Bumps version number to 1.10.0

[Beta] Paperless-ngx v1.10.0 Release Candidate

.build-config.json

@@ -0,0 +1,9 @@
+{
+  "qpdf": {
+      "version": "11.1.1"
+    },
+  "jbig2enc": {
+      "version": "0.29",
+      "git_tag": "0.29"
+    }
+}

.dockerignore

@@ -17,3 +17,5 @@
 **/htmlcov
 /src/.pytest_cache
 .idea
+.venv/
+.vscode/

.editorconfig

@@ -18,14 +18,23 @@ 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
 # the 79 character rule, but in the interests of clarity, tests often need to
 # violate it.
 [**/test_*.py]
 max_line_length = off
+
+[Dockerfile*]
+indent_style = space

.github/ISSUE_TEMPLATE/bug-report.yml

@@ -0,0 +1,97 @@
+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).
+        - Disable any customer container initialization scripts, if using any
+
+        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: Logs from the web server related to your issue.
+      render: bash
+    validations:
+      required: true
+  - type: textarea
+    id: logs_browser
+    attributes:
+      label: Browser logs
+      description: Logs from the web browser related to your issue, if needed
+      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/bug_report.md

@@ -1,48 +0,0 @@
----
-name: Bug report
-about: Something is not working
-title: "[BUG] Concise description of the issue"
-labels: ''
-assignees: ''
-
----
-
-<!---
-=> Before opening an issue, please check the documentation and see if it helps you resolve your issue: https://paperless-ngx.readthedocs.io/en/latest/troubleshooting.html
-=> Please also make sure that you followed the installation instructions.
-=> Please search the issues and look for similar issues before opening a bug report.
-
-=> If you would like to submit a feature request please submit one under https://github.com/paperless-ngx/paperless-ngx/discussions/categories/feature-requests
-
-=> If you encounter issues while installing of configuring Paperless-ngx, please post that in the "Support" section of the discussions. Remember that Paperless successfully runs on a variety of different systems. If paperless does not start, it's probably an issue with your system, and not an issue of paperless.
-
-=> Don't remove the [BUG] prefix from the title.
--->
-
-**Describe the bug**
-A clear and concise description of what the bug is.
-
-**To Reproduce**
-Steps to reproduce the behavior:
-1. Go to '...'
-2. Click on '....'
-3. Scroll down to '....'
-4. See error
-
-**Expected behavior**
-A clear and concise description of what you expected to happen.
-
-**Screenshots**
-If applicable, add screenshots to help explain your problem.
-
-**Webserver logs**
-```
-If available, post any logs from the web server related to your issue.
-```
-
-**Relevant information**
- - Host OS of the machine running paperless: [e.g. Archlinux / Ubuntu 20.04]
- - Browser [e.g. chrome, safari]
- - Version [e.g. 1.0.0]
- - Installation method: [docker / bare metal]
- - Any configuration changes you made in `docker-compose.yml`, `docker-compose.env` or `paperless.conf`.

.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/ISSUE_TEMPLATE/other.md

@@ -1,20 +0,0 @@
----
-name: Other
-about: Anything that is not a feature request or bug.
-title: "[Other] Title of your issue"
-labels: ''
-assignees: ''
-
----
-
-<!--
-
-=> Discussions, Feedback and other suggestions belong in the "Discussion" section and not on the issue tracker.
-
-=> If you would like to submit a feature request please submit one under https://github.com/paperless-ngx/paperless-ngx/discussions/categories/feature-requests
-
-=> If you encounter issues while installing of configuring Paperless-ngx, please post that in the "Support" section of the discussions. Remember that Paperless successfully runs on a variety of different systems. If paperless does not start, it's probably is an issue with your system, and not an issue of paperless.
-
-=> Don't remove the [Other] prefix from the title.
-
--->

.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

@@ -6,11 +6,17 @@ updates:
   # Enable version updates for npm
   - package-ecosystem: "npm"
     target-branch: "dev"
-    # Look for `package.json` and `lock` files in the `root` directory
+    # Look for `package.json` and `lock` files in the `/src-ui` directory
     directory: "/src-ui"
-    # Check the npm registry for updates every week
+    # Check the npm registry for updates every month
     schedule:
-      interval: "weekly"
+      interval: "monthly"
+    labels:
+      - "frontend"
+      - "dependencies"
+    # Add reviewers
+    reviewers:
+      - "paperless-ngx/frontend"
 
   # Enable version updates for Python
   - package-ecosystem: "pip"
@@ -20,3 +26,23 @@ updates:
     # 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 +1,402 @@
+#!/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 typing import Optional
+
+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}"
+
+
+class RegistryTagsCleaner:
+    """
+    This is the base class for the image registry cleaning.  Given a package
+    name, it will keep all images which are tagged and all untagged images
+    referred to by a manifest.  This results in only images which have been untagged
+    and cannot be referenced except by their SHA in being removed.  None of these
+    images should be referenced, so it is fine to delete them.
+    """
+
+    def __init__(
+        self,
+        package_name: str,
+        repo_owner: str,
+        repo_name: str,
+        package_api: GithubContainerRegistryApi,
+        branch_api: Optional[GithubBranchApi],
+    ):
+        self.actually_delete = False
+        self.package_api = package_api
+        self.branch_api = branch_api
+        self.package_name = package_name
+        self.repo_owner = repo_owner
+        self.repo_name = repo_name
+        self.tags_to_delete: List[str] = []
+        self.tags_to_keep: List[str] = []
+
+        # Get the information about all versions of the given package
+        # These are active, not deleted, the default returned from the API
+        self.all_package_versions = self.package_api.get_active_package_versions(
+            self.package_name,
+        )
+
+        # Get a mapping from a tag like "1.7.0" or "feature-xyz" to the ContainerPackage
+        # tagged with it.  It makes certain lookups easy
+        self.all_pkgs_tags_to_version: Dict[str, ContainerPackage] = {}
+        for pkg in self.all_package_versions:
+            for tag in pkg.tags:
+                self.all_pkgs_tags_to_version[tag] = pkg
+        logger.info(
+            f"Located {len(self.all_package_versions)} versions of package {self.package_name}",
+        )
+
+        self.decide_what_tags_to_keep()
+
+    def clean(self):
+        """
+        This method will delete image versions, based on the selected tags to delete
+        """
+        for tag_to_delete in self.tags_to_delete:
+            package_version_info = self.all_pkgs_tags_to_version[tag_to_delete]
+
+            if self.actually_delete:
+                logger.info(
+                    f"Deleting {tag_to_delete} (id {package_version_info.id})",
+                )
+                self.package_api.delete_package_version(
+                    package_version_info,
+                )
+
+            else:
+                logger.info(
+                    f"Would delete {tag_to_delete} (id {package_version_info.id})",
+                )
+        else:
+            logger.info("No tags to delete")
+
+    def clean_untagged(self, is_manifest_image: bool):
+        """
+        This method will delete untagged images, that is those which are not named.  It
+        handles if the image tag is actually a manifest, which points to images that look otherwise
+        untagged.
+        """
+
+        def _clean_untagged_manifest():
+            """
+
+            Handles the deletion of untagged images, but where the package is a manifest, ie a multi
+            arch image, which means some "untagged" images need to exist still.
+
+            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
+            # At the moment, these are the images which APPEAR untagged.
+            untagged_versions = {}
+            for x in self.all_package_versions:
+                if x.untagged:
+                    untagged_versions[x.name] = x
+
+            skips = 0
+
+            # Parse manifests to locate digests pointed to
+            for tag in sorted(self.tags_to_keep):
+                full_name = f"ghcr.io/{self.repo_owner}/{self.package_name}:{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.info(
+                                f"Skipping deletion of {manifest.digest},"
+                                f" referred to by {full_name}"
+                                f" for {manifest.platform}",
+                            )
+                            del untagged_versions[manifest.digest]
+                            skips += 1
+
+                except Exception as err:
+                    self.actually_delete = False
+                    logger.exception(err)
+                    return
+
+            logger.info(
+                f"Skipping deletion of {skips} packages referred to by a manifest",
+            )
+
+            # Delete the untagged and not pointed at packages
+            logger.info(f"Deleting untagged packages of {self.package_name}")
+            for to_delete_name in untagged_versions:
+                to_delete_version = untagged_versions[to_delete_name]
+
+                if self.actually_delete:
+                    logger.info(
+                        f"Deleting id {to_delete_version.id} named {to_delete_version.name}",
+                    )
+                    self.package_api.delete_package_version(
+                        to_delete_version,
+                    )
+                else:
+                    logger.info(
+                        f"Would delete {to_delete_name} (id {to_delete_version.id})",
+                    )
+
+        def _clean_untagged_non_manifest():
+            """
+            If the package is not a multi-arch manifest, images without tags are safe to delete.
+            """
+
+            for package in self.all_package_versions:
+                if package.untagged:
+                    if self.actually_delete:
+                        logger.info(
+                            f"Deleting id {package.id} named {package.name}",
+                        )
+                        self.package_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 {self.package_name}",
+                    )
+
+        logger.info("Beginning untagged image cleaning")
+
+        if is_manifest_image:
+            _clean_untagged_manifest()
+        else:
+            _clean_untagged_non_manifest()
+
+    def decide_what_tags_to_keep(self):
+        """
+        This method holds the logic to delete what tags to keep and there fore
+        what tags to delete.
+
+        By default, any image with at least 1 tag will be kept
+        """
+        # By default, keep anything which is tagged
+        self.tags_to_keep = list(set(self.all_pkgs_tags_to_version.keys()))
+
+
+class MainImageTagsCleaner(RegistryTagsCleaner):
+    def decide_what_tags_to_keep(self):
+        """
+        Overrides the default logic for deciding what images to keep.  Images tagged as "feature-"
+        will be removed, if the corresponding branch no longer exists.
+        """
+
+        # Default to everything gets kept still
+        super().decide_what_tags_to_keep()
+
+        # Locate the feature branches
+        feature_branches = {}
+        for branch in self.branch_api.get_branches(
+            repo=self.repo_name,
+        ):
+            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")
+
+        if not len(feature_branches):
+            # Our work here is done, delete nothing
+            return
+
+        # Filter to packages which are tagged with feature-*
+        packages_tagged_feature: List[ContainerPackage] = []
+        for package in self.all_package_versions:
+            if package.tag_matches("feature-"):
+                packages_tagged_feature.append(package)
+
+        # Map tags like "feature-xyz" to a ContainerPackage
+        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 {self.package_name} tagged "feature-"',
+        )
+
+        # All the feature tags minus all the feature branches leaves us feature tags
+        # with no corresponding branch
+        self.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
+        self.tags_to_keep = list(
+            set(self.all_pkgs_tags_to_version.keys()) - set(self.tags_to_delete),
+        )
+        logger.info(
+            f"Located {len(self.tags_to_delete)} versions of package {self.package_name} to delete",
+        )
+
+
+class LibraryTagsCleaner(RegistryTagsCleaner):
+    """
+    Exists for the off change that someday, the installer library images
+    will need their own logic
+    """
+
+    pass
+
+
+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:
+        with GithubContainerRegistryApi(gh_token, repo_owner) as container_api:
+            if args.package in {"paperless-ngx", "paperless-ngx/builder/cache/app"}:
+                cleaner = MainImageTagsCleaner(
+                    args.package,
+                    repo_owner,
+                    repo,
+                    container_api,
+                    branch_api,
+                )
+            else:
+                cleaner = LibraryTagsCleaner(
+                    args.package,
+                    repo_owner,
+                    repo,
+                    container_api,
+                    None,
+                )
+
+            # Set if actually doing a delete vs dry run
+            cleaner.actually_delete = args.delete
+
+            # Clean images with tags
+            cleaner.clean()
+
+            # Clean images which are untagged
+            cleaner.clean_untagged(args.is_manifest)
+
+
+if __name__ == "__main__":
+    _main()

.github/scripts/common.py

@@ -0,0 +1,48 @@
+#!/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:
+    """
+    Returns a logging level, based
+    :param args:
+    :return:
+    """
+    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 +1,274 @@
+#!/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 httpx
+
+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._client: Optional[httpx.Client] = None
+
+    def __enter__(self) -> "_GithubApiBase":
+        """
+        Sets up the required headers for auth and response
+        type from the API
+        """
+        self._client = httpx.Client()
+        self._client.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._client.headers:
+            del self._client.headers["Accept"]
+        if "Authorization" in self._client.headers:
+            del self._client.headers["Authorization"]
+
+        # Close the session as well
+        self._client.close()
+        self._client = 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._client.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}")
+                resp.raise_for_status()
+
+        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.
+        """
+        # The environment GITHUB_REPOSITORY already contains the owner in the correct location
+        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}"
+        self._PACKAGE_VERSION_RESTORE_ENDPOINT = (
+            f"{self._PACKAGE_VERSION_DELETE_ENDPOINT}/restore"
+        )
+
+    def get_active_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 get_deleted_package_versions(
+        self,
+        package_name: str,
+    ) -> List[ContainerPackage]:
+        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,
+            )
+            + "?state=deleted"
+        )
+
+        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._client.delete(package_data.url)
+        if resp.status_code != 204:
+            logger.warning(
+                f"Request to delete {package_data.url} returned HTTP {resp.status_code}",
+            )
+
+    def restore_package_version(
+        self,
+        package_name: str,
+        package_data: ContainerPackage,
+    ):
+        package_type: str = "container"
+        endpoint = self._PACKAGE_VERSION_RESTORE_ENDPOINT.format(
+            ORG=self._owner_or_org,
+            PACKAGE_TYPE=package_type,
+            PACKAGE_NAME=package_name,
+            PACKAGE_VERSION_ID=package_data.id,
+        )
+
+        resp = self._client.post(endpoint)
+        if resp.status_code != 204:
+            logger.warning(
+                f"Request to delete {endpoint} returned HTTP {resp.status_code}",
+            )

.github/stale.yml

@@ -1,18 +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
-# Issues with these labels will never be considered stale
-exemptLabels:
-  - pinned
-  - security
-  - fixpending
+
+# 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

@@ -3,8 +3,10 @@ name: ci
 on:
   push:
     tags:
-      - ngx-*
-      - beta-*
+      # 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:
@@ -12,281 +14,442 @@ on:
       - '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@v2
+        uses: actions/checkout@v3
+      -
+        name: Install pipenv
+        run: |
+          pipx install pipenv==2022.10.12
       -
         name: Set up Python
-        uses: actions/setup-python@v2
+        uses: actions/setup-python@v4
         with:
           python-version: 3.9
-      -
-        name: Get pip cache dir
-        id: pip-cache
-        run: |
-          echo "::set-output name=dir::$(pip cache dir)"
-      -
-        name: Persistent Github pip cache
-        uses: actions/cache@v2
-        with:
-          path: ${{ steps.pip-cache.outputs.dir }}
-          key: ${{ runner.os }}-pip3.8}
+          cache: "pipenv"
+          cache-dependency-path: 'Pipfile.lock'
       -
         name: Install dependencies
         run: |
-          pip install --upgrade pipenv
-          pipenv install --system --dev --ignore-pipfile
+          pipenv sync --dev
+      -
+        name: List installed Python dependencies
+        run: |
+          pipenv run pip list
       -
         name: Make documentation
         run: |
           cd docs/
-          make html
+          pipenv run make html
       -
         name: Upload artifact
-        uses: actions/upload-artifact@v2
+        uses: actions/upload-artifact@v3
         with:
           name: documentation
           path: docs/_build/html/
 
