Merge branch 'dev'

Translate '/src-ui/messages.xlf' in 'fr'

.dockerignore

@@ -1,3 +1,4 @@
+**/__pycache__
 /src-ui/.vscode
 /src-ui/node_modules
 /src-ui/dist
@@ -10,3 +11,9 @@
 .pytest_cache
 /dist
 /scripts
+/resources
+**/tests
+**/*.spec.ts
+**/htmlcov
+/src/.pytest_cache
+.idea

.github/workflows/ansible.yml

@@ -0,0 +1,64 @@
+---
+name: Ansible Role
+
+on: [push, pull_request]
+
+jobs:
+  # https://molecule.readthedocs.io/en/latest/ci.html#github-actions
+  test:
+    runs-on: ubuntu-latest
+    # https://docs.github.com/en/free-pro-team@latest/actions/reference/context-and-expression-syntax-for-github-actions#github-context
+    if: github.event_name == 'pull_request' || (github.event_name == 'push' && contains(github.ref, 'refs/heads/'))
+    steps:
+      - name: Check out the codebase
+        uses: actions/checkout@v2
+        with:
+          path: "${{ github.repository }}"
+      - name: Set up Python
+        uses: actions/setup-python@v2
+      - name: Set up Docker
+        uses: docker-practice/actions-setup-docker@master
+      - name: Install dependencies
+        run: |
+          python3 -m pip install --upgrade pip
+          python3 -m pip install molecule[ansible,docker]
+          ansible --version
+          docker --version
+          molecule --version
+          python --version
+      - name: Test fresh installation with molecule
+        run: |
+          cd ansible
+          molecule test -s fresh
+        working-directory: "${{ github.repository }}"
+      - name: Test release update with molecule
+        run: |
+          cd ansible
+          molecule test -s update
+        working-directory: "${{ github.repository }}"
+  # # https://galaxy.ansible.com/docs/contributing/importing.html
+  # release:
+  #   runs-on: ubuntu-latest
+  #   needs:
+  #     - test
+  #   # https://docs.github.com/en/free-pro-team@latest/actions/reference/context-and-expression-syntax-for-github-actions#github-context
+  #   if: contains(github.ref, 'refs/tags/')
+  #   steps:
+  #     - name: Check out the codebase
+  #       uses: actions/checkout@v2
+  #       with:
+  #         path: "${{ github.repository }}"
+  #     - name: Set up Python
+  #       uses: actions/setup-python@v2
+  #     - name: Install dependencies
+  #       run: |
+  #         python3 -m pip install --upgrade ansible-base
+  #         ansible --version
+  #         python --version
+  #     - name: Trigger a new import on Galaxy
+  #     # TODO Check if source if pulled from cwd or imported from github
+  #     # https://github.com/ansible/ansible/blob/devel/lib/ansible/cli/galaxy.py
+  #       run: |
+  #         cd ansible
+  #         ansible-galaxy role import --api-key ${{ secrets.GALAXY_API_KEY }} $(echo ${{ github.repository }} | cut -d/ -f1) $(echo ${{ github.repository }} | cut -d/ -f2)
+  #       working-directory: "${{ github.repository }}"

.github/workflows/ci.yml

@@ -0,0 +1,291 @@
+name: ci
+
+on: [push, pull_request]
+
+jobs:
+  documentation:
+    runs-on: ubuntu-20.04
+    steps:
+      -
+        name: Checkout
+        uses: actions/checkout@v2
+      -
+        name: Set up Python
+        uses: actions/setup-python@v2
+        with:
+          python-version: 3.8
+      -
+        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: ${{ runner.os }}-pip3.8}
+      -
+        name: Install dependencies
+        run: |
+          sudo apt-get update -qq
+          sudo apt-get install -qq --no-install-recommends libpoppler-cpp-dev
+          pip install --upgrade pipenv
+          pipenv install --system --dev --ignore-pipfile
+      -
+        name: Make documentation
+        run: |
+          cd docs/
+          make html
+      -
+        name: Upload artifact
+        uses: actions/upload-artifact@v2
+        with:
+          name: documentation
+          path: docs/_build/html/
+
+  tests:
+    runs-on: ubuntu-20.04
+    strategy:
+      matrix:
+        python-version: ['3.6', '3.7', '3.8']
+      fail-fast: false
+    steps:
+      -
+        name: Checkout
+        uses: actions/checkout@v2
+      -
+        name: Set up Python
+        uses: actions/setup-python@v2
+        with:
+          python-version: "${{ matrix.python-version }}"
+      -
+        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: Prepare tests
+        run: |
+          sudo apt-get update -qq
+          sudo apt-get install -qq --no-install-recommends libpoppler-cpp-dev unpaper tesseract-ocr imagemagick ghostscript optipng
+          pip install --upgrade pipenv
+          pipenv install --system --dev --ignore-pipfile
+      -
+        name: Tests
+        run: |
+          cd src/
+          pytest
+      -
+        name: Codestyle
+        run: |
+          cd src/
+          pycodestyle
+      -
+        name: Publish coverage results
+        if: matrix.python-version == '3.8'
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        # https://github.com/coveralls-clients/coveralls-python/issues/251
+        run: |
+          cd src/
+          coveralls --service=github
+
+  frontend:
+    runs-on: ubuntu-20.04
+    steps:
+    -
+      name: Checkout
+      uses: actions/checkout@v2
+    -
+      uses: actions/setup-node@v2
+      with:
+        node-version: '15'
+    -
+      name: Build frontend
+      run: ./compile-frontend.sh
+    -
+      name: Upload artifact
+      uses: actions/upload-artifact@v2
+      with:
+        name: frontend-compiled
+        path: src/documents/static/frontend/
+
+  build-release:
+    needs: [frontend, documentation, tests]
+    runs-on: ubuntu-20.04
+    steps:
+      -
+        name: Checkout
+        uses: actions/checkout@v2
+      -
+        name: Set up Python
+        uses: actions/setup-python@v2
+        with:
+          python-version: 3.7
+      -
+        name: Install dependencies
+        run: |
+          sudo apt-get update -qq
+          sudo apt-get install -qq --no-install-recommends libpoppler-cpp-dev gettext liblept5
+          pip3 install -r requirements.txt
+      -
+        name: Download frontend artifact
+        uses: actions/download-artifact@v2
+        with:
+          name: frontend-compiled
+          path: src/documents/static/frontend/
+      -
+        name: Download documentation artifact
+        uses: actions/download-artifact@v2
+        with:
+          name: documentation
+          path: docs/_build/html/
+      -
+        name: Move files
+        run: |
+          mkdir dist
+          mkdir dist/paperless-ng
+          mkdir dist/paperless-ng/scripts
+          cp .dockerignore .env Dockerfile Pipfile Pipfile.lock LICENSE README.md requirements.txt dist/paperless-ng/
+          cp paperless.conf.example dist/paperless-ng/paperless.conf
+          cp docker/ dist/paperless-ng/docker -r
+          cp scripts/*.service scripts/*.sh dist/paperless-ng/scripts/
+          cp src/ dist/paperless-ng/src -r
+          cp docs/_build/html/ dist/paperless-ng/docs -r
+      -
+        name: Compile messages
+        run: |
+          cd dist/paperless-ng/src
+          python3 manage.py compilemessages
+      -
+        name: Collect static files
+        run: |
+          cd dist/paperless-ng/src
+          python3 manage.py collectstatic --no-input
+      -
+        name: Make release package
+        run: |
+          cd dist
+          find . -name __pycache__ | xargs rm -r
+          tar -cJf paperless-ng.tar.xz paperless-ng/
+      -
+        name: Upload release artifact
+        uses: actions/upload-artifact@v2
+        with:
+          name: release
+          path: dist/paperless-ng.tar.xz
+
+  publish-release:
+    runs-on: ubuntu-latest
+    needs: build-release
+    if: contains(github.ref, 'refs/tags/ng-')
+    steps:
+      -
+        name: Download release artifact
+        uses: actions/download-artifact@v2
+        with:
+          name: release
+          path: ./
+      -
+        name: Get version
+        id: get_version
+        run: |
+          echo ::set-output name=version::${GITHUB_REF#refs/tags/ng-}
+      -
+        name: Create release
+        id: create_release
+        uses: actions/create-release@v1
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        with:
+          tag_name: ng-${{ steps.get_version.outputs.version }}
+          release_name: Paperless-ng ${{ steps.get_version.outputs.version }}
+          draft: false
+          prerelease: false
+          body: |
+            For a complete list of changes, see the changelog at https://paperless-ng.readthedocs.io/en/latest/changelog.html.
+      -
+        name: Upload release archive
+        id: upload-release-asset
+        uses: actions/upload-release-asset@v1
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        with:
+          upload_url: ${{ steps.create_release.outputs.upload_url }} # This pulls from the CREATE RELEASE step above, referencing it's ID to get its outputs object, which include a `upload_url`. See this blog post for more info: https://jasonet.co/posts/new-features-of-github-actions/#passing-data-to-future-steps
+          asset_path: ./paperless-ng.tar.xz
+          asset_name: paperless-ng-${{ steps.get_version.outputs.version }}.tar.xz
+          asset_content_type: application/x-xz
+
+  # build and push image to docker hub.
+  build-docker-image:
+    if: github.event_name == 'push' && (github.ref == 'refs/heads/dev' || startsWith(github.ref, 'refs/tags/ng-'))
+    runs-on: ubuntu-latest
+    needs: [frontend, tests]
+    steps:
+      -
+        name: Prepare
+        id: prepare
+        run: |
+          IMAGE_NAME=jonaswinkler/paperless-ng
+          if [[ $GITHUB_REF == refs/tags/ng-* ]]; then
+            TAGS=${IMAGE_NAME}:${GITHUB_REF#refs/tags/ng-},${IMAGE_NAME}:latest
+            INSPECT_TAG=${IMAGE_NAME}:latest
+          elif [[ $GITHUB_REF == refs/heads/* ]]; then
+            TAGS=${IMAGE_NAME}:${GITHUB_REF#refs/heads/}
+            INSPECT_TAG=${TAGS}
+          else
+            exit 1
+          fi
+          echo ::set-output name=tags::${TAGS}
+          echo ::set-output name=inspect_tag::${INSPECT_TAG}
+      -
+        name: Checkout
+        uses: actions/checkout@v2
+      -
+        name: Download frontend artifact
+        uses: actions/download-artifact@v2
+        with:
+          name: frontend-compiled
+          path: src/documents/static/frontend/
+      -
+        name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v1
+      -
+        name: Set up QEMU
+        uses: docker/setup-qemu-action@v1
+      -
+        name: Cache Docker layers
+        uses: actions/cache@v2
+        with:
+          path: /tmp/.buildx-cache
+          key: ${{ runner.os }}-buildx-${{ github.sha }}
+          restore-keys: |
+            ${{ runner.os }}-buildx-
+      -
+        name: Login to DockerHub
+        uses: docker/login-action@v1
+        with:
+          username: ${{ secrets.DOCKER_USERNAME }}
+          password: ${{ secrets.DOCKER_PASSWORD }}
+      -
+        name: Build and push
+        uses: docker/build-push-action@v2
+        with:
+          context: .
+          file: ./Dockerfile
+          platforms: linux/amd64,linux/arm/v7,linux/arm64
+          push: true
+          tags: ${{ steps.prepare.outputs.tags }}
+          cache-from: type=local,src=/tmp/.buildx-cache
+          cache-to: type=local,dest=/tmp/.buildx-cache
+      -
+        name: Inspect image
+        run: |
+          docker buildx imagetools inspect ${{ steps.prepare.outputs.inspect_tag }}

.gitignore

@@ -65,8 +65,8 @@ target/
 .virtualenv
 virtualenv
 /venv
-docker-compose.env
-docker-compose.yml
+/docker-compose.env
+/docker-compose.yml
 
 # Used for development
 scripts/import-for-development
@@ -76,17 +76,13 @@ scripts/nuke
 /static/
 
 # Stored PDFs
-/media/documents/originals/*
-/media/documents/thumbnails/*
-
-/data/classification_model.pickle
-/data/db.sqlite3
-/data/index
-
+/media/
+/data/
 /paperless.conf
-/consume
-/export
+/consume/
+/export/
 /src-ui/.vscode
 
 # this is where the compiled frontend is moved to.
 /src/documents/static/frontend/
+/docs/.vscode/settings.json

.readthedocs.yml

@@ -0,0 +1,16 @@
+# .readthedocs.yml
+# Read the Docs configuration file
+# See https://docs.readthedocs.io/en/stable/config-file/v2.html for details
+
+# Required
+version: 2
+
+# Build documentation in the docs/ directory with Sphinx
+sphinx:
+  configuration: docs/conf.py
+
+# Optionally set the version of Python and requirements required to build your docs
+python:
+  version: 3.7
+  install:
+    - requirements: docs/requirements.txt

.travis.yml

@@ -1,48 +0,0 @@
-language: python
-
-jobs:
-  include:
-    - name: "Paperless on Python 3.6"
-      python: "3.6"
-
-    - name: "Paperless on Python 3.7"
-      python: "3.7"
-
-    - name: "Paperless on Python 3.8"
-      python: "3.8"
-
-    - name: "Documentation"
-      script:
-        - cd docs/
-        - make html
-      after_success: true
-
-    - name: "Front end"
-      language: node_js
-      node_js:
-        - 15
-      before_install: true
-      install:
-        - cd src-ui/
-        - npm install -g @angular/cli
-        - npm install
-      script:
-        - ng build --prod
-      after_success: true
-
-
-before_install:
-  - sudo apt-get update -qq
-  - sudo apt-get install -qq libpoppler-cpp-dev unpaper tesseract-ocr imagemagick ghostscript
-
-install:
-  - pip install --upgrade pipenv
-  - pipenv install --system --dev
-
-script:
-  - cd src/
-  - pipenv run pytest --cov
-  - pipenv run pycodestyle
-
-after_success:
-  - pipenv run coveralls

CONTRIBUTING.md

@@ -1,13 +1,30 @@
 # Contributing
 
-If you feel that somethings is not working, please submit an issue. You can also ask questions on the issue tracker by tagging your question with the question tag.
+There's still lots of things to be done, just have a look at that issue log. If you feel like conctributing to the project, please do! Bug fixes and improvements to the front end (I just can't seem to get some of these CSS things right) are always welcome.
 
