Merge pull request #1567 from paperless-ngx/feature-process-names

Feature: Display django-q process names

.build-config.json

@@ -0,0 +1,9 @@
+{
+  "qpdf": {
+      "version": "10.6.3"
+    },
+  "jbig2enc": {
+      "version": "0.29",
+      "git_tag": "0.29"
+    }
+}

.dockerignore

@@ -1,3 +1,4 @@
+**/__pycache__
 /src-ui/.vscode
 /src-ui/node_modules
 /src-ui/dist
@@ -10,3 +11,11 @@
 .pytest_cache
 /dist
 /scripts
+/resources
+**/tests
+**/*.spec.ts
+**/htmlcov
+/src/.pytest_cache
+.idea
+.venv/
+.vscode/

.editorconfig

@@ -18,7 +18,16 @@ max_line_length = off
 indent_size = 4
 indent_style = space
 
-[*.yml]
+[*.{yml,yaml}]
+indent_style = space
+
+[*.rst]
+indent_style = space
+
+[*.md]
+indent_style = space
+
+[Pipfile.lock]
 indent_style = space
 
 # Tests don't get a line width restriction.  It's still a good idea to follow
@@ -26,3 +35,6 @@ indent_style = space
 # violate it.
 [**/test_*.py]
 max_line_length = off
+
+[Dockerfile*]
+indent_style = space

.env

@@ -1 +1,2 @@
-COMPOSE_PROJECT_NAME=paperless
+COMPOSE_PROJECT_NAME=paperless
+export PROMPT="(pipenv-projectname)$P$G"

.github/ISSUE_TEMPLATE/bug-report.yml

@@ -0,0 +1,88 @@
+name: Bug report
+description: Something is not working
+title: "[BUG] Concise description of the issue"
+labels: ["bug", "unconfirmed"]
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Have a question? 👉 [Start a new discussion](https://github.com/paperless-ngx/paperless-ngx/discussions/new) or [ask in chat](https://matrix.to/#/#paperless:adnidor.de).
+
+        Before opening an issue, please double check:
+
+        - [The troubleshooting documentation](https://paperless-ngx.readthedocs.io/en/latest/troubleshooting.html).
+        - [The installation instructions](https://paperless-ngx.readthedocs.io/en/latest/setup.html#installation).
+        - [Existing issues and discussions](https://github.com/paperless-ngx/paperless-ngx/search?q=&type=issues).
+
+        If you encounter issues while installing or configuring Paperless-ngx, please post in the ["Support" section of the discussions](https://github.com/paperless-ngx/paperless-ngx/discussions/new?category=support).
+  - type: textarea
+    id: description
+    attributes:
+      label: Description
+      description: A clear and concise description of what the bug is. If applicable, add screenshots to help explain your problem.
+      placeholder: |
+        Currently Paperless does not work when...
+
+        [Screenshot if applicable]
+    validations:
+      required: true
+  - type: textarea
+    id: reproduction
+    attributes:
+      label: Steps to reproduce
+      description: Steps to reproduce the behavior.
+      placeholder: |
+        1. Go to '...'
+        2. Click on '....'
+        3. See error
+    validations:
+      required: true
+  - type: textarea
+    id: logs
+    attributes:
+      label: Webserver logs
+      description: If available, post any logs from the web server related to your issue.
+      render: bash
+  - type: input
+    id: version
+    attributes:
+      label: Paperless-ngx version
+      placeholder: e.g. 1.6.0
+    validations:
+      required: true
+  - type: input
+    id: host-os
+    attributes:
+      label: Host OS
+      description: Host OS of the machine running paperless-ngx. Please add the architecture (uname -m) if applicable.
+      placeholder: e.g. Archlinux / Ubuntu 20.04 / Raspberry Pi `arm64`
+    validations:
+      required: true
+  - type: dropdown
+    id: install-method
+    attributes:
+      label: Installation method
+      options:
+        - Docker - official image
+        - Docker - linuxserver.io image
+        - Bare metal
+        - Other (please describe above)
+      description: Note there are significant differences from the official image and linuxserver.io, please check if your issue is specific to the third-party image.
+    validations:
+      required: true
+  - type: input
+    id: browser
+    attributes:
+      label: Browser
+      description: Which browser you are using, if relevant.
+      placeholder: e.g. Chrome, Safari
+  - type: input
+    id: config-changes
+    attributes:
+      label: Configuration changes
+      description: Any configuration changes you made in `docker-compose.yml`, `docker-compose.env` or `paperless.conf`.
+  - type: input
+    id: other
+    attributes:
+      label: Other
+      description: Any other relevant details.

.github/ISSUE_TEMPLATE/config.yml

@@ -0,0 +1,11 @@
+blank_issues_enabled: false
+contact_links:
+  - name: 🤔 Questions and Help
+    url: https://github.com/paperless-ngx/paperless-ngx/discussions
+    about: This issue tracker is not for support questions. Please refer to our Discussions.
+  - name: 💬 Chat
+    url: https://matrix.to/#/#paperless:adnidor.de
+    about: Want to discuss Paperless-ngx with others? Check out our chat.
+  - name: 🚀 Feature Request
+    url: https://github.com/paperless-ngx/paperless-ngx/discussions/new?category=feature-requests
+    about: Remember to search for existing feature requests and "up-vote" any you like

.github/PULL_REQUEST_TEMPLATE.md

@@ -0,0 +1,32 @@
+<!--
+Note: All PRs with code changes should be targeted to the `dev` branch, pure documentation changes can target `main`
+-->
+
+## Proposed change
+
+<!--
+Please include a summary of the change and which issue is fixed (if any) and any relevant motivation / context. List any dependencies that are required for this change. If appropriate, please include an explanation of how your proposed change can be tested. Screenshots and / or videos can also be helpful if appropriate.
+-->
+
+Fixes # (issue)
+
+## Type of change
+
+<!--
+What type of change does your PR introduce to Paperless-ngx?
+NOTE: Please check only one box!
+-->
+
+- [ ] Bug fix (non-breaking change which fixes an issue)
+- [ ] New feature (non-breaking change which adds functionality)
+- [ ] Breaking change (fix or feature that would cause existing functionality to not work as expected)
+- [ ] Other (please explain)
+
+## Checklist:
+
+- [ ] I have read & agree with the [contributing guidelines](https://github.com/paperless-ngx/paperless-ngx/blob/main/CONTRIBUTING.md).
+- [ ] If applicable, I have tested my code for new features & regressions on both mobile & desktop devices, using the latest version of major browsers.
+- [ ] If applicable, I have checked that all tests pass, see [documentation](https://paperless-ngx.readthedocs.io/en/latest/extending.html#back-end-development).
+- [ ] I have run all `pre-commit` hooks, see [documentation](https://paperless-ngx.readthedocs.io/en/latest/extending.html#code-formatting-with-pre-commit-hooks).
+- [ ] I have made corresponding changes to the documentation as needed.
+- [ ] I have checked my modifications for any breaking changes.

.github/dependabot.yml

@@ -0,0 +1,48 @@
+# https://docs.github.com/en/code-security/supply-chain-security/keeping-your-dependencies-updated-automatically/configuration-options-for-dependency-updates#package-ecosystem
+
+version: 2
+updates:
+
+  # Enable version updates for npm
+  - package-ecosystem: "npm"
+    target-branch: "dev"
+    # Look for `package.json` and `lock` files in the `/src-ui` directory
+    directory: "/src-ui"
+    # Check the npm registry for updates every month
+    schedule:
+      interval: "monthly"
+    labels:
+      - "frontend"
+      - "dependencies"
+    # Add reviewers
+    reviewers:
+      - "paperless-ngx/frontend"
+
+  # Enable version updates for Python
+  - package-ecosystem: "pip"
+    target-branch: "dev"
+    # Look for a `Pipfile` in the `root` directory
+    directory: "/"
+    # Check for updates once a week
+    schedule:
+      interval: "weekly"
+    labels:
+      - "backend"
+      - "dependencies"
+    # Add reviewers
+    reviewers:
+      - "paperless-ngx/backend"
+
+  # Enable updates for Github Actions
+  - package-ecosystem: "github-actions"
+    target-branch: "dev"
+    directory: "/"
+    schedule:
+      # Check for updates to GitHub Actions every month
+      interval: "monthly"
+    labels:
+      - "ci-cd"
+      - "dependencies"
+    # Add reviewers
+    reviewers:
+      - "paperless-ngx/ci-cd"

.github/release-drafter.yml

@@ -0,0 +1,55 @@
+autolabeler:
+  - label: "bug"
+    branch:
+      - '/^fix/'
+    title:
+      - "/^fix/i"
+  - label: "enhancement"
+    branch:
+      - '/^feature/'
+    title:
+      - "/^feature/i"
+categories:
+  - title: 'Breaking Changes'
+    labels:
+      - 'breaking-change'
+  - title: 'Features'
+    labels:
+      - 'enhancement'
+  - title: 'Bug Fixes'
+    labels:
+      - 'bug'
+  - title: 'Documentation'
+    label: 'documentation'
+  - title: 'Maintenance'
+    labels:
+      - 'chore'
+      - 'deployment'
+      - 'translation'
+      - 'ci-cd'
+  - title: 'Dependencies'
+    collapse-after: 3
+    label: 'dependencies'
+  - title: 'All App Changes'
+    labels:
+      - 'frontend'
+      - 'backend'
+    collapse-after: 0
+include-labels:
+  - 'enhancement'
+  - 'bug'
+  - 'chore'
+  - 'deployment'
+  - 'translation'
+  - 'dependencies'
+  - 'documentation'
+  - 'frontend'
+  - 'backend'
+  - 'ci-cd'
+category-template: '### $TITLE'
+change-template: '- $TITLE @$AUTHOR ([#$NUMBER]($URL))'
+change-title-escapes: '\<*_&#@'
+template: |
+  ## paperless-ngx $RESOLVED_VERSION
+
+  $CHANGES

.github/scripts/cleanup-tags.py

@@ -0,0 +1,290 @@
+#!/usr/bin/env python3
+import json
+import logging
+import os
+import shutil
+import subprocess
+from argparse import ArgumentParser
+from typing import Dict
+from typing import Final
+from typing import List
+
+from common import get_log_level
+from github import ContainerPackage
+from github import GithubBranchApi
+from github import GithubContainerRegistryApi
+
+logger = logging.getLogger("cleanup-tags")
+
+
+class DockerManifest2:
+    """
+    Data class wrapping the Docker Image Manifest Version 2.
+
+    See https://docs.docker.com/registry/spec/manifest-v2-2/
+    """
+
+    def __init__(self, data: Dict) -> None:
+        self._data = data
+        # This is the sha256: digest string.  Corresponds to Github API name
+        # if the package is an untagged package
+        self.digest = self._data["digest"]
+        platform_data_os = self._data["platform"]["os"]
+        platform_arch = self._data["platform"]["architecture"]
+        platform_variant = self._data["platform"].get(
+            "variant",
+            "",
+        )
+        self.platform = f"{platform_data_os}/{platform_arch}{platform_variant}"
+
+
+def _main():
+    parser = ArgumentParser(
+        description="Using the GitHub API locate and optionally delete container"
+        " tags which no longer have an associated feature branch",
+    )
+
+    # Requires an affirmative command to actually do a delete
+    parser.add_argument(
+        "--delete",
+        action="store_true",
+        default=False,
+        help="If provided, actually delete the container tags",
+    )
+
+    # When a tagged image is updated, the previous version remains, but it no longer tagged
+    # Add this option to remove them as well
+    parser.add_argument(
+        "--untagged",
+        action="store_true",
+        default=False,
+        help="If provided, delete untagged containers as well",
+    )
+
+    # If given, the package is assumed to be a multi-arch manifest.  Cache packages are
+    # not multi-arch, all other types are
+    parser.add_argument(
+        "--is-manifest",
+        action="store_true",
+        default=False,
+        help="If provided, the package is assumed to be a multi-arch manifest following schema v2",
+    )
+
+    # Allows configuration of log level for debugging
+    parser.add_argument(
+        "--loglevel",
+        default="info",
+        help="Configures the logging level",
+    )
+
+    # Get the name of the package being processed this round
+    parser.add_argument(
+        "package",
+        help="The package to process",
+    )
+
+    args = parser.parse_args()
+
+    logging.basicConfig(
+        level=get_log_level(args),
+        datefmt="%Y-%m-%d %H:%M:%S",
+        format="%(asctime)s %(levelname)-8s %(message)s",
+    )
+
+    # Must be provided in the environment
+    repo_owner: Final[str] = os.environ["GITHUB_REPOSITORY_OWNER"]
+    repo: Final[str] = os.environ["GITHUB_REPOSITORY"]
+    gh_token: Final[str] = os.environ["TOKEN"]
+
+    # Find all branches named feature-*
+    # Note: Only relevant to the main application, but simpler to
+    # leave in for all packages
+    with GithubBranchApi(gh_token) as branch_api:
+        feature_branches = {}
+        for branch in branch_api.get_branches(
+            repo=repo,
+        ):
+            if branch.name.startswith("feature-"):
+                logger.debug(f"Found feature branch {branch.name}")
+                feature_branches[branch.name] = branch
+
+        logger.info(f"Located {len(feature_branches)} feature branches")
+
+    with GithubContainerRegistryApi(gh_token, repo_owner) as container_api:
+        # Get the information about all versions of the given package
+        all_package_versions: List[
+            ContainerPackage
+        ] = container_api.get_package_versions(args.package)
+
+        all_pkgs_tags_to_version: Dict[str, ContainerPackage] = {}
+        for pkg in all_package_versions:
+            for tag in pkg.tags:
+                all_pkgs_tags_to_version[tag] = pkg
+        logger.info(
+            f"Located {len(all_package_versions)} versions of package {args.package}",
+        )
+
+        # Filter to packages which are tagged with feature-*
+        packages_tagged_feature: List[ContainerPackage] = []
+        for package in all_package_versions:
+            if package.tag_matches("feature-"):
+                packages_tagged_feature.append(package)
+
+        feature_pkgs_tags_to_versions: Dict[str, ContainerPackage] = {}
+        for pkg in packages_tagged_feature:
+            for tag in pkg.tags:
+                feature_pkgs_tags_to_versions[tag] = pkg
+
+        logger.info(
+            f'Located {len(feature_pkgs_tags_to_versions)} versions of package {args.package} tagged "feature-"',
+        )
+
+        # All the feature tags minus all the feature branches leaves us feature tags
+        # with no corresponding branch
+        tags_to_delete = list(
+            set(feature_pkgs_tags_to_versions.keys()) - set(feature_branches.keys()),
+        )
+
+        # All the tags minus the set of going to be deleted tags leaves us the
+        # tags which will be kept around
+        tags_to_keep = list(
+            set(all_pkgs_tags_to_version.keys()) - set(tags_to_delete),
+        )
+        logger.info(
+            f"Located {len(tags_to_delete)} versions of package {args.package} to delete",
+        )
+
+        # Delete certain package versions for which no branch existed
+        for tag_to_delete in tags_to_delete:
+            package_version_info = feature_pkgs_tags_to_versions[tag_to_delete]
+
+            if args.delete:
+                logger.info(
+                    f"Deleting {tag_to_delete} (id {package_version_info.id})",
+                )
+                container_api.delete_package_version(
+                    package_version_info,
+                )
+
+            else:
+                logger.info(
+                    f"Would delete {tag_to_delete} (id {package_version_info.id})",
+                )
+
+        # Deal with untagged package versions
+        if args.untagged:
+
+            logger.info("Handling untagged image packages")
+
+            if not args.is_manifest:
+                # If the package is not a multi-arch manifest, images without tags are safe to delete.
+                # They are not referred to by anything.  This will leave all with at least 1 tag
+
+                for package in all_package_versions:
+                    if package.untagged:
+                        if args.delete:
+                            logger.info(
+                                f"Deleting id {package.id} named {package.name}",
+                            )
+                            container_api.delete_package_version(
+                                package,
+                            )
+                        else:
+                            logger.info(
+                                f"Would delete {package.name} (id {package.id})",
+                            )
+                    else:
+                        logger.info(
+                            f"Not deleting tag {package.tags[0]} of package {args.package}",
+                        )
+            else:
+
+                """
+                Ok, bear with me, these are annoying.
+
+                Our images are multi-arch, so the manifest is more like a pointer to a sha256 digest.
+                These images are untagged, but pointed to, and so should not be removed (or every pull fails).
+
+                So for each image getting kept, parse the manifest to find the digest(s) it points to.  Then
+                remove those from the list of untagged images.  The final result is the untagged, not pointed to
+                version which should be safe to remove.
+
+                Example:
+                    Tag: ghcr.io/paperless-ngx/paperless-ngx:1.7.1 refers to
+                        amd64: sha256:b9ed4f8753bbf5146547671052d7e91f68cdfc9ef049d06690b2bc866fec2690
+                        armv7: sha256:81605222df4ba4605a2ba4893276e5d08c511231ead1d5da061410e1bbec05c3
+                        arm64: sha256:374cd68db40734b844705bfc38faae84cc4182371de4bebd533a9a365d5e8f3b
+                    each of which appears as untagged image, but isn't really.
+
+                    So from the list of untagged packages, remove those digests.  Once all tags which
+                    are being kept are checked, the remaining untagged packages are actually untagged
+                    with no referrals in a manifest to them.
+
+                """
+
+                # Simplify the untagged data, mapping name (which is a digest) to the version
+                untagged_versions = {}
+                for x in all_package_versions:
+                    if x.untagged:
+                        untagged_versions[x.name] = x
+
+                skips = 0
+                # Extra security to not delete on an unexpected error
+                actually_delete = True
+
+                # Parse manifests to locate digests pointed to
+                for tag in sorted(tags_to_keep):
+                    full_name = f"ghcr.io/{repo_owner}/{args.package}:{tag}"
+                    logger.info(f"Checking manifest for {full_name}")
+                    try:
+                        proc = subprocess.run(
+                            [
+                                shutil.which("docker"),
+                                "manifest",
+                                "inspect",
+                                full_name,
+                            ],
+                            capture_output=True,
+                        )
+
+                        manifest_list = json.loads(proc.stdout)
+                        for manifest_data in manifest_list["manifests"]:
+                            manifest = DockerManifest2(manifest_data)
+
+                            if manifest.digest in untagged_versions:
+                                logger.debug(
+                                    f"Skipping deletion of {manifest.digest}, referred to by {full_name} for {manifest.platform}",
+                                )
+                                del untagged_versions[manifest.digest]
+                                skips += 1
+
+                    except Exception as err:
+                        actually_delete = False
+                        logger.exception(err)
+
+                logger.info(
+                    f"Skipping deletion of {skips} packages referred to by a manifest",
+                )
+
+                # Step 3.3 - Delete the untagged and not pointed at packages
+                logger.info(f"Deleting untagged packages of {args.package}")
+                for to_delete_name in untagged_versions:
+                    to_delete_version = untagged_versions[to_delete_name]
+
+                    if args.delete and actually_delete:
+                        logger.info(
+                            f"Deleting id {to_delete_version.id} named {to_delete_version.name}",
+                        )
+                        container_api.delete_package_version(
+                            to_delete_version,
+                        )
+                    else:
+                        logger.info(
+                            f"Would delete {to_delete_name} (id {to_delete_version.id})",
+                        )
+        else:
+            logger.info("Leaving untagged images untouched")
+
+
+if __name__ == "__main__":
+    _main()

.github/scripts/common.py

@@ -0,0 +1,43 @@
+#!/usr/bin/env python3
+import logging
+
+
+def get_image_tag(
+    repo_name: str,
+    pkg_name: str,
+    pkg_version: str,
+) -> str:
+    """
+    Returns a string representing the normal image for a given package
+    """
+    return f"ghcr.io/{repo_name.lower()}/builder/{pkg_name}:{pkg_version}"
+
+
+def get_cache_image_tag(
+    repo_name: str,
+    pkg_name: str,
+    pkg_version: str,
+    branch_name: str,
+) -> str:
+    """
+    Returns a string representing the expected image cache tag for a given package
+
+    Registry type caching is utilized for the builder images, to allow fast
+    rebuilds, generally almost instant for the same version
+    """
+    return f"ghcr.io/{repo_name.lower()}/builder/cache/{pkg_name}:{pkg_version}"
+
+
+def get_log_level(args) -> int:
+    levels = {
+        "critical": logging.CRITICAL,
+        "error": logging.ERROR,
+        "warn": logging.WARNING,
+        "warning": logging.WARNING,
+        "info": logging.INFO,
+        "debug": logging.DEBUG,
+    }
+    level = levels.get(args.loglevel.lower())
+    if level is None:
+        level = logging.INFO
+    return level

.github/scripts/get-build-json.py

@@ -0,0 +1,92 @@
+#!/usr/bin/env python3
+"""
+This is a helper script for the mutli-stage Docker image builder.
+It provides a single point of configuration for package version control.
+The output JSON object is used by the CI workflow to determine what versions
+to build and pull into the final Docker image.
+
+Python package information is obtained from the Pipfile.lock.  As this is
+kept updated by dependabot, it usually will need no further configuration.
+The sole exception currently is pikepdf, which has a dependency on qpdf,
+and is configured here to use the latest version of qpdf built by the workflow.
+
+Other package version information is configured directly below, generally by
+setting the version and Git information, if any.
+
+"""
+import argparse
+import json
+import os
+from pathlib import Path
+from typing import Final
+
+from common import get_cache_image_tag
+from common import get_image_tag
+
+
+def _main():
+    parser = argparse.ArgumentParser(
+        description="Generate a JSON object of information required to build the given package, based on the Pipfile.lock",
+    )
+    parser.add_argument(
+        "package",
+        help="The name of the package to generate JSON for",
+    )
+
+    PIPFILE_LOCK_PATH: Final[Path] = Path("Pipfile.lock")
+    BUILD_CONFIG_PATH: Final[Path] = Path(".build-config.json")
+
+    # Read the main config file
+    build_json: Final = json.loads(BUILD_CONFIG_PATH.read_text())
+
+    # Read Pipfile.lock file
+    pipfile_data: Final = json.loads(PIPFILE_LOCK_PATH.read_text())
+
+    args: Final = parser.parse_args()
+
+    # Read from environment variables set by GitHub Actions
+    repo_name: Final[str] = os.environ["GITHUB_REPOSITORY"]
+    branch_name: Final[str] = os.environ["GITHUB_REF_NAME"]
+
+    # Default output values
+    version = None
+    extra_config = {}
+
+    if args.package in pipfile_data["default"]:
+        # Read the version from Pipfile.lock
+        pkg_data = pipfile_data["default"][args.package]
+        pkg_version = pkg_data["version"].split("==")[-1]
+        version = pkg_version
+
+        # Any extra/special values needed
+        if args.package == "pikepdf":
+            extra_config["qpdf_version"] = build_json["qpdf"]["version"]
+
+    elif args.package in build_json:
+        version = build_json[args.package]["version"]
+
+    else:
+        raise NotImplementedError(args.package)
+
+    # The JSON object we'll output
+    output = {
+        "name": args.package,
+        "version": version,
+        "image_tag": get_image_tag(repo_name, args.package, version),
+        "cache_tag": get_cache_image_tag(
+            repo_name,
+            args.package,
+            version,
+            branch_name,
+        ),
+    }
+
+    # Add anything special a package may need
+    output.update(extra_config)
+
+    # Output the JSON info to stdout
+    print(json.dumps(output))
+
+
+if __name__ == "__main__":
+    _main()

.github/scripts/github.py

@@ -0,0 +1,227 @@
+#!/usr/bin/env python3
+"""
+This module contains some useful classes for interacting with the Github API.
+The full documentation for the API can be found here: https://docs.github.com/en/rest
+
+Mostly, this focusses on two areas, repo branches and repo packages, as the use case
+is cleaning up container images which are no longer referred to.
+
+"""
+import functools
+import logging
+import re
+import urllib.parse
+from typing import Dict
+from typing import List
+from typing import Optional
+
+import requests
+
+logger = logging.getLogger("github-api")
+
+
+class _GithubApiBase:
+    """
+    A base class for interacting with the Github API.  It
+    will handle the session and setting authorization headers.
+    """
+
+    def __init__(self, token: str) -> None:
+        self._token = token
+        self._session: Optional[requests.Session] = None
+
+    def __enter__(self) -> "_GithubApiBase":
+        """
+        Sets up the required headers for auth and response
+        type from the API
+        """
+        self._session = requests.Session()
+        self._session.headers.update(
+            {
+                "Accept": "application/vnd.github.v3+json",
+                "Authorization": f"token {self._token}",
+            },
+        )
+        return self
+
+    def __exit__(self, exc_type, exc_val, exc_tb):
+        """
+        Ensures the authorization token is cleaned up no matter
+        the reason for the exit
+        """
+        if "Accept" in self._session.headers:
+            del self._session.headers["Accept"]
+        if "Authorization" in self._session.headers:
+            del self._session.headers["Authorization"]
+
+        # Close the session as well
+        self._session.close()
+        self._session = None
+
+    def _read_all_pages(self, endpoint):
+        """
+        Helper function to read all pages of an endpoint, utilizing the
+        next.url until exhausted.  Assumes the endpoint returns a list
+        """
+        internal_data = []
+
+        while True:
+            resp = self._session.get(endpoint)
+            if resp.status_code == 200:
+                internal_data += resp.json()
+                if "next" in resp.links:
+                    endpoint = resp.links["next"]["url"]
+                else:
+                    logger.debug("Exiting pagination loop")
+                    break
+            else:
+                logger.warning(f"Request to {endpoint} return HTTP {resp.status_code}")
+                break
+
+        return internal_data
+
+
+class _EndpointResponse:
+    """
+    For all endpoint JSON responses, store the full
+    response data, for ease of extending later, if need be.
+    """
+
+    def __init__(self, data: Dict) -> None:
+        self._data = data
+
+
+class GithubBranch(_EndpointResponse):
+    """
+    Simple wrapper for a repository branch, only extracts name information
+    for now.
+    """
+
+    def __init__(self, data: Dict) -> None:
+        super().__init__(data)
+        self.name = self._data["name"]
+
+
+class GithubBranchApi(_GithubApiBase):
+    """
+    Wrapper around branch API.
+
+    See https://docs.github.com/en/rest/branches/branches
+
+    """
+
+    def __init__(self, token: str) -> None:
+        super().__init__(token)
+
+        self._ENDPOINT = "https://api.github.com/repos/{REPO}/branches"
+
+    def get_branches(self, repo: str) -> List[GithubBranch]:
+        """
+        Returns all current branches of the given repository owned by the given
+        owner or organization.
+        """
+        endpoint = self._ENDPOINT.format(REPO=repo)
+        internal_data = self._read_all_pages(endpoint)
+        return [GithubBranch(branch) for branch in internal_data]
+
+
+class ContainerPackage(_EndpointResponse):
+    """
+    Data class wrapping the JSON response from the package related
+    endpoints
+    """
+
+    def __init__(self, data: Dict):
+        super().__init__(data)
+        # This is a numerical ID, required for interactions with this
+        # specific package, including deletion of it or restoration
+        self.id: int = self._data["id"]
+
+        # A string name.  This might be an actual name or it could be a
+        # digest string like "sha256:"
+        self.name: str = self._data["name"]
+
+        # URL to the package, including its ID, can be used for deletion
+        # or restoration without needing to build up a URL ourselves
+        self.url: str = self._data["url"]
+
+        # The list of tags applied to this image. Maybe an empty list
+        self.tags: List[str] = self._data["metadata"]["container"]["tags"]
+
+    @functools.cached_property
+    def untagged(self) -> bool:
+        """
+        Returns True if the image has no tags applied to it, False otherwise
+        """
+        return len(self.tags) == 0
+
+    @functools.cache
+    def tag_matches(self, pattern: str) -> bool:
+        """
+        Returns True if the image has at least one tag which matches the given regex,
+        False otherwise
+        """
+        for tag in self.tags:
+            if re.match(pattern, tag) is not None:
+                return True
+        return False
+
+    def __repr__(self):
+        return f"Package {self.name}"
+
+
+class GithubContainerRegistryApi(_GithubApiBase):
+    """
+    Class wrapper to deal with the Github packages API.  This class only deals with
+    container type packages, the only type published by paperless-ngx.
+    """
+
+    def __init__(self, token: str, owner_or_org: str) -> None:
+        super().__init__(token)
+        self._owner_or_org = owner_or_org
+        if self._owner_or_org == "paperless-ngx":
+            # https://docs.github.com/en/rest/packages#get-all-package-versions-for-a-package-owned-by-an-organization
+            self._PACKAGES_VERSIONS_ENDPOINT = "https://api.github.com/orgs/{ORG}/packages/{PACKAGE_TYPE}/{PACKAGE_NAME}/versions"
+            # https://docs.github.com/en/rest/packages#delete-package-version-for-an-organization
+            self._PACKAGE_VERSION_DELETE_ENDPOINT = "https://api.github.com/orgs/{ORG}/packages/{PACKAGE_TYPE}/{PACKAGE_NAME}/versions/{PACKAGE_VERSION_ID}"
+        else:
+            # https://docs.github.com/en/rest/packages#get-all-package-versions-for-a-package-owned-by-the-authenticated-user
+            self._PACKAGES_VERSIONS_ENDPOINT = "https://api.github.com/user/packages/{PACKAGE_TYPE}/{PACKAGE_NAME}/versions"
+            # https://docs.github.com/en/rest/packages#delete-a-package-version-for-the-authenticated-user
+            self._PACKAGE_VERSION_DELETE_ENDPOINT = "https://api.github.com/user/packages/{PACKAGE_TYPE}/{PACKAGE_NAME}/versions/{PACKAGE_VERSION_ID}"
+
+    def get_package_versions(
+        self,
+        package_name: str,
+    ) -> List[ContainerPackage]:
+        """
+        Returns all the versions of a given package (container images) from
+        the API
+        """
+
+        package_type: str = "container"
+        # Need to quote this for slashes in the name
+        package_name = urllib.parse.quote(package_name, safe="")
+
+        endpoint = self._PACKAGES_VERSIONS_ENDPOINT.format(
+            ORG=self._owner_or_org,
+            PACKAGE_TYPE=package_type,
+            PACKAGE_NAME=package_name,
+        )
+
+        pkgs = []
+
+        for data in self._read_all_pages(endpoint):
+            pkgs.append(ContainerPackage(data))
+
+        return pkgs
+
+    def delete_package_version(self, package_data: ContainerPackage):
+        """
+        Deletes the given package version from the GHCR
+        """
+        resp = self._session.delete(package_data.url)
+        if resp.status_code != 204:
+            logger.warning(
+                f"Request to delete {package_data.url} returned HTTP {resp.status_code}",
+            )

.github/stale.yml

@@ -0,0 +1,23 @@
+# Number of days of inactivity before an issue becomes stale
+daysUntilStale: 30
+
+# Number of days of inactivity before a stale issue is closed
+daysUntilClose: 7
+
+# Only issues or pull requests with all of these labels are check if stale. Defaults to `[]` (disabled)
+onlyLabels: [cant-reproduce]
+
+# Label to use when marking an issue as stale
+staleLabel: stale
+
+# Comment to post when marking an issue as stale. Set to `false` to disable
+markComment: >
+  This issue has been automatically marked as stale because it has not had
+  recent activity. It will be closed if no further activity occurs. Thank you
+  for your contributions.
+
+# Comment to post when closing a stale issue. Set to `false` to disable
+closeComment: false
+
+# See https://github.com/marketplace/stale for more info on the app
+# and https://github.com/probot/stale for the configuration docs

.github/workflows/ci.yml

@@ -0,0 +1,523 @@
+name: ci
+
+on:
+  push:
+    tags:
+      # https://semver.org/#spec-item-2
+      - 'v[0-9]+.[0-9]+.[0-9]+'
+      # https://semver.org/#spec-item-9
+      - 'v[0-9]+.[0-9]+.[0-9]+-beta.rc[0-9]+'
+    branches-ignore:
+      - 'translations**'
+  pull_request:
+    branches-ignore:
+      - 'translations**'
+
+jobs:
+  pre-commit:
+    name: Linting Checks
+    runs-on: ubuntu-latest
+    steps:
+      -
+        name: Checkout repository
+        uses: actions/checkout@v3
+
+      -
+        name: Install tools
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.9"
+
+      -
+        name: Check files
+        uses: pre-commit/action@v3.0.0
+
+  documentation:
+    name: "Build Documentation"
+    runs-on: ubuntu-20.04
+    needs:
+      - pre-commit
+    steps:
+      -
+        name: Checkout
+        uses: actions/checkout@v3
+      -
+        name: Install pipenv
+        run: |
+          pipx install pipenv==2022.8.5
+          pipenv --version
+      -
+        name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: 3.9
+          cache: "pipenv"
+          cache-dependency-path: 'Pipfile.lock'
+      -
+        name: Install dependencies
+        run: |
+          pipenv sync --dev
+      -
+        name: List installed Python dependencies
+        run: |
+          pipenv run pip list
+      -
+        name: Make documentation
+        run: |
+          cd docs/
+          pipenv run make html
+      -
+        name: Upload artifact
+        uses: actions/upload-artifact@v3
+        with:
+          name: documentation
+          path: docs/_build/html/
+
+  tests-backend:
+    name: "Tests (${{ matrix.python-version }})"
+    runs-on: ubuntu-20.04
+    needs:
+      - pre-commit
+    strategy:
+      matrix:
+        python-version: ['3.8', '3.9', '3.10']
+      fail-fast: false
+    steps:
+      -
+        name: Checkout
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 2
+      -
+        name: Install pipenv
+        run: |
+          pipx install pipenv==2022.8.5
+          pipenv --version
+      -
+        name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: "${{ matrix.python-version }}"
+          cache: "pipenv"
+          cache-dependency-path: 'Pipfile.lock'
+      -
+        name: Install system dependencies
+        run: |
+          sudo apt-get update -qq
+          sudo apt-get install -qq --no-install-recommends unpaper tesseract-ocr imagemagick ghostscript libzbar0 poppler-utils
+      -
+        name: Install Python dependencies
+        run: |
+          pipenv sync --dev
+      -
+        name: List installed Python dependencies
+        run: |
+          pipenv run pip list
+      -
+        name: Tests
+        run: |
+          cd src/
+          pipenv run pytest
+      -
+        name: Get changed files
+        id: changed-files-specific
+        uses: tj-actions/changed-files@v29.0.2
+        with:
+          files: |
+            src/**
+      -
+        name: List all changed files
+        run: |
+          for file in ${{ steps.changed-files-specific.outputs.all_changed_files }}; do
+            echo "${file} was changed"
+          done
+      -
+        name: Publish coverage results
+        if: matrix.python-version == '3.9' && steps.changed-files-specific.outputs.any_changed == 'true'
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        # https://github.com/coveralls-clients/coveralls-python/issues/251
+        run: |
+          cd src/
+          pipenv run coveralls --service=github
+
+  tests-frontend:
+    name: "Tests Frontend"
+    runs-on: ubuntu-20.04
+    needs:
+      - pre-commit
+    strategy:
+      matrix:
+        node-version: [16.x]
+    steps:
+      - uses: actions/checkout@v3
+      -
+        name: Use Node.js ${{ matrix.node-version }}
+        uses: actions/setup-node@v3
+        with:
+          node-version: ${{ matrix.node-version }}
+      - run: cd src-ui && npm ci
+      - run: cd src-ui && npm run test
+      - run: cd src-ui && npm run e2e:ci
+
+  prepare-docker-build:
+    name: Prepare Docker Pipeline Data
+    if: github.event_name == 'push' && (startsWith(github.ref, 'refs/heads/feature-') || github.ref == 'refs/heads/dev' || github.ref == 'refs/heads/beta' || contains(github.ref, 'beta.rc') || startsWith(github.ref, 'refs/tags/v'))
+    runs-on: ubuntu-20.04
+    # If the push triggered the installer library workflow, wait for it to
+    # complete here.  This ensures the required versions for the final
+    # image have been built, while not waiting at all if the versions haven't changed
+    concurrency:
+      group: build-installer-library
+      cancel-in-progress: false
+    needs:
+      - documentation
+      - tests-backend
+      - tests-frontend
+    steps:
+      -
+        name: Set ghcr repository name
+        id: set-ghcr-repository
+        run: |
+          ghcr_name=$(echo "${GITHUB_REPOSITORY}" | awk '{ print tolower($0) }')
+          echo ::set-output name=repository::${ghcr_name}
+      -
+        name: Checkout
+        uses: actions/checkout@v3
+      -
+        name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.9"
+      -
+        name: Setup qpdf image
+        id: qpdf-setup
+        run: |
+          build_json=$(python ${GITHUB_WORKSPACE}/.github/scripts/get-build-json.py qpdf)
+
+          echo ${build_json}
+
+          echo ::set-output name=qpdf-json::${build_json}
+      -
+        name: Setup psycopg2 image
+        id: psycopg2-setup
+        run: |
+          build_json=$(python ${GITHUB_WORKSPACE}/.github/scripts/get-build-json.py psycopg2)
+
+          echo ${build_json}
+
+          echo ::set-output name=psycopg2-json::${build_json}
+      -
+        name: Setup pikepdf image
+        id: pikepdf-setup
+        run: |
+          build_json=$(python ${GITHUB_WORKSPACE}/.github/scripts/get-build-json.py pikepdf)
+
+          echo ${build_json}
+
+          echo ::set-output name=pikepdf-json::${build_json}
+      -
+        name: Setup jbig2enc image
+        id: jbig2enc-setup
+        run: |
+          build_json=$(python ${GITHUB_WORKSPACE}/.github/scripts/get-build-json.py jbig2enc)
+
+          echo ${build_json}
+
+          echo ::set-output name=jbig2enc-json::${build_json}
+
+    outputs:
+
+      ghcr-repository: ${{ steps.set-ghcr-repository.outputs.repository }}
+
+      qpdf-json: ${{ steps.qpdf-setup.outputs.qpdf-json }}
+
+      pikepdf-json: ${{ steps.pikepdf-setup.outputs.pikepdf-json }}
+
+      psycopg2-json: ${{ steps.psycopg2-setup.outputs.psycopg2-json }}
+
+      jbig2enc-json: ${{ steps.jbig2enc-setup.outputs.jbig2enc-json}}
+
+  # build and push image to docker hub.
+  build-docker-image:
+    runs-on: ubuntu-20.04
+    concurrency:
+      group: ${{ github.workflow }}-build-docker-image-${{ github.ref_name }}
+      cancel-in-progress: true
+    needs:
+      - prepare-docker-build
+    steps:
+      -
+        name: Check pushing to Docker Hub
+        id: docker-hub
+        # Only push to Dockerhub from the main repo AND the ref is either:
+        #  main
+        #  dev
+        #  beta
+        #  a tag
+        # Otherwise forks would require a Docker Hub account and secrets setup
+        run: |
+          if [[ ${{ needs.prepare-docker-build.outputs.ghcr-repository }} == "paperless-ngx/paperless-ngx" && ( ${{ github.ref_name }} == "main" || ${{ github.ref_name }} == "dev" || ${{ github.ref_name }} == "beta" || ${{ startsWith(github.ref, 'refs/tags/v') }} == "true" ) ]] ; then
+            echo "Enabling DockerHub image push"
+            echo ::set-output name=enable::"true"
+          else
+            echo "Not pushing to DockerHub"
+            echo ::set-output name=enable::"false"
+          fi
+      -
+        name: Gather Docker metadata
+        id: docker-meta
+        uses: docker/metadata-action@v4
+        with:
+          images: |
+            ghcr.io/${{ needs.prepare-docker-build.outputs.ghcr-repository }}
+            name=paperlessngx/paperless-ngx,enable=${{ steps.docker-hub.outputs.enable }}
+          tags: |
+            # Tag branches with branch name
+            type=ref,event=branch
+            # Process semver tags
+            # For a tag x.y.z or vX.Y.Z, output an x.y.z and x.y image tag
+            type=semver,pattern={{version}}
+            type=semver,pattern={{major}}.{{minor}}
+      -
+        name: Checkout
+        uses: actions/checkout@v3
+      -
+        name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v2
+      -
+        name: Set up QEMU
+        uses: docker/setup-qemu-action@v2
+      -
+        name: Login to Github Container Registry
+        uses: docker/login-action@v2
+        with:
+          registry: ghcr.io
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+      -
+        name: Login to Docker Hub
+        uses: docker/login-action@v2
+        # Don't attempt to login is not pushing to Docker Hub
+        if: steps.docker-hub.outputs.enable == 'true'
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+      -
+        name: Build and push
+        uses: docker/build-push-action@v3
+        with:
+          context: .
+          file: ./Dockerfile
+          platforms: linux/amd64,linux/arm/v7,linux/arm64
+          push: ${{ github.event_name != 'pull_request' }}
+          tags: ${{ steps.docker-meta.outputs.tags }}
+          labels: ${{ steps.docker-meta.outputs.labels }}
+          build-args: |
+            JBIG2ENC_VERSION=${{ fromJSON(needs.prepare-docker-build.outputs.jbig2enc-json).version }}
+            QPDF_VERSION=${{ fromJSON(needs.prepare-docker-build.outputs.qpdf-json).version }}
+            PIKEPDF_VERSION=${{ fromJSON(needs.prepare-docker-build.outputs.pikepdf-json).version }}
+            PSYCOPG2_VERSION=${{ fromJSON(needs.prepare-docker-build.outputs.psycopg2-json).version }}
+          # Get cache layers from this branch, then dev, then main
+          # This allows new branches to get at least some cache benefits, generally from dev
+          cache-from: |
+            type=registry,ref=ghcr.io/${{ needs.prepare-docker-build.outputs.ghcr-repository }}/builder/cache/app:${{ github.ref_name }}
+            type=registry,ref=ghcr.io/${{ needs.prepare-docker-build.outputs.ghcr-repository }}/builder/cache/app:dev
+            type=registry,ref=ghcr.io/${{ needs.prepare-docker-build.outputs.ghcr-repository }}/builder/cache/app:main
+          cache-to: |
+            type=registry,mode=max,ref=ghcr.io/${{ needs.prepare-docker-build.outputs.ghcr-repository }}/builder/cache/app:${{ github.ref_name }}
+      -
+        name: Inspect image
+        run: |
+          docker buildx imagetools inspect ${{ fromJSON(steps.docker-meta.outputs.json).tags[0] }}
+      -
+        name: Export frontend artifact from docker
+        run: |
+          docker create --name frontend-extract ${{ fromJSON(steps.docker-meta.outputs.json).tags[0] }}
+          docker cp frontend-extract:/usr/src/paperless/src/documents/static/frontend src/documents/static/frontend/
+      -
+        name: Upload frontend artifact
+        uses: actions/upload-artifact@v3
+        with:
+          name: frontend-compiled
+          path: src/documents/static/frontend/
+
+  build-release:
+    needs:
+      - build-docker-image
+    runs-on: ubuntu-20.04
+    steps:
+      -
+        name: Checkout
+        uses: actions/checkout@v3
+      -
+        name: Install pipenv
+        run: |
+          pip3 install --upgrade pip setuptools wheel pipx
+          pipx install pipenv
+      -
+        name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: 3.9
+          cache: "pipenv"
+          cache-dependency-path: 'Pipfile.lock'
+      -
+        name: Install Python dependencies
+        run: |
+          pipenv sync --dev
+      -
+        name: Install system dependencies
+        run: |
+          sudo apt-get update -qq
+          sudo apt-get install -qq --no-install-recommends gettext liblept5
+      -
+        name: Download frontend artifact
+        uses: actions/download-artifact@v3
+        with:
+          name: frontend-compiled
+          path: src/documents/static/frontend/
+      -
+        name: Download documentation artifact
+        uses: actions/download-artifact@v3
+        with:
+          name: documentation
+          path: docs/_build/html/
+      -
+        name: Generate requirements file
+        run: |
+          pipenv requirements > requirements.txt
+      -
+        name: Compile messages
+        run: |
+          cd src/
+          pipenv run python3 manage.py compilemessages
+      -
+        name: Collect static files
+        run: |
+          cd src/
+          pipenv run python3 manage.py collectstatic --no-input
+      -
+        name: Move files
+        run: |
+          mkdir dist
+          mkdir dist/paperless-ngx
+          mkdir dist/paperless-ngx/scripts
+          cp .dockerignore .env Dockerfile Pipfile Pipfile.lock requirements.txt LICENSE README.md dist/paperless-ngx/
+          cp paperless.conf.example dist/paperless-ngx/paperless.conf
+          cp gunicorn.conf.py dist/paperless-ngx/gunicorn.conf.py
+          cp -r docker/ dist/paperless-ngx/docker
+          cp scripts/*.service scripts/*.sh dist/paperless-ngx/scripts/
+          cp -r src/ dist/paperless-ngx/src
+          cp -r docs/_build/html/ dist/paperless-ngx/docs
+          mv static dist/paperless-ngx
+      -
+        name: Make release package
+        run: |
+          cd dist
+          tar -cJf paperless-ngx.tar.xz paperless-ngx/
+      -
+        name: Upload release artifact
+        uses: actions/upload-artifact@v3
+        with:
+          name: release
+          path: dist/paperless-ngx.tar.xz
+
+  publish-release:
+    runs-on: ubuntu-20.04
+    outputs:
+      prerelease: ${{ steps.get_version.outputs.prerelease }}
+      changelog: ${{ steps.create-release.outputs.body }}
+      version: ${{ steps.get_version.outputs.version }}
+    needs:
+      - build-release
+    if: github.ref_type == 'tag' && (startsWith(github.ref_name, 'v') || contains(github.ref_name, '-beta.rc'))
+    steps:
+      -
+        name: Download release artifact
+        uses: actions/download-artifact@v3
+        with:
+          name: release
+          path: ./
+      -
+        name: Get version
+        id: get_version
+        run: |
+          echo ::set-output name=version::${{ github.ref_name }}
+          if [[ ${{ contains(github.ref_name, '-beta.rc') }} == 'true' ]]; then
+            echo ::set-output name=prerelease::true
+          else
+            echo ::set-output name=prerelease::false
+          fi
+      -
+        name: Create Release and Changelog
+        id: create-release
+        uses: paperless-ngx/release-drafter@master
+        with:
+          name: Paperless-ngx ${{ steps.get_version.outputs.version }}
+          tag: ${{ steps.get_version.outputs.version }}
+          version: ${{ steps.get_version.outputs.version }}
+          prerelease: ${{ steps.get_version.outputs.prerelease }}
+          publish: true # ensures release is not marked as draft
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+      -
+        name: Upload release archive
+        id: upload-release-asset
+        uses: actions/upload-release-asset@v1
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        with:
+          upload_url: ${{ steps.create-release.outputs.upload_url }}
+          asset_path: ./paperless-ngx.tar.xz
+          asset_name: paperless-ngx-${{ steps.get_version.outputs.version }}.tar.xz
+          asset_content_type: application/x-xz
+
+  append-changelog:
+    runs-on: ubuntu-20.04
+    needs:
+      - publish-release
+    if: needs.publish-release.outputs.prerelease == 'false'
+    steps:
+      -
+        name: Checkout
+        uses: actions/checkout@v3
+        with:
+          ref: main
+      -
+        name: Append Changelog to docs
+        id: append-Changelog
+        working-directory: docs
+        run: |
+          git branch ${{ needs.publish-release.outputs.version }}-changelog
+          git checkout ${{ needs.publish-release.outputs.version }}-changelog
+          echo -e "# Changelog\n\n${{ needs.publish-release.outputs.changelog }}\n" > changelog-new.md
+          echo "Manually linking usernames"
+          sed -i -r 's|@(.+?) \(\[#|[@\1](https://github.com/\1) ([#|ig' changelog-new.md
+          CURRENT_CHANGELOG=`tail --lines +2 changelog.md`
+          echo -e "$CURRENT_CHANGELOG" >> changelog-new.md
+          mv changelog-new.md changelog.md
+          git config --global user.name "github-actions"
+          git config --global user.email "41898282+github-actions[bot]@users.noreply.github.com"
+          git commit -am "Changelog ${{ steps.get_version.outputs.version }} - GHA"
+          git push origin ${{ needs.publish-release.outputs.version }}-changelog
+      -
+        name: Create Pull Request
+        uses: actions/github-script@v6
+        with:
+          script: |
+            const { repo, owner } = context.repo;
+            const result = await github.rest.pulls.create({
+              title: '[Documentation] Add ${{ needs.publish-release.outputs.version }} changelog',
+              owner,
+              repo,
+              head: '${{ needs.publish-release.outputs.version }}-changelog',
+              base: 'main',
+              body: 'This PR is auto-generated by CI.'
+            });
+            github.rest.issues.addLabels({
+              owner,
+              repo,
+              issue_number: result.data.number,
+              labels: ['documentation']
+            });