-  codestyle:
-    runs-on: ubuntu-20.04
-    steps:
-      -
-        name: Checkout
-        uses: actions/checkout@v2
-      -
-        name: Set up Python
-        uses: actions/setup-python@v2
-        with:
-          python-version: 3.9
-      -
-        name: Get pip cache dir
-        id: pip-cache
-        run: |
-          echo "::set-output name=dir::$(pip cache dir)"
-      -
-        name: Persistent Github pip cache
-        uses: actions/cache@v2
-        with:
-          path: ${{ steps.pip-cache.outputs.dir }}
-          key: ${{ runner.os }}-pip${{ matrix.python-version }}
-      -
-        name: Install dependencies
-        run: |
-          pip install --upgrade pipenv
-          pipenv install --system --dev --ignore-pipfile
-      -
-        name: Codestyle
-        run: |
-          cd src/
-          pycodestyle --max-line-length=88 --ignore=E121,E123,E126,E226,E24,E704,W503,W504,E203
-  codeformatting:
-    runs-on: ubuntu-20.04
-    steps:
-      -
-        name: Checkout
-        uses: actions/checkout@v2
-      -
-        name: Run black
-        uses: psf/black@stable
-        with:
-          options: "--check --diff"
-          version: "22.1.0"
-
-  tests:
+  tests-backend:
+    name: "Tests (${{ matrix.python-version }})"
     runs-on: ubuntu-20.04
+    needs:
+      - pre-commit
     strategy:
       matrix:
-        python-version: ['3.8', '3.9']
+        python-version: ['3.8', '3.9', '3.10']
       fail-fast: false
+    services:
+      tika:
+        image: ghcr.io/paperless-ngx/tika:latest
+        ports:
+          - "9998:9998/tcp"
+      gotenberg:
+        image: docker.io/gotenberg/gotenberg:7.6
+        ports:
+          - "3000:3000/tcp"
+    env:
+      # Enable Tika end to end testing
+      TIKA_LIVE: 1
+      # Enable paperless_mail testing against real server
+      PAPERLESS_MAIL_TEST_HOST: ${{ secrets.TEST_MAIL_HOST }}
+      PAPERLESS_MAIL_TEST_USER: ${{ secrets.TEST_MAIL_USER }}
+      PAPERLESS_MAIL_TEST_PASSWD: ${{ secrets.TEST_MAIL_PASSWD }}
     steps:
       -
         name: Checkout
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+      -
+        name: Install pipenv
+        run: |
+          pipx install pipenv==2022.10.12
       -
         name: Set up Python
-        uses: actions/setup-python@v2
+        uses: actions/setup-python@v4
         with:
           python-version: "${{ matrix.python-version }}"
+          cache: "pipenv"
+          cache-dependency-path: 'Pipfile.lock'
       -
-        name: Get pip cache dir
-        id: pip-cache
-        run: |
-          echo "::set-output name=dir::$(pip cache dir)"
-      -
-        name: Persistent Github pip cache
-        uses: actions/cache@v2
-        with:
-          path: ${{ steps.pip-cache.outputs.dir }}
-          key: ${{ runner.os }}-pip${{ matrix.python-version }}
-      -
-        name: Install dependencies
+        name: Install system dependencies
         run: |
           sudo apt-get update -qq
-          sudo apt-get install -qq --no-install-recommends unpaper tesseract-ocr imagemagick ghostscript optipng
-          pip install --upgrade pipenv
-          pipenv install --system --dev --ignore-pipfile
+          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/
-          pytest
+          pipenv run pytest -rfEp
+      -
+        name: Get changed files
+        id: changed-files-specific
+        uses: tj-actions/changed-files@v34
+        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'
+        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/
-          coveralls --service=github
+          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($0) }')
+          echo "repository=${ghcr_name}" >> $GITHUB_OUTPUT
+      -
+        name: Checkout
+        uses: actions/checkout@v3
+      -
+        name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.9"
+      -
+        name: Setup qpdf image
+        id: qpdf-setup
+        run: |
+          build_json=$(python ${GITHUB_WORKSPACE}/.github/scripts/get-build-json.py qpdf)
+
+          echo ${build_json}
+
+          echo "qpdf-json=${build_json}" >> $GITHUB_OUTPUT
+      -
+        name: Setup psycopg2 image
+        id: psycopg2-setup
+        run: |
+          build_json=$(python ${GITHUB_WORKSPACE}/.github/scripts/get-build-json.py psycopg2)
+
+          echo ${build_json}
+
+          echo "psycopg2-json=${build_json}" >> $GITHUB_OUTPUT
+      -
+        name: Setup pikepdf image
+        id: pikepdf-setup
+        run: |
+          build_json=$(python ${GITHUB_WORKSPACE}/.github/scripts/get-build-json.py pikepdf)
+
+          echo ${build_json}
+
+          echo "pikepdf-json=${build_json}" >> $GITHUB_OUTPUT
+      -
+        name: Setup jbig2enc image
+        id: jbig2enc-setup
+        run: |
+          build_json=$(python ${GITHUB_WORKSPACE}/.github/scripts/get-build-json.py jbig2enc)
+
+          echo ${build_json}
+
+          echo "jbig2enc-json=${build_json}" >> $GITHUB_OUTPUT
+
+    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:
-    if: github.event_name == 'push' && (startsWith(github.ref, 'refs/heads/feature-') || github.ref == 'refs/heads/dev' || github.ref == 'refs/heads/beta' || startsWith(github.ref, 'refs/tags/ngx-') || startsWith(github.ref, 'refs/tags/beta-'))
-    runs-on: ubuntu-latest
-    needs: [tests, codeformatting, codestyle]
+    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: Prepare
-        id: prepare
+        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: |
-          IMAGE_NAME=ghcr.io/${{ github.repository }}
-          if [[ $GITHUB_REF == refs/tags/ngx-* ]]; then
-            TAGS=${IMAGE_NAME}:${GITHUB_REF#refs/tags/ngx-},${IMAGE_NAME}:latest
-            INSPECT_TAG=${IMAGE_NAME}:latest
-          elif [[ $GITHUB_REF == refs/tags/beta-* ]]; then
-            TAGS=${IMAGE_NAME}:beta
-            INSPECT_TAG=${TAGS}
-          elif [[ $GITHUB_REF == refs/heads/* ]]; then
-            TAGS=${IMAGE_NAME}:${GITHUB_REF#refs/heads/}
-            INSPECT_TAG=${TAGS}
+          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 "enable=true" >> $GITHUB_OUTPUT
           else
-            exit 1
+            echo "Not pushing to DockerHub"
+            echo "enable=false" >> $GITHUB_OUTPUT
           fi
-          echo ::set-output name=tags::${TAGS}
-          echo ::set-output name=inspect_tag::${INSPECT_TAG}
+      -
+        name: Gather Docker metadata
+        id: docker-meta
+        uses: docker/metadata-action@v4
+        with:
+          images: |
+            ghcr.io/${{ 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@v2
+        uses: actions/checkout@v3
       -
         name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v1
+        uses: docker/setup-buildx-action@v2
       -
         name: Set up QEMU
-        uses: docker/setup-qemu-action@v1
+        uses: docker/setup-qemu-action@v2
       -
         name: Login to Github Container Registry
-        uses: docker/login-action@v1
+        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@v2
+        uses: docker/build-push-action@v3
         with:
           context: .
           file: ./Dockerfile
           platforms: linux/amd64,linux/arm/v7,linux/arm64
-          push: true
-          tags: ${{ steps.prepare.outputs.tags }}
-          cache-from: type=gha
-          cache-to: type=gha,mode=max
+          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 ${{ steps.prepare.outputs.inspect_tag }}
+          docker buildx imagetools inspect ${{ fromJSON(steps.docker-meta.outputs.json).tags[0] }}
       -
         name: Export frontend artifact from docker
         run: |
-          docker run -d --name frontend-extract ${{ steps.prepare.outputs.tags }}
+          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@v2
+        uses: actions/upload-artifact@v3
         with:
           name: frontend-compiled
           path: src/documents/static/frontend/
 
   build-release:
-    needs: [build-docker-image, documentation, tests, codeformatting, codestyle]
+    needs:
+      - build-docker-image
     runs-on: ubuntu-20.04
     steps:
       -
         name: Checkout
-        uses: actions/checkout@v2
+        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@v2
+        uses: actions/setup-python@v4
         with:
           python-version: 3.9
+          cache: "pipenv"
+          cache-dependency-path: 'Pipfile.lock'
       -
-        name: Install dependencies
+        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
-          pip3 install --upgrade pip setuptools wheel
-          pip3 install -r requirements.txt
       -
         name: Download frontend artifact
-        uses: actions/download-artifact@v2
+        uses: actions/download-artifact@v3
         with:
           name: frontend-compiled
           path: src/documents/static/frontend/
       -
         name: Download documentation artifact
-        uses: actions/download-artifact@v2
+        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 LICENSE README.md requirements.txt dist/paperless-ngx/
+          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 docker/ dist/paperless-ngx/docker -r
+          cp -r docker/ dist/paperless-ngx/docker
           cp scripts/*.service scripts/*.sh dist/paperless-ngx/scripts/
-          cp src/ dist/paperless-ngx/src -r
-          cp docs/_build/html/ dist/paperless-ngx/docs -r
-      -
-        name: Compile messages
-        run: |
-          cd dist/paperless-ngx/src
-          python3 manage.py compilemessages
-      -
-        name: Collect static files
-        run: |
-          cd dist/paperless-ngx/src
-          python3 manage.py collectstatic --no-input
+          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
-          find . -name __pycache__ | xargs rm -r
           tar -cJf paperless-ngx.tar.xz paperless-ngx/
       -
         name: Upload release artifact
-        uses: actions/upload-artifact@v2
+        uses: actions/upload-artifact@v3
         with:
           name: release
           path: dist/paperless-ngx.tar.xz
 
   publish-release:
-    runs-on: ubuntu-latest
-    needs: build-release
-    if: contains(github.ref, 'refs/tags/ngx-') || contains(github.ref, 'refs/tags/beta-')
+    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@v2
+        uses: actions/download-artifact@v3
         with:
           name: release
           path: ./
@@ -294,26 +457,24 @@ jobs:
         name: Get version
         id: get_version
         run: |
-          if [[ $GITHUB_REF == refs/tags/ngx-* ]]; then
-            echo ::set-output name=version::${GITHUB_REF#refs/tags/ngx-}
-            echo ::set-output name=prerelease::false
-          elif [[ $GITHUB_REF == refs/tags/beta-* ]]; then
-            echo ::set-output name=version::${GITHUB_REF#refs/tags/beta-}
-            echo ::set-output name=prerelease::true
+          echo "version=${{ github.ref_name }}" >> $GITHUB_OUTPUT
+          if [[ ${{ contains(github.ref_name, '-beta.rc') }} == 'true' ]]; then
+            echo "prerelease=true" >> $GITHUB_OUTPUT
+          else
+            echo "prerelease=false" >> $GITHUB_OUTPUT
           fi
       -
-        name: Create release
-        id: create_release
-        uses: actions/create-release@v1
+        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: ${{ secrets.GITHUB_TOKEN }}
-        with:
-          tag_name: ngx-${{ steps.get_version.outputs.version }}
-          release_name: Paperless-ngx ${{ steps.get_version.outputs.version }}
-          draft: false
-          prerelease: ${{ steps.get_version.outputs.prerelease }}
-          body: |
-            For a complete list of changes, see the changelog at https://paperless-ngx.readthedocs.io/en/latest/changelog.html.
       -
         name: Upload release archive
         id: upload-release-asset
@@ -321,7 +482,69 @@ jobs:
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
         with:
-          upload_url: ${{ steps.create_release.outputs.upload_url }} # This pulls from the CREATE RELEASE step above, referencing it's ID to get its outputs object, which include a `upload_url`. See this blog post for more info: https://jasonet.co/posts/new-features-of-github-actions/#passing-data-to-future-steps
+          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: 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: 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
+          pipenv run pre-commit --files 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 ${{ needs.publish-release.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 +1,95 @@
+# 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"
+
+concurrency:
+  group: registry-tags-cleanup
+  cancel-in-progress: false
+
+jobs:
+  cleanup-images:
+    name: Cleanup Image Tags for ${{ matrix.primary-name }}
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        include:
+          - primary-name: "paperless-ngx"
+            cache-name: "paperless-ngx/builder/cache/app"
+
+          - primary-name: "paperless-ngx/builder/qpdf"
+            cache-name: "paperless-ngx/builder/cache/qpdf"
+
+          - primary-name: "paperless-ngx/builder/pikepdf"
+            cache-name: "paperless-ngx/builder/cache/pikepdf"
+
+          - primary-name: "paperless-ngx/builder/jbig2enc"
+            cache-name: "paperless-ngx/builder/cache/jbig2enc"
+
+          - primary-name: "paperless-ngx/builder/psycopg2"
+            cache-name: "paperless-ngx/builder/cache/psycopg2"
+    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@v2
+        with:
+          registry: ghcr.io
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+      -
+        name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.10"
+      -
+        name: Install httpx
+        run: |
+          python -m pip install httpx
+      #
+      # Clean up primary package
+      #
+      -
+        name: Cleanup for package "${{ matrix.primary-name }}"
+        if: "${{ env.TOKEN != '' }}"
+        run: |
+          python ${GITHUB_WORKSPACE}/.github/scripts/cleanup-tags.py --untagged --is-manifest --delete "${{ matrix.primary-name }}"
+      #
+      # Clean up registry cache package
+      #
+      -
+        name: Cleanup for package "${{ matrix.cache-name }}"
+        if: "${{ env.TOKEN != '' }}"
+        run: |
+          python ${GITHUB_WORKSPACE}/.github/scripts/cleanup-tags.py --untagged --delete "${{ matrix.cache-name }}"
+      #
+      # Verify tags which are left still pull
+      #
+      -
+        name: Check all tags still pull
+        run: |
+          ghcr_name=$(echo "ghcr.io/${GITHUB_REPOSITORY_OWNER}/${{ matrix.primary-name }}" | awk '{ print tolower($0) }')
+          echo "Pulling all tags of ${ghcr_name}"
+          docker pull --quiet --all-tags ${ghcr_name}
+          docker image list

.github/workflows/codeql-analysis.yml

@@ -38,11 +38,11 @@ jobs:
 
     steps:
     - name: Checkout repository
-      uses: actions/checkout@v2
+      uses: actions/checkout@v3
 
     # Initializes the CodeQL tools for scanning.
     - name: Initialize CodeQL
-      uses: github/codeql-action/init@v1
+      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.
@@ -51,4 +51,4 @@ jobs:
         # queries: ./path/to/local/query, your-org/your-repo/queries@main
 
     - name: Perform CodeQL Analysis
-      uses: github/codeql-action/analyze@v1
+      uses: github/codeql-action/analyze@v2

.github/workflows/installer-library.yml

@@ -0,0 +1,170 @@
+# 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($0) }')
+          echo "repository=${ghcr_name}" >> $GITHUB_OUTPUT
+      -
+        name: Checkout
+        uses: actions/checkout@v3
+      -
+        name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.9"
+      -
+        name: Install jq
+        run: |
+          sudo apt-get update
+          sudo apt-get install jq
+      -
+        name: Setup qpdf image
+        id: qpdf-setup
+        run: |
+          build_json=$(python ${GITHUB_WORKSPACE}/.github/scripts/get-build-json.py qpdf)
+
+          echo ${build_json}
+
+          echo "qpdf-json=${build_json}" >> $GITHUB_OUTPUT
+      -
+        name: Setup psycopg2 image
+        id: psycopg2-setup
+        run: |
+          build_json=$(python ${GITHUB_WORKSPACE}/.github/scripts/get-build-json.py psycopg2)
+
+          echo ${build_json}
+
+          echo "psycopg2-json=${build_json}" >> $GITHUB_OUTPUT
+      -
+        name: Setup pikepdf image
+        id: pikepdf-setup
+        run: |
+          build_json=$(python ${GITHUB_WORKSPACE}/.github/scripts/get-build-json.py pikepdf)
+
+          echo ${build_json}
+
+          echo "pikepdf-json=${build_json}" >> $GITHUB_OUTPUT
+      -
+        name: Setup jbig2enc image
+        id: jbig2enc-setup
+        run: |
+          build_json=$(python ${GITHUB_WORKSPACE}/.github/scripts/get-build-json.py jbig2enc)
+
+          echo ${build_json}
+
+          echo "jbig2enc-json=${build_json}" >> $GITHUB_OUTPUT
+      -
+        name: Setup other versions
+        id: cache-bust-setup
+        run: |
+          pillow_version=$(jq ".default.pillow.version" Pipfile.lock | sed 's/=//g' | sed 's/"//g')
+          lxml_version=$(jq ".default.lxml.version" Pipfile.lock | sed 's/=//g' | sed 's/"//g')
+
+          echo "Pillow is ${pillow_version}"
+          echo "lxml is ${lxml_version}"
+
+          echo "pillow-version=${pillow_version}" >> $GITHUB_OUTPUT
+          echo "lxml-version=${lxml_version}" >> $GITHUB_OUTPUT
+
+    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 }}
+
+      pillow-version: ${{ steps.cache-bust-setup.outputs.pillow-version }}
+
+      lxml-version: ${{ steps.cache-bust-setup.outputs.lxml-version }}
+
+  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 }}
+        PILLOW_VERSION=${{ needs.prepare-docker-build.outputs.pillow-version }}
+        LXML_VERSION=${{ needs.prepare-docker-build.outputs.lxml-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@v2.0.1
+        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@v2.0.1
+        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

@@ -61,10 +61,16 @@ target/
 # PyCharm
 .idea
 
+# VS Code
+.vscode
+/src-ui/.vscode
+/docs/.vscode
+
 # Other stuff that doesn't belong
 .virtualenv
 virtualenv
 /venv
+.venv/
 /docker-compose.env
 /docker-compose.yml
 
@@ -81,8 +87,12 @@ scripts/nuke
 /paperless.conf
 /consume/
 /export/
-/src-ui/.vscode
 
 # this is where the compiled frontend is moved to.
 /src/documents/static/frontend/
-/docs/.vscode/settings.json
+
+# mac os
+.DS_Store
+
+# celery schedule file
+celerybeat-schedule*

.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: v3.9.0
+    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: "v2.3.0"
+    hooks:
+      - id: add-trailing-comma
+        exclude: "(migrations)"
+  - repo: https://github.com/PyCQA/flake8
+    rev: 5.0.4
+    hooks:
+      - id: flake8
+        files: ^src/
+        args:
+          - "--config=./src/setup.cfg"
+  - repo: https://github.com/psf/black
+    rev: 22.10.0
+    hooks:
+      - id: black
+  - repo: https://github.com/asottile/pyupgrade
+    rev: v3.2.2
+    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

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

@@ -4,10 +4,10 @@ If you feel like contributing to the project, please do! Bug fixes and improveme
 
 If you want to implement something big:
 
-* 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.
+- 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
 
@@ -15,7 +15,7 @@ Paperless supports python 3.8 and 3.9. We format Python code with [Black](https:
 
 ## Branches
 
-`master` always reflects the latest release. Apart from changes to the documentation or readme, absolutely no functional changes on this branch in between releases.
+`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.
 
