Merge branch 'dev' into feature-permissions

.codecov.yml

@@ -0,0 +1,19 @@
+# https://docs.codecov.com/docs/pull-request-comments
+# codecov will only comment if coverage changes
+comment:
+  require_changes: true
+coverage:
+  status:
+    project:
+      default:
+        # https://docs.codecov.com/docs/commit-status#threshold
+        threshold: 1%
+        # https://docs.codecov.com/docs/commit-status#only_pulls
+        only_pulls: true
+    patch:
+      default:
+        # For the changed lines only, target 75% covered, but
+        # allow as low as 50%
+        target: 75%
+        threshold: 25%
+        only_pulls: true

.github/workflows/ci.yml

@@ -113,16 +113,12 @@ jobs:
       PAPERLESS_MAIL_TEST_HOST: ${{ secrets.TEST_MAIL_HOST }}
       PAPERLESS_MAIL_TEST_USER: ${{ secrets.TEST_MAIL_USER }}
       PAPERLESS_MAIL_TEST_PASSWD: ${{ secrets.TEST_MAIL_PASSWD }}
-      # Skip Tests which require convert
-      PAPERLESS_TEST_SKIP_CONVERT: 1
       # Enable Gotenberg end to end testing
       GOTENBERG_LIVE: 1
     steps:
       -
         name: Checkout
         uses: actions/checkout@v3
-        with:
-          fetch-depth: 0
       -
         name: Start containers
         run: |
@@ -145,6 +141,10 @@ jobs:
         run: |
           sudo apt-get update -qq
           sudo apt-get install -qq --no-install-recommends unpaper tesseract-ocr imagemagick ghostscript libzbar0 poppler-utils
+      -
+        name: Configure ImageMagick
+        run: |
+          sudo cp docker/imagemagick-policy.xml /etc/ImageMagick-6/policy.xml
       -
         name: Install Python dependencies
         run: |
@@ -160,27 +160,14 @@ jobs:
           cd src/
           pipenv --python ${{ steps.setup-python.outputs.python-version }} run pytest -ra
       -
-        name: Get changed files
+        name: Upload coverage to Codecov
-        id: changed-files-specific
+        if: matrix.python-version == ${{ env.DEFAULT_PYTHON_VERSION }}
-        uses: tj-actions/changed-files@v35
+        uses: codecov/codecov-action@v3
         with:
-          files: |
+          # not required for public repos, but intermittently fails otherwise
-            src/**
+          token: ${{ secrets.CODECOV_TOKEN }}
-      -
+          # future expansion
-        name: List all changed files
+          flags: backend
-        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 == ${{ env.DEFAULT_PYTHON_VERSION }} && steps.changed-files-specific.outputs.any_changed == 'true'
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        # https://github.com/coveralls-clients/coveralls-python/issues/251
-        run: |
-          cd src/
-          pipenv --python ${{ steps.setup-python.outputs.python-version }} run coveralls --service=github
       -
         name: Stop containers
         if: always()
@@ -347,7 +334,7 @@ jobs:
           password: ${{ secrets.DOCKERHUB_TOKEN }}
       -
         name: Build and push
-        uses: docker/build-push-action@v3
+        uses: docker/build-push-action@v4
         with:
           context: .
           file: ./Dockerfile
@@ -442,21 +429,48 @@ jobs:
       -
         name: Move files
         run: |
-          mkdir dist
+          echo "Making dist folders"
-          mkdir dist/paperless-ngx
+          for directory in dist \
-          mkdir dist/paperless-ngx/scripts
+                          dist/paperless-ngx \
-          cp .dockerignore .env Dockerfile Pipfile Pipfile.lock requirements.txt LICENSE README.md dist/paperless-ngx/
+                          dist/paperless-ngx/scripts;
-          cp paperless.conf.example dist/paperless-ngx/paperless.conf
+          do
-          cp gunicorn.conf.py dist/paperless-ngx/gunicorn.conf.py
+            mkdir --verbose --parents ${directory}
-          cp -r docker/ dist/paperless-ngx/docker
+          done
-          cp scripts/*.service scripts/*.sh scripts/*.socket dist/paperless-ngx/scripts/
+
-          cp -r src/ dist/paperless-ngx/src
+          echo "Copying basic files"
-          cp -r docs/_build/html/ dist/paperless-ngx/docs
+          for file_name in .dockerignore \
-          mv static dist/paperless-ngx
+                          .env \
+                          Dockerfile \
+                          Pipfile \
+                          Pipfile.lock \
+                          requirements.txt \
+                          LICENSE \
+                          README.md \
+                          paperless.conf.example \
+                          gunicorn.conf.py
+          do
+            cp --verbose ${file_name} dist/paperless-ngx/
+          done
+          mv --verbose dist/paperless-ngx/paperless.conf.example paperless.conf
+
+          echo "Copying Docker related files"
+          cp --recursive docker/ dist/paperless-ngx/docker
+
+          echo "Copying startup scripts"
+          cp --verbose scripts/*.service scripts/*.sh scripts/*.socket dist/paperless-ngx/scripts/
+
+          echo "Copying source files"
+          cp --recursive src/ dist/paperless-ngx/src
+          echo "Copying documentation"
+          cp --recursive docs/_build/html/ dist/paperless-ngx/docs
+
+          mv --verbose static dist/paperless-ngx
       -
         name: Make release package
         run: |
+          echo "Creating release archive"
           cd dist
+          sudo chown -R 1000:1000 paperless-ngx/
           tar -cJf paperless-ngx.tar.xz paperless-ngx/
       -
         name: Upload release artifact

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

@@ -45,7 +45,7 @@ jobs:
         uses: docker/setup-qemu-action@v2
       -
         name: Build ${{ fromJSON(inputs.build-json).name }}
-        uses: docker/build-push-action@v3
+        uses: docker/build-push-action@v4
         with:
           context: .
           file: ${{ inputs.dockerfile }}

Dockerfile

@@ -1,4 +1,5 @@
 # syntax=docker/dockerfile:1.4
+# https://github.com/moby/buildkit/blob/master/frontend/dockerfile/docs/reference.md
 
 FROM --platform=$BUILDPLATFORM node:16-bullseye-slim AS compile-frontend
 
@@ -61,10 +62,6 @@ ARG PSYCOPG2_VERSION
 
 # Packages need for running
 ARG RUNTIME_PACKAGES="\
-  # Python
-  python3 \
-  python3-pip \
-  python3-setuptools \
   # General utils
   curl \
   # Docker specific
@@ -128,7 +125,7 @@ RUN set -eux \
     && 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
+    && python3 -m pip install --default-timeout=1000 --upgrade --no-cache-dir supervisor==4.2.5
 
 # Copy gunicorn config
 # Changes very infrequently
@@ -137,7 +134,6 @@ 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/
 
@@ -179,7 +175,6 @@ RUN set -eux \
     && ./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 set -eux \
   && echo "Getting binaries" \
@@ -203,7 +198,8 @@ RUN set -eux \
     && python3 -m pip list \
   && echo "Cleaning up image layer" \
     && cd ../ \
-    && rm -rf paperless-ngx
+    && rm -rf paperless-ngx \
+    && rm paperless-ngx.tar.gz
 
 WORKDIR /usr/src/paperless/src/
 
@@ -247,11 +243,12 @@ COPY ./src ./
 COPY --from=compile-frontend /src/src/documents/static/frontend/ ./documents/static/frontend/
 
 # add users, setup scripts
+# Mount the compiled frontend to expected location
 RUN set -eux \
   && addgroup --gid 1000 paperless \
   && useradd --uid 1000 --gid paperless --home-dir /usr/src/paperless paperless \
-  && chown -R paperless:paperless ../ \
+  && chown -R paperless:paperless /usr/src/paperless \
-  && gosu paperless python3 manage.py collectstatic --clear --no-input \
+  && gosu paperless python3 manage.py collectstatic --clear --no-input --link \
   && gosu paperless python3 manage.py compilemessages
 