-Pull requests are welcome, however, I will be a little bit more strict about what goes into the code and what does not. If you want to make a big change, please ask me about it first.
+If you want to implement something big: Please start a discussion about that in the issues! Maybe I've already had something similar in mind and we can make it happen together. However, keep in mind that the general roadmap is to make the existing features stable and get them tested. See the roadmap in the readme.
 
 * 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.
 
-However:
+## Python
 
-* Bug fixes and are always welcome. Docker makes things easier, however, I alone cannot ensure that this runs on all platforms.
-* Improvements to the styling of the front-end are always welcome. I'm no expert in things UX, and simply copied one of the Bootstrap examples. I think it turned out rather good, but I just can't seem to get some things working properly.
+Use python 3.6 for development. Paperless supports python 3.6, 3.7 and 3.8.
+
+## Branches
+
+master always reflects the latest release.
+
+dev contains all changes that will be part of the next release. Use this branch to start making your changes.
+
+feature-X branches is for experimental stuff that will eventually be merged into dev, and then released as part of the next release.
+
+## Testing:
+
+I'm trying to get most of paperless tested, so please do the same for your code! I know its a hassle, but it makes sure that your code works now and will allow us to detect regressions easily.
+
+To test your code, execute `pytest` in the src/ directory. Executing that in the project root is no good. This also generates a html coverage report, which you can use to see if you missed anything important during testing.
+
+## More info:
+
+... is available in the documentation. https://paperless-ng.readthedocs.io/en/latest/extending.html

Dockerfile

@@ -0,0 +1,110 @@
+FROM ubuntu:20.04 AS jbig2enc
+
+WORKDIR /usr/src/jbig2enc
+
+RUN apt-get update && apt-get install -y --no-install-recommends build-essential automake libtool libleptonica-dev zlib1g-dev git ca-certificates
+
+RUN git clone https://github.com/agl/jbig2enc .
+RUN ./autogen.sh
+RUN ./configure && make
+
+FROM python:3.7-slim
+
+WORKDIR /usr/src/paperless/
+
+COPY requirements.txt ./
+
+# Binary dependencies
+RUN apt-get update \
+  && apt-get -y --no-install-recommends install \
+  	# Basic dependencies
+		curl \
+		file \
+		# fonts for text file thumbnail generation
+		fonts-liberation \
+		# for making translations further down
+		gettext \
+		gnupg \
+		imagemagick \
+		# for Numpy
+		libatlas-base-dev \
+		libxslt1-dev \
+		mime-support \
+		# thumbnail size reduction
+		optipng \
+		sudo \
+		tzdata \
+  	# OCRmyPDF dependencies
+		ghostscript \
+		icc-profiles-free \
+		liblept5 \
+		libxml2 \
+		pngquant \
+		qpdf \
+		tesseract-ocr \
+		tesseract-ocr-eng \
+		tesseract-ocr-deu \
+		tesseract-ocr-fra \
+		tesseract-ocr-ita \
+		tesseract-ocr-spa \
+		unpaper \
+		zlib1g \
+		&& rm -rf /var/lib/apt/lists/*
+
+# This pulls in updated dependencies from bullseye to fix some issues with file type detection.
+# TODO: Remove this once bullseye releases.
+RUN echo "deb http://deb.debian.org/debian bullseye main" > /etc/apt/sources.list.d/bullseye.list \
+  && apt-get update \
+  && apt-get install --no-install-recommends -y file libmagic-dev \
+  && rm -rf /var/lib/apt/lists/* \
+  && rm /etc/apt/sources.list.d/bullseye.list
+
+# Python dependencies
+RUN apt-get update \
+  && apt-get -y --no-install-recommends install \
+		build-essential \
+		libpoppler-cpp-dev \
+		libpq-dev \
+		libqpdf-dev \
+	&& python3 -m pip install --upgrade --no-cache-dir supervisor \
+  && python3 -m pip install --no-cache-dir -r requirements.txt \
+	&& apt-get -y purge build-essential libqpdf-dev \
+	&& apt-get -y autoremove --purge \
+	&& rm -rf /var/lib/apt/lists/* \
+	&& mkdir /var/log/supervisord /var/run/supervisord
+
+
+# copy scripts
+# this fixes issues with imagemagick and PDF
+COPY docker/imagemagick-policy.xml /etc/ImageMagick-6/policy.xml
+COPY docker/gunicorn.conf.py ./
+COPY docker/supervisord.conf /etc/supervisord.conf
+COPY docker/docker-entrypoint.sh /sbin/docker-entrypoint.sh
+
+# copy 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/
+
+
+# copy app
+COPY src/ ./src/
+
+# add users, setup scripts
+RUN addgroup --gid 1000 paperless \
+	&& useradd --uid 1000 --gid paperless --home-dir /usr/src/paperless paperless \
+	&& chown -R paperless:paperless . \
+	&& chmod 755 /sbin/docker-entrypoint.sh
+
+WORKDIR /usr/src/paperless/src/
+
+RUN sudo -HEu paperless python3 manage.py collectstatic --clear --no-input
+
+RUN sudo -HEu 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"]
+
+LABEL maintainer="Jonas Winkler <dev@jpwinkler.de>"

Pipfile

@@ -8,9 +8,6 @@ url = "https://www.piwheels.org/simple"
 verify_ssl = true
 name = "piwheels"
 
-[requires]
-python_version = "3.6"
-
 [packages]
 dateparser = "~=0.7.6"
 django = "~=3.1.3"
@@ -19,14 +16,16 @@ django-extensions = "*"
 django-filter = "~=2.4.0"
 django-q = "~=1.3.4"
 djangorestframework = "~=3.12.2"
+filelock = "*"
 fuzzywuzzy = "*"
 gunicorn = "*"
 imap-tools = "*"
 langdetect = "*"
 pdftotext = "*"
 pathvalidate = "*"
-pillow = "*"
-pyocr = "~=0.7.2"
+# pinned to 8.1.0, since aarch64 wheels might not be available beyond that https://github.com/python-pillow/Pillow/issues/5202
+pillow = "==8.1.0"
+pikepdf = "~=2.2.5"
 python-gnupg = "*"
 python-dotenv = "*"
 python-dateutil = "*"
@@ -34,11 +33,14 @@ python-Levenshtein = "*"
 python-magic = "*"
 psycopg2-binary = "*"
 redis = "*"
-scikit-learn="~=0.23.2"
+scikit-learn="~=0.24.0"
 whitenoise = "~=5.2.0"
 watchdog = "*"
 whoosh="~=2.7.4"
-inotify-simple = "*"
+inotifyrecursive = "~=0.3.4"
+ocrmypdf = "~=11.4.5"
+tqdm = "*"
+tika = "*"
 
 [dev-packages]
 coveralls = "*"
@@ -50,6 +52,6 @@ pytest-django = "*"
 pytest-env = "*"
 pytest-sugar = "*"
 pytest-xdist = "*"
-sphinx = "~=3.3"
+sphinx = "~=3.4.2"
 sphinx_rtd_theme = "*"
 tox = "*"

README.md

@@ -1,87 +1,121 @@
-[![Build Status](https://travis-ci.org/jonaswinkler/paperless-ng.svg?branch=master)](https://travis-ci.org/jonaswinkler/paperless-ng)
+![ci](https://github.com/jonaswinkler/paperless-ng/workflows/ci/badge.svg)
 [![Documentation Status](https://readthedocs.org/projects/paperless-ng/badge/?version=latest)](https://paperless-ng.readthedocs.io/en/latest/?badge=latest)
+[![Gitter](https://badges.gitter.im/paperless-ng/community.svg)](https://gitter.im/paperless-ng/community?utm_source=badge&utm_medium=badge&utm_campaign=pr-badge&utm_content=badge)
 [![Docker Hub Pulls](https://img.shields.io/docker/pulls/jonaswinkler/paperless-ng.svg)](https://hub.docker.com/r/jonaswinkler/paperless-ng)
 [![Coverage Status](https://coveralls.io/repos/github/jonaswinkler/paperless-ng/badge.svg?branch=master)](https://coveralls.io/github/jonaswinkler/paperless-ng?branch=master)
 
 # Paperless-ng
 
-[Paperless](https://github.com/the-paperless-project/paperless) is an application by Daniel Quinn and others that indexes your scanned documents and allows you to easily search for documents and store metadata alongside your documents.
+[Paperless](https://github.com/the-paperless-project/paperless) is an application by Daniel Quinn and contributors that indexes your scanned documents and allows you to easily search for documents and store metadata alongside your documents.
 
-Paperless-ng is a fork of the original project, adding a new interface and many other changes under the hood. For a detailed list of changes, see below.
+Paperless-ng is a fork of the original project, adding a new interface and many other changes under the hood. For a detailed list of changes, have a look at the changelog in the documentation.
 
-This project is still in development and some things may not work as expected.
+# Survey
+
+If you already used Paperless-ng for a bit, would like to give some anonymous feedback, and help me decide on what to focus on next: I've created a survey, [see here](https://github.com/jonaswinkler/paperless-ng/issues/402). Thank you!
 
 # How it Works
 
 Paperless does not control your scanner, it only helps you deal with what your scanner produces.
 
-1. Buy a document scanner that can write to a place on your network.  If you need some inspiration, have a look at the [scanner recommendations](https://paperless-ng.readthedocs.io/en/latest/scanners.html) page.
-2. Set it up to "scan to FTP" or something similar. It should be able to push scanned images to a server without you having to do anything.  Of course if your scanner doesn't know how to automatically upload the file somewhere, you can always do that manually. Paperless doesn't care how the documents get into its local consumption directory.
-3. Have the target server run the Paperless consumption script to OCR the file and index it into a local database.
-4. Use the web frontend to sift through the database and find what you want.
-5. Download the PDF you need/want via the web interface and do whatever you like with it.  You can even print it and send it as if it's the original. In most cases, no one will care or notice.
+1. Buy a document scanner that can write to a place on your network.  If you need some inspiration, have a look at the [scanner recommendations](https://paperless-ng.readthedocs.io/en/latest/scanners.html) page. Set it up to "scan to FTP" or something similar. It should be able to push scanned images to a server without you having to do anything.  Of course if your scanner doesn't know how to automatically upload the file somewhere, you can always do that manually. Paperless doesn't care how the documents get into its local consumption directory.
+
+	- Alternatively, you can use any of the mobile scanning apps out there. We have an app that allows you to share documents with paperless, if you're on Android. See the section on affiliated projects.
+
+2. Wait for paperless to process your files. OCR is expensive, and depending on the power of your machine, this might take a bit of time.
+3. Use the web frontend to sift through the database and find what you want.
+4. Download the PDF you need/want via the web interface and do whatever you like with it.  You can even print it and send it as if it's the original. In most cases, no one will care or notice.
 
 Here's what you get:
 
 ![Dashboard](https://github.com/jonaswinkler/paperless-ng/raw/master/docs/_static/screenshots/dashboard.png)
 
-# Why Paperless-ng?
+# Features
 
-I wanted to make big changes to the project that will impact the way it is used by its users greatly. Among the users who currently use paperless in production there are probably many that don't want these changes right away. I also wanted to have more control over what goes into the code and what does not. Therefore, paperless-ng was created. NG stands for both Angular (the framework used for the Frontend) and next-gen. Publishing this project under a different name also avoids confusion between paperless and paperless-ng.
-
-The gist of the changes is the following:
-
-* New front end. This will eventually be mobile friendly as well.
-* New full text search.
-* New email processing.
+* Performs OCR on your documents, adds selectable text to image only documents and adds tags, correspondents and document types to your documents.
+* Paperless stores your documents plain on disk. Filenames and folders are managed by paperless and can be configured freely.
+* Single page application front end. Should be pretty snappy. Will be mobile friendly in the future.
+	* Includes a dashboard that shows basic statistics and has document upload.
+	* Filtering by tags, correspondents, types, and more.
+	* Customizable views can be saved and displayed on the dashboard.
+* Full text search helps you find what you need.
+	* Auto completion suggests relevant words from your documents.
+	* Results are sorted by relevance to your search query.
+	* Highlighting shows you which parts of the document matched the query.
+	* 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 mails, paperless can move these mails to a new folder, mark them as read, flag them or delete them.
 * Machine learning powered document matching.
-* Code cleanup in many, MANY areas.
+	* Paperless learns from your documents and will be able to automatically assign tags, correspondents and types to documents once you've stored a few documents in paperless.
+* A task processor that processes documents in parallel and also tells you when something goes wrong. On modern multi core systems, consumption is blazing fast.
 