@@ -27,6 +27,8 @@ Please format and test your code! I know it's a hassle, but it makes sure that y
 
 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-ngx.readthedocs.io/en/latest/extending.html
@@ -41,9 +43,9 @@ PRs deemed `non-trivial` will go through a stricter review process before being
 
 Examples of `non-trivial` PRs might include:
 
-* Additional features
-* Large changes to many distinct files
-* Breaking or depreciation of existing features
+- 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:
 
@@ -75,21 +77,56 @@ If a language has already been added, and you would like to contribute new trans
 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.
+- 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_)
+- 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

@@ -1,134 +1,255 @@
-FROM node:16 AS compile-frontend
+# syntax=docker/dockerfile:1.4
 
-COPY . /src
+# 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 npm update npm -g && npm install
-RUN ./node_modules/.bin/ng build --configuration production
+RUN set -eux \
+  && npm update npm -g \
+  && npm ci --omit=optional
+RUN set -eux \
+  && ./node_modules/.bin/ng build --configuration production
 
+FROM --platform=$BUILDPLATFORM python:3.9-slim-bullseye as pipenv-base
 
-FROM ubuntu:20.04 AS jbig2enc
+# This stage generates the requirements.txt file using pipenv
+# This stage runs once for the native platform, as the outputs are not
+# dependent on target arch
+# This way, pipenv dependencies are not left in the final image
+# nor can pipenv mess up the final image somehow
+# Inputs: None
 
-WORKDIR /usr/src/jbig2enc
+WORKDIR /usr/src/pipenv
 
-RUN apt-get update && apt-get install -y --no-install-recommends build-essential automake libtool libleptonica-dev zlib1g-dev git ca-certificates
+COPY Pipfile* ./
 
-RUN git clone https://github.com/agl/jbig2enc .
-RUN ./autogen.sh
-RUN ./configure && make
+RUN set -eux \
+  && echo "Installing pipenv" \
+    && python3 -m pip install --no-cache-dir --upgrade pipenv \
+  && echo "Generating requirement.txt" \
+    && pipenv requirements > requirements.txt
 
-
-FROM python:3.9-slim-bullseye
-
-# Binary dependencies
-RUN apt-get update \
-	&& apt-get -y --no-install-recommends install \
-  	# Basic dependencies
-		curl \
-		gnupg \
-		imagemagick \
-		gettext \
-		tzdata \
-		gosu \
-		# fonts for text file thumbnail generation
-		fonts-liberation \
-		# for Numpy
-		libatlas-base-dev \
-		libxslt1-dev \
-		# thumbnail size reduction
-		optipng \
-		libxml2 \
-		pngquant \
-		unpaper \
-		zlib1g \
-		ghostscript \
-		icc-profiles-free \
-  	# Mime type detection
-		file \
-		libmagic-dev \
-		media-types \
-		# OCRmyPDF dependencies
-		liblept5 \
-		tesseract-ocr \
-		tesseract-ocr-eng \
-		tesseract-ocr-deu \
-		tesseract-ocr-fra \
-		tesseract-ocr-ita \
-		tesseract-ocr-spa \
-  && rm -rf /var/lib/apt/lists/*
-
-# copy jbig2enc
-COPY --from=jbig2enc /usr/src/jbig2enc/src/.libs/libjbig2enc* /usr/local/lib/
-COPY --from=jbig2enc /usr/src/jbig2enc/src/jbig2 /usr/local/bin/
-COPY --from=jbig2enc /usr/src/jbig2enc/src/*.h /usr/local/include/
-
-WORKDIR /usr/src/paperless/src/
-
-COPY requirements.txt ../
-
-# Python dependencies
-RUN apt-get update \
-  && apt-get -y --no-install-recommends install \
-		build-essential \
-		libpq-dev \
-		git \
-		zlib1g-dev \
-		libjpeg62-turbo-dev \
-	&& if [ "$(uname -m)" = "armv7l" ] || [ "$(uname -m)" = "aarch64" ]; \
-	  then echo "Building qpdf" \
-	  && mkdir -p /usr/src/qpdf \
-	  && cd /usr/src/qpdf \
-	  && git clone https://github.com/qpdf/qpdf.git . \
-	  && git checkout --quiet release-qpdf-10.6.2 \
-	  && ./configure \
-	  && make \
-	  && make install \
-	  && cd /usr/src/paperless/src/ \
-	  && rm -rf /usr/src/qpdf; \
-	else \
-	  echo "Skipping qpdf build because pikepdf binary wheels are available."; \
-	fi \
-    && python3 -m pip install --upgrade pip wheel \
-	&& python3 -m pip install --default-timeout=1000 --upgrade --no-cache-dir supervisor \
-  	&& python3 -m pip install --default-timeout=1000 --no-cache-dir -r ../requirements.txt \
-	&& apt-get -y purge build-essential git zlib1g-dev libjpeg62-turbo-dev \
-	&& apt-get -y autoremove --purge \
-	&& rm -rf /var/lib/apt/lists/*
-
-# setup docker-specific things
-COPY docker/ ./docker/
-
-RUN cd docker \
-  	&& cp imagemagick-policy.xml /etc/ImageMagick-6/policy.xml \
-	&& mkdir /var/log/supervisord /var/run/supervisord \
-	&& cp supervisord.conf /etc/supervisord.conf \
-	&& cp docker-entrypoint.sh /sbin/docker-entrypoint.sh \
-	&& cp docker-prepare.sh /sbin/docker-prepare.sh \
-	&& chmod 755 /sbin/docker-entrypoint.sh \
-	&& chmod +x install_management_commands.sh \
-	&& ./install_management_commands.sh \
-	&& cd .. \
-	&& rm docker -rf
-
-COPY gunicorn.conf.py ../
-
-# copy app
-COPY --from=compile-frontend /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 ../ \
-	&& 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/supervisord", "-c", "/etc/supervisord.conf"]
+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/flower-conditional.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 \
+    && mv flower-conditional.sh /usr/local/bin/flower-conditional.sh \
+    && chmod 755 /usr/local/bin/flower-conditional.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/libqpdf29_*.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 --from=pipenv-base /usr/src/pipenv/requirements.txt ./
+
+# 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 Python requirements" \
+    && python3 -m pip install --default-timeout=1000 --no-cache-dir --requirement requirements.txt \
+  && echo "Cleaning up image" \
+    && apt-get -y purge ${BUILD_PACKAGES} \
+    && apt-get -y autoremove --purge \
+    && apt-get clean --yes \
+    && 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

@@ -9,48 +9,57 @@ verify_ssl = true
 name = "piwheels"
 
 [packages]
-dateparser = "~=1.1.0"
-django = "~=3.2"
+dateparser = "~=1.1"
+django = "~=4.1"
 django-cors-headers = "*"
 django-extensions = "*"
-django-filter = "~=21.1"
-django-q = "~=1.3.4"
-djangorestframework = "~=3.13.1"
+django-filter = "~=22.1"
+djangorestframework = "~=3.14"
 filelock = "*"
-fuzzywuzzy = {extras = ["speedup"], version = "*"}
 gunicorn = "*"
 imap-tools = "*"
 langdetect = "*"
-numpy = "~=1.22.0"
 pathvalidate = "*"
-pillow = "~=9.0"
-pikepdf = "~=5.0"
+pillow = "~=9.3"
+pikepdf = "*"
 python-gnupg = "*"
 python-dotenv = "*"
 python-dateutil = "*"
 python-magic = "*"
-psycopg2-binary = "*"
-redis = "*"
-# Pinned because aarch64 wheels and updates cause warnings when loading the classifier model.
-scikit-learn="==0.24.0"
-whitenoise = "~=6.0.0"
-watchdog = "~=2.1.0"
-whoosh="~=2.7.4"
-inotifyrecursive = "~=0.3.4"
-ocrmypdf = "~=13.4.0"
+psycopg2 = "*"
+rapidfuzz = "*"
+redis = {extras = ["hiredis"], version = "*"}
+scikit-learn = "~=1.1"
+# Pin this until piwheels is building 1.9 (see https://www.piwheels.org/project/scipy/)
+scipy = "==1.8.1"
+numpy = "*"
+whitenoise = "~=6.2"
+watchdog = "~=2.1"
+whoosh="~=2.7"
+inotifyrecursive = "~=0.3"
+ocrmypdf = "~=14.0"
 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 = "*"
+# Locked version until https://github.com/django/channels_redis/issues/332
+# is resolved
+channels-redis = "==3.4.1"
 uvicorn = {extras = ["standard"], version = "*"}
 concurrent-log-handler = "*"
-# uvloop 0.15+ incompatible with python 3.6
-uvloop = "~=0.16"
-cryptography = "~=36.0.1"
 "pdfminer.six" = "*"
-"backports.zoneinfo" = "*"
+"backports.zoneinfo" = {version = "*", markers = "python_version < '3.9'"}
+"importlib-resources" = {version = "*", markers = "python_version < '3.9'"}
+zipp = {version = "*", markers = "python_version < '3.9'"}
+pyzbar = "*"
+mysqlclient = "*"
+celery = {extras = ["redis"], version = "*"}
+django-celery-results = "*"
+setproctitle = "*"
+nltk = "*"
+pdf2image = "*"
+flower = "*"
 
 [dev-packages]
 coveralls = "*"
@@ -62,7 +71,10 @@ pytest-django = "*"
 pytest-env = "*"
 pytest-sugar = "*"
 pytest-xdist = "*"
-sphinx = "~=3.4.2"
+sphinx = "~=5.3"
 sphinx_rtd_theme = "*"
 tox = "*"
 black = "*"
+pre-commit = "*"
+sphinx-autobuild = "*"
+myst-parser = "*"

README.md

@@ -2,7 +2,7 @@
 [![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)
+[![Chat on Matrix](https://matrix.to/img/matrix-badge.svg)](https://matrix.to/#/%23paperlessngx%3Amatrix.org)
 
 <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%" />
@@ -10,23 +10,23 @@
 </p>
 
 <!-- omit in toc -->
+
 # Paperless-ngx
 
-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 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](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).
 
-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.*
-
+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._
 
 - [Features](#features)
 - [Getting started](#getting-started)
 - [Contributing](#contributing)
-	- [Community Support](#community-support)
-	- [Translation](#translation)
-	- [Feature Requests](#feature-requests)
-	- [Bugs](#bugs)
+  - [Community Support](#community-support)
+  - [Translation](#translation)
+  - [Feature Requests](#feature-requests)
+  - [Bugs](#bugs)
 - [Affiliated Projects](#affiliated-projects)
 - [Important Note](#important-note)
 
@@ -35,28 +35,28 @@ A demo is available at [demo.paperless-ngx.com](https://demo.paperless-ngx.com)
 ![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)
 
-* 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).
+- 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
 
@@ -65,7 +65,7 @@ The easiest way to deploy paperless is docker-compose. The files in the [`/docke
 If you'd like to jump right in, you can configure a docker-compose environment with our install script:
 
 ```bash
-bash -c "$(curl -L https://raw.githubusercontent.com/paperless-ngx/paperless-ngx/master/install-paperless-ngx.sh)"
+bash -c "$(curl -L https://raw.githubusercontent.com/paperless-ngx/paperless-ngx/main/install-paperless-ngx.sh)"
 ```
 
 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.
@@ -73,6 +73,7 @@ Alternatively, you can install the dependencies and setup apache and a database
 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.
 
 <!-- omit in toc -->
+
 ### Documentation
 
 The documentation for Paperless-ngx is available on [ReadTheDocs](https://paperless-ngx.readthedocs.io/).
@@ -101,18 +102,19 @@ For bugs please [open an issue](https://github.com/paperless-ngx/paperless-ngx/i
 
 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-ngx. Also works with the original Paperless and Paperless-ngx.
-* [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.
+- [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.
+- [Paperless Mobile](https://github.com/astubenbord/paperless-mobile): A modern, feature rich mobile application for Paperless.
 
 These projects also exist, but their status and compatibility with paperless-ngx is unknown.
 
-* [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)
+- [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
 

build-docker-image.sh

@@ -0,0 +1,47 @@
+#!/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=$(jq ".default.psycopg2.version" Pipfile.lock | sed 's/=//g' | sed 's/"//g')
+pillow_version=$(jq ".default.pillow.version" Pipfile.lock | sed 's/=//g' | sed 's/"//g')
+lxml_version=$(jq ".default.lxml.version" Pipfile.lock | sed 's/=//g' | sed 's/"//g')
+# Read this from the other config file
+qpdf_version=$(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="${pikepdf_version}" \
+	--build-arg PILLOW_VERSION="${pillow_version}" \
+	--build-arg LXML_VERSION="${lxml_version}" \
+	--build-arg PSYCOPG2_VERSION="${psycopg2_version}" "${@:2}" .

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 +1,92 @@
+# 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
+# These are not used, but will still bust the cache if one changes
+# Otherwise, the main image will try to build thing (and fail)
+ARG PILLOW_VERSION
+ARG LXML_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 libqpdf29_*.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 +1,48 @@
+# This Dockerfile compiles the jbig2enc library
+# Inputs:
+#    - QPDF_VERSION - the version of qpdf to build a .deb.
+#                     Must be present as a deb-src in bookworm
+
+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 \
+  cmake \
+  zlib1g-dev"
+
+WORKDIR /usr/src
+
+RUN set -eux \
+  && echo "Installing build tools" \
+    && apt-get update --quiet \
+    && apt-get install --yes --quiet --no-install-recommends $BUILD_PACKAGES \
+  && echo "Getting qpdf src" \
+    && echo "deb-src http://deb.debian.org/debian/ bookworm main" > /etc/apt/sources.list.d/bookworm-src.list \
+    && apt-get update \
+    && mkdir qpdf \
+    && cd qpdf \
+    && apt-get source --yes --quiet qpdf=${QPDF_VERSION}-1/bookworm \
+  && echo "Building qpdf" \
+    && cd qpdf-$QPDF_VERSION \
+    && 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/docker-compose.env

@@ -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 +1,102 @@
+# 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 # only needed if non-default username
+      PAPERLESS_DBPASS: paperless # only needed if non-default password
+      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:7.6
+    restart: unless-stopped
+    command:
+      - "gotenberg"
+      - "--chromium-disable-routes=true"
+
+  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 # only needed if non-default username
+      PAPERLESS_DBPASS: paperless # only needed if non-default password
+      PAPERLESS_DBPORT: 3306
+
+
+volumes:
+  data:
+  media:
+  dbdata:
+  redisdata:

docker/compose/docker-compose.portainer.yml

@@ -31,13 +31,13 @@
 version: "3.4"
 services:
   broker:
-    image: redis:6.0
+    image: docker.io/library/redis:7
     restart: unless-stopped
     volumes:
       - redisdata:/data
 
   db:
-    image: postgres:13
+    image: docker.io/library/postgres:13
     restart: unless-stopped
     volumes:
       - pgdata:/var/lib/postgresql/data
@@ -55,7 +55,7 @@ services:
     ports:
       - 8010:8000
     healthcheck:
-      test: ["CMD", "curl", "-f", "http://localhost:8000"]
+      test: ["CMD", "curl", "-fs", "-S", "--max-time", "2", "http://localhost:8000"]
       interval: 30s
       timeout: 10s
       retries: 5

