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

Merge branch 'dev' into feature-created-date

Browse Source
This commit is contained in:
shamoon
2022-05-26 14:28:33 -07:00
committed by GitHub
parent e7c370b3eb d7654e978d
commit e168bde125
118 changed files with 5276 additions and 3044 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
docs/Makefile
View File

@@ -24,6 +24,7 @@ I18NSPHINXOPTS = $(PAPEROPT_$(PAPER)) $(SPHINXOPTS) .
help:
@echo "Please use \`make <target>' where <target> is one of"
@echo " html to make standalone HTML files"
@echo " livehtml to preview changes with live reload in your browser"
@echo " dirhtml to make HTML files named index.html in directories"
@echo " singlehtml to make a single large HTML file"
@echo " pickle to make pickle files"
@@ -54,6 +55,9 @@ html:
@echo
@echo "Build finished. The HTML pages are in $(BUILDDIR)/html."
livehtml:
sphinx-autobuild "./" "$(BUILDDIR)" $(O)
dirhtml:
$(SPHINXBUILD) -b dirhtml $(ALLSPHINXOPTS) $(BUILDDIR)/dirhtml
@echo

4
docs/_static/css/custom.css vendored
View File

@@ -64,6 +64,10 @@ body {
color: var(--color-text-body);
}
.rst-content p {
word-break: break-word;
}
h1, h2, h3, h4, h5, h6 {
font-family: inherit;
}

52
docs/_static/js/darkmode.js vendored
View File

@@ -1,47 +1,47 @@
let toggleButton;
let icon;
let toggleButton
let icon
function load() {
"use strict";
'use strict'
toggleButton = document.createElement("button");
toggleButton.setAttribute("title", "Toggle dark mode");
toggleButton.classList.add("dark-mode-toggle");
icon = document.createElement("i");
icon.classList.add("fa", darkModeState ? "fa-sun-o" : "fa-moon-o");
toggleButton.appendChild(icon);
document.body.prepend(toggleButton);
toggleButton = document.createElement('button')
toggleButton.setAttribute('title', 'Toggle dark mode')
toggleButton.classList.add('dark-mode-toggle')
icon = document.createElement('i')
icon.classList.add('fa', darkModeState ? 'fa-sun-o' : 'fa-moon-o')
toggleButton.appendChild(icon)
document.body.prepend(toggleButton)
// Listen for changes in the OS settings
// addListener is used because older versions of Safari don't support addEventListener
// prefersDarkQuery set in <head>
if (prefersDarkQuery) {
prefersDarkQuery.addListener(function (evt) {
toggleDarkMode(evt.matches);
});
toggleDarkMode(evt.matches)
})
}
// Initial setting depending on the prefers-color-mode or localstorage
// darkModeState should be set in the document <head> to prevent flash
if (darkModeState == undefined) darkModeState = false;
toggleDarkMode(darkModeState);
if (darkModeState == undefined) darkModeState = false
toggleDarkMode(darkModeState)
// Toggles the "dark-mode" class on click and sets localStorage state
toggleButton.addEventListener("click", () => {
darkModeState = !darkModeState;
toggleButton.addEventListener('click', () => {
darkModeState = !darkModeState
toggleDarkMode(darkModeState);
localStorage.setItem("dark-mode", darkModeState);
});
toggleDarkMode(darkModeState)
localStorage.setItem('dark-mode', darkModeState)
})
}
function toggleDarkMode(state) {
document.documentElement.classList.toggle("dark-mode", state);
document.documentElement.classList.toggle("light-mode", !state);
icon.classList.remove("fa-sun-o");
icon.classList.remove("fa-moon-o");
icon.classList.add(state ? "fa-sun-o" : "fa-moon-o");
darkModeState = state;
document.documentElement.classList.toggle('dark-mode', state)
document.documentElement.classList.toggle('light-mode', !state)
icon.classList.remove('fa-sun-o')
icon.classList.remove('fa-moon-o')
icon.classList.add(state ? 'fa-sun-o' : 'fa-moon-o')
darkModeState = state
}
document.addEventListener("DOMContentLoaded", load);
document.addEventListener('DOMContentLoaded', load)

