gistfile1.txt

# Example of papermerge.conf.py
#
#  papermerge.conf.py - is a configuration files with python syntax
#
# Copy this file to /etc/papermerge.conf.py or to your project's root directory
# and modify it to suit your needs.
# As this file contains passwords it should only be readable by the user
# running Papermerge.


#   Paths & Folders
#######################


# You can specify where you want the SQLite database to be stored instead of
# the default location of /data/ within the install directory.
DBDIR = "./db"

# Override the default  MEDIA_ROOT. This is where all files are stored.
# The default location is /media/documents/ within the install directory.
MEDIA_DIR = "./media"

# Override the default  STATIC_ROOT. All static files created with
# "collectstatic" manager-command, their default location is /.... ?
STATIC_DIR = "./static"

# Override the default  MEDIA_URL here.  Unless you're hosting Papermerge off a subdomain
# like /papermerge/, you probably don't need to change this.
#MEDIA_URL = "/media/"

# Override the  STATIC_URL here.  Unless you're hosting Papermerge off a
# subdomain like /papermerge/, you probably don't need to change this.
# STATIC_URL = "/static/"


#   Document Importer
#########################

# Configuration for ./manage.py importer command

# This where ./manage importer will import your documents from.
# IMPORTER_DIR = "/path/to/import/dir"

# Files are considered ready for import if they have been unmodified
# for this duration (in seconds)
# FILES_MIN_UNMODIFIED_DURATION = 1

# This setting is ignored on Linux where inotify is used instead of a
# polling loop.
# The number of seconds that Papermerge will wait between checking
# IMPORTER_DIR. If you tend to write documents to this directory
# rarely, you may want to use a higher value than the default (5).
# IMPORTER_LOOP_TIME = 5


# These values are required if you want papermerge to import email attachments
# from specific email account.
# If you don't define a HOST, mail checking will just be disabled.
# IMPORT_MAIL_HOST = ""
# IMPORT_MAIL_USER = ""
# IMPORT_MAIL_PASS = ""

# Override the default IMAP inbox here. If not set Papermerge defaults to
# "INBOX".
#IMPORT_MAIL_INBOX="INBOX"

# Any email sent to the target account that does not contain this text will be ignored.
# IMPORT_MAIL_SECRET = ""

#   Worker
########################

# These settings are used by built-in asyncronious task (celery).
# By default, celery will use local directory as message broker.
# This directory will be created automatically when you start papermerge.
# TASK_QUEUE_DIR = "/var/tmp/papermerge/queue"


#   Storage
###############

# DEFAULT_FILE_STORAGE = "mglib.storage.FileSystemStorage"


#  Search Backend
###################

# SEARCH_BACKEND = "papermerge.search.backends.db.SearchBackend"

# Metadata
####################

# Metadata plugins. These are external applications (very simple ones), that will
# extract and populate metadata fields.
#
#   METADATA_PLUGINS = [
#       "lidl_receipts_de.Lidl",             # (1)
#       "deutschlandradio.Deutschlandradio"  # (2)
#    ]
#
# (1) check:
#     https://github.com/papermerge/lidl-receipts-de
# (2) check:
#     https://github.com/papermerge/papermerge-meta-plugin-ard-zdf-deutschlandradio

# METADATA_PLUGINS = []

# METADATA_DATE_FORMATS = [
#     'dd.mm.yy',
#     'dd.mm.yyyy',
#     'dd.M.yyyy',
#     'month',  Month as locale’s full name, January, February, …, December (en_US);
				#Januar, Februar, …, Dezember (de_DE)
# ]
#
# METADATA_CURRENCY_FORMATS = [
#     'dd.cc',
#     'dd,cc'
# ]
#
# METADATA_NUMERIC_FORMATS = [
#     'dddd',
#     'd,ddd',
#     'd.ddd'
# ]


# OCR
#######

# Customize the default language that tesseract 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
# Examples:
# eng = for English
# deu = for German
# spa = for Spanish

OCR_DEFAULT_LANGUAGE = "eng"

OCR_LANGUAGES = {
    "eng": "English"
}


# Internationalization & Localization
######################################

# Internationalization = i18n
#
# In what language is user interface.
# At this point there two options:
#
#  en, en-US, en-UK, ... = for user interface in English language
#  de, de-DE, de-AT, ... = for user interface in German language
#
#  English is default fallback i.e. if you don't specify anything,
#  of specify unsupported language - English will be used.

LANGUAGE_CODE = 'en'

# If is set to True, will use same language code as your Web Browser (agent) does.
# Browsers send 'Accept-Language' header with their locale.
# For more, read: https://developer.mozilla.org/en-US/docs/Web/HTTP/Headers/Accept-Language
# If set to True  - will override LANGUAGE_CODE option
# If set to False - language code specified in LANGUAGE_CODE option will be used.

LANGUAGE_FROM_AGENT = False


# Binary Dependencies
###########################
#
# Papermerge uses a number of open source 3rd parties for various purposes.
# One of the most obvious example is tesseract - used to OCR documents (extract
# text from binary image file). Another, less obvious example is pdfinfo
# utility provided by poppler-utils package: pdfinfo is used to count number of
# pages in pdf document.
#
# Settings prefixed with BINARY_ are used to configure paths to those dependencies.
# Here is the full list of all binary dependencies and their default values.

# file utility used to find out mime type of a file

# BINARY_FILE = "/usr/bin/file"

# Provided by ImageMagick package.
# convert is used for resizing images.

# BINARY_CONVERT = "/usr/bin/convert"

# Provided by Poppler Utils.
# pdftoppm used to extract images from PDF file.

# BINARY_PDFTOPPM = "/usr/bin/pdftoppm"

# Provided by Poppler Utils.
# pdfinfo is used to get page count in PDF file

# BINARY_PDFINFO = "/usr/bin/pdfinfo"

# Provided by ImageMagick package.
# identity is used to get number of pages in TIFF file.

# BINARY_IDENTIFY = "/usr/bin/identify"

# Provided by tesseract package.
# tesseract is used to extract text from images/PDF files.

# BINARY_OCR = "/usr/bin/tesseract"

# Provided by pdftk package
# pdftok is used to reorder, cut/paste, delete pages withing PDF document

# BINARY_PDFTK = "/usr/bin/pdftk"