-If you want to see some screenshots of paperless-ng in action, [some are available in the documentation](https://paperless-ng.readthedocs.io/en/latest/screenshots.html).
+If you want to see some screenshots of paperless-ng in action, [some are available in the documentation](https://paperless-ng.readthedocs.io/en/latest/screenshots.html). However, some parts of the UI have changed since I took these.
 
-For a complete list of changes, check out the [changelog](https://paperless-ng.readthedocs.io/en/latest/changelog.html)
+For a complete list of changes from paperless, check out the [changelog](https://paperless-ng.readthedocs.io/en/latest/changelog.html)
 
-## Planned
+# Roadmap for 1.0
 
-These features will make it into the application at some point, sorted by priority.
-
-- **More search.** The search backend is incredibly versatile and customizable. Searching is the most important feature of this project and thus, I want to implement things like:
-  - Group and limit search results by correspondent, show “more from this” links in the results.
-  - Ability to search for “Similar documents” in the search results
-  - Provide corrections for mispelled queries
-- **More robust consumer** that shows its progress on the web page.
-- **Arbitrary tag colors**. Allow the selection of any color with a color picker.
+- Make the front end nice (except mobile).
+- Fix whatever bugs I and you find.
+- Make the documentation nice.
 
 ## On the chopping block.
 
-- **GnuPG encrypion.** Since its disabled by default and the website allows transparent access to encrypted documents anyway, this doesn’t really provide any benefit over having the application stored on an encrypted file system.
+- **GnuPG encrypion.** [Here's a note about encryption in paperless](https://paperless-ng.readthedocs.io/en/latest/administration.html#managing-encryption). The gist of it is that I don't see which attacks this implementation protects against. It gives a false sense of security to users who don't care about how it works.
+
+## Wont-do list.
+
+These features will probably never make it into paperless, since paperless is meant to be an easy to use set-and-forget solution.
+
+- **Document versions.** I might consider adding the ability to update a document with a newer version, but that's about it. The kind of documents that get added to paperless usually don't change at all.
+- **Workflows.** I don't see a use case for these, yet.
+- **Folders.** Tags are superior in just about every way.
+- **Apps / extension support.** Again, paperless is meant to be simple.
 
 # Getting started
 
-The recommended way to deploy paperless is docker-compose. Grab the latest release to get started. the dockerfiles archive contains just the docker files which will pull the image from docker hub. The source archive contains everything you need to build the docker image yourself.
+The recommended way to deploy paperless is docker-compose. The files in the /docker/hub directory are configured to pull the image from Docker Hub.
 
 Read the [documentation](https://paperless-ng.readthedocs.io/en/latest/setup.html#installation) on how to get started.
 
-Alternatively, you can install the dependencies and setup apache and a database server yourself. Details for that will be available in the documentation at some point.
+Alternatively, you can install the dependencies and setup apache and a database server yourself. The documenation has a step by step guide on how to do it.
 
 # Migrating to paperless-ng
 
-Read the section about [migration](https://paperless-ng.readthedocs.io/en/latest/setup.html#migration-to-paperless-ng) in the documentation.
+Read the section about [migration](https://paperless-ng.readthedocs.io/en/latest/setup.html#migration-to-paperless-ng) in the documentation. Its also entirely possible to go back to paperless by reverting the database migrations.
 
 # Documentation
 
 The documentation for Paperless-ng is available on [ReadTheDocs](https://paperless-ng.readthedocs.io/).
 
+# Translation
+
+Paperless is currently available in English, German, Dutch and French. Translation is coordinated at transifex: https://www.transifex.com/paperless/paperless-ng
+
+If you want to see paperless in your own language, request that language at transifex and you can start translating after I approve the language.
+
+# Suggestions? Questions? Something not working?
+
+Please open an issue and start a discussion about it!
+
+## Feel like helping out?
+
+There's still lots of things to be done, just have a look at that issue log. If you feel like contributing to the project, please do! Bug fixes and improvements to the front end (I just can't seem to get some of these CSS things right) are always welcome. The documentation has some basic information on how to get started.
+
+If you want to implement something big: Please start a discussion about that in the issues! Maybe I've already had something similar in mind and we can make it happen together. However, keep in mind that the general roadmap is to make the existing features stable and get them tested. See the roadmap above.
+
 # Affiliated Projects
 
 Paperless has been around a while now, and people are starting to build stuff on top of it.  If you're one of those people, we can add your project to this list:
 
-* [Paperless App](https://github.com/bauerj/paperless_app): An Android/iOS app for Paperless.
-* [Paperless Desktop](https://github.com/thomasbrueggemann/paperless-desktop): A desktop UI for your Paperless installation.  Runs on Mac, Linux, and Windows.
-* [ansible-role-paperless](https://github.com/ovv/ansible-role-paperless): An easy way to get Paperless running via Ansible.
-* [paperless-cli](https://github.com/stgarf/paperless-cli): A golang command line binary to interact with a Paperless instance.
+* [Paperless App](https://github.com/bauerj/paperless_app): An Android/iOS app for Paperless. Updated to work with paperless-ng.
+* [Paperless Share](https://github.com/qcasey/paperless_share). Share any files from your Android application with paperless. Very simple, but works with all of the mobile scanning apps out there that allow you to share scanned documents.
 
-Compatibility with Paperless-ng is unknown.
+These projects also exist, but their status and compatibility with paperless-ng is unknown.
+
+* [Paperless Desktop](https://github.com/thomasbrueggemann/paperless-desktop): A desktop UI for your Paperless installation.  Runs on Mac, Linux, and Windows.
+* [paperless-cli](https://github.com/stgarf/paperless-cli): A golang command line binary to interact with a Paperless instance.
 
 # Important Note
 

ansible/README.md

@@ -0,0 +1,114 @@
+Ansible Role: paperless-ng
+==========================
+
+Installs and configures paperless-ng EDMS on Debian/Ubuntu systems.
+
+Requirements
+------------
+
+No special system requirements. Ansible 2.7 or newer is required.
+
+Note that this role requires root access, so either run it in a playbook with a global `become: yes`, or invoke the role in your playbook like:
+
+    - hosts: all
+      roles:
+        - role: ansible
+          become: yes
+
+Role Variables
+--------------
+
+Most configuration variables from paperless-ng itself are available and accept their respective arguments.
+Every `PAPERLESS_*` configuration varaible is lowercased and instead prefixed with `paperlessng_*` in `defaults/main.yml`.
+
+For a full listing including explainations and allowed values, see the current [documentation](https://paperless-ng.readthedocs.io/en/ng-0.9.14/configuration.html).
+
+Additional variables available in this role are listed below, along with default values:
+
+    paperlessng_version: 0.9.14
+
+The [release](https://github.com/jonaswinkler/paperless-ng/releases) archive version of paperless-ng to install.
+
+    paperlessng_redis_host: localhost
+    paperlessng_redis_port: 6379
+
+Seperate configuration values that combine into `PAPERLESS_REDIS`.
+
+    paperlessng_db_type: sqlite
+
+Database to use. Default is file-based SQLite.
+
+    paperlessng_db_host: localhost
+    paperlessng_db_port: 5432
+    paperlessng_db_name: paperlessng
+    paperlessng_db_user: paperlessng
+    paperlessng_db_pass: paperlessng
+    paperlessng_db_sslmode: prefer
+
+Database configuration (only applicable if `paperlessng_db_type == 'postgresql'`).
+
+    paperlessng_directory: /opt/paperless-ng
+
+Root directory paperless-ng is installed into.
+
+    paperlessng_virtualenv: "{{ paperlessng_directory }}/.venv"
+
+Directory used for the virtual environment for paperless-ng.
+
+    paperlessng_ocr_languages:
+      - eng
+
+List of OCR languages to install and configure (`apt search tesseract-ocr-*`).
+
+    paperlessng_use_jbig2enc: True
+
+Whether to install and use [jbig2enc](https://github.com/agl/jbig2enc) for OCRmyPDF.
+
+    paperlessng_big2enc_lossy: False
+
+Whether to use jbig2enc's lossy compression mode.
+
+    paperlessng_superuser_name: paperlessng
+    paperlessng_superuser_email: paperlessng@example.com
+    paperlessng_superuser_password: paperlessng
+
+Credentials of the initial superuser in paperless-ng.
+
+    paperlessng_system_user: paperlessng
+    paperlessng_system_group: paperlessng
+
+System user and group to run the paperless-ng services as (will be created if required).
+
+    paperlessng_listen_address: 127.0.0.1
+    paperlessng_listen_port: 8000
+
+Address and port for the paperless-ng service to listen on.
+
+Dependencies
+------------
+
+No ansible dependencies.
+
+Example Playbook
+----------------
+`playbook.yml`:
+
+    - hosts: all
+      become: yes
+      vars_files:
+        - vars/main.yml
+      roles:
+        - ansible
+
+`vars/main.yml`:
+
+    paperlessng_media_root: /mnt/media/smbshare
+
+    paperlessng_db_type: postgresql
+    paperlessng_db_pass: PLEASEPROVIDEASTRONGPASSWORDHERE
+
+    paperless_secret_key: AGAINPLEASECHANGETHISNOW
+
+    paperlessng_ocr_languages:
+      - eng
+      - deu

ansible/defaults/main.yml

@@ -0,0 +1,78 @@
+---
+paperlessng_version: 0.9.14
+
+# Required services
+paperlessng_redis_host: localhost
+paperlessng_redis_port: 6379
+paperlessng_db_type: sqlite # or postgresql
+# Below entries only apply for paperlessng_db_type=='postgresql'
+paperlessng_db_host: localhost
+paperlessng_db_port: 5432
+paperlessng_db_name: paperlessng
+paperlessng_db_user: paperlessng
+paperlessng_db_pass: paperlessng
+paperlessng_db_sslmode: prefer
+
+# Paths and folders
+paperlessng_directory: /opt/paperless-ng
+paperlessng_consumption_dir: "{{ paperlessng_directory }}/consumption"
+paperlessng_data_dir: "{{ paperlessng_directory }}/data"
+paperlessng_media_root: "{{ paperlessng_directory }}/media"
+paperlessng_static_dir: "{{ paperlessng_directory }}/static"
+paperlessng_filename_format:
+paperlessng_virtualenv: "{{ paperlessng_directory }}/.venv"
+
+# Hosting & Security
+paperless_secret_key: PLEASECHANGETHISFORTHELOVEOFGOD
+paperless_allowed_hosts: "*"
+paperless_cors_allowed_hosts: http://localhost:8000
+paperless_force_script_name:
+paperless_static_url: /static/
+paperless_auto_login_username:
+paperless_cookie_prefix: ""
+paperless_enable_http_remote_user: False
+
+# OCR settings
+paperlessng_ocr_languages:
+  - eng
+paperlessng_ocr_mode: skip
+paperlessng_ocr_output_type: pdfa
+paperlessng_ocr_pages: 0
+paperlessng_ocr_image_dpi:
+# see https://ocrmypdf.readthedocs.io/en/latest/api.html#ocrmypdf.ocr
+paperlessng_ocr_user_args:
+  #- "deskew": True  # https://github.com/jonaswinkler/paperless-ng/issues/231
+  - "optimize": 1
+paperlessng_use_jbig2enc: True
+paperlessng_big2enc_lossy: False
+
+# Tika settings
+paperlessng_tika_enabled: False
+paperlessng_tika_endpoint: http://localhost:9998
+paperlessng_tika_gotenberg_endpoint: http://localhost:3000
+
+# Software tweaks
+paperlessng_time_zone: Europe/Berlin
+paperlessng_consumer_polling: 0
+paperlessng_consumer_delete_duplicates: False
+paperlessng_consumer_recursive: False
+paperlessng_consumer_subdirs_as_tags: False
+paperlessng_optimize_thumbnails: True
+paperlessng_post_consume_script:
+paperlessng_filename_date_order:
+paperlessng_filename_parse_transforms:
+paperlessng_thumbnail_font_name: /usr/share/fonts/liberation/LiberationSerif-Regular.ttf
+paperlessng_ignore_dates: ""
+
+# Superuser settings
+paperlessng_superuser_name: paperlessng
+paperlessng_superuser_email: paperlessng@example.com
+paperlessng_superuser_password: paperlessng
+
+# System user settings
+paperlessng_system_user: paperlessng
+paperlessng_system_group: paperlessng
+
+# Webserver settings
+paperlessng_listen_address: 127.0.0.1
+paperlessng_listen_port: 8000

ansible/meta/main.yml

@@ -0,0 +1,17 @@
+dependencies: []
+
+galaxy_info:
+  author: C0nsultant
+  description: Bare-metal deployment of paperless-ng DMS
+  license: license (GPLv3)
+  min_ansible_version: 2.7
+
+  platforms:
+    - name: Debian
+      versions:
+        - buster
+    - name: Ubuntu
+      versions:
+        - focal
+
+  galaxy_tags: [EDMS, django, python, web]

ansible/molecule/fresh/converge.yml

@@ -0,0 +1,7 @@
+---
+- name: fresh installation
+  hosts: all
+  tasks:
+    - name: install paperless-ng with default parameters
+      include_role:
+        name: ansible

