abort+chaptertitle+dashboardupgrade

bookscraper/README.md

@@ -130,3 +130,7 @@ docker builder prune -af
 docker volume prune -f
 docker compose build --no-cache
 docker compose up
+
+docker compose down
+docker compose build
+docker compose up

bookscraper/app.py

@@ -111,14 +111,6 @@ def progress(book_id):
     return jsonify(get_progress(book_id))
 
 
-# =====================================================
-# LOGS — GLOBAL UI LOGS
-# =====================================================
-@app.route("/logs", methods=["GET"])
-def logs():
-    return jsonify({"logs": get_ui_logs()})
-
-
 # =====================================================
 # CELERY RESULT → return book_id
 # =====================================================
@@ -215,11 +207,12 @@ def api_book_logs(book_id):
 # =====================================================
 @app.route("/dashboard")
 def dashboard():
+    logs_list = get_ui_logs() or []
     # ★ FIX: dashboard moet altijd books + logs krijgen
     return render_template(
         "dashboard/dashboard.html",
         books=list_active_books(),
-        logs=get_ui_logs(),
+        logs=logs_list,  # dashboard krijgt LIST, geen dict
     )
 
 
@@ -255,6 +248,34 @@ def debug_redis_keys():
     return jsonify(results)
 
 
+# ============================================================
+# Rolling log endpoint (no new file)
+# ============================================================
+
+from flask import jsonify, request
+
+# =====================================================
+# ROLLING LOG ENDPOINT — DELTA POLLING VIA ui_log
+# =====================================================
+from scraper.ui_log import get_ui_logs_delta
+
+
+@app.route("/logs", methods=["GET"])
+def logs():
+    """
+    Delta log delivery for WebGUI.
+    Browser sends ?last_index=N, we return only new lines.
+    """
+    try:
+        last_index = int(request.args.get("last_index", -1))
+    except:
+        last_index = -1
+
+    new_lines, total = get_ui_logs_delta(last_index)
+
+    return jsonify({"lines": new_lines, "total": total})
+
+
 # =====================================================
 # RUN FLASK
 # =====================================================

bookscraper/logbus/publisher.py

@@ -27,3 +27,32 @@ def log(message: str):
         push_ui(message)
     except Exception:
         pass
+
+
+# ============================================================
+# Delta-based log retrieval using Redis indexes
+# ============================================================
+
+
+def get_ui_logs_delta(last_index: int):
+    """
+    Returns (new_lines, total_count)
+    Only returns log lines AFTER last_index.
+
+    Example:
+        last_index = 10 → returns logs with Redis indexes 11..end
+    """
+    # Determine total lines in buffer
+    total = r.llen(UI_LOG_KEY)
+
+    if total == 0:
+        return [], 0
+
+    # First load OR index invalid → send entire buffer
+    if last_index < 0 or last_index >= total:
+        logs = r.lrange(UI_LOG_KEY, 0, -1)
+        return logs, total
+
+    # Only new lines:
+    new_lines = r.lrange(UI_LOG_KEY, last_index + 1, -1)
+    return new_lines, total

bookscraper/scraper/tasks/controller_tasks.py

@@ -13,6 +13,9 @@ from scraper.download_controller import DownloadController
 from scraper.progress import (
     set_total,
 )
+from urllib.parse import urlparse
+import redis
+import os
 from scraper.abort import abort_requested
 
 print(">>> [IMPORT] controller_tasks.py loaded")
@@ -31,8 +34,30 @@ def launch_downloads(self, book_id: str, scrape_result: dict):
     title = scrape_result.get("title", "UnknownBook")
     chapters = scrape_result.get("chapters", []) or []
     total = len(chapters)
+    # ------------------------------------------------------------
+    # INIT BOOK STATE MODEL (required for Active Books dashboard)
+    # ------------------------------------------------------------
+
+    broker_url = os.getenv("REDIS_BROKER", "redis://redis:6379/0")
+    parsed = urlparse(broker_url)
+
+    state = redis.Redis(
+        host=parsed.hostname,
+        port=parsed.port,
+        db=int(parsed.path.strip("/")),
+        decode_responses=True,
+    )
+
+    # Book metadata
+    state.set(f"book:{book_id}:title", title)
+    state.set(f"book:{book_id}:status", "starting")
+
+    # Download counters
+    state.set(f"book:{book_id}:download:total", total)
+    state.set(f"book:{book_id}:download:done", 0)
 
