Merge branch 'development' of gitea.centx.de:lelo/bethaus-app into development

app.py

@@ -249,6 +249,7 @@ def serve_sw():
 @app.route('/api/path/<path:subpath>')
 @auth.require_secret
 def api_browse(subpath):
+    toplist_categories = app_config.get('toplist_categories', None)
     
     if subpath == '': # root directory
         foldernames = []
@@ -260,7 +261,8 @@ def api_browse(subpath):
             'directories': foldernames,
             'files': [],
             'folder_today': a.return_folder_today(),
-            'folder_yesterday': a.return_folder_yesterday()
+            'folder_yesterday': a.return_folder_yesterday(),
+            'toplist_enabled': bool(toplist_categories)
         })
 
     if subpath == 'heute' or subpath == 'gestern':
@@ -284,14 +286,12 @@ def api_browse(subpath):
         foldernames = []
         files = []
         split_path = subpath.split('/')
-        
-        valid_categories = ['Predigt', 'Erzählung', 'Gedicht', 'Gemeinsamer Gesang', 'Chor', 'Kinderchor', 'Jugendchor', 'Orchester', 'Instrumental', 'Gruppenlied']
 
         if len(split_path) == 1 and split_path[0] == 'toplist':
             foldernames = [
                 {
                     'name': categorie,  'path': 'toplist/' + categorie
-                } for categorie in valid_categories
+                } for categorie in toplist_categories
             ]
         elif len(split_path) > 1 and split_path[0] == 'toplist':
             files = hf.generate_top_list(split_path[1])

helperfunctions.py

@@ -1,57 +1,78 @@
 from flask import session
-from datetime import datetime
 import re
 import os
 import sqlite3
 from datetime import datetime, timedelta
+from typing import Optional
+import auth
+
+app_config = auth.return_app_config()
+BASE_DIR = os.path.realpath(app_config['BASE_DIR'])
 
 log_db = sqlite3.connect("access_log.db", check_same_thread=False)
 
-def extract_date_from_string(string_with_date):
-    # grab X.Y.Z where X,Y,Z are 1–4 digits
-    m = re.search(r'(\d{1,4}\.\d{1,2}\.\d{1,4})', string_with_date)
-    if not m:
-        return None
 
-    date_str = m.group(1)
-    parts = date_str.split('.')
-    
-    # 1) Unambiguous “last group = YYYY”
-    if len(parts) == 3 and len(parts[2]) == 4:
-        fmt = '%d.%m.%Y'
 
-    # 2) Unambiguous “first group = YYYY”
+# Precompiled regex to find date-like patterns: either dotted X.Y.Z or ISO dashed YYYY-MM-DD
-    elif len(parts) == 3 and len(parts[0]) == 4:
+_DATE_REGEX = re.compile(
-        fmt = '%Y.%m.%d'
+    r"("  # start group
+    r"\d{4}-\d{1,2}-\d{1,2}"          # ISO: YYYY-M-D or YYYY-MM-DD
+    r"|"                              # or
+    r"\d{1,4}\.\d{1,2}\.\d{1,4}"      # dotted: X.Y.Z, where each is 1–4 digits (year may be 1–4)
+    r")"
+)
 
-    # 3) Ambiguous “XX.XX.XX” → prefer DD.MM.YY, fallback to YY.MM.DD
-    elif len(parts) == 3 and all(len(p) == 2 for p in parts):
-        # try last-group-as-year first
-        try:
-            dt = datetime.strptime(date_str, '%d.%m.%y')
-            return dt.strftime('%Y-%m-%d')
-        except ValueError:
-            # fallback to first-group-as-year
-            fmt = '%y.%m.%d'
 
-    else:
+def _try_parse(date_str: str, fmt: str) -> Optional[datetime]:
-        # optional: handle ISO with dashes
+    """Try to parse date_str with fmt, return datetime or None."""
-        if '-' in date_str:
-            try:
-                dt = datetime.strptime(date_str, '%Y-%m-%d')
-                return dt.strftime('%Y-%m-%d')
-            except ValueError:
-                return None
-        return None
-
-    # parse with whichever fmt we settled on
     try:
-        dt = datetime.strptime(date_str, fmt)
+        return datetime.strptime(date_str, fmt)
-        return dt.strftime('%Y-%m-%d')
     except ValueError:
         return None
 
 
+def extract_date_from_string(text: str) -> Optional[str]:
+    """
+    Extract the first date-like substring from text and return it in ISO format (YYYY-MM-DD).
+    Supports:
+    - ISO-style dates with dashes (YYYY-M-D or YYYY-MM-DD)
+    - Dotted dates (DD.MM.YYYY, YYYY.MM.DD, DD.MM.YY, YY.MM.DD)
+    """
+    match = _DATE_REGEX.search(text)
+    if not match:
+        return None
+
+    date_str = match.group(1)
+
+    # 1) ISO dashed format takes priority
+    if '-' in date_str:
+        dt = _try_parse(date_str, '%Y-%m-%d')
+        return dt.strftime('%Y-%m-%d') if dt else None
+
+    # 2) Dotted formats
+    parts = date_str.split('.')
+    candidates = []
+
+    # Unambiguous: last part 4 digits → DD.MM.YYYY
+    if len(parts) == 3 and len(parts[2]) == 4:
+        candidates.append('%d.%m.%Y')
+    # Unambiguous: first part 4 digits → YYYY.MM.DD
+    if len(parts) == 3 and len(parts[0]) == 4:
+        candidates.append('%Y.%m.%d')
+    # Ambiguous two-digit groups: try DD.MM.YY, then YY.MM.DD
+    if len(parts) == 3 and all(len(p) == 2 for p in parts):
+        candidates.extend(['%d.%m.%y', '%y.%m.%d'])
+
+    # Try each candidate
+    for fmt in candidates:
+        dt = _try_parse(date_str, fmt)
+        if dt:
+            return dt.strftime('%Y-%m-%d')
+
+    # no valid parse
+    return None
+
+
 def extract_structure_from_string(input_string):
     # extract category and titel from filename
     filepathname_ext = os.path.splitext(input_string)[0] # remove file extension
@@ -67,30 +88,28 @@ def extract_structure_from_string(input_string):
         # first part not a number
         pass
     
