Updated Paperless-ng with additional variables (#392)

* added more variables supported by paperless-ng and added variable descriptions

* fixed regex validator for numeric inputs and email

* fixed regex validator

* removed a few optional variables

* unique variable name patterns

* added url protocol for CORS header

* added pre-consume script variable

Co-authored-by: ak4zh <akash@gmail.com>

public/v4/apps/paperless-ng.yml

@@ -9,30 +9,61 @@ services:
         restart: always
         environment:
             APP_URL: http://$$cap_appname.$$cap_root_domain
+            # Required services (https://paperless-ng.readthedocs.io/en/latest/configuration.html#required-services)
             PAPERLESS_REDIS: redis://srv-captain--$$cap_appname-redis:6379/0
             PAPERLESS_DBHOST: srv-captain--$$cap_appname-db
             PAPERLESS_DBNAME: $$cap_dbname
             PAPERLESS_DBUSER: $$cap_dbuser
             PAPERLESS_DBPASS: $$cap_dbpass
+            # Paths and folders (https://paperless-ng.readthedocs.io/en/latest/configuration.html#paths-and-folders)
+            PAPERLESS_FILENAME_FORMAT: $$cap_filename_format
+            # Logging (https://paperless-ng.readthedocs.io/en/latest/configuration.html#logging)
             PAPERLESS_LOGROTATE_MAX_SIZE: $$cap_logrotate_max_size
             PAPERLESS_LOGROTATE_MAX_BACKUPS: $$cap_logrotate_max_backup
+            # Hosting & Security (https://paperless-ng.readthedocs.io/en/latest/configuration.html#hosting-security)
             PAPERLESS_SECRET_KEY: $$cap_secret_key
+            PAPERLESS_ALLOWED_HOSTS: $$cap_appname.$$cap_root_domain
+            PAPERLESS_CORS_ALLOWED_HOSTS: http://$$cap_appname.$$cap_root_domain
             PAPERLESS_ADMIN_USER: $$cap_admin_user
             PAPERLESS_ADMIN_PASSWORD: $$cap_admin_password
+            PAPERLESS_ADMIN_MAIL: $$cap_admin_email
             PAPERLESS_COOKIE_PREFIX: $$cap_cookie_prefix
+            # OCR settings (https://paperless-ng.readthedocs.io/en/latest/configuration.html#ocr-settings)
             PAPERLESS_OCR_LANGUAGE: $$cap_ocr_language
             PAPERLESS_OCR_MODE: $$cap_ocr_mode
             PAPERLESS_OCR_CLEAN: $$cap_ocr_clean
             PAPERLESS_OCR_DESKEW: $$cap_ocr_deskew
             PAPERLESS_OCR_ROTATE_PAGES: $$cap_ocr_rotate_pages
+            PAPERLESS_OCR_ROTATE_PAGES_THRESHOLD: $$cap_ocr_rotate_threshold
             PAPERLESS_OCR_OUTPUT_TYPE: $$cap_ocr_output_type
-            PAPERLESS_OCR_PAGES: $$cap_ocr_page_count
+            PAPERLESS_OCR_PAGES: $$cap_ocr_pages
+            PAPERLESS_OCR_IMAGE_DPI: $$cap_ocr_image_dpi
             PAPERLESS_OCR_USER_ARGS: $cap_ocr_user_args
-            PAPERLESS_TIME_ZONE: $$cap_timezone
+            # Tika settings (https://paperless-ng.readthedocs.io/en/latest/configuration.html#tika-settings)
             PAPERLESS_TIKA_ENABLED: 1
             PAPERLESS_TIKA_GOTENBERG_ENDPOINT: http://srv-captain--$$cap_appname-gotenberg:3000
             PAPERLESS_TIKA_ENDPOINT: http://srv-captain--$$cap_appname-tika:9998
-
+            # Software tweaks (https://paperless-ng.readthedocs.io/en/latest/configuration.html#software-tweaks)
+            # PAPERLESS_TASK_WORKERS: $$cap_task_workers
+            # PAPERLESS_THREADS_PER_WORKER: $$cap_threads_per_worker
+            PAPERLESS_TIME_ZONE: $$cap_timezone
+            PAPERLESS_CONSUMER_POLLING: $$cap_consumer_polling
+            PAPERLESS_CONSUMER_DELETE_DUPLICATES: $$cap_consumer_delete_duplicates
+            PAPERLESS_CONSUMER_RECURSIVE: $$cap_consumer_recursive
+            PAPERLESS_CONSUMER_SUBDIRS_AS_TAGS: $$cap_consumer_subdirs_as_tags
+            PAPERLESS_CONVERT_MEMORY_LIMIT: $$cap_convert_memory_limit
+            PAPERLESS_CONVERT_TMPDIR: $$cap_convert_tempdir
+            PAPERLESS_OPTIMIZE_THUMBNAILS: $$cap_optimize_thumbnails
+            PAPERLESS_PRE_CONSUME_SCRIPT: $$cap_pre_consume_script
+            PAPERLESS_POST_CONSUME_SCRIPT: $$cap_post_consume_script
+            PAPERLESS_FILENAME_DATE_ORDER: $$cap_filename_date_order
+            PAPERLESS_THUMBNAIL_FONT_NAME: $$cap_thumbnail_font_name
+            PAPERLESS_IGNORE_DATES: $$cap_paperless_ignore_dates
+            # Docker-specific options (https://paperless-ng.readthedocs.io/en/latest/configuration.html#docker-specific-options)
+            PAPERLESS_WEBSERVER_WORKERS: $$cap_webserver_workers
+            USERMAP_UID: $$cap_usermap_uid
+            USERMAP_GID: $$cap_usermap_gid
+            PAPERLESS_OCR_LANGUAGES: $$cap_docker_ocr_languages
         volumes:
             - $$cap_appname-data:/usr/src/paperless/data
             - $$cap_appname-media:/usr/src/paperless/media
@@ -54,7 +85,7 @@ services:
 
