Redis State Model changes

bookscraper/scraper/download_controller.py

@@ -5,6 +5,7 @@
 #   and pass book_id for abort/progress/log functionality.
 #   + Download and replicate cover image to all volume folders
 #   + Generate scripts (allinone.txt, makebook, say)
+#   + Initialize Redis Book State Model (status + counters)
 # =========================================================
 
 from celery import group
@@ -16,6 +17,13 @@ import requests
 import shutil
 from scraper.abort import abort_requested  # DEBUG allowed
 
+# NEW: Redis State Model (C&U)
+from scraper.progress import (
+    init_book_state,
+    set_status,
+    set_chapter_total,
+)
+
 
 class DownloadController:
     """
@@ -26,6 +34,7 @@ class DownloadController:
       - book_id-based abort + progress tracking
       - cover download + volume replication
       - script generation (allinone.txt, makebook, say)
+      - Redis book state initialisation and status updates
     """
 
     def __init__(self, book_id: str, scrape_result: dict):
@@ -66,6 +75,20 @@ class DownloadController:
         except Exception as e:
             log(f"[CTRL_DEBUG] abort_requested ERROR: {e}")
 
+        # -------------------------------------------------
+        # NEW: Initialize Redis Book State Model
+        # -------------------------------------------------
+        try:
+            init_book_state(
+                book_id=self.book_id,
+                title=self.title,
+                url=self.scrape_result.get("book_url"),
+                chapters_total=len(self.chapters),
+            )
+            log(f"[CTRL_STATE] init_book_state() completed for {self.title}")
+        except Exception as e:
+            log(f"[CTRL_STATE] init_book_state FAILED: {e}")
+
     # ---------------------------------------------------------
     # Cover Download
     # ---------------------------------------------------------
@@ -144,6 +167,16 @@ class DownloadController:
         )
         log(f"[CTRL] Output root: {self.book_base}")
 
+        # -------------------------------------
+        # NEW: Redis state update
+        # -------------------------------------
+        try:
+            set_status(self.book_id, "downloading")
+            set_chapter_total(self.book_id, total)
+            log(f"[CTRL_STATE] Status set to 'downloading' for {self.book_id}")
+        except Exception as e:
+            log(f"[CTRL_STATE] set_status/set_chapter_total FAILED: {e}")
+
         # -------------------------------------
         # 1) Download cover
         # -------------------------------------

bookscraper/scraper/progress.py

@@ -1,15 +1,22 @@
 # ============================================================
 # File: scraper/progress.py
-# Purpose: Track chapter counters for WebGUI progress.
+# Purpose: Track chapter counters for WebGUI progress +
+#          Book State Model (Redis-backed).
 # ============================================================
 
 import os
+import time
 import redis
 
 REDIS_URL = os.getenv("REDIS_BROKER", "redis://redis:6379/0")
 r = redis.Redis.from_url(REDIS_URL, decode_responses=True)
 
 
+# ============================================================
+# LEGACY PROGRESS FUNCTIONS (ONAANGEROERD BEHOUDEN)
+# ============================================================
+
+
 # ------------------------------------------------------------
 # SET TOTAL
 # ------------------------------------------------------------
@@ -45,7 +52,7 @@ def get_failed_list(book_id: str):
 
 
 # ------------------------------------------------------------
-# READ STRUCT FOR UI
+# READ STRUCT FOR UI (legacy view)
 # ------------------------------------------------------------
 def get_progress(book_id: str):
     total = int(r.get(f"progress:{book_id}:total") or 0)
@@ -64,3 +71,118 @@ def get_progress(book_id: str):
         "failed_list": failed_list,
         "abort": abort,
     }
+
+
+# ============================================================
+# BOOK STATE MODEL (NIEUWE FUNCTIES — GEEN BREAKING CHANGES)
+# ============================================================
+
+
+# ------------------------------------------------------------
+# Initialize book state at start of scrape
+# ------------------------------------------------------------
+def init_book_state(
+    book_id: str, title: str = "", url: str = "", chapters_total: int = 0
+):
+    key = f"book:{book_id}:state"
+    now = int(time.time())
+
+    r.hset(
+        key,
+        mapping={
+            "book_id": book_id,
+            "title": title or "",
+            "url": url or "",
+            "status": "scraping",
+            "chapters_total": chapters_total,
+            "chapters_done": 0,
+            "audio_total": 0,
+            "audio_done": 0,
+            "last_update": now,
+        },
+    )
+
+    # Track in library list
+    r.sadd("books", book_id)
+
+
+# ------------------------------------------------------------
+# Status + timestamps
+# ------------------------------------------------------------
+def set_status(book_id: str, status: str):
+    key = f"book:{book_id}:state"
+    r.hset(key, "status", status)
+    r.hset(key, "last_update", int(time.time()))
+
+
+def set_last_update(book_id: str):
+    r.hset(f"book:{book_id}:state", "last_update", int(time.time()))
+
+
+# ------------------------------------------------------------
+# Chapter counters
+# ------------------------------------------------------------
+def set_chapter_total(book_id: str, total: int):
+    key = f"book:{book_id}:state"
+    r.hset(key, "chapters_total", total)
+    set_last_update(book_id)
+
+
+def inc_chapter_done(book_id: str):
+    key = f"book:{book_id}:state"
+    r.hincrby(key, "chapters_done", 1)
+    set_last_update(book_id)
+
+
+# ------------------------------------------------------------
+# Audio counters
+# ------------------------------------------------------------
+def set_audio_total(book_id: str, total: int):
+    key = f"book:{book_id}:state"
+    r.hset(key, "audio_total", total)
+    set_last_update(book_id)
+
+
+def inc_audio_done(book_id: str):
+    key = f"book:{book_id}:state"
+    r.hincrby(key, "audio_done", 1)
+    set_last_update(book_id)
+
+
+# ------------------------------------------------------------
+# Skip reasons
+# ------------------------------------------------------------
+def save_skip_reason(book_id: str, chapter: int, reason: str):
+    """
+    Store explicit skip reason for transparency in UI.
+    """
+    r.hset(f"book:{book_id}:skip_reasons", chapter, reason)
+    set_last_update(book_id)
+
+
+# ------------------------------------------------------------
+# Full state readout
+# ------------------------------------------------------------
+def get_state(book_id: str):
+    """
+    Read global Book State Model + legacy progress, merged but not mixed.
+    """
+    key = f"book:{book_id}:state"
+    state = r.hgetall(key) or {}
+
+    # Numeric conversions
+    numeric_fields = ["chapters_total", "chapters_done", "audio_total", "audio_done"]
+    for field in numeric_fields:
+        if field in state:
+            try:
+                state[field] = int(state[field])
+            except ValueError:
+                pass
+
+    # Skip reasons
+    state["skip_reasons"] = r.hgetall(f"book:{book_id}:skip_reasons") or {}
+
+    # Attach legacy progress separately
+    state["legacy_progress"] = get_progress(book_id)
+
+    return state