(name_map[opf_path.lower()])
+        else:
+            raise ValueError(f"OPF file not found in archive: {opf_path}")
+
+    # 2. Extract metadata (title, author)
+    title = "Untitled"
+    author = ""
+    opf_tree = None
+    try:
+        opf_tree = ET.fromstring(opf_content)
+        title_el = opf_tree.find(".//{*}title")
+        if title_el is not None and title_el.text:
+            title = title_el.text.strip()
+        creator_el = opf_tree.find(".//{*}creator")
+        if creator_el is not None and creator_el.text:
+            author = creator_el.text.strip()
+    except Exception:
+        opf_str = opf_content.decode("utf-8", errors="ignore")
+        tm = re.search(r"<[^:]*:?title[^>]*>(.*?)</[^:]*:?title>", opf_str, re.I | re.S)
+        if tm:
+            title = re.sub(r"<[^>]+>", "", tm.group(1)).strip()
+        cm = re.search(r"<[^:]*:?creator[^>]*>(.*?)</[^:]*:?creator>", opf_str, re.I | re.S)
+        if cm:
+            author = re.sub(r"<[^>]+>", "", cm.group(1)).strip()
+
+    # 3. Parse Manifest (id -> href, media-type)
+    manifest: Dict[str, Dict[str, str]] = {}
+    if opf_tree is not None:
+        for item in opf_tree.findall(".//{*}item"):
+            iid = item.attrib.get("id")
+            href = item.attrib.get("href")
+            media_type = item.attrib.get("media-type", "").lower()
+            if iid and href:
+                manifest[iid] = {"href": href, "media_type": media_type}
+    else:
+        opf_str = opf_content.decode("utf-8", errors="ignore")
+        for m in re.finditer(r'<item\s+[^>]*id=["\']([^"\']+)["\'][^>]*href=["\']([^"\']+)["\']', opf_str, re.I):
+            manifest[m.group(1)] = {"href": m.group(2), "media_type": ""}
+
+    # 4. Spine items in reading order
+    spine_ids: List[str] = []
+    if opf_tree is not None:
+        for itemref in opf_tree.findall(".//{*}itemref"):
+            idref = itemref.attrib.get("idref")
+            if idref:
+                spine_ids.append(idref)
+    else:
+        opf_str = opf_content.decode("utf-8", errors="ignore")
+        for m in re.finditer(r'<itemref\s+[^>]*idref=["\']([^"\']+)["\']', opf_str, re.I):
+            spine_ids.append(m.group(1))
+
+    # Fallback if spine is empty: find all html/xhtml files in manifest
+    candidate_paths: List[str] = []
+    if spine_ids:
+        for idref in spine_ids:
+            item = manifest.get(idref)
+            if item:
+                candidate_paths.append(item["href"])
+    else:
+        for item in manifest.values():
+            href = item["href"]
+            if href.lower().endswith((".xhtml", ".html", ".htm")):
+                candidate_paths.append(href)
+
+    namelist_map = {name.lower(): name for name in z.namelist()}
+    chapters: List[Dict[str, str]] = []
+    chapter_num = 1
+
+    for href in candidate_paths:
+        unquoted = urllib.parse.unquote(href)
+        rel_path = posixpath.normpath(posixpath.join(opf_dir, unquoted)) if opf_dir else unquoted
+        rel_path = rel_path.replace("\\", "/").lstrip("/")
+
+        actual_path = None
+        if rel_path in z.namelist():
+            actual_path = rel_path
+        elif rel_path.lower() in namelist_map:
+            actual_path = namelist_map[rel_path.lower()]
+
+        if not actual_path:
+            continue
+
+        try:
+            raw_bytes = z.read(actual_path)
+            try:
+                html_str = raw_bytes.decode("utf-8")
+            except UnicodeDecodeError:
+                html_str = raw_bytes.decode("latin-1", errors="replace")
+        except Exception:
+            continue
+
+        parser = HTMLTextExtractor()
+        parser.feed(html_str)
+        text = parser.get_text()
+
+        # Skip chapters with little or no readable text
+        if count_words(text) < 1:
+            continue
+
+        ch_title = parser.heading or parser.title or f"Chapter {chapter_num}"
+        # If ch_title is identical to book title or very long, format nicely
+        if len(ch_title) > 120:
+            ch_title = f"Chapter {chapter_num}"
+
+        chapters.append({"title": ch_title, "content": text})
+        chapter_num += 1
+
+    if not chapters:
+        chapters = [{"title": title if title != "Untitled" else "Chapter 1", "content": ""}]
+
+    return title, author, chapters
+
+
+def split_long_text(text: str, target_words: int = 3000) -> List[str]:
+    """
+    Splits text into chunks of approximately target_words on paragraph boundaries.
+    """
+    paragraphs = [p.strip() for p in re.split(r"\n{2,}", text) if p.strip()]
+    if not paragraphs:
+        return [text.strip()] if text.strip() else []
+
+    chunks: List[str] = []
+    current_paras: List[str] = []
+    current_count = 0
+
+    for p in paragraphs:
+        w_count = count_words(p)
+        # If single paragraph is massive (> target_words * 1.5), split by words
+        if w_count > target_words * 1.5:
+            if current_paras:
+                chunks.append("\n\n".join(current_paras))
+                current_paras = []
+                current_count = 0
+            words = p.split()
+            for i in range(0, len(words), target_words):
+                chunk = " ".join(words[i : i + target_words])
+                if chunk.strip():
+                    chunks.append(chunk)
+            continue
+
+        if current_count + w_count > target_words and current_count > 0:
+            chunks.append("\n\n".join(current_paras))
+            current_paras = [p]
+            current_count = w_count
+        else:
+            current_paras.append(p)
+            current_count += w_count
+
+    if current_paras:
+        chunks.append("\n\n".join(current_paras))
+
+    return chunks
+
+
+def parse_text(content: str, title: str = "Untitled", author: str = "") -> Tuple[str, str, List[Dict[str, str]]]:
+    """
+    Parses plain text or Markdown into readable chapters.
+    Splits by explicit chapter markers (e.g. 'Chapter X', '# Chapter') or chunks of ~3000 words.
+    """
+    content = content.replace("\r\n", "\n").replace("\r", "\n").strip()
+    if not content:
+        return title, author, [{"title": title if title != "Untitled" else "Chapter 1", "content": ""}]
+
+    lines = content.split("\n")
+    first_line = lines[0].strip()
+
+    # Extract title from first line if default
+    if title == "Untitled":
+        if first_line.startswith("# "):
+            title = first_line.lstrip("# ").strip()
+            if len(lines) > 1:
+                content = "\n".join(lines[1:]).strip()
+        elif first_line.lower().startswith("title:"):
+            title = first_line.split(":", 1)[1].strip()
+            if len(lines) > 1:
+                content = "\n".join(lines[1:]).strip()
+
+    # Extract author from next line if missing
+    if not author:
+        lines = content.split("\n")
+        if lines and lines[0].lower().startswith(("author:", "by:")):
+            author = lines[0].split(":", 1)[1].strip()
+            if len(lines) > 1:
+                content = "\n".join(lines[1:]).strip()
+
+    heading_pattern = re.compile(
+        r"^[ \t]*(?:"
+        r"#{1,3}[ \t]+(.+)|"
+        r"((?:Chapter|CHAPTER|Глава|ГЛАВА|Part|PART|Section|SECTION|Act|ACT|Scene|SCENE)[ \t]+[0-9IVXLCDMivxlcdm\w\.\-]+(?:[ \t]*[:\-–—\.][ \t]*.*|[ \t]+[^\n\r]+)?)"
+        r")[ \t]*$",
+        re.MULTILINE,
+    )
+
+    matches = list(heading_pattern.finditer(content))
+    chapters: List[Dict[str, str]] = []
+
+    if len(matches) >= 1:
+        # Pre-chapter intro text
+        intro = content[: matches[0].start()].strip()
+        if intro and count_words(intro) > 10:
+            chapters.append({"title": "Introduction", "content": intro})
+
+        for i, m in enumerate(matches):
+            h_text = (m.group(1) or m.group(2)).strip()
+            start = m.start()
+            end = matches[i + 1].start() if i + 1 < len(matches) else len(content)
+            body = content[start:end].strip()
+            if body:
+                chapters.append({"title": h_text, "content": body})
+
+    if not chapters:
+        # No headings detected: split by ~3000 words chunks
+        chunks = split_long_text(content, target_words=3000)
+        if len(chunks) == 1:
+            chapters = [{"title": title if title != "Untitled" else "Chapter 1", "content": chunks[0]}]
+        else:
+            for idx, chunk in enumerate(chunks, start=1):
+                chapters.append({"title": f"Chapter {idx}", "content": chunk})
+
+    return title, author, chapters

