lelo/bethaus-app
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix date in index

Browse Source
This commit is contained in:
lelo 2025-05-11 12:33:09 +02:00
parent da98a8b6e6
commit 688625f451
1 changed files with 57 additions and 55 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

112
index_for_search.py
View File

@ -101,6 +101,10 @@ def updatefileindex():
relative_path = os.path.join(foldername, rel_part).replace(os.sep, '/') relative_path = os.path.join(foldername, rel_part).replace(os.sep, '/')
filetype = os.path.splitext(entry.name)[1].lower() filetype = os.path.splitext(entry.name)[1].lower()
if filetype not in ['.mp3', '.wav', '.ogg', '.m4a', '.flac']:
# Skip non-audio files.
continue
# Retrieve the hit count for this file. # Retrieve the hit count for this file.
hit_count = get_hit_count(relative_path) hit_count = get_hit_count(relative_path)
@ -111,68 +115,66 @@ def updatefileindex():
site = 'Speyer' site = 'Speyer'
elif foldername == 'Gottesdienste Schwegenheim': elif foldername == 'Gottesdienste Schwegenheim':
site = 'Schwegenheim' site = 'Schwegenheim'
if filetype == '.mp3':
# Check for a corresponding transcript file in a sibling "Transkription" folder. # Check for a corresponding transcript file in a sibling "Transkription" folder.
parent_dir = os.path.dirname(entry_path) parent_dir = os.path.dirname(entry_path)
transcript_dir = os.path.join(parent_dir, "Transkription") transcript_dir = os.path.join(parent_dir, "Transkription")
transcript_filename = os.path.splitext(entry.name)[0] + ".md" transcript_filename = os.path.splitext(entry.name)[0] + ".md"
transcript_path = os.path.join(transcript_dir, transcript_filename) transcript_path = os.path.join(transcript_dir, transcript_filename)
if os.path.exists(transcript_path): if os.path.exists(transcript_path):
try:
with open(transcript_path, 'r', encoding='utf-8') as tf:
transcript = tf.read()
except Exception:
transcript = None
# extract category and titel from filename
filename_ext = os.path.splitext(entry.name)[0]
left_side, right_side = filename_ext.split('-', 1) if '-' in filename_ext else (filename_ext, None)
try: try:
int(left_side.strip()) with open(transcript_path, 'r', encoding='utf-8') as tf:
# first part is only a number transcript = tf.read()
previous_right_side = right_side except Exception:
left_side, right_side = previous_right_side.split('-', 1) if '-' in previous_right_side else (previous_right_side, None) transcript = None
except:
# first part not a number
pass
if 'predig' in left_side.lower():
category = 'Predigt'
elif 'wort' in left_side.lower() or 'einladung' in left_side.lower():
category = 'Vorwort'
elif 'chor' in left_side.lower():
category = 'Chor'
elif 'orchester' in left_side.lower():
category = 'Orchester'
elif 'gruppenlied' in left_side.lower() or 'jugendlied' in left_side.lower():
category = 'Gruppenlied'
elif 'gemeinsam' in left_side.lower() or 'gesang' in left_side.lower() or 'lied' in left_side.lower():
category = 'Gemeinsamer Gesang'
elif 'gedicht' in left_side.lower():
category = 'Gedicht'
elif 'instrumental' in left_side.lower() or 'musikstück' in left_side.lower():
category = 'Instrumental'
else:
category = None
if right_side: # extract category and titel from filename
titel, name = right_side.split('-', 1) if '-' in right_side else (right_side, None) filename_ext = os.path.splitext(entry.name)[0]
if category == 'Predigt' or category == 'Vorwort' or category == 'Gedicht': left_side, right_side = filename_ext.split('-', 1) if '-' in filename_ext else (filename_ext, None)
if not name: # kein Titel, nur Name try:
name = titel int(left_side.strip())
titel = None # first part is only a number
else: previous_right_side = right_side
titel = None left_side, right_side = previous_right_side.split('-', 1) if '-' in previous_right_side else (previous_right_side, None)
name = None except:
# first part not a number
pass
if 'predig' in left_side.lower():
category = 'Predigt'
elif 'wort' in left_side.lower() or 'einladung' in left_side.lower():
category = 'Vorwort'
elif 'chor' in left_side.lower():
category = 'Chor'
elif 'orchester' in left_side.lower():
category = 'Orchester'
elif 'gruppenlied' in left_side.lower() or 'jugendlied' in left_side.lower():
category = 'Gruppenlied'
elif 'gemeinsam' in left_side.lower() or 'gesang' in left_side.lower() or 'lied' in left_side.lower():
category = 'Gemeinsamer Gesang'
elif 'gedicht' in left_side.lower():
category = 'Gedicht'
elif 'instrumental' in left_side.lower() or 'musikstück' in left_side.lower():
category = 'Instrumental'
else:
category = None
if right_side:
titel, name = right_side.split('-', 1) if '-' in right_side else (right_side, None)
if category == 'Predigt' or category == 'Vorwort' or category == 'Gedicht':
if not name: # kein Titel, nur Name
name = titel
titel = None
else:
titel = None
name = None
# extract the date from path using regex (dd.mm.yyyy or dd.mm.yy) # extract the date from path using regex (supports YYYY.MM.DD, DD.MM.YYYY or DD.MM.YY)
date_match = re.search(r'(\d{1,2}\.\d{1,2}\.\d{2,4})', relative_path) date_match = re.search(r'(\d{1,2}\.\d{1,2}\.\d{2,4}|\d{4}\.\d{2}\.\d{2})', relative_path)
if date_match: if date_match:
date_str = date_match.group(1) date_str = date_match.group(1)
performance_date = None performance_date = None
for fmt in ('%d.%m.%Y', '%d.%m.%y', '%Y-%m-%d'): for fmt in ('%Y.%m.%d', '%d.%m.%Y', '%d.%m.%y', '%Y-%m-%d'):
try: try:
date_obj = datetime.strptime(date_str, fmt) date_obj = datetime.strptime(date_str, fmt)
# Convert to ISO format YYYY-MM-DD # Convert to ISO format YYYY-MM-DD