.github/workflows/cleanup-tags.yml

@@ -0,0 +1,108 @@
+# This workflow runs on certain conditions to check for and potentially
+# delete container images from the GHCR which no longer have an associated
+# code branch.
+# Requires a PAT with the correct scope set in the secrets
+
+name: Cleanup Image Tags
+
+on:
+  schedule:
+    - cron: '0 0 * * SAT'
+  delete:
+  pull_request:
+    types:
+      - closed
+  push:
+    paths:
+      - ".github/workflows/cleanup-tags.yml"
+      - ".github/scripts/cleanup-tags.py"
+      - ".github/scripts/github.py"
+      - ".github/scripts/common.py"
+
+jobs:
+  cleanup:
+    name: Cleanup Image Tags
+    runs-on: ubuntu-20.04
+    env:
+      # Requires a personal access token with the OAuth scope delete:packages
+      TOKEN: ${{ secrets.GHA_CONTAINER_DELETE_TOKEN }}
+    steps:
+      -
+        name: Checkout
+        uses: actions/checkout@v3
+      -
+        name: Login to Github Container Registry
+        uses: docker/login-action@v1
+        with:
+          registry: ghcr.io
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+      -
+        name: Set up Python
+        uses: actions/setup-python@v3
+        with:
+          python-version: "3.10"
+      -
+        name: Install requests
+        run: |
+          python -m pip install requests
+      # Clean up primary packages
+      -
+        name: Cleanup for package "paperless-ngx"
+        if: "${{ env.TOKEN != '' }}"
+        run: |
+          python ${GITHUB_WORKSPACE}/.github/scripts/cleanup-tags.py --loglevel info --untagged --is-manifest --delete "paperless-ngx"
+      -
+        name: Cleanup for package "qpdf"
+        if: "${{ env.TOKEN != '' }}"
+        run: |
+          python ${GITHUB_WORKSPACE}/.github/scripts/cleanup-tags.py --loglevel info --untagged --is-manifest --delete "paperless-ngx/builder/qpdf"
+      -
+        name: Cleanup for package "pikepdf"
+        if: "${{ env.TOKEN != '' }}"
+        run: |
+          python ${GITHUB_WORKSPACE}/.github/scripts/cleanup-tags.py --loglevel info --untagged --is-manifest --delete "paperless-ngx/builder/pikepdf"
+      -
+        name: Cleanup for package "jbig2enc"
+        if: "${{ env.TOKEN != '' }}"
+        run: |
+          python ${GITHUB_WORKSPACE}/.github/scripts/cleanup-tags.py --loglevel info --untagged --is-manifest --delete "paperless-ngx/builder/jbig2enc"
+      -
+        name: Cleanup for package "psycopg2"
+        if: "${{ env.TOKEN != '' }}"
+        run: |
+          python ${GITHUB_WORKSPACE}/.github/scripts/cleanup-tags.py --loglevel info --untagged --is-manifest --delete "paperless-ngx/builder/psycopg2"
+      #
+      # Clean up registry cache packages
+      #
+      -
+        name: Cleanup for package "builder/cache/app"
+        if: "${{ env.TOKEN != '' }}"
+        run: |
+          python ${GITHUB_WORKSPACE}/.github/scripts/cleanup-tags.py --loglevel info --untagged --delete "paperless-ngx/builder/cache/app"
+      -
+        name: Cleanup for package "builder/cache/qpdf"
+        if: "${{ env.TOKEN != '' }}"
+        run: |
+          python ${GITHUB_WORKSPACE}/.github/scripts/cleanup-tags.py --loglevel info --untagged --delete "paperless-ngx/builder/cache/qpdf"
+      -
+        name: Cleanup for package "builder/cache/psycopg2"
+        if: "${{ env.TOKEN != '' }}"
+        run: |
+          python ${GITHUB_WORKSPACE}/.github/scripts/cleanup-tags.py --loglevel info --untagged --delete "paperless-ngx/builder/cache/psycopg2"
+      -
+        name: Cleanup for package "builder/cache/jbig2enc"
+        if: "${{ env.TOKEN != '' }}"
+        run: |
+          python ${GITHUB_WORKSPACE}/.github/scripts/cleanup-tags.py --loglevel info --untagged --delete "paperless-ngx/builder/cache/jbig2enc"
+      -
+        name: Cleanup for package "builder/cache/pikepdf"
+        if: "${{ env.TOKEN != '' }}"
+        run: |
+          python ${GITHUB_WORKSPACE}/.github/scripts/cleanup-tags.py --loglevel info --untagged --delete "paperless-ngx/builder/cache/pikepdf"
+      -
+        name: Check all tags still pull
+        run: |
+          ghcr_name=$(echo "${GITHUB_REPOSITORY}" | awk '{ print tolower($0) }')
+          echo "Pulling all tags of ghcr.io/${ghcr_name}"
+          docker pull --quiet --all-tags ghcr.io/${ghcr_name}

.github/workflows/codeql-analysis.yml

@@ -0,0 +1,54 @@
+# For most projects, this workflow file will not need changing; you simply need
+# to commit it to your repository.
+#
+# You may wish to alter this file to override the set of languages analyzed,
+# or to provide custom queries or build logic.
+#
+# ******** NOTE ********
+# We have attempted to detect the languages in your repository. Please check
+# the `language` matrix defined below to confirm you have the correct set of
+# supported CodeQL languages.
+#
+name: "CodeQL"
+
+on:
+  push:
+    branches: [ main, dev ]
+  pull_request:
+    # The branches below must be a subset of the branches above
+    branches: [ dev ]
+  schedule:
+    - cron: '28 13 * * 5'
+
+jobs:
+  analyze:
+    name: Analyze
+    runs-on: ubuntu-latest
+    permissions:
+      actions: read
+      contents: read
+      security-events: write
+
+    strategy:
+      fail-fast: false
+      matrix:
+        language: [ 'javascript', 'python' ]
+        # CodeQL supports [ 'cpp', 'csharp', 'go', 'java', 'javascript', 'python', 'ruby' ]
+        # Learn more about CodeQL language support at https://git.io/codeql-language-support
+
+    steps:
+    - name: Checkout repository
+      uses: actions/checkout@v2
+
+    # Initializes the CodeQL tools for scanning.
+    - name: Initialize CodeQL
+      uses: github/codeql-action/init@v2
+      with:
+        languages: ${{ matrix.language }}
+        # If you wish to specify custom queries, you can do so here or in a config file.
+        # By default, queries listed here will override any specified in a config file.
+        # Prefix the list here with "+" to use these queries and those in the config file.
+        # queries: ./path/to/local/query, your-org/your-repo/queries@main
+
+    - name: Perform CodeQL Analysis
+      uses: github/codeql-action/analyze@v2

.github/workflows/installer-library.yml

@@ -0,0 +1,147 @@
+# This workflow will run to update the installer library of
+# Docker images.  These are the images which provide updated wheels
+# .deb installation packages or maybe just some compiled library
+
+name: Build Image Library
+
+on:
+  push:
+    # Must match one of these branches AND one of the paths
+    # to be triggered
+    branches:
+      - "main"
+      - "dev"
+      - "library-*"
+      - "feature-*"
+    paths:
+      # Trigger the workflow if a Dockerfile changed
+      - "docker-builders/**"
+      # Trigger if a package was updated
+      - ".build-config.json"
+      - "Pipfile.lock"
+      # Also trigger on workflow changes related to the library
+      - ".github/workflows/installer-library.yml"
+      - ".github/workflows/reusable-workflow-builder.yml"
+      - ".github/scripts/**"
+
+# Set a workflow level concurrency group so primary workflow
+# can wait for this to complete if needed
+# DO NOT CHANGE without updating main workflow group
+concurrency:
+  group: build-installer-library
+  cancel-in-progress: false
+
+jobs:
+  prepare-docker-build:
+    name: Prepare Docker Image Version Data
+    runs-on: ubuntu-20.04
+    steps:
+      -
+        name: Set ghcr repository name
+        id: set-ghcr-repository
+        run: |
+          ghcr_name=$(echo "${GITHUB_REPOSITORY}" | awk '{ print tolower($0) }')
+          echo ::set-output name=repository::${ghcr_name}
+      -
+        name: Checkout
+        uses: actions/checkout@v3
+      -
+        name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.9"
+      -
+        name: Setup qpdf image
+        id: qpdf-setup
+        run: |
+          build_json=$(python ${GITHUB_WORKSPACE}/.github/scripts/get-build-json.py qpdf)
+
+          echo ${build_json}
+
+          echo ::set-output name=qpdf-json::${build_json}
+      -
+        name: Setup psycopg2 image
+        id: psycopg2-setup
+        run: |
+          build_json=$(python ${GITHUB_WORKSPACE}/.github/scripts/get-build-json.py psycopg2)
+
+          echo ${build_json}
+
+          echo ::set-output name=psycopg2-json::${build_json}
+      -
+        name: Setup pikepdf image
+        id: pikepdf-setup
+        run: |
+          build_json=$(python ${GITHUB_WORKSPACE}/.github/scripts/get-build-json.py pikepdf)
+
+          echo ${build_json}
+
+          echo ::set-output name=pikepdf-json::${build_json}
+      -
+        name: Setup jbig2enc image
+        id: jbig2enc-setup
+        run: |
+          build_json=$(python ${GITHUB_WORKSPACE}/.github/scripts/get-build-json.py jbig2enc)
+
+          echo ${build_json}
+
+          echo ::set-output name=jbig2enc-json::${build_json}
+
+    outputs:
+
+      ghcr-repository: ${{ steps.set-ghcr-repository.outputs.repository }}
+
+      qpdf-json: ${{ steps.qpdf-setup.outputs.qpdf-json }}
+
+      pikepdf-json: ${{ steps.pikepdf-setup.outputs.pikepdf-json }}
+
+      psycopg2-json: ${{ steps.psycopg2-setup.outputs.psycopg2-json }}
+
+      jbig2enc-json: ${{ steps.jbig2enc-setup.outputs.jbig2enc-json}}
+
+  build-qpdf-debs:
+    name: qpdf
+    needs:
+      - prepare-docker-build
+    uses: ./.github/workflows/reusable-workflow-builder.yml
+    with:
+      dockerfile: ./docker-builders/Dockerfile.qpdf
+      build-json: ${{ needs.prepare-docker-build.outputs.qpdf-json }}
+      build-args: |
+        QPDF_VERSION=${{ fromJSON(needs.prepare-docker-build.outputs.qpdf-json).version }}
+
+  build-jbig2enc:
+    name: jbig2enc
+    needs:
+      - prepare-docker-build
+    uses: ./.github/workflows/reusable-workflow-builder.yml
+    with:
+      dockerfile: ./docker-builders/Dockerfile.jbig2enc
+      build-json: ${{ needs.prepare-docker-build.outputs.jbig2enc-json }}
+      build-args: |
+        JBIG2ENC_VERSION=${{ fromJSON(needs.prepare-docker-build.outputs.jbig2enc-json).version }}
+
+  build-psycopg2-wheel:
+    name: psycopg2
+    needs:
+      - prepare-docker-build
+    uses: ./.github/workflows/reusable-workflow-builder.yml
+    with:
+      dockerfile: ./docker-builders/Dockerfile.psycopg2
+      build-json: ${{ needs.prepare-docker-build.outputs.psycopg2-json }}
+      build-args: |
+        PSYCOPG2_VERSION=${{ fromJSON(needs.prepare-docker-build.outputs.psycopg2-json).version }}
+
+  build-pikepdf-wheel:
+    name: pikepdf
+    needs:
+      - prepare-docker-build
+      - build-qpdf-debs
+    uses: ./.github/workflows/reusable-workflow-builder.yml
+    with:
+      dockerfile: ./docker-builders/Dockerfile.pikepdf
+      build-json: ${{ needs.prepare-docker-build.outputs.pikepdf-json }}
+      build-args: |
+        REPO=${{ needs.prepare-docker-build.outputs.ghcr-repository }}
+        QPDF_VERSION=${{ fromJSON(needs.prepare-docker-build.outputs.qpdf-json).version }}
+        PIKEPDF_VERSION=${{ fromJSON(needs.prepare-docker-build.outputs.pikepdf-json).version }}

.github/workflows/project-actions.yml

@@ -0,0 +1,57 @@
+name: Project Automations
+
+on:
+  issues:
+    types:
+      - opened
+      - reopened
+  pull_request_target: #_target allows access to secrets
+    types:
+      - opened
+      - reopened
+    branches:
+      - main
+      - dev
+
+permissions:
+  contents: read
+
+env:
+  todo: Todo
+  done: Done
+  in_progress: In Progress
+
+jobs:
+  issue_opened_or_reopened:
+    name: issue_opened_or_reopened
+    runs-on: ubuntu-latest
+    if: github.event_name == 'issues' && (github.event.action == 'opened' || github.event.action == 'reopened')
+    steps:
+      - name: Add issue to project and set status to ${{ env.todo }}
+        uses: leonsteinhaeuser/project-beta-automations@v1.3.0
+        with:
+          gh_token: ${{ secrets.GH_TOKEN }}
+          organization: paperless-ngx
+          project_id: 2
+          resource_node_id: ${{ github.event.issue.node_id }}
+          status_value: ${{ env.todo }} # Target status
+  pr_opened_or_reopened:
+    name: pr_opened_or_reopened
+    runs-on: ubuntu-latest
+    permissions:
+      # write permission is required for autolabeler
+      pull-requests: write
+    if: github.event_name == 'pull_request_target' && (github.event.action == 'opened' || github.event.action == 'reopened') && github.event.pull_request.user.login != 'dependabot'
+    steps:
+      - name: Add PR to project and set status to "Needs Review"
+        uses: leonsteinhaeuser/project-beta-automations@v1.3.0
+        with:
+          gh_token: ${{ secrets.GH_TOKEN }}
+          organization: paperless-ngx
+          project_id: 2
+          resource_node_id: ${{ github.event.pull_request.node_id }}
+          status_value: "Needs Review" # Target status
+      - name: Label PR with release-drafter
+        uses: release-drafter/release-drafter@v5
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/reusable-workflow-builder.yml

@@ -0,0 +1,53 @@
+name: Reusable Image Builder
+
+on:
+  workflow_call:
+    inputs:
+      dockerfile:
+        required: true
+        type: string
+      build-json:
+        required: true
+        type: string
+      build-args:
+        required: false
+        default: ""
+        type: string
+
+concurrency:
+  group: ${{ github.workflow }}-${{ fromJSON(inputs.build-json).name }}-${{ fromJSON(inputs.build-json).version }}
+  cancel-in-progress: false
+
+jobs:
+  build-image:
+    name: Build ${{ fromJSON(inputs.build-json).name }} @ ${{ fromJSON(inputs.build-json).version }}
+    runs-on: ubuntu-latest
+    steps:
+      -
+        name: Checkout
+        uses: actions/checkout@v3
+      -
+        name: Login to Github Container Registry
+        uses: docker/login-action@v2
+        with:
+          registry: ghcr.io
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+      -
+        name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v2
+      -
+        name: Set up QEMU
+        uses: docker/setup-qemu-action@v2
+      -
+        name: Build ${{ fromJSON(inputs.build-json).name }}
+        uses: docker/build-push-action@v3
+        with:
+          context: .
+          file: ${{ inputs.dockerfile }}
+          tags: ${{ fromJSON(inputs.build-json).image_tag }}
+          platforms: linux/amd64,linux/arm64,linux/arm/v7
+          build-args: ${{ inputs.build-args }}
+          push: true
+          cache-from: type=registry,ref=${{ fromJSON(inputs.build-json).cache_tag }}
+          cache-to: type=registry,mode=max,ref=${{ fromJSON(inputs.build-json).cache_tag }}

.gitignore

@@ -61,12 +61,18 @@ target/
 # PyCharm
 .idea
 
+# VS Code
+.vscode
+/src-ui/.vscode
+/docs/.vscode
+
 # Other stuff that doesn't belong
 .virtualenv
 virtualenv
 /venv
-docker-compose.env
-docker-compose.yml
+.venv/
+/docker-compose.env
+/docker-compose.yml
 
 # Used for development
 scripts/import-for-development
@@ -81,7 +87,9 @@ scripts/nuke
 /paperless.conf
 /consume/
 /export/
-/src-ui/.vscode
 
 # this is where the compiled frontend is moved to.
 /src/documents/static/frontend/
+
+# mac os
+.DS_Store

.hadolint.yml

@@ -0,0 +1,8 @@
+failure-threshold: warning
+ignored:
+  # https://github.com/hadolint/hadolint/wiki/DL3008
+  - DL3008
+  # https://github.com/hadolint/hadolint/wiki/DL3013
+  - DL3013
+  # https://github.com/hadolint/hadolint/wiki/DL3003
+  - DL3003

.pre-commit-config.yaml

@@ -0,0 +1,87 @@
+# This file configures pre-commit hooks.
+# See https://pre-commit.com/ for general information
+# See https://pre-commit.com/hooks.html for a listing of possible hooks
+
+repos:
+  # General hooks
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.3.0
+    hooks:
+      - id: check-docstring-first
+      - id: check-json
+        exclude: "tsconfig.*json"
+      - id: check-yaml
+      - id: check-toml
+      - id: check-executables-have-shebangs
+      - id: end-of-file-fixer
+        exclude_types:
+          - svg
+          - pofile
+        exclude: "(^LICENSE$)"
+      - id: mixed-line-ending
+        args:
+          - "--fix=lf"
+      - id: trailing-whitespace
+        exclude_types:
+          - svg
+      - id: check-case-conflict
+      - id: detect-private-key
+  - repo: https://github.com/pre-commit/mirrors-prettier
+    rev: "v2.7.1"
+    hooks:
+      - id: prettier
+        types_or:
+          - javascript
+          - ts
+          - markdown
+        exclude: "(^Pipfile\\.lock$)"
+  # Python hooks
+  - repo: https://github.com/asottile/reorder_python_imports
+    rev: v3.8.2
+    hooks:
+      - id: reorder-python-imports
+        exclude: "(migrations)"
+  - repo: https://github.com/asottile/yesqa
+    rev: "v1.4.0"
+    hooks:
+      - id: yesqa
+        exclude: "(migrations)"
+  - repo: https://github.com/asottile/add-trailing-comma
+    rev: "v2.2.3"
+    hooks:
+      - id: add-trailing-comma
+        exclude: "(migrations)"
+  - repo: https://gitlab.com/pycqa/flake8
+    rev: 3.9.2
+    hooks:
+      - id: flake8
+        files: ^src/
+        args:
+          - "--config=./src/setup.cfg"
+  - repo: https://github.com/psf/black
+    rev: 22.6.0
+    hooks:
+      - id: black
+  - repo: https://github.com/asottile/pyupgrade
+    rev: v2.37.3
+    hooks:
+      - id: pyupgrade
+        exclude: "(migrations)"
+        args:
+          - "--py38-plus"
+  # Dockerfile hooks
+  - repo: https://github.com/AleksaC/hadolint-py
+    rev: v2.10.0
+    hooks:
+      - id: hadolint
+  # Shell script hooks
+  - repo: https://github.com/lovesegfault/beautysh
+    rev: v6.2.1
+    hooks:
+      - id: beautysh
+        args:
+          - "--tab"
+  - repo: https://github.com/shellcheck-py/shellcheck-py
+    rev: "v0.8.0.4"
+    hooks:
+      - id: shellcheck

.prettierrc

@@ -0,0 +1,4 @@
+# https://prettier.io/docs/en/options.html#semicolons
+semi: false
+# https://prettier.io/docs/en/options.html#quotes
+singleQuote: true

.readthedocs.yml

@@ -0,0 +1,16 @@
+# .readthedocs.yml
+# Read the Docs configuration file
+# See https://docs.readthedocs.io/en/stable/config-file/v2.html for details
+
+# Required
+version: 2
+
+# Build documentation in the docs/ directory with Sphinx
+sphinx:
+  configuration: docs/conf.py
+
+# Optionally set the version of Python and requirements required to build your docs
+python:
+  version: "3.8"
+  install:
+    - requirements: docs/requirements.txt

.travis.yml

@@ -1,51 +0,0 @@
-language: python
-
-dist: focal
-os: linux
-
-jobs:
-  include:
-    - name: "Paperless on Python 3.6"
-      python: "3.6"
-
-    - name: "Paperless on Python 3.7"
-      python: "3.7"
-
-    - name: "Paperless on Python 3.8"
-      python: "3.8"
-
-    - name: "Documentation"
-      script:
-        - cd docs/
-        - make html
-      after_success: true
-
-    - name: "Front end"
-      language: node_js
-      node_js:
-        - 15
-      before_install: true
-      install:
-        - cd src-ui/
-        - npm install -g @angular/cli
-        - npm install
-      script:
-        - ng build --prod
-      after_success: true
-
-
-before_install:
-  - sudo apt-get update -qq
-  - sudo apt-get install -qq libpoppler-cpp-dev unpaper tesseract-ocr imagemagick ghostscript optipng
-
-install:
-  - pip install --upgrade pipenv
-  - pipenv install --system --dev
-
-script:
-  - cd src/
-  - pipenv run pytest --cov
-  - pipenv run pycodestyle
-
-after_success:
-  - pipenv run coveralls

CODEOWNERS

@@ -0,0 +1,9 @@
+/.github/workflows/ @paperless-ngx/ci-cd
+/docker/ @paperless-ngx/ci-cd
+/scripts/ @paperless-ngx/ci-cd
+
+/src-ui/ @paperless-ngx/frontend
+
+/src/ @paperless-ngx/backend
+Pipfile* @paperless-ngx/backend
+*.py @paperless-ngx/backend

CODE_OF_CONDUCT.md

@@ -0,0 +1,128 @@
+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+We as members, contributors, and leaders pledge to make participation in our
+community a harassment-free experience for everyone, regardless of age, body
+size, visible or invisible disability, ethnicity, sex characteristics, gender
+identity and expression, level of experience, education, socio-economic status,
+nationality, personal appearance, race, religion, or sexual identity
+and orientation.
+
+We pledge to act and interact in ways that contribute to an open, welcoming,
+diverse, inclusive, and healthy community.
+
+## Our Standards
+
+Examples of behavior that contributes to a positive environment for our
+community include:
+
+- Demonstrating empathy and kindness toward other people
+- Being respectful of differing opinions, viewpoints, and experiences
+- Giving and gracefully accepting constructive feedback
+- Accepting responsibility and apologizing to those affected by our mistakes,
+  and learning from the experience
+- Focusing on what is best not just for us as individuals, but for the
+  overall community
+
+Examples of unacceptable behavior include:
+
+- The use of sexualized language or imagery, and sexual attention or
+  advances of any kind
+- Trolling, insulting or derogatory comments, and personal or political attacks
+- Public or private harassment
+- Publishing others' private information, such as a physical or email
+  address, without their explicit permission
+- Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Enforcement Responsibilities
+
+Community leaders are responsible for clarifying and enforcing our standards of
+acceptable behavior and will take appropriate and fair corrective action in
+response to any behavior that they deem inappropriate, threatening, offensive,
+or harmful.
+
+Community leaders have the right and responsibility to remove, edit, or reject
+comments, commits, code, wiki edits, issues, and other contributions that are
+not aligned to this Code of Conduct, and will communicate reasons for moderation
+decisions when appropriate.
+
+## Scope
+
+This Code of Conduct applies within all community spaces, and also applies when
+an individual is officially representing the community in public spaces.
+Examples of representing our community include using an official e-mail address,
+posting via an official social media account, or acting as an appointed
+representative at an online or offline event.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported to the community leaders responsible for enforcement at
+hello@paperless-ngx.com.
+All complaints will be reviewed and investigated promptly and fairly.
+
+All community leaders are obligated to respect the privacy and security of the
+reporter of any incident.
+
+## Enforcement Guidelines
+
+Community leaders will follow these Community Impact Guidelines in determining
+the consequences for any action they deem in violation of this Code of Conduct:
+
+### 1. Correction
+
+**Community Impact**: Use of inappropriate language or other behavior deemed
+unprofessional or unwelcome in the community.
+
+**Consequence**: A private, written warning from community leaders, providing
+clarity around the nature of the violation and an explanation of why the
+behavior was inappropriate. A public apology may be requested.
+
+### 2. Warning
+
+**Community Impact**: A violation through a single incident or series
+of actions.
+
+**Consequence**: A warning with consequences for continued behavior. No
+interaction with the people involved, including unsolicited interaction with
+those enforcing the Code of Conduct, for a specified period of time. This
+includes avoiding interactions in community spaces as well as external channels
+like social media. Violating these terms may lead to a temporary or
+permanent ban.
+
+### 3. Temporary Ban
+
+**Community Impact**: A serious violation of community standards, including
+sustained inappropriate behavior.
+
+**Consequence**: A temporary ban from any sort of interaction or public
+communication with the community for a specified period of time. No public or
+private interaction with the people involved, including unsolicited interaction
+with those enforcing the Code of Conduct, is allowed during this period.
+Violating these terms may lead to a permanent ban.
+
+### 4. Permanent Ban
+
+**Community Impact**: Demonstrating a pattern of violation of community
+standards, including sustained inappropriate behavior, harassment of an
+individual, or aggression toward or disparagement of classes of individuals.
+
+**Consequence**: A permanent ban from any sort of public interaction within
+the community.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage],
+version 2.0, available at
+https://www.contributor-covenant.org/version/2/0/code_of_conduct.html.
+
+Community Impact Guidelines were inspired by [Mozilla's code of conduct
+enforcement ladder](https://github.com/mozilla/diversity).
+
+[homepage]: https://www.contributor-covenant.org
+
+For answers to common questions about this code of conduct, see the FAQ at
+https://www.contributor-covenant.org/faq. Translations are available at
+https://www.contributor-covenant.org/translations.

CONTRIBUTING.md

@@ -1,30 +1,132 @@
 # Contributing
 
-There's still lots of things to be done, just have a look at that issue log. If you feel like conctributing to the project, please do! Bug fixes and improvements to the front end (I just can't seem to get some of these CSS things right) are always welcome.
+If you feel like contributing to the project, please do! Bug fixes and improvements are always welcome.
 
-If you want to implement something big: Please start a discussion about that in the issues! Maybe I've already had something similar in mind and we can make it happen together. However, keep in mind that the general roadmap is to make the existing features stable and get them tested. See the roadmap in the readme.
+If you want to implement something big:
 
-* When making additions to the project, consider if the majority of users will benefit from your change. If not, you're probably better of forking the project.
-* Also consider if your change will get in the way of other users. A good change is a change that enhances the experience of some users who want that change and does not affect users who do not care about the change.
+- Please start a discussion about that in the issues! Maybe something similar is already in development and we can make it happen together.
+- When making additions to the project, consider if the majority of users will benefit from your change. If not, you're probably better of forking the project.
+- Also consider if your change will get in the way of other users. A good change is a change that enhances the experience of some users who want that change and does not affect users who do not care about the change.
+- Please see the [paperless-ngx merge process](#merging-prs) below.
 
 ## Python
 
-Use python 3.6 for development. Paperless supports python 3.6, 3.7 and 3.8.
+Paperless supports python 3.8 and 3.9. We format Python code with [Black](https://github.com/psf/black).
 
 ## Branches
 
-master always reflects the latest release.
+`main` always reflects the latest release. Apart from changes to the documentation or readme, absolutely no functional changes on this branch in between releases.
 
-dev contains all changes that will be part of the next release. Use this branch to start making your changes.
+`dev` contains all changes that will be part of the next release. Use this branch to start making your changes.
 
-feature-X branches is for experimental stuff that will eventually be merged into dev, and then released as part of the next release.
+`feature-X` branches are for experimental stuff that will eventually be merged into dev.
 
 ## Testing:
 
-I'm trying to get most of paperless tested, so please do the same for your code! I know its a hassle, but it makes sure that your code works now and will allow us to detect regressions easily.
+Please format and test your code! I know it's a hassle, but it makes sure that your code works now and will allow us to detect regressions easily.
 
-To test your code, execute `pytest` in the src/ directory. Executing that in the project root is no good. This also generates a html coverage report, which you can use to see if you missed anything important during testing.
+To test your code, execute `pytest` in the src/ directory. This also generates a html coverage report, which you can use to see if you missed anything important during testing.
+
+Before you can run `pytest`, ensure to [properly set up your local environment](https://paperless-ngx.readthedocs.io/en/latest/extending.html#initial-setup-and-first-start).
 
 ## More info:
 
-... is available in the documentation. https://paperless-ng.readthedocs.io/en/latest/extending.html
+... is available in the documentation. https://paperless-ngx.readthedocs.io/en/latest/extending.html
+
+# Merging PRs
+
+Once you have submitted a **P**ull **R**equest it will be reviewed, approved, and merged by one or more community members of any team. Automated code tests and formatting checks must be passed.
+
+## Non-Trivial Requests
+
+PRs deemed `non-trivial` will go through a stricter review process before being merged into `dev`. This is to ensure code quality and complete functionality (free of side effects).
+
+Examples of `non-trivial` PRs might include:
+
+- Additional features
+- Large changes to many distinct files
+- Breaking or depreciation of existing features
+
+Our community review process for `non-trivial` PRs is the following:
+
+1. Must pass usual automated code tests and formatting checks.
+2. The PR will be assigned and pinged to the appropriately experienced team (i.e. @paperless-ngx/backend for backend changes).
+3. Development team will check and test code manually (possibly over several days).
+   - You may be asked to make changes or rebase.
+   - The team may ask for additional testing done by @paperless-ngx/test
+4. **At least two** members of the team will approve and finally merge the request into `dev` 🎉.
+
+This process might be slow as community members have different schedules and time to dedicate to the Paperless project. However it ensures community code reviews are as brilliantly thorough as they once were with @jonaswinkler.
+
+# Translating Paperless-ngx
+
+Some notes about translation:
+
+- There are two resources:
+  - `src-ui/messages.xlf` contains the translation strings for the front end. This is the most important.
+  - `django.po` contains strings for the administration section of paperless, which is nice to have translated.
+- Most of the front-end strings are used on buttons, menu items, etc., so ideally the translated string should not be much longer than the English original.
+- Translation units may contain placeholders. These usually mean that there's a name of a tag or document or something in the string. You can click on the placeholders to copy them.
+- Translation units may contain plural expressions such as `{PLURAL_VAR, plural, =1 {one result} =0 {no results} other {<placeholder> results}}`. Copy these verbatim and translate only the content in the inner `{}` brackets. Example: `{PLURAL_VAR, plural, =1 {Ein Ergebnis} =0 {Keine Ergebnisse} other {<placeholder> Ergebnisse}}`
+- Changes to translations on Crowdin will get pushed into the repository automatically.
+
+## Adding new languages to the codebase
+
+If a language has already been added, and you would like to contribute new translations or change existing translations, please read the "Translation" section in the README.md file for further details on that.
+
+If you would like the project to be translated to another language, first head over to https://crwd.in/paperless-ngx to check if that language has already been enabled for translation.
+If not, please request the language to be added by creating an issue on GitHub. The issue should contain:
+
+- English name of the language (the localized name can be added on Crowdin).
+- ISO language code. A list of those can be found here: https://support.crowdin.com/enterprise/language-codes/
+- Date format commonly used for the language, e.g. dd/mm/yyyy, mm/dd/yyyy, etc.
+
+After the language has been added and some translations have been made on Crowdin, the language needs to be enabled in the code.
+Note that there is no need to manually add a .po of .xlf file as those will be automatically generated and imported from Crowdin.
+The following files need to be changed:
+
+- src-ui/angular.json (under the _projects/paperless-ui/i18n/locales_ JSON key)
+- src/paperless/settings.py (in the _LANGUAGES_ array)
+- src-ui/src/app/services/settings.service.ts (inside the _getLanguageOptions_ method)
+- src-ui/src/app/app.module.ts (import locale from _angular/common/locales_ and call _registerLocaleData_)
+
+Please add the language in the correct order, alphabetically by locale.
+Note that _en-us_ needs to stay on top of the list, as it is the default project language
+
+If you are familiar with Git, feel free to send a Pull Request with those changes.
+If not, let us know in the issue you created for the language, so that another developer can make these changes.
+
+# Organization Structure & Membership
+
+Paperless-ngx is a community project. We do our best to delegate permission and responsibility among a team of people to ensure the longevity of the project.
+
+## Structure
+
+As of writing, there are 21 members in paperless-ngx. 4 of these people have complete administrative privileges to the repo:
+
+- [@shamoon](https://github.com/shamoon)
+- [@bauerj](https://github.com/bauerj)
+- [@qcasey](https://github.com/qcasey)
+- [@FrankStrieter](https://github.com/FrankStrieter)
+
+There are 5 teams collaborating on specific tasks within paperless-ngx:
+
+- @paperless-ngx/backend (Python / django)
+- @paperless-ngx/frontend (JavaScript / Typescript)
+- @paperless-ngx/ci-cd (GitHub Actions / Deployment)
+- @paperless-ngx/issues (Issue triage)
+- @paperless-ngx/test (General testing for larger PRs)
+
+## Permissions
+
+All team members are notified when mentioned or assigned to a relevant issue or pull request. Additionally, each team has slightly different access to paperless-ngx:
+
+- The **test** team has no special permissions.
+- The **issues** team has `triage` access. This means they can organize issues and pull requests.
+- The **backend**, **frontend**, and **ci-cd** teams have `write` access. This means they can approve PRs and push code, containers, releases, and more.
+
+## Joining
+
+We are not overly strict with inviting people to the organization. If you have read the [team permissions](#permissions) and think having additional access would enhance your contributions, please reach out to an [admin](#structure) of the team.
+
+The admins occasionally invite contributors directly if we believe having them on a team will accelerate their work.

