feat(paperless): add support for setting absender custom field
Co-authored-by: christianlouis <361235+christianlouis@users.noreply.github.com>
This commit is contained in:
@@ -117,6 +117,10 @@ NEXTCLOUD_PASSWORD=<NEXTCLOUD_PASSWORD>
|
||||
# Paperless-ngx
|
||||
PAPERLESS_HOST=https://paperless.example.com
|
||||
PAPERLESS_NGX_API_TOKEN=<PAPERLESS_API_TOKEN>
|
||||
# Optional: Name of the custom field in Paperless-ngx to store the "absender" (sender) value
|
||||
# If set, the extracted sender information will be automatically set as a custom field in Paperless
|
||||
# Example: PAPERLESS_CUSTOM_FIELD_ABSENDER=Absender
|
||||
# PAPERLESS_CUSTOM_FIELD_ABSENDER=
|
||||
|
||||
# Dropbox
|
||||
DROPBOX_APP_KEY=<DROPBOX_APP_KEY>
|
||||
|
||||
@@ -31,6 +31,7 @@ class Settings(BaseSettings):
|
||||
# Making Paperless optional
|
||||
paperless_ngx_api_token: Optional[str] = None
|
||||
paperless_host: Optional[str] = None
|
||||
paperless_custom_field_absender: Optional[str] = None # Name or ID of the "absender" custom field in Paperless
|
||||
|
||||
azure_ai_key: str
|
||||
azure_region: str
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
#!/usr/bin/env python3
|
||||
|
||||
import json
|
||||
import logging
|
||||
import os
|
||||
import time
|
||||
@@ -78,10 +79,85 @@ def poll_task_for_document_id(task_id: str) -> int:
|
||||
raise TimeoutError(f"Task {task_id} didn't reach SUCCESS within {POLL_MAX_ATTEMPTS} attempts.")
|
||||
|
||||
|
||||
def get_custom_field_id(field_name: str) -> int:
|
||||
"""
|
||||
Retrieves the ID of a custom field by its name from Paperless-ngx.
|
||||
|
||||
Args:
|
||||
field_name: The name of the custom field to look up
|
||||
|
||||
Returns:
|
||||
The integer ID of the custom field
|
||||
|
||||
Raises:
|
||||
ValueError: If the custom field is not found
|
||||
"""
|
||||
url = _paperless_api_url("/api/custom_fields/")
|
||||
try:
|
||||
resp = requests.get(url, headers=_get_headers(), timeout=settings.http_request_timeout)
|
||||
resp.raise_for_status()
|
||||
data = resp.json()
|
||||
|
||||
# Handle paginated response
|
||||
results = data.get("results", []) if isinstance(data, dict) else data
|
||||
|
||||
for field in results:
|
||||
if field.get("name") == field_name:
|
||||
return field.get("id")
|
||||
|
||||
raise ValueError(f"Custom field '{field_name}' not found in Paperless-ngx")
|
||||
except requests.exceptions.RequestException as exc:
|
||||
logger.error(f"Failed to retrieve custom fields from Paperless: {exc}")
|
||||
raise
|
||||
|
||||
|
||||
def set_document_custom_fields(doc_id: int, custom_fields: dict, task_id: str) -> None:
|
||||
"""
|
||||
Updates custom fields for a document in Paperless-ngx using PATCH.