app/srs.py

@@ -248,3 +248,57 @@ def build_activity_heatmap(review_dates: Dict[str, int], days: int = 180) -> Dic
         "current_streak": current_streak,
         "longest_streak": max(longest_streak, current_streak),
     }
+
+
+def calculate_cefr_level(
+    mastered_count: int,
+    review_count: int,
+    retention_rate: float,
+    total_cards: int = 0
+) -> Dict[str, Any]:
+    """
+    Computes strict CEFR level based on active vocabulary weight and memory retention rate (PLAN.md 4.3).
+    Only words in Mastered (weight 1.0) and Review (weight 0.5) stages count, scaled by retention rate %.
+    """
+    safe_retention = max(0.0, min(100.0, float(retention_rate)))
+    retention_factor = (safe_retention / 100.0) if safe_retention > 0 else 1.0
+
+    # Active weighted vocabulary: Mastered gives 1.0, Review gives 0.5
+    weighted_words = (mastered_count * 1.0) + (review_count * 0.5)
+    active_vocab = int(round(weighted_words * retention_factor))
+
+    # CEFR thresholds: (min_words, level, title, next_level, next_target)
+    brackets = [
+        (0, "A1", "Начальный словарный запас", "A2", 300),
+        (300, "A2", "Элементарный словарный запас", "B1", 800),
+        (800, "B1", "Уверенное понимание общих и рабочих тем", "B2", 1600),
+        (1600, "B2", "Свободное чтение тех. литературы и документации", "C1", 3000),
+        (3000, "C1", "Продвинутый профессиональный уровень", "C2", 5000),
+    ]
+
+    current_bracket = brackets[0]
+    for b in brackets:
+        if active_vocab >= b[0]:
+            current_bracket = b
+
+    min_w, level, title, next_lvl, next_w = current_bracket
+    words_to_next = max(0, next_w - active_vocab)
+    range_span = next_w - min_w
+    current_progress = active_vocab - min_w
+    pct = int(min(100, max(0, (current_progress / range_span) * 100))) if range_span > 0 else 100
+
+    if words_to_next > 0:
+        message = f"До уровня {next_lvl} осталось закрепить {words_to_next} активных слов"
+    else:
+        message = f"Уровень {level} полностью освоен!"
+
+    return {
+        "level": level,
+        "title": title,
+        "active_vocab": active_vocab,
+        "next_level": next_lvl,
+        "words_to_next": words_to_next,
+        "progress_percent": pct,
+        "message": message,
+        "retention_rate": safe_retention,
+    }