8
docs/administration.rst
View File

@@ -118,10 +118,10 @@ Then you can start paperless-ngx with ``-d`` to have it run in the background.
image: ghcr.io/paperless-ngx/paperless-ngx:latest
.. note::
In version 1.7.1 and onwards, the Docker image can now pinned to a release series.
In version 1.7.1 and onwards, the Docker image can now be pinned to a release series.
This is often combined with automatic updaters such as Watchtower to allow safer
unattended upgrading to new bugfix releases only. It is still recommended to always
review release notes before upgrading. To ping your install to a release series, edit
review release notes before upgrading. To pin your install to a release series, edit
the ``docker-compose.yml`` find the line that says
.. code::
@@ -390,8 +390,8 @@ the naming scheme.
.. warning::
Since this command moves you documents around a lot, it is advised to to
a backup before. The renaming logic is robust and will never overwrite
Since this command moves your documents, it is advised to do
a backup beforehand. The renaming logic is robust and will never overwrite
or delete a file, but you can't ever be careful enough.
.. code::

124
docs/advanced_usage.rst
View File

@@ -7,12 +7,12 @@ easier.
.. _advanced-matching:
Matching tags, correspondents and document types
################################################
Matching tags, correspondents, document types, and storage paths
################################################################
Paperless will compare the matching algorithms defined by every tag and
correspondent already set in your database to see if they apply to the text in
a document. In other words, if you defined a tag called ``Home Utility``
Paperless will compare the matching algorithms defined by every tag, correspondent,
document type, and storage path in your database to see if they apply to the text
in a document. In other words, if you define a tag called ``Home Utility``
that had a ``match`` property of ``bc hydro`` and a ``matching_algorithm`` of
``literal``, Paperless will automatically tag your newly-consumed document with
your ``Home Utility`` tag so long as the text ``bc hydro`` appears in the body
@@ -22,10 +22,10 @@ The matching logic is quite powerful. It supports searching the text of your
document with different algorithms, and as such, some experimentation may be
necessary to get things right.
In order to have a tag, correspondent, or type assigned automatically to newly
consumed documents, assign a match and matching algorithm using the web
interface. These settings define when to assign correspondents, tags, and types
to documents.
In order to have a tag, correspondent, document type, or storage path assigned
automatically to newly consumed documents, assign a match and matching algorithm
using the web interface. These settings define when to assign tags, correspondents,
document types, and storage paths to documents.
The following algorithms are available:
@@ -37,7 +37,7 @@ The following algorithms are available:
* **Literal:** Matches only if the match appears exactly as provided (i.e. preserve ordering) in the PDF.
* **Regular expression:** Parses the match as a regular expression and tries to
find a match within the document.
* **Fuzzy match:** I dont know. Look at the source.
* **Fuzzy match:** I don't know. Look at the source.
* **Auto:** Tries to automatically match new documents. This does not require you
to set a match. See the notes below.
@@ -47,9 +47,9 @@ defining a match text of ``"Bank of America" BofA`` using the *any* algorithm,
will match documents that contain either "Bank of America" or "BofA", but will
not match documents containing "Bank of South America".
Then just save your tag/correspondent and run another document through the
consumer. Once complete, you should see the newly-created document,
automatically tagged with the appropriate data.
Then just save your tag, correspondent, document type, or storage path and run
another document through the consumer. Once complete, you should see the
newly-created document, automatically tagged with the appropriate data.
.. _advanced-automatic_matching:
@@ -58,9 +58,9 @@ Automatic matching
==================
Paperless-ngx comes with a new matching algorithm called *Auto*. This matching
algorithm tries to assign tags, correspondents, and document types to your
documents based on how you have already assigned these on existing documents. It
uses a neural network under the hood.
algorithm tries to assign tags, correspondents, document types, and storage paths
to your documents based on how you have already assigned these on existing documents.
It uses a neural network under the hood.
If, for example, all your bank statements of your account 123 at the Bank of
America are tagged with the tag "bofa_123" and the matching algorithm of this
