paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-07-28 18:24:38 -05:00
Code Issues Packages Projects Releases Wiki Activity

reworked PDF parser that uses OCRmyPDF and produces archive files.

Browse Source
This commit is contained in:
Jonas Winkler
2020-11-25 14:50:43 +01:00
parent ac6c72a6c9
commit 15935ab61f
7 changed files with 374 additions and 186 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
src/paperless/settings.py
View File

@@ -338,9 +338,13 @@ OCR_PAGES = int(os.getenv('PAPERLESS_OCR_PAGES', 0))
# documents. It should be a 3-letter language code consistent with ISO 639.
OCR_LANGUAGE = os.getenv("PAPERLESS_OCR_LANGUAGE", "eng")
# OCRmyPDF --output-type options are available.
# TODO: validate this setting.
OCR_OUTPUT_TYPE = os.getenv("PAPERLESS_OCR_OUTPUT_TYPE", "pdfa")
# OCR all documents?
OCR_ALWAYS = __get_boolean("PAPERLESS_OCR_ALWAYS", "false")
# skip. redo, force
# TODO: validate this.
OCR_MODE = os.getenv("PAPERLESS_OCR_MODE", "skip")
# GNUPG needs a home directory for some reason
GNUPG_HOME = os.getenv("HOME", "/tmp")