app/static/css/style.css

@@ -2396,4 +2396,386 @@ body {
     }
 }
 
+/* ==========================================================================
+   Stage 5: Interactive Reader & Bookshelf Styles
+   ========================================================================== */
+
+.reader-view {
+    max-width: 1100px;
+    margin: 0 auto;
+    padding: 24px 20px 80px;
+}
+
+.bookshelf-header {
+    display: flex;
+    justify-content: space-between;
+    align-items: center;
+    flex-wrap: wrap;
+    gap: 16px;
+    margin-bottom: 28px;
+    padding-bottom: 20px;
+    border-bottom: 1px solid var(--border-color);
+}
+
+.bookshelf-title-wrap h2 {
+    font-size: 24px;
+    font-weight: 700;
+    color: var(--text-main);
+    display: flex;
+    align-items: center;
+    gap: 8px;
+}
+
+.bookshelf-title-wrap .subtitle {
+    font-size: 14px;
+    color: var(--text-muted);
+    margin-top: 4px;
+}
+
+.bookshelf-actions {
+    display: flex;
+    align-items: center;
+    gap: 12px;
+}
+
+.file-upload-label {
+    cursor: pointer;
+    display: inline-flex;
+    align-items: center;
+    gap: 6px;
+}
+
+.bookshelf-grid {
+    display: grid;
+    grid-template-columns: repeat(auto-fill, minmax(300px, 1fr));
+    gap: 20px;
+}
+
+.book-card {
+    background-color: var(--bg-surface);
+    border: 1px solid var(--border-color);
+    border-radius: var(--radius-lg);
+    padding: 20px;
+    display: flex;
+    flex-direction: column;
+    justify-content: space-between;
+    transition: var(--transition);
+    position: relative;
+    box-shadow: var(--shadow-sm);
+}
+
+.book-card:hover {
+    border-color: var(--border-focus);
+    box-shadow: var(--shadow-md);
+    transform: translateY(-2px);
+}
+
+.book-card-top {
+    display: flex;
+    align-items: flex-start;
+    gap: 14px;
+    margin-bottom: 14px;
+}
+
+.book-cover-icon {
+    font-size: 32px;
+    background: var(--bg-input);
+    border: 1px solid var(--border-color);
+    border-radius: var(--radius-md);
+    width: 52px;
+    height: 64px;
+    display: flex;
+    align-items: center;
+    justify-content: center;
+    flex-shrink: 0;
+}
+
+.book-card-info {
+    flex: 1;
+    min-width: 0;
+}
+
+.book-card-title {
+    font-size: 16px;
+    font-weight: 700;
+    color: var(--text-main);
+    margin-bottom: 4px;
+    overflow: hidden;
+    text-overflow: ellipsis;
+    white-space: nowrap;
+}
+
+.book-card-author {
+    font-size: 13px;
+    color: var(--text-muted);
+    margin-bottom: 8px;
+    overflow: hidden;
+    text-overflow: ellipsis;
+    white-space: nowrap;
+}
+
+.book-card-badges {
+    display: flex;
+    align-items: center;
+    gap: 8px;
+}
+
+.badge-format {
+    text-transform: uppercase;
+    font-size: 10px;
+    font-weight: 700;
+    padding: 2px 6px;
+    border-radius: var(--radius-sm);
+    background: var(--tag-bg);
+    color: var(--tag-text);
+}
+
+.badge-words {
+    font-size: 12px;
+    color: var(--text-dim);
+}
+
+.book-progress-wrap {
+    margin: 14px 0 16px;
+}
+
+.book-progress-labels {
+    display: flex;
+    justify-content: space-between;
+    font-size: 12px;
+    color: var(--text-dim);
+    margin-bottom: 6px;
+}
+
+.book-progress-bar-bg {
+    width: 100%;
+    height: 6px;
+    background-color: var(--bg-input);
+    border-radius: var(--radius-full);
+    overflow: hidden;
+}
+
+.book-progress-bar-fill {
+    height: 100%;
+    background-color: var(--primary);
+    border-radius: var(--radius-full);
+    transition: width 0.3s ease;
+}
+
+.book-card-actions {
+    display: flex;
+    align-items: center;
+    justify-content: space-between;
+    gap: 8px;
+    padding-top: 12px;
+    border-top: 1px solid var(--border-color);
+}
+
+/* Reader Interface */
+.reader-interface {
+    background-color: var(--bg-surface);
+    border: 1px solid var(--border-color);
+    border-radius: var(--radius-lg);
+    box-shadow: var(--shadow-lg);
+    overflow: hidden;
+}
+
+.reader-toolbar {
+    position: sticky;
+    top: 0;
+    z-index: 100;
+    background-color: var(--bg-surface);
+    border-bottom: 1px solid var(--border-color);
+    padding: 12px 18px;
+    display: flex;
+    justify-content: space-between;
+    align-items: center;
+    flex-wrap: wrap;
+    gap: 12px;
+}
+
+.reader-toolbar-left {
+    display: flex;
+    align-items: center;
+    gap: 14px;
+}
+
+.reader-meta {
+    display: flex;
+    flex-direction: column;
+}
+
+.reader-title {
+    font-size: 16px;
+    font-weight: 700;
+    color: var(--text-main);
+    line-height: 1.2;
+}
+
+.reader-author {
+    font-size: 12px;
+    color: var(--text-muted);
+}
+
+.reader-toolbar-center {
+    display: flex;
+    align-items: center;
+    gap: 8px;
+}
+
+.reader-select {
+    padding: 6px 12px;
+    border-radius: var(--radius-sm);
+    background-color: var(--bg-input);
+    color: var(--text-main);
+    border: 1px solid var(--border-color);
+    font-size: 13px;
+    outline: none;
+    max-width: 240px;
+}
+
+.reader-toolbar-right {
+    display: flex;
+    align-items: center;
+    gap: 10px;
+}
+
+.font-controls {
+    display: flex;
+    align-items: center;
+    gap: 4px;
+}
+
+.reader-scroll-area {
+    padding: 36px 24px 60px;
+    max-width: 780px;
+    margin: 0 auto;
+    min-height: 60vh;
+}
+
+.reader-content-body {
+    font-family: Georgia, 'Times New Roman', serif;
+    font-size: 19px;
+    line-height: 1.85;
+    color: var(--text-main);
+    word-break: break-word;
+    user-select: text;
+}
+
+.reader-content-body h1,
+.reader-content-body h2,
+.reader-content-body h3 {
+    font-family: var(--font-family);
+    margin: 28px 0 16px;
+    color: var(--text-main);
+}
+
+.reader-content-body p {
+    margin-bottom: 20px;
+    text-indent: 1.2em;
+}
+
+/* Interactive Words */
+.reader-word {
+    cursor: pointer;
+    border-radius: 3px;
+    transition: background-color 0.12s ease, color 0.12s ease;
+    padding: 1px 2px;
+}
+
+.reader-word:hover {
+    background-color: var(--primary-dim);
+    color: var(--primary);
+}
+
+.reader-word.status-mastered.highlight-enabled {
+    border-bottom: 2px dotted rgba(16, 185, 129, 0.5);
+}
+
+.reader-word.status-learning.highlight-enabled {
+    border-bottom: 2px dotted rgba(56, 189, 248, 0.5);
+}
+
+/* Click-to-Translate Popup */
+.reader-word-popup {
+    position: fixed;
+    z-index: 10001;
+    background-color: var(--bg-surface);
+    border: 1px solid var(--border-focus);
+    border-radius: var(--radius-lg);
+    box-shadow: 0 12px 24px -4px rgba(0, 0, 0, 0.5);
+    width: 320px;
+    max-width: calc(100vw - 32px);
+    padding: 16px;
+    animation: fadeInScale 0.15s ease-out;
+}
+
+.popup-header {
+    display: flex;
+    justify-content: space-between;
+    align-items: center;
+    margin-bottom: 12px;
+    padding-bottom: 8px;
+    border-bottom: 1px solid var(--border-color);
+}
+
+.popup-term-wrap {
+    display: flex;
+    align-items: center;
+    gap: 8px;
+    flex-wrap: wrap;
+}
+
+.popup-term {
+    font-size: 18px;
+    color: var(--text-main);
+}
+
+.popup-phonetic {
+    font-size: 13px;
+    color: var(--primary);
+    font-family: monospace;
+}
+
+.popup-close-btn {
+    background: none;
+    border: none;
+    color: var(--text-dim);
+    font-size: 16px;
+    cursor: pointer;
+    padding: 4px;
+}
+
+.popup-close-btn:hover {
+    color: var(--text-main);
+}
+
+.popup-translation {
+    font-size: 15px;
+    font-weight: 600;
+    color: var(--success);
+    margin-bottom: 8px;
+}
+
+.popup-context {
+    font-size: 12px;
+    color: var(--text-muted);
+    font-style: italic;
+    background: var(--bg-input);
+    padding: 8px 10px;
+    border-radius: var(--radius-sm);
+    margin-bottom: 14px;
+    line-height: 1.4;
+    border-left: 3px solid var(--primary);
+}
+
+.popup-saved-badge {
+    text-align: center;
+    font-size: 13px;
+    font-weight: 600;
+    color: var(--success);
+    padding: 6px;
+}
+
+
 