Dockerfile

@@ -0,0 +1,245 @@
+# syntax=docker/dockerfile:1.4
+
+# Pull the installer images from the library
+# These are all built previously
+# They provide either a .deb or .whl
+
+ARG JBIG2ENC_VERSION
+ARG QPDF_VERSION
+ARG PIKEPDF_VERSION
+ARG PSYCOPG2_VERSION
+
+FROM ghcr.io/paperless-ngx/paperless-ngx/builder/jbig2enc:${JBIG2ENC_VERSION} as jbig2enc-builder
+FROM ghcr.io/paperless-ngx/paperless-ngx/builder/qpdf:${QPDF_VERSION} as qpdf-builder
+FROM ghcr.io/paperless-ngx/paperless-ngx/builder/pikepdf:${PIKEPDF_VERSION} as pikepdf-builder
+FROM ghcr.io/paperless-ngx/paperless-ngx/builder/psycopg2:${PSYCOPG2_VERSION} as psycopg2-builder
+
+FROM --platform=$BUILDPLATFORM node:16-bullseye-slim AS compile-frontend
+
+# This stage compiles the frontend
+# This stage runs once for the native platform, as the outputs are not
+# dependent on target arch
+# Inputs: None
+
+COPY ./src-ui /src/src-ui
+
+WORKDIR /src/src-ui
+RUN set -eux \
+  && npm update npm -g \
+  && npm ci --omit=optional
+RUN set -eux \
+  && ./node_modules/.bin/ng build --configuration production
+
+FROM python:3.9-slim-bullseye as main-app
+
+LABEL org.opencontainers.image.authors="paperless-ngx team <hello@paperless-ngx.com>"
+LABEL org.opencontainers.image.documentation="https://paperless-ngx.readthedocs.io/en/latest/"
+LABEL org.opencontainers.image.source="https://github.com/paperless-ngx/paperless-ngx"
+LABEL org.opencontainers.image.url="https://github.com/paperless-ngx/paperless-ngx"
+LABEL org.opencontainers.image.licenses="GPL-3.0-only"
+
+ARG DEBIAN_FRONTEND=noninteractive
+
+#
+# Begin installation and configuration
+# Order the steps below from least often changed to most
+#
+
+# copy jbig2enc
+# Basically will never change again
+COPY --from=jbig2enc-builder /usr/src/jbig2enc/src/.libs/libjbig2enc* /usr/local/lib/
+COPY --from=jbig2enc-builder /usr/src/jbig2enc/src/jbig2 /usr/local/bin/
+COPY --from=jbig2enc-builder /usr/src/jbig2enc/src/*.h /usr/local/include/
+
+# Packages need for running
+ARG RUNTIME_PACKAGES="\
+  curl \
+  file \
+  # fonts for text file thumbnail generation
+  fonts-liberation \
+  gettext \
+  ghostscript \
+  gnupg \
+  gosu \
+  icc-profiles-free \
+  imagemagick \
+  media-types \
+  liblept5 \
+  libpq5 \
+  libxml2 \
+  liblcms2-2 \
+  libtiff5 \
+  libxslt1.1 \
+  libfreetype6 \
+  libwebp6 \
+  libopenjp2-7 \
+  libimagequant0 \
+  libraqm0 \
+  libgnutls30 \
+  libjpeg62-turbo \
+  python3 \
+  python3-pip \
+  python3-setuptools \
+  postgresql-client \
+  mariadb-client \
+  # For Numpy
+  libatlas3-base \
+  # OCRmyPDF dependencies
+  tesseract-ocr \
+  tesseract-ocr-eng \
+  tesseract-ocr-deu \
+  tesseract-ocr-fra \
+  tesseract-ocr-ita \
+  tesseract-ocr-spa \
+  # Suggested for OCRmyPDF
+  pngquant \
+  # Suggested for pikepdf
+  jbig2dec \
+  tzdata \
+  unpaper \
+  # Mime type detection
+  zlib1g \
+  # Barcode splitter
+  libzbar0 \
+  poppler-utils"
+
+# Install basic runtime packages.
+# These change very infrequently
+RUN set -eux \
+  echo "Installing system packages" \
+    && apt-get update \
+    && apt-get install --yes --quiet --no-install-recommends ${RUNTIME_PACKAGES} \
+    && rm -rf /var/lib/apt/lists/* \
+  && echo "Installing supervisor" \
+    && python3 -m pip install --default-timeout=1000 --upgrade --no-cache-dir supervisor==4.2.4
+
+# Copy gunicorn config
+# Changes very infrequently
+WORKDIR /usr/src/paperless/
+
+COPY gunicorn.conf.py .
+
+# setup docker-specific things
+# Use mounts to avoid copying installer files into the image
+# These change sometimes, but rarely
+WORKDIR /usr/src/paperless/src/docker/
+
+COPY [ \
+  "docker/imagemagick-policy.xml", \
+  "docker/supervisord.conf", \
+  "docker/docker-entrypoint.sh", \
+  "docker/docker-prepare.sh", \
+  "docker/paperless_cmd.sh", \
+  "docker/wait-for-redis.py", \
+  "docker/management_script.sh", \
+  "docker/install_management_commands.sh", \
+  "/usr/src/paperless/src/docker/" \
+]
+
+RUN set -eux \
+  && echo "Configuring ImageMagick" \
+    && mv imagemagick-policy.xml /etc/ImageMagick-6/policy.xml \
+  && echo "Configuring supervisord" \
+    && mkdir /var/log/supervisord /var/run/supervisord \
+    && mv supervisord.conf /etc/supervisord.conf \
+  && echo "Setting up Docker scripts" \
+    && mv docker-entrypoint.sh /sbin/docker-entrypoint.sh \
+    && chmod 755 /sbin/docker-entrypoint.sh \
+    && mv docker-prepare.sh /sbin/docker-prepare.sh \
+    && chmod 755 /sbin/docker-prepare.sh \
+    && mv wait-for-redis.py /sbin/wait-for-redis.py \
+    && chmod 755 /sbin/wait-for-redis.py \
+    && mv paperless_cmd.sh /usr/local/bin/paperless_cmd.sh \
+    && chmod 755 /usr/local/bin/paperless_cmd.sh \
+  && echo "Installing managment commands" \
+    && chmod +x install_management_commands.sh \
+    && ./install_management_commands.sh
+
+# Install the built packages from the installer library images
+# Use mounts to avoid copying installer files into the image
+# These change sometimes
+RUN --mount=type=bind,from=qpdf-builder,target=/qpdf \
+    --mount=type=bind,from=psycopg2-builder,target=/psycopg2 \
+    --mount=type=bind,from=pikepdf-builder,target=/pikepdf \
+  set -eux \
+  && echo "Installing qpdf" \
+    && apt-get install --yes --no-install-recommends /qpdf/usr/src/qpdf/libqpdf28_*.deb \
+    && apt-get install --yes --no-install-recommends /qpdf/usr/src/qpdf/qpdf_*.deb \
+  && echo "Installing pikepdf and dependencies" \
+    && python3 -m pip install --no-cache-dir /pikepdf/usr/src/wheels/pyparsing*.whl \
+    && python3 -m pip install --no-cache-dir /pikepdf/usr/src/wheels/packaging*.whl \
+    && python3 -m pip install --no-cache-dir /pikepdf/usr/src/wheels/lxml*.whl \
+    && python3 -m pip install --no-cache-dir /pikepdf/usr/src/wheels/Pillow*.whl \
+    && python3 -m pip install --no-cache-dir /pikepdf/usr/src/wheels/pikepdf*.whl \
+    && python3 -m pip list \
+  && echo "Installing psycopg2" \
+    && python3 -m pip install --no-cache-dir /psycopg2/usr/src/wheels/psycopg2*.whl \
+    && python3 -m pip list
+
+WORKDIR /usr/src/paperless/src/
+
+# Python dependencies
+# Change pretty frequently
+COPY Pipfile* ./
+
+# Packages needed only for building a few quick Python
+# dependencies
+ARG BUILD_PACKAGES="\
+  build-essential \
+  git \
+  default-libmysqlclient-dev \
+  python3-dev"
+
+RUN set -eux \
+  && echo "Installing build system packages" \
+    && apt-get update \
+    && apt-get install --yes --quiet --no-install-recommends ${BUILD_PACKAGES} \
+    && python3 -m pip install --no-cache-dir --upgrade wheel \
+  && echo "Installing pipenv" \
+    && python3 -m pip install --no-cache-dir --upgrade pipenv \
+  && echo "Installing Python requirements" \
+    # pipenv tries to be too fancy and prints so much junk
+    && pipenv requirements > requirements.txt \
+    && python3 -m pip install --default-timeout=1000 --no-cache-dir --requirement requirements.txt \
+    && rm requirements.txt \
+  && echo "Cleaning up image" \
+    && apt-get -y purge ${BUILD_PACKAGES} \
+    && apt-get -y autoremove --purge \
+    && apt-get clean --yes \
+    # Remove pipenv and its unique packages
+    && python3 -m pip uninstall --yes \
+      pipenv \
+      distlib \
+      platformdirs \
+      virtualenv \
+      virtualenv-clone \
+    && rm -rf /var/lib/apt/lists/* \
+    && rm -rf /tmp/* \
+    && rm -rf /var/tmp/* \
+    && rm -rf /var/cache/apt/archives/* \
+    && truncate -s 0 /var/log/*log
+
+# copy backend
+COPY ./src ./
+
+# copy frontend
+COPY --from=compile-frontend /src/src/documents/static/frontend/ ./documents/static/frontend/
+
+# add users, setup scripts
+RUN set -eux \
+  && addgroup --gid 1000 paperless \
+  && useradd --uid 1000 --gid paperless --home-dir /usr/src/paperless paperless \
+  && chown -R paperless:paperless ../ \
+  && gosu paperless python3 manage.py collectstatic --clear --no-input \
+  && gosu paperless python3 manage.py compilemessages
+
+VOLUME ["/usr/src/paperless/data", \
+        "/usr/src/paperless/media", \
+        "/usr/src/paperless/consume", \
+        "/usr/src/paperless/export"]
+
+ENTRYPOINT ["/sbin/docker-entrypoint.sh"]
+
+EXPOSE 8000
+
+CMD ["/usr/local/bin/paperless_cmd.sh"]

Pipfile

@@ -8,40 +8,52 @@ url = "https://www.piwheels.org/simple"
 verify_ssl = true
 name = "piwheels"
 
-[requires]
-python_version = "3.6"
-
 [packages]
-dateparser = "~=0.7.6"
-django = "~=3.1.3"
+dateparser = "~=1.1"
+django = "~=4.0"
 django-cors-headers = "*"
 django-extensions = "*"
-django-filter = "~=2.4.0"
-django-q = "~=1.3.4"
-djangorestframework = "~=3.12.2"
+django-filter = "~=22.1"
+django-q = {editable = true, ref = "paperless-main", git = "https://github.com/paperless-ngx/django-q.git"}
+djangorestframework = "~=3.13"
 filelock = "*"
-fuzzywuzzy = "*"
+fuzzywuzzy = {extras = ["speedup"], version = "*"}
 gunicorn = "*"
 imap-tools = "*"
 langdetect = "*"
-pdftotext = "*"
 pathvalidate = "*"
-pillow = "*"
-pikepdf = "*"
+pillow = "~=9.2"
+pikepdf = "~=5.6"
 python-gnupg = "*"
 python-dotenv = "*"
 python-dateutil = "*"
-python-Levenshtein = "*"
 python-magic = "*"
-psycopg2-binary = "*"
+psycopg2 = "*"
 redis = "*"
-scikit-learn="~=0.23.2"
-whitenoise = "~=5.2.0"
-watchdog = "*"
-whoosh="~=2.7.4"
-inotifyrecursive = "~=0.3.4"
-ocrmypdf = "*"
+scikit-learn = "~=1.1"
+# Pin this until piwheels is building 1.9 (see https://www.piwheels.org/project/scipy/)
+scipy = "==1.8.1"
+whitenoise = "~=6.2"
+watchdog = "~=2.1"
+whoosh="~=2.7"
+inotifyrecursive = "~=0.3"
+ocrmypdf = "~=13.7"
 tqdm = "*"
+tika = "*"
+# TODO: This will sadly also install daphne+dependencies,
+#  which an ASGI server we don't need. Adds about 15MB image size.
+channels = "~=3.0"
+channels-redis = "*"
+uvicorn = {extras = ["standard"], version = "*"}
+concurrent-log-handler = "*"
+"pdfminer.six" = "*"
+"backports.zoneinfo" = {version = "*", markers = "python_version < '3.9'"}
+"importlib-resources" = {version = "*", markers = "python_version < '3.9'"}
+zipp = {version = "*", markers = "python_version < '3.9'"}
+pyzbar = "*"
+pdf2image = "*"
+mysqlclient = "*"
+setproctitle = "*"
 
 [dev-packages]
 coveralls = "*"
@@ -53,6 +65,10 @@ pytest-django = "*"
 pytest-env = "*"
 pytest-sugar = "*"
 pytest-xdist = "*"
-sphinx = "~=3.3"
+sphinx = "~=5.1"
 sphinx_rtd_theme = "*"
 tox = "*"
+black = "*"
+pre-commit = "*"
+sphinx-autobuild = "*"
+myst-parser = "*"

README.md

@@ -1,124 +1,120 @@
-[![Build Status](https://travis-ci.org/jonaswinkler/paperless-ng.svg?branch=master)](https://travis-ci.org/jonaswinkler/paperless-ng)
-[![Documentation Status](https://readthedocs.org/projects/paperless-ng/badge/?version=latest)](https://paperless-ng.readthedocs.io/en/latest/?badge=latest)
-[![Docker Hub Pulls](https://img.shields.io/docker/pulls/jonaswinkler/paperless-ng.svg)](https://hub.docker.com/r/jonaswinkler/paperless-ng)
-[![Coverage Status](https://coveralls.io/repos/github/jonaswinkler/paperless-ng/badge.svg?branch=master)](https://coveralls.io/github/jonaswinkler/paperless-ng?branch=master)
+[![ci](https://github.com/paperless-ngx/paperless-ngx/workflows/ci/badge.svg)](https://github.com/paperless-ngx/paperless-ngx/actions)
+[![Crowdin](https://badges.crowdin.net/paperless-ngx/localized.svg)](https://crowdin.com/project/paperless-ngx)
+[![Documentation Status](https://readthedocs.org/projects/paperless-ngx/badge/?version=latest)](https://paperless-ngx.readthedocs.io/en/latest/?badge=latest)
+[![Coverage Status](https://coveralls.io/repos/github/paperless-ngx/paperless-ngx/badge.svg?branch=master)](https://coveralls.io/github/paperless-ngx/paperless-ngx?branch=master)
+[![Chat on Matrix](https://matrix.to/img/matrix-badge.svg)](https://matrix.to/#/#paperless:adnidor.de)
 
-# Paperless-ng
+<p align="center">
+<img src="https://github.com/paperless-ngx/paperless-ngx/raw/main/resources/logo/web/png/Black%20logo%20-%20no%20background.png#gh-light-mode-only" width="50%" />
+<img src="https://github.com/paperless-ngx/paperless-ngx/raw/main/resources/logo/web/png/White%20logo%20-%20no%20background.png#gh-dark-mode-only" width="50%" />
+</p>
 
-[Paperless](https://github.com/the-paperless-project/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.
+<!-- omit in toc -->
 
-Paperless-ng is a fork of the original project, adding a new interface and many other changes under the hood. For a detailed list of changes, have a look at the changelog in the documentation.
+# Paperless-ngx
 
-This project is still in development and some things may not work as expected.
+Paperless-ngx is a document management system that transforms your physical documents into a searchable online archive so you can keep, well, _less paper_.
 
-# How it Works
+Paperless-ngx forked from [paperless-ng](https://github.com/jonaswinkler/paperless-ng) to continue the great work and distribute responsibility of supporting and advancing the project among a team of people. [Consider joining us!](#community-support) Discussion of this transition can be found in issues
+[#1599](https://github.com/jonaswinkler/paperless-ng/issues/1599) and [#1632](https://github.com/jonaswinkler/paperless-ng/issues/1632).
 
-Paperless does not control your scanner, it only helps you deal with what your scanner produces.
+A demo is available at [demo.paperless-ngx.com](https://demo.paperless-ngx.com) using login `demo` / `demo`. _Note: demo content is reset frequently and confidential information should not be uploaded._
 
-1. Buy a document scanner that can write to a place on your network.  If you need some inspiration, have a look at the [scanner recommendations](https://paperless-ng.readthedocs.io/en/latest/scanners.html) page. Set it up to "scan to FTP" or something similar. It should be able to push scanned images to a server without you having to do anything.  Of course if your scanner doesn't know how to automatically upload the file somewhere, you can always do that manually. Paperless doesn't care how the documents get into its local consumption directory.
-
-	- Alternatively, you can use any of the mobile scanning apps out there. We have an app that allows you to share documents with paperless, if you're on Android. See the section on affiliated projects.
-
-2. Wait for paperless to process your files. OCR is expensive, and depending on the power of your machine, this might take a bit of time.
-3. Use the web frontend to sift through the database and find what you want.
-4. Download the PDF you need/want via the web interface and do whatever you like with it.  You can even print it and send it as if it's the original. In most cases, no one will care or notice.
-
-Here's what you get:
-
-![Dashboard](https://github.com/jonaswinkler/paperless-ng/raw/master/docs/_static/screenshots/dashboard.png)
+- [Features](#features)
+- [Getting started](#getting-started)
+- [Contributing](#contributing)
+  - [Community Support](#community-support)
+  - [Translation](#translation)
+  - [Feature Requests](#feature-requests)
+  - [Bugs](#bugs)
+- [Affiliated Projects](#affiliated-projects)
+- [Important Note](#important-note)
 
 # Features
 
-* Performs OCR on your documents, adds selectable text to image only documents and adds tags, correspondents and document types to your documents.
-* Paperless stores your documents plain on disk. Filenames and folders are managed by paperless and can be configured freely.
-* Single page application front end. Should be pretty snappy. Will be mobile friendly in the future.
-	* Includes a dashboard that shows basic statistics and has document upload.
-	* Filtering by tags, correspondents, types, and more.
-	* Customizable views can be saved and displayed on the dashboard.
-* Full text search helps you find what you need.
-	* Auto completion suggests relevant words from your documents.
-	* Results are sorted by relevance to your search query.
-	* Highlighting shows you which parts of the document matched the query.
-* Email processing: Paperless adds documents from your email accounts.
-	* Configure multiple accounts and filters for each account.
-	* When adding documents from mails, paperless can move these mails to a new folder, mark them as read, flag them or delete them.
-* Machine learning powered document matching.
-	* Paperless learns from your documents and will be able to automatically assign tags, correspondents and types to documents once you've stored a few documents in paperless.
-* A task processor that processes documents in parallel and also tells you when something goes wrong. On modern multi core systems, consumption is blazing fast.
-* Code cleanup in many, MANY areas. Some of the code from OG paperless was just overly complicated.
-* More tests, more stability.
+![Dashboard](https://raw.githubusercontent.com/paperless-ngx/paperless-ngx/main/docs/_static/screenshots/documents-wchrome.png#gh-light-mode-only)
+![Dashboard](https://raw.githubusercontent.com/paperless-ngx/paperless-ngx/main/docs/_static/screenshots/documents-wchrome-dark.png#gh-dark-mode-only)
 
-If you want to see some screenshots of paperless-ng in action, [some are available in the documentation](https://paperless-ng.readthedocs.io/en/latest/screenshots.html).
-
-For a complete list of changes from paperless, check out the [changelog](https://paperless-ng.readthedocs.io/en/latest/changelog.html)
-
-# Roadmap for 1.0
-
-- **Bulk editing**. Add/remove metadata from multiple documents at once.
-
-- Make the front end nice (except mobile).
-- Test coverage at 90%.
-- Fix whatever bugs I and you find.
-
-## Roadmap for versions beyond 1.0
-
-These are things that I want to add to paperless eventually. They are sorted by priority.
-
-- **More search.** The search backend is incredibly versatile and customizable. Searching is the most important feature of this project and thus, I want to implement things like:
-  - Group and limit search results by correspondent, show “more from this” links in the results.
-  - Ability to search for “Similar documents” in the search results
-- **Nested tags**. Organize tags in a hierarchical structure. This will combine the benefits of folders and tags in one coherent system.
-- **An interactive consumer** that shows its progress for documents it processes on the web page.
-	- With live updates ans websockets. This already works on a dev branch, but requires a lot of new dependencies, which I'm not particular happy about.
-	- Notifications when a document was added with buttons to open the new document right away.
-- **Arbitrary tag colors**. Allow the selection of any color with a color picker.
-- **More file types**. Possibly allow more file types to be processed by paperless, such as office .odt, .doc, .docx documents.
-
-Apart from that, paperless is pretty much feature complete.
-
-## On the chopping block.
-
-- **GnuPG encrypion.** [Here's a note about encryption in paperless](https://paperless-ng.readthedocs.io/en/latest/administration.html#managing-encryption). The gist of it is that I don't see which attacks this implementation protects against. It gives a false sense of security to users who don't care about how it works.
+- Organize and index your scanned documents with tags, correspondents, types, and more.
+- Performs OCR on your documents, adds selectable text to image only documents and adds tags, correspondents and document types to your documents.
+- Supports PDF documents, images, plain text files, and Office documents (Word, Excel, Powerpoint, and LibreOffice equivalents).
+  - Office document support is optional and provided by Apache Tika (see [configuration](https://paperless-ngx.readthedocs.io/en/latest/configuration.html#tika-settings))
+- Paperless stores your documents plain on disk. Filenames and folders are managed by paperless and their format can be configured freely.
+- Single page application front end.
+  - Includes a dashboard that shows basic statistics and has document upload.
+  - Filtering by tags, correspondents, types, and more.
+  - Customizable views can be saved and displayed on the dashboard.
+- Full text search helps you find what you need.
+  - Auto completion suggests relevant words from your documents.
+  - Results are sorted by relevance to your search query.
+  - Highlighting shows you which parts of the document matched the query.
+  - Searching for similar documents ("More like this")
+- Email processing: Paperless adds documents from your email accounts.
+  - Configure multiple accounts and filters for each account.
+  - When adding documents from mail, paperless can move these mail to a new folder, mark them as read, flag them as important or delete them.
+- Machine learning powered document matching.
+  - Paperless-ngx learns from your documents and will be able to automatically assign tags, correspondents and types to documents once you've stored a few documents in paperless.
+- Optimized for multi core systems: Paperless-ngx consumes multiple documents in parallel.
+- The integrated sanity checker makes sure that your document archive is in good health.
+- [More screenshots are available in the documentation](https://paperless-ngx.readthedocs.io/en/latest/screenshots.html).
 
 # Getting started
 
-The recommended way to deploy paperless is docker-compose. Don't clone the repository, grab the latest release to get started instead. The dockerfiles archive contains just the docker files which will pull the image from docker hub. The source archive contains everything you need to build the docker image yourself (i.e. if you want to run on Raspberry Pi).
+The easiest way to deploy paperless is docker-compose. The files in the [`/docker/compose` directory](https://github.com/paperless-ngx/paperless-ngx/tree/main/docker/compose) are configured to pull the image from Github Packages.
 
-Read the [documentation](https://paperless-ng.readthedocs.io/en/latest/setup.html#installation) on how to get started.
+If you'd like to jump right in, you can configure a docker-compose environment with our install script:
 
-Alternatively, you can install the dependencies and setup apache and a database server yourself. The documenation has a step by step guide on how to do it.
+```bash
+bash -c "$(curl -L https://raw.githubusercontent.com/paperless-ngx/paperless-ngx/main/install-paperless-ngx.sh)"
+```
 
-# Migrating to paperless-ng
+Alternatively, you can install the dependencies and setup apache and a database server yourself. The [documentation](https://paperless-ngx.readthedocs.io/en/latest/setup.html#installation) has a step by step guide on how to do it.
 
-Read the section about [migration](https://paperless-ng.readthedocs.io/en/latest/setup.html#migration-to-paperless-ng) in the documentation. Its also entirely possible to go back to paperless by reverting the database migrations.
+Migrating from Paperless-ng is easy, just drop in the new docker image! See the [documentation on migrating](https://paperless-ngx.readthedocs.io/en/latest/setup.html#migrating-from-paperless-ng) for more details.
 
-# Documentation
+<!-- omit in toc -->
 
-The documentation for Paperless-ng is available on [ReadTheDocs](https://paperless-ng.readthedocs.io/).
+### Documentation
 
-# Suggestions? Questions? Something not working?
+The documentation for Paperless-ngx is available on [ReadTheDocs](https://paperless-ngx.readthedocs.io/).
 
-Please open an issue and start a discussion about it!
+# Contributing
 
-## Feel like helping out?
+If you feel like contributing to the project, please do! Bug fixes, enhancements, visual fixes etc. are always welcome. If you want to implement something big: Please start a discussion about that! The [documentation](https://paperless-ngx.readthedocs.io/en/latest/extending.html) has some basic information on how to get started.
 
-There's still lots of things to be done, just have a look at that issue log. If you feel like contributing to the project, please do! Bug fixes and improvements to the front end (I just can't seem to get some of these CSS things right) are always welcome. The documentation has some basic information on how to get started.
+## Community Support
 
-If you want to implement something big: Please start a discussion about that in the issues! Maybe I've already had something similar in mind and we can make it happen together. However, keep in mind that the general roadmap is to make the existing features stable and get them tested. See the roadmap above.
+People interested in continuing the work on paperless-ngx are encouraged to reach out here on github and in the [Matrix Room](https://matrix.to/#/#paperless:adnidor.de). If you would like to contribute to the project on an ongoing basis there are multiple [teams](https://github.com/orgs/paperless-ngx/people) (frontend, ci/cd, etc) that could use your help so please reach out!
+
+## Translation
+
+Paperless-ngx is available in many languages that are coordinated on Crowdin. If you want to help out by translating paperless-ngx into your language, please head over to https://crwd.in/paperless-ngx, and thank you! More details can be found in [CONTRIBUTING.md](https://github.com/paperless-ngx/paperless-ngx/blob/main/CONTRIBUTING.md#translating-paperless-ngx).
+
+## Feature Requests
+
+Feature requests can be submitted via [GitHub Discussions](https://github.com/paperless-ngx/paperless-ngx/discussions/categories/feature-requests), you can search for existing ideas, add your own and vote for the ones you care about.
+
+## Bugs
+
+For bugs please [open an issue](https://github.com/paperless-ngx/paperless-ngx/issues) or [start a discussion](https://github.com/paperless-ngx/paperless-ngx/discussions) if you have questions.
 
 # Affiliated Projects
 
-Paperless has been around a while now, and people are starting to build stuff on top of it.  If you're one of those people, we can add your project to this list:
+Paperless has been around a while now, and people are starting to build stuff on top of it. If you're one of those people, we can add your project to this list:
 
-* [Paperless App](https://github.com/bauerj/paperless_app): An Android/iOS app for Paperless. Updated to work with paperless-ng.
-* [Paperless Share](https://github.com/qcasey/paperless_share). Share any files from your Android application with paperless. Very simple, but works with all of the mobile scanning apps out there that allow you to share scanned documents.
+- [Paperless App](https://github.com/bauerj/paperless_app): An Android/iOS app for Paperless-ngx. Also works with the original Paperless and Paperless-ng.
+- [Paperless Share](https://github.com/qcasey/paperless_share). Share any files from your Android application with paperless. Very simple, but works with all of the mobile scanning apps out there that allow you to share scanned documents.
+- [Scan to Paperless](https://github.com/sbrunner/scan-to-paperless): Scan and prepare (crop, deskew, OCR, ...) your documents for Paperless.
 
-These projects also exist, but their status and compatibility with paperless-ng is unknown.
+These projects also exist, but their status and compatibility with paperless-ngx is unknown.
 
-* [Paperless Desktop](https://github.com/thomasbrueggemann/paperless-desktop): A desktop UI for your Paperless installation.  Runs on Mac, Linux, and Windows.
-* [ansible-role-paperless](https://github.com/ovv/ansible-role-paperless): An easy way to get Paperless running via Ansible.
-* [paperless-cli](https://github.com/stgarf/paperless-cli): A golang command line binary to interact with a Paperless instance.
+- [paperless-cli](https://github.com/stgarf/paperless-cli): A golang command line binary to interact with a Paperless instance.
+
+This project also exists, but needs updates to be compatible with paperless-ngx.
+
+- [Paperless Desktop](https://github.com/thomasbrueggemann/paperless-desktop): A desktop UI for your Paperless installation. Runs on Mac, Linux, and Windows.
+  Known issues on Mac: (Could not load reminders and documents)
 
 # Important Note
 
-Document scanners are typically used to scan sensitive documents.  Things like your social insurance number, tax records, invoices, etc.  Everything is stored in the clear without encryption by default (it needs to be searchable, so if someone has ideas on how to do that on encrypted data, I'm all ears).  This means that Paperless should never be run on an untrusted host.  Instead, I recommend that if you do want to use it, run it locally on a server in your own home.
+Document scanners are typically used to scan sensitive documents. Things like your social insurance number, tax records, invoices, etc. Everything is stored in the clear without encryption. This means that Paperless should never be run on an untrusted host. Instead, I recommend that if you do want to use it, run it locally on a server in your own home.

build-docker-image.sh

@@ -0,0 +1,43 @@
+#!/usr/bin/env bash
+
+# Helper script for building the Docker image locally.
+# Parses and provides the nessecary versions of other images to Docker
+# before passing in the rest of script args.
+
+# First Argument: The Dockerfile to build
+# Other Arguments: Additional arguments to docker build
+
+# Example Usage:
+#	./build-docker-image.sh Dockerfile -t paperless-ngx:my-awesome-feature
+
+set -eux
+
+if ! command -v jq;  then
+	echo "jq required"
+	exit 1
+elif [ ! -f "$1" ]; then
+	echo "$1 is not a file, please provide the Dockerfile"
+	exit 1
+fi
+
+# Parse what we can from Pipfile.lock
+pikepdf_version=$(jq ".default.pikepdf.version" Pipfile.lock  | sed 's/=//g' | sed 's/"//g')
+psycopg2_version=$(jq ".default.psycopg2.version" Pipfile.lock | sed 's/=//g' | sed 's/"//g')
+# Read this from the other config file
+qpdf_version=$(jq ".qpdf.version" .build-config.json | sed 's/"//g')
+jbig2enc_version=$(jq ".jbig2enc.version" .build-config.json | sed 's/"//g')
+# Get the branch name (used for caching)
+branch_name=$(git rev-parse --abbrev-ref HEAD)
+
+# https://docs.docker.com/develop/develop-images/build_enhancements/
+# Required to use cache-from
+export DOCKER_BUILDKIT=1
+
+docker build --file "$1" \
+	--progress=plain \
+	--cache-from ghcr.io/paperless-ngx/paperless-ngx/builder/cache/app:"${branch_name}" \
+	--cache-from ghcr.io/paperless-ngx/paperless-ngx/builder/cache/app:dev \
+	--build-arg JBIG2ENC_VERSION="${jbig2enc_version}" \
+	--build-arg QPDF_VERSION="${qpdf_version}" \
+	--build-arg PIKEPDF_VERSION="${pikepdf_version}" \
+	--build-arg PSYCOPG2_VERSION="${psycopg2_version}" "${@:2}" .

crowdin.yml

@@ -0,0 +1,6 @@
+commit_message: '[ci skip]'
+files:
+  - source: /src/locale/en_US/LC_MESSAGES/django.po
+    translation: /src/locale/%locale_with_underscore%/LC_MESSAGES/django.po
+  - source: /src-ui/messages.xlf
+    translation: /src-ui/src/locale/messages.%locale_with_underscore%.xlf

docker-builders/Dockerfile.frontend

@@ -0,0 +1,14 @@
+# This Dockerfile compiles the frontend
+# Inputs: None
+
+FROM node:16-bullseye-slim AS compile-frontend
+
+COPY ./src /src/src
+COPY ./src-ui /src/src-ui
+
+WORKDIR /src/src-ui
+RUN set -eux \
+  && npm update npm -g \
+  && npm ci --omit=optional
+RUN set -eux \
+  && ./node_modules/.bin/ng build --configuration production

docker-builders/Dockerfile.jbig2enc

@@ -0,0 +1,35 @@
+# This Dockerfile compiles the jbig2enc library
+# Inputs:
+#    - JBIG2ENC_VERSION - the Git tag to checkout and build
+
+FROM debian:bullseye-slim as main
+
+LABEL org.opencontainers.image.description="A intermediate image with jbig2enc built"
+
+ARG DEBIAN_FRONTEND=noninteractive
+ARG JBIG2ENC_VERSION
+
+ARG BUILD_PACKAGES="\
+  build-essential \
+  automake \
+  libtool \
+  libleptonica-dev \
+  zlib1g-dev \
+  git \
+  ca-certificates"
+
+WORKDIR /usr/src/jbig2enc
+
+RUN set -eux \
+  && echo "Installing build tools" \
+    && apt-get update --quiet \
+    && apt-get install --yes --quiet --no-install-recommends ${BUILD_PACKAGES} \
+  && echo "Building jbig2enc" \
+    && git clone --quiet --branch $JBIG2ENC_VERSION https://github.com/agl/jbig2enc . \
+    && ./autogen.sh \
+    && ./configure \
+    && make \
+  && echo "Cleaning up image" \
+    && apt-get -y purge ${BUILD_PACKAGES} \
+    && apt-get -y autoremove --purge \
+    && rm -rf /var/lib/apt/lists/*

docker-builders/Dockerfile.pikepdf

@@ -0,0 +1,88 @@
+# This Dockerfile builds the pikepdf wheel
+# Inputs:
+#    - REPO - Docker repository to pull qpdf from
+#    - QPDF_VERSION - The image qpdf version to copy .deb files from
+#    - PIKEPDF_VERSION - Version of pikepdf to build wheel for
+
+# Default to pulling from the main repo registry when manually building
+ARG REPO="paperless-ngx/paperless-ngx"
+
+ARG QPDF_VERSION
+FROM ghcr.io/${REPO}/builder/qpdf:${QPDF_VERSION} as qpdf-builder
+
+# This does nothing, except provide a name for a copy below
+
+FROM python:3.9-slim-bullseye as main
+
+LABEL org.opencontainers.image.description="A intermediate image with pikepdf wheel built"
+
+ARG DEBIAN_FRONTEND=noninteractive
+ARG PIKEPDF_VERSION
+
+ARG BUILD_PACKAGES="\
+  build-essential \
+  python3-dev \
+  python3-pip \
+  # qpdf requirement - https://github.com/qpdf/qpdf#crypto-providers
+  libgnutls28-dev \
+  # lxml requrements - https://lxml.de/installation.html
+  libxml2-dev \
+  libxslt1-dev \
+  # Pillow requirements - https://pillow.readthedocs.io/en/stable/installation.html#external-libraries
+  # JPEG functionality
+  libjpeg62-turbo-dev \
+  # conpressed PNG
+  zlib1g-dev \
+  # compressed TIFF
+  libtiff-dev \
+  # type related services
+  libfreetype-dev \
+  # color management
+  liblcms2-dev \
+  # WebP format
+  libwebp-dev \
+  # JPEG 2000
+  libopenjp2-7-dev \
+  # improved color quantization
+  libimagequant-dev \
+  # complex text layout support
+  libraqm-dev"
+
+WORKDIR /usr/src
+
+COPY --from=qpdf-builder /usr/src/qpdf/*.deb ./
+
+# As this is an base image for a multi-stage final image
+# the added size of the install is basically irrelevant
+
+RUN set -eux \
+  && echo "Installing build tools" \
+    && apt-get update --quiet \
+    && apt-get install --yes --quiet --no-install-recommends ${BUILD_PACKAGES} \
+  && echo "Installing qpdf" \
+    && dpkg --install libqpdf28_*.deb \
+    && dpkg --install libqpdf-dev_*.deb \
+  && echo "Installing Python tools" \
+    && python3 -m pip install --no-cache-dir --upgrade \
+      pip \
+      wheel \
+      # https://pikepdf.readthedocs.io/en/latest/installation.html#requirements
+      pybind11 \
+  && echo "Building pikepdf wheel ${PIKEPDF_VERSION}" \
+    && mkdir wheels \
+    && python3 -m pip wheel \
+      # Build the package at the required version
+      pikepdf==${PIKEPDF_VERSION} \
+      # Output the *.whl into this directory
+      --wheel-dir wheels \
+      # Do not use a binary packge for the package being built
+      --no-binary=pikepdf \
+      # Do use binary packages for dependencies
+      --prefer-binary \
+      # Don't cache build files
+      --no-cache-dir \
+    && ls -ahl wheels \
+  && echo "Cleaning up image" \
+    && apt-get -y purge ${BUILD_PACKAGES} \
+    && apt-get -y autoremove --purge \
+    && rm -rf /var/lib/apt/lists/*

docker-builders/Dockerfile.psycopg2

@@ -0,0 +1,48 @@
+# This Dockerfile builds the psycopg2 wheel
+# Inputs:
+#    - PSYCOPG2_VERSION - Version to build
+
+FROM python:3.9-slim-bullseye as main
+
+LABEL org.opencontainers.image.description="A intermediate image with psycopg2 wheel built"
+
+ARG PSYCOPG2_VERSION
+ARG DEBIAN_FRONTEND=noninteractive
+
+ARG BUILD_PACKAGES="\
+  build-essential \
+  python3-dev \
+  python3-pip \
+  # https://www.psycopg.org/docs/install.html#prerequisites
+  libpq-dev"
+
+WORKDIR /usr/src
+
+# As this is an base image for a multi-stage final image
+# the added size of the install is basically irrelevant
+
+RUN set -eux \
+  && echo "Installing build tools" \
+    && apt-get update --quiet \
+    && apt-get install --yes --quiet --no-install-recommends ${BUILD_PACKAGES} \
+  && echo "Installing Python tools" \
+    && python3 -m pip install --no-cache-dir --upgrade pip wheel \
+  && echo "Building psycopg2 wheel ${PSYCOPG2_VERSION}" \
+    && cd /usr/src \
+    && mkdir wheels \
+    && python3 -m pip wheel \
+      # Build the package at the required version
+      psycopg2==${PSYCOPG2_VERSION} \
+      # Output the *.whl into this directory
+      --wheel-dir wheels \
+      # Do not use a binary packge for the package being built
+      --no-binary=psycopg2 \
+      # Do use binary packages for dependencies
+      --prefer-binary \
+      # Don't cache build files
+      --no-cache-dir \
+    && ls -ahl wheels/ \
+  && echo "Cleaning up image" \
+    && apt-get -y purge ${BUILD_PACKAGES} \
+    && apt-get -y autoremove --purge \
+    && rm -rf /var/lib/apt/lists/*

docker-builders/Dockerfile.qpdf

@@ -0,0 +1,52 @@
+# This Dockerfile compiles the jbig2enc library
+# Inputs:
+#    - QPDF_VERSION - the version of qpdf to build a .deb.
+#                     Must be preset as a deb-src
+
+FROM debian:bullseye-slim as main
+
+LABEL org.opencontainers.image.description="A intermediate image with qpdf built"
+
+ARG DEBIAN_FRONTEND=noninteractive
+# This must match to pikepdf's minimum at least
+ARG QPDF_VERSION
+
+ARG BUILD_PACKAGES="\
+  build-essential \
+  debhelper \
+  debian-keyring \
+  devscripts \
+  equivs  \
+  libtool \
+  # https://qpdf.readthedocs.io/en/stable/installation.html#system-requirements
+  libjpeg62-turbo-dev \
+  libgnutls28-dev \
+  packaging-dev \
+  zlib1g-dev"
+
+WORKDIR /usr/src
+
+# As this is an base image for a multi-stage final image
+# the added size of the install is basically irrelevant
+
+RUN set -eux \
+  && echo "Installing build tools" \
+    && apt-get update --quiet \
+    && apt-get install --yes --quiet --no-install-recommends $BUILD_PACKAGES \
+  && echo "Building qpdf" \
+    && echo "deb-src http://deb.debian.org/debian/ bookworm main" > /etc/apt/sources.list.d/bookworm-src.list \
+    && apt-get update \
+    && mkdir qpdf \
+    && cd qpdf \
+    && apt-get source --yes --quiet qpdf=${QPDF_VERSION}-1/bookworm \
+    && cd qpdf-$QPDF_VERSION \
+    # We don't need to build the tests (also don't run them)
+    && rm -rf libtests \
+    && DEBEMAIL=hello@paperless-ngx.com debchange --bpo \
+    && export DEB_BUILD_OPTIONS="terse nocheck nodoc parallel=2" \
+    && dpkg-buildpackage --build=binary --unsigned-source --unsigned-changes --post-clean \
+    && ls -ahl ../*.deb \
+  && echo "Cleaning up image" \
+    && apt-get -y purge ${BUILD_PACKAGES} \
+    && apt-get -y autoremove --purge \
+    && rm -rf /var/lib/apt/lists/*

docker/compose/.env

@@ -0,0 +1 @@
+COMPOSE_PROJECT_NAME=paperless

docker/compose/docker-compose.env

@@ -7,7 +7,7 @@
 # Additional languages to install for text recognition, separated by a
 # whitespace. Note that this is
 # different from PAPERLESS_OCR_LANGUAGE (default=eng), which defines the
-# default language used when guessing the language from the OCR output.
+# language used for OCR.
 # The container installs English, German, Italian, Spanish and French by
 # default.
 # See https://packages.debian.org/search?keywords=tesseract-ocr-&searchon=names&suite=buster
@@ -22,6 +22,10 @@
 # Docker setup does not use the configuration file.
 # A few commonly adjusted settings are provided below.
 