-    log(f"[CTRL] Book '{title}' → {total} chapters (book_id={book_id})")
+    # Audio counters (start at zero)
+    state.set(f"book:{book_id}:audio:done", 0)
 
     # ------------------------------------------------------------
     # INIT PROGRESS

bookscraper/scraper/tasks/parse_tasks.py

@@ -26,11 +26,10 @@ def parse_chapter(self, download_result: dict):
     book_id = download_result.get("book_id", "NOBOOK")
     chapter_dict = download_result.get("chapter") or {}
     book_meta = download_result.get("book_meta") or {}
-
+    chapter_title = chapter_dict.get("title")
     chapter_num = chapter_dict.get("num")
     chapter_url = chapter_dict.get("url")
     html = download_result.get("html")
-
     # ------------------------------------------------------------
     # SKIPPED DOWNLOAD → SKIP PARSE
     # ------------------------------------------------------------
@@ -127,9 +126,8 @@ def parse_chapter(self, download_result: dict):
         else:
             prev_blank = False
             cleaned.append(stripped)
-
     text = "\n".join(cleaned)
-
+    text = chapter_title + "\n" + text
     # ------------------------------------------------------------
     # Add header to chapter 1
     # ------------------------------------------------------------

bookscraper/scraper/ui_log.py

@@ -44,3 +44,31 @@ def reset_ui_logs():
       - Auto-clear when new book scraping starts
     """
     r.delete(UI_LOG_KEY)
+
+
+# ============================================================
+# Delta-based log retrieval using Redis indexes
+# ============================================================
+
+
+def get_ui_logs_delta(last_index: int):
+    """
+    Returns (new_lines, total_count).
+    Only returns log lines AFTER last_index.
+
+    Example:
+        last_index = 10 → returns logs with Redis indexes 11..end
+    """
+    total = r.llen(UI_LOG_KEY)
+
+    if total == 0:
+        return [], 0
+
+    # First load OR index invalid → send entire buffer
+    if last_index < 0 or last_index >= total:
+        logs = r.lrange(UI_LOG_KEY, 0, -1)
+        return logs, total
+
+    # Only new logs
+    new_lines = r.lrange(UI_LOG_KEY, last_index + 1, -1)
+    return new_lines, total

bookscraper/static/css/dashboard.css

@@ -186,40 +186,41 @@
   white-space: pre-wrap; /* wraps text */
   word-break: break-word; /* lange links breken */
 }
-
+/* Basestijl voor alle logregels */
 .log-line {
   white-space: pre-wrap;
   padding: 2px 0;
+  font-family: "SF Mono", "Consolas", "Courier New", monospace;
 }
 
-.log-empty {
-  color: #888;
-  font-style: italic;
-}
-.log-line {
-  color: #00ff66;
+/* Subklassen per logtype */
+.log-line.default {
+  color: #00ff66; /* groen */
 }
 
-.log-line:has([DL]),
-.log-line:has([DOWNLOAD]) {
+.log-line.dl {
   color: #00ccff; /* cyan */
 }
 