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

@@ -1,4 +1,4 @@
-# docker-compose file for running paperless from the Docker Hub.
+# 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.
 #
@@ -33,13 +33,13 @@
 version: "3.4"
 services:
   broker:
-    image: redis:6.0
+    image: docker.io/library/redis:7
     restart: unless-stopped
     volumes:
       - redisdata:/data
 
   db:
-    image: postgres:13
+    image: docker.io/library/postgres:13
     restart: unless-stopped
     volumes:
       - pgdata:/var/lib/postgresql/data
@@ -59,7 +59,7 @@ services:
     ports:
       - 8000:8000
     healthcheck:
-      test: ["CMD", "curl", "-f", "http://localhost:8000"]
+      test: ["CMD", "curl", "-fs", "-S", "--max-time", "2", "http://localhost:8000"]
       interval: 30s
       timeout: 10s
       retries: 5
@@ -77,13 +77,14 @@ services:
       PAPERLESS_TIKA_ENDPOINT: http://tika:9998
 
   gotenberg:
-    image: gotenberg/gotenberg:7
+    image: docker.io/gotenberg/gotenberg:7.6
     restart: unless-stopped
-    environment:
-      CHROMIUM_DISABLE_ROUTES: 1
+    command:
+      - "gotenberg"
+      - "--chromium-disable-routes=true"
 
   tika:
-    image: apache/tika
+    image: ghcr.io/paperless-ngx/tika:latest
     restart: unless-stopped
 
 volumes:

docker/compose/docker-compose.postgres.yml

@@ -29,13 +29,13 @@
 version: "3.4"
 services:
   broker:
-    image: redis:6.0
+    image: docker.io/library/redis:7
     restart: unless-stopped
     volumes:
       - redisdata:/data
 
   db:
-    image: postgres:13
+    image: docker.io/library/postgres:13
     restart: unless-stopped
     volumes:
       - pgdata:/var/lib/postgresql/data
@@ -53,7 +53,7 @@ services:
     ports:
       - 8000:8000
     healthcheck:
-      test: ["CMD", "curl", "-f", "http://localhost:8000"]
+      test: ["CMD", "curl", "-fs", "-S", "--max-time", "2", "http://localhost:8000"]
       interval: 30s
       timeout: 10s
       retries: 5

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

@@ -1,7 +1,6 @@
-# docker-compose file for running paperless from the Docker Hub.
+# 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.
@@ -34,7 +33,7 @@
 version: "3.4"
 services:
   broker:
-    image: redis:6.0
+    image: docker.io/library/redis:7
     restart: unless-stopped
     volumes:
       - redisdata:/data
@@ -49,7 +48,7 @@ services:
     ports:
       - 8000:8000
     healthcheck:
-      test: ["CMD", "curl", "-f", "http://localhost:8000"]
+      test: ["CMD", "curl", "-fs", "-S", "--max-time", "2", "http://localhost:8000"]
       interval: 30s
       timeout: 10s
       retries: 5
@@ -66,13 +65,14 @@ services:
       PAPERLESS_TIKA_ENDPOINT: http://tika:9998
 
   gotenberg:
-    image: gotenberg/gotenberg:7
+    image: docker.io/gotenberg/gotenberg:7.6
     restart: unless-stopped
-    environment:
-      CHROMIUM_DISABLE_ROUTES: 1
+    command:
+      - "gotenberg"
+      - "--chromium-disable-routes=true"
 
   tika:
-    image: apache/tika
+    image: ghcr.io/paperless-ngx/tika:latest
     restart: unless-stopped
 
 volumes:

docker/compose/docker-compose.sqlite.yml

@@ -26,7 +26,7 @@
 version: "3.4"
 services:
   broker:
-    image: redis:6.0
+    image: docker.io/library/redis:7
     restart: unless-stopped
     volumes:
       - redisdata:/data
@@ -39,7 +39,7 @@ services:
     ports:
       - 8000:8000
     healthcheck:
-      test: ["CMD", "curl", "-f", "http://localhost:8000"]
+      test: ["CMD", "curl", "-fs", "-S", "--max-time", "2", "http://localhost:8000"]
       interval: 30s
       timeout: 10s
       retries: 5

docker/docker-entrypoint.sh

@@ -1,47 +1,143 @@
-#!/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 -r var="$1"
+	local -r fileVar="${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
+	local -r usermap_original_uid=$(id -u paperless)
+	local -r usermap_original_gid=$(id -g paperless)
+	local -r usermap_new_uid=${USERMAP_UID:-$usermap_original_uid}
+	local -r usermap_new_gid=${USERMAP_GID:-${usermap_original_gid:-$usermap_new_uid}}
+	if [[ ${usermap_new_uid} != "${usermap_original_uid}" || ${usermap_new_gid} != "${usermap_original_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
 }
 
+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}"
+	export CONSUME_DIR="${PAPERLESS_CONSUMPTION_DIR:-/usr/src/paperless/consume}"
+}
+
+nltk_data () {
+	# Store the NLTK data outside the Docker container
+	local -r nltk_data_dir="${DATA_DIR}/nltk"
+	local -r truthy_things=("yes y 1 t true")
+
+	# If not set, or it looks truthy
+	if [[ -z "${PAPERLESS_ENABLE_NLTK}" ]] || [[ "${truthy_things[*]}" =~ ${PAPERLESS_ENABLE_NLTK,} ]]; then
+
+		# Download or update the snowball stemmer data
+		python3 -W ignore::RuntimeWarning -m nltk.downloader -d "${nltk_data_dir}" snowball_data
+
+		# Download or update the stopwords corpus
+		python3 -W ignore::RuntimeWarning -m nltk.downloader -d "${nltk_data_dir}" stopwords
+
+		# Download or update the punkt tokenizer data
+		python3 -W ignore::RuntimeWarning -m nltk.downloader -d "${nltk_data_dir}" punkt
+
+	else
+		echo "Skipping NLTK data download"
+
+	fi
+
+}
+
 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 ../$dir
+	# Check for overrides of certain folders
+	map_folders
+
+	local -r export_dir="/usr/src/paperless/export"
+
+	for dir in \
+		"${export_dir}" \
+		"${DATA_DIR}" "${DATA_DIR}/index" \
+		"${MEDIA_ROOT_DIR}" "${MEDIA_ROOT_DIR}/documents" "${MEDIA_ROOT_DIR}/documents/originals" "${MEDIA_ROOT_DIR}/documents/thumbnails" \
+		"${CONSUME_DIR}"; do
+		if [[ ! -d "${dir}" ]]; then
+			echo "Creating directory ${dir}"
+			mkdir "${dir}"
 		fi
 	done
 
-	echo "Creating directory /tmp/paperless"
-	mkdir -p /tmp/paperless
+	local -r tmp_dir="/tmp/paperless"
+	echo "Creating directory ${tmp_dir}"
+	mkdir -p "${tmp_dir}"
+
+	nltk_data
 
 	set +e
 	echo "Adjusting permissions of paperless files. This may take a while."
-	chown -R paperless:paperless /tmp/paperless
-	find .. -not \( -user paperless -and -group paperless \) -exec chown paperless:paperless {} +
+	chown -R paperless:paperless ${tmp_dir}
+	for dir in \
+		"${export_dir}" \
+		"${DATA_DIR}" \
+		"${MEDIA_ROOT_DIR}" \
+		"${CONSUME_DIR}"; do
+		find "${dir}" -not \( -user paperless -and -group paperless \) -exec chown paperless:paperless {} +
+	done
 	set -e
 
-	gosu paperless /sbin/docker-prepare.sh
+	"${gosu_cmd[@]}" /sbin/docker-prepare.sh
 }
 
 install_languages() {
 	echo "Installing languages..."
 
-	local langs="$1"
-	read -ra langs <<<"$langs"
+	read -ra langs <<<"$1"
 
 	# Check that it is not empty
 	if [ ${#langs[@]} -eq 0 ]; then
@@ -56,12 +152,12 @@ install_languages() {
 		#    continue
 		#fi
 
-		if dpkg -s $pkg &>/dev/null; then
+		if dpkg -s "$pkg" &>/dev/null; then
 			echo "Package $pkg already installed!"
 			continue
 		fi
 
-		if ! apt-cache show $pkg &>/dev/null; then
+		if ! apt-cache show "$pkg" &>/dev/null; then
 			echo "Package $pkg not found! :("
 			continue
 		fi
@@ -76,8 +172,13 @@ install_languages() {
 
 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 "$PAPERLESS_OCR_LANGUAGES" ]]; then
+if [[ -n "$PAPERLESS_OCR_LANGUAGES" ]]; then
 	install_languages "$PAPERLESS_OCR_LANGUAGES"
 fi
 
@@ -85,7 +186,7 @@ initialize
 
 if [[ "$1" != "/"* ]]; then
 	echo Executing management command "$@"
-	exec gosu paperless python3 manage.py "$@"
+	exec "${gosu_cmd[@]}" python3 manage.py "$@"
 else
 	echo Executing "$@"
 	exec "$@"

docker/docker-prepare.sh

@@ -1,19 +1,19 @@
 #!/usr/bin/env bash
 
+set -e
+
 wait_for_postgres() {
-	attempt_num=1
-	max_attempts=5
+	local attempt_num=1
+	local -r max_attempts=5
 
 	echo "Waiting for PostgreSQL to start..."
 
-	host="${PAPERLESS_DBHOST}"
-	port="${PAPERLESS_DBPORT}"
+	local -r host="${PAPERLESS_DBHOST:-localhost}"
+	local -r port="${PAPERLESS_DBPORT:-5432}"
 
-	if [[ -z $port ]]; then
-		port="5432"
-	fi
-
-	while ! </dev/tcp/$host/$port; do
+	# Disable warning, host and port can't have spaces
+	# shellcheck disable=SC2086
+	while [ ! "$(pg_isready -h ${host} -p ${port})" ]; do
 
 		if [ $attempt_num -eq $max_attempts ]; then
 			echo "Unable to connect to database."
@@ -23,11 +23,43 @@ wait_for_postgres() {
 
 		fi
 
-		attempt_num=$(expr "$attempt_num" + 1)
+		attempt_num=$(("$attempt_num" + 1))
 		sleep 5
 	done
 }
 
+wait_for_mariadb() {
+	echo "Waiting for MariaDB to start..."
+
+	local -r host="${PAPERLESS_DBHOST:=localhost}"
+	local -r port="${PAPERLESS_DBPORT:=3306}"
+
+	local attempt_num=1
+	local -r 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 $attempt_num failed! Trying again in 5 seconds..."
+
+		fi
+
+		attempt_num=$(("$attempt_num" + 1))
+		sleep 5
+	done
+}
+
+wait_for_redis() {
+	# We use a Python script to send the Redis ping
+	# instead of installing redis-tools just for 1 thing
+	if ! python3 /sbin/wait-for-redis.py; then
+		exit 1
+	fi
+}
+
 migrations() {
 	(
 		# flock is in place to prevent multiple containers from doing migrations
@@ -36,17 +68,18 @@ migrations() {
 		flock 200
 		echo "Apply database migrations..."
 		python3 manage.py migrate
-	) 200>/usr/src/paperless/data/migration_lock
+	) 200>"${DATA_DIR}/migration_lock"
 }
 
 search_index() {
-	index_version=1
-	index_version_file=/usr/src/paperless/data/.index_version
 
-	if [[ (! -f "$index_version_file") || $(<$index_version_file) != "$index_version" ]]; then
+	local -r index_version=1
+	local -r index_version_file=${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
-		echo $index_version | tee $index_version_file >/dev/null
+		python3 manage.py document_index reindex --no-progress-bar
+		echo ${index_version} | tee "${index_version_file}" >/dev/null
 	fi
 }
 
@@ -56,17 +89,64 @@ superuser() {
 	fi
 }
 
+custom_container_init() {
+	# Mostly borrowed from the LinuxServer.io base image
+	# https://github.com/linuxserver/docker-baseimage-ubuntu/tree/bionic/root/etc/cont-init.d
+	local -r custom_script_dir="/custom-cont-init.d"
+	# Tamper checking.
+	# Don't run files which are owned by anyone except root
+	# Don't run files which are writeable by others
+	if [ -d "${custom_script_dir}" ]; then
+		if [ -n "$(/usr/bin/find "${custom_script_dir}" -maxdepth 1 ! -user root)" ]; then
+			echo "**** Potential tampering with custom scripts detected ****"
+			echo "**** The folder '${custom_script_dir}' must be owned by root ****"
+			return 0
+		fi
+		if [ -n "$(/usr/bin/find "${custom_script_dir}" -maxdepth 1 -perm -o+w)" ]; then
+			echo "**** The folder '${custom_script_dir}' or some of contents have write permissions for others, which is a security risk. ****"
+			echo "**** Please review the permissions and their contents to make sure they are owned by root, and can only be modified by root. ****"
+			return 0
+		fi
+
+		# Make sure custom init directory has files in it
+		if [ -n "$(/bin/ls -A "${custom_script_dir}" 2>/dev/null)" ]; then
+			echo "[custom-init] files found in ${custom_script_dir} executing"
+			# Loop over files in the directory
+			for SCRIPT in "${custom_script_dir}"/*; do
+				NAME="$(basename "${SCRIPT}")"
+				if [ -f "${SCRIPT}" ]; then
+					echo "[custom-init] ${NAME}: executing..."
+					/bin/bash "${SCRIPT}"
+					echo "[custom-init] ${NAME}: exited $?"
+				elif [ ! -f "${SCRIPT}" ]; then
+					echo "[custom-init] ${NAME}: is not a file"
+				fi
+			done
+		else
+			echo "[custom-init] no custom files found exiting..."
+		fi
+
+	fi
+}
+
 do_work() {
-	if [[ -n "${PAPERLESS_DBHOST}" ]]; then
+	if [[ "${PAPERLESS_DBENGINE}" == "mariadb" ]]; then
+		wait_for_mariadb
+	elif [[ -n "${PAPERLESS_DBHOST}" ]]; then
 		wait_for_postgres
 	fi
 
+	wait_for_redis
+
 	migrations
 
 	search_index
 
 	superuser
 
+	# Leave this last thing
+	custom_container_init
+
 }
 
 do_work

docker/flower-conditional.sh

@@ -0,0 +1,7 @@
+#!/usr/bin/env bash
+
+echo "Checking if we should start flower..."
+
+if [[ -n  "${PAPERLESS_ENABLE_FLOWER}" ]]; then
+	celery --app paperless flower
+fi

docker/install_management_commands.sh

@@ -1,4 +1,19 @@
-for command in document_archiver document_exporter document_importer mail_fetcher document_create_classifier document_index document_renamer document_retagger document_thumbnails document_sanity_checker manage_superuser;
+#!/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

docker/management_script.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 
 set -e
 
@@ -6,10 +6,10 @@ cd /usr/src/paperless/src/
 
 if [[ $(id -u) == 0 ]] ;
 then
-  gosu paperless python3 manage.py management_command "$@"
+	gosu paperless python3 manage.py management_command "$@"
 elif [[ $(id -un) == "paperless" ]] ;
 then
-  python3 manage.py management_command "$@"
+	python3 manage.py management_command "$@"
 else
-  echo "Unknown user."
+	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
+
+exec /usr/local/bin/supervisord -c /etc/supervisord.conf "${rootless_args[@]}"

docker/supervisord.conf

@@ -10,7 +10,7 @@ user=root
 [program:gunicorn]
 command=gunicorn -c /usr/src/paperless/gunicorn.conf.py paperless.asgi:application
 user=paperless
-
+priority = 1
 stdout_logfile=/dev/stdout
 stdout_logfile_maxbytes=0
 stderr_logfile=/dev/stderr
@@ -19,16 +19,41 @@ stderr_logfile_maxbytes=0
 [program:consumer]
 command=python3 manage.py document_consumer
 user=paperless
-
+stopsignal=INT
+priority = 20
 stdout_logfile=/dev/stdout
 stdout_logfile_maxbytes=0
 stderr_logfile=/dev/stderr
 stderr_logfile_maxbytes=0
 
-[program:scheduler]
-command=python3 manage.py qcluster
+[program:celery]
+
+command = celery --app paperless worker --loglevel INFO
 user=paperless
-
+stopasgroup = true
+stopwaitsecs = 60
+priority = 5
+stdout_logfile=/dev/stdout
+stdout_logfile_maxbytes=0
+stderr_logfile=/dev/stderr
+stderr_logfile_maxbytes=0
+
+[program:celery-beat]
+
+command = celery --app paperless beat --loglevel INFO
+user=paperless
+stopasgroup = true
+priority = 10
+stdout_logfile=/dev/stdout
+stdout_logfile_maxbytes=0
+stderr_logfile=/dev/stderr
+stderr_logfile_maxbytes=0
+
+[program:celery-flower]
+command = /usr/local/bin/flower-conditional.sh
+user = paperless
+startsecs = 0
+priority = 40
 stdout_logfile=/dev/stdout
 stdout_logfile_maxbytes=0
 stderr_logfile=/dev/stderr

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

@@ -35,13 +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:
 
@@ -49,7 +51,7 @@ 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:
 
@@ -117,6 +119,23 @@ Then you can start paperless-ngx with ``-d`` to have it run in the background.
 
                 image: ghcr.io/paperless-ngx/paperless-ngx:latest
 
+    .. note::
+        In version 1.7.1 and onwards, the Docker image can now 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
 ================
 
@@ -270,6 +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:
 
@@ -289,6 +312,7 @@ there are tools for it.
     -c, --correspondent
     -T, --tags
     -t, --document_type
+    -s, --storage_path
     -i, --inbox-only
     --use-first
     -f, --overwrite
@@ -297,7 +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.
 
