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/process_with_azure_document_intelligence.py
+24 -21
View File
@@ -1,23 +1,23 @@
import os
import logging
import os
import azure.core.exceptions
import PyPDF2
from azure.core.credentials import AzureKeyCredential
from azure.ai.documentintelligence import DocumentIntelligenceClient
from azure.ai.documentintelligence.models import AnalyzeOutputOption, AnalyzeResult
import azure.core.exceptions
from azure.core.credentials import AzureKeyCredential
from app.celery_app import celery
from app.config import settings
from app.tasks.retry_config import BaseTaskWithRetry
from app.tasks.rotate_pdf_pages import rotate_pdf_pages
from app.celery_app import celery
logger = logging.getLogger(__name__)
# Initialize Azure Document Intelligence client with error handling
try:
document_intelligence_client = DocumentIntelligenceClient(
endpoint=settings.azure_endpoint,
credential=AzureKeyCredential(settings.azure_ai_key)
endpoint=settings.azure_endpoint, credential=AzureKeyCredential(settings.azure_ai_key)
)
logger.info("Azure Document Intelligence client initialized successfully")
except (ValueError, azure.core.exceptions.ClientAuthenticationError) as e:
@@ -33,36 +33,38 @@ AZURE_DOC_INTELLIGENCE_LIMITS = {
"max_pages": 2000,
}
def get_pdf_page_count(file_path):
"""Get the number of pages in a PDF file."""
try:
with open(file_path, 'rb') as file:
with open(file_path, "rb") as file:
pdf_reader = PyPDF2.PdfReader(file)
return len(pdf_reader.pages)
except Exception as e:
logger.error(f"Error getting PDF page count: {e}")
return None
def check_page_rotation(result, filename):
"""
Checks if pages in the document are rotated and logs the rotation information.
Args:
result: The AnalyzeResult from Azure Document Intelligence API
filename: The name of the file being processed
Returns:
dict: Dictionary mapping page indices (integers) to rotation angles
"""
logger.error(f"Checking rotation for document: {filename}")
rotation_data = {}
if not hasattr(result, 'pages') or not result.pages:
if not hasattr(result, "pages") or not result.pages:
logger.error(f"No page information available for rotation check: {filename}")
return rotation_data
for i, page in enumerate(result.pages):
if hasattr(page, 'angle'):
if hasattr(page, "angle"):
rotation_angle = page.angle
if rotation_angle != 0:
logger.error(f"Page {i+1} is rotated by {rotation_angle} degrees")
@@ -72,15 +74,16 @@ def check_page_rotation(result, filename):
logger.error(f"Page {i+1} has no rotation (0 degrees)")
else:
logger.error(f"Page {i+1} rotation information not available")
return rotation_data
@celery.task(base=BaseTaskWithRetry)
def process_with_azure_document_intelligence(filename: str, file_id: int = None):
"""
Processes a PDF document using Azure Document Intelligence and overlays OCR text onto
the local temporary file (stored under <workdir>/tmp).
Steps:
0. Verify the file meets Azure Document Intelligence service limits
1. Uploads the document for OCR using Azure Document Intelligence.
@@ -88,7 +91,7 @@ def process_with_azure_document_intelligence(filename: str, file_id: int = None)
3. Saves the OCR-processed PDF locally in the same location as before.
4. Checks for page rotation and triggers page rotation if needed.
5. Triggers downstream metadata extraction.
Args:
filename: Name of the file to process
file_id: Optional file ID to pass through to subsequent tasks
@@ -101,13 +104,15 @@ def process_with_azure_document_intelligence(filename: str, file_id: int = None)
# Check file size against service limits
file_size = os.path.getsize(tmp_file_path)
if file_size > AZURE_DOC_INTELLIGENCE_LIMITS["max_file_size_bytes"]:
error_msg = f"File size ({file_size / (1024 * 1024):.2f} MB) exceeds Azure Document Intelligence limit of 500 MB"
error_msg = (
f"File size ({file_size / (1024 * 1024):.2f} MB) exceeds Azure Document Intelligence limit of 500 MB"
)
logger.error(error_msg)
return {"error": error_msg, "file": filename, "status": "Failed - Size limit exceeded"}
# For PDF files, check page count against service limits
# "Fail open" approach: only reject if we're sure it exceeds the limit
if filename.lower().endswith('.pdf'):
if filename.lower().endswith(".pdf"):
page_count = get_pdf_page_count(tmp_file_path)
if page_count is not None and page_count > AZURE_DOC_INTELLIGENCE_LIMITS["max_pages"]:
error_msg = f"PDF page count ({page_count}) exceeds Azure Document Intelligence limit of 2000 pages"
@@ -130,9 +135,7 @@ def process_with_azure_document_intelligence(filename: str, file_id: int = None)
rotation_data = check_page_rotation(result, filename)
# Retrieve the processed searchable PDF
response = document_intelligence_client.get_analyze_result_pdf(
model_id=result.model_id, result_id=operation_id
)
response = document_intelligence_client.get_analyze_result_pdf(model_id=result.model_id, result_id=operation_id)
searchable_pdf_path = tmp_file_path # Overwrite the original PDF location
with open(searchable_pdf_path, "wb") as writer:
writer.writelines(response)