-    if 'predig' in left_side.lower() or 'thema' in left_side.lower():
+    # define your mapping: category → list of trigger-words
-        category = 'Predigt'
+    CATEGORY_KEYWORDS = {
-    elif 'wort' in left_side.lower() or 'einladung' in left_side.lower() or 'begrüßung' in left_side.lower() or 'ansprache' in left_side.lower() or 'einleitung' in left_side.lower() or 'aufruf zum' in left_side.lower() or 'zuruf zum' in left_side.lower():
+        'Predigt':              ['predig', 'thema'],
-        category = 'Vorwort'
+        'Vorwort':              ['wort', 'einladung', 'begrüßung', 'ansprache', 'einleitung', 'aufruf zum', 'zuruf zum'],
-    elif 'kinderchor' in left_side.lower():
+        'Kinderchor':           ['kinderchor'],
-        category = 'Kinderchor'
+        'Jugendchor':           ['jugendchor'],
-    elif 'jugendchor' in left_side.lower():
+        'Orchester':            ['orchester', 'sinfonie', 'symphonie'],
-        category = 'Jugendchor'
+        'Chor':                 ['chor'],
-    elif 'orchester' in input_string.lower() or 'sinfonie' in input_string.lower() or 'symphonie' in input_string.lower():
+        'Gemeinsamer Gesang':   ['gemeinsam', 'gemeindelied', 'gemeinsamer gesang'],
-        category = 'Orchester'
+        'Gruppenlied':          ['gruppenlied', 'jugend', 'lied', 'musikgruppe'],
-    elif 'chor' in left_side.lower():
+        'Gedicht':              ['gedicht'],
-        category = 'Chor'
+        'Erzählung':            ['vortrag', 'erzä', 'program'],
-    elif 'gemeinsam' in left_side.lower() or 'gemeindelied' in left_side.lower() or 'gemeinsamer gesang' in input_string.lower():
+        'Instrumental':         ['instrumental', 'musikstück', 'harfenstück'],
-        category = 'Gemeinsamer Gesang'
+    }
-    elif 'gruppenlied' in left_side.lower() or 'jugend' in left_side.lower() or 'lied' in left_side.lower():
+
-        category = 'Gruppenlied'
+    # walk the dict in your desired priority order
-    elif 'gedicht' in left_side.lower():
+    category = None
-        category = 'Gedicht'
+    text = left_side.lower()
-    elif 'vortrag' in left_side.lower() or 'erzä' in left_side.lower() or 'program' in left_side.lower():
+    for cat, keywords in CATEGORY_KEYWORDS.items():
-        category = 'Erzählung'
+        if any(kw in text for kw in keywords):
-    elif 'instrumental' in input_string.lower() or 'musikstück' in left_side.lower() or 'harfenstück' in left_side.lower():
+            category = cat
-        category = 'Instrumental'
+            break
-    else:
-        category = None
 
     if right_side:
         titel, name = right_side.split('-', 1) if '-' in right_side else (right_side, None)
@@ -128,15 +147,15 @@ def generate_top_list(category):
         cursor = log_db.execute(query, params_for_filter)
         rows = cursor.fetchall()
 
-    # Filter by allowed basefolders
+    # Filter by allowed base folders
     allowed_basefolders = list(session['folders'].keys())
     rows = [
         (rel_path, access_count) for rel_path, access_count in rows
         if any(rel_path.startswith(folder) for folder in allowed_basefolders)
     ]
 
-    # Convert rows to a list of dictionaries and add category
+    # Convert rows to a list of dicts and add category
-    rows = [
+    records = [
         {
             'rel_path': rel_path,
             'access_count': access_count,
@@ -144,15 +163,18 @@ def generate_top_list(category):
         }
         for rel_path, access_count in rows
     ]
-    rows = [r for r in rows if r['category'] == category][:20]
+    # Filter by requested category and limit
+    records = [r for r in records if r['category'] == category][:20]
 
-    filelist = [
+    # Build file list and check existence
-        {
+    filelist = []
-            'name': rel_path.split('/')[-1],
+    for record in records:
-            'path': rel_path,
+        rel_path = record['rel_path']
-            'file_type': 'music'
+        if os.path.exists(os.path.join(BASE_DIR, rel_path)):  # ensure file exists on disk // slow operation. maybe improve later
-        }
+            filelist.append({
-        for rel_path in [r['rel_path'] for r in rows]
+                'name': os.path.basename(rel_path),
-    ]
+                'path': rel_path,
+                'file_type': 'music'
+            })
 
     return filelist

static/app.js

@@ -113,7 +113,7 @@ function renderContent(data) {
         } else if (data.breadcrumbs.length === 1 && Array.isArray(data.folder_yesterday) && data.folder_yesterday.length > 0) {
           contentHTML += `<li class="directory-item"><a href="#" class="directory-link" data-path="gestern">📅 Gestern</a></li>`;
         }
-        if (data.breadcrumbs.length === 1 ) {
+        if (data.breadcrumbs.length === 1 && data.toplist_enabled) {
           contentHTML += `<li class="directory-item"><a href="#" class="directory-link" data-path="toplist">🔥 oft angehört</a></li>`;
         }
         console.log(data.folder_today, data.folder_yesterday);