ansible/molecule/fresh/molecule.yml

@@ -0,0 +1,35 @@
+---
+dependency:
+  name: galaxy
+driver:
+  name: docker
+platforms:
+  - name: ubuntu_focal
+    image: jrei/systemd-ubuntu:20.04
+    privileged: true
+    volumes:
+      - /sys/fs/cgroup:/sys/fs/cgroup:ro
+    tmpfs:
+      - /tmp
+      - /run
+      - /run/lock
+    override_command: False
+  # ubuntu 18.04 bionic works except that
+  #   the default redis configuration expects IPv6 which is not enabled in docker by default
+  #   the default Python environment is configured for ASCII instead of UTF-8
+  # ubuntu 16.04 xenial only has Python 3.5 which is EOL and breaks multiple dependencies
+  - name: debian_buster
+    image: jrei/systemd-debian:10
+    privileged: true
+    volumes:
+      - /sys/fs/cgroup:/sys/fs/cgroup:ro
+    tmpfs:
+      - /tmp
+      - /run
+      - /run/lock
+    override_command: False
+  # debian 9 stretch only has Python 3.5 which is EOL and breaks multiple dependencies
+provisioner:
+  name: ansible
+verifier:
+  name: ansible

ansible/molecule/fresh/verify.yml

@@ -0,0 +1,60 @@
+---
+- name: Verify
+  hosts: all
+  gather_facts: false
+
+  vars_files:
+    - ../../defaults/main.yml
+
+  tasks:
+    - name: check if webserver is up
+      uri:
+        url: http://localhost:8000
+        status_code: [200, 302]
+        return_content: yes
+      register: landingpage
+      failed_when: "'Sign in</button>' not in landingpage.content"
+
+    - name: check if document posting works
+      uri:
+        url: http://localhost:8000/api/documents/post_document/
+        method: POST
+        body_format: form-multipart
+        body:
+          document:
+            content: FOO
+            filename: document.txt
+            mime_type: text/plain
+        headers:
+          Authorization: 'Basic {{ (paperlessng_superuser_name + ":" + paperlessng_superuser_password) | b64encode }}'
+        return_content: yes
+      register: post_document
+      failed_when: "'OK' not in post_document.content"
+
+    - name: verify uploaded document has been accepted
+      uri:
+        url: http://localhost:8000/api/logs/
+        headers:
+          Authorization: 'Basic {{ (paperlessng_superuser_name + ":" + paperlessng_superuser_password) | b64encode }}'
+        return_content: yes
+      register: logs
+      failed_when: "'Consuming document.txt' not in logs.content"
+
+    # assumes txt consumption finished by now, might have to sleep a bit
+    - name: verify uploaded document has been consumed
+      uri:
+        url: http://localhost:8000/api/logs/
+        headers:
+          Authorization: 'Basic {{ (paperlessng_superuser_name + ":" + paperlessng_superuser_password) | b64encode }}'
+        return_content: yes
+      register: logs
+      failed_when: "'document consumption finished' not in logs.content"
+
+    - name: verify uploaded document is avaiable
+      uri:
+        url: http://localhost:8000/api/documents/1/
+        headers:
+          Authorization: 'Basic {{ (paperlessng_superuser_name + ":" + paperlessng_superuser_password) | b64encode }}'
+        return_content: yes
+      register: document
+      failed_when: "'Not found.' in document.content or 'FOO' not in document.content"

ansible/molecule/update/converge.yml

@@ -0,0 +1,11 @@
+---
+- name: update previous release to newest release
+  hosts: all
+  tasks:
+    - name: set current version as installation target
+      set_fact:
+        paperlessng_version: 0.9.14
+
+    - name: update to newest paperless-ng release
+      include_role:
+        name: ansible

ansible/molecule/update/molecule.yml

@@ -0,0 +1,35 @@
+---
+dependency:
+  name: galaxy
+driver:
+  name: docker
+platforms:
+  - name: ubuntu_focal
+    image: jrei/systemd-ubuntu:20.04
+    privileged: true
+    volumes:
+      - /sys/fs/cgroup:/sys/fs/cgroup:ro
+    tmpfs:
+      - /tmp
+      - /run
+      - /run/lock
+    override_command: False
+  # ubuntu 18.04 bionic works except that
+  #   the default redis configuration expects IPv6 which is not enabled in docker by default
+  #   the default Python environment is configured for ASCII instead of UTF-8
+  # ubuntu 16.04 xenial only has Python 3.5 which is EOL and breaks multiple dependencies
+  - name: debian_buster
+    image: jrei/systemd-debian:10
+    privileged: true
+    volumes:
+      - /sys/fs/cgroup:/sys/fs/cgroup:ro
+    tmpfs:
+      - /tmp
+      - /run
+      - /run/lock
+    override_command: False
+  # debian 9 stretch only has Python 3.5 which is EOL and breaks multiple dependencies
+provisioner:
+  name: ansible
+verifier:
+  name: ansible

ansible/molecule/update/prepare.yml

@@ -0,0 +1,10 @@
+- name: install previous release
+  hosts: all
+  tasks:
+    - name: set previous version as installation target
+      set_fact:
+        paperlessng_version: 0.9.13
+
+    - name: install previous paperless-ng release
+      include_role:
+        name: ansible

ansible/molecule/update/verify.yml

@@ -0,0 +1,60 @@
+---
+- name: Verify
+  hosts: all
+  gather_facts: false
+
+  vars_files:
+    - ../../defaults/main.yml
+
+  tasks:
+    - name: check if webserver is up
+      uri:
+        url: http://localhost:8000
+        status_code: [200, 302]
+        return_content: yes
+      register: landingpage
+      failed_when: "'Sign in</button>' not in landingpage.content"
+
+    - name: check if document posting works
+      uri:
+        url: http://localhost:8000/api/documents/post_document/
+        method: POST
+        body_format: form-multipart
+        body:
+          document:
+            content: FOO
+            filename: document.txt
+            mime_type: text/plain
+        headers:
+          Authorization: 'Basic {{ (paperlessng_superuser_name + ":" + paperlessng_superuser_password) | b64encode }}'
+        return_content: yes
+      register: post_document
+      failed_when: "'OK' not in post_document.content"
+
+    - name: verify uploaded document has been accepted
+      uri:
+        url: http://localhost:8000/api/logs/
+        headers:
+          Authorization: 'Basic {{ (paperlessng_superuser_name + ":" + paperlessng_superuser_password) | b64encode }}'
+        return_content: yes
+      register: logs
+      failed_when: "'Consuming document.txt' not in logs.content"
+
+    # assumes txt consumption finished by now, might have to sleep a bit
+    - name: verify uploaded document has been consumed
+      uri:
+        url: http://localhost:8000/api/logs/
+        headers:
+          Authorization: 'Basic {{ (paperlessng_superuser_name + ":" + paperlessng_superuser_password) | b64encode }}'
+        return_content: yes
+      register: logs
+      failed_when: "'document consumption finished' not in logs.content"
+
+    - name: verify uploaded document is avaiable
+      uri:
+        url: http://localhost:8000/api/documents/1/
+        headers:
+          Authorization: 'Basic {{ (paperlessng_superuser_name + ":" + paperlessng_superuser_password) | b64encode }}'
+        return_content: yes
+      register: document
+      failed_when: "'Not found.' in document.content or 'FOO' not in document.content"