@@ -369,8 +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::
@@ -379,7 +403,7 @@ the naming scheme.
 
 The command takes no arguments and processes all your documents at once.
 
-Learn how to use :ref:`Management Utilities<Management utilities>`.
+Learn how to use :ref:`Management Utilities<utilities-management-commands>`.
 
 
 .. _utilities-sanity-checker:
@@ -423,6 +447,14 @@ command:
 
 The command takes no arguments and processes all your mail accounts and rules.
 
+ .. note::
+
+    As of October 2022 Microsoft no longer supports IMAP authentication for Exchange
+    servers, thus Exchange is no longer supported until a solution is implemented in
+    the Python IMAP library used by Paperless. See  `learn.microsoft.com`_
+
+.. _learn.microsoft.com: https://learn.microsoft.com/en-us/exchange/clients-and-mobile-in-exchange-online/deprecation-of-basic-authentication-exchange-online
+
 .. _utilities-archiver:
 
 Creating archived documents

docs/advanced_usage.rst

@@ -7,12 +7,12 @@ easier.
 
 .. _advanced-matching:
 
-Matching tags, correspondents and document types
-################################################
+Matching tags, correspondents, document types, and storage paths
+################################################################
 
-Paperless will compare the matching algorithms defined by every tag and
-correspondent already set in your database to see if they apply to the text in
-a document.  In other words, if you defined a tag called ``Home Utility``
+Paperless will compare the matching algorithms defined by every tag, correspondent,
+document type, and storage path in your database to see if they apply to the text
+in a document. In other words, if you define a tag called ``Home Utility``
 that had a ``match`` property of ``bc hydro`` and a ``matching_algorithm`` of
 ``literal``, Paperless will automatically tag your newly-consumed document with
 your ``Home Utility`` tag so long as the text ``bc hydro`` appears in the body
@@ -22,10 +22,10 @@ The matching logic is quite powerful. It supports searching the text of your
 document with different algorithms, and as such, some experimentation may be
 necessary to get things right.
 
-In order to have a tag, correspondent, or type assigned automatically to newly
-consumed documents, assign a match and matching algorithm using the web
-interface. These settings define when to assign correspondents, tags, and types
-to documents.
+In order to have a tag, correspondent, document type, or storage path assigned
+automatically to newly consumed documents, assign a match and matching algorithm
+using the web interface. These settings define when to assign tags, correspondents,
+document types, and storage paths to documents.
 
 The following algorithms are available:
 
@@ -37,7 +37,7 @@ The following algorithms are available:
 * **Literal:** Matches only if the match appears exactly as provided (i.e. preserve ordering) in the PDF.
 * **Regular expression:** Parses the match as a regular expression and tries to
   find a match within the document.
-* **Fuzzy match:** I dont know. Look at the source.
+* **Fuzzy match:** I don't know. Look at the source.
 * **Auto:** Tries to automatically match new documents. This does not require you
   to set a match. See the notes below.
 
@@ -47,9 +47,9 @@ defining a match text of ``"Bank of America" BofA`` using the *any* algorithm,
 will match documents that contain either "Bank of America" or "BofA", but will
 not match documents containing "Bank of South America".
 
-Then just save your tag/correspondent and run another document through the
-consumer.  Once complete, you should see the newly-created document,
-automatically tagged with the appropriate data.
+Then just save your tag, correspondent, document type, or storage path and run
+another document through the consumer.  Once complete, you should see the
+newly-created document, automatically tagged with the appropriate data.
 
 
 .. _advanced-automatic_matching:
@@ -58,9 +58,9 @@ Automatic matching
 ==================
 
 Paperless-ngx comes with a new matching algorithm called *Auto*. This matching
-algorithm tries to assign tags, correspondents, and document types to your
-documents based on how you have already assigned these on existing documents. It
-uses a neural network under the hood.
+algorithm tries to assign tags, correspondents, document types, and storage paths
+to your documents based on how you have already assigned these on existing documents.
+It uses a neural network under the hood.
 
 If, for example, all your bank statements of your account 123 at the Bank of
 America are tagged with the tag "bofa_123" and the matching algorithm of this
@@ -80,20 +80,21 @@ feature:
   that the neural network only learns from documents which you have correctly
   tagged before.
 * The matching algorithm can only work if there is a correlation between the
-  tag, correspondent, or document type and the document itself. Your bank
-  statements usually contain your bank account number and the name of the bank,
-  so this works reasonably well, However, tags such as "TODO" cannot be
-  automatically assigned.
+  tag, correspondent, document type, or storage path and the document itself.
+  Your bank statements usually contain your bank account number and the name
+  of the bank, so this works reasonably well, However, tags such as "TODO"
+  cannot be automatically assigned.
 * The matching algorithm needs a reasonable number of documents to identify when
-  to assign tags, correspondents, and types. If one out of a thousand documents
-  has the correspondent "Very obscure web shop I bought something five years
-  ago", it will probably not assign this correspondent automatically if you buy
-  something from them again. The more documents, the better.
+  to assign tags, correspondents, storage paths, and types. If one out of a
+  thousand documents has the correspondent "Very obscure web shop I bought
+  something five years ago", it will probably not assign this correspondent
+  automatically if you buy something from them again. The more documents, the better.
 * Paperless also needs a reasonable amount of negative examples to decide when
-  not to assign a certain tag, correspondent or type. This will usually be the
-  case as you start filling up paperless with documents. Example: If all your
-  documents are either from "Webshop" and "Bank", paperless will assign one of
-  these correspondents to ANY new document, if both are set to automatic matching.
+  not to assign a certain tag, correspondent, document type, or storage path. This will
+  usually be the case as you start filling up paperless with documents.
+  Example: If all your documents are either from "Webshop" and "Bank", paperless
+  will assign one of these correspondents to ANY new document, if both are set
+  to automatic matching.
 
 Hooking into the consumption process
 ####################################
@@ -120,10 +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:
@@ -133,7 +134,7 @@ this:
 .. code:: bash
 
     #!/usr/bin/env bash
-    pdf2pdfocr.py -i ${1}
+    pdf2pdfocr.py -i ${DOCUMENT_SOURCE_PATH}
 
 ``/etc/paperless.conf``
 
@@ -148,6 +149,9 @@ which will in turn call `pdf2pdfocr.py`_ on your document, which will then
 overwrite the file with an OCR'd version of the file and exit.  At which point,
 the consumption process will begin with the newly modified file.
 
+The script's stdout and stderr will be logged line by line to the webserver log, along
+with the exit code of the script.
+
 .. _pdf2pdfocr.py: https://github.com/LeoFCardoso/pdf2pdfocr
 
 .. _advanced-post_consume_script:
@@ -156,22 +160,31 @@ 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, 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.
 
+The script's stdout and stderr will be logged line by line to the webserver log, along
+with the exit code of the script.
+
+
 Docker
 ------
 Assumed you have ``/home/foo/paperless-ngx/scripts/post-consumption-example.sh``.
@@ -179,13 +192,14 @@ 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/
-   ...
+
+  ...
+  consumer:
+    ...
+    volumes:
+      ...
+      - /home/paperless-ngx/scripts:/path/in/container/scripts/
+  ...
 
 Example (docker-compose.yml): ``- /home/foo/paperless-ngx/scripts:/usr/src/paperless/scripts``
 
@@ -199,7 +213,7 @@ Troubleshooting:
 - 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/jonaswinkler/paperless-ngx/blob/master/scripts/post-consumption-example.sh
+.. _post-consumption-example.sh: https://github.com/paperless-ngx/paperless-ngx/blob/main/scripts/post-consumption-example.sh
 
 .. _advanced-file_name_handling:
 
@@ -211,7 +225,8 @@ using the identifier which it has assigned to each document. You will end up get
 files like ``0000123.pdf`` in your media directory. This isn't necessarily a bad
 thing, because you normally don't have to access these files manually. However, if
 you wish to name your files differently, you can do that by adjusting the
-``PAPERLESS_FILENAME_FORMAT`` configuration option.
+``PAPERLESS_FILENAME_FORMAT`` configuration option. Paperless adds the correct
+file extension e.g. ``.pdf``, ``.jpg`` automatically.
 
 This variable allows you to configure the filename (folders are allowed) using
 placeholders. For example, configuring this to
@@ -242,7 +257,7 @@ 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".
@@ -250,12 +265,18 @@ Paperless provides the following placeholders withing filenames:
 * ``{tag_list}``: A comma separated list of all tags assigned to the document.
 * ``{title}``: The title of the document.
 * ``{created}``: The full date (ISO format) the document was created.
-* ``{created_year}``: Year created only.
+* ``{created_year}``: Year created only, formatted as the year with century.
+* ``{created_year_short}``: Year created only, formatted as the year without century, zero padded.
 * ``{created_month}``: Month created only (number 01-12).
+* ``{created_month_name}``: Month created name, as per locale
+* ``{created_month_name_short}``: Month created abbreviated name, as per locale
 * ``{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_year_short}``: Year added only, formatted as the year without century, zero padded.
 * ``{added_month}``: Month added only (number 01-12).
+* ``{added_month_name}``: Month added name, as per locale
+* ``{added_month_name_short}``: Month added abbreviated name, as per locale
 * ``{added_day}``: Day added only (number 01-31).
 
 
@@ -267,6 +288,17 @@ 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,
@@ -289,3 +321,127 @@ 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.
+
+.. _advanced-celery-monitoring:
+
+Celery Monitoring
+#################
+
+The monitoring tool `Flower <https://flower.readthedocs.io/en/latest/index.html>`_ can be used to view more
+detailed information about the health of the celery workers used for asynchronous tasks.  This includes details
+on currently running, queued and completed tasks, timing and more.  Flower can also be used with Prometheus, as it
+exports metrics.  For details on its capabilities, refer to the Flower documentation.
+
+To configure Flower further, create a `flowerconfig.py` and place it into the `src/paperless` directory.  For
+a Docker installation, you can use volumes to accomplish this:
+
+.. code:: yaml
+
+    services:
+      # ...
+      webserver:
+        # ...
+        volumes:
+          - /path/to/my/flowerconfig.py:/usr/src/paperless/src/paperless/flowerconfig.py:ro
+
+Custom Container Initialization
+###############################
+
+The Docker image includes the ability to run custom user scripts during startup.  This could be
+utilized for installing additional tools or Python packages, for example.
+
+To utilize this, mount a folder containing your scripts to the custom initialization directory, `/custom-cont-init.d`
+and place scripts you wish to run inside.  For security, the folder and its contents must be owned by `root`.
+Additionally, scripts must only be writable by `root`.
+
+Your scripts will be run directly before the webserver completes startup.  Scripts will be run by the `root` user.
+This is an advanced functionality with which you could break functionality or lose data.
+
+For example, using Docker Compose:
+
+
+.. code:: yaml
+
+    services:
+      # ...
+      webserver:
+        # ...
+        volumes:
+          - /path/to/my/scripts:/custom-cont-init.d:ro
+
+.. _advanced-mysql-caveats:
+
+MySQL Caveats
+#############
+
+Case Sensitivity
+================
+
+The database interface does not provide a method to configure a MySQL database to
+be case sensitive.  This would prevent a user from creating a tag ``Name`` and ``NAME``
+as they are considered the same.
+
+Per Django documentation, to enable this requires manual intervention.  To enable
+case sensetive tables, you can execute the following command against each table:
+
+``ALTER TABLE <table_name> CONVERT TO CHARACTER SET utf8mb4 COLLATE utf8mb4_bin;``
+
+You can also set the default for new tables (this does NOT affect existing tables) with:
+
+``ALTER DATABASE <db_name> CHARACTER SET utf8mb4 COLLATE utf8mb4_bin;``

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::
@@ -240,11 +241,13 @@ 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.

docs/conf.py

@@ -2,6 +2,8 @@ import sphinx_rtd_theme
 
 
 __version__ = None
+__full_version_str__ = None
+__major_minor_version_str__ = None
 exec(open("../src/paperless/version.py").read())
 
 
@@ -12,13 +14,17 @@ extensions = [
     "sphinx.ext.imgmath",
     "sphinx.ext.viewcode",
     "sphinx_rtd_theme",
+    "myst_parser",
 ]
 
 # Add any paths that contain templates here, relative to this directory.
-# templates_path = ['_templates']
+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'
@@ -41,9 +47,9 @@ copyright = "2015-2022, Daniel Quinn, Jonas Winkler, and the paperless-ngx team"
 #
 
 # 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.
@@ -119,6 +125,16 @@ html_theme_path = []
 # so a file named "default.css" will overwrite the builtin "default.css".
 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.

docs/configuration.rst

@@ -27,11 +27,29 @@ 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`.
+
+    .. warning::
+
+      Using MariaDB comes with some caveats.  See :ref:`advanced-mysql-caveats` for details.
+
+
 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.
@@ -39,17 +57,17 @@ 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".
 
@@ -60,6 +78,13 @@ PAPERLESS_DBSSLMODE=<mode>
 
     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
 #################
 
@@ -111,6 +136,14 @@ PAPERLESS_FILENAME_FORMAT=<format>
 
     Default is none, which disables this feature.
 
+PAPERLESS_FILENAME_FORMAT_REMOVE_NONE=<bool>
+    Tells paperless to replace placeholders in `PAPERLESS_FILENAME_FORMAT` that would resolve
+    to 'none' to be omitted from the resulting filename. This also holds true for directory
+    names.
+    See :ref:`advanced-file_name_handling` for details.
+
+    Defaults to `false` which disables this feature.
+
 PAPERLESS_LOGGING_DIR=<path>
     This is where paperless will store log files.
 
@@ -130,6 +163,8 @@ PAPERLESS_LOGROTATE_MAX_BACKUPS=<num>
 
     Defaults to 20.
 
+.. _hosting-and-security:
+
 Hosting & Security
 ##################
 
@@ -142,7 +177,24 @@ 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:
@@ -151,12 +203,19 @@ 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>
@@ -168,9 +227,16 @@ PAPERLESS_FORCE_SCRIPT_NAME=<path>
 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.
@@ -185,7 +251,7 @@ PAPERLESS_AUTO_LOGIN_USERNAME=<username>
 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 seperately, such as Kubernetes
+    where you can not run the `createsuperuser` command separately, such as Kubernetes
     or AWS ECS.
 
     Requires `PAPERLESS_ADMIN_PASSWORD` to be set.
@@ -389,6 +455,24 @@ PAPERLESS_OCR_IMAGE_DPI=<num>
     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.
+
+    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
@@ -439,7 +523,7 @@ PAPERLESS_TIKA_GOTENBERG_ENDPOINT=<url>
     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.tika.yml`` file for reference). The changes
+file (see the provided ``docker-compose.sqlite-tika.yml`` file for reference). The changes
 requires are as follows:
 
 .. code:: yaml
@@ -460,19 +544,22 @@ requires are as follows:
         # ...
 
         gotenberg:
-            image: gotenberg/gotenberg:7
+            image: gotenberg/gotenberg:7.6
             restart: unless-stopped
-            environment:
-                CHROMIUM_DISABLE_ROUTES: 1
+            command:
+                - "gotenberg"
+                - "--chromium-disable-routes=true"
 
         tika:
-            image: apache/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
 ###############
 
@@ -481,6 +568,8 @@ 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
@@ -528,6 +617,10 @@ PAPERLESS_WORKER_TIMEOUT=<num>
     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.
@@ -548,6 +641,28 @@ PAPERLESS_CONSUMER_POLLING=<num>
 
     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
@@ -576,6 +691,38 @@ PAPERLESS_CONSUMER_SUBDIRS_AS_TAGS=<bool>
 
     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
@@ -600,13 +747,6 @@ 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
@@ -622,8 +762,24 @@ 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
@@ -639,10 +795,7 @@ PAPERLESS_IGNORE_DATES=<string>
     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.
 