 VOLUME ["/usr/src/paperless/data", \

README.md

@@ -1,7 +1,7 @@
 [![ci](https://github.com/paperless-ngx/paperless-ngx/workflows/ci/badge.svg)](https://github.com/paperless-ngx/paperless-ngx/actions)
 [![Crowdin](https://badges.crowdin.net/paperless-ngx/localized.svg)](https://crowdin.com/project/paperless-ngx)
 [![Documentation Status](https://img.shields.io/github/deployments/paperless-ngx/paperless-ngx/github-pages?label=docs)](https://docs.paperless-ngx.com)
-[![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)
+[![codecov](https://codecov.io/gh/paperless-ngx/paperless-ngx/branch/main/graph/badge.svg?token=VK6OUPJ3TY)](https://codecov.io/gh/paperless-ngx/paperless-ngx)
 [![Chat on Matrix](https://matrix.to/img/matrix-badge.svg)](https://matrix.to/#/%23paperlessngx%3Amatrix.org)
 [![demo](https://cronitor.io/badges/ve7ItY/production/W5E_B9jkelG9ZbDiNHUPQEVH3MY.svg)](https://demo.paperless-ngx.com)
 

docker/docker-prepare.sh

@@ -80,7 +80,7 @@ django_checks() {
 
 search_index() {
 
-	local -r index_version=2
+	local -r index_version=3
 	local -r index_version_file=${DATA_DIR}/.index_version
 
 	if [[ (! -f "${index_version_file}") || $(<"${index_version_file}") != "$index_version" ]]; then

docs/advanced_usage.md

@@ -121,7 +121,17 @@ Executed after the consumer sees a new document in the consumption
 folder, but before any processing of the document is performed. This
 script can access the following relevant environment variables set:
 
-- `DOCUMENT_SOURCE_PATH`
+| Environment Variable    | Description                                                  |
+| ----------------------- | ------------------------------------------------------------ |
+| `DOCUMENT_SOURCE_PATH`  | Original path of the consumed document                       |
+| `DOCUMENT_WORKING_PATH` | Path to a copy of the original that consumption will work on |
+
+!!! note
+
+    Pre-consume scripts which modify the document should only change
+    the `DOCUMENT_WORKING_PATH` file or a second consume task may
+    be triggered, leading to failures as two tasks work on the
+    same document path
 
 A simple but common example for this would be creating a simple script
 like this:
@@ -130,7 +140,7 @@ like this:
 
 ```bash
 #!/usr/bin/env bash
-pdf2pdfocr.py -i ${DOCUMENT_SOURCE_PATH}
+pdf2pdfocr.py -i ${DOCUMENT_WORKING_PATH}
 ```
 
 `/etc/paperless.conf`
@@ -157,27 +167,37 @@ Executed after the consumer has successfully processed a document and
 has moved it into paperless. It receives the following environment
 variables:
 
-- `DOCUMENT_ID`
+| Environment Variable         | Description                                   |
-- `DOCUMENT_FILE_NAME`
+| ---------------------------- | --------------------------------------------- |
-- `DOCUMENT_CREATED`
+| `DOCUMENT_ID`                | Database primary key of the document          |
-- `DOCUMENT_MODIFIED`
+| `DOCUMENT_FILE_NAME`         | Formatted filename, not including paths       |
-- `DOCUMENT_ADDED`
+| `DOCUMENT_CREATED`           | Date & time when document created             |
-- `DOCUMENT_SOURCE_PATH`
+| `DOCUMENT_MODIFIED`          | Date & time when document was last modified   |
-- `DOCUMENT_ARCHIVE_PATH`
+| `DOCUMENT_ADDED`             | Date & time when document was added           |
-- `DOCUMENT_THUMBNAIL_PATH`
+| `DOCUMENT_SOURCE_PATH`       | Path to the original document file            |
-- `DOCUMENT_DOWNLOAD_URL`
+| `DOCUMENT_ARCHIVE_PATH`      | Path to the generate archive file (if any)    |
-- `DOCUMENT_THUMBNAIL_URL`
+| `DOCUMENT_THUMBNAIL_PATH`    | Path to the generated thumbnail               |
-- `DOCUMENT_CORRESPONDENT`
+| `DOCUMENT_DOWNLOAD_URL`      | URL for document download                     |
-- `DOCUMENT_TAGS`
+| `DOCUMENT_THUMBNAIL_URL`     | URL for the document thumbnail                |
-- `DOCUMENT_ORIGINAL_FILENAME`
+| `DOCUMENT_CORRESPONDENT`     | Assigned correspondent (if any)               |
+| `DOCUMENT_TAGS`              | Comma separated list of tags applied (if any) |
+| `DOCUMENT_ORIGINAL_FILENAME` | Filename of original document                 |
 
-The script can be in any language, but for a simple shell script
+The script can be in any language, A simple shell script example:
-example, you can take a look at
+
-[post-consumption-example.sh](https://github.com/paperless-ngx/paperless-ngx/blob/main/scripts/post-consumption-example.sh)
+```bash title="post-consumption-example"
-in this project.
+--8<-- "./scripts/post-consumption-example.sh"
+```
+
+!!! note
 
     The post consumption script cannot cancel the consumption process.
 
+!!! warning
+
+    The post consumption script should not modify the document files
+    directly
+
 The script's stdout and stderr will be logged line by line to the
 webserver log, along with the exit code of the script.
 

docs/configuration.md

@@ -141,7 +141,8 @@ directory.
 files created using "collectstatic" manager command are stored.
 
     Unless you're doing something fancy, there is no need to override
-    this.
+    this.  If this is changed, you may need to run
+    `collectstatic` again.
 
     Defaults to "../static/", relative to the "src" directory.
 

docs/development.md

@@ -1,9 +1,9 @@
 # Development
 
 This section describes the steps you need to take to start development
-on paperless-ngx.
+on Paperless-ngx.
 
-Check out the source from github. The repository is organized in the
+Check out the source from GitHub. The repository is organized in the
 following way:
 
 - `main` always represents the latest release and will only see
@@ -12,7 +12,7 @@ following way:
 - `feature-X` contain bigger changes that will be in some release, but
   not necessarily the next one.
 
-When making functional changes to paperless, _always_ make your changes
+When making functional changes to Paperless-ngx, _always_ make your changes
 on the `dev` branch.
 
 Apart from that, the folder structure is as follows:
@@ -24,9 +24,9 @@ Apart from that, the folder structure is as follows:
   development.
 - `docker/` - Files required to build the docker image.
 
-## Contributing to Paperless
+## Contributing to Paperless-ngx
 
-Maybe you've been using Paperless for a while and want to add a feature
+Maybe you've been using Paperless-ngx 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!
@@ -36,13 +36,13 @@ conduct](https://github.com/paperless-ngx/paperless-ngx/blob/main/CODE_OF_CONDUC
 and other important information in the [contributing
 guidelines](https://github.com/paperless-ngx/paperless-ngx/blob/main/CONTRIBUTING.md).
 
-## 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`](https://git-scm.com/book/en/v2/Customizing-Git-Git-Hooks)
+the project utilizes Git [`pre-commit`](https://git-scm.com/book/en/v2/Customizing-Git-Git-Hooks)
-hook to perform some formatting and linting before a commit is allowed.
+hooks 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.
+early on.
 
 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.
@@ -51,129 +51,110 @@ 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
+## General setup
 
-After you forked and cloned the code from github you need to perform a
+After you forked and cloned the code from GitHub you need to perform a
-first-time setup. To do the setup you need to perform the steps from the
+first-time setup.
-following chapters in a certain order:
+
+!!! note
+
+    Every command is executed directly from the root folder of the project unless specified otherwise.
 
 1.  Install prerequisites + pipenv as mentioned in
-    [Bare metal route](/setup#bare_metal)
+    [Bare metal route](/setup#bare_metal).
 
 2.  Copy `paperless.conf.example` to `paperless.conf` and enable debug
-    mode.
+    mode within the file via `PAPERLESS_DEBUG=true`.
 
-3.  Install the Angular CLI interface:
+3.  Create `consume` and `media` directories:
 
-    ```shell-session
+    ```bash
-    $ npm install -g @angular/cli
+    $ mkdir -p consume media
     ```
 
-4.  Install pre-commit hooks
+4.  Install the Python dependencies:
 
-    ```shell-session
+    ```bash
-    pre-commit install
+    $ pipenv install --dev
     ```
 
-5.  Create `consume` and `media` folders in the cloned root folder.
+    !!! note
 
-    ```shell-session
+        Using a virtual environment is highly recommended. You can spawn one via `pipenv shell`.
-    mkdir -p consume media
+        Make sure you're using Python 3.10.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.
+
+5.  Install pre-commit hooks:
+
+    ```bash
+    $ pre-commit install
     ```
 
-6.  You can now either ...
+6.  Apply migrations and create a superuser for your development instance:
+
+    ```bash
+    # src/
+
+    $ python3 manage.py migrate
+    $ python3 manage.py createsuperuser
+    ```
+
+7.  You can now either ...
 