+# This is required if you will be exposing Paperless-ngx on a public domain
+# (if doing so please consider security measures such as reverse proxy)
+#PAPERLESS_URL=https://paperless.example.com
+
 # Adjust this key if you plan to make paperless available publicly. It should
 # be a very long sequence of random characters. You don't need to remember it.
 #PAPERLESS_SECRET_KEY=change-me
@@ -32,3 +36,7 @@
 # The default language to use for OCR. Set this to the language most of your
 # documents are written in.
 #PAPERLESS_OCR_LANGUAGE=eng
+
+# Set if accessing paperless via a domain subpath e.g. https://domain.com/PATHPREFIX and using a reverse-proxy like traefik or nginx
+#PAPERLESS_FORCE_SCRIPT_NAME=/PATHPREFIX
+#PAPERLESS_STATIC_URL=/PATHPREFIX/static/ # trailing slash required

docker/compose/docker-compose.mariadb-tika.yml

@@ -0,0 +1,101 @@
+# docker-compose file for running paperless from the Docker Hub.
+# This file contains everything paperless needs to run.
+# Paperless supports amd64, arm and arm64 hardware.
+#
+# All compose files of paperless configure paperless in the following way:
+#
+# - Paperless is (re)started on system boot, if it was running before shutdown.
+# - Docker volumes for storing data are managed by Docker.
+# - Folders for importing and exporting files are created in the same directory
+#   as this file and mounted to the correct folders inside the container.
+# - Paperless listens on port 8000.
+#
+# In addition to that, this docker-compose file adds the following optional
+# configurations:
+#
+# - Instead of SQLite (default), MariaDB is used as the database server.
+# - Apache Tika and Gotenberg servers are started with paperless and paperless
+#   is configured to use these services. These provide support for consuming
+#   Office documents (Word, Excel, Power Point and their LibreOffice counter-
+#   parts.
+#
+# To install and update paperless with this file, do the following:
+#
+# - Copy this file as 'docker-compose.yml' and the files 'docker-compose.env'
+#   and '.env' into a folder.
+# - Run 'docker-compose pull'.
+# - Run 'docker-compose run --rm webserver createsuperuser' to create a user.
+# - Run 'docker-compose up -d'.
+#
+# For more extensive installation and update instructions, refer to the
+# documentation.
+
+version: "3.4"
+services:
+  broker:
+    image: docker.io/library/redis:7
+    restart: unless-stopped
+    volumes:
+      - redisdata:/data
+
+  db:
+    image: docker.io/library/mariadb:10
+    restart: unless-stopped
+    volumes:
+      - dbdata:/var/lib/mysql
+    environment:
+      MARIADB_HOST: paperless
+      MARIADB_DATABASE: paperless
+      MARIADB_USER: paperless
+      MARIADB_PASSWORD: paperless
+      MARIADB_ROOT_PASSWORD: paperless
+    ports:
+      - "3306:3306"
+
+  webserver:
+    image: ghcr.io/paperless-ngx/paperless-ngx:latest
+    restart: unless-stopped
+    depends_on:
+      - db
+      - broker
+      - gotenberg
+      - tika
+    ports:
+      - 8000:8000
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:8000"]
+      interval: 30s
+      timeout: 10s
+      retries: 5
+    volumes:
+      - data:/usr/src/paperless/data
+      - media:/usr/src/paperless/media
+      - ./export:/usr/src/paperless/export
+      - ./consume:/usr/src/paperless/consume
+    env_file: docker-compose.env
+    environment:
+      PAPERLESS_REDIS: redis://broker:6379
+      PAPERLESS_DBENGINE: mariadb
+      PAPERLESS_DBHOST: db
+      PAPERLESS_DBUSER: paperless
+      PAPERLESS_DBPASSWORD: paperless
+      PAPERLESS_DBPORT: 3306
+      PAPERLESS_TIKA_ENABLED: 1
+      PAPERLESS_TIKA_GOTENBERG_ENDPOINT: http://gotenberg:3000
+      PAPERLESS_TIKA_ENDPOINT: http://tika:9998
+
+  gotenberg:
+    image: docker.io/gotenberg/gotenberg:7.4
+    restart: unless-stopped
+    environment:
+      CHROMIUM_DISABLE_ROUTES: 1
+
+  tika:
+    image: ghcr.io/paperless-ngx/tika:latest
+    restart: unless-stopped
+
+volumes:
+  data:
+  media:
+  dbdata:
+  redisdata:

docker/compose/docker-compose.mariadb.yml

@@ -0,0 +1,83 @@
+# docker-compose file for running paperless from the Docker Hub.
+# This file contains everything paperless needs to run.
+# Paperless supports amd64, arm and arm64 hardware.
+#
+# All compose files of paperless configure paperless in the following way:
+#
+# - Paperless is (re)started on system boot, if it was running before shutdown.
+# - Docker volumes for storing data are managed by Docker.
+# - Folders for importing and exporting files are created in the same directory
+#   as this file and mounted to the correct folders inside the container.
+# - Paperless listens on port 8000.
+#
+# In addition to that, this docker-compose file adds the following optional
+# configurations:
+#
+# - Instead of SQLite (default), MariaDB is used as the database server.
+#
+# To install and update paperless with this file, do the following:
+#
+# - Copy this file as 'docker-compose.yml' and the files 'docker-compose.env'
+#   and '.env' into a folder.
+# - Run 'docker-compose pull'.
+# - Run 'docker-compose run --rm webserver createsuperuser' to create a user.
+# - Run 'docker-compose up -d'.
+#
+# For more extensive installation and update instructions, refer to the
+# documentation.
+
+version: "3.4"
+services:
+  broker:
+    image: docker.io/library/redis:7
+    restart: unless-stopped
+    volumes:
+      - redisdata:/data
+
+  db:
+    image: docker.io/library/mariadb:10
+    restart: unless-stopped
+    volumes:
+      - dbdata:/var/lib/mysql
+    environment:
+      MARIADB_HOST: paperless
+      MARIADB_DATABASE: paperless
+      MARIADB_USER: paperless
+      MARIADB_PASSWORD: paperless
+      MARIADB_ROOT_PASSWORD: paperless
+    ports:
+      - "3306:3306"
+
+  webserver:
+    image: ghcr.io/paperless-ngx/paperless-ngx:latest
+    restart: unless-stopped
+    depends_on:
+      - db
+      - broker
+    ports:
+      - 8000:8000
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:8000"]
+      interval: 30s
+      timeout: 10s
+      retries: 5
+    volumes:
+      - data:/usr/src/paperless/data
+      - media:/usr/src/paperless/media
+      - ./export:/usr/src/paperless/export
+      - ./consume:/usr/src/paperless/consume
+    env_file: docker-compose.env
+    environment:
+      PAPERLESS_REDIS: redis://broker:6379
+      PAPERLESS_DBENGINE: mariadb
+      PAPERLESS_DBHOST: db
+      PAPERLESS_DBUSER: paperless
+      PAPERLESS_DBPASSWORD: paperless
+      PAPERLESS_DBPORT: 3306
+
+
+volumes:
+  data:
+  media:
+  dbdata:
+  redisdata:

docker/compose/docker-compose.portainer.yml

@@ -0,0 +1,97 @@
+# docker-compose file for running paperless from the Docker Hub.
+# This file contains everything paperless needs to run.
+# Paperless supports amd64, arm and arm64 hardware.
+#
+# All compose files of paperless configure paperless in the following way:
+#
+# - Paperless is (re)started on system boot, if it was running before shutdown.
+# - Docker volumes for storing data are managed by Docker.
+# - Folders for importing and exporting files are created in the same directory
+#   as this file and mounted to the correct folders inside the container.
+# - Paperless listens on port 8010.
+#
+# In addition to that, this docker-compose file adds the following optional
+# configurations:
+#
+# - Instead of SQLite (default), PostgreSQL is used as the database server.
+#
+# To install and update paperless with this file, do the following:
+#
+# - Open portainer Stacks list and click 'Add stack'
+# - Paste the contents of this file and assign a name, e.g. 'Paperless'
+# - Click 'Deploy the stack' and wait for it to be deployed
+# - Open the list of containers, select paperless_webserver_1
+# - Click 'Console' and then 'Connect' to open the command line inside the container
+# - Run 'python3 manage.py createsuperuser' to create a user
+# - Exit the console
+#
+# For more extensive installation and update instructions, refer to the
+# documentation.
+
+version: "3.4"
+services:
+  broker:
+    image: docker.io/library/redis:7
+    restart: unless-stopped
+    volumes:
+      - redisdata:/data
+
+  db:
+    image: docker.io/library/postgres:13
+    restart: unless-stopped
+    volumes:
+      - pgdata:/var/lib/postgresql/data
+    environment:
+      POSTGRES_DB: paperless
+      POSTGRES_USER: paperless
+      POSTGRES_PASSWORD: paperless
+
+  webserver:
+    image: ghcr.io/paperless-ngx/paperless-ngx:latest
+    restart: unless-stopped
+    depends_on:
+      - db
+      - broker
+    ports:
+      - 8010:8000
+    healthcheck:
+      test: ["CMD", "curl", "-fs", "-S", "--max-time", "2", "http://localhost:8000"]
+      interval: 30s
+      timeout: 10s
+      retries: 5
+    volumes:
+      - data:/usr/src/paperless/data
+      - media:/usr/src/paperless/media
+      - ./export:/usr/src/paperless/export
+      - ./consume:/usr/src/paperless/consume
+    environment:
+      PAPERLESS_REDIS: redis://broker:6379
+      PAPERLESS_DBHOST: db
+# The UID and GID of the user used to run paperless in the container. Set this
+# to your UID and GID on the host so that you have write access to the
+# consumption directory.
+      USERMAP_UID: 1000
+      USERMAP_GID: 100
+# Additional languages to install for text recognition, separated by a
+# whitespace. Note that this is
+# different from PAPERLESS_OCR_LANGUAGE (default=eng), which defines the
+# language used for OCR.
+# The container installs English, German, Italian, Spanish and French by
+# default.
+# See https://packages.debian.org/search?keywords=tesseract-ocr-&searchon=names&suite=buster
+# for available languages.
+      #PAPERLESS_OCR_LANGUAGES: tur ces
+# Adjust this key if you plan to make paperless available publicly. It should
+# be a very long sequence of random characters. You don't need to remember it.
+      #PAPERLESS_SECRET_KEY: change-me
+# Use this variable to set a timezone for the Paperless Docker containers. If not specified, defaults to UTC.
+      #PAPERLESS_TIME_ZONE: America/Los_Angeles
+# The default language to use for OCR. Set this to the language most of your
+# documents are written in.
+      #PAPERLESS_OCR_LANGUAGE: eng
+
+volumes:
+  data:
+  media:
+  pgdata:
+  redisdata:

docker/compose/docker-compose.postgres-tika.yml

@@ -0,0 +1,94 @@
+# docker-compose file for running paperless from the docker container registry.
+# This file contains everything paperless needs to run.
+# Paperless supports amd64, arm and arm64 hardware.
+#
+# All compose files of paperless configure paperless in the following way:
+#
+# - Paperless is (re)started on system boot, if it was running before shutdown.
+# - Docker volumes for storing data are managed by Docker.
+# - Folders for importing and exporting files are created in the same directory
+#   as this file and mounted to the correct folders inside the container.
+# - Paperless listens on port 8000.
+#
+# In addition to that, this docker-compose file adds the following optional
+# configurations:
+#
+# - Instead of SQLite (default), PostgreSQL is used as the database server.
+# - Apache Tika and Gotenberg servers are started with paperless and paperless
+#   is configured to use these services. These provide support for consuming
+#   Office documents (Word, Excel, Power Point and their LibreOffice counter-
+#   parts.
+#
+# To install and update paperless with this file, do the following:
+#
+# - Copy this file as 'docker-compose.yml' and the files 'docker-compose.env'
+#   and '.env' into a folder.
+# - Run 'docker-compose pull'.
+# - Run 'docker-compose run --rm webserver createsuperuser' to create a user.
+# - Run 'docker-compose up -d'.
+#
+# For more extensive installation and update instructions, refer to the
+# documentation.
+
+version: "3.4"
+services:
+  broker:
+    image: docker.io/library/redis:7
+    restart: unless-stopped
+    volumes:
+      - redisdata:/data
+
+  db:
+    image: docker.io/library/postgres:13
+    restart: unless-stopped
+    volumes:
+      - pgdata:/var/lib/postgresql/data
+    environment:
+      POSTGRES_DB: paperless
+      POSTGRES_USER: paperless
+      POSTGRES_PASSWORD: paperless
+
+  webserver:
+    image: ghcr.io/paperless-ngx/paperless-ngx:latest
+    restart: unless-stopped
+    depends_on:
+      - db
+      - broker
+      - gotenberg
+      - tika
+    ports:
+      - 8000:8000
+    healthcheck:
+      test: ["CMD", "curl", "-fs", "-S", "--max-time", "2", "http://localhost:8000"]
+      interval: 30s
+      timeout: 10s
+      retries: 5
+    volumes:
+      - data:/usr/src/paperless/data
+      - media:/usr/src/paperless/media
+      - ./export:/usr/src/paperless/export
+      - ./consume:/usr/src/paperless/consume
+    env_file: docker-compose.env
+    environment:
+      PAPERLESS_REDIS: redis://broker:6379
+      PAPERLESS_DBHOST: db
+      PAPERLESS_TIKA_ENABLED: 1
+      PAPERLESS_TIKA_GOTENBERG_ENDPOINT: http://gotenberg:3000
+      PAPERLESS_TIKA_ENDPOINT: http://tika:9998
+
+  gotenberg:
+    image: docker.io/gotenberg/gotenberg:7.4
+    restart: unless-stopped
+    command:
+      - "gotenberg"
+      - "--chromium-disable-routes=true"
+
+  tika:
+    image: ghcr.io/paperless-ngx/tika:latest
+    restart: unless-stopped
+
+volumes:
+  data:
+  media:
+  pgdata:
+  redisdata:

docker/compose/docker-compose.postgres.yml

@@ -0,0 +1,75 @@
+# docker-compose file for running paperless from the Docker Hub.
+# This file contains everything paperless needs to run.
+# Paperless supports amd64, arm and arm64 hardware.
+#
+# All compose files of paperless configure paperless in the following way:
+#
+# - Paperless is (re)started on system boot, if it was running before shutdown.
+# - Docker volumes for storing data are managed by Docker.
+# - Folders for importing and exporting files are created in the same directory
+#   as this file and mounted to the correct folders inside the container.
+# - Paperless listens on port 8000.
+#
+# In addition to that, this docker-compose file adds the following optional
+# configurations:
+#
+# - Instead of SQLite (default), PostgreSQL is used as the database server.
+#
+# To install and update paperless with this file, do the following:
+#
+# - Copy this file as 'docker-compose.yml' and the files 'docker-compose.env'
+#   and '.env' into a folder.
+# - Run 'docker-compose pull'.
+# - Run 'docker-compose run --rm webserver createsuperuser' to create a user.
+# - Run 'docker-compose up -d'.
+#
+# For more extensive installation and update instructions, refer to the
+# documentation.
+
+version: "3.4"
+services:
+  broker:
+    image: docker.io/library/redis:7
+    restart: unless-stopped
+    volumes:
+      - redisdata:/data
+
+  db:
+    image: docker.io/library/postgres:13
+    restart: unless-stopped
+    volumes:
+      - pgdata:/var/lib/postgresql/data
+    environment:
+      POSTGRES_DB: paperless
+      POSTGRES_USER: paperless
+      POSTGRES_PASSWORD: paperless
+
+  webserver:
+    image: ghcr.io/paperless-ngx/paperless-ngx:latest
+    restart: unless-stopped
+    depends_on:
+      - db
+      - broker
+    ports:
+      - 8000:8000
+    healthcheck:
+      test: ["CMD", "curl", "-fs", "-S", "--max-time", "2", "http://localhost:8000"]
+      interval: 30s
+      timeout: 10s
+      retries: 5
+    volumes:
+      - data:/usr/src/paperless/data
+      - media:/usr/src/paperless/media
+      - ./export:/usr/src/paperless/export
+      - ./consume:/usr/src/paperless/consume
+    env_file: docker-compose.env
+    environment:
+      PAPERLESS_REDIS: redis://broker:6379
+      PAPERLESS_DBHOST: db
+
+
+volumes:
+  data:
+  media:
+  pgdata:
+  redisdata:

docker/compose/docker-compose.sqlite-tika.yml

@@ -0,0 +1,81 @@
+# docker-compose file for running paperless from the docker container registry.
+# This file contains everything paperless needs to run.
+# Paperless supports amd64, arm and arm64 hardware.
+# All compose files of paperless configure paperless in the following way:
+#
+# - Paperless is (re)started on system boot, if it was running before shutdown.
+# - Docker volumes for storing data are managed by Docker.
+# - Folders for importing and exporting files are created in the same directory
+#   as this file and mounted to the correct folders inside the container.
+# - Paperless listens on port 8000.
+#
+# SQLite is used as the database. The SQLite file is stored in the data volume.
+#
+# In addition to that, this docker-compose file adds the following optional
+# configurations:
+#
+# - Apache Tika and Gotenberg servers are started with paperless and paperless
+#   is configured to use these services. These provide support for consuming
+#   Office documents (Word, Excel, Power Point and their LibreOffice counter-
+#   parts.
+#
+# To install and update paperless with this file, do the following:
+#
+# - Copy this file as 'docker-compose.yml' and the files 'docker-compose.env'
+#   and '.env' into a folder.
+# - Run 'docker-compose pull'.
+# - Run 'docker-compose run --rm webserver createsuperuser' to create a user.
+# - Run 'docker-compose up -d'.
+#
+# For more extensive installation and update instructions, refer to the
+# documentation.
+
+version: "3.4"
+services:
+  broker:
+    image: docker.io/library/redis:7
+    restart: unless-stopped
+    volumes:
+      - redisdata:/data
+
+  webserver:
+    image: ghcr.io/paperless-ngx/paperless-ngx:latest
+    restart: unless-stopped
+    depends_on:
+      - broker
+      - gotenberg
+      - tika
+    ports:
+      - 8000:8000
+    healthcheck:
+      test: ["CMD", "curl", "-fs", "-S", "--max-time", "2", "http://localhost:8000"]
+      interval: 30s
+      timeout: 10s
+      retries: 5
+    volumes:
+      - data:/usr/src/paperless/data
+      - media:/usr/src/paperless/media
+      - ./export:/usr/src/paperless/export
+      - ./consume:/usr/src/paperless/consume
+    env_file: docker-compose.env
+    environment:
+      PAPERLESS_REDIS: redis://broker:6379
+      PAPERLESS_TIKA_ENABLED: 1
+      PAPERLESS_TIKA_GOTENBERG_ENDPOINT: http://gotenberg:3000
+      PAPERLESS_TIKA_ENDPOINT: http://tika:9998
+
+  gotenberg:
+    image: docker.io/gotenberg/gotenberg:7.4
+    restart: unless-stopped
+    command:
+      - "gotenberg"
+      - "--chromium-disable-routes=true"
+
+  tika:
+    image: ghcr.io/paperless-ngx/tika:latest
+    restart: unless-stopped
+
+volumes:
+  data:
+  media:
+  redisdata:

docker/compose/docker-compose.sqlite.yml

@@ -0,0 +1,59 @@
+# docker-compose file for running paperless from the Docker Hub.
+# This file contains everything paperless needs to run.
+# Paperless supports amd64, arm and arm64 hardware.
+#
+# All compose files of paperless configure paperless in the following way:
+#
+# - Paperless is (re)started on system boot, if it was running before shutdown.
+# - Docker volumes for storing data are managed by Docker.
+# - Folders for importing and exporting files are created in the same directory
+#   as this file and mounted to the correct folders inside the container.
+# - Paperless listens on port 8000.
+#
+# SQLite is used as the database. The SQLite file is stored in the data volume.
+#
+# To install and update paperless with this file, do the following:
+#
+# - Copy this file as 'docker-compose.yml' and the files 'docker-compose.env'
+#   and '.env' into a folder.
+# - Run 'docker-compose pull'.
+# - Run 'docker-compose run --rm webserver createsuperuser' to create a user.
+# - Run 'docker-compose up -d'.
+#
+# For more extensive installation and update instructions, refer to the
+# documentation.
+
+version: "3.4"
+services:
+  broker:
+    image: docker.io/library/redis:7
+    restart: unless-stopped
+    volumes:
+      - redisdata:/data
+
+  webserver:
+    image: ghcr.io/paperless-ngx/paperless-ngx:latest
+    restart: unless-stopped
+    depends_on:
+      - broker
+    ports:
+      - 8000:8000
+    healthcheck:
+      test: ["CMD", "curl", "-fs", "-S", "--max-time", "2", "http://localhost:8000"]
+      interval: 30s
+      timeout: 10s
+      retries: 5
+    volumes:
+      - data:/usr/src/paperless/data
+      - media:/usr/src/paperless/media
+      - ./export:/usr/src/paperless/export
+      - ./consume:/usr/src/paperless/consume
+    env_file: docker-compose.env
+    environment:
+      PAPERLESS_REDIS: redis://broker:6379
+
+
+volumes:
+  data:
+  media:
+  redisdata:

docker/docker-entrypoint.sh

@@ -1,90 +1,107 @@
-#!/bin/bash
+#!/usr/bin/env bash
 
 set -e
 
+# Adapted from:
+# https://github.com/docker-library/postgres/blob/master/docker-entrypoint.sh
+# usage: file_env VAR
+#    ie: file_env 'XYZ_DB_PASSWORD' will allow for "$XYZ_DB_PASSWORD_FILE" to
+# fill in the value of "$XYZ_DB_PASSWORD" from a file, especially for Docker's
+# secrets feature
+file_env() {
+	local var="$1"
+	local fileVar="${var}_FILE"
+
+	# Basic validation
+	if [ "${!var:-}" ] && [ "${!fileVar:-}" ]; then
+		echo >&2 "error: both $var and $fileVar are set (but are exclusive)"
+		exit 1
+	fi
+
+	# Only export var if the _FILE exists
+	if [ "${!fileVar:-}" ]; then
+		# And the file exists
+		if [[ -f ${!fileVar} ]]; then
+			echo "Setting ${var} from file"
+			val="$(< "${!fileVar}")"
+			export "$var"="$val"
+		else
+			echo "File ${!fileVar} doesn't exist"
+			exit 1
+		fi
+	fi
+
+}
+
 # Source: https://github.com/sameersbn/docker-gitlab/
 map_uidgid() {
-    USERMAP_ORIG_UID=$(id -u paperless)
-    USERMAP_ORIG_GID=$(id -g paperless)
-    USERMAP_NEW_UID=${USERMAP_UID:-$USERMAP_ORIG_UID}
-    USERMAP_NEW_GID=${USERMAP_GID:-${USERMAP_ORIG_GID:-$USERMAP_NEW_UID}}
-    if [[ ${USERMAP_NEW_UID} != "${USERMAP_ORIG_UID}" || ${USERMAP_NEW_GID} != "${USERMAP_ORIG_GID}" ]]; then
-        echo "Mapping UID and GID for paperless:paperless to $USERMAP_NEW_UID:$USERMAP_NEW_GID"
-        usermod -u "${USERMAP_NEW_UID}" paperless
-        groupmod -o -g "${USERMAP_NEW_GID}" paperless
-    fi
+	USERMAP_ORIG_UID=$(id -u paperless)
+	USERMAP_ORIG_GID=$(id -g paperless)
+	USERMAP_NEW_UID=${USERMAP_UID:-$USERMAP_ORIG_UID}
+	USERMAP_NEW_GID=${USERMAP_GID:-${USERMAP_ORIG_GID:-$USERMAP_NEW_UID}}
+	if [[ ${USERMAP_NEW_UID} != "${USERMAP_ORIG_UID}" || ${USERMAP_NEW_GID} != "${USERMAP_ORIG_GID}" ]]; then
+		echo "Mapping UID and GID for paperless:paperless to $USERMAP_NEW_UID:$USERMAP_NEW_GID"
+		usermod -o -u "${USERMAP_NEW_UID}" paperless
+		groupmod -o -g "${USERMAP_NEW_GID}" paperless
+	fi
 }
 
-
-wait_for_postgres() {
-	attempt_num=1
-	max_attempts=5
-
-	echo "Waiting for PostgreSQL to start..."
-
-	host="${PAPERLESS_DBHOST}"
-	port="${PAPERLESS_DBPORT}"
-
-	if [[ -z $port ]] ;
-	then
-		port="5432"
-	fi
-
-	while !</dev/tcp/$host/$port ;
-	do
-
-		if [ $attempt_num -eq $max_attempts ]
-		then
-			echo "Unable to connect to database."
-			exit 1
-		else
-			echo "Attempt $attempt_num failed! Trying again in 5 seconds..."
-
-		fi
-
-		attempt_num=$(expr "$attempt_num" + 1)
-		sleep 5
-	done
-
-
-}
-
-
-migrations() {
-
-	if [[ -n "${PAPERLESS_DBHOST}" ]]
-	then
-		wait_for_postgres
-	fi
-
-	(
-		# flock is in place to prevent multiple containers from doing migrations
-		# simultaneously. This also ensures that the db is ready when the command
-		# of the current container starts.
-		flock 200
-		sudo -HEu paperless python3 manage.py migrate
-	)  200>/usr/src/paperless/data/migration_lock
-
+map_folders() {
+	# Export these so they can be used in docker-prepare.sh
+	export DATA_DIR="${PAPERLESS_DATA_DIR:-/usr/src/paperless/data}"
+	export MEDIA_ROOT_DIR="${PAPERLESS_MEDIA_ROOT:-/usr/src/paperless/media}"
 }
 
 initialize() {
+
+	# Setup environment from secrets before anything else
+	for env_var in \
+		PAPERLESS_DBUSER \
+		PAPERLESS_DBPASS \
+		PAPERLESS_SECRET_KEY \
+		PAPERLESS_AUTO_LOGIN_USERNAME \
+		PAPERLESS_ADMIN_USER \
+		PAPERLESS_ADMIN_MAIL \
+		PAPERLESS_ADMIN_PASSWORD \
+		PAPERLESS_REDIS; do
+		# Check for a version of this var with _FILE appended
+		# and convert the contents to the env var value
+		file_env ${env_var}
+	done
+
+	# Change the user and group IDs if needed
 	map_uidgid
 
-	for dir in export data data/index media media/documents media/documents/originals media/documents/thumbnails; do
-		if [[ ! -d "../$dir" ]]
-		then
-			echo "creating directory ../$dir"
-			mkdir ../$dir
+	# Check for overrides of certain folders
+	map_folders
+
+	local export_dir="/usr/src/paperless/export"
+
+	for dir in "${export_dir}" "${DATA_DIR}" "${DATA_DIR}/index" "${MEDIA_ROOT_DIR}" "${MEDIA_ROOT_DIR}/documents" "${MEDIA_ROOT_DIR}/documents/originals" "${MEDIA_ROOT_DIR}/documents/thumbnails"; do
+		if [[ ! -d "${dir}" ]]; then
+			echo "Creating directory ${dir}"
+			mkdir "${dir}"
 		fi
 	done
 
-	chown -R paperless:paperless ../
+	local tmp_dir="/tmp/paperless"
+	echo "Creating directory ${tmp_dir}"
+	mkdir -p "${tmp_dir}"
 
-	migrations
+	set +e
+	echo "Adjusting permissions of paperless files. This may take a while."
+	chown -R paperless:paperless ${tmp_dir}
+	for dir in "${export_dir}" "${DATA_DIR}" "${MEDIA_ROOT_DIR}"; do
+		find "${dir}" -not \( -user paperless -and -group paperless \) -exec chown paperless:paperless {} +
+	done
+	set -e
 
+	"${gosu_cmd[@]}" /sbin/docker-prepare.sh
 }
 
 install_languages() {
+	echo "Installing languages..."
+
 	local langs="$1"
 	read -ra langs <<<"$langs"
 
@@ -95,40 +112,48 @@ install_languages() {
 	apt-get update
 
 	for lang in "${langs[@]}"; do
-        pkg="tesseract-ocr-$lang"
-        # English is installed by default
-        #if [[ "$lang" ==  "eng" ]]; then
-        #    continue
-        #fi
+		pkg="tesseract-ocr-$lang"
+		# English is installed by default
+		#if [[ "$lang" ==  "eng" ]]; then
+		#    continue
+		#fi
 
-        if dpkg -s $pkg &> /dev/null; then
-        	echo "package $pkg already installed!"
-        	continue
-        fi
+		if dpkg -s "$pkg" &>/dev/null; then
+			echo "Package $pkg already installed!"
+			continue
+		fi
 
-        if ! apt-cache show $pkg &> /dev/null; then
-        	echo "package $pkg not found! :("
-        	continue
-        fi
+		if ! apt-cache show "$pkg" &>/dev/null; then
+			echo "Package $pkg not found! :("
+			continue
+		fi
 
-				echo "Installing package $pkg..."
-				if ! apt-get -y install "$pkg" &> /dev/null; then
-					echo "Could not install $pkg"
-					exit 1
-				fi
-    done
+		echo "Installing package $pkg..."
+		if ! apt-get -y install "$pkg" &>/dev/null; then
+			echo "Could not install $pkg"
+			exit 1
+		fi
+	done
 }
 
+echo "Paperless-ngx docker container starting..."
+
+gosu_cmd=(gosu paperless)
+if [ "$(id -u)" == "$(id -u paperless)" ]; then
+	gosu_cmd=()
+fi
+
 # Install additional languages if specified
-if [[ ! -z "$PAPERLESS_OCR_LANGUAGES"  ]]; then
-		install_languages "$PAPERLESS_OCR_LANGUAGES"
+if [[ -n "$PAPERLESS_OCR_LANGUAGES" ]]; then
+	install_languages "$PAPERLESS_OCR_LANGUAGES"
 fi
 
 initialize
 
 if [[ "$1" != "/"* ]]; then
-	exec sudo -HEu paperless python3 manage.py "$@"
+	echo Executing management command "$@"
+	exec "${gosu_cmd[@]}" python3 manage.py "$@"
 else
+	echo Executing "$@"
 	exec "$@"
 fi
-

docker/docker-prepare.sh

@@ -0,0 +1,109 @@
+#!/usr/bin/env bash
+
+set -e
+
+wait_for_postgres() {
+	local attempt_num=1
+	local max_attempts=5
+
+	echo "Waiting for PostgreSQL to start..."
+
+	local host="${PAPERLESS_DBHOST:-localhost}"
+	local port="${PAPERLESS_DBPORT:-5432}"
+
+	# Disable warning, host and port can't have spaces
+	# shellcheck disable=SC2086
+	while [ ! "$(pg_isready -h ${host} -p ${port})" ]; do
+
+		if [ $attempt_num -eq $max_attempts ]; then
+			echo "Unable to connect to database."
+			exit 1
+		else
+			echo "Attempt $attempt_num failed! Trying again in 5 seconds..."
+
+		fi
+
+		attempt_num=$(("$attempt_num" + 1))
+		sleep 5
+	done
+}
+
+wait_for_mariadb() {
+	echo "Waiting for MariaDB to start..."
+
+	host="${PAPERLESS_DBHOST:=localhost}"
+	port="${PAPERLESS_DBPORT:=3306}"
+
+	attempt_num=1
+	max_attempts=5
+
+	while ! true > /dev/tcp/$host/$port; do
+
+		if [ $attempt_num -eq $max_attempts ]; then
+			echo "Unable to connect to database."
+			exit 1
+		else
+			echo "Attempt $attempt_num failed! Trying again in 5 seconds..."
+
+		fi
+
+		attempt_num=$(("$attempt_num" + 1))
+		sleep 5
+	done
+}
+
+wait_for_redis() {
+	# We use a Python script to send the Redis ping
+	# instead of installing redis-tools just for 1 thing
+	if ! python3 /sbin/wait-for-redis.py; then
+		exit 1
+	fi
+}
+
+migrations() {
+	(
+		# flock is in place to prevent multiple containers from doing migrations
+		# simultaneously. This also ensures that the db is ready when the command
+		# of the current container starts.
+		flock 200
+		echo "Apply database migrations..."
+		python3 manage.py migrate
+	) 200>"${DATA_DIR}/migration_lock"
+}
+
+search_index() {
+
+	local index_version=1
+	local index_version_file=${DATA_DIR}/.index_version
+
+	if [[ (! -f "${index_version_file}") || $(<"${index_version_file}") != "$index_version" ]]; then
+		echo "Search index out of date. Updating..."
+		python3 manage.py document_index reindex --no-progress-bar
+		echo ${index_version} | tee "${index_version_file}" >/dev/null
+	fi
+}
+
+superuser() {
+	if [[ -n "${PAPERLESS_ADMIN_USER}" ]]; then
+		python3 manage.py manage_superuser
+	fi
+}
+
+do_work() {
+	if [[ "${PAPERLESS_DBENGINE}" == "mariadb" ]]; then
+		wait_for_mariadb
+	elif [[ -n "${PAPERLESS_DBHOST}" ]]; then
+		wait_for_postgres
+	fi
+
+	wait_for_redis
+
+	migrations
+
+	search_index
+
+	superuser
+
+}
+
+do_work

docker/hub/docker-compose.postgres.yml

@@ -1,44 +0,0 @@
-version: "3.4"
-services:
-  broker:
-    image: redis:6.0
-    restart: always
-
-  db:
-    image: postgres:13
-    restart: always
-    volumes:
-      - pgdata:/var/lib/postgresql/data
-    environment:
-      POSTGRES_DB: paperless
-      POSTGRES_USER: paperless
-      POSTGRES_PASSWORD: paperless
-
-  webserver:
-    image: jonaswinkler/paperless-ng:0.9.9
-    restart: always
-    depends_on:
-      - db
-      - broker
-    ports:
-      - 8000:8000
-    healthcheck:
-      test: ["CMD", "curl", "-f", "http://localhost:8000"]
-      interval: 30s
-      timeout: 10s
-      retries: 5
-    volumes:
-      - data:/usr/src/paperless/data
-      - media:/usr/src/paperless/media
-      - ./export:/usr/src/paperless/export
-      - ./consume:/usr/src/paperless/consume
-    env_file: docker-compose.env
-    environment:
-      PAPERLESS_REDIS: redis://broker:6379
-      PAPERLESS_DBHOST: db
-
-
-volumes:
-  data:
-  media:
-  pgdata:

docker/hub/docker-compose.sqlite.yml

@@ -1,31 +0,0 @@
-version: "3.4"
-services:
-  broker:
-    image: redis:6.0
-    restart: always
-
-  webserver:
-    image: jonaswinkler/paperless-ng:0.9.9
-    restart: always
-    depends_on:
-      - broker
-    ports:
-      - 8000:8000
-    healthcheck:
-      test: ["CMD", "curl", "-f", "http://localhost:8000"]
-      interval: 30s
-      timeout: 10s
-      retries: 5
-    volumes:
-      - data:/usr/src/paperless/data
-      - media:/usr/src/paperless/media
-      - ./export:/usr/src/paperless/export
-      - ./consume:/usr/src/paperless/consume
-    env_file: docker-compose.env
-    environment:
-      PAPERLESS_REDIS: redis://broker:6379
-
-
-volumes:
-  data:
-  media:

docker/install_management_commands.sh

@@ -0,0 +1,21 @@
+#!/usr/bin/env bash
+
+set -eu
+
+for command in decrypt_documents \
+	document_archiver \
+	document_exporter \
+	document_importer \
+	mail_fetcher \
+	document_create_classifier \
+	document_index \
+	document_renamer \
+	document_retagger \
+	document_thumbnails \
+	document_sanity_checker \
+	manage_superuser;
+do
+	echo "installing $command..."
+	sed "s/management_command/$command/g" management_script.sh > /usr/local/bin/$command
+	chmod +x /usr/local/bin/$command
+done

docker/local/Dockerfile

@@ -1,67 +0,0 @@
-FROM python:3.7-slim
-
-WORKDIR /usr/src/paperless/
-
-COPY requirements.txt ./
-
-#Dependencies
-RUN apt-get update \
-  && apt-get -y --no-install-recommends install \
-		build-essential \
-		curl \
-		ghostscript \
-		gnupg \
-		icc-profiles-free \
-		imagemagick \
-		libatlas-base-dev \
-		liblept5 \
-		libmagic-dev \
-		libpoppler-cpp-dev \
-		libpq-dev \
-		libqpdf-dev \
-		libxml2 \
-		optipng \
-		pngquant \
-		qpdf \
-		sudo \
-		tesseract-ocr \
-		tesseract-ocr-eng \
-		tesseract-ocr-deu \
-		tesseract-ocr-fra \
-		tesseract-ocr-ita \
-		tesseract-ocr-spa \
-		tzdata \
-		unpaper \
-		zlib1g \
-	&& pip3 install --upgrade supervisor setuptools \
-	&& pip install --no-cache-dir -r requirements.txt \
-	&& apt-get -y purge build-essential libqpdf-dev \
-	&& apt-get -y autoremove --purge \
-	&& rm -rf /var/lib/apt/lists/* \
-	&& mkdir /var/log/supervisord /var/run/supervisord
-
-# copy scripts
-# this fixes issues with imagemagick and PDF
-COPY docker/imagemagick-policy.xml /etc/ImageMagick-6/policy.xml
-COPY docker/gunicorn.conf.py ./
-COPY docker/supervisord.conf /etc/supervisord.conf
-COPY docker/docker-entrypoint.sh /sbin/docker-entrypoint.sh
-
-# copy app
-COPY src/ ./src/
-
-# add users, setup scripts
-RUN addgroup --gid 1000 paperless \
-	&& useradd --uid 1000 --gid paperless --home-dir /usr/src/paperless paperless \
-	&& chown -R paperless:paperless . \
-	&& chmod 755 /sbin/docker-entrypoint.sh
-
-WORKDIR /usr/src/paperless/src/
-
-RUN sudo -HEu paperless python3 manage.py collectstatic --clear --no-input
-
-VOLUME ["/usr/src/paperless/data", "/usr/src/paperless/media", "/usr/src/paperless/consume", "/usr/src/paperless/export"]
-ENTRYPOINT ["/sbin/docker-entrypoint.sh"]
-CMD ["/usr/local/bin/supervisord", "-c", "/etc/supervisord.conf"]
-
-LABEL maintainer="Jonas Winkler <dev@jpwinkler.de>"

docker/local/docker-compose.postgres.yml

@@ -1,44 +0,0 @@
-version: "3.4"
-services:
-  broker:
-    image: redis:6.0
-    restart: always
-
-  db:
-    image: postgres:13
-    restart: always
-    volumes:
-      - pgdata:/var/lib/postgresql/data
-    environment:
-      POSTGRES_DB: paperless
-      POSTGRES_USER: paperless
-      POSTGRES_PASSWORD: paperless
-
-  webserver:
-    build: .
-    restart: always
-    depends_on:
-      - db
-      - broker
-    ports:
-      - 8000:8000
-    healthcheck:
-      test: ["CMD", "curl", "-f", "http://localhost:8000"]
-      interval: 30s
-      timeout: 10s
-      retries: 5
-    volumes:
-      - data:/usr/src/paperless/data
-      - media:/usr/src/paperless/media
-      - ./export:/usr/src/paperless/export
-      - ./consume:/usr/src/paperless/consume
-    env_file: docker-compose.env
-    environment:
-      PAPERLESS_REDIS: redis://broker:6379
-      PAPERLESS_DBHOST: db
-
-
-volumes:
-  data:
-  media:
-  pgdata:

docker/local/docker-compose.sqlite.yml

@@ -1,31 +0,0 @@
-version: "3.4"
-services:
-  broker:
-    image: redis:6.0
-    restart: always
-
-  webserver:
-    build: .
-    restart: always
-    depends_on:
-      - broker
-    ports:
-      - 8000:8000
-    healthcheck:
-      test: ["CMD", "curl", "-f", "http://localhost:8000"]
-      interval: 30s
-      timeout: 10s
-      retries: 5
-    volumes:
-      - data:/usr/src/paperless/data
-      - media:/usr/src/paperless/media
-      - ./export:/usr/src/paperless/export
-      - ./consume:/usr/src/paperless/consume
-    env_file: docker-compose.env
-    environment:
-      PAPERLESS_REDIS: redis://broker:6379
-
-
-volumes:
-  data:
-  media:

docker/management_script.sh

@@ -0,0 +1,15 @@
+#!/usr/bin/env bash
+
+set -e
+
+cd /usr/src/paperless/src/
+
+if [[ $(id -u) == 0 ]] ;
+then
+	gosu paperless python3 manage.py management_command "$@"
+elif [[ $(id -un) == "paperless" ]] ;
+then
+	python3 manage.py management_command "$@"
+else
+	echo "Unknown user."
+fi

docker/paperless_cmd.sh

@@ -0,0 +1,15 @@
+#!/usr/bin/env bash
+
+rootless_args=()
+if [ "$(id -u)" == "$(id -u paperless)" ]; then
+	rootless_args=(
+		--user
+		paperless
+		--logfile
+		supervisord.log
+		--pidfile
+		supervisord.pid
+	)
+fi
+
+/usr/local/bin/supervisord -c /etc/supervisord.conf "${rootless_args[@]}"

docker/supervisord.conf

@@ -8,7 +8,7 @@ loglevel=info                ; log level; default info; others: debug,warn,trace
 user=root
 
