Merge pull request #204 from jovandeginste/paperless_tika

WIP: Add the new paperless_tika parser
This commit is contained in:
Jonas Winkler
2021-01-01 20:21:18 +01:00
committed by GitHub
8 changed files with 273 additions and 0 deletions

View File

@@ -87,6 +87,7 @@ INSTALLED_APPS = [
"documents.apps.DocumentsConfig",
"paperless_tesseract.apps.PaperlessTesseractConfig",
"paperless_text.apps.PaperlessTextConfig",
"paperless_tika.apps.PaperlessTikaConfig",
"paperless_mail.apps.PaperlessMailConfig",
"django.contrib.admin",
@@ -424,3 +425,10 @@ for t in json.loads(os.getenv("PAPERLESS_FILENAME_PARSE_TRANSFORMS", "[]")):
PAPERLESS_FILENAME_FORMAT = os.getenv("PAPERLESS_FILENAME_FORMAT")
THUMBNAIL_FONT_NAME = os.getenv("PAPERLESS_THUMBNAIL_FONT_NAME", "/usr/share/fonts/liberation/LiberationSerif-Regular.ttf")
# Tika settings
PAPERLESS_TIKA_ENABLED = __get_boolean("PAPERLESS_TIKA_ENABLED", "NO")
PAPERLESS_TIKA_ENDPOINT = os.getenv("PAPERLESS_TIKA_ENDPOINT", "http://localhost:9998")
PAPERLESS_TIKA_GOTENBERG_ENDPOINT = os.getenv(
"PAPERLESS_TIKA_GOTENBERG_ENDPOINT", "http://localhost:3000"
)