Integrate OCRmyPDF args into ansible config

ansible/defaults/main.yml

@@ -11,12 +11,13 @@ paperlessng_virtualenv: "{{ paperlessng_directory }}/.venv"
 paperlessng_ocr_languages:
   - eng
 paperlessng_time_zone: Europe/Berlin
-paperlessng_ocrmypdf_args: --optimize 1
-# TODO Does optimze==1 really work with jbig2enc?
-# https://ocrmypdf.readthedocs.io/en/latest/jbig2.html#lossy-mode-jbig2
-# Documentation states -O1 only applies lossless transformations
-# https://ocrmypdf.readthedocs.io/en/latest/optimizer.html#lossless-optimizations
+# see https://ocrmypdf.readthedocs.io/en/latest/api.html#ocrmypdf.ocr
+paperlessng_ocrmypdf_args:
+  - "deskew": true
+  - "clean": true
+  - "optimize": 1
 paperlessng_use_jbig2enc: true
+paperlessng_big2enc_lossy: false
 
 paperlessng_superuser_name: paperlessng
 paperlessng_superuser_email: paperlessng@example.com

ansible/tasks/main.yml

@@ -183,10 +183,8 @@
       line: "PAPERLESS_FILENAME_FORMAT={{ paperlessng_filename_format }}"
     - regexp: "^#?PAPERLESS_OCR_LANGUAGE="
       line: "PAPERLESS_OCR_LANGUAGE={{ paperlessng_ocr_languages | join('+') }}"
-    # - regexp: "^#PAPERLESS_OCR_USER_ARG="
-    #   # TODO JSON dict required in conf
-    #   # https://paperless-ng.readthedocs.io/en/latest/configuration.html#ocr-settings
-    #   line: "PAPERLESS_OCR_USER_ARG=\"{{ paperlessng_ocrmypdf_args }}{{ ' --jbig2-lossy' if  paperlessng_use_jbig2enc else '' }}\""
+    - regexp: "^#PAPERLESS_OCR_USER_ARG="
+      line: "PAPERLESS_OCR_USER_ARG={{ paperlessng_ocrmypdf_args | combine({'jbig2_lossy': true} if paperlessng_big2enc_lossy else {}) }}"
     - regexp: "^#?PAPERLESS_TIME_ZONE="
       line: "PAPERLESS_TIME_ZONE={{ paperlessng_time_zone }}"
   no_log: yes