@@ -80,20 +80,21 @@ feature:
that the neural network only learns from documents which you have correctly
tagged before.
* The matching algorithm can only work if there is a correlation between the
tag, correspondent, or document type and the document itself. Your bank
statements usually contain your bank account number and the name of the bank,
so this works reasonably well, However, tags such as "TODO" cannot be
automatically assigned.
tag, correspondent, document type, or storage path and the document itself.
Your bank statements usually contain your bank account number and the name
of the bank, so this works reasonably well, However, tags such as "TODO"
cannot be automatically assigned.
* The matching algorithm needs a reasonable number of documents to identify when
to assign tags, correspondents, and types. If one out of a thousand documents
has the correspondent "Very obscure web shop I bought something five years
ago", it will probably not assign this correspondent automatically if you buy
something from them again. The more documents, the better.
to assign tags, correspondents, storage paths, and types. If one out of a
thousand documents has the correspondent "Very obscure web shop I bought
something five years ago", it will probably not assign this correspondent
automatically if you buy something from them again. The more documents, the better.
* Paperless also needs a reasonable amount of negative examples to decide when
not to assign a certain tag, correspondent or type. This will usually be the
case as you start filling up paperless with documents. Example: If all your
documents are either from "Webshop" and "Bank", paperless will assign one of
these correspondents to ANY new document, if both are set to automatic matching.
not to assign a certain tag, correspondent, document type, or storage path. This will
usually be the case as you start filling up paperless with documents.
Example: If all your documents are either from "Webshop" and "Bank", paperless
will assign one of these correspondents to ANY new document, if both are set
to automatic matching.
Hooking into the consumption process
####################################
@@ -268,6 +269,17 @@ If paperless detects that two documents share the same filename, paperless will
append ``_01``, ``_02``, etc to the filename. This happens if all the placeholders in a filename
evaluate to the same value.
.. hint::
You can affect how empty placeholders are treated by changing the following setting to
`true`.
.. code::
PAPERLESS_FILENAME_FORMAT_REMOVE_NONE=True
Doing this results in all empty placeholders resolving to "" instead of "none" as stated above.
Spaces before empty placeholders are removed as well, empty directories are omitted.
.. hint::
Paperless checks the filename of a document whenever it is saved. Therefore,
@@ -290,3 +302,59 @@ evaluate to the same value.
However, keep in mind that inside docker, if files get stored outside of the
predefined volumes, they will be lost after a restart of paperless.
Storage paths
#############
One of the best things in Paperless is that you can not only access the documents via the
web interface, but also via the file system.
When as single storage layout is not sufficient for your use case, storage paths come to
the rescue. Storage paths allow you to configure more precisely where each document is stored
in the file system.
- Each storage path is a `PAPERLESS_FILENAME_FORMAT` and follows the rules described above
- Each document is assigned a storage path using the matching algorithms described above, but
can be overwritten at any time
For example, you could define the following two storage paths:
1. Normal communications are put into a folder structure sorted by `year/correspondent`
2. Communications with insurance companies are stored in a flat structure with longer file names,
but containing the full date of the correspondence.
.. code::
By Year = {created_year}/{correspondent}/{title}
Insurances = Insurances/{correspondent}/{created_year}-{created_month}-{created_day} {title}
If you then map these storage paths to the documents, you might get the following result.
For simplicity, `By Year` defines the same structure as in the previous example above.
.. code:: text
2019/ # By Year
My bank/
Statement January.pdf
Statement February.pdf
Insurances/ # Insurances
Healthcare 123/
2022-01-01 Statement January.pdf
2022-02-02 Letter.pdf
2022-02-03 Letter.pdf
Dental 456/
2021-12-01 New Conditions.pdf
.. hint::
Defining a storage path is optional. If no storage path is defined for a document, the global
`PAPERLESS_FILENAME_FORMAT` is applied.
.. caution::
If you adjust the format of an existing storage path, old documents don't get relocated automatically.
You need to run the :ref:`document renamer <utilities-renamer>` to adjust their pathes.