 [program:gunicorn]
-command=gunicorn -c /usr/src/paperless/gunicorn.conf.py -b 0.0.0.0:8000 paperless.wsgi
+command=gunicorn -c /usr/src/paperless/gunicorn.conf.py paperless.asgi:application
 user=paperless
 
 stdout_logfile=/dev/stdout
@@ -19,6 +19,7 @@ stderr_logfile_maxbytes=0
 [program:consumer]
 command=python3 manage.py document_consumer
 user=paperless
+stopsignal=INT
 
 stdout_logfile=/dev/stdout
 stdout_logfile_maxbytes=0
@@ -28,6 +29,7 @@ stderr_logfile_maxbytes=0
 [program:scheduler]
 command=python3 manage.py qcluster
 user=paperless
+stopasgroup = true
 
 stdout_logfile=/dev/stdout
 stdout_logfile_maxbytes=0

docker/wait-for-redis.py

@@ -0,0 +1,44 @@
+#!/usr/bin/env python3
+"""
+Simple script which attempts to ping the Redis broker as set in the environment for
+a certain number of times, waiting a little bit in between
+
+"""
+import os
+import sys
+import time
+from typing import Final
+
+from redis import Redis
+
+if __name__ == "__main__":
+
+    MAX_RETRY_COUNT: Final[int] = 5
+    RETRY_SLEEP_SECONDS: Final[int] = 5
+
+    REDIS_URL: Final[str] = os.getenv("PAPERLESS_REDIS", "redis://localhost:6379")
+
+    print(f"Waiting for Redis...", flush=True)
+
+    attempt = 0
+    with Redis.from_url(url=REDIS_URL) as client:
+        while attempt < MAX_RETRY_COUNT:
+            try:
+                client.ping()
+                break
+            except Exception as e:
+                print(
+                    f"Redis ping #{attempt} failed.\n"
+                    f"Error: {str(e)}.\n"
+                    f"Waiting {RETRY_SLEEP_SECONDS}s",
+                    flush=True,
+                )
+                time.sleep(RETRY_SLEEP_SECONDS)
+                attempt += 1
+
+    if attempt >= MAX_RETRY_COUNT:
+        print(f"Failed to connect to redis using environment variable PAPERLESS_REDIS.")
+        sys.exit(os.EX_UNAVAILABLE)
+    else:
+        print(f"Connected to Redis broker.")
+        sys.exit(os.EX_OK)

docs/Dockerfile

@@ -1,18 +0,0 @@
-FROM python:3.5.1
-MAINTAINER Pit Kleyersburg <pitkley@googlemail.com>
-
-# Install Sphinx and Pygments
-RUN pip install Sphinx Pygments
-
-# Setup directories, copy data
-RUN mkdir /build
-COPY . /build
-WORKDIR /build/docs
-
-# Build documentation
-RUN make html
-
-# Start webserver
-WORKDIR /build/docs/_build/html
-EXPOSE 8000/tcp
-CMD ["python3", "-m", "http.server"]

docs/Makefile

@@ -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

docs/_static/css/custom.css

@@ -0,0 +1,597 @@
+/* Variables */
+:root {
+  --color-text-body: #5c5962;
+  --color-text-body-light: #fcfcfc;
+  --color-text-anchor: #7253ed;
+  --color-text-alt: rgba(0, 0, 0, 0.3);
+  --color-text-title: #27262b;
+  --color-text-code-inline: #e74c3c;
+  --color-text-code-nt: #062873;
+  --color-text-selection: #b19eff;
+  --color-bg-body: #fcfcfc;
+  --color-bg-body-alt: #f3f6f6;
+  --color-bg-side-nav: #f5f6fa;
+  --color-bg-side-nav-hover: #ebedf5;
+  --color-bg-code-block: var(--color-bg-side-nav);
+  --color-border: #eeebee;
+  --color-btn-neutral-bg: #f3f6f6;
+  --color-btn-neutral-bg-hover: #e5ebeb;
+  --color-success-title: #1abc9c;
+  --color-success-body: #dbfaf4;
+  --color-warning-title: #f0b37e;
+  --color-warning-body: #ffedcc;
+  --color-danger-title: #f29f97;
+  --color-danger-body: #fdf3f2;
+  --color-info-title: #6ab0de;
+  --color-info-body: #e7f2fa;
+}
+
+.dark-mode {
+  --color-text-body: #abb2bf;
+  --color-text-body-light: #9499a2;
+  --color-text-alt: rgba(0255, 255, 255, 0.5);
+  --color-text-title: var(--color-text-anchor);
+  --color-text-code-inline: #abb2bf;
+  --color-text-code-nt: #2063f3;
+  --color-text-selection: #030303;
+  --color-bg-body: #1d1d20 !important;
+  --color-bg-body-alt: #131315;
+  --color-bg-side-nav: #18181a;
+  --color-bg-side-nav-hover: #101216;
+  --color-bg-code-block: #101216;
+  --color-border: #47494f;
+  --color-btn-neutral-bg: #242529;
+  --color-btn-neutral-bg-hover: #101216;
+  --color-success-title: #02120f;
+  --color-success-body: #041b17;
+  --color-warning-title: #1b0e03;
+  --color-warning-body: #371d06;
+  --color-danger-title: #120902;
+  --color-danger-body: #1b0503;
+  --color-info-title: #020608;
+  --color-info-body: #06141e;
+}
+
+* {
+  transition: background-color 0.3s ease, border-color 0.3s ease;
+}
+
+/* Typography */
+body {
+  font-family: system-ui,-apple-system,BlinkMacSystemFont,"Segoe UI",Roboto,"Helvetica Neue",Arial,sans-serif;
+  font-size: inherit;
+  line-height: 1.4;
+  color: var(--color-text-body);
+}
+
+.rst-content p {
+  word-break: break-word;
+}
+
+h1, h2, h3, h4, h5, h6 {
+  font-family: inherit;
+}
+
+.rst-content .toctree-wrapper>p.caption, .rst-content h1, .rst-content h2, .rst-content h3, .rst-content h4, .rst-content h5, .rst-content h6 {
+  padding-top: .5em;
+}
+
+p, .main-content-wrap, .rst-content .section ul, .rst-content .toctree-wrapper ul, .rst-content section ul, .wy-plain-list-disc, article ul {
+  line-height: 1.6;
+}
+
+pre, .code, .rst-content .linenodiv pre, .rst-content div[class^=highlight] pre, .rst-content pre.literal-block {
+  font-family: "SFMono-Regular", Menlo,Consolas, Monospace;
+  font-size: 0.75em;
+  line-height: 1.8;
+}
+
+.wy-menu-vertical li.toctree-l3,.wy-menu-vertical li.toctree-l4 {
+  font-size: 1rem
+}
+
+.rst-versions {
+  font-family: inherit;
+  line-height: 1;
+}
+
+footer, footer p {
+  font-size: .8rem;
+}
+
+footer .rst-footer-buttons {
+  font-size: 1rem;
+}
+
+@media (max-width: 400px) {
+  /* break code lines on mobile */
+  pre, code {
+    word-break: break-word;
+  }
+}
+
+
+/* Layout */
+.wy-side-nav-search, .wy-menu-vertical {
+  width: auto;
+}
+
+.wy-nav-side {
+  z-index: 0;
+  display: flex;
+  flex-wrap: wrap;
+  background-color: var(--color-bg-side-nav);
+}
+
+.wy-side-scroll {
+  width: 100%;
+  overflow-y: auto;
+}
+
+@media (min-width: 66.5rem) {
+  .wy-side-scroll {
+      width:264px
+  }
+}
+
+@media (min-width: 50rem) {
+  .wy-nav-side {
+      flex-wrap: nowrap;
+      position: fixed;
+      width: 248px;
+      height: 100%;
+      flex-direction: column;
+      border-right: 1px solid var(--color-border);
+      align-items:flex-end
+  }
+}
+
+@media (min-width: 66.5rem) {
+  .wy-nav-side {
+      width: calc((100% - 1064px) / 2 + 264px);
+      min-width:264px
+  }
+}
+
+@media (min-width: 50rem) {
+  .wy-nav-content-wrap {
+      position: relative;
+      max-width: 800px;
+      margin-left:248px
+  }
+}
+
+@media (min-width: 66.5rem) {
+  .wy-nav-content-wrap {
+      margin-left:calc((100% - 1064px) / 2 + 264px)
+  }
+}
+
+
+/* Colors */
+body.wy-body-for-nav,
+.wy-nav-content {
+  background: var(--color-bg-body);
+}
+
+.wy-nav-side {
+  border-right: 1px solid var(--color-border);
+}
+
+.wy-side-nav-search, .wy-nav-top {
+  background: var(--color-bg-side-nav);
+  border-bottom: 1px solid var(--color-border);
+}
+
+.wy-nav-content-wrap {
+  background: inherit;
+}
+
+.wy-side-nav-search > a, .wy-nav-top a, .wy-nav-top i {
+  color: var(--color-text-title);
+}
+
+.wy-side-nav-search > a:hover, .wy-nav-top a:hover {
+  background: transparent;
+}
+
+.wy-side-nav-search > div.version {
+  color: var(--color-text-alt)
+}
+
+.wy-side-nav-search > div[role="search"] {
+  border-top: 1px solid var(--color-border);
+}
+
+.wy-menu-vertical li.toctree-l2.current>a, .wy-menu-vertical li.toctree-l2.current li.toctree-l3>a,
+.wy-menu-vertical li.toctree-l3.current>a, .wy-menu-vertical li.toctree-l3.current li.toctree-l4>a {
+  background: var(--color-bg-side-nav);
+}
+
+.rst-content .highlighted {
+  background: #eedd85;
+  box-shadow: 0 0 0 2px #eedd85;
+  font-weight: 600;
+}
+
+.wy-side-nav-search input[type=text],
+html.writer-html5 .rst-content table.docutils th {
+  color: var(--color-text-body);
+}
+
+.rst-content table.docutils:not(.field-list) tr:nth-child(2n-1) td,
+.wy-table-backed,
+.wy-table-odd td,
+.wy-table-striped tr:nth-child(2n-1) td {
+  background-color: var(--color-bg-body-alt);
+}
+
+.rst-content table.docutils,
+.wy-table-bordered-all,
+html.writer-html5 .rst-content table.docutils th,
+.rst-content table.docutils td,
+.wy-table-bordered-all td,
+hr {
+  border-color: var(--color-border) !important;
+}
+
+::selection {
+  background: var(--color-text-selection);
+}
+
+/* Ridiculous rules are taken from sphinx_rtd */
+.rst-content .admonition-title,
+.wy-alert-title {
+  color: var(--color-text-body-light);
+}
+
+.rst-content .hint,
+.rst-content .important,
+.rst-content .tip,
+.rst-content .wy-alert-success,
+.wy-alert.wy-alert-success {
+  background: var(--color-success-body);
+}
+
+.rst-content .hint .admonition-title,
+.rst-content .hint .wy-alert-title,
+.rst-content .important .admonition-title,
+.rst-content .important .wy-alert-title,
+.rst-content .tip .admonition-title,
+.rst-content .tip .wy-alert-title,
+.rst-content .wy-alert-success .admonition-title,
+.rst-content .wy-alert-success .wy-alert-title,
+.wy-alert.wy-alert-success .rst-content .admonition-title,
+.wy-alert.wy-alert-success .wy-alert-title {
+  background-color: var(--color-success-title);
+}
+
+.rst-content .admonition-todo,
+.rst-content .attention,
+.rst-content .caution,
+.rst-content .warning,
+.rst-content .wy-alert-warning,
+.wy-alert.wy-alert-warning {
+  background: var(--color-warning-body);
+}
+
+.rst-content .admonition-todo .admonition-title,
+.rst-content .admonition-todo .wy-alert-title,
+.rst-content .attention .admonition-title,
+.rst-content .attention .wy-alert-title,
+.rst-content .caution .admonition-title,
+.rst-content .caution .wy-alert-title,
+.rst-content .warning .admonition-title,
+.rst-content .warning .wy-alert-title,
+.rst-content .wy-alert-warning .admonition-title,
+.rst-content .wy-alert-warning .wy-alert-title,
+.rst-content .wy-alert.wy-alert-warning .admonition-title,
+.wy-alert.wy-alert-warning .rst-content .admonition-title,
+.wy-alert.wy-alert-warning .wy-alert-title {
+  background: var(--color-warning-title);
+}
+
+.rst-content .danger,
+.rst-content .error,
+.rst-content .wy-alert-danger,
+.wy-alert.wy-alert-danger {
+  background: var(--color-danger-body);
+}
+
+.rst-content .danger .admonition-title,
+.rst-content .danger .wy-alert-title,
+.rst-content .error .admonition-title,
+.rst-content .error .wy-alert-title,
+.rst-content .wy-alert-danger .admonition-title,
+.rst-content .wy-alert-danger .wy-alert-title,
+.wy-alert.wy-alert-danger .rst-content .admonition-title,
+.wy-alert.wy-alert-danger .wy-alert-title {
+  background: var(--color-danger-title);
+}
+
+.rst-content .note,
+.rst-content .seealso,
+.rst-content .wy-alert-info,
+.wy-alert.wy-alert-info {
+  background: var(--color-info-body);
+}
+
+.rst-content .note .admonition-title,
+.rst-content .note .wy-alert-title,
+.rst-content .seealso .admonition-title,
+.rst-content .seealso .wy-alert-title,
+.rst-content .wy-alert-info .admonition-title,
+.rst-content .wy-alert-info .wy-alert-title,
+.wy-alert.wy-alert-info .rst-content .admonition-title,
+.wy-alert.wy-alert-info .wy-alert-title {
+  background: var(--color-info-title);
+}
+
+
+
+/* Links */
+a, a:visited,
+.wy-menu-vertical a,
+a.icon.icon-home,
+.wy-menu-vertical li.toctree-l1.current > a.current {
+  color: var(--color-text-anchor);
+  text-decoration: none;
+}
+
+a:hover, .wy-breadcrumbs-aside a {
+  color: var(--color-text-anchor); /* reset */
+}
+
+.rst-versions a, .rst-versions .rst-current-version {
+  color: #var(--color-text-anchor);
+}
+
+.wy-nav-content a.reference, .wy-nav-content a:not([class]) {
+  background-image: linear-gradient(var(--color-border) 0%, var(--color-border) 100%);
+  background-repeat: repeat-x;
+  background-position: 0 100%;
+  background-size: 1px 1px;
+}
+
+.wy-nav-content a.reference:hover, .wy-nav-content a:not([class]):hover {
+  background-image: linear-gradient(rgba(114,83,237,0.45) 0%, rgba(114,83,237,0.45) 100%);
+  background-size: 1px 1px;
+}
+
+.wy-menu-vertical a:hover,
+.wy-menu-vertical li.current a:hover,
+.wy-menu-vertical a:active {
+  background: var(--color-bg-side-nav-hover) !important;
+  color: var(--color-text-body);
+}
+
+.wy-menu-vertical li.toctree-l1.current>a,
+.wy-menu-vertical li.current>a,
+.wy-menu-vertical li.on a {
+  background-color: var(--color-bg-side-nav-hover);
+  border: none;
+  font-weight: normal;
+}
+
+.wy-menu-vertical li.current {
+  background-color: inherit;
+}
+
+.wy-menu-vertical li.current a {
+  border-right: none;
+}
+
+.wy-menu-vertical li.toctree-l2 a,
+.wy-menu-vertical li.toctree-l3 a,
+.wy-menu-vertical li.toctree-l4 a,
+.wy-menu-vertical li.toctree-l5 a,
+.wy-menu-vertical li.toctree-l6 a,
+.wy-menu-vertical li.toctree-l7 a,
+.wy-menu-vertical li.toctree-l8 a,
+.wy-menu-vertical li.toctree-l9 a,
+.wy-menu-vertical li.toctree-l10 a {
+  color: var(--color-text-body);
+}
+
+a.image-reference, a.image-reference:hover {
+  background: none !important;
+}
+
+a.image-reference img {
+  cursor: zoom-in;
+}
+
+
+/* Code blocks */
+.rst-content code, .rst-content tt, code {
+  padding: 0.25em;
+  font-weight: 400;
+  background-color: var(--color-bg-code-block);
+  border: 1px solid var(--color-border);
+  border-radius: 4px;
+}
+
+.rst-content div[class^=highlight], .rst-content pre.literal-block {
+  padding: 0.7rem;
+  margin-top: 0;
+  margin-bottom: 0.75rem;
+  overflow-x: auto;
+  background-color: var(--color-bg-side-nav);
+  border-color: var(--color-border);
+  border-radius: 4px;
+  box-shadow: none;
+}
+
+.rst-content .admonition-title,
+.rst-content div.admonition,
+.wy-alert-title {
+  padding: 10px 12px;
+  border-top-left-radius: 4px;
+  border-top-right-radius: 4px;
+}
+
+.highlight .go {
+  color: inherit;
+}
+
+.highlight .nt {
+  color: var(--color-text-code-nt);
+}
+
+.rst-content code.literal,
+.rst-content tt.literal,
+html.writer-html5 .rst-content dl.footnote code {
+  border-color: var(--color-border);
+  background-color: var(--color-border);
+  color: var(--color-text-code-inline)
+}
+
+
+/* Search */
+.wy-side-nav-search input[type=text] {
+  border: none;
+  border-radius: 0;
+  background-color: transparent;
+  font-family: inherit;
+  font-size: .85rem;
+  box-shadow: none;
+  padding: .7rem 1rem .7rem 2.8rem;
+  margin: 0;
+}
+
+#rtd-search-form {
+  position: relative;
+}
+
+#rtd-search-form:before {
+  font: normal normal normal 14px/1 FontAwesome;
+  font-size: inherit;
+  text-rendering: auto;
+  -webkit-font-smoothing: antialiased;
+  -moz-osx-font-smoothing: grayscale;
+  content: "\f002";
+  color: var(--color-text-alt);
+  position: absolute;
+  left: 1.5rem;
+  top: .7rem;
+}
+
+/* Side nav */
+.wy-side-nav-search {
+  padding: 1rem 0 0 0;
+}
+
+.wy-menu-vertical li a button.toctree-expand {
+  float: right;
+  margin-right: -1.5em;
+  padding: 0 .5em;
+}
+
+.wy-menu-vertical a,
+.wy-menu-vertical li.current>a,
+.wy-menu-vertical li.current li>a {
+  padding-right: 1.5em !important;
+}
+
+.wy-menu-vertical li.current li>a.current {
+  font-weight: 600;
+}
+
+/* Misc spacing */
+.rst-content .admonition-title, .wy-alert-title {
+  padding: 10px 12px;
+}
+
+/* Buttons */
+.btn {
+  display: inline-block;
+  box-sizing: border-box;
+  padding: 0.3em 1em;
+  margin: 0;
+  font-family: inherit;
+  font-size: inherit;
+  font-weight: 500;
+  line-height: 1.5;
+  color: #var(--color-text-anchor);
+  text-decoration: none;
+  vertical-align: baseline;
+  background-color: #f7f7f7;
+  border-width: 0;
+  border-radius: 4px;
+  box-shadow: 0 1px 2px rgba(0,0,0,0.12),0 3px 10px rgba(0,0,0,0.08);
+  appearance: none;
+}
+
+.btn:active {
+  padding: 0.3em 1em;
+}
+
+.rst-content .btn:focus {
+  outline: 1px solid #ccc;
+}
+
+.rst-content .btn-neutral, .rst-content .btn span.fa {
+  color: var(--color-text-body) !important;
+}
+
+.btn-neutral {
+  background-color: var(--color-btn-neutral-bg) !important;
+  color: var(--color-btn-neutral-text) !important;
+  border: 1px solid var(--color-btn-neutral-bg);
+}
+
+.btn:hover, .btn-neutral:hover {
+  background-color: var(--color-btn-neutral-bg-hover) !important;
+}
+
+
+/* Icon overrides */
+.wy-side-nav-search a.icon-home:before {
+  display: none;
+}
+
+.fa-minus-square-o:before,.wy-menu-vertical li.current>a button.toctree-expand:before,.wy-menu-vertical li.on a button.toctree-expand:before {
+  content: "\f106"; /* fa-angle-up */
+}
+
+.fa-plus-square-o:before, .wy-menu-vertical li button.toctree-expand:before {
+  content: "\f107"; /* fa-angle-down */
+}
+
+
+/* Misc */
+.wy-nav-top {
+  line-height: 36px;
+}
+
+.wy-nav-top > i {
+  font-size: 24px;
+  padding: 8px 0 0 2px;
+  color:#var(--color-text-anchor);
+}
+
+.rst-content table.docutils td,
+.rst-content table.docutils th,
+.rst-content table.field-list td,
+.rst-content table.field-list th,
+.wy-table td,
+.wy-table th {
+  padding: 8px 14px;
+}
+
+.dark-mode-toggle {
+  position: absolute;
+  top: 14px;
+  right: 12px;
+  height: 20px;
+  width: 24px;
+  z-index: 10;
+  border: none;
+  background-color: transparent;
+  color: inherit;
+  opacity: 0.7;
+}
+
+.wy-nav-content-wrap {
+  z-index: 20;
+}

docs/_static/custom.css

@@ -1,14 +0,0 @@
-/* override table width restrictions */
-@media screen and (min-width: 767px) {
-
-  .wy-table-responsive table td {
-    /* !important prevents the common CSS stylesheets from
-       overriding this as on RTD they are loaded after this stylesheet */
-    white-space: normal !important;
-  }
-
-  .wy-table-responsive {
-    overflow: visible !important;
-  }
-
-}

docs/_static/js/darkmode.js

@@ -0,0 +1,47 @@
+let toggleButton
+let icon
+
+function load() {
+	'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)
+
+	// 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)
+		})
+	}
+
+	// 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)
+
+	// Toggles the "dark-mode" class on click and sets localStorage state
+	toggleButton.addEventListener('click', () => {
+		darkModeState = !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.addEventListener('DOMContentLoaded', load)

docs/_templates/layout.html

@@ -0,0 +1,13 @@
+{% extends "!layout.html" %}
+{% block extrahead %}
+    <script>
+        // MediaQueryList object
+        const prefersDarkQuery = window.matchMedia("(prefers-color-scheme: dark)");
+        const lsDark = localStorage.getItem("dark-mode");
+        let darkModeState = lsDark !== null ? lsDark == "true" : prefersDarkQuery.matches;
+
+        document.documentElement.classList.toggle("dark-mode", darkModeState);
+        document.documentElement.classList.toggle("light-mode", !darkModeState);
+    </script>
+    {{ super() }}
+{% endblock %}

docs/administration.rst

@@ -20,6 +20,14 @@ Options available to any installation of paperless:
     metadata to a specific folder. You may import your documents into a
     fresh instance of paperless again or store your documents in another
     DMS with this export.
+*   The document exporter is also able to update an already existing export.
+    Therefore, incremental backups with ``rsync`` are entirely possible.
+
+.. caution::
+
+    You cannot import the export generated with one version of paperless in a
+    different version of paperless. The export contains an exact image of the
+    database, and migrations may change the database layout.
 
 Options available to docker installations:
 
@@ -27,13 +35,15 @@ Options available to docker installations:
     ``/var/lib/docker/volumes`` on the host and you need to be root in order
     to access them.
 
-    Paperless uses 3 volumes:
+    Paperless uses 4 volumes:
 
     *   ``paperless_media``: This is where your documents are stored.
     *   ``paperless_data``: This is where auxillary data is stored. This
         folder also contains the SQLite database, if you use it.
     *   ``paperless_pgdata``: Exists only if you use PostgreSQL and contains
         the database.
+    *   ``paperless_dbdata``: Exists only if you use MariaDB and contains
+        the database.
 
 Options available to bare-metal and non-docker installations:
 
@@ -41,24 +51,24 @@ Options available to bare-metal and non-docker installations:
     crashes at some point or your disk fails, you can simply copy the folder back
     into place and it works.
 
-    When using PostgreSQL, you'll also have to backup the database.
+    When using PostgreSQL or MariaDB, you'll also have to backup the database.
 
 .. _migrating-restoring:
 
 Restoring
 =========
 
-
-
-
 .. _administration-updating:
 
-Updating paperless
+Updating Paperless
 ##################
 
-If a new release of paperless-ng is available, upgrading depends on how you
-installed paperless-ng in the first place. The releases are available at
-`release page <https://github.com/jonaswinkler/paperless-ng/releases>`_.
+Docker Route
+============
+
+If a new release of paperless-ngx is available, upgrading depends on how you
+installed paperless-ngx in the first place. The releases are available at the
+`release page <https://github.com/paperless-ngx/paperless-ngx/releases>`_.
 
 First of all, ensure that paperless is stopped.
 
@@ -69,106 +79,147 @@ First of all, ensure that paperless is stopped.
 
 After that, :ref:`make a backup <administration-backup>`.
 
-A.  If you used the dockerfiles archive, simply download the files of the new release,
-    adjust the settings in the files (i.e., the path to your consumption directory),
-    and replace your existing docker-compose files. Then start paperless as usual,
-    which will pull the new image, and update your database, if necessary:
+A.  If you pull the image from the docker hub, all you need to do is:
 
     .. code:: shell-session
 
-        $ cd /path/to/paperless
+        $ docker-compose pull
         $ docker-compose up
 
-    If you see everything working, you can start paperless-ng with "-d" to have it
-    run in the background.
+    The docker-compose files refer to the ``latest`` version, which is always the latest
+    stable release.
 
-    .. hint::
-
-        The released docker-compose files specify exact versions to be pulled from the hub.
-        This is to ensure that if the docker-compose files should change at some point
-        (i.e., services updates/configured differently), you wont run into trouble due to
-        docker pulling the ``latest`` image and running it in an older environment.
-        
-B.  If you built the image yourself, grab the new archive and replace your current
-    paperless folder with the new contents.
-
-    After that, make the necessary adjustments to the docker-compose.yml (i.e.,
-    adjust your consumption directory).
-
-    Build and start the new image with:
+B.  If you built the image yourself, do the following:
 
     .. code:: shell-session
 
-        $ cd /path/to/paperless
+        $ git pull
         $ docker-compose build
         $ docker-compose up
 
-    If you see everything working, you can start paperless-ng with "-d" to have it
-    run in the background.
+Running ``docker-compose up`` will also apply any new database migrations.
+If you see everything working, press CTRL+C once to gracefully stop paperless.
+Then you can start paperless-ngx with ``-d`` to have it run in the background.
 
-.. hint::
+    .. note::
 
-    You can usually keep your ``docker-compose.env`` file, since this file will
-    never include mandatory configuration options. However, it is worth checking
-    out the new version of this file, since it might have new recommendations
-    on what to configure.
+        In version 0.9.14, the update process was changed. In 0.9.13 and earlier, the
+        docker-compose files specified exact versions and pull won't automatically
+        update to newer versions. In order to enable updates as described above, either
+        get the new ``docker-compose.yml`` file from `here <https://github.com/paperless-ngx/paperless-ngx/tree/master/docker/compose>`_
+        or edit the ``docker-compose.yml`` file, find the line that says
 
+            .. code::
 
-Updating paperless without docker
-=================================
+                image: ghcr.io/paperless-ngx/paperless-ngx:0.9.x
+
+        and replace the version with ``latest``:
+
+            .. code::
+
+                image: ghcr.io/paperless-ngx/paperless-ngx:latest
+
+    .. note::
+        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 pin your install to a release series, edit
+        the ``docker-compose.yml`` find the line that says
+
+            .. code::
+
+                image: ghcr.io/paperless-ngx/paperless-ngx:latest
+
+        and replace the version with the series you want to track, for example:
+
+            .. code::
+
+                image: ghcr.io/paperless-ngx/paperless-ngx:1.7
+
+Bare Metal Route
+================
 
 After grabbing the new release and unpacking the contents, do the following:
 
 1.  Update dependencies. New paperless version may require additional
-    dependencies. The dependencies required are listed in the section about 
+    dependencies. The dependencies required are listed in the section about
     :ref:`bare metal installations <setup-bare_metal>`.
 
-2.  Update python requirements. If you use Pipenv, this is done with the following steps.
+2.  Update python requirements. Keep in mind to activate your virtual environment
+    before that, if you use one.
 
     .. code:: shell-session
 
-        $ pip install --upgrade pipenv
-        $ cd /path/to/paperless
-        $ pipenv clean
-        $ pipenv install
+        $ pip install -r requirements.txt
 
-    This creates a new virtual environment (or uses your existing environment)
-    and installs all dependencies into it.
-
-3.  Collect static files.
+3.  Migrate the database.
 
     .. code:: shell-session
 
         $ cd src
-        $ pipenv run python3 manage.py collectstatic --clear
-    
-4.  Migrate the database.
+        $ python3 manage.py migrate
 
-    .. code:: shell-session
+    This might not actually do anything. Not every new paperless version comes with new
+    database migrations.
 
-        $ cd src
-        $ pipenv run python3 manage.py migrate
+Downgrading Paperless
+#####################
+
+Downgrades are possible. However, some updates also contain database migrations (these change the layout of the database and may move data).
+In order to move back from a version that applied database migrations, you'll have to revert the database migration *before* downgrading,
+and then downgrade paperless.
+
+This table lists the compatible versions for each database migration number.
+
++------------------+-----------------+
+| Migration number | Version range   |
++------------------+-----------------+
+| 1011             | 1.0.0           |
++------------------+-----------------+
+| 1012             | 1.1.0 - 1.2.1   |
++------------------+-----------------+
+| 1014             | 1.3.0 - 1.3.1   |
++------------------+-----------------+
+| 1016             | 1.3.2 - current |
++------------------+-----------------+
+
+Execute the following management command to migrate your database:
+
+.. code:: shell-session
+
+    $ python3 manage.py migrate documents <migration number>
+
+.. note::
+
+    Some migrations cannot be undone. The command will issue errors if that happens.
+
+.. _utilities-management-commands:
 
-        
 Management utilities
 ####################
 
 Paperless comes with some management commands that perform various maintenance
-tasks on your paperless instance. You can invoke these commands either by
+tasks on your paperless instance. You can invoke these commands in the following way:
+
+With docker-compose, while paperless is running:
 
 .. code:: shell-session
 
     $ cd /path/to/paperless
-    $ docker-compose run --rm webserver <command> <arguments>
+    $ docker-compose exec webserver <command> <arguments>
 
-or
+With docker, while paperless is running:
+
+.. code:: shell-session
+
+    $ docker exec -it <container-name> <command> <arguments>
+
+Bare metal:
 
 .. code:: shell-session
 
     $ cd /path/to/paperless/src
-    $ pipenv run python manage.py <command> <arguments>
-
-depending on whether you use docker or not.
+    $ python3 manage.py <command> <arguments>
 
 All commands have built-in help, which can be accessed by executing them with
 the argument ``--help``.
@@ -181,9 +232,16 @@ Document exporter
 The document exporter exports all your data from paperless into a folder for
 backup or migration to another DMS.
 
+If you use the document exporter within a cronjob to backup your data you might use the ``-T`` flag behind exec to suppress "The input device is not a TTY" errors. For example: ``docker-compose exec -T webserver document_exporter ../export``
+
 .. code::
 
-    document_exporter target
+    document_exporter target [-c] [-f] [-d]
+
+    optional arguments:
+    -c, --compare-checksums
+    -f, --use-filename-format
+    -d, --delete
 
 ``target`` is a folder to which the data gets written. This includes documents,
 thumbnails and a ``manifest.json`` file. The manifest contains all metadata from
@@ -193,6 +251,24 @@ When you use the provided docker compose script, specify ``../export`` as the
 target. This path inside the container is automatically mounted on your host on
 the folder ``export``.
 
+If the target directory already exists and contains files, paperless will assume
+that the contents of the export directory are a previous export and will attempt
+to update the previous export. Paperless will only export changed and added files.
+Paperless determines whether a file has changed by inspecting the file attributes
+"date/time modified" and "size". If that does not work out for you, specify
+``--compare-checksums`` and paperless will attempt to compare file checksums instead.
+This is slower.
+
+Paperless will not remove any existing files in the export directory. If you want
+paperless to also remove files that do not belong to the current export such as files
+from deleted documents, specify ``--delete``. Be careful when pointing paperless to
+a directory that already contains other files.
+
+The filenames generated by this command follow the format
+``[date created] [correspondent] [title].[extension]``.
+If you want paperless to use ``PAPERLESS_FILENAME_FORMAT`` for exported filenames
+instead, specify ``--use-filename-format``.
+
 
 .. _utilities-importer:
 
@@ -213,6 +289,10 @@ When you use the provided docker compose script, put the export inside the
 ``export`` folder in your paperless source directory. Specify ``../export``
 as the ``source``.
 
+.. note::
+
+    Importing from a previous version of Paperless may work, but for best results
+    it is suggested to match the versions.
 
 .. _utilities-retagger:
 
@@ -232,6 +312,7 @@ there are tools for it.
     -c, --correspondent
     -T, --tags
     -t, --document_type
+    -s, --storage_path
     -i, --inbox-only
     --use-first
     -f, --overwrite
@@ -240,7 +321,7 @@ Run this after changing or adding matching rules. It'll loop over all
 of the documents in your database and attempt to match documents
 according to the new rules.
 
-Specify any combination of ``-c``, ``-T`` and ``-t`` to have the
+Specify any combination of ``-c``, ``-T``, ``-t`` and ``-s`` to have the
 retagger perform matching of the specified metadata type. If you don't
 specify any of these options, the document retagger won't do anything.
 
@@ -312,8 +393,8 @@ the naming scheme.
 
 .. warning::
 
-    Since this command moves you documents around alot, 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::
@@ -322,6 +403,36 @@ the naming scheme.
 
 The command takes no arguments and processes all your documents at once.
 
+Learn how to use :ref:`Management Utilities<utilities-management-commands>`.
+
+
+.. _utilities-sanity-checker:
+
+Sanity checker
+==============
+
+Paperless has a built-in sanity checker that inspects your document collection for issues.
+
+The issues detected by the sanity checker are as follows:
+
+* Missing original files.
+* Missing archive files.
+* Inaccessible original files due to improper permissions.
+* Inaccessible archive files due to improper permissions.
+* Corrupted original documents by comparing their checksum against what is stored in the database.
+* Corrupted archive documents by comparing their checksum against what is stored in the database.
+* Missing thumbnails.
+* Inaccessible thumbnails due to improper permissions.
+* Documents without any content (warning).
+* Orphaned files in the media directory (warning). These are files that are not referenced by any document im paperless.
+
+
+.. code::
+
+    document_sanity_checker
+
+The command takes no arguments. Depending on the size of your document archive, this may take some time.
+
 
 Fetching e-mail
 ===============
@@ -381,13 +492,13 @@ Documents can be stored in Paperless using GnuPG encryption.
 
 .. danger::
 
-    Encryption is deprecated since paperless-ng 0.9 and doesn't really provide any
+    Encryption is deprecated since paperless-ngx 0.9 and doesn't really provide any
     additional security, since you have to store the passphrase in a configuration
     file on the same system as the encrypted documents for paperless to work.
     Furthermore, the entire text content of the documents is stored plain in the
     database, even if your documents are encrypted. Filenames are not encrypted as
     well.
-    
+
     Also, the web server provides transparent access to your encrypted documents.
 
     Consider running paperless on an encrypted filesystem instead, which will then
@@ -410,6 +521,3 @@ Basic usage to disable encryption of your document store:
 .. code::
 
     decrypt_documents [--passphrase SECR3TP4SSPHRA$E]
-
-
-.. _Pipenv: https://pipenv.pypa.io/en/latest/

docs/advanced_usage.rst

@@ -7,26 +7,25 @@ easier.
 
 .. _advanced-matching:
 
-Matching tags, correspondents and document types
-################################################
+Matching tags, correspondents, document types, and storage paths
+################################################################
 
-After the consumer has tried to figure out what it could from the file name,
-it starts looking at the content of the document itself.  It 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 that document.  In other words,
-if you defined 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 of the document somewhere.
+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
+of the document somewhere.
 
-The matching logic is quite powerful, and supports searching the text of your
+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:
 
@@ -35,22 +34,22 @@ The following algorithms are available:
   either of these terms.
 * **All:** Requires that every word provided appears in the PDF, albeit not in the
   order provided.
-* **Literal:** Matches only if the match appears exactly as provided in the PDF.
+* **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.
 
-When using the "any" or "all" matching algorithms, you can search for terms
+When using the *any* or *all* matching algorithms, you can search for terms
 that consist of multiple words by enclosing them in double quotes. For example,
-defining a match text of ``"Bank of America" BofA`` using the "any" algorithm,
+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:
@@ -58,10 +57,10 @@ automatically tagged with the appropriate data.
 Automatic matching
 ==================
 
-Paperless-ng 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 assigned these on existing documents. It
-uses a neural network under the hood.
+Paperless-ngx comes with a new matching algorithm called *Auto*. This matching
+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
@@ -77,24 +76,25 @@ feature:
   changes. Paperless periodically (default: once each hour) checks for changes
   and does this automatically for you.
 * The Auto matching algorithm only takes documents into account which are NOT
-  placed in your inbox (i.e., have inbox tags assigned to them). This ensures
+  placed in your inbox (i.e. have any inbox tags assigned to them). This ensures
   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
 ####################################
@@ -105,7 +105,7 @@ you execute scripts of your own choosing just before or after a document is
 consumed using a couple simple hooks.
 
 Just write a script, put it somewhere that Paperless can read & execute, and
-then put the path to that script in ``paperless.conf`` with the variable name
+then put the path to that script in ``paperless.conf`` or ``docker-compose.env`` with the variable name
 of either ``PAPERLESS_PRE_CONSUME_SCRIPT`` or
 ``PAPERLESS_POST_CONSUME_SCRIPT``.
 
@@ -121,10 +121,10 @@ Pre-consumption script
 ======================
 
 Executed after the consumer sees a new document in the consumption folder, but
-before any processing of the document is performed. This script receives exactly
-one argument:
+before any processing of the document is performed. This script can access the
+following relevant environment variables set:
 
-* Document file name
+* ``DOCUMENT_SOURCE_PATH``
 
 A simple but common example for this would be creating a simple script like
 this:
@@ -134,7 +134,7 @@ this:
 .. code:: bash
 
     #!/usr/bin/env bash
-    pdf2pdfocr.py -i ${1}
+    pdf2pdfocr.py -i ${DOCUMENT_SOURCE_PATH}
 
 ``/etc/paperless.conf``
 
@@ -157,23 +157,57 @@ Post-consumption script
 =======================
 
 Executed after the consumer has successfully processed a document and has moved it
-into paperless. It receives the following arguments:
+into paperless. It receives the following environment variables:
 
-* Document id
-* Generated file name
-* Source path
-* Thumbnail path
-* Download URL
-* Thumbnail URL
-* Correspondent
-* Tags
+* ``DOCUMENT_ID``
+* ``DOCUMENT_FILE_NAME``
+* ``DOCUMENT_CREATED``
+* ``DOCUMENT_MODIFIED``
+* ``DOCUMENT_ADDED``
+* ``DOCUMENT_SOURCE_PATH``
+* ``DOCUMENT_ARCHIVE_PATH``
+* ``DOCUMENT_THUMBNAIL_PATH``
+* ``DOCUMENT_DOWNLOAD_URL``
+* ``DOCUMENT_THUMBNAIL_URL``
+* ``DOCUMENT_CORRESPONDENT``
+* ``DOCUMENT_TAGS``
+* ``DOCUMENT_ORIGINAL_FILENAME``
 
-The script can be in any language you like, but for a simple shell script
-example, you can take a look at ``post-consumption-example.sh`` in the
-``scripts`` directory in this project.
+The script can be in any language, but for a simple shell script
+example, you can take a look at `post-consumption-example.sh`_ in this project.
 
 The post consumption script cannot cancel the consumption process.
 
+Docker
+------
+Assumed you have ``/home/foo/paperless-ngx/scripts/post-consumption-example.sh``.
+
+You can pass that script into the consumer container via a host mount in your ``docker-compose.yml``.
+
+.. code:: bash
+
+  ...
+  consumer:
+    ...
+    volumes:
+      ...
+      - /home/paperless-ngx/scripts:/path/in/container/scripts/
+  ...
+
+Example (docker-compose.yml): ``- /home/foo/paperless-ngx/scripts:/usr/src/paperless/scripts``
+
+which in turn requires the variable ``PAPERLESS_POST_CONSUME_SCRIPT`` in ``docker-compose.env``  to point to ``/path/in/container/scripts/post-consumption-example.sh``.
+
+Example (docker-compose.env): ``PAPERLESS_POST_CONSUME_SCRIPT=/usr/src/paperless/scripts/post-consumption-example.sh``
+
+Troubleshooting:
+
+- Monitor the docker-compose log ``cd ~/paperless-ngx; docker-compose logs -f``
+- Check your script's permission e.g. in case of permission error ``sudo chmod 755 post-consumption-example.sh``
+- Pipe your scripts's output to a log file e.g. ``echo "${DOCUMENT_ID}" | tee --append /usr/src/paperless/scripts/post-consumption-example.log``
+
+.. _post-consumption-example.sh: https://github.com/paperless-ngx/paperless-ngx/blob/main/scripts/post-consumption-example.sh
+
 .. _advanced-file_name_handling:
 
 File name handling
@@ -215,20 +249,21 @@ will create a directory structure as follows:
     last filename a document was stored as. If you do rename a file, paperless will
     report your files as missing and won't be able to find them.
 
-Paperless provides the following placeholders withing filenames:
+Paperless provides the following placeholders within filenames:
 
+* ``{asn}``: The archive serial number of the document, or "none".
 * ``{correspondent}``: The name of the correspondent, or "none".
 * ``{document_type}``: The name of the document type, or "none".
 * ``{tag_list}``: A comma separated list of all tags assigned to the document.
 * ``{title}``: The title of the document.
-* ``{created}``: The full date and time the document was created.
+* ``{created}``: The full date (ISO format) the document was created.
 * ``{created_year}``: Year created only.
-* ``{created_month}``: Month created only (number 1-12).
-* ``{created_day}``: Day created only (number 1-31).
-* ``{added}``: The full date and time the document was added to paperless.
+* ``{created_month}``: Month created only (number 01-12).
+* ``{created_day}``: Day created only (number 01-31).
+* ``{added}``: The full date (ISO format) the document was added to paperless.
 * ``{added_year}``: Year added only.
-* ``{added_month}``: Month added only (number 1-12).
-* ``{added_day}``: Day added only (number 1-31).
+* ``{added_month}``: Month added only (number 01-12).
+* ``{added_day}``: Day added only (number 01-31).
 
 
 Paperless will try to conserve the information from your database as much as possible.
@@ -239,6 +274,17 @@ 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,
@@ -261,3 +307,59 @@ 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.

docs/api.rst

@@ -31,7 +31,8 @@ The objects served by the document endpoint contain the following fields:
 *   ``tags``: List of IDs of tags assigned to this document, or empty list.
 *   ``document_type``: Document type of this document, or null.
 *   ``correspondent``:  Correspondent of this document or null.
-*   ``created``: The date at which this document was created.
+*   ``created``: The date time at which this document was created.
+*   ``created_date``: The date (YYYY-MM-DD) at which this document was created. Optional. If also passed with created, this is ignored.
 *   ``modified``: The date at which this document was last edited in paperless. Read-only.
 *   ``added``: The date at which this document was added to paperless. Read-only.
 *   ``archive_serial_number``: The identifier of this document in a physical document archive.
@@ -60,7 +61,7 @@ The endpoints correctly serve the response header fields ``Content-Disposition``
 and ``Content-Type`` to indicate the filename for download and the type of content of
 the document.
 
-In order to download or preview the original document when an archied document is available,
+In order to download or preview the original document when an archived document is available,
 supply the query parameter ``original=true``.
 
 .. hint::
@@ -147,93 +148,57 @@ The REST api provides three different forms of authentication.
 Searching for documents
 #######################
 
-Paperless-ng offers API endpoints for full text search. These are as follows:
+Full text searching is available on the ``/api/documents/`` endpoint. Two specific
+query parameters cause the API to return full text search results:
 
-``/api/search/``
-================
+*   ``/api/documents/?query=your%20search%20query``: Search for a document using a full text query.
+    For details on the syntax, see :ref:`basic-usage_searching`.
 
-Get search results based on a query.
+*   ``/api/documents/?more_like=1234``: Search for documents similar to the document with id 1234.
 
-Query parameters:
+Pagination works exactly the same as it does for normal requests on this endpoint.
 
-*   ``query``: The query string. See
-    `here <https://whoosh.readthedocs.io/en/latest/querylang.html>`_
-    for details on the syntax.
-*   ``page``: Specify the page you want to retrieve. Each page
-    contains 10 search results and the first page is ``page=1``, which
-    is the default if this is omitted.
+Certain limitations apply to full text queries:
 
-Result list object returned by the endpoint:
+*   Results are always sorted by search score. The results matching the query best will show up first.
 