     # Database
     $$cap_appname-db:
-        image: postgres:13
+        image: postgres:$$cap_postgres_version
         volumes:
             - $$cap_appname-db:/var/lib/postgresql/data
         restart: always
@@ -88,89 +119,229 @@ caproverOneClickApp:
           defaultValue: '1.4.1'
           description: Check out their docker page for the valid tags https://hub.docker.com/r/jonaswinkler/paperless-ng/tags
 
-        - id: $$cap_dbpass
+        - id: $$cap_postgres_version
-          label: Database Password
+          label: Postgres Version
-          defaultValue: $$cap_gen_random_hex(64)
+          defaultValue: '13'
+          description: Check out their Docker page for the valid tags https://hub.docker.com/r/library/postgres/tags/
+          validRegex: /^([^\s^\/])+$/
 
         - id: $$cap_redis_version
           label: Redis version
-          defaultValue: 6.0
+          defaultValue: '6.2.1-alpine'
+          validRegex: /^([^\s^\/])+$/
 
         - id: $$cap_dbname
-          label: Database name
+          label: Database Name
           defaultValue: 'paperless'
+          validRegex: /^([^\s^\/])+$/
 
         - id: $$cap_dbuser
           label: Database User
           defaultValue: 'paperless'
+          validRegex: /^([^\s^\/])+$/
+
+        - id: $$cap_dbpass
+          label: Database Password
+          defaultValue: $$cap_gen_random_hex(64)
+          validRegex: /^([^\s^\/])+$/
 
         - id: $$cap_filename_format
-          label: Database User
+          label: Filename Format
           defaultValue:
           description: 'Changes the filenames paperless uses to store documents in the media directory. See File name handling (https://paperless-ng.readthedocs.io/en/latest/advanced_usage.html#advanced-file-name-handling) for details. Default is none, which disables this feature.'
 
         - id: $$cap_logrotate_max_size
-          label: Log Rotate Max Size (MB)
+          label: Log Rotate Max Size (in bytes)
-          defaultValue: 1
+          description: Maximum file size for log files before they are rotated, in bytes.
 
         - id: $$cap_logrotate_max_backup
           label: Log Rotate Max Backup Count
-          defaultValue: 20
+          defaultValue: '20'
+          validRegex: /^\d{0,}$/
+          description: Number of rotated log files to keep.
 
         - id: $$cap_secret_key
-          label: Secret Key
+          label: Paperless Secret Key
           defaultValue: $$cap_gen_random_hex(64)
+          validRegex: /^([^\s^\/])+$/
+          description: Paperless uses this to make session tokens.
 
         - id: $$cap_admin_user
           label: Admin User
           defaultValue: 'admin'
+          validRegex: /^([^\s^\/])+$/
 
         - id: $$cap_admin_password
           label: Admin Password
-          defaultValue: $$cap_gen_random_hex(64)
+          defaultValue: $$cap_gen_random_hex(10)
+          validRegex: /^([^\s^\/])+$/
+
+        - id: $$cap_admin_email
+          label: Admin Email
+          defaultValue: root@localhost
+          validRegex: /^([^\s^\/])+$/
 
         - id: $$cap_cookie_prefix
           label: Cookie Prefix
           defaultValue: $$cap_appname
+          description: Specify a prefix that is added to the cookies used by paperless to identify the currently logged in user. This is useful for when you’re running two instances of paperless on the same host.
 
