gitea-admin/gh-christianlouis-docuelevate
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

style: fix all flake8 linter errors across app/ directory

Browse Source 
- Run Black formatter and isort on all app/ files
- Remove unused imports (F401) across multiple files
- Add # noqa: F401 for intentional re-exports in celery_worker.py,
  tasks/__init__.py, utils.py, frontend.py, views/base.py
- Fix f-strings without placeholders (F541) in azure.py, notification.py,
  check_credentials.py, upload_to_onedrive.py, settings.py
- Fix bare except (E722) in upload_to_sftp.py
- Fix block comment format (E265) in models.py
- Move imports to top of file to fix E402 in celery_app.py, celery_worker.py
- Fix line-too-long (E501) by wrapping strings in multiple files
- Remove unused variable (F841) in upload_to_nextcloud.py

Co-authored-by: christianlouis <361235+christianlouis@users.noreply.github.com>
This commit is contained in:
copilot-swe-agent[bot]
2026-02-08 17:42:33 +00:00
parent 7827b97e06
commit d08040ac4a
73 changed files with 2200 additions and 2185 deletions
Download Patch File Download Diff File Expand all files Collapse all files
app/tasks/upload_to_paperless.py
+34 -28
View File
@@ -1,29 +1,26 @@
#!/usr/bin/env python3
import os
import json
import time
import requests
import logging
from typing import Dict, Any
import os
import time
import requests
from app.celery_app import celery
from app.config import settings
from app.tasks.retry_config import BaseTaskWithRetry
from app.celery_app import celery
from app.utils import log_task_progress
from app.database import SessionLocal
from app.models import FileRecord
logger = logging.getLogger(__name__)
POLL_MAX_ATTEMPTS = 10
POLL_INTERVAL_SEC = 3
def _get_headers():
"""Returns HTTP headers for Paperless-ngx API calls."""
return {
"Authorization": f"Token {settings.paperless_ngx_api_token}"
}
return {"Authorization": f"Token {settings.paperless_ngx_api_token}"}
def _paperless_api_url(path: str) -> str:
"""
@@ -35,6 +32,7 @@ def _paperless_api_url(path: str) -> str:
path = "/" + path
return f"{host}{path}"
def poll_task_for_document_id(task_id: str) -> int:
"""
Polls /api/tasks/?task_id=<uuid> until we get status=SUCCESS or FAILURE,
@@ -49,14 +47,13 @@ def poll_task_for_document_id(task_id: str) -> int:
while attempts < POLL_MAX_ATTEMPTS:
try:
resp = requests.get(url, headers=_get_headers(), params={"task_id": task_id}, timeout=settings.http_request_timeout)
resp = requests.get(
url, headers=_get_headers(), params={"task_id": task_id}, timeout=settings.http_request_timeout
)
resp.raise_for_status()
tasks_data = resp.json()
except requests.exceptions.RequestException as exc:
logger.warning(
"Failed to poll for task_id='%s'. Attempt=%d Error=%s",
task_id, attempts + 1, exc
)
logger.warning("Failed to poll for task_id='%s'. Attempt=%d Error=%s", task_id, attempts + 1, exc)
time.sleep(POLL_INTERVAL_SEC)
attempts += 1
continue
@@ -71,31 +68,34 @@ def poll_task_for_document_id(task_id: str) -> int:
doc_str = task_info.get("related_document")
if doc_str:
return int(doc_str)
raise RuntimeError(
f"Task {task_id} completed but no doc ID found. Task info: {task_info}"
)
raise RuntimeError(f"Task {task_id} completed but no doc ID found. Task info: {task_info}")
elif status == "FAILURE":
raise RuntimeError(f"Task {task_id} failed: {task_info.get('result')}")
attempts += 1
time.sleep(POLL_INTERVAL_SEC)
raise TimeoutError(
f"Task {task_id} didn't reach SUCCESS within {POLL_MAX_ATTEMPTS} attempts."
)
raise TimeoutError(f"Task {task_id} didn't reach SUCCESS within {POLL_MAX_ATTEMPTS} attempts.")
@celery.task(base=BaseTaskWithRetry, bind=True)
def upload_to_paperless(self, file_path: str, file_id: int = None):
"""
Uploads a file to Paperless-ngx.
Args:
file_path: Path to the file to upload
file_id: Optional file ID to associate with logs
"""
task_id = self.request.id
logger.info(f"[{task_id}] Starting Paperless upload: {file_path}")
log_task_progress(task_id, "upload_to_paperless", "in_progress", f"Uploading to Paperless: {os.path.basename(file_path)}", file_id=file_id)
log_task_progress(
task_id,
"upload_to_paperless",
"in_progress",
f"Uploading to Paperless: {os.path.basename(file_path)}",
file_id=file_id,
)
if not os.path.exists(file_path):
error_msg = f"File not found: {file_path}"
@@ -125,13 +125,17 @@ def upload_to_paperless(self, file_path: str, file_id: int = None):
try:
logger.debug("Posting document to Paperless: file=%s", filename)
resp = requests.post(post_url, headers=_get_headers(), files=files, data=data, timeout=settings.http_request_timeout)
resp = requests.post(
post_url, headers=_get_headers(), files=files, data=data, timeout=settings.http_request_timeout
)
resp.raise_for_status()
except requests.exceptions.RequestException as exc:
error_msg = f"Failed to upload to Paperless: {exc}"
logger.error(
f"[{task_id}] Failed to upload document '%s' to Paperless. Error: %s. Response=%s",
file_path, exc, getattr(exc.response, "text", "<no response>")
file_path,
exc,
getattr(exc.response, "text", "<no response>"),
)
log_task_progress(task_id, "upload_to_paperless", "failure", error_msg, file_id=file_id)
raise
@@ -145,11 +149,13 @@ def upload_to_paperless(self, file_path: str, file_id: int = None):
log_task_progress(task_id, "poll_task", "in_progress", "Waiting for Paperless processing", file_id=file_id)
doc_id = poll_task_for_document_id(raw_task_id)
logger.info(f"[{task_id}] Document {file_path} successfully ingested => ID={doc_id}")
log_task_progress(task_id, "upload_to_paperless", "success", f"Uploaded to Paperless: Doc ID {doc_id}", file_id=file_id)
log_task_progress(
task_id, "upload_to_paperless", "success", f"Uploaded to Paperless: Doc ID {doc_id}", file_id=file_id
)
return {
"status": "Completed",
"paperless_task_id": raw_task_id,
"paperless_document_id": doc_id,
"file_path": file_path
"file_path": file_path,
}