app/static/index.html

@@ -67,6 +67,9 @@
             </div>
 
             <div class="nav-actions">
+                <button id="nav-reader-btn" class="btn btn-outline btn-sm" title="Интерактивная читалка и библиотека книг">
+                    <span>📚 Читалка</span>
+                </button>
                 <button id="srs-trainer-btn" class="btn btn-trainer" title="Интервальный тренажер (Flashcards, 4 варианта, диктант, ввод)">
                     <span class="trainer-icon">🎓</span>
                     <span class="trainer-text">Тренажёр SRS</span>
@@ -517,6 +520,92 @@
             </div>
         </section>
 
+        <!-- VIEW 3: Interactive Reader & Bookshelf View -->
+        <section id="reader-view" class="reader-view hidden">
+            <!-- Bookshelf View -->
+            <div id="bookshelf-container" class="bookshelf-container">
+                <div class="bookshelf-header">
+                    <div class="bookshelf-title-wrap">
+                        <h2>📚 Библиотека & Интерактивная Читалка</h2>
+                        <p class="subtitle">Читайте тексты и книги с мгновенным клик-переводом, озвучкой и авто-захватом контекста</p>
+                    </div>
+                    <div class="bookshelf-actions">
+                        <button id="add-text-btn" class="btn btn-outline">✏️ Вставить текст</button>
+                        <label for="book-file-input" class="btn btn-primary file-upload-label">
+                            📁 Загрузить EPUB / TXT
+                            <input type="file" id="book-file-input" accept=".epub,.txt,.md" style="display: none;">
+                        </label>
+                    </div>
+                </div>
+
+                <!-- Bookshelf Grid / Empty -->
+                <div id="bookshelf-empty" class="empty-state hidden">
+                    <div class="empty-icon">📖</div>
+                    <h3>Ваша библиотека пуста</h3>
+                    <p>Загрузите книгу в формате EPUB, текстовый файл TXT/MD или вставьте текст статьи, чтобы начать интерактивное чтение.</p>
+                </div>
+                <div id="bookshelf-grid" class="bookshelf-grid"></div>
+            </div>
+
+            <!-- Reading Interface (Active when a book is open) -->
+            <div id="reader-interface" class="reader-interface hidden">
+                <header class="reader-toolbar">
+                    <div class="reader-toolbar-left">
+                        <button id="reader-back-btn" class="btn btn-sm btn-outline">← Библиотека</button>
+                        <div class="reader-meta">
+                            <h3 id="reader-book-title" class="reader-title">Книга</h3>
+                            <span id="reader-book-author" class="reader-author">Автор</span>
+                        </div>
+                    </div>
+
+                    <div class="reader-toolbar-center">
+                        <button id="reader-prev-ch-btn" class="btn btn-xs btn-outline" title="Предыдущая глава">◀</button>
+                        <select id="reader-chapter-select" class="reader-select"></select>
+                        <button id="reader-next-ch-btn" class="btn btn-xs btn-outline" title="Следующая глава">▶</button>
+                    </div>
+
+                    <div class="reader-toolbar-right">
+                        <div class="font-controls">
+                            <button id="reader-font-dec-btn" class="btn btn-xs btn-outline" title="Уменьшить шрифт">A-</button>
+                            <button id="reader-font-inc-btn" class="btn btn-xs btn-outline" title="Увеличить шрифт">A+</button>
+                        </div>
+                        <button id="reader-toggle-highlight-btn" class="btn btn-xs btn-outline" title="Вкл/Выкл подсветку изучаемых слов">✨ Подсветка</button>
+                        <button id="reader-train-btn" class="btn btn-xs btn-trainer" title="Тренировать слова из этой книги">🎓 Слова книги</button>
+                    </div>
+                </header>
+
+                <!-- Reading Container -->
+                <div class="reader-scroll-area" id="reader-scroll-area">
+                    <div class="reader-content-body" id="reader-content-body">
+                        <!-- Interactive paragraphs dynamically rendered here -->
+                    </div>
+                </div>
+            </div>
+
+            <!-- Interactive Click-to-Translate Popup -->
+            <div id="reader-word-popup" class="reader-word-popup hidden">
+                <div class="popup-header">
+                    <div class="popup-term-wrap">
+                        <strong id="popup-term" class="popup-term">word</strong>
+                        <span id="popup-phonetic" class="popup-phonetic">/wɜːd/</span>
+                        <button id="popup-audio-btn" class="icon-btn audio-btn" title="Слушать произношение">🔊</button>
+                    </div>
+                    <button id="popup-close-btn" class="popup-close-btn">✕</button>
+                </div>
+                <div class="popup-body">
+                    <div id="popup-loading" class="popup-loading hidden">Переводим...</div>
+                    <div id="popup-content" class="popup-content">
+                        <div class="popup-translation" id="popup-translation">перевод</div>
+                        <div class="popup-context" id="popup-context">“Контекст из книги...”</div>
+                    </div>
+                </div>
+                <div class="popup-footer">
+                    <button id="popup-save-btn" class="btn btn-primary btn-sm btn-block">💾 Добавить в словарь</button>
+                    <div id="popup-saved-badge" class="popup-saved-badge hidden">✅ Сохранено в словарь!</div>
+                </div>
+            </div>
+        </section>
+
         <!-- Sticky Bulk Action Bar for Batch Selection Mode -->
         <div id="batch-action-bar" class="batch-action-bar hidden">
             <div class="batch-left">
@@ -800,6 +889,33 @@
                     <button type="submit" id="change-pwd-save-btn" class="btn btn-primary">Сохранить</button>
                 </div>
             </form>
+    <!-- Add Book Modal (Paste Text) -->
+    <div id="add-book-modal" class="modal-backdrop hidden">
+        <div class="modal-window">
+            <div class="modal-header">
+                <h3>✏️ Добавить текст или статью</h3>
+                <button id="close-add-book-modal-btn" class="icon-btn">✕</button>
+            </div>
+            <form id="add-book-form">
+                <div class="modal-body">
+                    <div class="form-group">
+                        <label for="book-title-input">Название книги / статьи *</label>
+                        <input type="text" id="book-title-input" class="input-styled" required placeholder="Например: Clean Code Principles">
+                    </div>
+                    <div class="form-group">
+                        <label for="book-author-input">Автор / Источник</label>
+                        <input type="text" id="book-author-input" class="input-styled" placeholder="Например: Robert C. Martin">
+                    </div>
+                    <div class="form-group">
+                        <label for="book-content-input">Текст материала (English) *</label>
+                        <textarea id="book-content-input" class="input-styled" rows="10" required placeholder="Вставьте английский текст книги, статьи или документации..."></textarea>
+                    </div>
+                </div>
+                <div class="modal-footer">
+                    <button type="button" id="cancel-add-book-btn" class="btn btn-outline">Отмена</button>
+                    <button type="submit" id="submit-add-book-btn" class="btn btn-primary">📚 Сохранить в библиотеку</button>
+                </div>
+            </form>
         </div>
     </div>
 