|
||||
|
||||
Args:
|
||||
doc_id: The Paperless document ID
|
||||
custom_fields: Dictionary mapping field names to values
|
||||
task_id: Task ID for logging
|
||||
"""
|
||||
if not custom_fields:
|
||||
return
|
||||
|
||||
# Build custom_fields array for PATCH request
|
||||
custom_fields_array = []
|
||||
for field_name, value in custom_fields.items():
|
||||
if value and value != "Unknown": # Only set non-empty, non-Unknown values
|
||||
try:
|
||||
field_id = get_custom_field_id(field_name)
|
||||
custom_fields_array.append({"field": field_id, "value": value})
|
||||
logger.info(f"[{task_id}] Mapped custom field '{field_name}' to ID {field_id} with value '{value}'")
|
||||
except ValueError as e:
|
||||
logger.warning(f"[{task_id}] {str(e)}, skipping this field")
|
||||
continue
|
||||
|
||||
if not custom_fields_array:
|
||||
logger.info(f"[{task_id}] No valid custom fields to set")
|
||||
return
|
||||
|
||||
# PATCH the document with custom fields
|
||||
url = _paperless_api_url(f"/api/documents/{doc_id}/")
|
||||
payload = {"custom_fields": custom_fields_array}
|
||||
|
||||
try:
|
||||
logger.info(f"[{task_id}] Setting custom fields for document {doc_id}: {payload}")
|
||||
resp = requests.patch(url, headers=_get_headers(), json=payload, timeout=settings.http_request_timeout)
|
||||
resp.raise_for_status()
|
||||
logger.info(f"[{task_id}] Successfully set custom fields for document {doc_id}")
|
||||
except requests.exceptions.RequestException as exc:
|
||||
logger.error(f"[{task_id}] Failed to set custom fields for document {doc_id}: {exc}")
|
||||
# Don't raise - this is a non-critical failure, document is already uploaded
|
||||
logger.error(f"[{task_id}] Response: {getattr(exc.response, 'text', '<no response>')}")
|
||||
|
||||
|
||||
@celery.task(base=BaseTaskWithRetry, bind=True)
|
||||
def upload_to_paperless(self, file_path: str, file_id: int = None):
|
||||
"""
|
||||
Uploads a file to Paperless-ngx.
|
||||
Uploads a file to Paperless-ngx and sets custom fields from metadata.
|
||||
|
||||
Args:
|
||||
file_path: Path to the file to upload
|
||||
@@ -113,6 +189,20 @@ def upload_to_paperless(self, file_path: str, file_id: int = None):
|
||||
log_task_progress(task_id, "upload_to_paperless", "failure", error_msg, file_id=file_id)
|
||||
raise ValueError(error_msg)
|
||||
|
||||
# Try to load metadata from accompanying JSON file
|
||||
metadata = {}
|
||||
json_path = os.path.splitext(file_path)[0] + ".json"
|
||||
if os.path.exists(json_path):
|
||||
try:
|
||||
with open(json_path, "r", encoding="utf-8") as f:
|
||||
metadata = json.load(f)
|
||||
logger.info(f"[{task_id}] Loaded metadata from {json_path}")
|
||||
except Exception as e:
|
||||
logger.warning(f"[{task_id}] Failed to load metadata from {json_path}: {e}")
|
||||
metadata = {}
|
||||
else:
|
||||
logger.info(f"[{task_id}] No metadata file found at {json_path}")
|
||||
|
||||
# Upload the PDF
|
||||
logger.info(f"[{task_id}] Posting document to Paperless")
|
||||
log_task_progress(task_id, "post_document", "in_progress", "Posting to Paperless API", file_id=file_id)
|
||||
@@ -153,6 +243,24 @@ def upload_to_paperless(self, file_path: str, file_id: int = None):
|
||||
task_id, "upload_to_paperless", "success", f"Uploaded to Paperless: Doc ID {doc_id}", file_id=file_id
|
||||
)
|
||||
|
||||
# Set custom fields if configured and metadata available
|
||||
if settings.paperless_custom_field_absender and metadata.get("absender"):
|
||||
logger.info(f"[{task_id}] Setting custom fields for document {doc_id}")
|
||||
log_task_progress(task_id, "set_custom_fields", "in_progress", "Setting custom fields", file_id=file_id)
|
||||
|
||||
# Prepare custom fields to set
|
||||
custom_fields_to_set = {}
|
||||
if settings.paperless_custom_field_absender:
|
||||
custom_fields_to_set[settings.paperless_custom_field_absender] = metadata.get("absender")
|
||||
|
||||
try:
|
||||
set_document_custom_fields(doc_id, custom_fields_to_set, task_id)
|
||||
log_task_progress(task_id, "set_custom_fields", "success", "Custom fields set", file_id=file_id)
|
||||
except Exception as e:
|
||||
logger.error(f"[{task_id}] Failed to set custom fields: {e}")
|
||||
log_task_progress(task_id, "set_custom_fields", "failure", f"Failed: {str(e)}", file_id=file_id)
|
||||
# Don't fail the entire upload if custom fields fail
|
||||
|
||||
return {
|
||||
"status": "Completed",
|
||||
"paperless_task_id": raw_task_id,
|
||||
|
||||
Reference in New Issue
Block a user