-.. code:: json
+*   Only a small subset of filtering parameters are supported.
+
+Furthermore, each returned document has an additional ``__search_hit__`` attribute with various information
+about the search results:
+
+.. code::
 
     {
-        "count": 1,
-        "page": 1,
-        "page_count": 1,
-        "corrected_query": "",
+        "count": 31,
+        "next": "http://localhost:8000/api/documents/?page=2&query=test",
+        "previous": null,
         "results": [
 
+            ...
+
+            {
+                "id": 123,
+                "title": "title",
+                "content": "content",
+
+                ...
+
+                "__search_hit__": {
+                    "score": 0.343,
+                    "highlights": "text <span class=\"match\">Test</span> text",
+                    "rank": 23
+                }
+            },
+
+            ...
+
         ]
     }
 
-*   ``count``: The approximate total number of results.
-*   ``page``: The page returned to you. This might be different from
-    the page you requested, if you requested a page that is behind
-    the last page. In that case, the last page is returned.
-*   ``page_count``: The total number of pages.
-*   ``corrected_query``: Corrected version of the query string. Can be null.
-    If not null, can be used verbatim to start a new query.
-*   ``results``: A list of result objects on the current page.
-
-Result object:
-
-.. code:: json
-
-    {
-        "id": 1,
-        "highlights": [
-
-        ],
-        "score": 6.34234,
-        "rank": 23,
-        "document": {
-
-        }
-    }
-
-*   ``id``: the primary key of the found document
-*   ``highlights``: an object containing parsable highlights for the result.
-    See below.
-*   ``score``: The score assigned to the document. A higher score indicates a
-    better match with the query. Search results are sorted descending by score.
-*   ``rank``: the position of the document within the entire search results list.
-*   ``document``: The full json of the document, as returned by
-    ``/api/documents/<id>/``.
-
-Highlights object:
-
-Highlights are provided as a list of fragments. A fragment is a longer section of
-text from the original document.
-Each fragment contains a list of strings, and some of them are marked as a highlight.
-
-.. code:: json
-
-    [
-        [
-            {"text": "This is a sample text with a ", "highlight": false},
-            {"text": "highlighted", "highlight": true},
-            {"text": " word.", "highlight": false}
-        ],
-        [
-            {"text": "Another", "highlight": true},
-            {"text": " fragment with a highlight.", "highlight": false}
-        ]
-    ]
-
-A client may use this example to produce the following output:
-
-... This is a sample text with a **highlighted** word. ... **Another** fragment with a highlight. ...
+*   ``score`` is an indication how well this document matches the query relative to the other search results.
+*   ``highlights`` is an excerpt from the document content and highlights the search terms with ``<span>`` tags as shown above.
+*   ``rank`` is the index of the search results. The first result will have rank 0.
 
 ``/api/search/autocomplete/``
 =============================
@@ -276,11 +241,63 @@ be instructed to consume the document from there.
 The endpoint supports the following optional form fields:
 
 *   ``title``: Specify a title that the consumer should use for the document.
+*   ``created``: Specify a DateTime where the document was created (e.g. "2016-04-19" or "2016-04-19 06:15:00+02:00").
 *   ``correspondent``: Specify the ID of a correspondent that the consumer should use for the document.
 *   ``document_type``: Similar to correspondent.
 *   ``tags``: Similar to correspondent. Specify this multiple times to have multiple tags added
     to the document.
 
+
 The endpoint will immediately return "OK" if the document consumption process
 was started successfully. No additional status information about the consumption
 process itself is available, since that happens in a different process.
+
+
+.. _api-versioning:
+
+API Versioning
+##############
+
+The REST API is versioned since Paperless-ngx 1.3.0.
+
+* Versioning ensures that changes to the API don't break older clients.
+* Clients specify the specific version of the API they wish to use with every request and Paperless will handle the request using the specified API version.
+* Even if the underlying data model changes, older API versions will always serve compatible data.
+* If no version is specified, Paperless will serve version 1 to ensure compatibility with older clients that do not request a specific API version.
+
+API versions are specified by submitting an additional HTTP ``Accept`` header with every request:
+
+.. code::
+
+    Accept: application/json; version=6
+
+If an invalid version is specified, Paperless 1.3.0 will respond with "406 Not Acceptable" and an error message in the body.
+Earlier versions of Paperless will serve API version 1 regardless of whether a version is specified via the ``Accept`` header.
+
+If a client wishes to verify whether it is compatible with any given server, the following procedure should be performed:
+
+1.  Perform an *authenticated* request against any API endpoint. If the server is on version 1.3.0 or newer, the server will
+    add two custom headers to the response:
+
+    .. code::
+
+        X-Api-Version: 2
+        X-Version: 1.3.0
+
+2.  Determine whether the client is compatible with this server based on the presence/absence of these headers and their values if present.
+
+
+API Changelog
+=============
+
+Version 1
+---------
+
+Initial API version.
+
+Version 2
+---------
+
+* Added field ``Tag.color``. This read/write string field contains a hex color such as ``#a6cee3``.
+* Added read-only field ``Tag.text_color``. This field contains the text color to use for a specific tag, which is either black or white depending on the brightness of ``Tag.color``.
+* Removed field ``Tag.colour``.

docs/conf.py

@@ -2,33 +2,39 @@ import sphinx_rtd_theme
 
 
 __version__ = None
+__full_version_str__ = None
+__major_minor_version_str__ = None
 exec(open("../src/paperless/version.py").read())
 
 
 extensions = [
-    'sphinx.ext.autodoc',
-    'sphinx.ext.intersphinx',
-    'sphinx.ext.todo',
-    'sphinx.ext.imgmath',
-    'sphinx.ext.viewcode',
-    'sphinx_rtd_theme',
+    "sphinx.ext.autodoc",
+    "sphinx.ext.intersphinx",
+    "sphinx.ext.todo",
+    "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']
+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'
+# source_encoding = 'utf-8-sig'
 
 # The master toctree document.
-master_doc = 'index'
+master_doc = "index"
 
 # General information about the project.
-project = u'Paperless-ng'
-copyright = u'2015, Daniel Quinn'
+project = "Paperless-ngx"
+copyright = "2015-2022, Daniel Quinn, Jonas Winkler, and the paperless-ngx team"
 
 # The version info for the project you're documenting, acts as replacement for
 # |version| and |release|, also used in various other places throughout the
@@ -41,186 +47,190 @@ copyright = u'2015, Daniel Quinn'
 #
 
 # The short X.Y version.
-version = ".".join([str(_) for _ in __version__[:2]])
+version = __major_minor_version_str__
 # The full version, including alpha/beta/rc tags.
-release = ".".join([str(_) for _ in __version__[:3]])
+release = __full_version_str__
 
 # The language for content autogenerated by Sphinx. Refer to documentation
 # for a list of supported languages.
-#language = None
+# language = None
 
 # There are two options for replacing |today|: either, you set today to some
 # non-false value, then it is used:
-#today = ''
+# today = ''
 # Else, today_fmt is used as the format for a strftime call.
-#today_fmt = '%B %d, %Y'
+# today_fmt = '%B %d, %Y'
 
 # List of patterns, relative to source directory, that match files and
 # directories to ignore when looking for source files.
-exclude_patterns = ['_build']
+exclude_patterns = ["_build"]
 
 # The reST default role (used for this markup: `text`) to use for all
 # documents.
-#default_role = None
+# default_role = None
 
 # If true, '()' will be appended to :func: etc. cross-reference text.
-#add_function_parentheses = True
+# add_function_parentheses = True
 
 # If true, the current module name will be prepended to all description
 # unit titles (such as .. function::).
-#add_module_names = True
+# add_module_names = True
 
 # If true, sectionauthor and moduleauthor directives will be shown in the
 # output. They are ignored by default.
-#show_authors = False
+# show_authors = False
 
 # The name of the Pygments (syntax highlighting) style to use.
-pygments_style = 'sphinx'
+pygments_style = "sphinx"
 
 # A list of ignored prefixes for module index sorting.
-#modindex_common_prefix = []
+# modindex_common_prefix = []
 
 # If true, keep warnings as "system message" paragraphs in the built documents.
-#keep_warnings = False
+# keep_warnings = False
 
 
 # -- Options for HTML output ----------------------------------------------
 
 # The theme to use for HTML and HTML Help pages.  See the documentation for
 # a list of builtin themes.
-html_theme = 'sphinx_rtd_theme'
+html_theme = "sphinx_rtd_theme"
 
 # Theme options are theme-specific and customize the look and feel of a theme
 # further.  For a list of options available for each theme, see the
 # documentation.
-#html_theme_options = {}
+# html_theme_options = {}
 
 # Add any paths that contain custom themes here, relative to this directory.
 html_theme_path = []
 
 # The name for this set of Sphinx documents.  If None, it defaults to
 # "<project> v<release> documentation".
-#html_title = None
+# html_title = None
 
 # A shorter title for the navigation bar.  Default is the same as html_title.
-#html_short_title = None
+# html_short_title = None
 
 # The name of an image file (relative to this directory) to place at the top
 # of the sidebar.
-#html_logo = None
+# html_logo = None
 
 # The name of an image file (within the static path) to use as favicon of the
 # docs.  This file should be a Windows icon file (.ico) being 16x16 or 32x32
 # pixels large.
-#html_favicon = None
+# html_favicon = None
 
 # Add any paths that contain custom static files (such as style sheets) here,
 # relative to this directory. They are copied after the builtin static files,
 # so a file named "default.css" will overwrite the builtin "default.css".
-html_static_path = ['_static']
+html_static_path = ["_static"]
+
+# These paths are either relative to html_static_path
+# or fully qualified paths (eg. https://...)
+html_css_files = [
+    "css/custom.css",
+]
+
+html_js_files = [
+    "js/darkmode.js",
+]
 
 # Add any extra paths that contain custom files (such as robots.txt or
 # .htaccess) here, relative to this directory. These files are copied
 # directly to the root of the documentation.
-#html_extra_path = []
+# html_extra_path = []
 
 # If not '', a 'Last updated on:' timestamp is inserted at every page bottom,
 # using the given strftime format.
-#html_last_updated_fmt = '%b %d, %Y'
+# html_last_updated_fmt = '%b %d, %Y'
 
 # If true, SmartyPants will be used to convert quotes and dashes to
 # typographically correct entities.
-#html_use_smartypants = True
+# html_use_smartypants = True
 
 # Custom sidebar templates, maps document names to template names.
-#html_sidebars = {}
+# html_sidebars = {}
 
 # Additional templates that should be rendered to pages, maps page names to
 # template names.
-#html_additional_pages = {}
+# html_additional_pages = {}
 
 # If false, no module index is generated.
-#html_domain_indices = True
+# html_domain_indices = True
 
 # If false, no index is generated.
-#html_use_index = True
+# html_use_index = True
 
 # If true, the index is split into individual pages for each letter.
-#html_split_index = False
+# html_split_index = False
 
 # If true, links to the reST sources are added to the pages.
-#html_show_sourcelink = True
+# html_show_sourcelink = True
 
 # If true, "Created using Sphinx" is shown in the HTML footer. Default is True.
-#html_show_sphinx = True
+# html_show_sphinx = True
 
 # If true, "(C) Copyright ..." is shown in the HTML footer. Default is True.
-#html_show_copyright = True
+# html_show_copyright = True
 
 # If true, an OpenSearch description file will be output, and all pages will
 # contain a <link> tag referring to it.  The value of this option must be the
 # base URL from which the finished HTML is served.
-#html_use_opensearch = ''
+# html_use_opensearch = ''
 
 # This is the file name suffix for HTML files (e.g. ".xhtml").
-#html_file_suffix = None
+# html_file_suffix = None
 
 # Output file base name for HTML help builder.
-htmlhelp_basename = 'paperless'
+htmlhelp_basename = "paperless"
 
 # -- Options for LaTeX output ---------------------------------------------
 
 latex_elements = {
-# The paper size ('letterpaper' or 'a4paper').
-#'papersize': 'letterpaper',
-
-# The font size ('10pt', '11pt' or '12pt').
-#'pointsize': '10pt',
-
-# Additional stuff for the LaTeX preamble.
-#'preamble': '',
+    # The paper size ('letterpaper' or 'a4paper').
+    #'papersize': 'letterpaper',
+    # The font size ('10pt', '11pt' or '12pt').
+    #'pointsize': '10pt',
+    # Additional stuff for the LaTeX preamble.
+    #'preamble': '',
 }
 
 # Grouping the document tree into LaTeX files. List of tuples
 # (source start file, target name, title,
 #  author, documentclass [howto, manual, or own class]).
 latex_documents = [
-  ('index', 'paperless.tex', u'Paperless Documentation',
-   u'Daniel Quinn', 'manual'),
+    ("index", "paperless.tex", "Paperless Documentation", "Daniel Quinn", "manual"),
 ]
 
 # The name of an image file (relative to this directory) to place at the top of
 # the title page.
-#latex_logo = None
+# latex_logo = None
 
 # For "manual" documents, if this is true, then toplevel headings are parts,
 # not chapters.
-#latex_use_parts = False
+# latex_use_parts = False
 
 # If true, show page references after internal links.
-#latex_show_pagerefs = False
+# latex_show_pagerefs = False
 
 # If true, show URL addresses after external links.
-#latex_show_urls = False
+# latex_show_urls = False
 
 # Documents to append as an appendix to all manuals.
-#latex_appendices = []
+# latex_appendices = []
 
 # If false, no module index is generated.
-#latex_domain_indices = True
+# latex_domain_indices = True
 
 
 # -- Options for manual page output ---------------------------------------
 
 # One entry per manual page. List of tuples
 # (source start file, name, description, authors, manual section).
-man_pages = [
-    ('index', 'paperless', u'Paperless Documentation',
-     [u'Daniel Quinn'], 1)
-]
+man_pages = [("index", "paperless", "Paperless Documentation", ["Daniel Quinn"], 1)]
 
 # If true, show URL addresses after external links.
-#man_show_urls = False
+# man_show_urls = False
 
 
 # -- Options for Texinfo output -------------------------------------------
@@ -229,93 +239,99 @@ man_pages = [
 # (source start file, target name, title, author,
 #  dir menu entry, description, category)
 texinfo_documents = [
-  ('index', 'Paperless', u'Paperless Documentation',
-   u'Daniel Quinn', 'paperless', 'Scan, index, and archive all of your paper documents.',
-   'Miscellaneous'),
+    (
+        "index",
+        "Paperless",
+        "Paperless Documentation",
+        "Daniel Quinn",
+        "paperless",
+        "Scan, index, and archive all of your paper documents.",
+        "Miscellaneous",
+    ),
 ]
 
 # Documents to append as an appendix to all manuals.
-#texinfo_appendices = []
+# texinfo_appendices = []
 
 # If false, no module index is generated.
-#texinfo_domain_indices = True
+# texinfo_domain_indices = True
 
 # How to display URL addresses: 'footnote', 'no', or 'inline'.
-#texinfo_show_urls = 'footnote'
+# texinfo_show_urls = 'footnote'
 
 # If true, do not generate a @detailmenu in the "Top" node's menu.
-#texinfo_no_detailmenu = False
+# texinfo_no_detailmenu = False
 
 
 # -- Options for Epub output ----------------------------------------------
 
 # Bibliographic Dublin Core info.
-epub_title = u'Paperless'
-epub_author = u'Daniel Quinn'
-epub_publisher = u'Daniel Quinn'
-epub_copyright = u'2015, Daniel Quinn'
+epub_title = "Paperless"
+epub_author = "Daniel Quinn"
+epub_publisher = "Daniel Quinn"
+epub_copyright = "2015, Daniel Quinn"
 
 # The basename for the epub file. It defaults to the project name.
-#epub_basename = u'Paperless'
+# epub_basename = u'Paperless'
 
 # The HTML theme for the epub output. Since the default themes are not optimized
 # for small screen space, using the same theme for HTML and epub output is
 # usually not wise. This defaults to 'epub', a theme designed to save visual
 # space.
-#epub_theme = 'epub'
+# epub_theme = 'epub'
 
 # The language of the text. It defaults to the language option
 # or en if the language is not set.
-#epub_language = ''
+# epub_language = ''
 
 # The scheme of the identifier. Typical schemes are ISBN or URL.
-#epub_scheme = ''
+# epub_scheme = ''
 
 # The unique identifier of the text. This can be a ISBN number
 # or the project homepage.
-#epub_identifier = ''
+# epub_identifier = ''
 
 # A unique identification for the text.
-#epub_uid = ''
+# epub_uid = ''
 
 # A tuple containing the cover image and cover page html template filenames.
-#epub_cover = ()
+# epub_cover = ()
 
 # A sequence of (type, uri, title) tuples for the guide element of content.opf.
-#epub_guide = ()
+# epub_guide = ()
 
 # HTML files that should be inserted before the pages created by sphinx.
 # The format is a list of tuples containing the path and title.
-#epub_pre_files = []
+# epub_pre_files = []
 
 # HTML files shat should be inserted after the pages created by sphinx.
 # The format is a list of tuples containing the path and title.
-#epub_post_files = []
+# epub_post_files = []
 
 # A list of files that should not be packed into the epub file.
-epub_exclude_files = ['search.html']
+epub_exclude_files = ["search.html"]
 
 # The depth of the table of contents in toc.ncx.
-#epub_tocdepth = 3
+# epub_tocdepth = 3
 
 # Allow duplicate toc entries.
-#epub_tocdup = True
+# epub_tocdup = True
 
 # Choose between 'default' and 'includehidden'.
-#epub_tocscope = 'default'
+# epub_tocscope = 'default'
 
 # Fix unsupported image types using the PIL.
-#epub_fix_images = False
+# epub_fix_images = False
 
 # Scale large images.
-#epub_max_image_width = 0
+# epub_max_image_width = 0
 
 # How to display URL addresses: 'footnote', 'no', or 'inline'.
-#epub_show_urls = 'inline'
+# epub_show_urls = 'inline'
 
 # If false, no index is generated.
-#epub_use_index = True
+# epub_use_index = True
 
 
 # Example configuration for intersphinx: refer to the Python standard library.
-intersphinx_mapping = {'http://docs.python.org/': None}
+intersphinx_mapping = {"http://docs.python.org/": None}

docs/configuration.rst

@@ -27,11 +27,23 @@ PAPERLESS_REDIS=<url>
     This is required for processing scheduled tasks such as email fetching, index
     optimization and for training the automatic document matcher.
 
+    * If your Redis server needs login credentials PAPERLESS_REDIS = ``redis://<username>:<password>@<host>:<port>``
+
+    * With the requirepass option PAPERLESS_REDIS = ``redis://:<password>@<host>:<port>``
+
+    `More information on securing your Redis Instance <https://redis.io/docs/getting-started/#securing-redis>`_.
+
     Defaults to redis://localhost:6379.
 
+PAPERLESS_DBENGINE=<engine_name>
+    Optional, gives the ability to choose Postgres or MariaDB for database engine.
+    Available options are `postgresql` and `mariadb`.
+    Default is `postgresql`.
+
 PAPERLESS_DBHOST=<hostname>
     By default, sqlite is used as the database backend. This can be changed here.
-    Set PAPERLESS_DBHOST and PostgreSQL will be used instead of mysql.
+
+    Set PAPERLESS_DBHOST and another database will be used instead of sqlite.
 
 PAPERLESS_DBPORT=<port>
     Adjust port if necessary.
@@ -39,20 +51,33 @@ PAPERLESS_DBPORT=<port>
     Default is 5432.
 
 PAPERLESS_DBNAME=<name>
-    Database name in PostgreSQL.
+    Database name in PostgreSQL or MariaDB.
 
     Defaults to "paperless".
 
 PAPERLESS_DBUSER=<name>
-    Database user in PostgreSQL.
+    Database user in PostgreSQL or MariaDB.
 
     Defaults to "paperless".
 
 PAPERLESS_DBPASS=<password>
-    Database password for PostgreSQL.
+    Database password for PostgreSQL or MariaDB.
 
     Defaults to "paperless".
 
+PAPERLESS_DBSSLMODE=<mode>
+    SSL mode to use when connecting to PostgreSQL.
+
+    See `the official documentation about sslmode <https://www.postgresql.org/docs/current/libpq-ssl.html>`_.
+
+    Default is ``prefer``.
+
+PAPERLESS_DB_TIMEOUT=<float>
+    Amount of time for a database connection to wait for the database to unlock.
+    Mostly applicable for an sqlite based installation, consider changing to postgresql
+    if you need to increase this.
+
+    Defaults to unset, keeping the Django defaults.
 
 Paths and folders
 #################
@@ -66,13 +91,22 @@ PAPERLESS_CONSUMPTION_DIR=<path>
     container. Change the local consumption directory in the docker-compose.yml
     file instead.
 
-    Defaults to "../consume", relative to the "src" directory.
+    Defaults to "../consume/", relative to the "src" directory.
 
 PAPERLESS_DATA_DIR=<path>
     This is where paperless stores all its data (search index, SQLite database,
     classification model, etc).
 
-    Defaults to "../data", relative to the "src" directory.
+    Defaults to "../data/", relative to the "src" directory.
+
+PAPERLESS_TRASH_DIR=<path>
+    Instead of removing deleted documents, they are moved to this directory.
+
+    This must be writeable by the user running paperless. When running inside
+    docker, ensure that this path is within a permanent volume (such as
+    "../media/trash") so it won't get lost on upgrades.
+
+    Defaults to empty (i.e. really delete documents).
 
 PAPERLESS_MEDIA_ROOT=<path>
     This is where your documents and thumbnails are stored.
@@ -80,7 +114,7 @@ PAPERLESS_MEDIA_ROOT=<path>
     You can set this and PAPERLESS_DATA_DIR to the same folder to have paperless
     store all its data within the same volume.
 
-    Defaults to "../media", relative to the "src" directory.
+    Defaults to "../media/", relative to the "src" directory.
 
 PAPERLESS_STATICDIR=<path>
     Override the default STATIC_ROOT here.  This is where all static files
@@ -88,7 +122,7 @@ PAPERLESS_STATICDIR=<path>
 
     Unless you're doing something fancy, there is no need to override this.
 
-    Defaults to "../static", relative to the "src" directory.
+    Defaults to "../static/", relative to the "src" directory.
 
 PAPERLESS_FILENAME_FORMAT=<format>
     Changes the filenames paperless uses to store documents in the media directory.
@@ -96,6 +130,35 @@ 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.
+
+    Defaults to "``PAPERLESS_DATA_DIR``/log/".
+
+
+Logging
+#######
+
+PAPERLESS_LOGROTATE_MAX_SIZE=<num>
+    Maximum file size for log files before they are rotated, in bytes.
+
+    Defaults to 1 MiB.
+
+PAPERLESS_LOGROTATE_MAX_BACKUPS=<num>
+    Number of rotated log files to keep.
+
+    Defaults to 20.
+
+.. _hosting-and-security:
+
 Hosting & Security
 ##################
 
@@ -108,7 +171,24 @@ PAPERLESS_SECRET_KEY=<key>
 
     Default is listed in the file ``src/paperless/settings.py``.
 
-PAPERLESS_ALLOWED_HOSTS<comma-separated-list>
+PAPERLESS_URL=<url>
+    This setting can be used to set the three options below (ALLOWED_HOSTS,
+    CORS_ALLOWED_HOSTS and CSRF_TRUSTED_ORIGINS). If the other options are
+    set the values will be combined with this one. Do not include a trailing
+    slash. E.g. https://paperless.domain.com
+
+    Defaults to empty string, leaving the other settings unaffected.
+
+PAPERLESS_CSRF_TRUSTED_ORIGINS=<comma-separated-list>
+    A list of trusted origins for unsafe requests (e.g. POST). As of Django 4.0
+    this is required to access the Django admin via the web.
+    See https://docs.djangoproject.com/en/4.0/ref/settings/#csrf-trusted-origins
+
+    Can also be set using PAPERLESS_URL (see above).
+
+    Defaults to empty string, which does not add any origins to the trusted list.
+
+PAPERLESS_ALLOWED_HOSTS=<comma-separated-list>
     If you're planning on putting Paperless on the open internet, then you
     really should set this value to the domain name you're using.  Failing to do
     so leaves you open to HTTP host header attacks:
@@ -117,30 +197,40 @@ PAPERLESS_ALLOWED_HOSTS<comma-separated-list>
     Just remember that this is a comma-separated list, so "example.com" is fine,
     as is "example.com,www.example.com", but NOT " example.com" or "example.com,"
 
+    Can also be set using PAPERLESS_URL (see above).
+
+    If manually set, please remember to include "localhost". Otherwise docker
+    healthcheck will fail.
+
     Defaults to "*", which is all hosts.
 
-PAPERLESS_CORS_ALLOWED_HOSTS<comma-separated-list>
+PAPERLESS_CORS_ALLOWED_HOSTS=<comma-separated-list>
     You need to add your servers to the list of allowed hosts that can do CORS
     calls. Set this to your public domain name.
 
+    Can also be set using PAPERLESS_URL (see above).
+
     Defaults to "http://localhost:8000".
 
 PAPERLESS_FORCE_SCRIPT_NAME=<path>
     To host paperless under a subpath url like example.com/paperless you set
     this value to /paperless. No trailing slash!
 
-    .. note::
-
-        I don't know if this works in paperless-ng. Probably not.
-
     Defaults to none, which hosts paperless at "/".
 
 PAPERLESS_STATIC_URL=<path>
     Override the STATIC_URL here.  Unless you're hosting Paperless off a
     subdomain like /paperless/, you probably don't need to change this.
+    If you do change it, be sure to include the trailing slash.
 
     Defaults to "/static/".
 
+    .. note::
+
+        When hosting paperless behind a reverse proxy like Traefik or Nginx at a subpath e.g.
+        example.com/paperlessngx you will also need to set ``PAPERLESS_FORCE_SCRIPT_NAME``
+        (see above).
+
 PAPERLESS_AUTO_LOGIN_USERNAME=<username>
     Specify a username here so that paperless will automatically perform login
     with the selected user.
@@ -152,6 +242,30 @@ PAPERLESS_AUTO_LOGIN_USERNAME=<username>
 
     Defaults to none, which disables this feature.
 
+PAPERLESS_ADMIN_USER=<username>
+    If this environment variable is specified, Paperless automatically creates
+    a superuser with the provided username at start. This is useful in cases
+    where you can not run the `createsuperuser` command separately, such as Kubernetes
+    or AWS ECS.
+
+    Requires `PAPERLESS_ADMIN_PASSWORD` to be set.
+
+    .. note::
+
+        This will not change an existing [super]user's password, nor will
+        it recreate a user that already exists. You can leave this throughout
+        the lifecycle of the containers.
+
+PAPERLESS_ADMIN_MAIL=<email>
+    (Optional) Specify superuser email address. Only used when
+    `PAPERLESS_ADMIN_USER` is set.
+
+    Defaults to ``root@localhost``.
+
+PAPERLESS_ADMIN_PASSWORD=<password>
+    Only used when `PAPERLESS_ADMIN_USER` is set.
+    This will be the password of the automatically created superuser.
+
 
 PAPERLESS_COOKIE_PREFIX=<str>
     Specify a prefix that is added to the cookies used by paperless to identify
@@ -162,6 +276,39 @@ PAPERLESS_COOKIE_PREFIX=<str>
 
     Defaults to ``""``, which does not alter the cookie names.
 
+PAPERLESS_ENABLE_HTTP_REMOTE_USER=<bool>
+    Allows authentication via HTTP_REMOTE_USER which is used by some SSO
+    applications.
+
+    .. warning::
+
+        This will allow authentication by simply adding a ``Remote-User: <username>`` header
+        to a request. Use with care! You especially *must* ensure that any such header is not
+        passed from your proxy server to paperless.
+
+        If you're exposing paperless to the internet directly, do not use this.
+
+        Also see the warning `in the official documentation <https://docs.djangoproject.com/en/3.1/howto/auth-remote-user/#configuration>`.
+
+    Defaults to `false` which disables this feature.
+
+PAPERLESS_HTTP_REMOTE_USER_HEADER_NAME=<str>
+    If `PAPERLESS_ENABLE_HTTP_REMOTE_USER` is enabled, this property allows to
+    customize the name of the HTTP header from which the authenticated username
+    is extracted. Values are in terms of
+    [HttpRequest.META](https://docs.djangoproject.com/en/3.1/ref/request-response/#django.http.HttpRequest.META).
+    Thus, the configured value must start with `HTTP_` followed by the
+    normalized actual header name.
+
+    Defaults to `HTTP_REMOTE_USER`.
+
+PAPERLESS_LOGOUT_REDIRECT_URL=<str>
+    URL to redirect the user to after a logout. This can be used together with
+    `PAPERLESS_ENABLE_HTTP_REMOTE_USER` to redirect the user back to the SSO
+    application's logout page.
+
+    Defaults to None, which disables this feature.
+
 .. _configuration-ocr:
 
 OCR settings
@@ -171,7 +318,6 @@ Paperless uses `OCRmyPDF <https://ocrmypdf.readthedocs.io/en/latest/>`_ for
 performing OCR on documents and images. Paperless uses sensible defaults for
 most settings, but all of them can be configured to your needs.
 
-
 PAPERLESS_OCR_LANGUAGE=<lang>
     Customize the language that paperless will attempt to use when
     parsing documents.
@@ -188,6 +334,8 @@ PAPERLESS_OCR_LANGUAGE=<lang>
 
     Defaults to "eng".
 
+		Note: If your language contains a '-' such as chi-sim, you must use chi_sim
+
 PAPERLESS_OCR_MODE=<mode>
     Tell paperless when and how to perform ocr on your documents. Four modes
     are available:
@@ -210,20 +358,68 @@ PAPERLESS_OCR_MODE=<mode>
         into images and puts the OCRed text on top. This works for all documents,
         however, the resulting document may be significantly larger and text
         won't appear as sharp when zoomed in.
-    
+
     The default is ``skip``, which only performs OCR when necessary and always
     creates archived documents.
 
+    Read more about this in the `OCRmyPDF documentation <https://ocrmypdf.readthedocs.io/en/latest/advanced.html#when-ocr-is-skipped>`_.
+
+PAPERLESS_OCR_CLEAN=<mode>
+    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. The following modes are available:
+
+    *   ``clean``: Apply unpaper.
+    *   ``clean-final``: Apply unpaper, and use the cleaned images to build the
+        output file instead of the original images.
+    *   ``none``: Do not apply unpaper.
+
+    Defaults to ``clean``.
+
+    .. note::
+
+        ``clean-final`` is incompatible with ocr mode ``redo``. When both
+        ``clean-final`` and the ocr mode ``redo`` is configured, ``clean``
+        is used instead.
+
+PAPERLESS_OCR_DESKEW=<bool>
+    Tells paperless to correct skewing (slight rotation of input images mainly
+    due to improper scanning)
+
+    Defaults to ``true``, which enables this feature.
+
+    .. note::
+
+        Deskewing is incompatible with ocr mode ``redo``. Deskewing will get
+        disabled automatically if ``redo`` is used as the ocr mode.
+
+PAPERLESS_OCR_ROTATE_PAGES=<bool>
+    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).
+
+    Defaults to ``true``, which enables this feature.
+
+
+PAPERLESS_OCR_ROTATE_PAGES_THRESHOLD=<num>
+    Adjust the threshold for automatic page rotation by ``PAPERLESS_OCR_ROTATE_PAGES``.
+    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.
+
+    Defaults to "12".
+
 PAPERLESS_OCR_OUTPUT_TYPE=<type>
     Specify the the type of PDF documents that paperless should produce.
-    
+
     *   ``pdf``: Modify the PDF document as little as possible.
     *   ``pdfa``: Convert PDF documents into PDF/A-2b documents, which is a
         subset of the entire PDF specification and meant for storing
         documents long term.
     *   ``pdfa-1``, ``pdfa-2``, ``pdfa-3`` to specify the exact version of
         PDF/A you wish to use.
-    
+
     If not specified, ``pdfa`` is used. Remember that paperless also keeps
     the original input file as well as the archived version.
 
@@ -240,7 +436,6 @@ PAPERLESS_OCR_PAGES=<num>
 
     Defaults to 0, which disables this feature and always uses all pages.
 
-
 PAPERLESS_OCR_IMAGE_DPI=<num>
     Paperless will OCR any images you put into the system and convert them
     into PDF documents. This is useful if your scanner produces images.
@@ -251,17 +446,35 @@ PAPERLESS_OCR_IMAGE_DPI=<num>
 
     Set this to the DPI your scanner produces images at.
 
-    Default is none, which causes paperless to fail if no DPI information is
-    present in an image.
+    Default is none, which will automatically calculate image DPI so that
+    the produced PDF documents are A4 sized.
 
+PAPERLESS_OCR_MAX_IMAGE_PIXELS=<num>
+    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.
 
-PAPERLESS_OCR_USER_ARG=<json>
+    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
     additional arguments you wish to pass to OCRmyPDF. Since Paperless uses
     the API of OCRmyPDF, you have to specify these in a format that can be
     passed to the API. See `the API reference of OCRmyPDF <https://ocrmypdf.readthedocs.io/en/latest/api.html#reference>`_
     for valid parameters. All command line options are supported, but they
-    use underscores instead of dashed.
+    use underscores instead of dashes.
 
     .. caution::
 
@@ -275,9 +488,72 @@ PAPERLESS_OCR_USER_ARG=<json>
 
     .. code:: json
 
-        {"deskew": true, "optimize": 3, "unpaper_args": "--pre-rotate 90"}    
-    
-    
+        {"deskew": true, "optimize": 3, "unpaper_args": "--pre-rotate 90"}
+
+.. _configuration-tika:
+
+Tika settings
+#############
+
+Paperless can make use of `Tika <https://tika.apache.org/>`_ and
+`Gotenberg <https://gotenberg.dev/>`_ for parsing and
+converting "Office" documents (such as ".doc", ".xlsx" and ".odt"). If you
+wish to use this, you must provide a Tika server and a Gotenberg server,
+configure their endpoints, and enable the feature.
+
+PAPERLESS_TIKA_ENABLED=<bool>
+    Enable (or disable) the Tika parser.
+
+    Defaults to false.
+
+PAPERLESS_TIKA_ENDPOINT=<url>
+    Set the endpoint URL were Paperless can reach your Tika server.
+
+    Defaults to "http://localhost:9998".
+
+PAPERLESS_TIKA_GOTENBERG_ENDPOINT=<url>
+    Set the endpoint URL were Paperless can reach your Gotenberg server.
+
+    Defaults to "http://localhost:3000".
+
+If you run paperless on docker, you can add those services to the docker-compose
+file (see the provided ``docker-compose.sqlite-tika.yml`` file for reference). The changes
+requires are as follows:
+
+.. code:: yaml
+
+    services:
+        # ...
+
+        webserver:
+            # ...
+
+            environment:
+                # ...
+
+                PAPERLESS_TIKA_ENABLED: 1
+                PAPERLESS_TIKA_GOTENBERG_ENDPOINT: http://gotenberg:3000
+                PAPERLESS_TIKA_ENDPOINT: http://tika:9998
+
+        # ...
+
+        gotenberg:
+            image: gotenberg/gotenberg:7.4
+            restart: unless-stopped
+            command:
+                - "gotenberg"
+                - "--chromium-disable-routes=true"
+
+        tika:
+            image: ghcr.io/paperless-ngx/tika:latest
+            restart: unless-stopped
+
+Add the configuration variables to the environment of the webserver (alternatively
+put the configuration in the ``docker-compose.env`` file) and add the additional
+services below the webserver service. Watch out for indentation.
+
+Make sure to use the correct format `PAPERLESS_TIKA_ENABLED = 1` so python_dotenv can parse the statement correctly.
+
 Software tweaks
 ###############
 
@@ -286,6 +562,8 @@ PAPERLESS_TASK_WORKERS=<num>
     maintain the automatic matching algorithm, check emails, consume documents,
     etc. This variable specifies how many things it will do in parallel.
 
+    Defaults to 1
+
 
 PAPERLESS_THREADS_PER_WORKER=<num>
     Furthermore, paperless uses multiple threads when consuming documents to
@@ -304,13 +582,40 @@ PAPERLESS_THREADS_PER_WORKER=<num>
         use a higher thread per worker count.
 
     The default is a balance between the two, according to your CPU core count,
-    with a slight favor towards threads per worker, and using as much cores as
-    possible.
+    with a slight favor towards threads per worker:
+
+    +----------------+---------+---------+
+    | CPU core count | Workers | Threads |
+    +----------------+---------+---------+
+    |              1 |       1 |       1 |
+    +----------------+---------+---------+
+    |              2 |       2 |       1 |
+    +----------------+---------+---------+
+    |              4 |       2 |       2 |
+    +----------------+---------+---------+
+    |              6 |       2 |       3 |
+    +----------------+---------+---------+
+    |              8 |       2 |       4 |
+    +----------------+---------+---------+
+    |             12 |       3 |       4 |
+    +----------------+---------+---------+
+    |             16 |       4 |       4 |
+    +----------------+---------+---------+
 
     If you only specify PAPERLESS_TASK_WORKERS, paperless will adjust
     PAPERLESS_THREADS_PER_WORKER automatically.
 
 
+PAPERLESS_WORKER_TIMEOUT=<num>
+    Machines with few cores or weak ones might not be able to finish OCR on
+    large documents within the default 1800 seconds. So extending this timeout
+    may prove to be useful on weak hardware setups.
+
+PAPERLESS_WORKER_RETRY=<num>
+    If PAPERLESS_WORKER_TIMEOUT has been configured, the retry time for a task can
+    also be configured.  By default, this value will be set to 10s more than the
+    worker timeout.  This value should never be set less than the worker timeout.
+
 PAPERLESS_TIME_ZONE=<timezone>
     Set the time zone here.
     See https://docs.djangoproject.com/en/3.1/ref/settings/#std:setting-TIME_ZONE
@@ -319,14 +624,39 @@ PAPERLESS_TIME_ZONE=<timezone>
     Defaults to UTC.
 
 
+.. _configuration-polling:
+
 PAPERLESS_CONSUMER_POLLING=<num>
     If paperless won't find documents added to your consume folder, it might
     not be able to automatically detect filesystem changes. In that case,
     specify a polling interval in seconds here, which will then cause paperless
-    to periodically check your consumption directory for changes.
+    to periodically check your consumption directory for changes. This will also
+    disable listening for file system changes with ``inotify``.
 
     Defaults to 0, which disables polling and uses filesystem notifications.
 
+PAPERLESS_CONSUMER_POLLING_RETRY_COUNT=<num>
+    If consumer polling is enabled, sets the number of times paperless will check for a
+    file to remain unmodified.
+
+    Defaults to 5.
+
+PAPERLESS_CONSUMER_POLLING_DELAY=<num>
+    If consumer polling is enabled, sets the delay in seconds between each check (above) paperless
+    will do while waiting for a file to remain unmodified.
+
+    Defaults to 5.
+
+.. _configuration-inotify:
+
+PAPERLESS_CONSUMER_INOTIFY_DELAY=<num>
+    Sets the time in seconds the consumer will wait for additional events
+    from inotify before the consumer will consider a file ready and begin consumption.
+    Certain scanners or network setups may generate multiple events for a single file,
+    leading to multiple consumers working on the same file.  Configure this to
+    prevent that.
+
+    Defaults to 0.5 seconds.
 
 PAPERLESS_CONSUMER_DELETE_DUPLICATES=<bool>
     When the consumer detects a duplicate document, it will not touch the
@@ -348,10 +678,44 @@ PAPERLESS_CONSUMER_SUBDIRS_AS_TAGS=<bool>
     E.g. <CONSUMPTION_DIR>/foo/bar/file.pdf will add the tags "foo" and "bar" to
     the consumed file. Paperless will create any tags that don't exist yet.
 
+    This is useful for sorting documents with certain tags such as ``car`` or
+    ``todo`` prior to consumption. These folders won't be deleted.
+
     PAPERLESS_CONSUMER_RECURSIVE must be enabled for this to work.
 
     Defaults to false.
 
+PAPERLESS_CONSUMER_ENABLE_BARCODES=<bool>
+    Enables the scanning and page separation based on detected barcodes.
+    This allows for scanning and adding multiple documents per uploaded
+    file, which are separated by one or multiple barcode pages.
+
+    For ease of use, it is suggested to use a standardized separation page,
+    e.g. `here <https://www.alliancegroup.co.uk/patch-codes.htm>`_.
+
+    If no barcodes are detected in the uploaded file, no page separation
+    will happen.
+
+    The original document will be removed and the separated pages will be
+    saved as pdf.
+
+    Defaults to false.
+
+PAPERLESS_CONSUMER_BARCODE_TIFF_SUPPORT=<bool>
+    Whether TIFF image files should be scanned for barcodes.
+    This will automatically convert any TIFF image(s) to pdfs for later
+    processing.
+    This only has an effect, if PAPERLESS_CONSUMER_ENABLE_BARCODES has been
+    enabled.
+
+    Defaults to false.
+
+PAPERLESS_CONSUMER_BARCODE_STRING=PATCHT
+  Defines the string to be detected as a separator barcode.
+  If paperless is used with the PATCH-T separator pages, users
+  shouldn't change this.
+
+  Defaults to "PATCHT"
 
 PAPERLESS_CONVERT_MEMORY_LIMIT=<num>
     On smaller systems, or even in the case of Very Large Documents, the consumer
@@ -376,13 +740,6 @@ PAPERLESS_CONVERT_TMPDIR=<path>
 
     Default is none, which disables the temporary directory.
 
-PAPERLESS_OPTIMIZE_THUMBNAILS=<bool>
-    Use optipng to optimize thumbnails. This usually reduces the size of
-    thumbnails by about 20%, but uses considerable compute time during
-    consumption.
-
-    Defaults to true.
-
 PAPERLESS_POST_CONSUME_SCRIPT=<filename>
     After a document is consumed, Paperless can trigger an arbitrary script if
     you like.  This script will be passed a number of arguments for you to work
@@ -398,8 +755,57 @@ PAPERLESS_FILENAME_DATE_ORDER=<format>
     The filename will be checked first, and if nothing is found, the document
     text will be checked as normal.
 