         - id: $$cap_ocr_language
           label: OCR Language
           defaultValue: 'eng'
-          description: 'It should be a 3-letter language code consistent with ISO 639 https://www.loc.gov/standards/iso639-2/php/code_list.php This can be a combination of multiple languages such as deu+eng, in which case tesseract will use whatever language matches best. Keep in mind that tesseract uses much more cpu time with multiple languages enabled.'
+          description: Customize the language that paperless will attempt to use when parsing documents. It should be a 3-letter language code consistent with ISO 639 https://www.loc.gov/standards/iso639-2/php/code_list.php This can be a combination of multiple languages such as deu+eng, in which case tesseract will use whatever language matches best. Keep in mind that tesseract uses much more cpu time with multiple languages enabled.
 
         - id: $$cap_ocr_mode
           label: OCR Mode
           defaultValue: 'skip'
+          validRegex: /^(skip|skip_noarchive|redo|force)$/
+          description: Tell paperless when and how to perform ocr on your documents. Four modes are available- skip, skip_noarchive, redo, force. Read more about this in the OCRmyPDF documentation (https://ocrmypdf.readthedocs.io/en/latest/advanced.html#when-ocr-is-skipped).
 
         - id: $$cap_ocr_clean
           label: OCR Clean
           defaultValue: 'clean'
+          validRegex: /^(clean|clean-final|none)$/
+          description: Tells paperless to use unpaper to clean any input document before sending it to tesseract. This uses more resources, but generally results in better OCR results. Available mode- clean, clean-final, none
 
         - id: $$cap_ocr_deskew
           label: OCR Deskew
           defaultValue: 'true'
+          validRegex: /^(true|false)$/
+          description: Tells paperless to correct skewing (slight rotation of input images mainly due to improper scanning).
 
         - id: $$cap_ocr_rotate_pages
           label: OCR Rotate Pages
           defaultValue: 'true'
+          validRegex: /^(true|false)$/
+          description: Tells paperless to correct page rotation (90°, 180° and 270° rotation). If you notice that paperless is not rotating incorrectly rotated pages (or vice versa), try adjusting the threshold up or down (see below).
+
+        - id: $$cap_ocr_rotate_threshold
+          label: OCR Rotate Pages Threshold
+          defaultValue: '12'
+          validRegex: /^\d[\d.]*$/
+          description: This is an arbitrary value reported by tesseract. “15” is a very conservative value, whereas “2” is a very aggressive option and will often result in correctly rotated pages being rotated as well.
 
         - id: $$cap_ocr_output_type
           label: OCR Output Type
           defaultValue: 'pdfa'
+          validRegex: /^(pdf|pdfa|pdfa-1|pdfa-2|pdfa-3)$/
+          description: Specify the the type of PDF documents that paperless should produce. Choices- pdf, pdfa, pdfa-1, pdfa-2, pdfa-3
 
-        - id: $$cap_ocr_page_count
+        - id: $$cap_ocr_pages
           label: OCR Pages Count
           defaultValue: '0'
+          validRegex: /^\d{1,}$/
+          description: Tells paperless to use only the specified amount of pages for OCR. Documents with less than the specified amount of pages get OCR’ed completely. Specifying 1 here will only use the first page. Specifying 0 disables this feature a and always use all pages.
+
+        - id: $$cap_ocr_image_dpi
+          label: OCR Image DPI
+          description: Set this to the DPI your scanner produces images at. Default is none, which will automatically calculate image DPI so that the produced PDF documents are A4 sized.
 
         - id: $cap_ocr_user_args
           label: OCR User Args
-          description: OCRmyPDF Refrence https://ocrmypdf.readthedocs.io/en/latest/api.html#reference
+          description: See https://ocrmypdf.readthedocs.io/en/latest/api.html#reference for valid parameters. Specify arguments as a JSON dictionary. Keep note of lower case booleans and double quoted parameter names and strings.
+
+        #   commenting out but keeping the code if somone tries to add these variables
+        #   these are optional variables and paperless-ng calculates automatically if no value is provided
+        #   but leaving it blank raises ValueError: invalid literal for int() with base 10:
+        # - id: $$cap_task_workers
+        #   label: Paperless Task Workers
+        #   validRegex: /^\d{0,2}$/
+        #   description: Leave blank to calculate automatically based on CPU core count
+
+        # - id: $$cap_threads_per_worker
+        #   label: Paperless Threads per Workers
+        #   validRegex: /^\d{0,2}$/
+        #   description: Leave blank to calculate automatically based on CPU core count. Ensure that the product PAPERLESS_TASK_WORKERS * PAPERLESS_THREADS_PER_WORKER does not exceed your CPU core count
 
         - id: $$cap_timezone
           label: Timezone
           defaultValue: 'UTC'
           description: 'Set the time zone here. See https://docs.djangoproject.com/en/3.1/ref/settings/#std:setting-TIME_ZONE for details on how to set it.'
 