ansible/tasks/main.yml

@@ -0,0 +1,454 @@
+---
+- name: verify operating system
+  fail:
+    msg: Sorry, only Debian and Ubuntu supported at the moment.
+  when: not(ansible_distribution == 'Debian' or ansible_distribution == 'Ubuntu')
+
+- name: install base dependencies
+  apt:
+    update_cache: yes
+    pkg:
+      # paperless-ng
+      - python3-pip
+      - python3-dev
+      - fonts-liberation
+      - imagemagick
+      - optipng
+      - gnupg
+      - libpoppler-cpp-dev
+      - libpq-dev
+      - libmagic-dev
+      - mime-support
+      # OCRmyPDF
+      - unpaper
+      - ghostscript
+      - icc-profiles-free
+      - qpdf
+      - liblept5
+      - libxml2
+      - pngquant
+      - zlib1g
+      - tesseract-ocr
+      # dev
+      - sudo
+      - build-essential
+      - python3-setuptools
+      - python3-wheel
+      - python3-virtualenv
+
+- name: install ocr languages
+  apt:
+    pkg: "{{ paperlessng_ocr_languages | map('regex_replace', '^(.*)$', 'tesseract-ocr-\\1') | list }}"
+
+- name: set up notesalexp repository key (for jbig2enc)
+  apt_key:
+    url: https://notesalexp.org/debian/alexp_key.asc
+    state: present
+  when: paperlessng_use_jbig2enc
+
+- name: set up notesalexp repository (for jbig2enc)
+  apt_repository:
+    repo: "deb https://notesalexp.org/debian/{{ ansible_distribution_release }}/ {{ ansible_distribution_release }} main"
+    state: present
+  when: paperlessng_use_jbig2enc
+
+- name: set up notesalexp repository pinning
+  copy:
+    content: |
+      Package: *
+      Pin: release o=notesalexp.org
+      Pin-Priority: 1
+
+      Package: jbig2enc
+      Pin: release o=notesalexp.org
+      Pin-Priority: 500
+    dest: /etc/apt/preferences.d/notesalexp
+  when: paperlessng_use_jbig2enc
+
+- name: install jbig2enc
+  apt:
+    pkg: jbig2enc
+    update_cache: yes
+  when: paperlessng_use_jbig2enc
+
+- name: install redis
+  apt:
+    pkg: redis-server
+  when: paperlessng_redis_host == 'localhost' or paperlessng_redis_host == '127.0.0.1'
+
+- name: enable redis
+  systemd:
+    name: redis-server
+    enabled: yes
+    masked: no
+    state: started
+  when: paperlessng_redis_host == 'localhost' or paperlessng_redis_host == '127.0.0.1'
+
+- name: create paperless system group
+  group:
+    name: "{{ paperlessng_system_group }}"
+
+- name: create paperless system user
+  user:
+    name: "{{ paperlessng_system_user }}"
+    groups:
+      - "{{ paperlessng_system_group }}"
+    shell: /usr/sbin/nologin
+    # GNUPG_HOME required due to paperless db.py
+    create_home: yes
+
+- name: check for paperless-ng installation
+  command:
+    cmd: 'grep -Po "(?<=Paperless-ng )\d+\.\d+\.\d+" {{ paperlessng_directory }}/docs/changelog.html'
+  changed_when: '"No such file or directory" in paperlessng_current_version.stderr or paperlessng_current_version.stdout != paperlessng_version | string'
+  failed_when: false
+  ignore_errors: yes
+  register: paperlessng_current_version
+
+- name: register current state
+  set_fact:
+    fresh_installation: '{{ "No such file or directory" in paperlessng_current_version.stderr }}'
+    update_installation: '{{ "No such file or directory" not in paperlessng_current_version.stderr and paperlessng_current_version.stdout != paperlessng_version | string }}'
+    reconfigure_only: '{{ paperlessng_current_version.stdout == paperlessng_version | string }}'
+
+- name: backup current paperless-ng installation
+  copy:
+    src: "{{ paperlessng_directory }}"
+    remote_src: yes
+    dest: "{{ paperlessng_directory }}-{{ ansible_date_time.iso8601 }}/"
+  when: update_installation
+
+- name: remove current paperless sources
+  file:
+    path: "{{ paperlessng_directory }}/{{ item }}"
+    state: absent
+  with_items:
+    - docker
+    - docs
+    - scripts
+    - src
+    - static
+  when: update_installation
+
+- name: create temporary directory
+  tempfile:
+    state: directory
+  register: tempdir
+  when: not reconfigure_only
+
+- name: extract paperless-ng
+  unarchive:
+    src: "https://github.com/jonaswinkler/paperless-ng/releases/download/ng-{{ paperlessng_version }}/paperless-ng-{{ paperlessng_version }}.tar.xz"
+    remote_src: yes
+    dest: "{{ tempdir.path }}"
+  when: not reconfigure_only
+
+- name: change owner and permissions of paperless-ng
+  command:
+    cmd: "{{ item }}"
+    warn: false
+  with_items:
+    - "chown -R {{ paperlessng_system_user }}:{{ paperlessng_system_group }} {{ tempdir.path }}"
+    - "find {{ tempdir.path }} -type d -exec chmod 0750 {} ;"
+    - "find {{ tempdir.path }} -type f -exec chmod 0640 {} ;"
+  when: not reconfigure_only
+
+- name: move paperless-ng
+  command:
+    cmd: "cp -a {{ tempdir.path }}/paperless-ng/. {{ paperlessng_directory }}"
+  when: not reconfigure_only
+
+- name: remove temporary directory
+  file:
+    path: "{{ tempdir.path }}"
+    state: absent
+  when: not reconfigure_only
+
+- name: create paperless-ng directories and set permissions
+  file:
+    path: "{{ item }}"
+    state: directory
+    owner: "{{ paperlessng_system_user }}"
+    group: "{{ paperlessng_system_group }}"
+    mode: "750"
+  with_items:
+    - "{{ paperlessng_directory }}"
+    - "{{ paperlessng_consumption_dir }}"
+    - "{{ paperlessng_data_dir }}"
+    - "{{ paperlessng_media_root }}"
+    - "{{ paperlessng_static_dir }}"
+
+- name: rename initial config
+  command:
+    cmd: "mv {{ paperlessng_directory }}/paperless.conf {{ paperlessng_directory }}/paperless.conf.template"
+    removes: "{{ paperlessng_directory }}/paperless.conf"
+
+- name: configure paperless-ng
+  lineinfile:
+    path: "{{ paperlessng_directory }}/paperless.conf.template"
+    regexp: "^#?{{ item.regexp }}="
+    line: "{{ item.line }}"
+  with_items:
+    # Required services
+    - regexp: PAPERLESS_REDIS
+      line: "PAPERLESS_REDIS=redis://{{ paperlessng_redis_host }}:{{ paperlessng_redis_port }}"
+    # Paths and folders
+    - regexp: PAPERLESS_CONSUMPTION_DIR
+      line: "PAPERLESS_CONSUMPTION_DIR={{ paperlessng_consumption_dir }}"
+    - regexp: PAPERLESS_DATA_DIR
+      line: "PAPERLESS_DATA_DIR={{ paperlessng_data_dir }}"
+    - regexp: PAPERLESS_MEDIA_ROOT
+      line: "PAPERLESS_MEDIA_ROOT={{ paperlessng_media_root }}"
+    - regexp: PAPERLESS_STATICDIR
+      line: "PAPERLESS_STATICDIR={{ paperlessng_static_dir }}"
+    - regexp: PAPERLESS_FILENAME_FORMAT
+      line: "PAPERLESS_FILENAME_FORMAT={{ paperlessng_filename_format }}"
+    # Hosting & Security
+    - regexp: PAPERLESS_SECRET_KEY
+      line: "PAPERLESS_SECRET_KEY={{ paperless_secret_key }}"
+    - regexp: PAPERLESS_ALLOWED_HOSTS
+      line: "PAPERLESS_ALLOWED_HOSTS={{ paperless_allowed_hosts }}"
+    - regexp: PAPERLESS_CORS_ALLOWED_HOSTS
+      line: "PAPERLESS_CORS_ALLOWED_HOSTS={{ paperless_cors_allowed_hosts }}"
+    - regexp: PAPERLESS_FORCE_SCRIPT_NAME
+      line: "PAPERLESS_FORCE_SCRIPT_NAME={{ paperless_force_script_name }}"
+    - regexp: PAPERLESS_STATIC_URL
+      line: "PAPERLESS_STATIC_URL={{ paperless_static_url }}"
+    - regexp: PAPERLESS_AUTO_LOGIN_USERNAME
+      line: "PAPERLESS_AUTO_LOGIN_USERNAME={{ paperless_auto_login_username }}"
+    - regexp: PAPERLESS_COOKIE_PREFIX
+      line: "PAPERLESS_COOKIE_PREFIX={{ paperless_cookie_prefix }}"
+    - regexp: PAPERLESS_ENABLE_HTTP_REMOTE_USER
+      line: "PAPERLESS_ENABLE_HTTP_REMOTE_USER={{ paperless_enable_http_remote_user }}"
+    # OCR settings
+    - regexp: PAPERLESS_OCR_LANGUAGE
+      line: "PAPERLESS_OCR_LANGUAGE={{ paperlessng_ocr_languages | join('+') }}"
+    - regexp: PAPERLESS_OCR_MODE
+      line: "PAPERLESS_OCR_MODE={{ paperlessng_ocr_mode }}"
+    - regexp: PAPERLESS_OCR_OUTPUT_TYPE
+      line: "PAPERLESS_OCR_OUTPUT_TYPE={{ paperlessng_ocr_output_type }}"
+    - regexp: PAPERLESS_OCR_PAGES
+      line: "PAPERLESS_OCR_PAGES={{ paperlessng_ocr_pages }}"
+    - regexp: PAPERLESS_OCR_IMAGE_DPI
+      line: "PAPERLESS_OCR_IMAGE_DPI={{ paperlessng_ocr_image_dpi }}"
+    - regexp: PAPERLESS_OCR_USER_ARGS
+      line: "PAPERLESS_OCR_USER_ARGS={{ paperlessng_ocr_user_args | combine({'jbig2_lossy': true} if paperlessng_big2enc_lossy else {}) | to_json }}"
+    # Tika settings
+    - regexp: PAPERLESS_TIKA_ENABLED
+      line: "PAPERLESS_TIKA_ENABLED={{ paperlessng_tika_enabled }}"
+    - regexp: PAPERLESS_TIKA_ENDPOINT
+      line: "PAPERLESS_TIKA_ENDPOINT={{ paperlessng_tika_endpoint }}"
+    - regexp: PAPERLESS_TIKA_GOTENBERG_ENDPOINT
+      line: "PAPERLESS_TIKA_GOTENBERG_ENDPOINT={{ paperlessng_tika_endpoint }}"
+    # Software tweaks
+    - regexp: PAPERLESS_TIME_ZONE
+      line: "PAPERLESS_TIME_ZONE={{ paperlessng_time_zone }}"
+    - regexp: PAPERLESS_CONSUMER_POLLING
+      line: "PAPERLESS_CONSUMER_POLLING={{ paperlessng_consumer_polling }}"
+    - regexp: PAPERLESS_CONSUMER_DELETE_DUPLICATES
+      line: "PAPERLESS_CONSUMER_DELETE_DUPLICATES={{ paperlessng_consumer_delete_duplicates }}"
+    - regexp: PAPERLESS_CONSUMER_RECURSIVE
+      line: "PAPERLESS_CONSUMER_RECURSIVE={{ paperlessng_consumer_recursive }}"
+    - regexp: PAPERLESS_CONSUMER_SUBDIRS_AS_TAGS
+      line: "PAPERLESS_CONSUMER_SUBDIRS_AS_TAGS={{ paperlessng_consumer_subdirs_as_tags }}"
+    - regexp: PAPERLESS_OPTIMIZE_THUMBNAILS
+      line: "PAPERLESS_OPTIMIZE_THUMBNAILS={{ paperlessng_optimize_thumbnails }}"
+    - regexp: PAPERLESS_POST_CONSUME_SCRIPT
+      line: "PAPERLESS_POST_CONSUME_SCRIPT={{ paperlessng_post_consume_script }}"
+    - regexp: PAPERLESS_FILENAME_DATE_ORDER
+      line: "PAPERLESS_FILENAME_DATE_ORDER={{ paperlessng_filename_date_order }}"
+    - regexp: PAPERLESS_THUMBNAIL_FONT_NAME
+      line: "PAPERLESS_THUMBNAIL_FONT_NAME={{ paperlessng_thumbnail_font_name }}"
+    - regexp: PAPERLESS_IGNORE_DATES
+      line: "PAPERLESS_IGNORE_DATES={{ paperlessng_ignore_dates }}"
+  no_log: yes
+
+- name: configure paperless-ng database [sqlite]
+  lineinfile:
+    path: "{{ paperlessng_directory }}/paperless.conf.template"
+    regexp: "^#?PAPERLESS_DBHOST=(.*)$"
+    line: '#PAPERLESS_DBHOST=\1'
+    backrefs: yes
+  when: paperlessng_db_type == 'sqlite'
+
+- name: configure paperless-ng database [postgresql]
+  lineinfile:
+    path: "{{ paperlessng_directory }}/paperless.conf.template"
+    regexp: "^#?{{ item.regexp }}="
+    line: "{{ item.line }}"
+  with_items:
+    - regexp: PAPERLESS_DBHOST
+      line: "PAPERLESS_DBHOST={{ paperlessng_db_host }}"
+    - regexp: PAPERLESS_DBPORT
+      line: "PAPERLESS_DBPORT={{ paperlessng_db_port }}"
+    - regexp: PAPERLESS_DBNAME
+      line: "PAPERLESS_DBNAME={{ paperlessng_db_name }}"
+    - regexp: PAPERLESS_DBUSER
+      line: "PAPERLESS_DBUSER={{ paperlessng_db_user }}"
+    - regexp: PAPERLESS_DBPASS
+      line: "PAPERLESS_DBPASS={{ paperlessng_db_pass }}"
+    - regexp: PAPERLESS_DBSSLMODE
+      line: "PAPERLESS_DBSSLMODE={{ paperlessng_db_sslmode }}"
+  when: paperlessng_db_type == 'postgresql'
+  no_log: yes
+
+- name: deploy paperless-ng configuration
+  copy:
+    src: "{{ paperlessng_directory }}/paperless.conf.template"
+    remote_src: yes
+    dest: /etc/paperless.conf
+    owner: root
+    group: root
+    mode: "0644"
+  register: configuration
+
+- name: create paperlessng venv
+  become: yes
+  become_user: "{{ paperlessng_system_user }}"
+  command:
+    cmd: "python3 -m virtualenv {{ paperlessng_virtualenv }} -p /usr/bin/python3"
+    creates: "{{ paperlessng_virtualenv }}"
+  register: venv
+
+- name: install paperlessng requirements
+  become: yes
+  become_user: "{{ paperlessng_system_user }}"
+  pip:
+    requirements: "{{ paperlessng_directory }}/requirements.txt"
+    executable: "{{ paperlessng_virtualenv }}/bin/pip3"
+    extra_args: --upgrade
+  when: not reconfigure_only
+
+- name: migrate database schema
+  become: yes
+  become_user: "{{ paperlessng_system_user }}"
+  command: "{{ paperlessng_virtualenv }}/bin/python3 {{ paperlessng_directory }}/src/manage.py migrate"
+  register: database_schema
+  changed_when: '"No migrations to apply." not in database_schema.stdout'
+  when: not reconfigure_only
+
+- name: configure paperless superuser
+  become: yes
+  become_user: "{{ paperlessng_system_user }}"
+  # "manage.py createsuperuser" only works on interactive TTYs
+  vars:
+    creation_script: |
+      from django.contrib.auth.models import User
+      from django.contrib.auth.hashers import get_hasher
+
+      if User.objects.filter(username='{{ paperlessng_superuser_name }}').exists():
+          user = User.objects.get(username='{{ paperlessng_superuser_name }}')
+          old = user.__dict__.copy()
+
+          user.is_superuser = True
+          user.email = '{{ paperlessng_superuser_email }}'
+          user.set_password('{{ paperlessng_superuser_password }}')
+          user.save()
+          new = user.__dict__
+
+          algorithm, iterations, old_salt, old_hash = old['password'].split('$')
+          new_password_old_salt = get_hasher(algorithm).encode(password='{{ paperlessng_superuser_password }}', salt=old_salt, iterations=int(iterations))
+          _, _, _, new_hash = new_password_old_salt.split('$')
+          if not (old_hash == new_hash and old['is_superuser'] == new['is_superuser'] and old['email'] == new['email']):
+              print('changed')
+      else:
+          User.objects.create_superuser('{{ paperlessng_superuser_name }}', '{{ paperlessng_superuser_email }}', '{{ paperlessng_superuser_password }}')
+          print('changed')
+  command: '{{ paperlessng_virtualenv }}/bin/python3 {{ paperlessng_directory }}/src/manage.py shell -c "{{ creation_script }}"'
+  register: superuser
+  changed_when: superuser.stdout == 'changed'
+  no_log: yes
+
+- name: set ownership and permissions on paperlessng venv
+  file:
+    path: "{{ paperlessng_virtualenv }}"
+    state: directory
+    recurse: yes
+    owner: "{{ paperlessng_system_user }}"
+    group: "{{ paperlessng_system_group }}"
+    mode: g-w,o-rwx
+  when: venv.changed or not reconfigure_only
+
+- name: configure ghostscript for PDF
+  lineinfile:
+    path: /etc/ImageMagick-6/policy.xml
+    regexp: '(\s+)<policy domain="coder" rights=".*" pattern="PDF" />'
+    line: '\1<policy domain="coder" rights="read|write" pattern="PDF" />'
+    backrefs: yes
+
+- name: configure systemd services
+  ini_file:
+    path: "{{ paperlessng_directory }}/scripts/{{ item[0] }}"
+    section: "Service"
+    option: "{{ item[1].option  }}"
+    value: "{{ item[1].value }}"
+  with_nested:
+    - [
+        paperless-consumer.service,
+        paperless-scheduler.service,
+        paperless-webserver.service,
+      ]
+    - [
+        # https://www.freedesktop.org/software/systemd/man/systemd.exec.html
+        { option: "User", value: "{{ paperlessng_system_user }}" },
+        { option: "Group", value: "{{ paperlessng_system_group }}" },
+        { option: "WorkingDirectory", value: "{{ paperlessng_directory }}/src", },
+        { option: "ProtectSystem", value: "full" },
+        { option: "NoNewPrivileges", value: "true" },
+        { option: "PrivateUsers", value: "true" },
+        { option: "PrivateDevices", value: "true" },
+      ]
+
+- name: configure paperless-consumer service
+  ini_file:
+    path: "{{ paperlessng_directory }}/scripts/paperless-consumer.service"
+    section: "Service"
+    option: "ExecStart"
+    value: "{{ paperlessng_virtualenv }}/bin/python3 manage.py document_consumer"
+
+- name: configure paperless-scheduler service
+  ini_file:
+    path: "{{ paperlessng_directory }}/scripts/paperless-scheduler.service"
+    section: "Service"
+    option: "ExecStart"
+    value: "{{ paperlessng_virtualenv }}/bin/python3 manage.py qcluster"
+
+- name: configure paperless-webserver service
+  ini_file:
+    path: "{{ paperlessng_directory }}/scripts/paperless-webserver.service"
+    section: "Service"
+    option: "ExecStart"
+    value: "{{ paperlessng_virtualenv }}/bin/gunicorn paperless.wsgi -w 2 -b {{ paperlessng_listen_address }}:{{ paperlessng_listen_port }}"
+
+- name: copy systemd services
+  copy:
+    src: "{{ paperlessng_directory }}/scripts/{{ item }}"
+    remote_src: yes
+    dest: "/etc/systemd/system/{{ item }}"
+  with_items:
+    - paperless-consumer.service
+    - paperless-scheduler.service
+    - paperless-webserver.service
+  register: paperless_services
+
+- name: reload systemd daemon
+  systemd:
+    name: "{{ item }}"
+    state: restarted
+    daemon_reload: yes
+  with_items:
+    - paperless-consumer
+    - paperless-scheduler
+    - paperless-webserver
+  when: paperless_services.changed or configuration.changed
+
+- name: enable paperlessng services
+  systemd:
+    name: "{{ item }}"
+    enabled: yes
+    masked: no
+    state: started
+  with_items:
+    - paperless-consumer
+    - paperless-scheduler
+    - paperless-webserver