+    A date in a filename must have some separators (`.`, `-`, `/`, etc)
+    for it to be parsed.
+
     Defaults to none, which disables this feature.
 
+PAPERLESS_NUMBER_OF_SUGGESTED_DATES=<num>
+    Paperless searches an entire document for dates. The first date found will
+    be used as the initial value for the created date. When this variable is
+    greater than 0 (or left to it's default value), paperless will also suggest
+    other dates found in the document, up to a maximum of this setting. Note that
+    duplicates will be removed, which can result in fewer dates displayed in the
+    frontend than this setting value.
+
+    The task to find all dates can be time-consuming and increases with a higher
+    (maximum) number of suggested dates and slower hardware.
+
+    Defaults to 3. Set to 0 to disable this feature.
+
+PAPERLESS_THUMBNAIL_FONT_NAME=<filename>
+    Paperless creates thumbnails for plain text files by rendering the content
+    of the file on an image and uses a predefined font for that. This
+    font can be changed here.
+
+    Note that this won't have any effect on already generated thumbnails.
+
+    Defaults to ``/usr/share/fonts/liberation/LiberationSerif-Regular.ttf``.
+
+PAPERLESS_IGNORE_DATES=<string>
+    Paperless parses a documents creation date from filename and file content.
+    You may specify a comma separated list of dates that should be ignored during
+    this process. This is useful for special dates (like date of birth) that appear
+    in documents regularly but are very unlikely to be the documents creation date.
+
+    The date is parsed using the order specified in PAPERLESS_DATE_ORDER
+
+    Defaults to an empty string to not ignore any dates.
+
+PAPERLESS_DATE_ORDER=<format>
+    Paperless will try to determine the document creation date from its contents.
+    Specify the date format Paperless should expect to see within your documents.
+
+    This option defaults to DMY which translates to day first, month second, and year
+    last order. Characters D, M, or Y can be shuffled to meet the required order.
+
+PAPERLESS_CONSUMER_IGNORE_PATTERNS=<json>
+    By default, paperless ignores certain files and folders in the consumption
+    directory, such as system files created by the Mac OS.
+
+    This can be adjusted by configuring a custom json array with patterns to exclude.
+
+    Defaults to ``[".DS_STORE/*", "._*", ".stfolder/*", ".stversions/*", ".localized/*", "desktop.ini"]``.
 
 Binaries
 ########
@@ -412,10 +818,108 @@ the program doesn't automatically execute it (ie. the program isn't in your
 $PATH), then you'll need to specify the literal path for that program.
 
 PAPERLESS_CONVERT_BINARY=<path>
-    Defaults to "/usr/bin/convert".
+    Defaults to "convert".
 
 PAPERLESS_GS_BINARY=<path>
-    Defaults to "/usr/bin/gs".
+    Defaults to "gs".
 
-PAPERLESS_OPTIPNG_BINARY=<path>
-    Defaults to "/usr/bin/optipng".
+
+.. _configuration-docker:
+
+Docker-specific options
+#######################
+
+These options don't have any effect in ``paperless.conf``. These options adjust
+the behavior of the docker container. Configure these in `docker-compose.env`.
+
+PAPERLESS_WEBSERVER_WORKERS=<num>
+    The number of worker processes the webserver should spawn. More worker processes
+    usually result in the front end to load data much quicker. However, each worker process
+    also loads the entire application into memory separately, so increasing this value
+    will increase RAM usage.
+
+    Defaults to 1.
+
+PAPERLESS_BIND_ADDR=<ip address>
+    The IP address the webserver will listen on inside the container. There are
+    special setups where you may need to configure this value to restrict the
+    Ip address or interface the webserver listens on.
+
+    Defaults to [::], meaning all interfaces, including IPv6.
+
+PAPERLESS_PORT=<port>
+    The port number the webserver will listen on inside the container. There are
+    special setups where you may need this to avoid collisions with other
+    services (like using podman with multiple containers in one pod).
+
+    Don't change this when using Docker. To change the port the webserver is
+    reachable outside of the container, instead refer to the "ports" key in
+    ``docker-compose.yml``.
+
+    Defaults to 8000.
+
+USERMAP_UID=<uid>
+    The ID of the paperless user in the container. Set this to your actual user ID on the
+    host system, which you can get by executing
+
+    .. code:: shell-session
+
+        $ id -u
+
+    Paperless will change ownership on its folders to this user, so you need to get this right
+    in order to be able to write to the consumption directory.
+
+    Defaults to 1000.
+
+USERMAP_GID=<gid>
+    The ID of the paperless Group in the container. Set this to your actual group ID on the
+    host system, which you can get by executing
+
+    .. code:: shell-session
+
+        $ id -g
+
+    Paperless will change ownership on its folders to this group, so you need to get this right
+    in order to be able to write to the consumption directory.
+
+    Defaults to 1000.
+
+PAPERLESS_OCR_LANGUAGES=<list>
+    Additional OCR languages to install. By default, paperless comes with
+    English, German, Italian, Spanish and French. If your language is not in this list, install
+    additional languages with this configuration option:
+
+    .. code:: bash
+
+        PAPERLESS_OCR_LANGUAGES=tur ces
+
+    To actually use these languages, also set the default OCR language of paperless:
+
+    .. code:: bash
+
+        PAPERLESS_OCR_LANGUAGE=tur
+
+    Defaults to none, which does not install any additional languages.
+
+
+.. _configuration-update-checking:
+
+Update Checking
+###############
+
+PAPERLESS_ENABLE_UPDATE_CHECK=<bool>
+    Enable (or disable) the automatic check for available updates. This feature is disabled
+    by default but if it is not explicitly set Paperless-ngx will show a message about this.
+
+    If enabled, the feature works by pinging the the Github API for the latest release e.g.
+    https://api.github.com/repos/paperless-ngx/paperless-ngx/releases/latest
+    to determine whether a new version is available.
+
+    Actual updating of the app must still be performed manually.
+
+    Note that for users of thirdy-party containers e.g. linuxserver.io this notification
+    may be 'ahead' of a new release from the third-party maintainers.
+
+    In either case, no tracking data is collected by the app in any way.
+
+    Defaults to none, which disables the feature.

docs/contributing.rst

@@ -1,145 +0,0 @@
-.. _contributing:
-
-Contributing to Paperless
-#########################
-
-.. warning::
-
-    This section is not updated to paperless-ng yet.
-    
-Maybe you've been using Paperless for a while and want to add a feature or two,
-or maybe you've come across a bug that you have some ideas how to solve.  The
-beauty of Free software is that you can see what's wrong and help to get it
-fixed for everyone!
-
-
-How to Get Your Changes Rolled Into Paperless
-=============================================
-
-If you've found a bug, but don't know how to fix it, you can always post an
-issue on `GitHub`_ in the hopes that someone will have the time to fix it for
-you.  If however you're the one with the time, pull requests are always
-welcome, you just have to make sure that your code conforms to a few standards:
-
-Pep8
-----
-
-It's the standard for all Python development, so it's `very well documented`_.
-The short version is:
-
-* Lines should wrap at 79 characters
-* Use ``snake_case`` for variables, ``CamelCase`` for classes, and ``ALL_CAPS``
-  for constants.
-* Space out your operators: ``stuff + 7`` instead of ``stuff+7``
-* Two empty lines between classes, and functions, but 1 empty line between
-  class methods.
-
-There's more to it than that, but if you follow those, you'll probably be
-alright.  When you submit your pull request, there's a pep8 checker that'll
-look at your code to see if anything is off.  If it finds anything, it'll
-complain at you until you fix it.
-
-
-Additional Style Guides
------------------------
-
-Where pep8 is ambiguous, I've tried to be a little more specific.  These rules
-aren't hard-and-fast, but if you can conform to them, I'll appreciate it and
-spend less time trying to conform your PR before merging:
-
-
-Function calls
-..............
-
-If you're calling a function and that necessitates more than one line of code,
-please format it like this:
-
-.. code:: python
-
-    my_function(
-        argument1,
-        kwarg1="x",
-        kwarg2="y"
-        another_really_long_kwarg="some big value"
-        a_kwarg_calling_another_long_function=another_function(
-            another_arg,
-            another_kwarg="kwarg!"
-        )
-    )
-
-This is all in the interest of code uniformity rather than anything else.  If
-we stick to a style, everything is understandable in the same way.
-
-
-Quoting Strings
-...............
-
-pep8 is a little too open-minded on this for my liking.  Python strings should
-be quoted with double quotes (``"``) except in cases where the resulting string
-would require too much escaping of a double quote, in which case, a single
-quoted, or triple-quoted string will do:
-
-.. code:: python
-
-    my_string = "This is my string"
-    problematic_string = 'This is a "string" with "quotes" in it'
-
-In HTML templates, please use double-quotes for tag attributes, and single
-quotes for arguments passed to Django template tags:
-
-.. code:: html
-
-    <div class="stuff">
-        <a href="{% url 'some-url-name' pk='w00t' %}">link this</a>
-    </div>
-
-This is to keep linters happy they look at an HTML file and see an attribute
-closing the ``"`` before it should have been.
-
---
-
-That's all there is in terms of guidelines, so I hope it's not too daunting.
-
-
-Indentation & Spacing
-.....................
-
-When it comes to indentation:
-
-* For Python, the rule is: follow pep8 and use 4 spaces.
-* For Javascript, CSS, and HTML, please use 1 tab.
-
-Additionally, Django templates making use of block elements like ``{% if %}``,
-``{% for %}``, and ``{% block %}`` etc. should be indented:
-
-Good:
-
-.. code:: html
-
-    {% block stuff %}
-    	<h1>This is the stuff</h1>
-    {% endblock %}
-
-Bad:
-
-.. code:: html
-
-    {% block stuff %}
-    <h1>This is the stuff</h1>
-    {% endblock %}
-
-
-The Code of Conduct
-===================
-
-Paperless has a `code of conduct`_.  It's a lot like the other ones you see out
-there, with a few small changes, but basically it boils down to:
-
-> Don't be an ass, or you might get banned.
-
-I'm proud to say that the CoC has never had to be enforced because everyone has
-been awesome, friendly, and professional.
-
-.. _GitHub: https://github.com/the-paperless-project/paperless/issues
-.. _very well documented: https://www.python.org/dev/peps/pep-0008/
-.. _code of conduct: https://github.com/the-paperless-project/paperless/blob/master/CODE_OF_CONDUCT.md

docs/extending.rst

@@ -1,75 +1,163 @@
 .. _extending:
 
-Paperless development
-#####################
+Paperless-ngx Development
+#########################
 
-This section describes the steps you need to take to start development on paperless-ng.
+This section describes the steps you need to take to start development on paperless-ngx.
 
-1.  Check out the source from github. The repository is organized in the following way:
+Check out the source from github. The repository is organized in the following way:
 
-    *   ``master`` always represents the latest release and will only see changes
-        when a new release is made.
-    *   ``dev`` contains the code that will be in the next release.
-    *   ``feature-X`` contain bigger changes that will be in some release, but not
-        necessarily the next one.
-    
-    Apart from that, the folder structure is as follows:
+*   ``main`` always represents the latest release and will only see changes
+    when a new release is made.
+*   ``dev`` contains the code that will be in the next release.
+*   ``feature-X`` contain bigger changes that will be in some release, but not
+    necessarily the next one.
 
-    *   ``docs/`` - Documentation.
-    *   ``src-ui/`` - Code of the front end.
-    *   ``src/`` - Code of the back end.
-    *   ``scripts/`` - Various scripts that help with different parts of development.
-    *   ``docker/`` - Files required to build the docker image.
+When making functional changes to paperless, *always* make your changes on the ``dev`` branch.
 
-2.  Install some dependencies.
+Apart from that, the folder structure is as follows:
 
-    *   Python 3.6.
-    *   All dependencies listed in the :ref:`Bare metal route <setup-bare_metal>`
-    *   redis. You can either install redis or use the included scritps/start-redis.sh
-        to use docker to fire up a redis instance.
+*   ``docs/`` - Documentation.
+*   ``src-ui/`` - Code of the front end.
+*   ``src/`` - Code of the back end.
+*   ``scripts/`` - Various scripts that help with different parts of development.
+*   ``docker/`` - Files required to build the docker image.
+
+Contributing to Paperless
+=========================
+
+Maybe you've been using Paperless for a while and want to add a feature or two,
+or maybe you've come across a bug that you have some ideas how to solve.  The
+beauty of open source software is that you can see what's wrong and help to get
+it fixed for everyone!
+
+Before contributing please review our `code of conduct`_ and other important
+information in the `contributing guidelines`_.
+
+.. _code-formatting-with-pre-commit-hooks:
+
+Code formatting with pre-commit Hooks
+=====================================
+
+To ensure a consistent style and formatting across the project source, the project
+utilizes a Git `pre-commit` hook to perform some formatting and linting before a
+commit is allowed. That way, everyone uses the same style and some common issues
+can be caught early on. See below for installation instructions.
+
+Once installed, hooks will run when you commit. If the formatting isn't quite right
+or a linter catches something, the commit will be rejected. You'll need to look at the
+output and fix the issue. Some hooks, such as the Python formatting tool `black`,
+will format failing files, so all you need to do is `git add` those files again and
+retry your commit.
+
+Initial setup and first start
+=============================
+
+After you forked and cloned the code from github you need to perform a first-time setup.
+To do the setup you need to perform the steps from the following chapters in a certain order:
+
+1.  Install prerequisites + pipenv as mentioned in :ref:`Bare metal route <setup-bare_metal>`
+2.  Copy ``paperless.conf.example`` to ``paperless.conf`` and enable debug mode.
+3.  Install the Angular CLI interface:
+
+    .. code:: shell-session
+
+        $ npm install -g @angular/cli
+
+4.  Install pre-commit
+
+    .. code:: shell-session
+
+        pre-commit install
+
+5.  Create ``consume`` and ``media`` folders in the cloned root folder.
+
+    .. code:: shell-session
+
+        mkdir -p consume media
+
+6.  You can now either ...
+
+    *  install redis or
+    *  use the included scripts/start-services.sh to use docker to fire up a redis instance (and some other services such as tika, gotenberg and a database server) or
+    *  spin up a bare redis container
+
+        .. code:: shell-session
+
+            docker run -d -p 6379:6379 --restart unless-stopped redis:latest
+
+7.  Install the python dependencies by performing in the src/ directory.
+
+    .. code:: shell-session
+
+        pipenv install --dev
+
+  * Make sure you're using python 3.9.x or lower. Otherwise you might get issues with building dependencies. You can use `pyenv <https://github.com/pyenv/pyenv>`_ to install a specific python version.
+
+8.  Generate the static UI so you can perform a login to get session that is required for frontend development (this needs to be done one time only). From src-ui directory:
+
+    .. code:: shell-session
+
+        npm install .
+        ./node_modules/.bin/ng build --configuration production
+
+9.  Apply migrations and create a superuser for your dev instance:
+
+    .. code:: shell-session
+
+        python3 manage.py migrate
+        python3 manage.py createsuperuser
+
+10.  Now spin up the dev backend. Depending on which part of paperless you're developing for, you need to have some or all of them running.
+
+    .. code:: shell-session
+
+        python3 manage.py runserver & python3 manage.py document_consumer & python3 manage.py qcluster
+
+11. Login with the superuser credentials provided in step 8 at ``http://localhost:8000`` to create a session that enables you to use the backend.
+
+Backend development environment is now ready, to start Frontend development go to ``/src-ui`` and run ``ng serve``. From there you can use ``http://localhost:4200`` for a preview.
 
 Back end development
 ====================
 
-The backend is a django application. I use PyCharm for development, but you can use whatever
+The backend is a django application. PyCharm works well for development, but you can use whatever
 you want.
 
-Install the python dependencies by performing ``pipenv install --dev`` in the src/ directory.
-This will also create a virtual environment, which you can enter with ``pipenv shell`` or
-execute one-shot commands in with ``pipenv run``.
-
-In ``src/paperless.conf``, enable debug mode.
-
 Configure the IDE to use the src/ folder as the base source folder. Configure the following
 launch configurations in your IDE:
 
 *   python3 manage.py runserver
 *   python3 manage.py qcluster
-*   python3 manage.py consumer
+*   python3 manage.py document_consumer
 
-Depending on which part of paperless you're developing for, you need to have some or all of
-them running.
+To start them all:
+
+.. code:: shell-session
+
+    python3 manage.py runserver & python3 manage.py document_consumer & python3 manage.py qcluster
 
 Testing and code style:
 
 *   Run ``pytest`` in the src/ directory to execute all tests. This also generates a HTML coverage
     report. When runnings test, paperless.conf is loaded as well. However: the tests rely on the default
     configuration. This is not ideal. But for now, make sure no settings except for DEBUG are overridden when testing.
-*   Run ``pycodestyle`` to test your code for issues with the configured code style settings.
+*   Coding style is enforced by the Git pre-commit hooks.  These will ensure your code is formatted and do some
+    linting when you do a `git commit`.
+*   You can also run ``black`` manually to format your code
 
     .. note::
 
         The line length rule E501 is generally useful for getting multiple source files
         next to each other on the screen. However, in some cases, its just not possible
-        to make some lines fit, especially complicated IF cases. Append ``  # NOQA: E501``
+        to make some lines fit, especially complicated IF cases. Append ``# NOQA: E501``
         to disable this check for certain lines.
 
 Front end development
 =====================
 
-The front end is build using angular. I use the ``Code - OSS`` IDE for development.
-
-In order to get started, you need ``npm``. Install the Angular CLI interface with
+The front end is built using Angular. In order to get started, you need ``npm``.
+Install the Angular CLI interface with
 
 .. code:: shell-session
 
@@ -98,22 +186,165 @@ X-Frame-Options are in place so that the front end behaves exactly as in product
 relies on you being logged into the back end. Without a valid session, The front end will simply
 not work.
 
+Testing and code style:
+
+*   The frontend code (.ts, .html, .scss) use ``prettier`` for code formatting via the Git
+    ``pre-commit`` hooks which run automatically on commit. See
+    :ref:`above <code-formatting-with-pre-commit-hooks>` for installation. You can also run this
+    via cli with a command such as
+
+    .. code:: shell-session
+
+        $ git ls-files -- '*.ts' | xargs pre-commit run prettier --files
+
+*   Frontend testing uses jest and cypress. There is currently a need for significantly more
+    frontend tests. Unit tests and e2e tests, respectively, can be run non-interactively with:
+
+    .. code:: shell-session
+
+        $ ng test
+        $ npm run e2e:ci
+
+    Cypress also includes a UI which can be run from within the ``src-ui`` directory with
+
+    .. code:: shell-session
+
+        $ ./node_modules/.bin/cypress open
+
 In order to build the front end and serve it as part of django, execute
 
 .. code:: shell-session
 
-    $ ng build --prod --output-path ../src/documents/static/frontend/
+    $ ng build --prod
 
 This will build the front end and put it in a location from which the Django server will serve
 it as static content. This way, you can verify that authentication is working.
 
-Making a release
-================
 
-Execute the ``make-release.sh <ver>`` script.
+Localization
+============
 
-This will test and assemble everything and also build and tag a docker image.
+Paperless is available in many different languages. Since paperless consists both of a django
+application and an Angular front end, both these parts have to be translated separately.
 
+Front end localization
+----------------------
+
+*   The Angular front end does localization according to the `Angular documentation <https://angular.io/guide/i18n>`_.
+*   The source language of the project is "en_US".
+*   The source strings end up in the file "src-ui/messages.xlf".
+*   The translated strings need to be placed in the "src-ui/src/locale/" folder.
+*   In order to extract added or changed strings from the source files, call ``ng xi18n --ivy``.
+
+Adding new languages requires adding the translated files in the "src-ui/src/locale/" folder and adjusting a couple files.
+
+1.  Adjust "src-ui/angular.json":
+
+    .. code:: json
+
+        "i18n": {
+            "sourceLocale": "en-US",
+            "locales": {
+                "de": "src/locale/messages.de.xlf",
+                "nl-NL": "src/locale/messages.nl_NL.xlf",
+                "fr": "src/locale/messages.fr.xlf",
+                "en-GB": "src/locale/messages.en_GB.xlf",
+                "pt-BR": "src/locale/messages.pt_BR.xlf",
+                "language-code": "language-file"
+            }
+        }
+
+2.  Add the language to the available options in "src-ui/src/app/services/settings.service.ts":
+
+    .. code:: typescript
+
+        getLanguageOptions(): LanguageOption[] {
+            return [
+                {code: "en-us", name: $localize`English (US)`, englishName: "English (US)", dateInputFormat: "mm/dd/yyyy"},
+                {code: "en-gb", name: $localize`English (GB)`, englishName: "English (GB)", dateInputFormat: "dd/mm/yyyy"},
+                {code: "de", name: $localize`German`, englishName: "German", dateInputFormat: "dd.mm.yyyy"},
+                {code: "nl", name: $localize`Dutch`, englishName: "Dutch", dateInputFormat: "dd-mm-yyyy"},
+                {code: "fr", name: $localize`French`, englishName: "French", dateInputFormat: "dd/mm/yyyy"},
+                {code: "pt-br", name: $localize`Portuguese (Brazil)`, englishName: "Portuguese (Brazil)", dateInputFormat: "dd/mm/yyyy"}
+                // Add your new language here
+            ]
+        }
+
+    ``dateInputFormat`` is a special string that defines the behavior of the date input fields and absolutely needs to contain "dd", "mm" and "yyyy".
+
+3.  Import and register the Angular data for this locale in "src-ui/src/app/app.module.ts":
+
+    .. code:: typescript
+
+        import localeDe from '@angular/common/locales/de';
+        registerLocaleData(localeDe)
+
+Back end localization
+---------------------
+
+A majority of the strings that appear in the back end appear only when the admin is used. However,
+some of these are still shown on the front end (such as error messages).
+
+*   The django application does localization according to the `django documentation <https://docs.djangoproject.com/en/3.1/topics/i18n/translation/>`_.
+*   The source language of the project is "en_US".
+*   Localization files end up in the folder "src/locale/".
+*   In order to extract strings from the application, call ``python3 manage.py makemessages -l en_US``. This is important after making changes to translatable strings.
+*   The message files need to be compiled for them to show up in the application. Call ``python3 manage.py compilemessages`` to do this. The generated files don't get
+    committed into git, since these are derived artifacts. The build pipeline takes care of executing this command.
+
+Adding new languages requires adding the translated files in the "src/locale/" folder and adjusting the file "src/paperless/settings.py" to include the new language:
+
+.. code:: python
+
+    LANGUAGES = [
+        ("en-us", _("English (US)")),
+        ("en-gb", _("English (GB)")),
+        ("de", _("German")),
+        ("nl-nl", _("Dutch")),
+        ("fr", _("French")),
+        ("pt-br", _("Portuguese (Brazil)")),
+        # Add language here.
+    ]
+
+
+Building the documentation
+==========================
+
+The documentation is built using sphinx. I've configured ReadTheDocs to automatically build
+the documentation when changes are pushed. If you want to build the documentation locally,
+this is how you do it:
+
+1.  Install python dependencies.
+
+    .. code:: shell-session
+
+        $ cd /path/to/paperless
+        $ pipenv install --dev
+
+2.  Build the documentation
+
+    .. code:: shell-session
+
+        $ cd /path/to/paperless/docs
+        $ pipenv run make clean html
+
+This will build the HTML documentation, and put the resulting files in the ``_build/html``
+directory.
+
+Building the Docker image
+=========================
+
+The docker image is primarily built by the GitHub actions workflow, but it can be
+faster when developing to build and tag an image locally.
+
+To provide the build arguments automatically, build the image using the helper
+script ``build-docker-image.sh``.
+
+Building the docker image from source:
+
+    .. code:: shell-session
+
+        ./build-docker-image.sh Dockerfile -t <your-tag>
 
 Extending Paperless
 ===================
@@ -149,7 +380,7 @@ methods ``parse`` and ``get_thumbnail``. You can provide your own implementation
 
             # The content of the document.
             self.text = "content"
-            
+
             # Optional: path to a PDF document that you created from the original.
             self.archive_path = os.path.join(self.tempdir, "archived.pdf")
 
@@ -195,3 +426,6 @@ that returns information about your parser:
     download. We could guess that from the file extensions, but some mime types have many extensions
     associated with them and the python methods responsible for guessing the extension do not always
     return the same value.
+
+.. _code of conduct: https://github.com/paperless-ngx/paperless-ngx/blob/main/CODE_OF_CONDUCT.md
+.. _contributing guidelines: https://github.com/paperless-ngx/paperless-ngx/blob/main/CONTRIBUTING.md

docs/faq.rst

@@ -3,17 +3,13 @@
 Frequently asked questions
 **************************
 
-**Q:** *What's the general plan for Paperless-ng?*
+**Q:** *What's the general plan for Paperless-ngx?*
 
-**A:** Paperless-ng is already almost feature-complete. This project will remain
-as simple as it is right now. It will see improvements to features that are already there.
-If you need advanced features such as document versions,
-workflows or multi-user with customizable access to individual files, this is
-not the tool for you.
-
-Features that *are* planned are some more quality of life extensions for the searching
-(i.e., search for similar documents, group results by correspondents with "more from this"
-links, etc), bulk editing and hierarchical tags.
+**A:** While Paperless-ngx is already considered largely "feature-complete" it is a community-driven
+project and development will be guided in this way. New features can be submitted via
+GitHub discussions and "up-voted" by the community but this is not a guarantee the feature
+will be implemented. This project will always be open to collaboration in the form of PRs,
+ideas etc.
 
 **Q:** *I'm using docker. Where are my documents?*
 
@@ -33,56 +29,62 @@ is
     files around manually. This folder is meant to be entirely managed by docker
     and paperless.
 
-**Q:** *Let's say you don't support this project anymore in a year. Can I easily move to other systems?*
+**Q:** *Let's say I want to switch tools in a year. Can I easily move to other systems?*
 
 **A:** Your documents are stored as plain files inside the media folder. You can always drag those files
 out of that folder to use them elsewhere. Here are a couple notes about that.
 
-*   Paperless never modifies your original documents. It keeps checksums of all documents and uses a
+*   Paperless-ngx never modifies your original documents. It keeps checksums of all documents and uses a
     scheduled sanity checker to check that they remain the same.
 *   By default, paperless uses the internal ID of each document as its filename. This might not be very
     convenient for export. However, you can adjust the way files are stored in paperless by
     :ref:`configuring the filename format <advanced-file_name_handling>`.
 *   :ref:`The exporter <utilities-exporter>` is another easy way to get your files out of paperless with reasonable file names.
 
-**Q:** *What file types does paperless-ng support?*
+**Q:** *What file types does paperless-ngx support?*
 
 **A:** Currently, the following files are supported:
 
 *   PDF documents, PNG images, JPEG images, TIFF images and GIF images are processed with OCR and converted into PDF documents.
 *   Plain text documents are supported as well and are added verbatim
     to paperless.
+*   With the optional Tika integration enabled (see :ref:`Configuration <configuration-tika>`), Paperless also supports various
+    Office documents (.docx, .doc, odt, .ppt, .pptx, .odp, .xls, .xlsx, .ods).
 
-Paperless determines the type of a file by inspecting its content. The
+Paperless-ngx determines the type of a file by inspecting its content. The
 file extensions do not matter.
 
-**Q:** *Will paperless-ng run on Raspberry Pi?*
+**Q:** *Will paperless-ngx run on Raspberry Pi?*
 
 **A:** The short answer is yes. I've tested it on a Raspberry Pi 3 B.
 The long answer is that certain parts of
-Paperless will run very slow, such as the tesseract OCR. On Raspberry Pi,
+Paperless will run very slow, such as the OCR. On Raspberry Pi,
 try to OCR documents before feeding them into paperless so that paperless can
-reuse the text. The web interface should be a lot snappier, since it runs
+reuse the text. The web interface is a lot snappier, since it runs
 in your browser and paperless has to do much less work to serve the data.
 
 .. note::
-    
+
     You can adjust some of the settings so that paperless uses less processing
     power. See :ref:`setup-less_powerful_devices` for details.
-    
 
-**Q:** *How do I install paperless-ng on Raspberry Pi?*
 
-**A:** There is no docker image for ARM available. If you know how to build
-that automatically, I'm all ears. For now, you have to grab the latest release
-archive from the project page and build the image yourself. The release comes
-with the front end already compiled, so you don't have to do this on the Pi.
+**Q:** *How do I install paperless-ngx on Raspberry Pi?*
 
-**Q:** *How do I run this on unRaid?*
+**A:** Docker images are available for arm and arm64 hardware, so just follow
+the docker-compose instructions. Apart from more required disk space compared to
+a bare metal installation, docker comes with close to zero overhead, even on
+Raspberry Pi.
 
-**A:** Head over to `<https://github.com/selfhosters/unRAID-CA-templates>`_,
-`Uli Fahrer <https://github.com/Tooa>`_ created a container template for that.
-I don't exactly know how to use that though, since I don't use unRaid.
+If you decide to got with the bare metal route, be aware that some of the
+python requirements do not have precompiled packages for ARM / ARM64. Installation
+of these will require additional development libraries and compilation will take
+a long time.
+
+**Q:** *How do I run this on Unraid?*
+
+**A:** Paperless-ngx is available as `community app <https://unraid.net/community/apps?q=paperless-ngx>`_
+in Unraid. `Uli Fahrer <https://github.com/Tooa>`_ created a container template for that.
 
 **Q:** *How do I run this on my toaster?*
 
@@ -95,12 +97,21 @@ occasionally build the image on and see if it works.
 
 **Q:** *How do I proxy this with NGINX?*
 
-.. code::
+**A:** See :ref:`here <setup-nginx>`.
 
-    location / {
-        proxy_pass http://localhost:8000/
-    }
+.. _faq-mod_wsgi:
 
-And that's about it. Paperless serves everything, including static files by itself
-when running the docker image. If you want to do anything fancy, you have to
-install paperless bare metal.
+**Q:** *How do I get WebSocket support with Apache mod_wsgi*?
+
+**A:** ``mod_wsgi`` by itself does not support ASGI. Paperless will continue
+to work with WSGI, but certain features such as status notifications about
+document consumption won't be available.
+
+If you want to continue using ``mod_wsgi``, you will have to run an ASGI-enabled
+web server as well that processes WebSocket connections, and configure Apache to
+redirect WebSocket connections to this server. Multiple options for ASGI servers
+exist:
+
+* ``gunicorn`` with ``uvicorn`` as the worker implementation (the default of paperless)
+* ``daphne`` as a standalone server, which is the reference implementation for ASGI.
+* ``uvicorn`` as a standalone server

docs/index.rst

@@ -22,19 +22,21 @@ finding stuff again. I feed documents right from the post box into the scanner
 and then shred them.  Perhaps you might find it useful too.
 
 
-Paperless-ng
-============
+Paperless-ngx
+=============
 
-Paperless-ng is a fork of the original paperless project. It changes many
-things both on the surface and under the hood. Paperless-ng was created
-because I feel that these changes are too big to be pushed into the main
-repository right away.
+Paperless-ngx is a document management system that transforms your physical
+documents into a searchable online archive so you can keep, well, *less paper*.
+
+Paperless-ngx forked from paperless-ng to continue the great work and
+distribute responsibility of supporting and advancing the project among a team
+of people.
 
 NG stands for both Angular (the framework used for the
 Frontend) and next-gen. Publishing this project under a different name also
-avoids confusion between paperless and paperless-ng.
+avoids confusion between paperless and paperless-ngx.
 
-If you want to learn about what's different in paperless-ng, check out these
+If you want to learn about what's different in paperless-ngx from Paperless, check out these
 resources in the documentation:
 
 *   :ref:`Some screenshots <screenshots>` of the new UI are available.
@@ -42,20 +44,16 @@ resources in the documentation:
     learn about how paperless automates all tagging using machine learning.
 *   Paperless now comes with a :ref:`proper email consumer <usage-email>`
     that's fully tested and production ready.
-*   Paperless creates searchable PDF/A documents from whatever you you put into
+*   Paperless creates searchable PDF/A documents from whatever you put into
     the consumption directory. This means that you can select text in
     image-only documents coming from your scanner.
 *   See :ref:`this note <utilities-encyption>` about GnuPG encryption in
-    paperless-ng.
+    paperless-ngx.
 *   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
-    in paperless-ng.
-
-It would be great if this project could eventually merge back into the main
-repository, but it needs a lot more work before that can happen.
-
+    at a glance when and why something is not working.
+*   The :doc:`changelog </changelog>` contains a detailed list of all changes
+    in paperless-ngx.
 
 Contents
 ========
@@ -70,9 +68,8 @@ Contents
    configuration
    api
    faq
-   extending
    troubleshooting
-   contributing
+   extending
    scanners
    screenshots
    changelog

docs/requirements.txt

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

docs/scanners.rst

@@ -1,43 +1,8 @@
 
 .. _scanners:
 
-***********************
-Scanner recommendations
-***********************
+*******************
+Scanners & Software
+*******************
 
-As Paperless operates by watching a folder for new files, doesn't care what
-scanner you use, but sometimes finding a scanner that will write to an FTP,
-NFS, or SMB server can be difficult.  This page is here to help you find one
-that works right for you based on recommendations from other Paperless users.
-
-+---------+----------------+-----+-----+-----+----------------+
-| Brand   | Model          | Supports        | Recommended By |
-+---------+----------------+-----+-----+-----+----------------+
-|         |                | FTP | NFS | SMB |                |
-+=========+================+=====+=====+=====+================+
-| Brother | `ADS-1500W`_   | yes | no  | yes | `danielquinn`_ |
-+---------+----------------+-----+-----+-----+----------------+
-| Brother | `MFC-J6930DW`_ | yes |     |     | `ayounggun`_   |
-+---------+----------------+-----+-----+-----+----------------+
-| Brother | `MFC-J5910DW`_ | yes |     |     | `bmsleight`_   |
-+---------+----------------+-----+-----+-----+----------------+
-| Brother | `MFC-9142CDN`_ | yes |     | yes | `REOLDEV`_     |
-+---------+----------------+-----+-----+-----+----------------+
-| Fujitsu | `ix500`_       | yes |     | yes | `eonist`_      |
-+---------+----------------+-----+-----+-----+----------------+
-| Fujitsu | `S1300i`_      | yes |     | yes | `jonaswinkler`_|
-+---------+----------------+-----+-----+-----+----------------+
-
-.. _ADS-1500W: https://www.brother.ca/en/p/ads1500w
-.. _MFC-J6930DW: https://www.brother.ca/en/p/MFCJ6930DW
-.. _MFC-J5910DW: https://www.brother.co.uk/printers/inkjet-printers/mfcj5910dw
-.. _MFC-9142CDN: https://www.brother.co.uk/printers/laser-printers/mfc9140cdn
-.. _ix500: https://www.fujitsu.com/global/products/computing/peripheral/scanners/scansnap/ix500/
-.. _S1300i: https://www.fujitsu.com/global/products/computing/peripheral/scanners/soho/s1300i/
-
-.. _danielquinn: https://github.com/danielquinn
-.. _ayounggun: https://github.com/ayounggun
-.. _bmsleight: https://github.com/bmsleight
-.. _eonist: https://github.com/eonist
-.. _REOLDEV: https://github.com/REOLDEV
-.. _jonaswinkler: https://github.com/jonaswinkler
+Paperless-ngx is compatible with many different scanners and scanning tools. A user-maintained list of scanners and other software is available on `the wiki <https://github.com/paperless-ngx/paperless-ngx/wiki/Scanner-&-Software-Recommendations>`_.

docs/screenshots.rst

@@ -4,42 +4,60 @@
 Screenshots
 ***********
 
-This is what paperless-ng looks like. You shouldn't use paperless to index
-research papers though, its a horrible tool for that job.
+This is what Paperless-ngx looks like.
 
 The dashboard shows customizable views on your document and allows document uploads:
 
 .. image:: _static/screenshots/dashboard.png
+    :target: _static/screenshots/dashboard.png
 
 The document list provides three different styles to scroll through your documents:
 
 .. image:: _static/screenshots/documents-table.png
+    :target: _static/screenshots/documents-table.png
 .. image:: _static/screenshots/documents-smallcards.png
+    :target: _static/screenshots/documents-smallcards.png
 .. image:: _static/screenshots/documents-largecards.png
+    :target: _static/screenshots/documents-largecards.png
+
+Paperless-ngx also supports "dark mode":
+
+.. image:: _static/screenshots/documents-smallcards-dark.png
+    :target: _static/screenshots/documents-smallcards-dark.png
 
 Extensive filtering mechanisms:
 
 .. image:: _static/screenshots/documents-filter.png
+    :target: _static/screenshots/documents-filter.png
 
-Side-by-side editing of documents. Optimized for 1080p.
+Bulk editing of document tags, correspondents, etc.:
+
+.. image:: _static/screenshots/bulk-edit.png
+    :target: _static/screenshots/bulk-edit.png
+
+Side-by-side editing of documents:
 
 .. image:: _static/screenshots/editing.png
+    :target: _static/screenshots/editing.png
 
 Tag editing. This looks about the same for correspondents and document types.
 
 .. image:: _static/screenshots/new-tag.png
+    :target: _static/screenshots/new-tag.png
 
 Searching provides auto complete and highlights the results.
 
 .. image:: _static/screenshots/search-preview.png
+    :target: _static/screenshots/search-preview.png
 .. image:: _static/screenshots/search-results.png
+    :target: _static/screenshots/search-results.png
 
 Fancy mail filters!
 
 .. image:: _static/screenshots/mail-rules-edited.png
+    :target: _static/screenshots/mail-rules-edited.png
 
-Mobile support in the future? This kinda works, however some layouts are still
-too wide.
+Mobile devices are supported.
 
 .. image:: _static/screenshots/mobile.png
-
+    :target: _static/screenshots/mobile.png

docs/setup.rst

@@ -3,39 +3,10 @@
 Setup
 *****
 
-Download
-########
+Overview of Paperless-ngx
+#########################
 
-Go to the project page on GitHub and download the
-`latest release <https://github.com/jonaswinkler/paperless-ng/releases>`_.
-There are multiple options available.
-
-*   Download the dockerfiles archive if you want to pull paperless from
-    Docker Hub.
-
-*   Download the dist archive and extract it if you want to build the docker image
-    yourself or want to install paperless without docker.
-
-.. hint::
-
-    In contrast to paperless, the recommended way to get and update paperless-ng
-    is not to pull the entire git repository. Paperless-ng includes artifacts
-    that need to be compiled, and that's already done for you in the release.
-
-.. admonition:: Want to try out paperless-ng before migrating?
-
-    The release contains a file ``.env`` which sets the docker-compose project
-    name to "paperless", which is the same as before and instructs docker-compose
-    to reuse and upgrade your paperless volumes.
-
-    Just rename the project name in that file to anything else and docker-compose
-    will create fresh volumes for you!
-
-
-Overview of Paperless-ng
-########################
-
-Compared to paperless, paperless-ng works a little different under the hood and has
+Compared to paperless, paperless-ngx works a little different under the hood and has
 more moving parts that work together. While this increases the complexity of
 the system, it also brings many benefits.
 
@@ -49,45 +20,45 @@ Paperless consists of the following components:
     .. code:: shell-session
 
         $ cd /path/to/paperless/src/
-        $ pipenv run gunicorn -c /usr/src/paperless/gunicorn.conf.py -b 0.0.0.0:8000 paperless.wsgi
+        $ gunicorn -c ../gunicorn.conf.py paperless.wsgi
 
     or by any other means such as Apache ``mod_wsgi``.
 
 *   **The consumer:** This is what watches your consumption folder for documents.
-    However, the consumer itself does not consume really consume your documents anymore.
-    It rather notifies a task processor that a new file is ready for consumption.
+    However, the consumer itself does not really consume your documents.
+    Now it notifies a task processor that a new file is ready for consumption.
     I suppose it should be named differently.
-    This also used to check your emails, but that's now gone elsewhere as well.
+    This was also used to check your emails, but that's now done elsewhere as well.
 
     Start the consumer with the management command ``document_consumer``:
 
     .. code:: shell-session
 
         $ cd /path/to/paperless/src/
-        $ pipenv run python3 manage.py document_consumer
+        $ python3 manage.py document_consumer
 
     .. _setup-task_processor:
 
 *   **The task processor:** Paperless relies on `Django Q <https://django-q.readthedocs.io/en/latest/>`_
-    for doing much of the heavy lifting. This is a task queue that accepts tasks from
-    multiple sources and processes tasks in parallel. It also comes with a scheduler that executes
+    for doing most of the heavy lifting. This is a task queue that accepts tasks from
+    multiple sources and processes these in parallel. It also comes with a scheduler that executes
     certain commands periodically.
 
     This task processor is responsible for:
 
     *   Consuming documents. When the consumer finds new documents, it notifies the task processor to
         start a consumption task.
-    *   Consuming emails. It periodically checks your configured accounts for new mails and
-        produces consumption tasks for any documents it finds.
     *   The task processor also performs the consumption of any documents you upload through
         the web interface.
-    *   Maintain the search index and the automatic matching algorithm. These are things that paperless
+    *   Consuming emails. It periodically checks your configured accounts for new emails and
+        notifies the task processor to consume the attachment of an email.
+    *   Maintaining the search index and the automatic matching algorithm. These are things that paperless
         needs to do from time to time in order to operate properly.
 
     This allows paperless to process multiple documents from your consumption folder in parallel! On
-    a modern multi core system, consumption with full ocr is blazing fast.
+    a modern multi core system, this makes the consumption process with full OCR blazingly fast.
 
-    The task processor comes with a built-in admin interface that you can use to see whenever any of the
+    The task processor comes with a built-in admin interface that you can use to check whenever any of the
     tasks fail and inspect the errors (i.e., wrong email credentials, errors during consuming a specific
     file, etc).
 