-    You may specify dates in a multitude of formats supported by dateparser (see
-    https://dateparser.readthedocs.io/en/latest/#popular-formats) but as the dates
-    need to be comma separated, the options are limited.
-    Example: "2020-12-02,22.04.1999"
+    The date is parsed using the order specified in PAPERLESS_DATE_ORDER
 
     Defaults to an empty string to not ignore any dates.
 
@@ -659,7 +812,7 @@ PAPERLESS_CONSUMER_IGNORE_PATTERNS=<json>
 
     This can be adjusted by configuring a custom json array with patterns to exclude.
 
-    Defautls to ``[".DS_STORE/*", "._*", ".stfolder/*"]``.
+    Defaults to ``[".DS_STORE/*", "._*", ".stfolder/*", ".stversions/*", ".localized/*", "desktop.ini"]``.
 
 Binaries
 ########
@@ -672,13 +825,10 @@ 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".
-
-PAPERLESS_OPTIPNG_BINARY=<path>
-    Defaults to "/usr/bin/optipng".
+    Defaults to "gs".
 
 
 .. _configuration-docker:
@@ -695,9 +845,14 @@ PAPERLESS_WEBSERVER_WORKERS=<num>
     also loads the entire application into memory separately, so increasing this value
     will increase RAM usage.
 
-    Consider configuring this to 1 on low power devices with limited amount of RAM.
+    Defaults to 1.
 
-    Defaults to 2.
+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
@@ -752,3 +907,25 @@ PAPERLESS_OCR_LANGUAGES=<list>
         PAPERLESS_OCR_LANGUAGE=tur
 
     Defaults to none, which does not install any additional languages.
+
+PAPERLESS_ENABLE_FLOWER=<defined>
+    If this environment variable is defined, the Celery monitoring tool
+    `Flower <https://flower.readthedocs.io/en/latest/index.html>`_ will
+    be started by the container.
+
+    You can read more about this in the :ref:`advanced setup <advanced-celery-monitoring>`
+    documentation.
+
+
+.. _configuration-update-checking:
+
+Update Checking
+###############
+
+PAPERLESS_ENABLE_UPDATE_CHECK=<bool>
+
+    .. note::
+
+            This setting was deprecated in favor of a frontend setting after v1.9.2. A one-time
+            migration is performed for users who have this setting set. This setting is always
+            ignored if the corresponding frontend setting has been set.

docs/contributing.rst

@@ -1,145 +0,0 @@
-.. _contributing:
-
-Contributing to Paperless
-#########################
-
-.. warning::
-
-    This section is not updated to paperless-ngx 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

@@ -1,13 +1,13 @@
 .. _extending:
 
-Paperless development
-#####################
+Paperless-ngx Development
+#########################
 
 This section describes the steps you need to take to start development on paperless-ngx.
 
 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
+*   ``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
@@ -23,6 +23,33 @@ Apart from that, the folder structure is as follows:
 *   ``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
 =============================
 
@@ -37,79 +64,87 @@ To do the setup you need to perform the steps from the following chapters in a c
 
         $ npm install -g @angular/cli
 
-4.  Create ``consume`` and ``media`` folders in the cloned root folder.
+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
 
-5.  You can now either ...
+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 postgresql server) 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
 
-6.  Install the python dependencies by performing in the src/ directory.
+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.
 
-7.  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:
+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
 
-8.  Apply migrations and create a superuser for your dev instance:
+9.  Apply migrations and create a superuser for your dev instance:
 
     .. code:: shell-session
 
         python3 manage.py migrate
         python3 manage.py createsuperuser
 
-9.  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.
+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
+        python3 manage.py runserver & python3 manage.py document_consumer & celery --app paperless worker
 
-10. Login with the superuser credentials provided in step 8 at ``http://localhost:8000`` to create a session that enables you to use the backend.
+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.
 
 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
+*   celery --app paperless worker
 *   python3 manage.py document_consumer
 
 To start them all:
 
 .. code:: shell-session
 
-    python3 manage.py runserver & python3 manage.py document_consumer & python3 manage.py qcluster
+    python3 manage.py runserver & python3 manage.py document_consumer & celery --app paperless worker
 
 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 ``black`` to format your code.
-*   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::
 
@@ -121,9 +156,8 @@ Testing and code style:
 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
 
@@ -152,6 +186,31 @@ 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
@@ -275,11 +334,17 @@ 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
 
-        docker build . -t <your-tag>
+        ./build-docker-image.sh Dockerfile -t <your-tag>
 
 Extending Paperless
 ===================
@@ -361,3 +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

@@ -7,7 +7,7 @@ Frequently asked questions
 
 **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 garauntee the feature
+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.
 
@@ -81,11 +81,10 @@ python requirements do not have precompiled packages for ARM / ARM64. Installati
 of these will require additional development libraries and compilation will take
 a long time.
 
-**Q:** *How do I run this on unRaid?*
+**Q:** *How do I run this on Unraid?*
 
-**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.
+**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?*
 

docs/index.rst

@@ -44,7 +44,7 @@ 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
@@ -52,7 +52,7 @@ resources in the documentation:
 *   Paperless is now integrated with a
     :ref:`task processing queue <setup-task_processor>` that tells you
     at a glance when and why something is not working.
-*   The :ref:`changelog <paperless_changelog>` contains a detailed list of all changes
+*   The :doc:`changelog </changelog>` contains a detailed list of all changes
     in paperless-ngx.
 
 Contents
@@ -70,7 +70,6 @@ Contents
    faq
    troubleshooting
    extending
-   contributing
    scanners
    screenshots
    changelog

docs/requirements.txt

@@ -0,0 +1 @@
+myst-parser==0.18.1

docs/scanners.rst

@@ -1,114 +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.
-
-Physical scanners
-=================
-
-+---------+----------------+-----+-----+-----+------+----------+----------------+
-| Brand   | Model          | Supports                          | Recommended By |
-+---------+----------------+-----+-----+-----+------+----------+----------------+
-|         |                | FTP | NFS | SMB | SMTP | API [1]_ |                |
-+=========+================+=====+=====+=====+======+==========+================+
-| Brother | `ADS-1700W`_   | yes |     | yes | yes  |          |`holzhannes`_   |
-+---------+----------------+-----+-----+-----+------+----------+----------------+
-| Brother | `ADS-1600W`_   | yes |     | yes | yes  |          |`holzhannes`_   |
-+---------+----------------+-----+-----+-----+------+----------+----------------+
-| Brother | `ADS-1500W`_   | yes |     | yes | yes  |          |`danielquinn`_  |
-+---------+----------------+-----+-----+-----+------+----------+----------------+
-| Brother | `ADS-1100W`_   | yes |     |     |      |          |`ytzelf`_       |
-+---------+----------------+-----+-----+-----+------+----------+----------------+
-| Brother | `ADS-2800W`_   | yes | yes |     | yes  | yes      |`philpagel`_    |
-+---------+----------------+-----+-----+-----+------+----------+----------------+
-| Brother | `MFC-J6930DW`_ | yes |     |     |      |          |`ayounggun`_    |
-+---------+----------------+-----+-----+-----+------+----------+----------------+
-| Brother | `MFC-L5850DW`_ | yes |     |     | yes  |          |`holzhannes`_   |
-+---------+----------------+-----+-----+-----+------+----------+----------------+
-| Brother | `MFC-L2750DW`_ | yes |     | yes | yes  |          |`muued`_        |
-+---------+----------------+-----+-----+-----+------+----------+----------------+
-| Brother | `MFC-J5910DW`_ | yes |     |     |      |          |`bmsleight`_    |
-+---------+----------------+-----+-----+-----+------+----------+----------------+
-| Brother | `MFC-8950DW`_  | yes |     |     | yes  | yes      |`philpagel`_    |
-+---------+----------------+-----+-----+-----+------+----------+----------------+
-| Brother | `MFC-9142CDN`_ | yes |     | yes |      |          |`REOLDEV`_      |
-+---------+----------------+-----+-----+-----+------+----------+----------------+
-| Fujitsu | `ix500`_       | yes |     | yes |      |          |`eonist`_       |
-+---------+----------------+-----+-----+-----+------+----------+----------------+
-| Epson   | `ES-580W`_     | yes |     | yes | yes  |          |`fignew`_       |
-+---------+----------------+-----+-----+-----+------+----------+----------------+
-| Epson   | `WF-7710DWF`_  | yes |     | yes |      |          |`Skylinar`_     |
-+---------+----------------+-----+-----+-----+------+----------+----------------+
-| Fujitsu | `S1300i`_      | yes |     | yes |      |          |`jonaswinkler`_ |
-+---------+----------------+-----+-----+-----+------+----------+----------------+
-| Doxie   | `Q2`_          |     |     |     |      | yes      |`Unkn0wnCat`_   |
-+---------+----------------+-----+-----+-----+------+----------+----------------+
-
-.. _MFC-L5850DW: https://www.brother-usa.com/products/mfcl5850dw
-.. _MFC-L2750DW: https://www.brother.de/drucker/laserdrucker/mfc-l2750dw
-.. _ADS-1700W: https://www.brother-usa.com/products/ads1700w
-.. _ADS-1600W: https://www.brother-usa.com/products/ads1600w
-.. _ADS-1500W: https://www.brother.ca/en/p/ads1500w
-.. _ADS-1100W: https://support.brother.com/g/b/downloadtop.aspx?c=fr&lang=fr&prod=ads1100w_eu_as_cn
-.. _ADS-2800W: https://www.brother-usa.com/products/ads2800w
-.. _MFC-J6930DW: https://www.brother.ca/en/p/MFCJ6930DW
-.. _MFC-J5910DW: https://www.brother.co.uk/printers/inkjet-printers/mfcj5910dw
-.. _MFC-8950DW: https://www.brother-usa.com/products/mfc8950dw
-.. _MFC-9142CDN: https://www.brother.co.uk/printers/laser-printers/mfc9140cdn
-.. _ES-580W: https://epson.com/Support/Scanners/ES-Series/Epson-WorkForce-ES-580W/s/SPT_B11B258201
-.. _WF-7710DWF: https://www.epson.de/en/products/printers/inkjet-printers/for-home/workforce-wf-7710dwf
-.. _ix500: http://www.fujitsu.com/us/products/computing/peripheral/scanners/scansnap/ix500/
-.. _S1300i: https://www.fujitsu.com/global/products/computing/peripheral/scanners/soho/s1300i/
-.. _Q2: https://www.getdoxie.com/product/doxie-q/
-
-.. _ayounggun: https://github.com/ayounggun
-.. _bmsleight: https://github.com/bmsleight
-.. _danielquinn: https://github.com/danielquinn
-.. _eonist: https://github.com/eonist
-.. _fignew: https://github.com/fignew
-.. _holzhannes: https://github.com/holzhannes
-.. _jonaswinkler: https://github.com/jonaswinkler
-.. _REOLDEV: https://github.com/REOLDEV
-.. _Skylinar: https://github.com/Skylinar
-.. _ytzelf: https://github.com/ytzelf
-.. _Unkn0wnCat: https://github.com/Unkn0wnCat
-.. _muued: https://github.com/muued
-.. _philpagel: https://github.com/philpagel
-
-.. [1] Scanners with API Integration allow to push scanned documents directly to :ref:`Paperless API <api-file_uploads>`, sometimes referred to as Webhook or Document POST.
-
-Mobile phone software
-=====================
-
-You can use your phone to "scan" documents. The regular camera app will work, but may have too low contrast for OCR to work well. Apps specifically for scanning are recommended.
-
-+-----------------------------+----------------+-----+-----+-----+-------+--------+------------------+
-| Name                        | OS             | Supports                         | Recommended By   |
-+-----------------------------+----------------+-----+-----+-----+-------+--------+------------------+
-|                             |                | FTP | NFS | SMB | Email | WebDAV |                  |
-+=============================+================+=====+=====+=====+=======+========+==================+
-| `Office Lens`_              | Android        | ?   | ?   | ?   | ?     | ?      | `jonaswinkler`_  |
-+-----------------------------+----------------+-----+-----+-----+-------+--------+------------------+
-| `Genius Scan`_              | Android        | yes | no  | yes | yes   | yes    | `hannahswain`_   |
-+-----------------------------+----------------+-----+-----+-----+-------+--------+------------------+
-| `OpenScan`_                 | Android        | no  | no  | no  | no    | no     | `benjaminfrank`_ |
-+-----------------------------+----------------+-----+-----+-----+-------+--------+------------------+
-| `OCR Scanner - QuickScan`_  | iOS            | no  | no  | no  | no    | yes    | `holzhannes`_    |
-+-----------------------------+----------------+-----+-----+-----+-------+--------+------------------+
-
-On Android, you can use these applications in combination with one of the :ref:`Paperless-ngx compatible apps <usage-mobile_upload>` to "Share" the documents produced by these scanner apps with paperless. On iOS, you can share the scanned documents via iOS-Sharing to other mail, WebDav or FTP apps.
-
-.. _Office Lens: https://play.google.com/store/apps/details?id=com.microsoft.office.officelens
-.. _Genius Scan: https://play.google.com/store/apps/details?id=com.thegrizzlylabs.geniusscan.free
-.. _OCR Scanner - QuickScan: https://apps.apple.com/us/app/quickscan-scanner-text-ocr/id1513790291
-.. _OpenScan: https://github.com/Ethereal-Developers-Inc/OpenScan
-
-.. _hannahswain: https://github.com/hannahswain
-.. _benjaminfrank: https://github.com/benjaminfrank
+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-ngx 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

@@ -39,7 +39,7 @@ Paperless consists of the following components:
 
     .. _setup-task_processor:
 
-*   **The task processor:** Paperless relies on `Django Q <https://django-q.readthedocs.io/en/latest/>`_
+*   **The task processor:** Paperless relies on `Celery - Distributed Task Queue <https://docs.celeryq.dev/en/stable/index.html>`_
     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.
@@ -62,18 +62,11 @@ Paperless consists of the following components:
     tasks fail and inspect the errors (i.e., wrong email credentials, errors during consuming a specific
     file, etc).
 
-    You may start the task processor by executing:
-
-    .. code:: shell-session
-
-        $ cd /path/to/paperless/src/
-        $ 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 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
@@ -110,7 +103,7 @@ performs all the steps described in :ref:`setup-docker_hub` automatically.
 
     .. code:: shell-session
 
-        $ bash -c "$(curl -L https://raw.githubusercontent.com/paperless-ngx/paperless-ngx/master/install-paperless-ngx.sh)"
+        $ bash -c "$(curl -L https://raw.githubusercontent.com/paperless-ngx/paperless-ngx/main/install-paperless-ngx.sh)"
 
 .. _setup-docker_hub:
 
@@ -184,6 +177,25 @@ Install Paperless from Docker Hub
     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. Use ``id -u`` and
@@ -200,6 +212,20 @@ Install Paperless from Docker Hub
         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.
 
+    .. note::
+
+        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
@@ -258,7 +284,20 @@ Build the Docker image yourself
     .. code:: yaml
 
         webserver:
-            build: .
+            build:
+              context: .
+              args:
+                QPDF_VERSION: x.y.x
+                PIKEPDF_VERSION: x.y.z
+                PSYCOPG2_VERSION: x.y.z
+                JBIG2ENC_VERSION: 0.29
+
+    .. note::
+
+        You should match the build argument versions to the version for the release you have
+        checked out.  These are pre-built images with certain, more updated software.
+        If you want to build these images your self, that is possible, but beyond
+        the scope of these steps.
 
 4.  Follow steps 3 to 8 of :ref:`setup-docker_hub`. When asked to run
     ``docker-compose pull`` to pull the image, do
@@ -284,19 +323,22 @@ writing. Windows is not and will never be supported.
     *   ``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 optimizing thumbnails
     *   ``gnupg`` for handling encrypted documents
     *   ``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 optipng gnupg libpq-dev libmagic-dev mime-support
+        python3 python3-pip python3-dev imagemagick fonts-liberation gnupg libpq-dev default-libmysqlclient-dev libmagic-dev mime-support libzbar0 poppler-utils
 
     These dependencies are required for OCRmyPDF, which is used for text recognition.
 
@@ -306,7 +348,7 @@ 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)
@@ -325,10 +367,16 @@ writing. Windows is not and will never be supported.
     You will also need ``build-essential``, ``python3-setuptools`` and ``python3-wheel``
     for installing some of the python dependencies.
 