     - install redis or
 
-    - use the included scripts/start-services.sh to use docker to fire
+    - 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
 
-      ```shell-session
+      ```
-      docker run -d -p 6379:6379 --restart unless-stopped redis:latest
+      $ docker run -d -p 6379:6379 --restart unless-stopped redis:latest
       ```
 
-7.  Install the python dependencies by performing in the src/ directory.
+8.  Continue with either back-end or front-end development – or both :-).
-
-    ```shell-session
-    pipenv install --dev
-    ```
-
-!!! note
-
-    Make sure you're using python 3.10.x or lower. Otherwise you might
-    get issues with building dependencies. You can use
-    [pyenv](https://github.com/pyenv/pyenv) to install a specific
-    python version.
-
-8.  Generate the static UI so you can perform a login to get session
-    that is required for frontend development (this needs to be done one
-    time only). From src-ui directory:
-
-    ```shell-session
-    npm install .
-    ./node_modules/.bin/ng build --configuration production
-    ```
-
-9.  Apply migrations and create a superuser for your dev instance:
-
-    ```shell-session
-    python3 manage.py migrate
-    python3 manage.py createsuperuser
-    ```
-
-10. Now spin up the dev backend. Depending on which part of paperless
-    you're developing for, you need to have some or all of them
-    running.
-
-    ```shell-session
-    python3 manage.py runserver & python3 manage.py document_consumer & celery --app paperless worker
-    ```
-
-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](https://www.djangoproject.com/) application. PyCharm works well for development,
+The back end is a [Django](https://www.djangoproject.com/) application. [PyCharm](https://www.jetbrains.com/de-de/pycharm/) as well as [Visual Studio Code](https://code.visualstudio.com) work well for development, but you can use whatever you want.
-but you can use whatever you want.
 
-Configure the IDE to use the src/ folder as the base source folder.
+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`
-- `celery --app paperless worker`
 - `python3 manage.py document_consumer`
+- `celery --app paperless worker -l DEBUG` (or any other log level)
 
 To start them all:
 
-```shell-session
+```bash
-python3 manage.py runserver & python3 manage.py document_consumer & celery --app paperless worker
+# src/
+
+$ python3 manage.py runserver & \
+  python3 manage.py document_consumer & \
+  celery --app paperless worker -l DEBUG
 ```
 
-Testing and code style:
+You might need the front end to test your back end code. This assumes that you have AngularJS installed on your system. Go to the [Front end development](#front-end-development) section for further details. To build the front end once use this commmand:
+
+```bash
+# src-ui/
+
+$ npm install
+$ ng build --configuration production
+```
+
+### Testing
 
 - Run `pytest` in the `src/` directory to execute all tests. This also
-  generates a HTML coverage report. When runnings test, paperless.conf
+  generates a HTML coverage report. When runnings test, `paperless.conf`
-  is loaded as well. However: the tests rely on the default
+  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.
 
-- 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
-
-- The `pre-commit` hooks will modify files and interact with each other.
-  It may take a couple of `git add`, `git commit` cycle to satisfy them.
-
 !!! note
 
       The line length rule E501 is generally useful for getting multiple
@@ -184,23 +165,31 @@ Testing and code style:
 
 ## Front end development
 
-The front end is built using Angular. In order to get started, you need
+The front end is built using AngularJS. In order to get started, you need Node.js (version 14.15+) and
-`npm`. Install the Angular CLI interface with
+`npm`.
 
-```shell-session
+!!! note
+
+    The following commands are all performed in the `src-ui`-directory. You will need a running back end (including an active session) to connect to the back end API. To spin it up refer to the commands under the section [above](#back-end-development).
+
+1. Install the Angular CLI. You might need sudo privileges
+   to perform this command:
+
+   ```bash
    $ npm install -g @angular/cli
    ```
 
-and make sure that it's on your path. Next, in the src-ui/ directory,
+2. Make sure that it's on your path.
-install the required dependencies of the project.
 
-```shell-session
+3. Install all neccessary modules:
+
+   ```bash
    $ npm install
    ```
 
-You can launch a development server by running
+4. You can launch a development server by running:
 
-```shell-session
+   ```bash
    $ ng serve
    ```
 
@@ -208,24 +197,17 @@ This will automatically update whenever you save. However, in-place
    compilation might fail on syntax errors, in which case you need to
    restart it.
 
-By default, the development server is available on
+   By default, the development server is available on `http://localhost:4200/` and is configured to access the API at
-`http://localhost:4200/` and is configured to access the API at
+   `http://localhost:8000/api/`, which is the default of the backend. If you enabled `DEBUG` on the back end, several security overrides for allowed hosts, CORS and X-Frame-Options are in place so that the front end behaves exactly as in production.
-`http://localhost:8000/api/`, which is the default of the backend. If
-you enabled DEBUG on the back end, several security overrides for
-allowed hosts, CORS and X-Frame-Options are in place so that the front
-end behaves exactly as in production. This also relies on you being
-logged into the back end. Without a valid session, The front end will
-simply not work.
 
-Testing and code style:
+### Testing and code style
 
 - The front end code (.ts, .html, .scss) use `prettier` for code
   formatting via the Git `pre-commit` hooks which run automatically on
-  commit. See
+  commit. See [above](#code-formatting-with-pre-commit-hooks) for installation instructions. You can also run this via the CLI with a
-  [above](#code-formatting-with-pre-commit-hooks) for installation. You can also run this via cli with a
   command such as
 
-  ```shell-session
+  ```bash
   $ git ls-files -- '*.ts' | xargs pre-commit run prettier --files
   ```
 
@@ -233,21 +215,20 @@ Testing and code style:
   for significantly more front end tests. Unit tests and e2e tests,
   respectively, can be run non-interactively with:
 
-  ```shell-session
+  ```bash
   $ ng test
   $ npm run e2e:ci
   ```
 
-  Cypress also includes a UI which can be run from within the `src-ui`
+  - Cypress also includes a UI which can be run with:
-  directory with
 
-  ```shell-session
+    ```bash
     $ ./node_modules/.bin/cypress open
     ```
 
-In order to build the front end and serve it as part of django, execute
+- In order to build the front end and serve it as part of Django, execute:
 
-```shell-session
+  ```bash
   $ ng build --configuration production
   ```
 
@@ -257,25 +238,25 @@ that authentication is working.
 
 ## Localization
 
-Paperless is available in many different languages. Since paperless
+Paperless-ngx is available in many different languages. Since Paperless-ngx
-consists both of a django application and an Angular front end, both
+consists both of a Django application and an AngularJS front end, both
 these parts have to be translated separately.
 
 ### Front end localization
 
-- The Angular front end does localization according to the [Angular
+- The AngularJS front end does localization according to the [Angular
   documentation](https://angular.io/guide/i18n).
 - The source language of the project is "en_US".
-- The source strings end up in the file "src-ui/messages.xlf".
+- The source strings end up in the file `src-ui/messages.xlf`.
 - The translated strings need to be placed in the
-  "src-ui/src/locale/" folder.
+  `src-ui/src/locale/` folder.
 - In order to extract added or changed strings from the source files,
   call `ng xi18n --ivy`.
 
 Adding new languages requires adding the translated files in the
-"src-ui/src/locale/" folder and adjusting a couple files.
+`src-ui/src/locale/` folder and adjusting a couple files.
 
-1.  Adjust "src-ui/angular.json":
+1.  Adjust `src-ui/angular.json`:
 
     ```json
     "i18n": {
@@ -292,7 +273,7 @@ Adding new languages requires adding the translated files in the
     ```
 
 2.  Add the language to the available options in
-    "src-ui/src/app/services/settings.service.ts":
+    `src-ui/src/app/services/settings.service.ts`:
 
     ```typescript
     getLanguageOptions(): LanguageOption[] {
@@ -313,7 +294,7 @@ Adding new languages requires adding the translated files in the
     and "yyyy".
 
 3.  Import and register the Angular data for this locale in
-    "src-ui/src/app/app.module.ts":
+    `src-ui/src/app/app.module.ts`:
 
     ```typescript
     import localeDe from '@angular/common/locales/de'
@@ -326,10 +307,10 @@ A majority of the strings that appear in the back end appear only when
 the admin is used. However, some of these are still shown on the front
 end (such as error messages).
 
-- The django application does localization according to the [django
+- The django application does localization according to the [Django
   documentation](https://docs.djangoproject.com/en/3.1/topics/i18n/translation/).
 - The source language of the project is "en_US".
-- Localization files end up in the folder "src/locale/".
+- Localization files end up in the folder `src/locale/`.
 - In order to extract strings from the application, call
   `python3 manage.py makemessages -l en_US`. This is important after
   making changes to translatable strings.
@@ -340,8 +321,8 @@ end (such as error messages).
   command.
 
