Mirrors/Dispatcharr
1
0
Fork 1
mirror of https://github.com/Dispatcharr/Dispatcharr.git synced 2026-08-03 15:22:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge pull request #294 from pantherale0/feat/chunked-extractor

Browse source 
Fix: Prevent memory exhaustion when extracting large compressed files
This commit is contained in:
SergeantPanda 2025-08-14 09:50:52 -05:00 • committed by GitHub
commit eec53d5874
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 13 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

16
apps/epg/tasks.py
View file

@ -28,6 +28,8 @@ from core.utils import acquire_task_lock, release_task_lock, send_websocket_upda
logger = logging.getLogger(__name__)
MAX_EXTRACT_CHUNK_SIZE = 65536 # 64kb (base2)
def send_epg_update(source_id, action, progress, **kwargs):
"""Send WebSocket update about EPG download/parsing progress"""
@ -641,7 +643,11 @@ def extract_compressed_file(file_path, output_path=None, delete_original=False):
# Reset file pointer and extract the content
gz_file.seek(0)
with open(extracted_path, 'wb') as out_file:
out_file.write(gz_file.read())
while True:
chunk = gz_file.read(MAX_EXTRACT_CHUNK_SIZE)
if not chunk or len(chunk) == 0:
break
out_file.write(chunk)
except Exception as e:
logger.error(f"Error extracting GZIP file: {e}", exc_info=True)
return None
@ -685,9 +691,13 @@ def extract_compressed_file(file_path, output_path=None, delete_original=False):
return None
# Extract the first XML file
xml_content = zip_file.read(xml_files[0])
with open(extracted_path, 'wb') as out_file:
out_file.write(xml_content)
with zip_file.open(xml_files[0], "r") as xml_file:
while True:
chunk = xml_file.read(MAX_EXTRACT_CHUNK_SIZE)
if not chunk or len(chunk) == 0:
break
out_file.write(chunk)
logger.info(f"Successfully extracted zip file to: {extracted_path}")