app/static/js/app.js

@@ -45,6 +45,8 @@ document.addEventListener('DOMContentLoaded', () => {
     const appShell = document.getElementById('app-shell');
     const dictionaryView = document.getElementById('dictionary-view');
     const srsView = document.getElementById('srs-view');
+    const readerView = document.getElementById('reader-view');
+    const navReaderBtn = document.getElementById('nav-reader-btn');
     const navBrandHome = document.getElementById('nav-brand-home');
     const themeToggle = document.getElementById('theme-toggle');
     const statTotal = document.getElementById('stat-total');
@@ -55,6 +57,53 @@ document.addEventListener('DOMContentLoaded', () => {
     const exportOpenBtn = document.getElementById('export-open-btn');
     const changePwdOpenBtn = document.getElementById('change-pwd-open-btn');
 
+    // Elements - Reader & Bookshelf
+    const bookshelfContainer = document.getElementById('bookshelf-container');
+    const bookshelfEmpty = document.getElementById('bookshelf-empty');
+    const bookshelfGrid = document.getElementById('bookshelf-grid');
+    const addTextBtn = document.getElementById('add-text-btn');
+    const bookFileInput = document.getElementById('book-file-input');
+    const addBookModal = document.getElementById('add-book-modal');
+    const closeAddBookModalBtn = document.getElementById('close-add-book-modal-btn');
+    const cancelAddBookBtn = document.getElementById('cancel-add-book-btn');
+    const addBookForm = document.getElementById('add-book-form');
+    const bookTitleInput = document.getElementById('book-title-input');
+    const bookAuthorInput = document.getElementById('book-author-input');
+    const bookContentInput = document.getElementById('book-content-input');
+
+    const readerInterface = document.getElementById('reader-interface');
+    const readerBackBtn = document.getElementById('reader-back-btn');
+    const readerBookTitle = document.getElementById('reader-book-title');
+    const readerBookAuthor = document.getElementById('reader-book-author');
+    const readerChapterSelect = document.getElementById('reader-chapter-select');
+    const readerPrevChBtn = document.getElementById('reader-prev-ch-btn');
+    const readerNextChBtn = document.getElementById('reader-next-ch-btn');
+    const readerFontDecBtn = document.getElementById('reader-font-dec-btn');
+    const readerFontIncBtn = document.getElementById('reader-font-inc-btn');
+    const readerToggleHighlightBtn = document.getElementById('reader-toggle-highlight-btn');
+    const readerTrainBtn = document.getElementById('reader-train-btn');
+    const readerContentBody = document.getElementById('reader-content-body');
+    const readerScrollArea = document.getElementById('reader-scroll-area');
+
+    const readerWordPopup = document.getElementById('reader-word-popup');
+    const popupTerm = document.getElementById('popup-term');
+    const popupPhonetic = document.getElementById('popup-phonetic');
+    const popupAudioBtn = document.getElementById('popup-audio-btn');
+    const popupCloseBtn = document.getElementById('popup-close-btn');
+    const popupLoading = document.getElementById('popup-loading');
+    const popupContent = document.getElementById('popup-content');
+    const popupTranslation = document.getElementById('popup-translation');
+    const popupContext = document.getElementById('popup-context');
+    const popupSaveBtn = document.getElementById('popup-save-btn');
+    const popupSavedBadge = document.getElementById('popup-saved-badge');
+
+    // Reader State
+    let currentBook = null;
+    let currentChapterIndex = 0;
+    let readerFontSize = 19;
+    let isHighlightEnabled = false;
+    let popupCurrentData = null;
+
     // Elements - Search & Capture
     const termInput = document.getElementById('term-input');
     const clearSearchBtn = document.getElementById('clear-search-btn');
@@ -891,19 +940,38 @@ document.addEventListener('DOMContentLoaded', () => {
         renderSrsCurrentCard();
     });
 
-    function openSrsView() {
-        dictionaryView.classList.add('hidden');
-        srsView.classList.remove('hidden');
-        startSrsTrainingSession(false);
-    }
-
-    function closeSrsView() {
+    function openDictionaryView() {
         srsView.classList.add('hidden');
+        if (readerView) readerView.classList.add('hidden');
         dictionaryView.classList.remove('hidden');
         loadInitialData();
     }
 
-    async function startSrsTrainingSession(forceAll = false) {
+    function openSrsView(tagFilter = null) {
+        dictionaryView.classList.add('hidden');
+        if (readerView) readerView.classList.add('hidden');
+        srsView.classList.remove('hidden');
+        startSrsTrainingSession(false, tagFilter);
+    }
+
+    function closeSrsView() {
+        srsView.classList.add('hidden');
+        if (readerView) readerView.classList.add('hidden');
+        dictionaryView.classList.remove('hidden');
+        loadInitialData();
+    }
+
+    function openReaderView() {
+        dictionaryView.classList.add('hidden');
+        srsView.classList.add('hidden');
+        if (readerView) readerView.classList.remove('hidden');
+        loadBookshelf();
+    }
+
+    navBrandHome.addEventListener('click', () => openDictionaryView());
+    if (navReaderBtn) navReaderBtn.addEventListener('click', () => openReaderView());
+
+    async function startSrsTrainingSession(forceAll = false, tagFilter = null) {
         srsLoading.classList.remove('hidden');
         srsEmpty.classList.add('hidden');
         srsSummary.classList.add('hidden');
@@ -914,9 +982,12 @@ document.addEventListener('DOMContentLoaded', () => {
 
         let queue = [];
         try {
-            const url = forceAll 
+            let url = forceAll 
                 ? `/api/srs/queue?limit=50` 
                 : `/api/srs/queue?limit=25&mix=${srsSmartMix}`;
+            if (tagFilter) {
+                url += `&tag=${encodeURIComponent(tagFilter)}`;
+            }
             const resp = await fetch(url);
             if (resp.ok) {
                 const data = await resp.json();
@@ -1431,7 +1502,11 @@ document.addEventListener('DOMContentLoaded', () => {
                 kpiTotalWords.textContent = s.total_cards;
                 kpiTodayAdded.textContent = `Сегодня добавлено: +${s.today_added}`;
 