-2.  Install ``redis`` >= 5.0 and configure it to start automatically.
+2.  Install ``redis`` >= 6.0 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 available as well.
+    to use PostgreSQL, MariaDB and SQLite are available as well.
+
+    .. note::
+
+        On bare-metal installations using SQLite, ensure the
+        `JSON1 extension <https://code.djangoproject.com/wiki/JSON1Extension>`_ is enabled. This is
+        usually the case, but not always.
 
 4.  Get the release archive from `<https://github.com/paperless-ngx/paperless-ngx/releases>`_.
     If you clone the git repo as it is, you also have to compile the front end by yourself.
@@ -338,6 +386,7 @@ writing. Windows is not and will never be supported.
     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
@@ -345,6 +394,8 @@ 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:
@@ -416,8 +467,9 @@ writing. Windows is not and will never be supported.
     as a starting point.
 
     Paperless needs the ``webserver`` script to run the webserver, the
-    ``consumer`` script to watch the input folder, and the ``scheduler``
-    script to run tasks such as email checking and document consumption.
+    ``consumer`` script to watch the input folder, ``taskqueue`` for the background workers
+    used to handle things like document consumption and the ``scheduler`` script to run tasks such as
+    email checking at certain times .
 
 		The ``socket`` script enables ``gunicorn`` to run on port 80 without
 		root privileges. For this you need to uncomment the ``Require=paperless-webserver.socket``
@@ -468,6 +520,13 @@ writing. Windows is not and will never be supported.
     to compile this by yourself, because this software has been patented until around 2017 and
     binary packages are not available for most distributions.
 
+15. Optional: If using the NLTK machine learning processing (see ``PAPERLESS_ENABLE_NLTK`` in
+    :ref:`configuration` for details), download the NLTK data for the Snowball Stemmer, Stopwords
+    and Punkt tokenizer to your ``PAPERLESS_DATA_DIR/nltk``.  Refer to
+    the `NLTK instructions <https://www.nltk.org/data.html>`_ for details on how to
+    download the data.
+
+
 Migrating to Paperless-ngx
 ##########################
 
@@ -509,7 +568,7 @@ how you installed paperless.
 This setup describes how to update an existing paperless Docker installation.
 The important things to keep in mind are as follows:
 
-* Read the :ref:`changelog <paperless_changelog>` and take note of breaking changes.
+* Read the :doc:`changelog </changelog>` and take note of breaking changes.
 * You should decide if you want to stick with SQLite or want to migrate your database
   to PostgreSQL. See :ref:`setup-sqlite_to_psql` for details on how to move your data from
   SQLite to PostgreSQL. Both work fine with paperless. However, if you already have a
@@ -589,13 +648,56 @@ Migration to paperless-ngx is then performed in a few simple steps:
 10.  Optionally, follow the instructions below to migrate your existing data to PostgreSQL.
 
 
+Migrating from LinuxServer.io Docker Image
+==========================================
+
+As with any upgrades and large changes, it is highly recommended to create a backup before
+starting.  This assumes the image was running using Docker Compose, but the instructions
+are translatable to Docker commands as well.
+
+1.  Stop and remove the paperless container
+2.  If using an external database, stop the container
+3.  Update Redis configuration
+
+    a)  If ``REDIS_URL`` is already set, change it to ``PAPERLESS_REDIS`` and continue
+        to step 4.
+    b)  Otherwise, in the ``docker-compose.yml`` add a new service for Redis,
+        following `the example compose files <https://github.com/paperless-ngx/paperless-ngx/tree/main/docker/compose>`_
+    c)  Set the environment variable ``PAPERLESS_REDIS`` so it points to the new Redis container
+
+4.  Update user mapping
+
+    a)  If set, change the environment variable ``PUID`` to ``USERMAP_UID``
+    b)  If set, change the environment variable ``PGID`` to ``USERMAP_GID``
+
+5.  Update configuration paths
+
+    a) Set the environment variable ``PAPERLESS_DATA_DIR``
+       to ``/config``
+
+6.  Update media paths
+
+    a) Set the environment variable ``PAPERLESS_MEDIA_ROOT``
+       to ``/data/media``
+
+7.  Update timezone
+
+    a) Set the environment variable ``PAPERLESS_TIME_ZONE``
+       to the same value as ``TZ``
+
+8.  Modify the ``image:`` to point to ``ghcr.io/paperless-ngx/paperless-ngx:latest`` or
+    a specific version if preferred.
+
+9.  Start the containers as before, using ``docker-compose``.
+
 .. _setup-sqlite_to_psql:
 
-Moving data from SQLite to PostgreSQL
-=====================================
+Moving data from SQLite to PostgreSQL or MySQL/MariaDB
+======================================================
 
-Moving your data from SQLite to PostgreSQL is done via executing a series of django
-management commands as below.
+Moving your data from SQLite to PostgreSQL or MySQL/MariaDB is done via executing a series of django
+management commands as below.  The commands below use PostgreSQL, but are applicable to MySQL/MariaDB
+with the
 
 .. caution::
 
@@ -612,6 +714,11 @@ management commands as below.
     and filenames (1024 characters). If you have data in these fields that surpasses these
     limits, migration to PostgreSQL is not possible and will fail with an error.
 
+.. warning::
+
+    MySQL is case insensitive by default, treating values like "Name" and "NAME" as identical.
+    See :ref:`advanced-mysql-caveats` for details.
+
 
 1.  Stop paperless, if it is running.
 2.  Tell paperless to use PostgreSQL:
@@ -720,10 +827,10 @@ configuring some options in paperless can help improve performance immensely:
 *   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.
-*   Set ``PAPERLESS_OPTIMIZE_THUMBNAILS`` to 'false' if you want faster consumption
-    times. Thumbnails will be about 20% larger.
 *   If using docker, consider setting ``PAPERLESS_WEBSERVER_WORKERS`` to
     1. This will save some memory.
+*   Consider setting ``PAPERLESS_ENABLE_NLTK`` to false, to disable the more
+    advanced language processing, which can take more memory and processing time.
 
 For details, refer to :ref:`configuration`.
 
@@ -782,4 +889,6 @@ the following configuration is required for paperless to operate:
         }
     }
 
+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

@@ -19,12 +19,25 @@ Check for the following issues:
 
     .. code:: shell-session
 
-        $ python3 manage.py qcluster
+        $ celery --app paperless worker
 
 *   Look at the output of paperless and inspect it for any errors.
 *   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
 ######################################
@@ -106,17 +119,18 @@ You may experience these errors when using the optional TIKA integration:
 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 an environment variable for Gotenberg (see also `here <https://gotenberg.dev/docs/modules/api#properties>`__).
+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
+        image: gotenberg/gotenberg:7.6
         restart: unless-stopped
-        environment:
-            CHROMIUM_DISABLE_ROUTES: 1
-            API_PROCESS_TIMEOUT: 60
+        command:
+            - "gotenberg"
+            - "--chromium-disable-routes=true"
+            - "--api-timeout=60"
 
 Permission denied errors in the consumption directory
 #####################################################
@@ -221,3 +235,94 @@ You might find messages like these in your log files:
 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.
+
+
+gunicorn fails to start with "is not a valid port number"
+#########################################################
+
+You are likely running using Kubernetes, which automatically creates an environment variable named `${serviceName}_PORT`.
+This is the same environment variable which is used by Paperless to optionally change the port gunicorn listens on.
+
+To fix this, set `PAPERLESS_PORT` again to your desired port, or the default of 8000.

docs/usage_overview.rst

@@ -62,7 +62,7 @@ your documents:
 
 1.  OCR the document, if it has no text. Digital documents usually have text,
     and this step will be skipped for those documents.
-2.  Paperless will create an archiveable PDF/A document from your document.
+2.  Paperless will create an archivable PDF/A document from your document.
     If this document is coming from your scanner, it will have embedded selectable text.
 3.  Paperless performs automatic matching of tags, correspondents and types on the
     document before storing it in the database.
@@ -102,12 +102,14 @@ files from the scanner.  Typically, you're looking at an FTP server like
 
 .. TODO: hyperref to configuration of the location of this magic folder.
 
-Dashboard upload
-================
+Web UI Upload
+=============
 
 The dashboard has a file drop field to upload documents to paperless. Simply drag a file
 onto this field or select a file with the file dialog. Multiple files are supported.
 
+You can also upload documents on any other page of the web UI by dragging-and-dropping
+files into your browser window.
 
 .. _usage-mobile_upload:
 
@@ -159,6 +161,9 @@ These are as follows:
     will not consume flagged mails.
 *   **Move to folder:** Moves consumed mails out of the way so that paperless wont
     consume them again.
+*   **Add custom Tag:** Adds a custom tag to mails with consumed documents (the IMAP
+    standard calls these "keywords"). Paperless will not consume mails already tagged.
+    Not all mail servers support this feature!
 
 .. caution::
 
@@ -178,6 +183,15 @@ These are as follows:
     automatically or manually and tell paperless to move them to yet another folder
     after consumption. It's up to you.
 
+.. note::
+
+    When defining a mail rule with a folder, you may need to try different characters to
+    define how the sub-folders are separated.  Common values include ".", "/" or "|", but
+    this varies by the mail server.  Check the documentation for your mail server.  In the
+    event of an error fetching mail from a certain folder, check the Paperless logs.  When
+    a folder is not located, Paperless will attempt to list all folders found in the account
+    to the Paperless logs.
+
 .. note::
 
     Paperless will process the rules in the order defined in the admin page.

gunicorn.conf.py

@@ -1,9 +1,17 @@
 import os
 
-bind = f'0.0.0.0:{os.getenv("PAPERLESS_PORT", 8000)}'
-workers = int(os.getenv("PAPERLESS_WEBSERVER_WORKERS", 2))
+# See https://docs.gunicorn.org/en/stable/settings.html for
+# explanations of settings
+
+bind = f'{os.getenv("PAPERLESS_BIND_ADDR", "[::]")}:{os.getenv("PAPERLESS_PORT", 8000)}'
+
+workers = int(os.getenv("PAPERLESS_WEBSERVER_WORKERS", 1))
 worker_class = "paperless.workers.ConfigurableWorker"
 timeout = 120
+preload_app = True
+
+# https://docs.gunicorn.org/en/stable/faq.html#blocking-os-fchmod
+worker_tmp_dir = "/dev/shm"
 
 
 def pre_fork(server, worker):
@@ -24,7 +32,7 @@ def worker_int(worker):
     ## get traceback info
     import threading, sys, traceback
 
-    id2name = dict([(th.ident, th.name) for th in threading.enumerate()])
+    id2name = {th.ident: th.name for th in threading.enumerate()}
     code = []
     for threadId, stack in sys._current_frames().items():
         code.append("\n# Thread: %s(%d)" % (id2name.get(threadId, ""), threadId))

install-paperless-ngx.sh

@@ -1,18 +1,18 @@
-#!/bin/bash
+#!/usr/bin/env bash
 
 ask() {
 	while true ; do
 		if [[ -z $3 ]] ; then
-			read -p "$1 [$2]: " result
+			read -r -p "$1 [$2]: " result
 		else
-			read -p "$1 ($3) [$2]: " result
+			read -r -p "$1 ($3) [$2]: " result
 		fi
 		if [[ -z $result ]]; then
 			ask_result=$2
 			return
 		fi
 		array=$3
-		if [[ -z $3 || " ${array[@]} " =~ " ${result} " ]]; then
+		if [[ -z $3 || " ${array[*]} " =~ ${result} ]]; then
 			ask_result=$result
 			return
 		else
@@ -24,7 +24,7 @@ ask() {
 ask_docker_folder() {
 	while true ; do
 
-		read -p "$1 [$2]: " result
+		read -r -p "$1 [$2]: " result
 
 		if [[ -z $result ]]; then
 			ask_result=$2
@@ -47,25 +47,29 @@ if [[ $(id -u) == "0" ]] ; then
 	exit 1
 fi
 
-if [[ -z $(which wget) ]] ; then
+if ! command -v wget &> /dev/null ; then
 	echo "wget executable not found. Is wget installed?"
 	exit 1
 fi
 
-if [[ -z $(which docker) ]] ; then
+if ! command -v docker &> /dev/null ; then
 	echo "docker executable not found. Is docker installed?"
 	exit 1
 fi
 
-if [[ -z $(which docker-compose) ]] ; then
-	echo "docker-compose executable not found. Is docker-compose installed?"
-	exit 1
+DOCKER_COMPOSE_CMD="docker-compose"
+if ! command -v ${DOCKER_COMPOSE_CMD} ; then
+	if docker compose version &> /dev/null ; then
+		DOCKER_COMPOSE_CMD="docker compose"
+	else
+		echo "docker-compose executable not found. Is docker-compose installed?"
+		exit 1
+	fi
 fi
 
 # Check if user has permissions to run Docker by trying to get the status of Docker (docker status).
 # If this fails, the user probably does not have permissions for Docker.
-docker stats --no-stream 2>/dev/null 1>&2
-if [ $? -ne 0 ] ; then
+if ! docker stats --no-stream &> /dev/null ; then
 	echo ""
 	echo "WARN: It look like the current user does not have Docker permissions."
 	echo "WARN: Use 'sudo usermod -aG docker $USER' to assign Docker permissions to the user."
@@ -88,6 +92,14 @@ echo ""
 echo "1. Application configuration"
 echo "============================"
 
+echo ""
+echo "The URL paperless will be available at. This is required if the"
+echo "installation will be accessible via the web, otherwise can be left blank."
+echo ""
+
+ask "URL" ""
+URL=$ask_result
+
 echo ""
 echo "The port on which the paperless webserver will listen for incoming"
 echo "connections."
@@ -106,12 +118,12 @@ ask "Current time zone" "$default_time_zone"
 TIME_ZONE=$ask_result
 
 echo ""
-echo "Database backend: PostgreSQL and SQLite are available. Use PostgreSQL"
+echo "Database backend: PostgreSQL, MariaDB, and SQLite are available. Use PostgreSQL"
 echo "if unsure. If you're running on a low-power device such as Raspberry"
 echo "Pi, use SQLite to save resources."
 echo ""
 
-ask "Database backend" "postgres" "postgres sqlite"
+ask "Database backend" "postgres" "postgres sqlite mariadb"
 DATABASE_BACKEND=$ask_result
 
 echo ""
@@ -162,7 +174,7 @@ ask "Target folder" "$(pwd)/paperless-ngx"
 TARGET_FOLDER=$ask_result
 
 echo ""
-echo "The consume folder is where paperles will search for new documents."
+echo "The consume folder is where paperless will search for new documents."
 echo "Point this to a folder where your scanner is able to put your scanned"
 echo "documents."
 echo ""
@@ -202,9 +214,9 @@ echo ""
 ask_docker_folder "Data folder" ""
 DATA_FOLDER=$ask_result
 
-if [[ "$DATABASE_BACKEND" == "postgres" ]] ; then
+if [[ "$DATABASE_BACKEND" == "postgres" || "$DATABASE_BACKEND" == "mariadb" ]] ; then
 	echo ""
-	echo "The database folder, where postgres stores its data."
+	echo "The database folder, where your database stores its data."
 	echo "Leave empty to have this managed by docker."
 	echo ""
 	echo "CAUTION: If specified, you must specify an absolute path starting with /"
@@ -212,7 +224,7 @@ if [[ "$DATABASE_BACKEND" == "postgres" ]] ; then
 	echo ""
 
 	ask_docker_folder "Database folder" ""
-	POSTGRES_FOLDER=$ask_result
+	DATABASE_FOLDER=$ask_result
 fi
 
 echo ""
@@ -228,7 +240,7 @@ ask "Paperless username" "$(whoami)"
 USERNAME=$ask_result
 
 while true; do
-	read -sp "Paperless password: " PASSWORD
+	read -r -sp "Paperless password: " PASSWORD
 	echo ""
 
 	if [[ -z $PASSWORD ]] ; then
@@ -236,7 +248,7 @@ while true; do
 		continue
 	fi
 
-	read -sp "Paperless password (again): " PASSWORD_REPEAT
+	read -r -sp "Paperless password (again): " PASSWORD_REPEAT
 	echo ""
 
 	if [[ ! "$PASSWORD" == "$PASSWORD_REPEAT" ]] ; then
@@ -266,14 +278,16 @@ if [[ -z $DATA_FOLDER ]] ; then
 else
 	echo "Data folder: $DATA_FOLDER"
 fi
-if [[ "$DATABASE_BACKEND" == "postgres" ]] ; then
-	if [[ -z $POSTGRES_FOLDER ]] ; then
-		echo "Database (postgres) folder: Managed by docker"
+if [[ "$DATABASE_BACKEND" == "postgres" || "$DATABASE_BACKEND" == "mariadb" ]] ; then
+	if [[ -z $DATABASE_FOLDER ]] ; then
+		echo "Database folder: Managed by docker"
 	else
-		echo "Database (postgres) folder: $POSTGRES_FOLDER"
+		echo "Database folder: $DATABASE_FOLDER"
 	fi
 fi
+
 echo ""
+echo "URL: $URL"
 echo "Port: $PORT"
 echo "Database: $DATABASE_BACKEND"
 echo "Tika enabled: $TIKA_ENABLED"
@@ -285,7 +299,7 @@ echo "Paperless username: $USERNAME"
 echo "Paperless email: $EMAIL"
 
 echo ""
-read -p "Press any key to install."
+read -r -p "Press any key to install."
 