@@ -96,62 +67,90 @@ Paperless consists of the following components:
     .. code:: shell-session
 
         $ cd /path/to/paperless/src/
-        $ pipenv run python3 manage.py qcluster
+        $ python3 manage.py qcluster
 
 *   A `redis <https://redis.io/>`_ message broker: This is a really lightweight service that is responsible
-    for getting the tasks from the webserver and consumer to the task scheduler. These run in different
-    processes (maybe even on different machines!), and therefore, this is necessary.
+    for getting the tasks from the webserver and the consumer to the task scheduler. These run in a different
+    process (maybe even on different machines!), and therefore, this is necessary.
 
-*   Optional: A database server. Paperless supports both PostgreSQL and SQLite for storing its data.
+*   Optional: A database server. Paperless supports PostgreSQL, MariaDB and SQLite for storing its data.
 
 
 Installation
 ############
 
-You can go multiple routes with setting up and running Paperless:
+You can go multiple routes to setup and run Paperless:
 
-* The `docker route`_
-* The `bare metal route`_
+* :ref:`Use the easy install docker script <setup-docker_script>`
+* :ref:`Pull the image from Docker Hub <setup-docker_hub>`
+* :ref:`Build the Docker image yourself <setup-docker_build>`
+* :ref:`Install Paperless directly on your system manually (bare metal) <setup-bare_metal>`
 
-The `docker route`_ is quick & easy. This is the recommended route. This configures all the stuff
-from above automatically so that it just works and uses sensible defaults for all configuration options.
+The Docker routes are quick & easy. These are the recommended routes. This configures all the stuff
+from the above automatically so that it just works and uses sensible defaults for all configuration options.
+Here you find a cheat-sheet for docker beginners: `CLI Basics <https://www.sehn.tech/refs/devops-with-docker/>`_
 
-The `bare metal route`_ is more complicated to setup but makes it easier
+The bare metal route is complicated to setup but makes it easier
 should you want to contribute some code back. You need to configure and
 run the above mentioned components yourself.
 
-.. _setup-docker_route:
+.. _CLI Basics: https://www.sehn.tech/refs/devops-with-docker/
 
-Docker Route
-============
+.. _setup-docker_script:
 
-1.  Install `Docker`_ and `docker-compose`_. [#compose]_
+Install Paperless from Docker Hub using the installation script
+===============================================================
 
-    .. caution::
+Paperless provides an interactive installation script. This script will ask you
+for a couple configuration options, download and create the necessary configuration files, pull the docker image, start paperless and create your user account. This script essentially
+performs all the steps described in :ref:`setup-docker_hub` automatically.
 
-        If you want to use the included ``docker-compose.*.yml`` file, you
-        need to have at least Docker version **17.09.0** and docker-compose
-        version **1.17.0**.
+1.  Make sure that docker and docker-compose are installed.
+2.  Download and run the installation script:
 
-        See the `Docker installation guide`_ on how to install the current
-        version of Docker for your operating system or Linux distribution of
-        choice. To get an up-to-date version of docker-compose, follow the
-        `docker-compose installation guide`_ if your package repository doesn't
-        include it.
+    .. code:: shell-session
 
-        .. _Docker installation guide: https://docs.docker.com/engine/installation/
-        .. _docker-compose installation guide: https://docs.docker.com/compose/install/
+        $ bash -c "$(curl -L https://raw.githubusercontent.com/paperless-ngx/paperless-ngx/main/install-paperless-ngx.sh)"
 
-2.  Copy either ``docker-compose.sqlite.yml`` or ``docker-compose.postgres.yml`` to
-    ``docker-compose.yml``, depending on which database backend you want to use.
+.. _setup-docker_hub:
+
+Install Paperless from Docker Hub
+=================================
+
+1.  Login with your user and create a folder in your home-directory `mkdir -v ~/paperless-ngx` to have a place for your configuration files and consumption directory.
+
+2.  Go to the `/docker/compose directory on the project page <https://github.com/paperless-ngx/paperless-ngx/tree/master/docker/compose>`_
+    and download one of the `docker-compose.*.yml` files, depending on which database backend you
+    want to use. Rename this file to `docker-compose.yml`.
+    If you want to enable optional support for Office documents, download a file with `-tika` in the file name.
+    Download the ``docker-compose.env`` file and the ``.env`` file as well and store them
+    in the same directory.
 
     .. hint::
 
         For new installations, it is recommended to use PostgreSQL as the database
         backend.
 
-2.  Modify ``docker-compose.yml`` to your preferences. You may want to change the path
-    to the consumption directory in this file. Find the line that specifies where
+3.  Install `Docker`_ and `docker-compose`_.
+
+    .. caution::
+
+        If you want to use the included ``docker-compose.*.yml`` file, you
+        need to have at least Docker version **17.09.0** and docker-compose
+        version **1.17.0**.
+        To check do: `docker-compose -v` or `docker -v`
+
+        See the `Docker installation guide`_ on how to install the current
+        version of Docker for your operating system or Linux distribution of
+        choice. To get the latest version of docker-compose, follow the
+        `docker-compose installation guide`_ if your package repository doesn't
+        include it.
+
+        .. _Docker installation guide: https://docs.docker.com/engine/installation/
+        .. _docker-compose installation guide: https://docs.docker.com/compose/install/
+
+4.  Modify ``docker-compose.yml`` to your preferences. You may want to change the path
+    to the consumption directory. Find the line that specifies where
     to mount the consumption directory:
 
     .. code::
@@ -166,25 +165,86 @@ Docker Route
 
     Don't change the part after the colon or paperless wont find your documents.
 
+    You may also need to change the default port that the webserver will use
+    from the default (8000):
 
-3.  Modify ``docker-compose.env``, following the comments in the file. The
+     .. code::
+
+        ports:
+          - 8000:8000
+
+    Replace the part BEFORE the colon with a port of your choice:
+
+     .. code::
+
+        ports:
+          - 8010:8000
+
+    Don't change the part after the colon or edit other lines that refer to
+    port 8000. Modifying the part before the colon will map requests on another
+    port to the webserver running on the default port.
+
+    **Rootless**
+
+    If you want to run Paperless as a rootless container, you will need to do the
+    following in your ``docker-compose.yml``:
+
+    - set the ``user`` running the container to map to the ``paperless`` user in the
+      container.
+      This value (``user_id`` below), should be the same id that ``USERMAP_UID`` and
+      ``USERMAP_GID`` are set to in the next step.
+      See ``USERMAP_UID`` and ``USERMAP_GID`` :ref:`here <configuration-docker>`.
+
+    Your entry for Paperless should contain something like:
+
+     .. code::
+
+        webserver:
+          image: ghcr.io/paperless-ngx/paperless-ngx:latest
+          user: <user_id>
+
+5.  Modify ``docker-compose.env``, following the comments in the file. The
     most important change is to set ``USERMAP_UID`` and ``USERMAP_GID``
-    to the uid and gid of your user on the host system. This ensures that
+    to the uid and gid of your user on the host system. Use ``id -u`` and
+    ``id -g`` to get these.
+
+    This ensures that
     both the docker container and you on the host machine have write access
     to the consumption directory. If your UID and GID on the host system is
     1000 (the default for the first normal user on most systems), it will
-    work out of the box without any modifications.
+    work out of the box without any modifications. `id "username"` to check.
 
     .. note::
 
-        You can use any settings from the file ``paperless.conf`` in this file.
-        Have a look at :ref:`configuration` to see whats available.
+        You can copy any setting from the file ``paperless.conf.example`` and paste it here.
+        Have a look at :ref:`configuration` to see what's available.
 
-4.  Run ``docker-compose up -d``. This will create and start the necessary
-    containers. This will also build the image of paperless if you grabbed the
-    source archive.
+    .. note::
 
-5.  To be able to login, you will need a super user. To create it, execute the
+        You can utilize Docker secrets for some configuration settings by
+        appending `_FILE` to some configuration values.  This is supported currently
+        only by:
+
+          * PAPERLESS_DBUSER
+          * PAPERLESS_DBPASS
+          * PAPERLESS_SECRET_KEY
+          * PAPERLESS_AUTO_LOGIN_USERNAME
+          * PAPERLESS_ADMIN_USER
+          * PAPERLESS_ADMIN_MAIL
+          * PAPERLESS_ADMIN_PASSWORD
+
+    .. caution::
+
+        Some file systems such as NFS network shares don't support file system
+        notifications with ``inotify``. When storing the consumption directory
+        on such a file system, paperless will not pick up new files
+        with the default configuration. You will need to use ``PAPERLESS_CONSUMER_POLLING``,
+        which will disable inotify. See :ref:`here <configuration-polling>`.
+
+6.  Run ``docker-compose pull``, followed by ``docker-compose up -d``.
+    This will pull the image, create and start the necessary containers.
+
+7.  To be able to login, you will need a super user. To create it, execute the
     following command:
 
     .. code-block:: shell-session
@@ -192,21 +252,57 @@ Docker Route
         $ docker-compose run --rm webserver createsuperuser
 
     This will prompt you to set a username, an optional e-mail address and
-    finally a password.
+    finally a password (at least 8 characters).
 
-6.  The default ``docker-compose.yml`` exports the webserver on your local port
-    8000. If you haven't adapted this, you should now be able to visit your
-    Paperless instance at ``http://127.0.0.1:8000``. You can login with the
-    user and password you just created.
+8.  The default ``docker-compose.yml`` exports the webserver on your local port
+    8000. If you did not change this, you should now be able to visit your
+    Paperless instance at ``http://127.0.0.1:8000`` or your servers IP-Address:8000.
+    Use the login credentials you have created with the previous step.
 
 .. _Docker: https://www.docker.com/
 .. _docker-compose: https://docs.docker.com/compose/install/
 
-.. [#compose] You of course don't have to use docker-compose, but it
-   simplifies deployment immensely. If you know your way around Docker, feel
-   free to tinker around without using compose!
+.. _setup-docker_build:
 
-.. _`setup-bare_metal`:
+Build the Docker image yourself
+===============================
+
+1.  Clone the entire repository of paperless:
+
+    .. code:: shell-session
+
+        git clone https://github.com/paperless-ngx/paperless-ngx
+
+    The master branch always reflects the latest stable version.
+
+2.  Copy one of the ``docker/compose/docker-compose.*.yml`` to ``docker-compose.yml`` in the root folder,
+    depending on which database backend you want to use. Copy
+    ``docker-compose.env`` into the project root as well.
+
+3.  In the ``docker-compose.yml`` file, find the line that instructs docker-compose to pull the paperless image from Docker Hub:
+
+    .. code:: yaml
+
+        webserver:
+            image: ghcr.io/paperless-ngx/paperless-ngx:latest
+
+    and replace it with a line that instructs docker-compose to build the image from the current working directory instead:
+
+    .. code:: yaml
+
+        webserver:
+            build: .
+
+4.  Follow steps 3 to 8 of :ref:`setup-docker_hub`. When asked to run
+    ``docker-compose pull`` to pull the image, do
+
+    .. code:: shell-session
+
+        $ docker-compose build
+
+    instead to build the image.
+
+.. _setup-bare_metal:
 
 Bare Metal Route
 ================
@@ -217,16 +313,26 @@ writing. Windows is not and will never be supported.
 
 1.  Install dependencies. Paperless requires the following packages.
 
-    *   ``python3`` 3.6, 3.7, 3.8 (3.9 is untested).
-    *   ``python3-pip``, optionally ``pipenv`` for package installation
+    *   ``python3`` 3.8, 3.9
+    *   ``python3-pip``
     *   ``python3-dev``
 
+    *   ``default-libmysqlclient-dev`` for MariaDB
+    *   ``fonts-liberation`` for generating thumbnails for plain text files
     *   ``imagemagick`` >= 6 for PDF conversion
-    *   ``optipng`` for optimising thumbnails
     *   ``gnupg`` for handling encrypted documents
-    *   ``libpoppler-cpp-dev`` for PDF to text conversion
-    *   ``libmagic-dev`` for mime type detection
     *   ``libpq-dev`` for PostgreSQL
+    *   ``libmagic-dev`` for mime type detection
+    *   ``mariadb-client`` for MariaDB compile time
+    *   ``mime-support`` for mime type detection
+    *   ``libzbar0`` for barcode detection
+    *   ``poppler-utils`` for barcode detection
+
+    Use this list for your preferred package management:
+
+    .. code::
+
+        python3 python3-pip python3-dev imagemagick fonts-liberation gnupg libpq-dev libmagic-dev mime-support libzbar0 poppler-utils
 
     These dependencies are required for OCRmyPDF, which is used for text recognition.
 
@@ -236,27 +342,45 @@ writing. Windows is not and will never be supported.
     *   ``qpdf``
     *   ``liblept5``
     *   ``libxml2``
-    *   ``pngquant``
+    *   ``pngquant`` (suggested for certain PDF image optimizations)
     *   ``zlib1g``
     *   ``tesseract-ocr`` >= 4.0.0 for OCR
     *   ``tesseract-ocr`` language packs (``tesseract-ocr-eng``, ``tesseract-ocr-deu``, etc)
 
+    Use this list for your preferred package management:
+
+    .. code::
+
+        unpaper ghostscript icc-profiles-free qpdf liblept5 libxml2 pngquant zlib1g tesseract-ocr
+
+    On Raspberry Pi, these libraries are required as well:
+
+    *   ``libatlas-base-dev``
+    *   ``libxslt1-dev``
+
     You will also need ``build-essential``, ``python3-setuptools`` and ``python3-wheel``
-    for installing some of the python dependencies. You can remove that
-    again after installation.
+    for installing some of the python dependencies.
 
 2.  Install ``redis`` >= 5.0 and configure it to start automatically.
 
 3.  Optional. Install ``postgresql`` and configure a database, user and password for paperless. If you do not wish
-    to use PostgreSQL, SQLite is avialable as well.
+    to use PostgreSQL, MariaDB and SQLite are available as well.
 
-4.  Get the release archive. If you pull the git repo as it is, you also have to compile the front end by yourself.
-    Extract the frontend to a place from where you wish to execute it, such as ``/opt/paperless``.
+    .. 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``.
 
 5.  Configure paperless. See :ref:`configuration` for details. Edit the included ``paperless.conf`` and adjust the
     settings to your needs. Required settings for getting paperless running are:
 
     *   ``PAPERLESS_REDIS`` should point to your redis server, such as redis://localhost:6379.
+    *   ``PAPERLESS_DBENGINE`` optional, and should be one of `postgres, mariadb, or sqlite`
     *   ``PAPERLESS_DBHOST`` should be the hostname on which your PostgreSQL server is running. Do not configure this
         to use SQLite instead. Also configure port, database name, user and password as necessary.
     *   ``PAPERLESS_CONSUMPTION_DIR`` should point to a folder which paperless should watch for documents. You might
@@ -264,58 +388,75 @@ writing. Windows is not and will never be supported.
         paperless stores its data. If you like, you can point both to the same directory.
     *   ``PAPERLESS_SECRET_KEY`` should be a random sequence of characters. It's used for authentication. Failure
         to do so allows third parties to forge authentication credentials.
-    
+    *   ``PAPERLESS_URL`` if you are behind a reverse proxy. This should point to your domain. Please see
+        :ref:`configuration` for more information.
+
     Many more adjustments can be made to paperless, especially the OCR part. The following options are recommended
     for everyone:
 
     *   Set ``PAPERLESS_OCR_LANGUAGE`` to the language most of your documents are written in.
     *   Set ``PAPERLESS_TIME_ZONE`` to your local time zone.
 
-6.  Setup permissions. Create a system users under which you wish to run paperless. Ensure that these directories exist
-    and that the user has write permissions to the following directories
-    
+6.  Create a system user under which you wish to run paperless.
+
+    .. code:: shell-session
+
+        adduser paperless --system --home /opt/paperless --group
+
+7.  Ensure that these directories exist
+    and that the paperless user has write permissions to the following directories:
+
     *   ``/opt/paperless/media``
     *   ``/opt/paperless/data``
     *   ``/opt/paperless/consume``
 
     Adjust as necessary if you configured different folders.
 
-7.  Install python requirements. Paperless comes with both Pipfiles for ``pipenv`` as well as with a ``requirements.txt``.
-    Both will install exactly the same requirements. It is up to you if you wish to use a virtual environment or not.
+8.  Install python requirements from the ``requirements.txt`` file.
+    It is up to you if you wish to use a virtual environment or not. First you should update your pip, so it gets the actual packages.
 
-8.  Go to ``/opt/paperless/src``, and execute the following commands:
+    .. code:: shell-session
+
+        sudo -Hu paperless pip3 install --upgrade pip
+
+    .. code:: shell-session
+
+        sudo -Hu paperless pip3 install -r requirements.txt
+
+    This will install all python dependencies in the home directory of
+    the new paperless user.
+
+9.  Go to ``/opt/paperless/src``, and execute the following commands:
 
     .. code:: bash
 
-        # This collects static files from paperless and django.
-        python3 manage.py collectstatic --clear --no-input
-        
         # This creates the database schema.
-        python3 manage.py migrate
+        sudo -Hu paperless python3 manage.py migrate
 
         # This creates your first paperless user
-        python3 manage.py createsuperuser
+        sudo -Hu paperless python3 manage.py createsuperuser
 
-9.  Optional: Test that paperless is working by executing
+10. Optional: Test that paperless is working by executing
 
       .. code:: bash
 
         # This collects static files from paperless and django.
-        python3 manage.py runserver
-    
+        sudo -Hu paperless python3 manage.py runserver
+
     and pointing your browser to http://localhost:8000/.
 
     .. warning::
 
         This is a development server which should not be used in
-        production.
+        production. It is not audited for security and performance
+        is inferior to production ready web servers.
 
     .. hint::
 
         This will not start the consumer. Paperless does this in a
         separate process.
 
-10. Setup systemd services to run paperless automatically. You may
+11. Setup systemd services to run paperless automatically. You may
     use the service definition files included in the ``scripts`` folder
     as a starting point.
 
@@ -323,17 +464,19 @@ writing. Windows is not and will never be supported.
     ``consumer`` script to watch the input folder, and the ``scheduler``
     script to run tasks such as email checking and document consumption.
 
+		The ``socket`` script enables ``gunicorn`` to run on port 80 without
+		root privileges. For this you need to uncomment the ``Require=paperless-webserver.socket``
+		in the ``webserver`` script and configure ``gunicorn`` to listen on port 80 (see ``paperless/gunicorn.conf.py``).
+
+    You may need to adjust the path to the ``gunicorn`` executable. This
+    will be installed as part of the python dependencies, and is either located
+    in the ``bin`` folder of your virtual environment, or in ``~/.local/bin/`` if
+    no virtual environment is used.
+
     These services rely on redis and optionally the database server, but
     don't need to be started in any particular order. The example files
     depend on redis being started. If you use a database server, you should
-    add additinal dependencies.
-
-    .. hint::
-
-        You may optionally set up your preferred web server to serve
-        paperless as a wsgi application directly instead of running the
-        ``webserver`` service. The module containing the wsgi application
-        is named ``paperless.wsgi``.
+    add additional dependencies.
 
     .. caution::
 
@@ -342,10 +485,13 @@ writing. Windows is not and will never be supported.
         however, the documentation of GUnicorn states that you should
         use a proxy server in front of gunicorn instead.
 
-11. Optional: Install a samba server and make the consumption folder
+        For instructions on how to use nginx for that,
+        :ref:`see the instructions below <setup-nginx>`.
+
+12. Optional: Install a samba server and make the consumption folder
     available as a network share.
 
-12. Configure ImageMagick to allow processing of PDF documents. Most distributions have
+13. Configure ImageMagick to allow processing of PDF documents. Most distributions have
     this disabled by default, since PDF documents can contain malware. If
     you don't do this, paperless will fall back to ghostscript for certain steps
     such as thumbnail generation.
@@ -355,21 +501,60 @@ writing. Windows is not and will never be supported.
     .. code::
 
         <policy domain="coder" rights="none" pattern="PDF" />
-    
+
     to
 
     .. code::
 
         <policy domain="coder" rights="read|write" pattern="PDF" />
 
-Migration to paperless-ng
-#########################
+14. Optional: Install the `jbig2enc <https://ocrmypdf.readthedocs.io/en/latest/jbig2.html>`_
+    encoder. This will reduce the size of generated PDF documents. You'll most likely need
+    to compile this by yourself, because this software has been patented until around 2017 and
+    binary packages are not available for most distributions.
 
-At its core, paperless-ng is still paperless and fully compatible. However, some
+Migrating to Paperless-ngx
+##########################
+
+Migration is possible both from Paperless-ng or directly from the 'original' Paperless.
+
+Migrating from Paperless-ng
+===========================
+
+Paperless-ngx is meant to be a drop-in replacement for Paperless-ng and thus upgrading should be
+trivial for most users, especially when using docker. However, as with any major change, it is
+recommended to take a full backup first. Once you are ready, simply change the docker image to
+point to the new source. E.g. if using Docker Compose, edit ``docker-compose.yml`` and change:
+
+.. code::
+
+  image: jonaswinkler/paperless-ng:latest
+
+to
+
+.. code::
+
+  image: ghcr.io/paperless-ngx/paperless-ngx:latest
+
+and then run ``docker-compose up -d`` which will pull the new image recreate the container.
+That's it!
+
+Users who installed with the bare-metal route should also update their Git clone to point to
+``https://github.com/paperless-ngx/paperless-ngx``, e.g. using the command
+``git remote set-url origin https://github.com/paperless-ngx/paperless-ngx`` and then pull the
+lastest version.
+
+Migrating from Paperless
+========================
+
+At its core, paperless-ngx is still paperless and fully compatible. However, some
 things have changed under the hood, so you need to adapt your setup depending on
-how you installed paperless. The important things to keep in mind are as follows.
+how you installed paperless.
 
-* Read the :ref:`changelog <paperless_changelog>` and take note of breaking changes.
+This setup describes how to update an existing paperless Docker installation.
+The important things to keep in mind are as follows:
+
+* 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
@@ -378,10 +563,10 @@ how you installed paperless. The important things to keep in mind are as follows
   such as email checking and maintenance, requires a `redis`_ message broker
   instance. The docker-compose route takes care of that.
 * The layout of the folder structure for your documents and data remains the
-  same, so you can just plug your old docker volumes into paperless-ng and
+  same, so you can just plug your old docker volumes into paperless-ngx and
   expect it to find everything where it should be.
 
-Migration to paperless-ng is then performed in a few simple steps:
+Migration to paperless-ngx is then performed in a few simple steps:
 
 1.  Stop paperless.
 
@@ -391,36 +576,38 @@ Migration to paperless-ng is then performed in a few simple steps:
         $ docker-compose down
 
 2.  Do a backup for two purposes: If something goes wrong, you still have your
-    data. Second, if you don't like paperless-ng, you can switch back to
+    data. Second, if you don't like paperless-ngx, you can switch back to
     paperless.
 
-3.  Download the latest release of paperless-ng. You can either go with the
-    docker-compose files or use the archive to build the image yourself.
-    You can either replace your current paperless folder or put paperless-ng
+3.  Download the latest release of paperless-ngx. You can either go with the
+    docker-compose files from `here <https://github.com/paperless-ngx/paperless-ngx/tree/master/docker/compose>`__
+    or clone the repository to build the image yourself (see :ref:`above <setup-docker_build>`).
+    You can either replace your current paperless folder or put paperless-ngx
     in a different location.
 
     .. caution::
 
-        The release include a ``.env`` file. This will set the
-        project name for docker compose to ``paperless`` so that paperless-ng will
-        automatically reuse your existing paperless volumes. When you start it, it
-        will migrate your existing data. After that, your old paperless installation
-        will be incompatible with the migrated volumes.
+        Paperless-ngx includes a ``.env`` file. This will set the
+        project name for docker compose to ``paperless``, which will also define the name
+        of the volumes by paperless-ngx. However, if you experience that paperless-ngx
+        is not using your old paperless volumes, verify the names of your volumes with
 
-4.  Copy the ``docker-compose.sqlite.yml`` file to ``docker-compose.yml``.
+        .. code:: shell-session
+
+            $ docker volume ls | grep _data
+
+        and adjust the project name in the ``.env`` file so that it matches the name
+        of the volumes before the ``_data`` part.
+
+
+4.  Download the ``docker-compose.sqlite.yml`` file to ``docker-compose.yml``.
     If you want to switch to PostgreSQL, do that after you migrated your existing
     SQLite database.
 
-5.  Adjust ``docker-compose.yml`` and
-    ``docker-compose.env`` to your needs.
-    See `docker route`_ for details on which edits are advised.
+5.  Adjust ``docker-compose.yml`` and ``docker-compose.env`` to your needs.
+    See :ref:`setup-docker_hub` for details on which edits are advised.
 
-6.  Since ``docker-compose`` would just use the the old paperless image, we need to
-    manually build a new image:
-
-    .. code:: shell-session
-
-        $ docker-compose build
+6.  :ref:`Update paperless. <administration-updating>`
 
 7.  In order to find your existing documents with the new search feature, you need
     to invoke a one-time operation that will create the search index:
@@ -428,11 +615,11 @@ Migration to paperless-ng is then performed in a few simple steps:
     .. code:: shell-session
 
         $ docker-compose run --rm webserver document_index reindex
-    
+
     This will migrate your database and create the search index. After that,
     paperless will take care of maintaining the index by itself.
 
-8.  Start paperless-ng.
+8.  Start paperless-ngx.
 
     .. code:: bash
 
@@ -441,7 +628,7 @@ Migration to paperless-ng is then performed in a few simple steps:
     This will run paperless in the background and automatically start it on system boot.
 
 9.  Paperless installed a permanent redirect to ``admin/`` in your browser. This
-    redirect is still in place and prevents access to the new UI. Clear
+    redirect is still in place and prevents access to the new UI. Clear your
     browsing cache in order to fix this.
 
 10.  Optionally, follow the instructions below to migrate your existing data to PostgreSQL.
@@ -489,19 +676,17 @@ management commands as below.
 
             $ cd /path/to/paperless
             $ docker-compose run --rm webserver /bin/bash
-        
+
         This will launch the container and initialize the PostgreSQL database.
-    
-    b)  Without docker, open a shell in your virtual environment, switch to
+
+    b)  Without docker, remember to activate any virtual environment, switch to
         the ``src`` directory and create the database schema:
 
         .. code:: shell-session
 
-            $ cd /path/to/paperless
-            $ pipenv shell
-            $ cd src
+            $ cd /path/to/paperless/src
             $ python3 manage.py migrate
-        
+
         This will not copy any data yet.
 
 4.  Dump your data from SQLite:
@@ -509,14 +694,14 @@ management commands as below.
     .. code:: shell-session
 
         $ python3 manage.py dumpdata --database=sqlite --exclude=contenttypes --exclude=auth.Permission > data.json
-    
+
 5.  Load your data into PostgreSQL:
 
     .. code:: shell-session
 
         $ python3 manage.py loaddata data.json
 
-6.  Exit the shell.
+6.  If operating inside Docker, you may exit the shell now.
 
     .. code:: shell-session
 
@@ -525,14 +710,14 @@ management commands as below.
 7.  Start paperless.
 
 
-Moving back to paperless
+Moving back to Paperless
 ========================
 
-Lets say you migrated to Paperless-ng and used it for a while, but decided that
+Lets say you migrated to Paperless-ngx and used it for a while, but decided that
 you don't like it and want to move back (If you do, send me a mail about what
 part you didn't like!), you can totally do that with a few simple steps.
 
-Paperless-ng modified the database schema slightly, however, these changes can
+Paperless-ngx modified the database schema slightly, however, these changes can
 be reverted while keeping your current data, so that your current data will
 be compatible with original Paperless.
 
@@ -550,7 +735,7 @@ Or without docker:
     $ cd /path/to/paperless/src
     $ python3 manage.py migrate documents 0023
 
-After that, you need to clear your cookies (Paperless-ng comes with updated
+After that, you need to clear your cookies (Paperless-ngx comes with updated
 dependencies that do cookie-processing differently) and probably your cache
 as well.
 
@@ -560,12 +745,13 @@ as well.
 Considerations for less powerful devices
 ########################################
 
-Paperless runs on Raspberry Pi. However, some things are rather slow on the Pi and 
+Paperless runs on Raspberry Pi. However, some things are rather slow on the Pi and
 configuring some options in paperless can help improve performance immensely:
 
 *   Stick with SQLite to save some resources.
 *   Consider setting ``PAPERLESS_OCR_PAGES`` to 1, so that paperless will only OCR
-    the first page of your documents.
+    the first page of your documents. In most cases, this page contains enough
+    information to be able to find it.
 *   ``PAPERLESS_TASK_WORKERS`` and ``PAPERLESS_THREADS_PER_WORKER`` are configured
     to use all cores. The Raspberry Pi models 3 and up have 4 cores, meaning that
     paperless will use 2 workers and 2 threads per worker. This may result in
@@ -576,23 +762,69 @@ configuring some options in paperless can help improve performance immensely:
     your documents before feeding them into paperless. Some scanners are able to
     do this! You might want to even specify ``skip_noarchive`` to skip archive
     file generation for already ocr'ed documents entirely.
-*   Set ``PAPERLESS_OPTIMIZE_THUMBNAILS`` to 'false' if you want faster consumption
-    times. Thumbnails will be about 20% larger.
+*   If you want to perform OCR on the device, consider using ``PAPERLESS_OCR_CLEAN=none``.
+    This will speed up OCR times and use less memory at the expense of slightly worse
+    OCR results.
+*   If using docker, consider setting ``PAPERLESS_WEBSERVER_WORKERS`` to
+    1. This will save some memory.
 
 For details, refer to :ref:`configuration`.
 
 .. note::
-    
+
     Updating the :ref:`automatic matching algorithm <advanced-automatic_matching>`
     takes quite a bit of time. However, the update mechanism checks if your
-    data has changed before doing the heavy lifting. If you experience the 
+    data has changed before doing the heavy lifting. If you experience the
     algorithm taking too much cpu time, consider changing the schedule in the
     admin interface to daily. You can also manually invoke the task
     by changing the date and time of the next run to today/now.
 
-    The actual matching of the algorithm is fast and works on Raspberry Pi as 
+    The actual matching of the algorithm is fast and works on Raspberry Pi as
     well as on any other device.
 
-
-
 .. _redis: https://redis.io/
+
+
+.. _setup-nginx:
+
+Using nginx as a reverse proxy
+##############################
+
+If you want to expose paperless to the internet, you should hide it behind a
+reverse proxy with SSL enabled.
+
+In addition to the usual configuration for SSL,
+the following configuration is required for paperless to operate:
+
+.. code:: nginx
+
+    http {
+
+        # Adjust as required. This is the maximum size for file uploads.
+        # The default value 1M might be a little too small.
+        client_max_body_size 10M;
+
+        server {
+
+            location / {
+
+                # Adjust host and port as required.
+                proxy_pass http://localhost:8000/;
+
+                # These configuration options are required for WebSockets to work.
+                proxy_http_version 1.1;
+                proxy_set_header Upgrade $http_upgrade;
+                proxy_set_header Connection "upgrade";
+
+                proxy_redirect off;
+                proxy_set_header Host $host;
+                proxy_set_header X-Real-IP $remote_addr;
+                proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
+                proxy_set_header X-Forwarded-Host $server_name;
+            }
+        }
+    }
+
+The ``PAPERLESS_URL`` configuration variable is also required when using a reverse proxy. Please refer to the :ref:`hosting-and-security` docs.
+
+Also read `this <https://channels.readthedocs.io/en/stable/deploying.html#nginx-supervisor-ubuntu>`__, towards the end of the section.

docs/troubleshooting.rst

@@ -25,14 +25,39 @@ Check for the following issues:
 *   Go to the admin interface, and check if there are failed tasks. If so, the
     tasks will contain an error message.
 
+Consumer warns ``OCR for XX failed``
+####################################
+
+If you find the OCR accuracy to be too low, and/or the document consumer warns
+that ``OCR for XX failed, but we're going to stick with what we've got since
+FORGIVING_OCR is enabled``, then you might need to install the
+`Tesseract language files <http://packages.ubuntu.com/search?keywords=tesseract-ocr>`_
+marching your document's languages.
+
+As an example, if you are running Paperless-ngx from any Ubuntu or Debian
+box, and your documents are written in Spanish you may need to run::
+
+    apt-get install -y tesseract-ocr-spa
 
 Consumer fails to pickup any new files
 ######################################
 
 If you notice that the consumer will only pickup files in the consumption
-directory at startup, but won't find any other files added later, check out
-the configuration file and enable filesystem polling with the setting
-``PAPERLESS_CONSUMER_POLLING``.
+directory at startup, but won't find any other files added later, you will need to
+enable filesystem polling with the configuration option
+``PAPERLESS_CONSUMER_POLLING``, see :ref:`here <configuration-polling>`.
+
+This will disable listening to filesystem changes with inotify and paperless will
+manually check the consumption directory for changes instead.
+
+
+Paperless always redirects to /admin
+####################################
+
+You probably had the old paperless installed at some point. Paperless installed
+a permanent redirect to /admin in your browser, and you need to clear your
+browsing data / cache to fix that.
+
 
 Operation not permitted
 #######################
@@ -48,7 +73,8 @@ required so that the user running paperless inside docker has write permissions
 to these folders. This happens when pointing these directories to NFS shares,
 for example.
 
-Ensure that `chown` is possible on these directories.
+Ensure that ``chown`` is possible on these directories.
+
 
 Classifier error: No training data available
 ############################################
@@ -61,6 +87,51 @@ This may have two reasons:
     with Inbox tags. Verify that there are documents in your archive without inbox tags.
     The algorithm will only learn from documents not in your inbox.
 
+
+UserWarning in sklearn on every single document
+###############################################
+
+You may encounter warnings like this:
+
+.. code::
+
+    /usr/local/lib/python3.7/site-packages/sklearn/base.py:315:
+    UserWarning: Trying to unpickle estimator CountVectorizer from version 0.23.2 when using version 0.24.0.
+    This might lead to breaking code or invalid results. Use at your own risk.
+
+This happens when certain dependencies of paperless that are responsible for the auto matching algorithm are
+updated. After updating these, your current training data *might* not be compatible anymore. This can be ignored
+in most cases. This warning will disappear automatically when paperless updates the training data.
+
+If you want to get rid of the warning or actually experience issues with automatic matching, delete
+the file ``classification_model.pickle`` in the data directory and let paperless recreate it.
+
+
+504 Server Error: Gateway Timeout when adding Office documents
+##############################################################
+
+You may experience these errors when using the optional TIKA integration:
+
+.. code::
+
+    requests.exceptions.HTTPError: 504 Server Error: Gateway Timeout for url: http://gotenberg:3000/forms/libreoffice/convert
+
+Gotenberg is a server that converts Office documents into PDF documents and has a default timeout of 30 seconds.
+When conversion takes longer, Gotenberg raises this error.
+
+You can increase the timeout by configuring a command flag for Gotenberg (see also `here <https://gotenberg.dev/docs/modules/api#properties>`__).
+If using docker-compose, this is achieved by the following configuration change in the ``docker-compose.yml`` file:
+
+.. code:: yaml
+
+    gotenberg:
+        image: gotenberg/gotenberg:7.4
+        restart: unless-stopped
+        command:
+            - "gotenberg"
+            - "--chromium-disable-routes=true"
+            - "--api-timeout=60"
+
 Permission denied errors in the consumption directory
 #####################################################
 
@@ -72,6 +143,177 @@ You might encounter errors such as:
 
 This happens when paperless does not have permission to delete files inside the consumption directory.
 Ensure that ``USERMAP_UID`` and ``USERMAP_GID`` are set to the user id and group id you use on the host operating system, if these are
-different from ``1000``. See :ref:`setup-docker_route`.
+different from ``1000``. See :ref:`setup-docker_hub`.
 
 Also ensure that you are able to read and write to the consumption directory on the host.
+
+
+OSError: [Errno 19] No such device when consuming files
+#######################################################
+
+If you experience errors such as:
+
+.. code:: shell-session
+
+    File "/usr/local/lib/python3.7/site-packages/whoosh/codec/base.py", line 570, in open_compound_file
+    return CompoundStorage(dbfile, use_mmap=storage.supports_mmap)
+    File "/usr/local/lib/python3.7/site-packages/whoosh/filedb/compound.py", line 75, in __init__
+    self._source = mmap.mmap(fileno, 0, access=mmap.ACCESS_READ)
+    OSError: [Errno 19] No such device
+
+    During handling of the above exception, another exception occurred:
+
+    Traceback (most recent call last):
+    File "/usr/local/lib/python3.7/site-packages/django_q/cluster.py", line 436, in worker
+    res = f(*task["args"], **task["kwargs"])
+    File "/usr/src/paperless/src/documents/tasks.py", line 73, in consume_file
+    override_tag_ids=override_tag_ids)
+    File "/usr/src/paperless/src/documents/consumer.py", line 271, in try_consume_file
+    raise ConsumerError(e)
+
+Paperless uses a search index to provide better and faster full text searching. This search index is stored inside
+the ``data`` folder. The search index uses memory-mapped files (mmap). The above error indicates that paperless
+was unable to create and open these files.
+
+This happens when you're trying to store the data directory on certain file systems (mostly network shares)
+that don't support memory-mapped files.
+
+
+Web-UI stuck at "Loading..."
+############################
+
+This might have multiple reasons.
+
+
+1.  If you built the docker image yourself or deployed using the bare metal route,
+    make sure that there are files in ``<paperless-root>/static/frontend/<lang-code>/``.
+    If there are no files, make sure that you executed ``collectstatic`` successfully, either
+    manually or as part of the docker image build.
+
+    If the front end is still missing, make sure that the front end is compiled (files present in
+    ``src/documents/static/frontend``). If it is not, you need to compile the front end yourself
+    or download the release archive instead of cloning the repository.
+
+2.  Check the output of the web server. You might see errors like this:
+
+
+    .. code::
+
+        [2021-01-25 10:08:04 +0000] [40] [ERROR] Socket error processing request.
+        Traceback (most recent call last):
+        File "/usr/local/lib/python3.7/site-packages/gunicorn/workers/sync.py", line 134, in handle
+            self.handle_request(listener, req, client, addr)
+        File "/usr/local/lib/python3.7/site-packages/gunicorn/workers/sync.py", line 190, in handle_request
+            util.reraise(*sys.exc_info())
+        File "/usr/local/lib/python3.7/site-packages/gunicorn/util.py", line 625, in reraise
+            raise value
+        File "/usr/local/lib/python3.7/site-packages/gunicorn/workers/sync.py", line 178, in handle_request
+            resp.write_file(respiter)
+        File "/usr/local/lib/python3.7/site-packages/gunicorn/http/wsgi.py", line 396, in write_file
+            if not self.sendfile(respiter):
+        File "/usr/local/lib/python3.7/site-packages/gunicorn/http/wsgi.py", line 386, in sendfile
+            sent += os.sendfile(sockno, fileno, offset + sent, count)
+        OSError: [Errno 22] Invalid argument
+
+    To fix this issue, add
+
+    .. code::
+
+        SENDFILE=0
+
+    to your `docker-compose.env` file.
+
+Error while reading metadata
+############################
+
+You might find messages like these in your log files:
+
+.. code::
+
+    [WARNING] [paperless.parsing.tesseract] Error while reading metadata
+
+This indicates that paperless failed to read PDF metadata from one of your documents. This happens when you
+open the affected documents in paperless for editing. Paperless will continue to work, and will simply not
+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
+        ocrmypdf.ocr(**args)
+      File "/usr/local/lib/python3.8/dist-packages/ocrmypdf/api.py", line 337, in ocr
+        return run_pipeline(options=options, plugin_manager=plugin_manager, api=True)
+      File "/usr/local/lib/python3.8/dist-packages/ocrmypdf/_sync.py", line 385, in run_pipeline
+        exec_concurrent(context, executor)
+      File "/usr/local/lib/python3.8/dist-packages/ocrmypdf/_sync.py", line 302, in exec_concurrent
+        pdf = post_process(pdf, context, executor)
+      File "/usr/local/lib/python3.8/dist-packages/ocrmypdf/_sync.py", line 235, in post_process
+        pdf_out = metadata_fixup(pdf_out, context)
+      File "/usr/local/lib/python3.8/dist-packages/ocrmypdf/_pipeline.py", line 798, in metadata_fixup
+        with pikepdf.open(context.origin) as original, pikepdf.open(working_file) as pdf:
+      File "/usr/local/lib/python3.8/dist-packages/pikepdf/_methods.py", line 923, in open
+        pdf = Pdf._open(
+    FileNotFoundError: [Errno 2] No such file or directory: '/tmp/ocrmypdf.io.yhk3zbv0/origin.pdf'
+
+This probably indicates paperless tried to consume the same file twice.  This can happen for a number of reasons,
+depending on how documents are placed into the consume folder.  If paperless is using inotify (the default) to
+check for documents, try adjusting the :ref:`inotify configuration <configuration-inotify>`.  If polling is enabled,
+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.
+Adjusting :ref:`polling configuration <configuration-polling>` values should resolve the issue.
+
+.. note::
+
+    The user will need to manually move the file out of the consume folder and
+    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
+crash, paperless did not try to consume the file.  If paperless is using inotify (the default) to
+check for documents, try adjusting the :ref:`inotify configuration <configuration-inotify>`.  If polling is enabled,
+try adjusting the :ref:`polling configuration <configuration-polling>`.
+
+.. note::
+
+    The user will need to manually move the file out of the consume folder and
+    back in, for the initial failing file to be consumed.
+
+Log reports "Creating PaperlessTask failed".
+#########################################################
+
+You might find messages like these in your log files:
+
+.. code::
+
+    [ERROR] [paperless.management.consumer] Creating PaperlessTask failed: db locked
+
+You are likely using an sqlite based installation, with an increased number of workers and are running into sqlite's concurrency limitations.
+Uploading or consuming multiple files at once results in many workers attempting to access the database simultaneously.
+
+Consider changing to the PostgreSQL database if you will be processing many documents at once often.  Otherwise,
+try tweaking the ``PAPERLESS_DB_TIMEOUT`` setting to allow more time for the database to unlock.  This may have
+minor performance implications.