+        - id: $$cap_consumer_polling
+          label: Consumer Polling (seconds)
+          defaultValue: '0'
+          validRegex: /^\d{1,}$/
+          description: Defaults to 0, which disables polling and uses filesystem notifications.
+
+        - id: $$cap_consumer_delete_duplicates
+          label: Consumer Delete Duplicates
+          defaultValue: 'false'
+          validRegex: /^(true|false)$/
+          description: When the consumer detects a duplicate document, it will not touch the original document.
+
+        - id: $$cap_consumer_recursive
+          label: Consumer Recursive
+          defaultValue: 'false'
+          validRegex: /^(true|false)$/
+          description: Enable recursive watching of the consumption directory. Paperless will then pickup files from files in subdirectories within your consumption directory as well.
+
+        - id: $$cap_consumer_subdirs_as_tags
+          label: Consumer Sub Directory as tags
+          defaultValue: 'false'
+          validRegex: /^(true|false)$/
+          description: Set the names of subdirectories as tags for consumed files. E.g. <CONSUMPTION_DIR>/foo/bar/file.pdf will add the tags “foo” and “bar” to the consumed file
+
+        - id: $$cap_convert_memory_limit
+          label: Convert Memory Limit
+          defaultValue: '0'
+          validRegex: /^\d{1,}$/
+          description: For more information on how to use this value, you should search the web for “MAGICK_MEMORY_LIMIT”.
+
+        - id: $$cap_convert_tempdir
+          label: Convert Memory Limit
+          description: For more information on how to use this value, you should search the web for “MAGICK_TMPDIR”.
+
+        - id: $$cap_optimize_thumbnails
+          label: Optimize Thumbnails
+          defaultValue: 'true'
+          validRegex: /^(true|false)$/
+          description: This usually reduces the size of thumbnails by about 20%, but uses considerable compute time during consumption.
+
+        - id: $$cap_pre_consume_script
+          label: Pre Consume Script (path)
+          description: Executed after the consumer sees a new document in the consumption folder, but before any processing of the document is performed. For more information, take a look at Pre-consumption script (https://paperless-ng.readthedocs.io/en/latest/advanced_usage.html?highlight=PAPERLESS_PRE_CONSUME_SCRIPT#pre-consumption-script)
+
+        - id: $$cap_post_consume_script
+          label: Post Consume Script (path)
+          description: Executed after the consumer has successfully processed a document and has moved it into paperless. For more information, take a look at Post-consumption script (https://paperless-ng.readthedocs.io/en/latest/advanced_usage.html#advanced-post-consume-script)
+
+        - id: $$cap_filename_date_order
+          label: Filename Date Order
+          description: Defaults to none, which disables this feature. The date order can be set to any option as specified in https://dateparser.readthedocs.io/en/latest/settings.html#date-order.
+
+        - id: $$cap_thumbnail_font_name
+          label: Thumbnail Font Name
+          defaultValue: '/usr/share/fonts/liberation/LiberationSerif-Regular.ttf'
+          description: Paperless creates thumbnails for plain text files by rendering the content of the file on an image and uses a predefined font for that
+
+        - id: $$cap_paperless_ignore_dates
+          label: Ignore Dates
+          description: You may specify dates in a multitude of formats supported by dateparser (see https://dateparser.readthedocs.io/en/latest/#popular-formats)
+
+        - id: $$cap_webserver_workers
+          label: Webserver Workers
+          defaultValue: '2'
+          validRegex: /^\d{1,}$/
+          description: The number of worker processes the webserver should spawn.
+
+        - id: $$cap_usermap_uid
+          label: Usermap UID
+          defaultValue: '1000'
+          validRegex: /^\d{1,}$/
+          description: Set this to your actual user ID on the host system, which you can get by executing ```id -u```
+
+        - id: $$cap_usermap_gid
+          label: Usermap GID
+          defaultValue: '1000'
+          validRegex: /^\d{1,}$/
+          description: Set this to your actual user ID on the host system, which you can get by executing ```id -g```
+
+        - id: $$cap_docker_ocr_languages
+          label: OCR Languages to install
+          description: Additional OCR languages to install. By default, paperless comes with English, German, Italian, Spanish and French.
+
     instructions:
         start: >-
             Paperless is an application by Daniel Quinn and others that indexes your scanned documents and allows you to easily search for documents and store metadata alongside your documents.