- Introduction of the Automatic HTML Processor

- Translation Service improvement
- Enable activation / deactivation of Processors
- Renew API-keys for Mistral (leading to workspaces)
- Align all Document views to use of a session catalog
- Allow for different processors for the same file type

common/utils/document_utils.py

@@ -3,7 +3,7 @@ from datetime import datetime as dt, timezone as tz
 from sqlalchemy import desc
 from sqlalchemy.exc import SQLAlchemyError
 from werkzeug.utils import secure_filename
-from common.models.document import Document, DocumentVersion, Catalog
+from common.models.document import Document, DocumentVersion, Catalog, Processor
 from common.extensions import db, minio_client
 from common.utils.celery_utils import current_celery
 from flask import current_app
@@ -11,6 +11,7 @@ import requests
 from urllib.parse import urlparse, unquote, urlunparse, parse_qs
 import os
 
+from config.type_defs.processor_types import PROCESSOR_TYPES
 from .config_field_types import normalize_json_field
 from .eveai_exceptions import (EveAIInvalidLanguageException, EveAIDoubleURLException, EveAIUnsupportedFileType,
                                EveAIInvalidCatalog, EveAIInvalidDocument, EveAIInvalidDocumentVersion, EveAIException)
@@ -469,3 +470,15 @@ def lookup_document(tenant_id: int, lookup_criteria: dict, metadata_type: str) -
             "Error during document lookup",
             status_code=500
         )
+
+def is_file_type_supported_by_catalog(catalog_id, file_type):
+    processors = Processor.query.filter_by(catalog_id=catalog_id).filter_by(active=True).all()
+
+    supported_file_types = []
+    for processor in processors:
+        processor_file_types = PROCESSOR_TYPES[processor.type]['file_types']
+        file_types = [f.strip() for f in processor_file_types.split(",")]
+        supported_file_types.extend(file_types)
+
+    if file_type not in supported_file_types:
+        raise EveAIUnsupportedFileType()