1947
docs/changelog.md Normal file
View File

File diff suppressed because it is too large Load Diff

1787
docs/changelog.rst
View File

File diff suppressed because it is too large Load Diff

6
docs/conf.py
View File

@@ -14,13 +14,17 @@ extensions = [
"sphinx.ext.imgmath",
"sphinx.ext.viewcode",
"sphinx_rtd_theme",
"myst_parser",
]
# Add any paths that contain templates here, relative to this directory.
templates_path = ["_templates"]
# The suffix of source filenames.
source_suffix = ".rst"
source_suffix = {
".rst": "restructuredtext",
".md": "markdown",
}
# The encoding of source files.
# source_encoding = 'utf-8-sig'

33
docs/configuration.rst
View File

@@ -111,6 +111,14 @@ PAPERLESS_FILENAME_FORMAT=<format>
Default is none, which disables this feature.
PAPERLESS_FILENAME_FORMAT_REMOVE_NONE=<bool>
Tells paperless to replace placeholders in `PAPERLESS_FILENAME_FORMAT` that would resolve
to 'none' to be omitted from the resulting filename. This also holds true for directory
names.
See :ref:`advanced-file_name_handling` for details.
Defaults to `false` which disables this feature.
PAPERLESS_LOGGING_DIR=<path>
This is where paperless will store log files.
@@ -416,14 +424,23 @@ PAPERLESS_OCR_IMAGE_DPI=<num>
the produced PDF documents are A4 sized.
PAPERLESS_OCR_MAX_IMAGE_PIXELS=<num>
Paperless will not OCR images that have more pixels than this limit.
This is intended to prevent decompression bombs from overloading paperless.
Increasing this limit is desired if you face a DecompressionBombError despite
the concerning file not being malicious; this could e.g. be caused by invalidly
recognized metadata.
If you have enough resources or if you are certain that your uploaded files
are not malicious you can increase this value to your needs.
The default value is 256000000, an image with more pixels than that would not be parsed.
Paperless will raise a warning when OCRing images which are over this limit and
will not OCR images which are more than twice this limit. Note this does not
prevent the document from being consumed, but could result in missing text content.
If unset, will default to the value determined by
`Pillow <https://pillow.readthedocs.io/en/stable/reference/Image.html#PIL.Image.MAX_IMAGE_PIXELS>`_.
.. note::
Increasing this limit could cause Paperless to consume additional resources
when consuming a file. Be sure you have sufficient system resources.
.. caution::
The limit is intended to prevent malicious files from consuming system resources
and causing crashes and other errors. Only increase this value if you are certain
your documents are not malicious and you need the text which was not OCRed
PAPERLESS_OCR_USER_ARGS=<json>
OCRmyPDF offers many more options. Use this parameter to specify any

2
docs/index.rst
View File

@@ -52,7 +52,7 @@ resources in the documentation:
* Paperless is now integrated with a
:ref:`task processing queue <setup-task_processor>` that tells you
at a glance when and why something is not working.
* The :ref:`changelog <paperless_changelog>` contains a detailed list of all changes
* The :doc:`changelog </changelog>` contains a detailed list of all changes
in paperless-ngx.
Contents