 Adding new languages requires adding the translated files in the
-"src/locale/" folder and adjusting the file
+`src/locale/`-folder and adjusting the file
-"src/paperless/settings.py" to include the new language:
+`src/paperless/settings.py` to include the new language:
 
 ```python
 LANGUAGES = [
@@ -360,18 +341,27 @@ LANGUAGES = [
 The documentation is built using material-mkdocs, see their [documentation](https://squidfunk.github.io/mkdocs-material/reference/).
 If you want to build the documentation locally, this is how you do it:
 
-1.  Install python dependencies.
+1.  Have an active pipenv shell (`pipenv shell`) and install Python dependencies:
 
-    ```shell-session
+    ```bash
-    $ cd /path/to/paperless
     $ pipenv install --dev
     ```
 
 2.  Build the documentation
 
-    ```shell-session
+    ```bash
-    $ cd /path/to/paperless
+    $ mkdocs build --config-file mkdocs.yml
-    $ pipenv mkdocs build --config-file mkdocs.yml
+    ```
+
+    _alternatively..._
+
+3.  Serve the documentation. This will spin up a
+    copy of the documentation at http://127.0.0.1:8000
+    that will automatically refresh everytime you change
+    something.
+
+    ```bash
+    $ mkdocs serve
     ```
 
 ## Building the Docker image
@@ -384,35 +374,35 @@ helper script `build-docker-image.sh`.
 
 Building the docker image from source:
 
-```shell-session
+```bash
 ./build-docker-image.sh Dockerfile -t <your-tag>
 ```
 
-## Extending Paperless
+## Extending Paperless-ngx
 
-Paperless does not have any fancy plugin systems and will probably never
+Paperless-ngx does not have any fancy plugin systems and will probably never
 have. However, some parts of the application have been designed to allow
 easy integration of additional features without any modification to the
 base code.
 
 ### Making custom parsers
 
-Paperless uses parsers to add documents to paperless. A parser is
+Paperless-ngx uses parsers to add documents. A parser is
 responsible for:
 
-- Retrieve the content from the original
+- Retrieving the content from the original
-- Create a thumbnail
+- Creating a thumbnail
-- Optional: Retrieve a created date from the original
+- _optional:_ Retrieving a created date from the original
-- Optional: Create an archived document from the original
+- _optional:_ Creainge an archived document from the original
 
-Custom parsers can be added to paperless to support more file types. In
+Custom parsers can be added to Paperless-ngx to support more file types. In
 order to do that, you need to write the parser itself and announce its
-existence to paperless.
+existence to Paperless-ngx.
 