-                // CEFR Level estimation
+                // Strict CEFR Level estimation (PLAN.md 4.3)
+                if (s.cefr) {
+                    kpiCefrLevel.textContent = s.cefr.level;
+                    kpiCefrDesc.textContent = `${s.cefr.title} • ${s.cefr.message}`;
+                } else {
                     const count = s.total_cards;
                     let lvl = 'A1';
                     let desc = 'Базовый словарный запас';
@@ -1439,9 +1514,9 @@ document.addEventListener('DOMContentLoaded', () => {
                     else if (count >= 1200) { lvl = 'B2'; desc = 'Уверенное чтение тех. документации'; }
                     else if (count >= 600) { lvl = 'B1'; desc = 'Понимание общих и рабочих тем'; }
                     else if (count >= 200) { lvl = 'A2'; desc = 'Элементарный словарный запас'; }
-
                     kpiCefrLevel.textContent = lvl;
                     kpiCefrDesc.textContent = desc;
+                }
 
                 // Mastery Progress Bar
                 cntMastered.textContent = s.mastered;
@@ -1669,6 +1744,492 @@ document.addEventListener('DOMContentLoaded', () => {
         }
     });
 
+    // =======================================================================
+    // STAGE 5: Interactive Reader & Bookshelf Implementation
+    // =======================================================================
+
+    function slugify(text) {
+        if (!text) return 'book';
+        return text.toString().toLowerCase().trim()
+            .replace(/[^\w\s-]/g, '')
+            .replace(/[\s_-]+/g, '-')
+            .replace(/^-+|-+$/g, '');
+    }
+
+    async function loadBookshelf() {
+        if (!bookshelfContainer) return;
+        bookshelfContainer.classList.remove('hidden');
+        if (readerInterface) readerInterface.classList.add('hidden');
+        if (bookshelfGrid) bookshelfGrid.innerHTML = '';
+        if (bookshelfEmpty) bookshelfEmpty.classList.add('hidden');
+
+        try {
+            const resp = await fetch('/api/books');
+            if (resp.ok) {
+                const books = await resp.json();
+                if (!books || books.length === 0) {
+                    if (bookshelfEmpty) bookshelfEmpty.classList.remove('hidden');
+                } else {
+                    renderBookshelf(books);
+                }
+            }
+        } catch (e) {
+            console.error('Error loading bookshelf:', e);
+        }
+    }
+
+    function renderBookshelf(books) {
+        if (!bookshelfGrid) return;
+        bookshelfGrid.innerHTML = '';
+        books.forEach(b => {
+            const card = document.createElement('div');
+            card.className = 'book-card';
+
+            const totalCh = b.chapters_count || 1;
+            const currentCh = (b.current_chapter || 0) + 1;
+            const pct = Math.min(100, Math.round((currentCh / totalCh) * 100));
+
+            card.innerHTML = `
+                <div>
+                    <div class="book-card-top">
+                        <div class="book-cover-icon">${b.source_type === 'epub' ? '📕' : '📄'}</div>
+                        <div class="book-card-info">
+                            <h4 class="book-card-title" title="${escapeHtml(b.title)}">${escapeHtml(b.title)}</h4>
+                            <p class="book-card-author">${escapeHtml(b.author || 'Неизвестный автор')}</p>
+                            <div class="book-card-badges">
+                                <span class="badge-format">${escapeHtml(b.source_type)}</span>
+                                <span class="badge-words">${b.total_words ? b.total_words.toLocaleString() + ' слов' : ''}</span>
+                            </div>
+                        </div>
+                    </div>
+                    <div class="book-progress-wrap">
+                        <div class="book-progress-labels">
+                            <span>Глава ${currentCh} из ${totalCh}</span>
+                            <span>${pct}%</span>
+                        </div>
+                        <div class="book-progress-bar-bg">
+                            <div class="book-progress-bar-fill" style="width: ${pct}%"></div>
+                        </div>
+                    </div>
+                </div>
+                <div class="book-card-actions">
+                    <button class="btn btn-primary btn-sm read-book-btn" data-id="${b.id}">📖 Читать</button>
+                    <button class="btn btn-outline btn-xs train-book-btn" data-title="${escapeHtml(b.title)}" title="Тренировать слова из этой книги">🎓 Слова книги</button>
+                    <button class="icon-btn delete-book-btn" data-id="${b.id}" title="Удалить книгу">🗑️</button>
+                </div>
+            `;
+
+            card.querySelector('.read-book-btn').addEventListener('click', () => openBook(b.id));
+            card.querySelector('.train-book-btn').addEventListener('click', () => {
+                const bookTag = slugify(b.title);
+                openSrsView(bookTag);
+            });
+            card.querySelector('.delete-book-btn').addEventListener('click', async () => {
+                if (confirm(`Удалить книгу "${b.title}" из библиотеки?`)) {
+                    await fetch(`/api/books/${b.id}`, { method: 'DELETE' });
+                    loadBookshelf();
+                }
+            });
+
+            bookshelfGrid.appendChild(card);
+        });
+    }
+
+    async function openBook(bookId) {
+        try {
+            const resp = await fetch(`/api/books/${bookId}`);
+            if (!resp.ok) return alert('Не удалось открыть книгу');
+            currentBook = await resp.json();
+            currentChapterIndex = currentBook.current_chapter || 0;
+
+            readerBookTitle.textContent = currentBook.title;
+            readerBookAuthor.textContent = currentBook.author || '';
+
+            // Populate chapter selector
+            readerChapterSelect.innerHTML = '';
+            const chapters = currentBook.chapters || [];
+            chapters.forEach((ch, idx) => {
+                const opt = document.createElement('option');
+                opt.value = idx;
+                opt.textContent = ch.title || `Глава ${idx + 1}`;
+                readerChapterSelect.appendChild(opt);
+            });
+
+            bookshelfContainer.classList.add('hidden');
+            readerInterface.classList.remove('hidden');
+
+            renderChapter(currentChapterIndex);
+        } catch (e) {
+            console.error('Error opening book:', e);
+        }
+    }
+
+    function renderChapter(index) {
+        if (!currentBook || !currentBook.chapters) return;
+        currentChapterIndex = Math.max(0, Math.min(index, currentBook.chapters.length - 1));
+        readerChapterSelect.value = currentChapterIndex;
+
+        readerPrevChBtn.disabled = currentChapterIndex <= 0;
+        readerNextChBtn.disabled = currentChapterIndex >= currentBook.chapters.length - 1;
