2024-06-09 07:34:22 -07:00

26 lines
1.1 KiB
Python

def get_parser(*args, **kwargs):
from paperless_tika.parsers import TikaDocumentParser
return TikaDocumentParser(*args, **kwargs)
def tika_consumer_declaration(sender, **kwargs):
return {
"parser": get_parser,
"weight": 10,
"mime_types": {
"application/msword": ".doc",
"application/vnd.openxmlformats-officedocument.wordprocessingml.document": ".docx",
"application/vnd.ms-excel": ".xls",
"application/vnd.openxmlformats-officedocument.spreadsheetml.sheet": ".xlsx",
"application/vnd.ms-powerpoint": ".ppt",
"application/vnd.openxmlformats-officedocument.presentationml.presentation": ".pptx",
"application/vnd.openxmlformats-officedocument.presentationml.slideshow": ".ppsx",
"application/vnd.oasis.opendocument.presentation": ".odp",
"application/vnd.oasis.opendocument.spreadsheet": ".ods",
"application/vnd.oasis.opendocument.text": ".odt",
"application/vnd.oasis.opendocument.graphics": ".odg",
"text/rtf": ".rtf",
},
}