1
docs/requirements.txt
View File

@@ -0,0 +1 @@
myst-parser==0.17.2

83
docs/scanners.rst
View File

@@ -13,43 +13,45 @@ that works right for you based on recommendations from other Paperless users.
Physical scanners
=================
+---------+----------------+-----+------+-----+-----+------+----------+----------------+
| Brand | Model | Supports | Recommended By |
+---------+----------------+-----+------+-----+-----+------+----------+----------------+
| | | FTP | SFTP | NFS | SMB | SMTP | API [1]_ | |
+=========+================+=====+======+=====+=====+======+==========+================+
| Brother | `ADS-1700W`_ | yes | | | yes | yes | |`holzhannes`_ |
+---------+----------------+-----+------+-----+-----+------+----------+----------------+
| Brother | `ADS-1600W`_ | yes | | | yes | yes | |`holzhannes`_ |
+---------+----------------+-----+------+-----+-----+------+----------+----------------+
| Brother | `ADS-1500W`_ | yes | | | yes | yes | |`danielquinn`_ |
+---------+----------------+-----+------+-----+-----+------+----------+----------------+
| Brother | `ADS-1100W`_ | yes | | | | | |`ytzelf`_ |
+---------+----------------+-----+------+-----+-----+------+----------+----------------+
| Brother | `ADS-2800W`_ | yes | yes | | yes | yes | |`philpagel`_ |
+---------+----------------+-----+------+-----+-----+------+----------+----------------+
| Brother | `MFC-J6930DW`_ | yes | | | | | |`ayounggun`_ |
+---------+----------------+-----+------+-----+-----+------+----------+----------------+
| Brother | `MFC-L5850DW`_ | yes | | | | yes | |`holzhannes`_ |
+---------+----------------+-----+------+-----+-----+------+----------+----------------+
| Brother | `MFC-L2750DW`_ | yes | | | yes | yes | |`muued`_ |
+---------+----------------+-----+------+-----+-----+------+----------+----------------+
| Brother | `MFC-J5910DW`_ | yes | | | | | |`bmsleight`_ |
+---------+----------------+-----+------+-----+-----+------+----------+----------------+
| Brother | `MFC-8950DW`_ | yes | | | yes | yes | |`philpagel`_ |
+---------+----------------+-----+------+-----+-----+------+----------+----------------+
| Brother | `MFC-9142CDN`_ | yes | | | yes | | |`REOLDEV`_ |
+---------+----------------+-----+------+-----+-----+------+----------+----------------+
| Fujitsu | `ix500`_ | yes | | | yes | | |`eonist`_ |
+---------+----------------+-----+------+-----+-----+------+----------+----------------+
| Epson | `ES-580W`_ | yes | | | yes | yes | |`fignew`_ |
+---------+----------------+-----+------+-----+-----+------+----------+----------------+
| Epson | `WF-7710DWF`_ | yes | | | yes | | |`Skylinar`_ |
+---------+----------------+-----+------+-----+-----+------+----------+----------------+
| Fujitsu | `S1300i`_ | yes | | | yes | | |`jonaswinkler`_ |
+---------+----------------+-----+------+-----+-----+------+----------+----------------+
| Doxie | `Q2`_ | | | | | | yes |`Unkn0wnCat`_ |
+---------+----------------+-----+------+-----+-----+------+----------+----------------+
+---------+-------------------+-----+------+-----+----------+------+----------+----------------+
| Brand | Model | Supports | Recommended By |
+---------+-------------------+-----+------+-----+----------+------+----------+----------------+
| | | FTP | SFTP | NFS | SMB | SMTP | API [1]_ | |
+=========+===================+=====+======+=====+==========+======+==========+================+
| Brother | `ADS-1700W`_ | yes | | | yes | yes | |`holzhannes`_ |
+---------+-------------------+-----+------+-----+----------+------+----------+----------------+
| Brother | `ADS-1600W`_ | yes | | | yes | yes | |`holzhannes`_ |
+---------+-------------------+-----+------+-----+----------+------+----------+----------------+
| Brother | `ADS-1500W`_ | yes | | | yes | yes | |`danielquinn`_ |
+---------+-------------------+-----+------+-----+----------+------+----------+----------------+
| Brother | `ADS-1100W`_ | yes | | | | | |`ytzelf`_ |
+---------+-------------------+-----+------+-----+----------+------+----------+----------------+
| Brother | `ADS-2800W`_ | yes | yes | | yes | yes | |`philpagel`_ |
+---------+-------------------+-----+------+-----+----------+------+----------+----------------+
| Brother | `MFC-J6930DW`_ | yes | | | | | |`ayounggun`_ |