-.log-line:has([PARSE]) {
-  color: #ffaa00;
-} /* orange */
-.log-line:has([SAVE]) {
-  color: #ffdd33;
+.log-line.parse {
+  color: #ffaa00; /* oranje */
+}
+
+.log-line.save {
+  color: #ffdd33; /* geel */
 }
-.log-line:has([AUDIO]) {
-  color: #ff66ff;
-} /* purple */
-.log-line:has([CTRL]) {
-  color: #66aaff;
+
+.log-line.audio {
+  color: #ff66ff; /* paars */
+}
+
+.log-line.ctrl {
+  color: #66aaff; /* lichtblauw */
+}
+
+.log-line.error {
+  color: #ff3333; /* rood */
 }
-.log-line:has([ERROR]) {
-  color: #ff3333;
-} /* red for errors */
 
 /* ------------------------------
    PLACEHOLDER
@@ -239,3 +240,23 @@
   font-size: 12px;
   border-top: 1px solid #ddd;
 }
+.book-abort-area {
+  margin-top: 10px;
+  text-align: right;
+}
+
+.abort-btn {
+  padding: 6px 12px;
+  border-radius: 4px;
+  border: 1px solid #cc0000;
+  background: #ff4444;
+  color: white;
+  font-size: 12px;
+  cursor: pointer;
+  transition: background 0.2s, border-color 0.2s;
+}
+
+.abort-btn:hover {
+  background: #ff2222;
+  border-color: #aa0000;
+}

bookscraper/static/js/dashboard.js

@@ -104,6 +104,41 @@ function selectBook(bookId) {
   // Immediate refresh
   refreshBook(ACTIVE_BOOK);
 }
+setInterval(refreshActiveBooks, 2000);
+async function refreshActiveBooks() {
+  const books = await apiGet("/api/books");
+  if (!books) return;
+
+  const container = $("#book-list");
+  if (!container) return;
+
+  // Herbouw de lijst
+  container.innerHTML = "";
+  books.forEach((b) => {
+    const div = document.createElement("div");
+    div.className = "book-list-item";
+    div.dataset.bookId = b.book_id;
+
+    div.innerHTML = `
+      <div class="book-title">${b.title}</div>
+      <div class="book-status">${b.status}</div>
+      <div class="book-progress">
+        ${b.download_done}/${b.download_total} downloaded,
+        ${b.audio_done}/${b.audio_total} audio
+      </div>
+    `;
+
+    // Event listener opnieuw koppelen
+    div.addEventListener("click", () => selectBook(b.book_id));
+
+    container.appendChild(div);
+  });
+
+  // Als ACTIVE_BOOK nog niet bekend → auto-selecteer eerste boek
+  if (!ACTIVE_BOOK && books.length > 0) {
+    selectBook(books[0].book_id);
+  }
+}
 
 /* ---------------------------------------------------------
    Fetch logs + progress from API
@@ -148,3 +183,16 @@ function updateLogs(logList) {
 
   autoScroll(output);
 }
+
+function abortBook(book_id) {
+  if (!confirm(`Abort tasks for book ${book_id}?`)) return;
+
+  fetch(`/abort/${book_id}`, { method: "POST" })
+    .then((r) => r.json())
+    .then((data) => {
+      console.log("Abort:", data);
+    })
+    .catch((err) => {
+      console.error("Abort failed:", err);
+    });
+}

bookscraper/static/js/log_view.js

@@ -5,7 +5,8 @@
          - filtering
          - clearing
          - auto-scroll
-         - refresh support for dashboard polling
+         - delta polling (efficient)
+         - rolling limit (prevent GUI freeze)
    ======================================================================= */
 
 console.log(">>> log_view.js LOADING…");
@@ -14,6 +15,8 @@ console.log(">>> log_view.js LOADING…");
    Log filtering
    --------------------------------------------------------- */
 let LOG_FILTER = "ALL";
+let LAST_LOG_INDEX = -1; // For delta polling
+const MAX_LOG_LINES = 2000; // Rolling cap to prevent freezing
 
 function applyLogFilter() {
   console.log(">>> log_view.js applyLogFilter(), filter =", LOG_FILTER);
@@ -56,32 +59,74 @@ document.addEventListener("DOMContentLoaded", () => {
   if (clearBtn) {
     clearBtn.addEventListener("click", () => {
       console.log(">>> log_view.js log-clear clicked → clearing output");
-      if (output) output.innerHTML = "";
+      if (output) {
+        output.innerHTML = "";
+        LAST_LOG_INDEX = -1; // reset delta polling
+      }
     });
   }
 });
 