+
+        const chapter = currentBook.chapters[currentChapterIndex] || { title: '', content: '' };
+        readerContentBody.innerHTML = '';
+
+        if (chapter.title) {
+            const h = document.createElement('h2');
+            h.textContent = chapter.title;
+            readerContentBody.appendChild(h);
+        }
+
+        // Map existing user vocabulary for status marking
+        const knownWordsMap = new Map();
+        allCards.forEach(c => {
+            if (c.term) knownWordsMap.set(c.term.trim().toLowerCase(), c);
+        });
+
+        // Split content into paragraphs
+        const paragraphs = chapter.content.split(/\n\s*\n/);
+        paragraphs.forEach(paraText => {
+            paraText = paraText.trim();
+            if (!paraText) return;
+
+            const p = document.createElement('p');
+            // Tokenize words while preserving spaces & punctuation
+            const tokens = paraText.split(/([A-Za-z0-9'-]+)/);
+            tokens.forEach(token => {
+                if (/^[A-Za-z0-9'-]+$/.test(token) && token.length > 1) {
+                    const span = document.createElement('span');
+                    span.className = 'reader-word';
+                    span.dataset.word = token;
+                    span.textContent = token;
+
+                    const lower = token.toLowerCase();
+                    if (knownWordsMap.has(lower)) {
+                        const card = knownWordsMap.get(lower);
+                        span.classList.add(card.srs_state === 'mastered' ? 'status-mastered' : 'status-learning');
+                    }
+                    if (isHighlightEnabled) {
+                        span.classList.add('highlight-enabled');
+                    }
+
+                    span.addEventListener('click', (e) => {
+                        e.stopPropagation();
+                        handleWordClick(token, paraText, span);
+                    });
+
+                    p.appendChild(span);
+                } else {
+                    p.appendChild(document.createTextNode(token));
+                }
+            });
+
+            readerContentBody.appendChild(p);
+        });
+
+        if (readerScrollArea) readerScrollArea.scrollTop = 0;
+
+        // Save progress to server
+        fetch(`/api/books/${currentBook.id}/progress`, {
+            method: 'PUT',
+            headers: { 'Content-Type': 'application/json' },
+            body: JSON.stringify({ current_chapter: currentChapterIndex, current_position: 0 }),
+        }).catch(err => console.log('Progress save error:', err));
+    }
+
+    // Extract cleanest surrounding sentence for context
+    function extractContextSentence(fullText, word) {
+        if (!fullText) return '';
+        const re = new RegExp(`([^.!?\\n]*?\\b${escapeRegex(word)}\\b[^.!?\\n]*[.!?]?)`, 'i');
+        const m = fullText.match(re);
+        if (m && m[1]) return m[1].trim();
+        return fullText.slice(0, 160).trim();
+    }
+
+    async function handleWordClick(word, paragraphText, targetElement) {
+        const sentence = extractContextSentence(paragraphText, word);
+        openWordPopup(word, sentence, targetElement);
+    }
+
+    async function openWordPopup(term, contextSentence, targetElement) {
+        popupCurrentData = {
+            term: term,
+            contextSentence: contextSentence,
+            targetElement: targetElement,
+        };
+
+        popupTerm.textContent = term;
+        popupPhonetic.textContent = '';
+        popupTranslation.textContent = '';
+        popupContext.textContent = contextSentence ? `“${contextSentence}”` : '';
+        popupLoading.classList.remove('hidden');
+        popupContent.classList.add('hidden');
+        popupSavedBadge.classList.add('hidden');
+        popupSaveBtn.classList.remove('hidden');
+        popupSaveBtn.disabled = false;
+
+        // Position popup near target element
+        readerWordPopup.classList.remove('hidden');
+        if (targetElement) {
+            const rect = targetElement.getBoundingClientRect();
+            let top = rect.bottom + window.scrollY + 6;
+            let left = rect.left + window.scrollX;
+
+            const popupWidth = 320;
+            if (left + popupWidth > window.innerWidth - 16) {
+                left = window.innerWidth - popupWidth - 16;
+            }
+            if (left < 16) left = 16;
+
+            readerWordPopup.style.top = `${top}px`;
+            readerWordPopup.style.left = `${left}px`;
+        }
+
+        try {
+            const resp = await fetch(`/api/lookup?q=${encodeURIComponent(term)}`);
+            if (resp.ok) {
+                const data = await resp.json();
+                popupCurrentData.lookup = data;
+
+                popupPhonetic.textContent = data.phonetic || '';
+                popupTranslation.textContent = data.translation_ru || 'Перевод не найден';
+                popupLoading.classList.add('hidden');
+                popupContent.classList.remove('hidden');
+
+                if (data.audio_url) {
+                    popupAudioBtn.classList.remove('hidden');
+                    popupAudioBtn.onclick = () => playAudio(data.audio_url);
+                } else {
+                    popupAudioBtn.classList.add('hidden');
+                }
+            } else {
+                popupTranslation.textContent = 'Ошибка перевода';
+                popupLoading.classList.add('hidden');
+                popupContent.classList.remove('hidden');
+            }
+        } catch (e) {
+            console.error('Popup lookup error:', e);
+            popupTranslation.textContent = 'Сетевая ошибка';
+            popupLoading.classList.add('hidden');
+            popupContent.classList.remove('hidden');
+        }
+    }
+
+    if (popupCloseBtn) {
+        popupCloseBtn.addEventListener('click', () => {
+            readerWordPopup.classList.add('hidden');
+        });
+    }
+
+    document.addEventListener('click', (e) => {
+        if (readerWordPopup && !readerWordPopup.contains(e.target) && !e.target.classList.contains('reader-word')) {
+            readerWordPopup.classList.add('hidden');
+        }
+    });
+
+    if (popupSaveBtn) {
+        popupSaveBtn.addEventListener('click', async () => {
+            if (!popupCurrentData) return;
+            const d = popupCurrentData;
+            const lookup = d.lookup || {};
+            const bookTag = currentBook ? slugify(currentBook.title) : 'reader';
+
+            const payload = {
+                term: d.term,
+                translation: lookup.translation_ru || popupTranslation.textContent,
+                context_sentence: d.contextSentence || '',
+                phonetic: lookup.phonetic || '',
+                audio_url: lookup.audio_url || '',
+                part_of_speech: lookup.part_of_speech || '',
+                definition_en: lookup.definition_en || '',