compile-frontend.sh

@@ -0,0 +1,7 @@
+#!/bin/bash
+
+set -e
+
+cd src-ui
+npm install
+./node_modules/.bin/ng build --prod

crowdin.yml

@@ -0,0 +1,5 @@
+files:
+  - source: /src/locale/en-us/LC_MESSAGES/django.po
+    translation: /src/locale/%two_letters_code%/LC_MESSAGES/django.po
+  - source: /src-ui/messages.xlf
+    translation: /src-ui/src/locale/messages.%two_letters_code%.xlf

docker/compose/.env

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

docker/compose/docker-compose.env

@@ -7,7 +7,7 @@
 # Additional languages to install for text recognition, separated by a
 # whitespace. Note that this is
 # different from PAPERLESS_OCR_LANGUAGE (default=eng), which defines the
-# default language used when guessing the language from the OCR output.
+# language used for OCR.
 # The container installs English, German, Italian, Spanish and French by
 # default.
 # See https://packages.debian.org/search?keywords=tesseract-ocr-&searchon=names&suite=buster
@@ -32,8 +32,3 @@
 # The default language to use for OCR. Set this to the language most of your
 # documents are written in.
 #PAPERLESS_OCR_LANGUAGE=eng
-
-# By default Paperless does not OCR a document if the text can be retrieved from
-# the document directly. Set to true to always OCR documents. (i.e., if you
-# know that some of your documents have faulty/bad OCR data)
-#PAPERLESS_OCR_ALWAYS=true

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

@@ -0,0 +1,90 @@
+# docker-compose file for running paperless from the Docker Hub.
+# This file contains everything paperless needs to run.
+# Paperless supports amd64, arm and arm64 hardware.
+#
+# All compose files of paperless configure paperless in the following way:
+#
+# - Paperless is (re)started on system boot, if it was running before shutdown.
+# - Docker volumes for storing data are managed by Docker.
+# - Folders for importing and exporting files are created in the same directory
+#   as this file and mounted to the correct folders inside the container.
+# - Paperless listens on port 8000.
+#
+# In addition to that, this docker-compose file adds the following optional
+# configurations:
+#
+# - Instead of SQLite (default), PostgreSQL is used as the database server.
+# - 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: redis:6.0
+    restart: unless-stopped
+
+  db:
+    image: postgres:13
+    restart: unless-stopped
+    volumes:
+      - pgdata:/var/lib/postgresql/data
+    environment:
+      POSTGRES_DB: paperless
+      POSTGRES_USER: paperless
+      POSTGRES_PASSWORD: paperless
+
+  webserver:
+    image: jonaswinkler/paperless-ng: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_DBHOST: db
+      PAPERLESS_TIKA_ENABLED: 1
+      PAPERLESS_TIKA_GOTENBERG_ENDPOINT: http://gotenberg:3000
+      PAPERLESS_TIKA_ENDPOINT: http://tika:9998
+
+  gotenberg:
+    image: thecodingmachine/gotenberg
+    restart: unless-stopped
+    environment:
+      DISABLE_GOOGLE_CHROME: 1
+
+  tika:
+    image: apache/tika
+    restart: unless-stopped
+
+volumes:
+  data:
+  media:
+  pgdata:

docker/compose/docker-compose.postgres.yml

@@ -0,0 +1,72 @@
+# docker-compose file for running paperless from the Docker Hub.
+# This file contains everything paperless needs to run.
+# Paperless supports amd64, arm and arm64 hardware.
+#
+# All compose files of paperless configure paperless in the following way:
+#
+# - Paperless is (re)started on system boot, if it was running before shutdown.
+# - Docker volumes for storing data are managed by Docker.
+# - Folders for importing and exporting files are created in the same directory
+#   as this file and mounted to the correct folders inside the container.
+# - Paperless listens on port 8000.
+#
+# In addition to that, this docker-compose file adds the following optional
+# configurations:
+#
+# - Instead of SQLite (default), PostgreSQL is used as the database server.
+#
+# To install and update paperless with this file, do the following:
+#
+# - Copy this file as 'docker-compose.yml' and the files 'docker-compose.env'
+#   and '.env' into a folder.
+# - Run 'docker-compose pull'.
+# - Run 'docker-compose run --rm webserver createsuperuser' to create a user.
+# - Run 'docker-compose up -d'.
+#
+# For more extensive installation and update instructions, refer to the
+# documentation.
+
+version: "3.4"
+services:
+  broker:
+    image: redis:6.0
+    restart: unless-stopped
+
+  db:
+    image: postgres:13
+    restart: unless-stopped
+    volumes:
+      - pgdata:/var/lib/postgresql/data
+    environment:
+      POSTGRES_DB: paperless
+      POSTGRES_USER: paperless
+      POSTGRES_PASSWORD: paperless
+
+  webserver:
+    image: jonaswinkler/paperless-ng: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_DBHOST: db
+
+
+volumes:
+  data:
+  media:
+  pgdata:

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

@@ -0,0 +1,78 @@
+# docker-compose file for running paperless from the Docker Hub.
+# This file contains everything paperless needs to run.
+# Paperless supports amd64, arm and arm64 hardware.
+#
+# All compose files of paperless configure paperless in the following way:
+#
+# - Paperless is (re)started on system boot, if it was running before shutdown.
+# - Docker volumes for storing data are managed by Docker.
+# - Folders for importing and exporting files are created in the same directory
+#   as this file and mounted to the correct folders inside the container.
+# - Paperless listens on port 8000.
+#
+# SQLite is used as the database. The SQLite file is stored in the data volume.
+#
+# In addition to that, this docker-compose file adds the following optional
+# configurations:
+#
+# - Apache Tika and Gotenberg servers are started with paperless and paperless
+#   is configured to use these services. These provide support for consuming
+#   Office documents (Word, Excel, Power Point and their LibreOffice counter-
+#   parts.
+#
+# To install and update paperless with this file, do the following:
+#
+# - Copy this file as 'docker-compose.yml' and the files 'docker-compose.env'
+#   and '.env' into a folder.
+# - Run 'docker-compose pull'.
+# - Run 'docker-compose run --rm webserver createsuperuser' to create a user.
+# - Run 'docker-compose up -d'.
+#
+# For more extensive installation and update instructions, refer to the
+# documentation.
+
+version: "3.4"
+services:
+  broker:
+    image: redis:6.0
+    restart: unless-stopped
+
+  webserver:
+    image: jonaswinkler/paperless-ng:latest
+    restart: unless-stopped
+    depends_on:
+      - 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_TIKA_ENABLED: 1
+      PAPERLESS_TIKA_GOTENBERG_ENDPOINT: http://gotenberg:3000
+      PAPERLESS_TIKA_ENDPOINT: http://tika:9998
+
+  gotenberg:
+    image: thecodingmachine/gotenberg
+    restart: unless-stopped
+    environment:
+      DISABLE_GOOGLE_CHROME: 1
+
+  tika:
+    image: apache/tika
+    restart: unless-stopped
+
+volumes:
+  data:
+  media:

docker/compose/docker-compose.sqlite.yml

@@ -0,0 +1,56 @@
+# docker-compose file for running paperless from the Docker Hub.
+# This file contains everything paperless needs to run.
+# Paperless supports amd64, arm and arm64 hardware.
+#
+# All compose files of paperless configure paperless in the following way:
+#
+# - Paperless is (re)started on system boot, if it was running before shutdown.
+# - Docker volumes for storing data are managed by Docker.
+# - Folders for importing and exporting files are created in the same directory
+#   as this file and mounted to the correct folders inside the container.
+# - Paperless listens on port 8000.
+#
+# SQLite is used as the database. The SQLite file is stored in the data volume.
+#
+# To install and update paperless with this file, do the following:
+#
+# - Copy this file as 'docker-compose.yml' and the files 'docker-compose.env'
+#   and '.env' into a folder.
+# - Run 'docker-compose pull'.
+# - Run 'docker-compose run --rm webserver createsuperuser' to create a user.
+# - Run 'docker-compose up -d'.
+#
+# For more extensive installation and update instructions, refer to the
+# documentation.
+
+version: "3.4"
+services:
+  broker:
+    image: redis:6.0
+    restart: unless-stopped
+
+  webserver:
+    image: jonaswinkler/paperless-ng:latest
+    restart: unless-stopped
+    depends_on:
+      - broker
+    ports:
+      - 8000:8000
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:8000"]
+      interval: 30s
+      timeout: 10s
+      retries: 5
+    volumes:
+      - data:/usr/src/paperless/data
+      - media:/usr/src/paperless/media
+      - ./export:/usr/src/paperless/export
+      - ./consume:/usr/src/paperless/consume
+    env_file: docker-compose.env
+    environment:
+      PAPERLESS_REDIS: redis://broker:6379
+
+
+volumes:
+  data:
+  media:

docker/docker-entrypoint.sh

@@ -23,8 +23,14 @@ wait_for_postgres() {
 	echo "Waiting for PostgreSQL to start..."
 
 	host="${PAPERLESS_DBHOST}"
+	port="${PAPERLESS_DBPORT}"
 
-	while !</dev/tcp/$host/5432 ;
+	if [[ -z $port ]] ;
+	then
+		port="5432"
+	fi
+
+	while !</dev/tcp/$host/$port ;
 	do
 
 		if [ $attempt_num -eq $max_attempts ]
@@ -56,6 +62,7 @@ migrations() {
 		# simultaneously. This also ensures that the db is ready when the command
 		# of the current container starts.
 		flock 200
+		echo "Apply database migrations..."
 		sudo -HEu paperless python3 manage.py migrate
 	)  200>/usr/src/paperless/data/migration_lock
 
@@ -72,13 +79,19 @@ initialize() {
 		fi
 	done
 
+	echo "creating directory /tmp/paperless"
+	mkdir -p /tmp/paperless
+
 	chown -R paperless:paperless ../
+	chown -R paperless:paperless /tmp/paperless
 
 	migrations
 
 }
 
 install_languages() {
+	echo "Installing languages..."
+
 	local langs="$1"
 	read -ra langs <<<"$langs"
 
@@ -113,16 +126,20 @@ install_languages() {
     done
 }
 
-initialize
+echo "Paperless-ng docker container starting..."
 
 # Install additional languages if specified
 if [[ ! -z "$PAPERLESS_OCR_LANGUAGES"  ]]; then
 		install_languages "$PAPERLESS_OCR_LANGUAGES"
 fi
 
+initialize
+
 if [[ "$1" != "/"* ]]; then
+	echo Executing management command "$@"
 	exec sudo -HEu paperless python3 manage.py "$@"
 else
+	echo Executing "$@"
 	exec "$@"
 fi
 

docker/gunicorn.conf.py

@@ -1,4 +1,4 @@
-bind = '127.0.0.1:8000'
+bind = '0.0.0.0:8000'
 backlog = 2048
 workers = 3
 worker_class = 'sync'

docker/hub/docker-compose.postgres.yml

@@ -1,44 +0,0 @@
-version: "3.4"
-services:
-  broker:
-    image: redis:6.0
-    restart: always
-
-  db:
-    image: postgres:13
-    restart: always
-    volumes:
-      - pgdata:/var/lib/postgresql/data
-    environment:
-      POSTGRES_DB: paperless
-      POSTGRES_USER: paperless
-      POSTGRES_PASSWORD: paperless
-
-  webserver:
-    image: jonaswinkler/paperless-ng:0.9.3
-    restart: always
-    depends_on:
-      - db
-      - broker
-    ports:
-      - 8000:8000
-    healthcheck:
-      test: ["CMD", "curl", "-f", "http://localhost:8000"]
-      interval: 30s
-      timeout: 10s
-      retries: 5
-    volumes:
-      - data:/usr/src/paperless/data
-      - media:/usr/src/paperless/media
-      - ./export:/usr/src/paperless/export
-      - ./consume:/usr/src/paperless/consume
-    env_file: docker-compose.env
-    environment:
-      PAPERLESS_REDIS: redis://broker:6379
-      PAPERLESS_DBHOST: db
-
-
-volumes:
-  data:
-  media:
-  pgdata:

docker/hub/docker-compose.sqlite.yml

@@ -1,31 +0,0 @@
-version: "3.4"
-services:
-  broker:
-    image: redis:6.0
-    restart: always
-
-  webserver:
-    image: jonaswinkler/paperless-ng:0.9.3
-    restart: always
-    depends_on:
-      - broker
-    ports:
-      - 8000:8000
-    healthcheck:
-      test: ["CMD", "curl", "-f", "http://localhost:8000"]
-      interval: 30s
-      timeout: 10s
-      retries: 5
-    volumes:
-      - data:/usr/src/paperless/data
-      - media:/usr/src/paperless/media
-      - ./export:/usr/src/paperless/export
-      - ./consume:/usr/src/paperless/consume
-    env_file: docker-compose.env
-    environment:
-      PAPERLESS_REDIS: redis://broker:6379
-
-
-volumes:
-  data:
-  media:

docker/local/Dockerfile

@@ -1,60 +0,0 @@
-FROM python:3.7-slim
-
-WORKDIR /usr/src/paperless/
-
-COPY requirements.txt ./
-
-#Dependencies
-RUN apt-get update \
-  && apt-get -y --no-install-recommends install \
-		build-essential \
-		curl \
-		ghostscript \
-		gnupg \
-		imagemagick \
-		libatlas-base-dev \
-		libmagic-dev \
-		libpoppler-cpp-dev \
-		libpq-dev \
-		optipng \
-		sudo \
-		tesseract-ocr \
-		tesseract-ocr-eng \
-		tesseract-ocr-deu \
-		tesseract-ocr-fra \
-		tesseract-ocr-ita \
-		tesseract-ocr-spa \
-		tzdata \
-		unpaper \
-	&& pip3 install --upgrade supervisor setuptools \
-	&& pip install --no-cache-dir -r requirements.txt \
-	&& apt-get -y purge build-essential \
-	&& apt-get -y autoremove --purge \
-	&& rm -rf /var/lib/apt/lists/* \
-	&& mkdir /var/log/supervisord /var/run/supervisord
-
-# copy scripts
-# this fixes issues with imagemagick and PDF
-COPY docker/imagemagick-policy.xml /etc/ImageMagick-6/policy.xml
-COPY docker/gunicorn.conf.py ./
-COPY docker/supervisord.conf /etc/supervisord.conf
-COPY docker/docker-entrypoint.sh /sbin/docker-entrypoint.sh
-
-# copy app
-COPY src/ ./src/
-
-# add users, setup scripts
-RUN addgroup --gid 1000 paperless \
-	&& useradd --uid 1000 --gid paperless --home-dir /usr/src/paperless paperless \
-	&& chown -R paperless:paperless . \
-	&& chmod 755 /sbin/docker-entrypoint.sh
-
-WORKDIR /usr/src/paperless/src/
-
-RUN sudo -HEu paperless python3 manage.py collectstatic --clear --no-input
-
-VOLUME ["/usr/src/paperless/data", "/usr/src/paperless/media", "/usr/src/paperless/consume", "/usr/src/paperless/export"]
-ENTRYPOINT ["/sbin/docker-entrypoint.sh"]
-CMD ["/usr/local/bin/supervisord", "-c", "/etc/supervisord.conf"]
-
-LABEL maintainer="Jonas Winkler <dev@jpwinkler.de>"

docker/local/docker-compose.postgres.yml

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

docker/local/docker-compose.sqlite.yml

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

docker/supervisord.conf

@@ -8,7 +8,7 @@ loglevel=info                ; log level; default info; others: debug,warn,trace
 user=root
 
 [program:gunicorn]
-command=gunicorn -c /usr/src/paperless/gunicorn.conf.py -b 0.0.0.0:8000 paperless.wsgi
+command=gunicorn -c /usr/src/paperless/gunicorn.conf.py paperless.wsgi
 user=paperless
 
 stdout_logfile=/dev/stdout

docs/administration.rst

@@ -20,6 +20,8 @@ Options available to any installation of paperless:
     metadata to a specific folder. You may import your documents into a
     fresh instance of paperless again or store your documents in another
     DMS with this export.
+*   The document exporter is also able to update an already existing export.
+    Therefore, incremental backups with ``rsync`` are entirely possible.
 
 Options available to docker installations:
 
@@ -48,16 +50,16 @@ Options available to bare-metal and non-docker installations:
 Restoring
 =========
 
-
-
-
 .. _administration-updating:
 
-Updating paperless
+Updating Paperless
 ##################
 
+Docker Route
+============
+
 If a new release of paperless-ng is available, upgrading depends on how you
-installed paperless-ng in the first place. The releases are available at
+installed paperless-ng in the first place. The releases are available at the
 `release page <https://github.com/jonaswinkler/paperless-ng/releases>`_.
 
 First of all, ensure that paperless is stopped.
@@ -69,58 +71,57 @@ First of all, ensure that paperless is stopped.
 
 After that, :ref:`make a backup <administration-backup>`.
 
-A.  If you used the dockerfiles archive, simply download the files of the new release,
-    adjust the settings in the files (i.e., the path to your consumption directory),
-    and replace your existing docker-compose files. Then start paperless as usual,
-    which will pull the new image, and update your database, if necessary:
+A.  If you pull the image from the docker hub, all you need to do is:
 
     .. code:: shell-session
 
-        $ cd /path/to/paperless
+        $ docker-compose pull
         $ docker-compose up
 
-    If you see everything working, you can start paperless-ng with "-d" to have it
-    run in the background.
+    The docker-compose files refer to the ``latest`` version, which is always the latest
+    stable release.
 
-    .. hint::
-
-        The released docker-compose files specify exact versions to be pulled from the hub.
-        This is to ensure that if the docker-compose files should change at some point
-        (i.e., services updates/configured differently), you wont run into trouble due to
-        docker pulling the ``latest`` image and running it in an older environment.
-        
-B.  If you built the image yourself, grab the new archive and replace your current
-    paperless folder with the new contents.
-
-    After that, make the necessary adjustments to the docker-compose.yml (i.e.,
-    adjust your consumption directory).
-
-    Build and start the new image with:
+B.  If you built the image yourself, do the following:
 
     .. code:: shell-session
 
-        $ cd /path/to/paperless
+        $ git pull
+        $ ./compile-frontend.sh
         $ docker-compose build
         $ docker-compose up
 
-    If you see everything working, you can start paperless-ng with "-d" to have it
-    run in the background.
+Running ``docker-compose up`` will also apply any new database migrations.
+If you see everything working, press CTRL+C once to gracefully stop paperless.
+Then you can start paperless-ng with ``-d`` to have it run in the background.
 
-.. hint::
+    .. note::
 
-    You can usually keep your ``docker-compose.env`` file, since this file will
-    never include mandatory configuration options. However, it is worth checking
-    out the new version of this file, since it might have new recommendations
-    on what to configure.
+        In version 0.9.14, the update process was changed. In 0.9.13 and earlier, the
+        docker-compose files specified exact versions and pull won't automatically
+        update to newer versions. In order to enable updates as described above, either
+        get the new ``docker-compose.yml`` file from `here <https://github.com/jonaswinkler/paperless-ng/tree/master/docker/compose>`_
+        or edit the ``docker-compose.yml`` file, find the line that says
+        
+            .. code::
 
+                image: jonaswinkler/paperless-ng:0.9.x
+        
+        and replace the version with ``latest``:
 
-Updating paperless without docker
-=================================
+            .. code::
+
+                image: jonaswinkler/paperless-ng:latest
+        
+Bare Metal Route
+================
 
 After grabbing the new release and unpacking the contents, do the following:
 
-1.  Update python requirements. Paperless uses
-    `Pipenv`_ for managing dependencies:
+1.  Update dependencies. New paperless version may require additional
+    dependencies. The dependencies required are listed in the section about
+    :ref:`bare metal installations <setup-bare_metal>`.
+
+2.  Update python requirements. If you use Pipenv, this is done with the following steps.
 
     .. code:: shell-session
 
@@ -132,13 +133,9 @@ After grabbing the new release and unpacking the contents, do the following:
     This creates a new virtual environment (or uses your existing environment)
     and installs all dependencies into it.
 
-2.  Collect static files.
+    You can also use the included ``requirements.txt`` file instead and create the virtual
+    environment yourself. This file includes exactly the same dependencies.
 
-    .. code:: shell-session
-
-        $ cd src
-        $ pipenv run python3 manage.py collectstatic --clear
-    
 3.  Migrate the database.
 
     .. code:: shell-session
@@ -146,21 +143,56 @@ After grabbing the new release and unpacking the contents, do the following:
         $ cd src
         $ pipenv run python3 manage.py migrate
 
-        
+    This might not actually do anything. Not every new paperless version comes with new
+    database migrations.
+
+Ansible Route
+=============
+
+Most of the update process is automated when using the ansible role.
+
+1.  Backup your defined role variables file outside the paperless source-tree:
+
+    .. code:: shell-session
+
+        $ cp ansible/vars.yml ~/vars.yml.old
+
+2.  Pull the release tag you want to update to:
+
+    .. code:: shell-session
+
+        $ git fetch --all
+        $ git checkout ng-0.9.14
+
+3.  Update the role variable definitions ``ansible/vars.yml`` (where appropriate).
+
+4.  Run the ansible playbook you created created during :ref:`installation <setup-ansible>` again:
+
+    .. note::
+
+        When ansible detects that an update run is in progress, it backs up the entire ``paperlessng_directory`` to ``paperlessng_directory-TIMESTAMP``.
+        Updates can be rolled back by simply moving the timestamped folder back to the original location.
+        If the update succeeds and you want to continue using the new release, please don't forget to delete the backup folder.
+
+    .. code:: shell-session
+
+        $ ansible-playbook playbook.yml
+
+
 Management utilities
 ####################
 
 Paperless comes with some management commands that perform various maintenance
 tasks on your paperless instance. You can invoke these commands either by
 
-.. code:: bash
+.. code:: shell-session
 
     $ cd /path/to/paperless
     $ docker-compose run --rm webserver <command> <arguments>
 
 or
 
-.. code:: bash
+.. code:: shell-session
 
     $ cd /path/to/paperless/src
     $ pipenv run python manage.py <command> <arguments>
@@ -180,8 +212,13 @@ backup or migration to another DMS.
 
 .. code::
 
-    document_exporter target
+    document_exporter target [-c] [-f] [-d]
 
+    optional arguments:
+    -c, --compare-checksums
+    -f, --use-filename-format
+    -d, --delete
+    
 ``target`` is a folder to which the data gets written. This includes documents,
 thumbnails and a ``manifest.json`` file. The manifest contains all metadata from
 the database (correspondents, tags, etc).
@@ -190,6 +227,24 @@ When you use the provided docker compose script, specify ``../export`` as the
 target. This path inside the container is automatically mounted on your host on
 the folder ``export``.
 
+If the target directory already exists and contains files, paperless will assume
+that the contents of the export directory are a previous export and will attempt
+to update the previous export. Paperless will only export changed and added files.
+Paperless determines whether a file has changed by inspecting the file attributes
+"date/time modified" and "size". If that does not work out for you, specify
+``--compare-checksums`` and paperless will attempt to compare file checksums instead.
+This is slower.
+
+Paperless will not remove any existing files in the export directory. If you want
+paperless to also remove files that do not belong to the current export such as files
+from deleted documents, specify ``--delete``. Be careful when pointing paperless to
+a directory that already contains other files.
+
+The filenames generated by this command follow the format
+``[date created] [correspondent] [title].[extension]``.
+If you want paperless to use ``PAPERLESS_FILENAME_FORMAT`` for exported filenames
+instead, specify ``--use-filename-format``.
+
 
 .. _utilities-importer:
 
@@ -274,6 +329,7 @@ management command:
 
 This command takes no arguments.
 
+.. _`administration-index`:
 
 Managing the document search index
 ==================================
@@ -332,6 +388,42 @@ command:
 
 The command takes no arguments and processes all your mail accounts and rules.
 
+.. _utilities-archiver:
+
+Creating archived documents
+===========================
+
+Paperless stores archived PDF/A documents alongside your original documents.
+These archived documents will also contain selectable text for image-only
+originals.
+These documents are derived from the originals, which are always stored
+unmodified. If coming from an earlier version of paperless, your documents
+won't have archived versions.
+
+This command creates PDF/A documents for your documents.
+
+.. code::
+
+    document_archiver --overwrite --document <id>
+
+This command will only attempt to create archived documents when no archived
+document exists yet, unless ``--overwrite`` is specified. If ``--document <id>``
+is specified, the archiver will only process that document.
+
+.. note::
+
+    This command essentially performs OCR on all your documents again,
+    according to your settings. If you run this with ``PAPERLESS_OCR_MODE=redo``,
+    it will potentially run for a very long time. You can cancel the command
+    at any time, since this command will skip already archived versions the next time
+    it is run.
+
+.. note::
+
+    Some documents will cause errors and cannot be converted into PDF/A documents,
+    such as encrypted PDF documents. The archiver will skip over these documents
+    each time it sees them.
+
 .. _utilities-encyption:
 
 Managing encryption
@@ -347,7 +439,7 @@ Documents can be stored in Paperless using GnuPG encryption.
     Furthermore, the entire text content of the documents is stored plain in the
     database, even if your documents are encrypted. Filenames are not encrypted as
     well.
-    
+
     Also, the web server provides transparent access to your encrypted documents.
 
     Consider running paperless on an encrypted filesystem instead, which will then
@@ -372,4 +464,4 @@ Basic usage to disable encryption of your document store:
     decrypt_documents [--passphrase SECR3TP4SSPHRA$E]
 
 
-.. _Pipenv: https://pipenv.pypa.io/en/latest/
+.. _Pipenv: https://pipenv.pypa.io/en/latest/

docs/advanced_usage.rst

@@ -5,85 +5,6 @@ Advanced topics
 Paperless offers a couple features that automate certain tasks and make your life
 easier.
 