 /* ---------------------------------------------------------
-   Append a line to the log output
+   Append + Rolling buffer
    --------------------------------------------------------- */
 function logAppend(lineText) {
   const output = $("#log-output");
+  if (!output) return;
 
-  if (!output) {
-    console.log(">>> log_view.js logAppend() SKIPPED — no #log-output");
-    return;
+  const div = document.createElement("div");
+  div.classList.add("log-line");
+
+  // -----------------------------------------------------
+  // Assign subtype classes
+  // -----------------------------------------------------
+  if (lineText.includes("[DL]") || lineText.includes("[DOWNLOAD]")) {
+    div.classList.add("dl");
+  } else if (lineText.includes("[PARSE]")) {
+    div.classList.add("parse");
+  } else if (lineText.includes("[SAVE]")) {
+    div.classList.add("save");
+  } else if (lineText.includes("[AUDIO]")) {
+    div.classList.add("audio");
+  } else if (lineText.includes("[CTRL]")) {
+    div.classList.add("ctrl");
+  } else if (lineText.includes("[ERROR]")) {
+    div.classList.add("error");
+  } else {
+    div.classList.add("default");
   }
 
-  console.log(">>> log_view.js logAppend():", lineText);
-
-  const div = document.createElement("div");
-  div.className = "log-line";
   div.innerText = lineText;
-
   output.appendChild(div);
 
+  // Rolling buffer
+  while (output.children.length > MAX_LOG_LINES) {
+    output.removeChild(output.firstChild);
+  }
+
   applyLogFilter();
   autoScroll(output);
 }
 
+/* ---------------------------------------------------------
+   Delta-based log polling
+   --------------------------------------------------------- */
+function pollLogs() {
+  fetch(`/logs?last_index=${LAST_LOG_INDEX}`)
+    .then((r) => r.json())
+    .then((data) => {
+      const lines = data.lines || [];
+      if (lines.length > 0) {
+        lines.forEach((line) => logAppend(line));
+        LAST_LOG_INDEX = data.total - 1;
+      }
+    })
+    .catch((err) => {
+      console.warn(">>> log_view.js pollLogs() error:", err);
+    });
+}
+
+// Poll every 800 ms
+setInterval(pollLogs, 800);
+
 console.log(">>> log_view.js LOADED");

bookscraper/templates/components/book_list_item.html

@@ -58,4 +58,11 @@
       <span class="mini-value">{{ pct_au }}%</span>
     </div>
   </div>
+  {% if book.status in ["running", "active", "processing"] %}
+  <div class="book-abort-area">
+    <button class="abort-btn" onclick="abortBook('{{ book.book_id }}')">
+      Abort
+    </button>
+  </div>
+  {% endif %}
 </div>

bookscraper/templates/components/nav.html

@@ -17,7 +17,7 @@
       </li>
 
       <li>
-        <a href="/active" class="nav-item"> Active Books </a>
+        <a href="/api/books" class="nav-item"> Active Books </a>
       </li>
 
       <li>

bookscraper/templates/dashboard/dashboard.html

@@ -29,12 +29,12 @@
     <h2>Actieve boeken</h2>
 
     {% if books and books|length > 0 %}
-    <div class="book-list">
+    <div id="book-list" class="book-list">
       {% for book in books %} {% include "components/book_list_item.html" %} {%
       endfor %}
     </div>
     {% else %}
-    <div class="book-list-empty">Geen actieve boeken.</div>
+    <div id="book-list" class="book-list-empty">Geen actieve boeken.</div>
     {% endif %}
   </section>