+                collection: 'Книги & Сериалы',
+                tags: `${bookTag}, reader`,
+                notes: currentBook ? `Из книги: ${currentBook.title}` : '',
+            };
+
+            try {
+                const resp = await fetch('/api/cards', {
+                    method: 'POST',
+                    headers: { 'Content-Type': 'application/json' },
+                    body: JSON.stringify(payload),
+                });
+
+                if (resp.ok) {
+                    popupSaveBtn.classList.add('hidden');
+                    popupSavedBadge.classList.remove('hidden');
+
+                    if (d.targetElement) {
+                        d.targetElement.classList.add('status-learning');
+                        if (isHighlightEnabled) d.targetElement.classList.add('highlight-enabled');
+                    }
+
+                    await fetchCards();
+                    await fetchTags();
+                } else {
+                    alert('Не удалось сохранить слово');
+                }
+            } catch (e) {
+                console.error('Save card from reader error:', e);
+            }
+        });
+    }
+
+    // Phrase/Chunk Selection in Reader
+    if (readerContentBody) {
+        readerContentBody.addEventListener('mouseup', () => {
+            const sel = window.getSelection();
+            const text = sel.toString().trim();
+            if (text && text.split(/\s+/).length >= 2 && text.length <= 80) {
+                const range = sel.getRangeAt(0);
+                const rect = range.getBoundingClientRect();
+                openWordPopup(text, text, {
+                    getBoundingClientRect: () => rect,
+                });
+            }
+        });
+    }
+
+    // Chapter Navigation & Reader Toolbar
+    if (readerChapterSelect) {
+        readerChapterSelect.addEventListener('change', () => {
+            renderChapter(parseInt(readerChapterSelect.value, 10));
+        });
+    }
+
+    if (readerPrevChBtn) {
+        readerPrevChBtn.addEventListener('click', () => {
+            if (currentChapterIndex > 0) renderChapter(currentChapterIndex - 1);
+        });
+    }
+
+    if (readerNextChBtn) {
+        readerNextChBtn.addEventListener('click', () => {
+            if (currentBook && currentChapterIndex < currentBook.chapters.length - 1) {
+                renderChapter(currentChapterIndex + 1);
+            }
+        });
+    }
+
+    if (readerBackBtn) {
+        readerBackBtn.addEventListener('click', () => {
+            readerInterface.classList.add('hidden');
+            bookshelfContainer.classList.remove('hidden');
+            loadBookshelf();
+        });
+    }
+
+    if (readerFontIncBtn) {
+        readerFontIncBtn.addEventListener('click', () => {
+            if (readerFontSize < 28) {
+                readerFontSize += 2;
+                readerContentBody.style.fontSize = `${readerFontSize}px`;
+            }
+        });
+    }
+
+    if (readerFontDecBtn) {
+        readerFontDecBtn.addEventListener('click', () => {
+            if (readerFontSize > 14) {
+                readerFontSize -= 2;
+                readerContentBody.style.fontSize = `${readerFontSize}px`;
+            }
+        });
+    }
+
+    if (readerToggleHighlightBtn) {
+        readerToggleHighlightBtn.addEventListener('click', () => {
+            isHighlightEnabled = !isHighlightEnabled;
+            readerToggleHighlightBtn.classList.toggle('btn-primary', isHighlightEnabled);
+            readerContentBody.querySelectorAll('.reader-word').forEach(w => {
+                w.classList.toggle('highlight-enabled', isHighlightEnabled);
+            });
+        });
+    }
+
+    if (readerTrainBtn) {
+        readerTrainBtn.addEventListener('click', () => {
+            if (currentBook) {
+                const bookTag = slugify(currentBook.title);
+                openSrsView(bookTag);
+            }
+        });
+    }
+
+    // Bookshelf Add/Upload Actions
+    if (addTextBtn) {
+        addTextBtn.addEventListener('click', () => {
+            addBookForm.reset();
+            addBookModal.classList.remove('hidden');
+        });
+    }
+
+    if (closeAddBookModalBtn) closeAddBookModalBtn.addEventListener('click', () => addBookModal.classList.add('hidden'));
+    if (cancelAddBookBtn) cancelAddBookBtn.addEventListener('click', () => addBookModal.classList.add('hidden'));
+
+    if (addBookForm) {
+        addBookForm.addEventListener('submit', async (e) => {
+            e.preventDefault();
+            const title = bookTitleInput.value.trim();
+            const author = bookAuthorInput.value.trim();
+            const content = bookContentInput.value.trim();
+
+            if (!title || !content) return;
+
+            try {
+                const resp = await fetch('/api/books', {
+                    method: 'POST',
+                    headers: { 'Content-Type': 'application/json' },
+                    body: JSON.stringify({
+                        title: title,
+                        author: author,
+                        content: content,
+                        source_type: 'text',
+                    }),
+                });
+
+                if (resp.ok) {
+                    const book = await resp.json();
+                    addBookModal.classList.add('hidden');
+                    await loadBookshelf();
+                    openBook(book.id);
+                } else {
+                    alert('Ошибка при сохранении книги');
+                }
+            } catch (err) {
+                console.error('Book create error:', err);
+            }
+        });
+    }
+
+    if (bookFileInput) {
+        bookFileInput.addEventListener('change', async () => {
+            const file = bookFileInput.files[0];
+            if (!file) return;
+
+            const formData = new FormData();
+            formData.append('file', file);
+
+            try {
+                const resp = await fetch('/api/books', {
+                    method: 'POST',
+                    body: formData,
+                });
+
+                if (resp.ok) {
+                    const book = await resp.json();
+                    bookFileInput.value = '';
+                    await loadBookshelf();
+                    openBook(book.id);
+                } else {
+                    const errData = await resp.json();
+                    alert(`Ошибка загрузки: ${errData.detail || 'Не удалось обработать файл'}`);
+                }
+            } catch (e) {
+                console.error('File upload error:', e);
+                alert('Ошибка сети при загрузке файла');
+            }
+        });
+    }
+
     // -----------------------------------------------------------------------
     // Utility helpers
     // -----------------------------------------------------------------------

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)
+
+
+