 The parser itself must extend `documents.parsers.DocumentParser` and
 must implement the methods `parse` and `get_thumbnail`. You can provide
 your own implementation to `get_date` if you don't want to rely on
-paperless' default date guessing mechanisms.
+Paperless-ngx' default date guessing mechanisms.
 
 ```python
 class MyCustomParser(DocumentParser):
@@ -444,7 +434,7 @@ to be empty and removed after consumption finished. You can use that
 directory to store any intermediate files and also use it to store the
 thumbnail / archived document.
 
-After that, you need to announce your parser to paperless. You need to
+After that, you need to announce your parser to Paperless-ngx. You need to
 connect a handler to the `document_consumer_declaration` signal. Have a
 look in the file `src/paperless_tesseract/apps.py` on how that's done.
 The handler is a method that returns information about your parser:
@@ -464,11 +454,11 @@ def myparser_consumer_declaration(sender, **kwargs):
 - `parser` is a reference to a class that extends `DocumentParser`.
 - `weight` is used whenever two or more parsers are able to parse a
   file: The parser with the higher weight wins. This can be used to
-  override the parsers provided by paperless.
+  override the parsers provided by Paperless-ngx.
 - `mime_types` is a dictionary. The keys are the mime types your
   parser supports and the value is the default file extension that
-  paperless should use when storing files and serving them for
+  Paperless-ngx should use when storing files and serving them for
   download. We could guess that from the file extensions, but some
-  mime types have many extensions associated with them and the python
+  mime types have many extensions associated with them and the Python
   methods responsible for guessing the extension do not always return
   the same value.

docs/setup.md

@@ -388,12 +388,7 @@ supported.
     ```
 
 8.  Install python requirements from the `requirements.txt` file. It is
-    up to you if you wish to use a virtual environment or not. First you
+    up to you if you wish to use a virtual environment or not. First you should update your pip, so it gets the actual packages.
-    should update your pip, so it gets the actual packages.
-
-    ```shell-session
-    sudo -Hu paperless pip3 install --upgrade pip
-    ```
 
     ```shell-session
     sudo -Hu paperless pip3 install -r requirements.txt

mkdocs.yml

@@ -41,6 +41,7 @@ markdown_extensions:
       anchor_linenums: true
   - pymdownx.superfences
   - pymdownx.inlinehilite
+  - pymdownx.snippets
 strict: true
 nav:
     - index.md
@@ -54,7 +55,7 @@ nav:
     - 'FAQs': faq.md
     - troubleshooting.md
     - changelog.md
-copyright: Copyright © 2016 - 2022 Daniel Quinn, Jonas Winkler, and the Paperless-ngx team
+copyright: Copyright © 2016 - 2023 Daniel Quinn, Jonas Winkler, and the Paperless-ngx team
 extra:
   social:
     - icon: fontawesome/brands/github

src-ui/angular.json

@@ -192,7 +192,8 @@
   "cli": {
     "schematicCollections": [
       "@angular-eslint/schematics"
-    ]
+    ],
+    "analytics": false
   },
   "schematics": {
     "@angular-eslint/schematics:application": {

src-ui/package.json

@@ -13,14 +13,14 @@
   },
   "private": true,
   "dependencies": {
-    "@angular/common": "~15.1.0",
+    "@angular/common": "~15.1.2",
-    "@angular/compiler": "~15.1.0",
+    "@angular/compiler": "~15.1.2",
-    "@angular/core": "~15.1.0",
+    "@angular/core": "~15.1.2",
-    "@angular/forms": "~15.1.0",
+    "@angular/forms": "~15.1.2",
-    "@angular/localize": "~15.1.0",
+    "@angular/localize": "~15.1.2",
-    "@angular/platform-browser": "~15.1.0",
+    "@angular/platform-browser": "~15.1.2",
-    "@angular/platform-browser-dynamic": "~15.1.0",
+    "@angular/platform-browser-dynamic": "~15.1.2",
-    "@angular/router": "~15.1.0",
+    "@angular/router": "~15.1.2",
     "@ng-bootstrap/ng-bootstrap": "^14.0.1",
     "@ng-select/ng-select": "^10.0.1",
     "@ngneat/dirty-check-forms": "^3.0.3",
@@ -39,18 +39,18 @@
   },
   "devDependencies": {
     "@angular-builders/jest": "15.0.0",
-    "@angular-devkit/build-angular": "~15.1.0",
+    "@angular-devkit/build-angular": "~15.1.4",
-    "@angular-eslint/builder": "15.1.0",
+    "@angular-eslint/builder": "15.2.0",
-    "@angular-eslint/eslint-plugin": "15.1.0",
+    "@angular-eslint/eslint-plugin": "15.2.0",
-    "@angular-eslint/eslint-plugin-template": "15.1.0",
+    "@angular-eslint/eslint-plugin-template": "15.2.0",
-    "@angular-eslint/schematics": "15.1.0",
+    "@angular-eslint/schematics": "15.2.0",
-    "@angular-eslint/template-parser": "15.1.0",
+    "@angular-eslint/template-parser": "15.2.0",
-    "@angular/cli": "~15.1.0",
+    "@angular/cli": "~15.1.4",
-    "@angular/compiler-cli": "~15.1.0",
+    "@angular/compiler-cli": "~15.1.2",
     "@types/jest": "28.1.6",
     "@types/node": "^18.7.23",
     "@typescript-eslint/eslint-plugin": "^5.43.0",
-    "@typescript-eslint/parser": "^5.43.0",
+    "@typescript-eslint/parser": "^5.50.0",
     "concurrently": "7.4.0",
     "eslint": "^8.31.0",
     "jest": "28.1.3",

src-ui/src/app/components/document-detail/document-detail.component.ts

@@ -229,6 +229,10 @@ export class DocumentDetailComponent
             )
             .subscribe({
               next: (titleValue) => {
+                // In the rare case when the field changed just after debounced event was fired.
+                // We dont want to overwrite whats actually in the text field, so just return
+                if (titleValue !== this.titleInput.value) return
+
                 this.title = titleValue
                 this.documentForm.patchValue({ title: titleValue })
               },

src-ui/src/environments/environment.prod.ts

@@ -5,7 +5,7 @@ export const environment = {
   apiBaseUrl: document.baseURI + 'api/',
   apiVersion: '2',
   appTitle: 'Paperless-ngx',
-  version: '1.12.1-dev',
+  version: '1.12.2-dev',
   webSocketHost: window.location.host,
   webSocketProtocol: window.location.protocol == 'https:' ? 'wss:' : 'ws:',
   webSocketBaseUrl: base_url.pathname + 'ws/',

src/documents/barcodes.py

@@ -4,18 +4,17 @@ import shutil
 import tempfile
 from dataclasses import dataclass
 from functools import lru_cache
-from math import ceil
 from pathlib import Path
+from typing import Dict
 from typing import List
 from typing import Optional
 
 import magic
 from django.conf import settings
 from pdf2image import convert_from_path
+from pdf2image.exceptions import PDFPageCountError
 from pikepdf import Page
-from pikepdf import PasswordError
 from pikepdf import Pdf
-from pikepdf import PdfImage
 from PIL import Image
 from PIL import ImageSequence
 from pyzbar import pyzbar
@@ -154,52 +153,15 @@ def scan_file_for_barcodes(
     (page_number, barcode_text) tuples
     """
 
-    def _pikepdf_barcode_scan(pdf_filepath: str) -> List[Barcode]:
-        detected_barcodes = []
-        with Pdf.open(pdf_filepath) as pdf:
-            for page_num, page in enumerate(pdf.pages):
-                for image_key in page.images:
-                    pdfimage = PdfImage(page.images[image_key])
-
-                    # This type is known to have issues:
-                    # https://github.com/pikepdf/pikepdf/issues/401
-                    if "/CCITTFaxDecode" in pdfimage.filters:
-                        raise BarcodeImageFormatError(
-                            "Unable to decode CCITTFaxDecode images",
-                        )
-
-                    # Not all images can be transcoded to a PIL image, which
-                    # is what pyzbar expects to receive, so this may
-                    # raise an exception, triggering fallback
-                    pillow_img = pdfimage.as_pil_image()
-
-                    # Scale the image down
-                    # See: https://github.com/paperless-ngx/paperless-ngx/issues/2385
-                    # TLDR: zbar has issues with larger images
-                    width, height = pillow_img.size
-                    if width > 1024:
-                        scaler = ceil(width / 1024)
-                        new_width = int(width / scaler)
-                        new_height = int(height / scaler)
-                        pillow_img = pillow_img.resize((new_width, new_height))
-
-                    width, height = pillow_img.size
-                    if height > 2048:
-                        scaler = ceil(height / 2048)
-                        new_width = int(width / scaler)
-                        new_height = int(height / scaler)
-                        pillow_img = pillow_img.resize((new_width, new_height))
-
-                    for barcode_value in barcode_reader(pillow_img):
-                        detected_barcodes.append(Barcode(page_num, barcode_value))
-
-        return detected_barcodes
-
     def _pdf2image_barcode_scan(pdf_filepath: str) -> List[Barcode]:
         detected_barcodes = []
         # use a temporary directory in case the file is too big to handle in memory
         with tempfile.TemporaryDirectory() as path:
-            pages_from_path = convert_from_path(pdf_filepath, output_folder=path)
+            pages_from_path = convert_from_path(
+                pdf_filepath,
+                dpi=300,
+                output_folder=path,
+            )
             for current_page_number, page in enumerate(pages_from_path):
                 for barcode_value in barcode_reader(page):
                     detected_barcodes.append(
@@ -219,27 +181,19 @@ def scan_file_for_barcodes(
         # Always try pikepdf first, it's usually fine, faster and
         # uses less memory
         try:
-            barcodes = _pikepdf_barcode_scan(pdf_filepath)
+            barcodes = _pdf2image_barcode_scan(pdf_filepath)
         # Password protected files can't be checked
-        except PasswordError as e:
+        # This is the exception raised for those
+        except PDFPageCountError as e:
             logger.warning(
                 f"File is likely password protected, not checking for barcodes: {e}",
             )
-        # Handle pikepdf related image decoding issues with a fallback to page
-        # by page conversion to images in a temporary directory
-        except Exception as e:
-            logger.warning(
-                f"Falling back to pdf2image because: {e}",
-            )
-            try:
-                barcodes = _pdf2image_barcode_scan(pdf_filepath)
         # This file is really borked, allow the consumption to continue
         # but it may fail further on
         except Exception as e:  # pragma: no cover
             logger.warning(