+---------+-------------------+-----+------+-----+----------+------+----------+----------------+
| Brother | `MFC-L5850DW`_ | yes | | | | yes | |`holzhannes`_ |
+---------+-------------------+-----+------+-----+----------+------+----------+----------------+
| Brother | `MFC-L2750DW`_ | yes | | | yes | yes | |`muued`_ |
+---------+-------------------+-----+------+-----+----------+------+----------+----------------+
| Brother | `MFC-J5910DW`_ | yes | | | | | |`bmsleight`_ |
+---------+-------------------+-----+------+-----+----------+------+----------+----------------+
| Brother | `MFC-8950DW`_ | yes | | | yes | yes | |`philpagel`_ |
+---------+-------------------+-----+------+-----+----------+------+----------+----------------+
| Brother | `MFC-9142CDN`_ | yes | | | yes | | |`REOLDEV`_ |
+---------+-------------------+-----+------+-----+----------+------+----------+----------------+
| Canon | `Maxify MB 5350`_ | | | | yes [2]_ | yes | |`eingemaischt`_ |
+---------+-------------------+-----+------+-----+----------+------+----------+----------------+
| Fujitsu | `ix500`_ | yes | | | yes | | |`eonist`_ |
+---------+-------------------+-----+------+-----+----------+------+----------+----------------+
| Epson | `ES-580W`_ | yes | | | yes | yes | |`fignew`_ |
+---------+-------------------+-----+------+-----+----------+------+----------+----------------+
| Epson | `WF-7710DWF`_ | yes | | | yes | | |`Skylinar`_ |
+---------+-------------------+-----+------+-----+----------+------+----------+----------------+
| Fujitsu | `S1300i`_ | yes | | | yes | | |`jonaswinkler`_ |
+---------+-------------------+-----+------+-----+----------+------+----------+----------------+
| Doxie | `Q2`_ | | | | | | yes |`Unkn0wnCat`_ |
+---------+-------------------+-----+------+-----+----------+------+----------+----------------+
.. _MFC-L5850DW: https://www.brother-usa.com/products/mfcl5850dw
.. _MFC-L2750DW: https://www.brother.de/drucker/laserdrucker/mfc-l2750dw
@@ -58,6 +60,7 @@ Physical scanners
.. _ADS-1500W: https://www.brother.ca/en/p/ads1500w
.. _ADS-1100W: https://support.brother.com/g/b/downloadtop.aspx?c=fr&lang=fr&prod=ads1100w_eu_as_cn
.. _ADS-2800W: https://www.brother-usa.com/products/ads2800w
.. _Maxify MB 5350: https://www.canon.de/printers/inkjet/maxify/maxify_mb5350/specification.html
.. _MFC-J6930DW: https://www.brother.ca/en/p/MFCJ6930DW
.. _MFC-J5910DW: https://www.brother.co.uk/printers/inkjet-printers/mfcj5910dw
.. _MFC-8950DW: https://www.brother-usa.com/products/mfc8950dw
@@ -81,8 +84,11 @@ Physical scanners
.. _Unkn0wnCat: https://github.com/Unkn0wnCat
.. _muued: https://github.com/muued
.. _philpagel: https://github.com/philpagel
.. _eingemaischt: https://github.com/eingemaischt
.. [1] Scanners with API Integration allow to push scanned documents directly to :ref:`Paperless API <api-file_uploads>`, sometimes referred to as Webhook or Document POST.
.. [2] Canon Multi Function Printers show strange behavior over SMB. They close and reopen the file after every page. It's recommended to tune the
:ref:`polling <configuration-polling>` and :ref:`inotify <configuration-inotify>` configuration values for your scanner. The scanner timeout is 3 minutes, so ``180`` is a good starting point.
Mobile phone software
=====================
@@ -105,6 +111,9 @@ You can use your phone to "scan" documents. The regular camera app will work, bu
On Android, you can use these applications in combination with one of the :ref:`Paperless-ngx compatible apps <usage-mobile_upload>` to "Share" the documents produced by these scanner apps with paperless. On iOS, you can share the scanned documents via iOS-Sharing to other mail, WebDav or FTP apps.
There is also an iOS Shortcut that allows you to directly upload text, PDF and image documents available here: https://www.icloud.com/shortcuts/d234abc0885040129d9d75fa45fe1154
Please note this only works for documents downloaded to iCloud / the device, in other words not directly from a URL.
.. _Office Lens: https://play.google.com/store/apps/details?id=com.microsoft.office.officelens
.. _Genius Scan: https://play.google.com/store/apps/details?id=com.thegrizzlylabs.geniusscan.free
.. _OCR Scanner - QuickScan: https://apps.apple.com/us/app/quickscan-scanner-text-ocr/id1513790291