 echo ""
 echo "Installing paperless..."
@@ -301,14 +315,20 @@ if [[ $TIKA_ENABLED == "yes" ]] ; then
 	DOCKER_COMPOSE_VERSION="$DOCKER_COMPOSE_VERSION-tika"
 fi
 
-wget "https://raw.githubusercontent.com/paperless-ngx/paperless-ngx/master/docker/compose/docker-compose.$DOCKER_COMPOSE_VERSION.yml" -O docker-compose.yml
-wget "https://raw.githubusercontent.com/paperless-ngx/paperless-ngx/master/docker/compose/.env" -O .env
+wget "https://raw.githubusercontent.com/paperless-ngx/paperless-ngx/main/docker/compose/docker-compose.$DOCKER_COMPOSE_VERSION.yml" -O docker-compose.yml
+wget "https://raw.githubusercontent.com/paperless-ngx/paperless-ngx/main/docker/compose/.env" -O .env
 
-SECRET_KEY=$(cat /dev/urandom | tr -dc 'a-zA-Z0-9' | fold -w 64 | head -n 1)
+SECRET_KEY=$(tr -dc 'a-zA-Z0-9' < /dev/urandom | fold -w 64 | head -n 1)
 
-DEFAULT_LANGUAGES="deu eng fra ita spa"
+DEFAULT_LANGUAGES=("deu eng fra ita spa")
+
+_split_langs="${OCR_LANGUAGE//+/ }"
+read -r -a OCR_LANGUAGES_ARRAY <<< "${_split_langs}"
 
 {
+	if [[ ! $URL == "" ]] ; then
+		echo "PAPERLESS_URL=$URL"
+	fi
 	if [[ ! $USERMAP_UID == "1000" ]] ; then
 		echo "USERMAP_UID=$USERMAP_UID"
 	fi
@@ -318,8 +338,8 @@ DEFAULT_LANGUAGES="deu eng fra ita spa"
 	echo "PAPERLESS_TIME_ZONE=$TIME_ZONE"
 	echo "PAPERLESS_OCR_LANGUAGE=$OCR_LANGUAGE"
 	echo "PAPERLESS_SECRET_KEY=$SECRET_KEY"
-	if [[ ! " ${DEFAULT_LANGUAGES[@]} " =~ " ${OCR_LANGUAGE} " ]] ; then
-		echo "PAPERLESS_OCR_LANGUAGES=$OCR_LANGUAGE"
+	if [[ ! ${DEFAULT_LANGUAGES[*]} =~ ${OCR_LANGUAGES_ARRAY[*]} ]] ; then
+		echo "PAPERLESS_OCR_LANGUAGES=${OCR_LANGUAGES_ARRAY[*]}"
 	fi
 } > docker-compose.env
 
@@ -329,18 +349,38 @@ sed -i "s#- \./consume:/usr/src/paperless/consume#- $CONSUME_FOLDER:/usr/src/pap
 
 if [[ -n $MEDIA_FOLDER ]] ; then
 	sed -i "s#- media:/usr/src/paperless/media#- $MEDIA_FOLDER:/usr/src/paperless/media#g" docker-compose.yml
+	sed -i "/^\s*media:/d" docker-compose.yml
 fi
 
 if [[ -n $DATA_FOLDER ]] ; then
 	sed -i "s#- data:/usr/src/paperless/data#- $DATA_FOLDER:/usr/src/paperless/data#g" docker-compose.yml
+	sed -i "/^\s*data:/d" docker-compose.yml
 fi
 
-if [[ -n $POSTGRES_FOLDER ]] ; then
-	sed -i "s#- pgdata:/var/lib/postgresql/data#- $POSTGRES_FOLDER:/var/lib/postgresql/data#g" docker-compose.yml
+# If the database folder was provided (not blank), replace the pgdata/dbdata volume with a bind mount
+# of the provided folder
+if [[ -n $DATABASE_FOLDER ]] ; then
+	if [[ "$DATABASE_BACKEND" == "postgres" ]] ; then
+		sed -i "s#- pgdata:/var/lib/postgresql/data#- $DATABASE_FOLDER:/var/lib/postgresql/data#g" docker-compose.yml
+		sed -i "/^\s*pgdata:/d" docker-compose.yml
+	elif [[ "$DATABASE_BACKEND" == "mariadb" ]]; then
+		sed -i "s#- dbdata:/var/lib/mysql#- $DATABASE_FOLDER:/var/lib/mysql#g" docker-compose.yml
+		sed -i "/^\s*dbdata:/d" docker-compose.yml
+	fi
 fi
 
-docker-compose pull
+# remove trailing blank lines from end of file
+sed -i -e :a -e '/^\n*$/{$d;N;};/\n$/ba' docker-compose.yml
+# if last line in file contains "volumes:", remove that line since no more named volumes are left
+l1=$(grep -n '^volumes:' docker-compose.yml | cut -d : -f 1)  # get line number containing volume: at begin of line
+l2=$(wc -l < docker-compose.yml)  # get total number of lines
+if [ "$l1" -eq "$l2" ] ; then
+	sed -i "/^volumes:/d" docker-compose.yml
+fi
 
-docker-compose run --rm -e DJANGO_SUPERUSER_PASSWORD="$PASSWORD" webserver createsuperuser --noinput --username "$USERNAME" --email "$EMAIL"
 
-docker-compose up -d
+${DOCKER_COMPOSE_CMD} pull
+
+${DOCKER_COMPOSE_CMD} run --rm -e DJANGO_SUPERUSER_PASSWORD="$PASSWORD" webserver createsuperuser --noinput --username "$USERNAME" --email "$EMAIL"
+
+${DOCKER_COMPOSE_CMD} up --detach

paperless.conf.example

@@ -23,12 +23,15 @@
 #PAPERLESS_MEDIA_ROOT=../media
 #PAPERLESS_STATICDIR=../static
 #PAPERLESS_FILENAME_FORMAT=
+#PAPERLESS_FILENAME_FORMAT_REMOVE_NONE=
 
 # Security and hosting
 
 #PAPERLESS_SECRET_KEY=change-me
-#PAPERLESS_ALLOWED_HOSTS=example.com,www.example.com
-#PAPERLESS_CORS_ALLOWED_HOSTS=http://example.com,http://localhost:8000
+#PAPERLESS_URL=https://example.com
+#PAPERLESS_CSRF_TRUSTED_ORIGINS=https://example.com # can be set using PAPERLESS_URL
+#PAPERLESS_ALLOWED_HOSTS=example.com,www.example.com # can be set using PAPERLESS_URL
+#PAPERLESS_CORS_ALLOWED_HOSTS=https://localhost:8080,https://example.com # can be set using PAPERLESS_URL
 #PAPERLESS_FORCE_SCRIPT_NAME=
 #PAPERLESS_STATIC_URL=/static/
 #PAPERLESS_AUTO_LOGIN_USERNAME=
@@ -58,15 +61,18 @@
 #PAPERLESS_CONSUMER_POLLING=10
 #PAPERLESS_CONSUMER_DELETE_DUPLICATES=false
 #PAPERLESS_CONSUMER_RECURSIVE=false
-#PAPERLESS_CONSUMER_IGNORE_PATTERNS=[".DS_STORE/*", "._*", ".stfolder/*"]
+#PAPERLESS_CONSUMER_IGNORE_PATTERNS=[".DS_STORE/*", "._*", ".stfolder/*", ".stversions/*", ".localized/*", "desktop.ini"]
 #PAPERLESS_CONSUMER_SUBDIRS_AS_TAGS=false
-#PAPERLESS_OPTIMIZE_THUMBNAILS=true
+#PAPERLESS_CONSUMER_ENABLE_BARCODES=false
+#PAPERLESS_CONSUMER_BARCODE_STRING=PATCHT
 #PAPERLESS_PRE_CONSUME_SCRIPT=/path/to/an/arbitrary/script.sh
 #PAPERLESS_POST_CONSUME_SCRIPT=/path/to/an/arbitrary/script.sh
 #PAPERLESS_FILENAME_DATE_ORDER=YMD
 #PAPERLESS_FILENAME_PARSE_TRANSFORMS=[]
+#PAPERLESS_NUMBER_OF_SUGGESTED_DATES=5
 #PAPERLESS_THUMBNAIL_FONT_NAME=
 #PAPERLESS_IGNORE_DATES=
+#PAPERLESS_ENABLE_UPDATE_CHECK=
 
 # Tika settings
 
@@ -78,4 +84,3 @@
 
 #PAPERLESS_CONVERT_BINARY=/usr/bin/convert
 #PAPERLESS_GS_BINARY=/usr/bin/gs
-#PAPERLESS_OPTIPNG_BINARY=/usr/bin/optipng

requirements.txt

@@ -1,109 +0,0 @@
-#
-# These requirements were autogenerated by pipenv
-# To regenerate from the project's Pipfile, run:
-#
-#    pipenv lock --requirements
-#
-
--i https://pypi.python.org/simple
---extra-index-url https://www.piwheels.org/simple
-aioredis==1.3.1
-arrow==1.2.2; python_version >= '3.6'
-asgiref==3.5.0; python_version >= '3.7'
-async-timeout==4.0.2; python_version >= '3.6'
-attrs==21.4.0; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3, 3.4'
-autobahn==22.2.2; python_version >= '3.7'
-automat==20.2.0
-backports.zoneinfo==0.2.1
-blessed==1.19.1; python_version >= '2.7'
-certifi==2021.10.8
-cffi==1.15.0
-channels-redis==3.3.1
-channels==3.0.4
-chardet==4.0.0; python_version >= '3.1'
-charset-normalizer==2.0.12; python_version >= '3'
-click==8.0.4; python_version >= '3.6'
-coloredlogs==15.0.1; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3, 3.4'
-concurrent-log-handler==0.9.20
-constantly==15.1.0
-cryptography==36.0.1
-daphne==3.0.2; python_version >= '3.6'
-dateparser==1.1.0
-django-cors-headers==3.11.0
-django-extensions==3.1.5
-django-filter==21.1
-django-picklefield==3.0.1; python_version >= '3'
-django-q==1.3.9
-django==3.2.12
-djangorestframework==3.13.1
-filelock==3.6.0
-fuzzywuzzy[speedup]==0.18.0
-gunicorn==20.1.0
-h11==0.13.0; python_version >= '3.6'
-hiredis==2.0.0; python_version >= '3.6'
-httptools==0.3.0
-humanfriendly==10.0; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3, 3.4'
-hyperlink==21.0.0
-idna==3.3; python_version >= '3.5'
-imap-tools==0.51.1
-img2pdf==0.4.3
-importlib-resources==5.4.0; python_version < '3.9'
-incremental==21.3.0
-inotify-simple==1.3.5; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3'
-inotifyrecursive==0.3.5
-joblib==1.1.0; python_version >= '3.6'
-langdetect==1.0.9
-lxml==4.8.0; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3, 3.4'
-msgpack==1.0.3
-numpy==1.22.2
-ocrmypdf==13.4.0
-packaging==21.3; python_version >= '3.6'
-pathvalidate==2.5.0
-pdfminer.six==20211012
-pikepdf==5.0.1
-pillow==9.0.1
-pluggy==1.0.0; python_version >= '3.6'
-portalocker==2.4.0; python_version >= '3'
-psycopg2-binary==2.9.3
-pyasn1-modules==0.2.8
-pyasn1==0.4.8
-pycparser==2.21; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3'
-pyopenssl==22.0.0; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3, 3.4'
-pyparsing==3.0.7; python_version >= '3.6'
-python-dateutil==2.8.2
-python-dotenv==0.19.2
-python-gnupg==0.4.8
-python-levenshtein==0.12.2
-python-magic==0.4.25
-pytz-deprecation-shim==0.1.0.post0; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3, 3.4, 3.5'
-pytz==2021.3
-pyyaml==6.0
-redis==3.5.3
-regex==2022.1.18
-reportlab==3.6.7; python_version >= '3.6' and python_version < '4'
-requests==2.27.1; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3, 3.4, 3.5'
-scikit-learn==0.24.0
-scipy==1.8.0; python_version < '3.11' and python_version >= '3.8'
-service-identity==21.1.0
-setuptools==60.9.3; python_version >= '3.7'
-six==1.16.0; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3'
-sqlparse==0.4.2; python_version >= '3.5'
-threadpoolctl==3.1.0; python_version >= '3.6'
-tika==1.24
-tqdm==4.62.3
-twisted[tls]==22.1.0; python_full_version >= '3.6.7'
-txaio==22.2.1; python_version >= '3.6'
-typing-extensions==4.1.1; python_version >= '3.6'
-tzdata==2021.5; python_version >= '3.6'
-tzlocal==4.1; python_version >= '3.6'
-urllib3==1.26.8; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3, 3.4' and python_version < '4'
-uvicorn[standard]==0.17.5
-uvloop==0.16.0
-watchdog==2.1.6
-watchgod==0.7
-wcwidth==0.2.5
-websockets==10.2
-whitenoise==6.0.0
-whoosh==2.7.4
-zipp==3.7.0; python_version < '3.10'
-zope.interface==5.4.0; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3, 3.4'

scripts/paperless-scheduler.service

@@ -1,12 +1,12 @@
 [Unit]
-Description=Paperless scheduler
+Description=Paperless Celery Beat
 Requires=redis.service
 
 [Service]
 User=paperless
 Group=paperless
 WorkingDirectory=/opt/paperless/src
-ExecStart=python3 manage.py qcluster
+ExecStart=celery --app paperless beat --loglevel INFO
 
 [Install]
 WantedBy=multi-user.target

scripts/paperless-task-queue.service

@@ -0,0 +1,12 @@
+[Unit]
+Description=Paperless Celery Workers
+Requires=redis.service
+
+[Service]
+User=paperless
+Group=paperless
+WorkingDirectory=/opt/paperless/src
+ExecStart=celery --app paperless worker --loglevel INFO
+
+[Install]
+WantedBy=multi-user.target

scripts/post-consumption-example.sh

@@ -1,21 +1,16 @@
 #!/usr/bin/env bash
 
-DOCUMENT_ID=${1}
-DOCUMENT_FILE_NAME=${2}
-DOCUMENT_SOURCE_PATH=${3}
-DOCUMENT_THUMBNAIL_PATH=${4}
-DOCUMENT_DOWNLOAD_URL=${5}
-DOCUMENT_THUMBNAIL_URL=${6}
-DOCUMENT_CORRESPONDENT=${7}
-DOCUMENT_TAGS=${8}
-
 echo "
 
 A document with an id of ${DOCUMENT_ID} was just consumed.  I know the
 following additional information about it:
 
 * Generated File Name: ${DOCUMENT_FILE_NAME}
+* Archive Path: ${DOCUMENT_ARCHIVE_PATH}
 * Source Path: ${DOCUMENT_SOURCE_PATH}
+* Created: ${DOCUMENT_CREATED}
+* Added: ${DOCUMENT_ADDED}
+* Modified: ${DOCUMENT_MODIFIED}
 * Thumbnail Path: ${DOCUMENT_THUMBNAIL_PATH}
 * Download URL: ${DOCUMENT_DOWNLOAD_URL}
 * Thumbnail URL: ${DOCUMENT_THUMBNAIL_URL}

scripts/start_services.sh

@@ -1,4 +1,6 @@
+#!/usr/bin/env bash
+
 docker run -p 5432:5432 -e POSTGRES_PASSWORD=password -v paperless_pgdata:/var/lib/postgresql/data -d postgres:13
 docker run -d -p 6379:6379 redis:latest
-docker run -p 3000:3000 -d gotenberg/gotenberg:7
-docker run -p 9998:9998 -d apache/tika
+docker run -p 3000:3000 -d gotenberg/gotenberg:7.6
+docker run -p 9998:9998 -d ghcr.io/paperless-ngx/tika:latest

src-ui/.gitignore

@@ -45,3 +45,7 @@ testem.log
 # System Files
 .DS_Store
 Thumbs.db
+
+# Cypress
+cypress/videos/**/*
+cypress/screenshots/**/*