smokephil/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-12-09 00:05:21 +01:00
Code Issues Projects Releases Packages Wiki Activity

Add the new paperless_tika parser

Browse source 
This parser will use an external Tika and Gotenberg server to parse
"Office" documents (.doc, .xls, .odt, etc.)

Signed-off-by: Jo Vandeginste <Jo.Vandeginste@kuleuven.be>
This commit is contained in:
Jo Vandeginste 2020-12-29 01:23:40 +01:00
parent d690b34ee0
commit b8e8bf3dd4
No known key found for this signature in database
GPG key ID: E349B1AD928B72FB
9 changed files with 276 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

20
src/paperless_tika/signals.py Normal file
View file

@ -0,0 +1,20 @@
from .parsers import TikaDocumentParser
def tika_consumer_declaration(sender, **kwargs):
return {
"parser": TikaDocumentParser,
"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",
},
}