8
docs/setup.rst
View File

@@ -332,6 +332,12 @@ writing. Windows is not and will never be supported.
3. Optional. Install ``postgresql`` and configure a database, user and password for paperless. If you do not wish
to use PostgreSQL, SQLite is available as well.
.. note::
On bare-metal installations using SQLite, ensure the
`JSON1 extension <https://code.djangoproject.com/wiki/JSON1Extension>`_ is enabled. This is
usually the case, but not always.
4. Get the release archive from `<https://github.com/paperless-ngx/paperless-ngx/releases>`_.
If you clone the git repo as it is, you also have to compile the front end by yourself.
Extract the archive to a place from where you wish to execute it, such as ``/opt/paperless``.
@@ -513,7 +519,7 @@ how you installed paperless.
This setup describes how to update an existing paperless Docker installation.
The important things to keep in mind are as follows:
* Read the :ref:`changelog <paperless_changelog>` and take note of breaking changes.
* Read the :doc:`changelog </changelog>` and take note of breaking changes.
* You should decide if you want to stick with SQLite or want to migrate your database
to PostgreSQL. See :ref:`setup-sqlite_to_psql` for details on how to move your data from
SQLite to PostgreSQL. Both work fine with paperless. However, if you already have a

9
docs/troubleshooting.rst
View File

@@ -237,11 +237,12 @@ open the affected documents in paperless for editing. Paperless will continue to
show the invalid metadata.
Consumer fails with a FileNotFoundError
############################
#######################################
You might find messages like these in your log files:
.. code::
[ERROR] [paperless.consumer] Error while consuming document SCN_0001.pdf: FileNotFoundError: [Errno 2] No such file or directory: '/tmp/ocrmypdf.io.yhk3zbv0/origin.pdf'
Traceback (most recent call last):
File "/app/paperless/src/paperless_tesseract/parsers.py", line 261, in parse
@@ -266,11 +267,12 @@ check for documents, try adjusting the :ref:`inotify configuration <configuratio
try adjusting the :ref:`polling configuration <configuration-polling>`.
Consumer fails waiting for file to remain unmodified.
############################
#####################################################
You might find messages like these in your log files:
.. code::
[ERROR] [paperless.management.consumer] Timeout while waiting on file /usr/src/paperless/src/../consume/SCN_0001.pdf to remain unmodified.
This indicates paperless timed out while waiting for the file to be completely written to the consume folder.
@@ -282,11 +284,12 @@ Adjusting :ref:`polling configuration <configuration-polling>` values should res
back in, for the initial failing file to be consumed.
Consumer fails reporting "OS reports file as busy still".
############################
#########################################################
You might find messages like these in your log files:
.. code::
[WARNING] [paperless.management.consumer] Not consuming file /usr/src/paperless/src/../consume/SCN_0001.pdf: OS reports file as busy still
This indicates paperless was unable to open the file, as the OS reported the file as still being in use. To prevent a