                 f"Exception during barcode scanning: {e}",
             )
-
     else:
         logger.warning(
             f"Unsupported file format for barcode reader: {str(mime_type)}",
@@ -248,16 +202,25 @@ def scan_file_for_barcodes(
     return DocumentBarcodeInfo(pdf_filepath, barcodes)
 
 
-def get_separating_barcodes(barcodes: List[Barcode]) -> List[int]:
+def get_separating_barcodes(barcodes: List[Barcode]) -> Dict[int, bool]:
     """
     Search the parsed barcodes for separators
-    and returns a list of page numbers, which
+    and returns a dict of page numbers, which
-    separate the file into new files.
+    separate the file into new files, together
+    with the information whether to keep the page.
     """
     # filter all barcodes for the separator string
     # get the page numbers of the separating barcodes
+    separator_pages = {bc.page: False for bc in barcodes if bc.is_separator}
+    if not settings.CONSUMER_ENABLE_ASN_BARCODE:
+        return separator_pages
 
-    return list({bc.page for bc in barcodes if bc.is_separator})
+    # add the page numbers of the ASN barcodes
+    # (except for first page, that might lead to infinite loops).
+    return {
+        **separator_pages,
+        **{bc.page: True for bc in barcodes if bc.is_asn and bc.page != 0},
+    }
 
 
 def get_asn_from_barcodes(barcodes: List[Barcode]) -> Optional[int]:
@@ -289,10 +252,11 @@ def get_asn_from_barcodes(barcodes: List[Barcode]) -> Optional[int]:
     return asn
 
 
-def separate_pages(filepath: str, pages_to_split_on: List[int]) -> List[str]:
+def separate_pages(filepath: str, pages_to_split_on: Dict[int, bool]) -> List[str]:
     """
     Separate the provided pdf file on the pages_to_split_on.
-    The pages which are defined by page_numbers will be removed.
+    The pages which are defined by the keys in page_numbers
+    will be removed if the corresponding value is false.
     Returns a list of (temporary) filepaths to consume.
     These will need to be deleted later.
     """
@@ -308,26 +272,28 @@ def separate_pages(filepath: str, pages_to_split_on: List[int]) -> List[str]:
     fname = os.path.splitext(os.path.basename(filepath))[0]
     pdf = Pdf.open(filepath)
 
+    # Start with an empty document
+    current_document: List[Page] = []
     # A list of documents, ie a list of lists of pages
-    documents: List[List[Page]] = []
+    documents: List[List[Page]] = [current_document]
-    # A single document, ie a list of pages
-    document: List[Page] = []
 
     for idx, page in enumerate(pdf.pages):
         # Keep building the new PDF as long as it is not a
         # separator index
         if idx not in pages_to_split_on:
-            document.append(page)
+            current_document.append(page)
-            # Make sure to append the very last document to the documents
+            continue
-            if idx == (len(pdf.pages) - 1):
+
-                documents.append(document)
+        # This is a split index
-                document = []
+        # Start a new destination page listing
-        else:
-            # This is a split index, save the current PDF pages, and restart
-            # a new destination page listing
         logger.debug(f"Starting new document at idx {idx}")
-            documents.append(document)
+        current_document = []
-            document = []
+        documents.append(current_document)
+        keep_page = pages_to_split_on[idx]
+        if keep_page:
+            # Keep the page
+            # (new document is started by asn barcode)
+            current_document.append(page)
 
     documents = [x for x in documents if len(x)]
 

src/documents/consumer.py

@@ -1,7 +1,10 @@
 import datetime
 import hashlib
 import os
+import shutil
+import tempfile
 import uuid
+from pathlib import Path
 from subprocess import CompletedProcess
 from subprocess import run
 from typing import Optional
@@ -95,7 +98,8 @@ class Consumer(LoggingMixin):
 
     def __init__(self):
         super().__init__()
-        self.path = None
+        self.path: Optional[Path] = None
+        self.original_path: Optional[Path] = None
         self.filename = None
         self.override_title = None
         self.override_correspondent_id = None
@@ -144,11 +148,16 @@ class Consumer(LoggingMixin):
             return
         # Validate the range is above zero and less than uint32_t max
         # otherwise, Whoosh can't handle it in the index
-        if self.override_asn < 0 or self.override_asn > 0xFF_FF_FF_FF:
+        if (
+            self.override_asn < Document.ARCHIVE_SERIAL_NUMBER_MIN
+            or self.override_asn > Document.ARCHIVE_SERIAL_NUMBER_MAX
+        ):
             self._fail(
                 MESSAGE_ASN_RANGE,
                 f"Not consuming {self.filename}: "
-                f"Given ASN {self.override_asn} is out of range [0, 4,294,967,295]",
+                f"Given ASN {self.override_asn} is out of range "
+                f"[{Document.ARCHIVE_SERIAL_NUMBER_MIN:,}, "
+                f"{Document.ARCHIVE_SERIAL_NUMBER_MAX:,}]",
             )
         if Document.objects.filter(archive_serial_number=self.override_asn).exists():
             self._fail(
@@ -169,16 +178,18 @@ class Consumer(LoggingMixin):
 
         self.log("info", f"Executing pre-consume script {settings.PRE_CONSUME_SCRIPT}")
 
-        filepath_arg = os.path.normpath(self.path)
+        working_file_path = str(self.path)
+        original_file_path = str(self.original_path)
 
         script_env = os.environ.copy()
-        script_env["DOCUMENT_SOURCE_PATH"] = filepath_arg
+        script_env["DOCUMENT_SOURCE_PATH"] = original_file_path
+        script_env["DOCUMENT_WORKING_PATH"] = working_file_path
 
         try:
             completed_proc = run(
                 args=[
                     settings.PRE_CONSUME_SCRIPT,
-                    filepath_arg,
+                    original_file_path,
                 ],
                 env=script_env,
                 capture_output=True,
@@ -197,7 +208,7 @@ class Consumer(LoggingMixin):
                 exception=e,
             )
 
-    def run_post_consume_script(self, document):
+    def run_post_consume_script(self, document: Document):
         if not settings.POST_CONSUME_SCRIPT:
             return
 
@@ -288,8 +299,8 @@ class Consumer(LoggingMixin):
         Return the document object if it was successfully created.
         """
 
-        self.path = path
+        self.path = Path(path).resolve()
-        self.filename = override_filename or os.path.basename(path)
+        self.filename = override_filename or self.path.name
         self.override_title = override_title
         self.override_correspondent_id = override_correspondent_id
         self.override_document_type_id = override_document_type_id
@@ -315,6 +326,15 @@ class Consumer(LoggingMixin):
 
         self.log("info", f"Consuming {self.filename}")
 
+        # For the actual work, copy the file into a tempdir
+        self.original_path = self.path
+        tempdir = tempfile.TemporaryDirectory(
+            prefix="paperless-ngx",
+            dir=settings.SCRATCH_DIR,
+        )
+        self.path = Path(tempdir.name) / Path(self.filename)
+        shutil.copy(self.original_path, self.path)
+
         # Determine the parser class.
 
         mime_type = magic.from_file(self.path, mime=True)
@@ -457,11 +477,12 @@ class Consumer(LoggingMixin):
                 # Delete the file only if it was successfully consumed
                 self.log("debug", f"Deleting file {self.path}")
                 os.unlink(self.path)
+                self.original_path.unlink()
 
                 # https://github.com/jonaswinkler/paperless-ng/discussions/1037
                 shadow_file = os.path.join(
-                    os.path.dirname(self.path),
+                    os.path.dirname(self.original_path),
-                    "._" + os.path.basename(self.path),
+                    "._" + os.path.basename(self.original_path),
                 )
 
                 if os.path.isfile(shadow_file):
@@ -478,6 +499,7 @@ class Consumer(LoggingMixin):
             )
         finally:
             document_parser.cleanup()
+            tempdir.cleanup()
 
         self.run_post_consume_script(document)
 

src/documents/index.py

@@ -5,6 +5,7 @@ from contextlib import contextmanager
 
 from dateutil.parser import isoparse
 from django.conf import settings
+from django.utils import timezone
 from documents.models import Comment
 from documents.models import Document
 from guardian.shortcuts import get_users_with_perms
@@ -94,10 +95,22 @@ def open_index_searcher():
         searcher.close()
 
 
-def update_document(writer, doc):
+def update_document(writer: AsyncWriter, doc: Document):
     tags = ",".join([t.name for t in doc.tags.all()])
     tags_ids = ",".join([str(t.id) for t in doc.tags.all()])
     comments = ",".join([str(c.comment) for c in Comment.objects.filter(document=doc)])
+    asn = doc.archive_serial_number
+    if asn is not None and (
+        asn < Document.ARCHIVE_SERIAL_NUMBER_MIN
+        or asn > Document.ARCHIVE_SERIAL_NUMBER_MAX
+    ):
+        logger.error(
+            f"Not indexing Archive Serial Number {asn} of document {doc.pk}. "
+            f"ASN is out of range "
+            f"[{Document.ARCHIVE_SERIAL_NUMBER_MIN:,}, "
+            f"{Document.ARCHIVE_SERIAL_NUMBER_MAX:,}.",
+        )
+        asn = 0
     users_with_perms = get_users_with_perms(
         doc,
         only_with_perms_in=["view_document"],
@@ -118,7 +131,7 @@ def update_document(writer, doc):
         has_type=doc.document_type is not None,
         created=doc.created,
         added=doc.added,
-        asn=doc.archive_serial_number,
+        asn=asn,
         modified=doc.modified,
         path=doc.storage_path.name if doc.storage_path else None,
         path_id=doc.storage_path.id if doc.storage_path else None,
@@ -283,7 +296,7 @@ class DelayedFullTextQuery(DelayedQuery):
             ["content", "title", "correspondent", "tag", "type", "comments"],
             self.searcher.ixreader.schema,
         )
-        qp.add_plugin(DateParserPlugin())
+        qp.add_plugin(DateParserPlugin(basedate=timezone.now()))
         q = qp.parse(q_str)
 
         corrected = self.searcher.correct_query(q, q_str)

src/documents/management/commands/document_exporter.py

@@ -311,8 +311,8 @@ class Command(BaseCommand):
                 archive_target = None
 
             # 3.4. write files to target folder
-            t = int(time.mktime(document.created.timetuple()))
             if document.storage_type == Document.STORAGE_TYPE_GPG:
+                t = int(time.mktime(document.created.timetuple()))
 
                 original_target.parent.mkdir(parents=True, exist_ok=True)
                 with document.source_file as out_file:

src/documents/migrations/1030_alter_paperlesstask_task_file_name.py

@@ -0,0 +1,23 @@
+# Generated by Django 4.1.5 on 2023-02-03 21:53
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("documents", "1029_alter_document_archive_serial_number"),
+    ]
+
+    operations = [
+        migrations.AlterField(
+            model_name="paperlesstask",
+            name="task_file_name",
+            field=models.CharField(
+                help_text="Name of the file which the Task was run for",
+                max_length=255,
+                null=True,
+                verbose_name="Task Filename",
+            ),
+        ),
+    ]

src/documents/models.py

@@ -3,6 +3,7 @@ import logging
 import os
 import re
 from collections import OrderedDict
+from typing import Final
 from typing import Optional
 
 import dateutil.parser
@@ -242,6 +243,9 @@ class Document(ModelWithOwner):
         help_text=_("The original name of the file when it was uploaded"),
     )
 
+    ARCHIVE_SERIAL_NUMBER_MIN: Final[int] = 0
+    ARCHIVE_SERIAL_NUMBER_MAX: Final[int] = 0xFF_FF_FF_FF
+
     archive_serial_number = models.PositiveIntegerField(
         _("archive serial number"),
         blank=True,
@@ -249,8 +253,8 @@ class Document(ModelWithOwner):
         unique=True,
         db_index=True,
         validators=[
-            MaxValueValidator(0xFF_FF_FF_FF),
+            MaxValueValidator(ARCHIVE_SERIAL_NUMBER_MAX),
-            MinValueValidator(0),
+            MinValueValidator(ARCHIVE_SERIAL_NUMBER_MIN),
         ],
         help_text=_(
             "The position of this document in your physical document " "archive.",
@@ -567,7 +571,7 @@ class PaperlessTask(models.Model):
     task_file_name = models.CharField(
         null=True,
         max_length=255,
-        verbose_name=_("Task Name"),
+        verbose_name=_("Task Filename"),
         help_text=_("Name of the file which the Task was run for"),
     )
 

src/documents/tasks.py

@@ -166,7 +166,7 @@ def consume_file(
                     # notify the sender, otherwise the progress bar
                     # in the UI stays stuck
                     payload = {
-                        "filename": override_filename,
+                        "filename": override_filename or path.name,
                         "task_id": task_id,
                         "current_progress": 100,
                         "max_progress": 100,

src/documents/tests/test_api.py

@@ -7,6 +7,7 @@ import tempfile
 import urllib.request
 import uuid
 import zipfile
+from datetime import timedelta
 from pathlib import Path
 from unittest import mock
 from unittest.mock import MagicMock
@@ -25,6 +26,7 @@ from django.contrib.auth.models import Permission
 from django.contrib.auth.models import User
 from django.test import override_settings
 from django.utils import timezone
+from dateutil.relativedelta import relativedelta
 from documents import bulk_edit
 from documents import index
 from documents.models import Correspondent
@@ -509,6 +511,270 @@ class TestDocumentApi(DirectoriesMixin, APITestCase):
         response = self.client.get("/api/documents/?query=content&page=3&page_size=10")
         self.assertEqual(response.status_code, 404)
 
+    @override_settings(
+        TIME_ZONE="UTC",
+    )
+    def test_search_added_in_last_week(self):
+        """
+        GIVEN:
+            - Three documents added right now
+            - The timezone is UTC time
+        WHEN:
+            - Query for documents added in the last 7 days
+        THEN:
+            - All three recent documents are returned
+        """
+        d1 = Document.objects.create(
+            title="invoice",
+            content="the thing i bought at a shop and paid with bank account",
+            checksum="A",
+            pk=1,
+        )
+        d2 = Document.objects.create(
+            title="bank statement 1",
+            content="things i paid for in august",
+            pk=2,
+            checksum="B",
+        )
+        d3 = Document.objects.create(
+            title="bank statement 3",
+            content="things i paid for in september",
+            pk=3,
+            checksum="C",
+        )
+        with index.open_index_writer() as writer:
+            index.update_document(writer, d1)
+            index.update_document(writer, d2)
+            index.update_document(writer, d3)
+
+        response = self.client.get("/api/documents/?query=added:[-1 week to now]")
+        results = response.data["results"]
+        # Expect 3 documents returned
+        self.assertEqual(len(results), 3)
+
+        for idx, subset in enumerate(
+            [
+                {"id": 1, "title": "invoice"},
+                {"id": 2, "title": "bank statement 1"},
+                {"id": 3, "title": "bank statement 3"},
+            ],
+        ):
+            result = results[idx]
+            # Assert subset in results
+            self.assertDictEqual(result, {**result, **subset})
+
+    @override_settings(
+        TIME_ZONE="America/Chicago",
+    )
+    def test_search_added_in_last_week_with_timezone_behind(self):
+        """
+        GIVEN:
+            - Two documents added right now
+            - One document added over a week ago
+            - The timezone is behind UTC time (-6)
+        WHEN:
+            - Query for documents added in the last 7 days
+        THEN:
+            - The two recent documents are returned
+        """
+        d1 = Document.objects.create(
+            title="invoice",
+            content="the thing i bought at a shop and paid with bank account",
+            checksum="A",
+            pk=1,
+        )
+        d2 = Document.objects.create(
+            title="bank statement 1",
+            content="things i paid for in august",
+            pk=2,
+            checksum="B",
+        )
+        d3 = Document.objects.create(
+            title="bank statement 3",
+            content="things i paid for in september",
+            pk=3,
+            checksum="C",
+            # 7 days, 1 hour and 1 minute ago
+            added=timezone.now() - timedelta(days=7, hours=1, minutes=1),
+        )
+        with index.open_index_writer() as writer:
+            index.update_document(writer, d1)
+            index.update_document(writer, d2)
+            index.update_document(writer, d3)
+
+        response = self.client.get("/api/documents/?query=added:[-1 week to now]")
+        results = response.data["results"]
+
+        # Expect 2 documents returned
+        self.assertEqual(len(results), 2)
+
+        for idx, subset in enumerate(
+            [{"id": 1, "title": "invoice"}, {"id": 2, "title": "bank statement 1"}],
+        ):
+            result = results[idx]
+            # Assert subset in results
+            self.assertDictEqual(result, {**result, **subset})
+
+    @override_settings(
+        TIME_ZONE="Europe/Sofia",
+    )
+    def test_search_added_in_last_week_with_timezone_ahead(self):
+        """
+        GIVEN:
+            - Two documents added right now
+            - One document added over a week ago
+            - The timezone is behind UTC time (+2)
+        WHEN:
+            - Query for documents added in the last 7 days
+        THEN:
+            - The two recent documents are returned
+        """
+        d1 = Document.objects.create(
+            title="invoice",
+            content="the thing i bought at a shop and paid with bank account",
+            checksum="A",
+            pk=1,
+        )
+        d2 = Document.objects.create(
+            title="bank statement 1",
+            content="things i paid for in august",
+            pk=2,
+            checksum="B",
+        )
+        d3 = Document.objects.create(
+            title="bank statement 3",
+            content="things i paid for in september",
+            pk=3,
+            checksum="C",
+            # 7 days, 1 hour and 1 minute ago
+            added=timezone.now() - timedelta(days=7, hours=1, minutes=1),
+        )
+        with index.open_index_writer() as writer:
+            index.update_document(writer, d1)
+            index.update_document(writer, d2)
+            index.update_document(writer, d3)
+
+        response = self.client.get("/api/documents/?query=added:[-1 week to now]")
+        results = response.data["results"]
+
+        # Expect 2 documents returned
+        self.assertEqual(len(results), 2)
+
+        for idx, subset in enumerate(
+            [{"id": 1, "title": "invoice"}, {"id": 2, "title": "bank statement 1"}],
+        ):
+            result = results[idx]
+            # Assert subset in results
+            self.assertDictEqual(result, {**result, **subset})
+
+    def test_search_added_in_last_month(self):
+        """
+        GIVEN:
+            - One document added right now
+            - One documents added about a week ago
+            - One document added over 1 month
+        WHEN:
+            - Query for documents added in the last month
+        THEN:
+            - The two recent documents are returned
+        """
+        d1 = Document.objects.create(
+            title="invoice",
+            content="the thing i bought at a shop and paid with bank account",
+            checksum="A",
+            pk=1,
+        )
+        d2 = Document.objects.create(
+            title="bank statement 1",
+            content="things i paid for in august",
+            pk=2,
+            checksum="B",
+            # 1 month, 1 day ago
+            added=timezone.now() - relativedelta(months=1, days=1),
+        )
+        d3 = Document.objects.create(
+            title="bank statement 3",
+            content="things i paid for in september",
+            pk=3,
+            checksum="C",
+            # 7 days, 1 hour and 1 minute ago
+            added=timezone.now() - timedelta(days=7, hours=1, minutes=1),
+        )
+
+        with index.open_index_writer() as writer:
+            index.update_document(writer, d1)
+            index.update_document(writer, d2)
+            index.update_document(writer, d3)
+
+        response = self.client.get("/api/documents/?query=added:[-1 month to now]")
+        results = response.data["results"]
+
+        # Expect 2 documents returned
+        self.assertEqual(len(results), 2)
+
+        for idx, subset in enumerate(
+            [{"id": 1, "title": "invoice"}, {"id": 3, "title": "bank statement 3"}],
+        ):
+            result = results[idx]
+            # Assert subset in results
+            self.assertDictEqual(result, {**result, **subset})
+
+    @override_settings(
+        TIME_ZONE="America/Denver",
+    )
+    def test_search_added_in_last_month_timezone_behind(self):
+        """
+        GIVEN:
+            - One document added right now
+            - One documents added about a week ago
+            - One document added over 1 month
+            - The timezone is behind UTC time (-6 or -7)
+        WHEN:
+            - Query for documents added in the last month
+        THEN:
+            - The two recent documents are returned
+        """
+        d1 = Document.objects.create(
+            title="invoice",
+            content="the thing i bought at a shop and paid with bank account",
+            checksum="A",
+            pk=1,
+        )
+        d2 = Document.objects.create(
+            title="bank statement 1",
+            content="things i paid for in august",
+            pk=2,
+            checksum="B",
+            # 1 month, 1 day ago
+            added=timezone.now() - relativedelta(months=1, days=1),
+        )
+        d3 = Document.objects.create(
+            title="bank statement 3",
+            content="things i paid for in september",
+            pk=3,
+            checksum="C",
+            # 7 days, 1 hour and 1 minute ago
+            added=timezone.now() - timedelta(days=7, hours=1, minutes=1),
+        )
+
+        with index.open_index_writer() as writer:
+            index.update_document(writer, d1)
+            index.update_document(writer, d2)
+            index.update_document(writer, d3)
+
+        response = self.client.get("/api/documents/?query=added:[-1 month to now]")
+        results = response.data["results"]
+
+        # Expect 2 documents returned
+        self.assertEqual(len(results), 2)
+
+        for idx, subset in enumerate(
+            [{"id": 1, "title": "invoice"}, {"id": 3, "title": "bank statement 3"}],
+        ):
+            result = results[idx]
+            # Assert subset in results
+            self.assertDictEqual(result, {**result, **subset})
+
     @mock.patch("documents.index.autocomplete")
     def test_search_autocomplete(self, m):
         m.side_effect = lambda ix, term, limit: [term for _ in range(limit)]

src/documents/tests/test_consumer.py

@@ -833,7 +833,8 @@ class PreConsumeTestCase(TestCase):
         with tempfile.NamedTemporaryFile() as script:
             with override_settings(PRE_CONSUME_SCRIPT=script.name):
                 c = Consumer()
-                c.path = "path-to-file"
+                c.original_path = "path-to-file"
+                c.path = "/tmp/somewhere/path-to-file"
                 c.run_pre_consume_script()
 
                 m.assert_called_once()
@@ -841,10 +842,19 @@ class PreConsumeTestCase(TestCase):
                 args, kwargs = m.call_args
 
                 command = kwargs["args"]
+                environment = kwargs["env"]
 
                 self.assertEqual(command[0], script.name)
                 self.assertEqual(command[1], "path-to-file")
 
+                self.assertDictContainsSubset(
+                    {
+                        "DOCUMENT_SOURCE_PATH": c.original_path,
+                        "DOCUMENT_WORKING_PATH": c.path,
+                    },
+                    environment,
+                )
+
     @mock.patch("documents.consumer.Consumer.log")
     def test_script_with_output(self, mocked_log):
         """
@@ -961,9 +971,10 @@ class PostConsumeTestCase(TestCase):
 
                 m.assert_called_once()
 
-                args, kwargs = m.call_args
+                _, kwargs = m.call_args
 
                 command = kwargs["args"]
+                environment = kwargs["env"]
 
                 self.assertEqual(command[0], script.name)
                 self.assertEqual(command[1], str(doc.pk))
@@ -972,6 +983,17 @@ class PostConsumeTestCase(TestCase):
                 self.assertEqual(command[7], "my_bank")
                 self.assertCountEqual(command[8].split(","), ["a", "b"])
 
+                self.assertDictContainsSubset(
+                    {
+                        "DOCUMENT_ID": str(doc.pk),
+                        "DOCUMENT_DOWNLOAD_URL": f"/api/documents/{doc.pk}/download/",
+                        "DOCUMENT_THUMBNAIL_URL": f"/api/documents/{doc.pk}/thumb/",
+                        "DOCUMENT_CORRESPONDENT": "my_bank",
+                        "DOCUMENT_TAGS": "a,b",
+                    },
+                    environment,
+                )
+
     def test_script_exit_non_zero(self):
         """
         GIVEN:

src/documents/tests/test_index.py

@@ -1,3 +1,5 @@
+from unittest import mock
+
 from django.test import TestCase
 from documents import index
 from documents.models import Document
@@ -31,3 +33,60 @@ class TestAutoComplete(DirectoriesMixin, TestCase):
         )
         self.assertListEqual(index.autocomplete(ix, "tes", limit=1), [b"test3"])
         self.assertListEqual(index.autocomplete(ix, "tes", limit=0), [])
+
+    def test_archive_serial_number_ranging(self):
+        """
+        GIVEN:
+            - Document with an archive serial number above schema allowed size
+        WHEN:
+            - Document is provided to the index
+        THEN:
+            - Error is logged
+            - Document ASN is reset to 0 for the index
+        """
+        doc1 = Document.objects.create(
+            title="doc1",
+            checksum="A",
+            content="test test2 test3",
+            # yes, this is allowed, unless full_clean is run
+            # DRF does call the validators, this test won't
+            archive_serial_number=Document.ARCHIVE_SERIAL_NUMBER_MAX + 1,
+        )
+        with self.assertLogs("paperless.index", level="ERROR") as cm:
+            with mock.patch(
+                "documents.index.AsyncWriter.update_document",
+            ) as mocked_update_doc:
+                index.add_or_update_document(doc1)
+
+                mocked_update_doc.assert_called_once()
+                _, kwargs = mocked_update_doc.call_args
+
+                self.assertEqual(kwargs["asn"], 0)
+
+                error_str = cm.output[0]
+                expected_str = "ERROR:paperless.index:Not indexing Archive Serial Number 4294967296 of document 1"
+                self.assertIn(expected_str, error_str)
+
+    def test_archive_serial_number_is_none(self):
+        """
+        GIVEN:
+            - Document with no archive serial number
+        WHEN:
+            - Document is provided to the index
+        THEN:
+            - ASN isn't touched
+        """
+        doc1 = Document.objects.create(
+            title="doc1",
+            checksum="A",
+            content="test test2 test3",
+        )
+        with mock.patch(
+            "documents.index.AsyncWriter.update_document",
+        ) as mocked_update_doc:
+            index.add_or_update_document(doc1)
+
+            mocked_update_doc.assert_called_once()
+            _, kwargs = mocked_update_doc.call_args
+
+            self.assertIsNone(kwargs["asn"])

src/documents/tests/utils.py

@@ -3,6 +3,7 @@ import shutil
 import tempfile
 from collections import namedtuple
 from contextlib import contextmanager
+from unittest import mock
 
 from django.apps import apps
 from django.db import connection
@@ -86,6 +87,30 @@ class DirectoriesMixin:
         remove_dirs(self.dirs)
 
 
+class ConsumerProgressMixin:
+    def setUp(self) -> None:
+        self.send_progress_patcher = mock.patch(
+            "documents.consumer.Consumer._send_progress",
+        )
+        self.send_progress_mock = self.send_progress_patcher.start()
+        super().setUp()
+
+    def tearDown(self) -> None:
+        super().tearDown()
+        self.send_progress_patcher.stop()
+
+
+class DocumentConsumeDelayMixin:
+    def setUp(self) -> None:
+        self.consume_file_patcher = mock.patch("documents.tasks.consume_file.delay")
+        self.consume_file_mock = self.consume_file_patcher.start()
+        super().setUp()
+
+    def tearDown(self) -> None:
+        super().tearDown()
+        self.consume_file_patcher.stop()
+
+
 class TestMigrations(TransactionTestCase):
     @property
     def app(self):

src/paperless/version.py

@@ -1,7 +1,7 @@
 from typing import Final
 from typing import Tuple
 
-__version__: Final[Tuple[int, int, int]] = (1, 12, 1)
+__version__: Final[Tuple[int, int, int]] = (1, 12, 2)
 # Version string like X.Y.Z
 __full_version_str__: Final[str] = ".".join(map(str, __version__))
 # Version string like X.Y

src/paperless_mail/tests/test_parsers_live.py

@@ -67,11 +67,6 @@ class TestParserLive(TestCase):
 
         return result
 
-    # Only run if convert is available
-    @pytest.mark.skipif(
-        "PAPERLESS_TEST_SKIP_CONVERT" in os.environ,
-        reason="PAPERLESS_TEST_SKIP_CONVERT set, skipping Test",
-    )
     @mock.patch("paperless_mail.parsers.MailDocumentParser.generate_pdf")
     def test_get_thumbnail(self, mock_generate_pdf: mock.MagicMock):
         """
@@ -204,11 +199,6 @@ class TestParserLive(TestCase):
         "GOTENBERG_LIVE" not in os.environ,
         reason="No gotenberg server",
     )
-    # Only run if convert is available
-    @pytest.mark.skipif(
-        "PAPERLESS_TEST_SKIP_CONVERT" in os.environ,
-        reason="PAPERLESS_TEST_SKIP_CONVERT set, skipping Test",
-    )
     def test_generate_pdf_from_mail(self):
         """
         GIVEN:
@@ -301,11 +291,6 @@ class TestParserLive(TestCase):
         "GOTENBERG_LIVE" not in os.environ,
         reason="No gotenberg server",
     )
-    # Only run if convert is available
-    @pytest.mark.skipif(
-        "PAPERLESS_TEST_SKIP_CONVERT" in os.environ,
-        reason="PAPERLESS_TEST_SKIP_CONVERT set, skipping Test",
-    )
     def test_generate_pdf_from_html(self):
         """
         GIVEN:

src/paperless_tika/parsers.py

@@ -90,7 +90,7 @@ class TikaDocumentParser(DocumentParser):
         with open(document_path, "rb") as document_handle:
             files = {
                 "files": (
-                    file_name or os.path.basename(document_path),
+                    "convert" + os.path.splitext(document_path)[-1],
                     document_handle,
                 ),
             }

src/setup.cfg

@@ -7,7 +7,7 @@ max-line-length = 88
 
 [tool:pytest]
 DJANGO_SETTINGS_MODULE=paperless.settings
-addopts = --pythonwarnings=all --cov --cov-report=html --numprocesses auto --quiet
+addopts = --pythonwarnings=all --cov --cov-report=html --cov-report=xml --numprocesses auto --quiet
 env =
   PAPERLESS_DISABLE_DBHANDLER=true