-Guesswork
-#########
-
-
-Any document you put into the consumption directory will be consumed, but if
-you name the file right, it'll automatically set some values in the database
-for you.  This is is the logic the consumer follows:
-
-1. Try to find the correspondent, title, and tags in the file name following
-   the pattern: ``Date - Correspondent - Title - tag,tag,tag.pdf``.  Note that
-   the format of the date is **rigidly defined** as ``YYYYMMDDHHMMSSZ`` or
-   ``YYYYMMDDZ``.  The ``Z`` refers "Zulu time" AKA "UTC".
-   The tags are optional, so the format ``Date - Correspondent - Title.pdf``
-   works as well.
-2. If that doesn't work, we skip the date and try this pattern:
-   ``Correspondent - Title - tag,tag,tag.pdf``.
-3. If that doesn't work, we try to find the correspondent and title in the file
-   name following the pattern: ``Correspondent - Title.pdf``.
-4. If that doesn't work, just assume that the name of the file is the title.
-
-So given the above, the following examples would work as you'd expect:
-
-* ``20150314000700Z - Some Company Name - Invoice 2016-01-01 - money,invoices.pdf``
-* ``20150314Z - Some Company Name - Invoice 2016-01-01 - money,invoices.pdf``
-* ``Some Company Name - Invoice 2016-01-01 - money,invoices.pdf``
-* ``Another Company - Letter of Reference.jpg``
-* ``Dad's Recipe for Pancakes.png``
-
-These however wouldn't work:
-
-* ``2015-03-14 00:07:00 UTC - Some Company Name, Invoice 2016-01-01, money, invoices.pdf``
-* ``2015-03-14 - Some Company Name, Invoice 2016-01-01, money, invoices.pdf``
-* ``Some Company Name, Invoice 2016-01-01, money, invoices.pdf``
-* ``Another Company- Letter of Reference.jpg``
-
-Do I have to be so strict about naming?
-=======================================
-
-Rather than using the strict document naming rules, one can also set the option
-``PAPERLESS_FILENAME_DATE_ORDER`` in ``paperless.conf`` to any date order
-that is accepted by dateparser_. Doing so will cause ``paperless`` to default
-to any date format that is found in the title, instead of a date pulled from
-the document's text, without requiring the strict formatting of the document
-filename as described above.
-
-.. _dateparser: https://github.com/scrapinghub/dateparser/blob/v0.7.0/docs/usage.rst#settings
-
-.. _advanced-transforming_filenames:
-
-Transforming filenames for parsing
-==================================
-
-Some devices can't produce filenames that can be parsed by the default
-parser. By configuring the option ``PAPERLESS_FILENAME_PARSE_TRANSFORMS`` in
-``paperless.conf`` one can add transformations that are applied to the filename
-before it's parsed.
-
-The option contains a list of dictionaries of regular expressions (key:
-``pattern``) and replacements (key: ``repl``) in JSON format, which are
-applied in order by passing them to ``re.subn``. Transformation stops
-after the first match, so at most one transformation is applied. The general
-syntax is
-
-.. code:: python
-
-   [{"pattern":"pattern1", "repl":"repl1"}, {"pattern":"pattern2", "repl":"repl2"}, ..., {"pattern":"patternN", "repl":"replN"}]
-
-The example below is for a Brother ADS-2400N, a scanner that allows
-different names to different hardware buttons (useful for handling
-multiple entities in one instance), but insists on adding ``_<count>``
-to the filename.
-
-.. code:: python
-
-   # Brother profile configuration, support "Name_Date_Count" (the default
-   # setting) and "Name_Count" (use "Name" as tag and "Count" as title).
-   PAPERLESS_FILENAME_PARSE_TRANSFORMS=[{"pattern":"^([a-z]+)_(\\d{8})_(\\d{6})_([0-9]+)\\.", "repl":"\\2\\3Z - \\4 - \\1."}, {"pattern":"^([a-z]+)_([0-9]+)\\.", "repl":" - \\2 - \\1."}]
-
-
 .. _advanced-matching:
 
 Matching tags, correspondents and document types
@@ -263,10 +184,10 @@ 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`` settings variable.
+``PAPERLESS_FILENAME_FORMAT`` configuration option.
 
-This variable allows you to configure the filename (folders are allowed!) using
-placeholders. For example, setting
+This variable allows you to configure the filename (folders are allowed) using
+placeholders. For example, configuring this to
 
 .. code:: bash
 
@@ -277,17 +198,16 @@ will create a directory structure as follows:
 .. code::
 
     2019/
-      my_bank/
-        statement-january-0000001.pdf
-        statement-february-0000002.pdf
+      My bank/
+        Statement January.pdf
+        Statement February.pdf
     2020/
-      my_bank/
-        statement-january-0000003.pdf
-      shoe_store/
-        my_new_shoes-0000004.pdf
-
-Paperless appends the unique identifier of each document to the filename. This
-avoids filename clashes.
+      My bank/
+        Statement January.pdf
+        Letter.pdf
+        Letter_01.pdf
+      Shoe store/
+        My new shoes.pdf
 
 .. danger::
 
@@ -298,6 +218,8 @@ avoids filename clashes.
 Paperless provides the following placeholders withing filenames:
 
 * ``{correspondent}``: The name of the correspondent, or "none".
+* ``{document_type}``: The name of the document type, or "none".
+* ``{tag_list}``: A comma separated list of all tags assigned to the document.
 * ``{title}``: The title of the document.
 * ``{created}``: The full date and time the document was created.
 * ``{created_year}``: Year created only.
@@ -307,10 +229,15 @@ Paperless provides the following placeholders withing filenames:
 * ``{added_year}``: Year added only.
 * ``{added_month}``: Month added only (number 1-12).
 * ``{added_day}``: Day added only (number 1-31).
-* ``{tags}``: I don't know how this works. Look at the source.
 
-Paperless will convert all values for the placeholders into values which are safe
-for use in filenames.
+
+Paperless will try to conserve the information from your database as much as possible.
+However, some characters that you can use in document titles and correspondent names (such
+as ``: \ /`` and a couple more) are not allowed in filenames and will be replaced with dashes.
+
+If paperless detects that two documents share the same filename, paperless will automatically
+append ``_01``, ``_02``, etc to the filename. This happens if all the placeholders in a filename
+evaluate to the same value.
 
 .. hint::
 

docs/api.rst

@@ -13,23 +13,55 @@ available filters and ordering fields.
 
 The API provides 5 main endpoints:
 
+*   ``/api/documents/``: Full CRUD support, except POSTing new documents. See below.
 *   ``/api/correspondents/``: Full CRUD support.
 *   ``/api/document_types/``: Full CRUD support.
-*   ``/api/documents/``: Full CRUD support, except POSTing new documents. See below.
 *   ``/api/logs/``: Read-Only.
 *   ``/api/tags/``: Full CRUD support.
 
-All of these endpoints except for the logging endpoint 
+All of these endpoints except for the logging endpoint
 allow you to fetch, edit and delete individual objects
 by appending their primary key to the path, for example ``/api/documents/454/``.
 
+The objects served by the document endpoint contain the following fields:
+
+*   ``id``: ID of the document. Read-only.
+*   ``title``: Title of the document.
+*   ``content``: Plain text content of the document.
+*   ``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.
+*   ``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.
+*   ``original_file_name``: Verbose filename of the original document. Read-only.
+*   ``archived_file_name``: Verbose filename of the archived document. Read-only. Null if no archived document is available.
+
+
+Downloading documents
+#####################
+
 In addition to that, the document endpoint offers these additional actions on
 individual documents:
 
-*   ``/api/documents/<pk>/download/``: Download the original document.
-*   ``/api/documents/<pk>/thumb/``: Download the PNG thumbnail of a document.
-*   ``/api/documents/<pk>/preview/``: Display the original document inline,
+*   ``/api/documents/<pk>/download/``: Download the document.
+*   ``/api/documents/<pk>/preview/``: Display the document inline,
     without downloading it.
+*   ``/api/documents/<pk>/thumb/``: Download the PNG thumbnail of a document.
+
+Paperless generates archived PDF/A documents from consumed files and stores both
+the original files as well as the archived files. By default, the endpoints
+for previews and downloads serve the archived file, if it is available.
+Otherwise, the original file is served.
+Some document cannot be archived.
+
+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,
+supply the query parameter ``original=true``.
 
 .. hint::
 
@@ -38,6 +70,80 @@ individual documents:
     are in place. However, if you use these old URLs to access documents, you
     should update your app or script to use the new URLs.
 
+
+Getting document metadata
+#########################
+
+The api also has an endpoint to retrieve read-only metadata about specific documents. this
+information is not served along with the document objects, since it requires reading
+files and would therefore slow down document lists considerably.
+
+Access the metadata of a document with an ID ``id`` at ``/api/documents/<id>/metadata/``.
+
+The endpoint reports the following data:
+
+*   ``original_checksum``: MD5 checksum of the original document.
+*   ``original_size``: Size of the original document, in bytes.
+*   ``original_mime_type``: Mime type of the original document.
+*   ``media_filename``: Current filename of the document, under which it is stored inside the media directory.
+*   ``has_archive_version``: True, if this document is archived, false otherwise.
+*   ``original_metadata``: A list of metadata associated with the original document. See below.
+*   ``archive_checksum``: MD5 checksum of the archived document, or null.
+*   ``archive_size``: Size of the archived document in bytes, or null.
+*   ``archive_metadata``: Metadata associated with the archived document, or null. See below.
+
+File metadata is reported as a list of objects in the following form:
+
+.. code:: json
+
+    [
+        {
+            "namespace": "http://ns.adobe.com/pdf/1.3/",
+            "prefix": "pdf",
+            "key": "Producer",
+            "value": "SparklePDF, Fancy edition"
+        },
+    ]
+
+``namespace`` and ``prefix`` can be null. The actual metadata reported depends on the file type and the metadata
+available in that specific document. Paperless only reports PDF metadata at this point.
+
+Authorization
+#############
+
+The REST api provides three different forms of authentication.
+
+1.  Basic authentication
+
+    Authorize by providing a HTTP header in the form
+
+    .. code::
+
+        Authorization: Basic <credentials>
+
+    where ``credentials`` is a base64-encoded string of ``<username>:<password>``
+
+2.  Session authentication
+
+    When you're logged into paperless in your browser, you're automatically
+    logged into the API as well and don't need to provide any authorization
+    headers.
+
+3.  Token authentication
+
+    Paperless also offers an endpoint to acquire authentication tokens.
+
+    POST a username and password as a form or json string to ``/api/token/``
+    and paperless will respond with a token, if the login data is correct.
+    This token can be used to authenticate other requests with the
+    following HTTP header:
+
+    .. code::
+
+        Authorization: Token <token>
+
+    Tokens can be managed and revoked in the paperless admin.
+
 Searching for documents
 #######################
 
@@ -65,8 +171,9 @@ Result list object returned by the endpoint:
         "count": 1,
         "page": 1,
         "page_count": 1,
+        "corrected_query": "",
         "results": [
-            
+
         ]
     }
 
@@ -75,6 +182,8 @@ Result list object returned by the endpoint:
     the page you requested, if you requested a page that is behind
     the last page. In that case, the last page is returned.
 *   ``page_count``: The total number of pages.
+*   ``corrected_query``: Corrected version of the query string. Can be null.
+    If not null, can be used verbatim to start a new query.
 *   ``results``: A list of result objects on the current page.
 
 Result object:
@@ -84,12 +193,12 @@ Result object:
     {
         "id": 1,
         "highlights": [
-            
+
         ],
         "score": 6.34234,
         "rank": 23,
         "document": {
-            
+
         }
     }
 
@@ -112,21 +221,16 @@ Each fragment contains a list of strings, and some of them are marked as a highl
 
     [
         [
-            {"text": "This is a sample text with a "},
-            {"text": "highlighted", "term": 0},
-            {"text": " word."}
+            {"text": "This is a sample text with a ", "highlight": false},
+            {"text": "highlighted", "highlight": true},
+            {"text": " word.", "highlight": false}
         ],
         [
-            {"text": "Another", "term": 1},
-            {"text": " fragment with a highlight."}
+            {"text": "Another", "highlight": true},
+            {"text": " fragment with a highlight.", "highlight": false}
         ]
     ]
-    
 
-
-When ``term`` is present within a string, the word within ``text`` should be highlighted.
-The term index groups multiple matches together and words with the same index
-should get identical highlighting.
 A client may use this example to produce the following output:
 
 ... This is a sample text with a **highlighted** word. ... **Another** fragment with a highlight. ...
@@ -166,8 +270,17 @@ The API provides a special endpoint for file uploads:
 
 POST a multipart form to this endpoint, where the form field ``document`` contains
 the document that you want to upload to paperless. The filename is sanitized and
-then used to store the document in the consumption folder, where the consumer will
-detect the document and process it as any other document.
+then used to store the document in a temporary directory, and the consumer will
+be instructed to consume the document from there.
 
-The endpoint will immediately return "OK." if the document was stored in the
-consumption directory.
+The endpoint supports the following optional form fields:
+
+*   ``title``: Specify a title that the consumer should use for the document.
+*   ``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/changelog.rst

@@ -5,6 +5,368 @@
 Changelog
 *********
 
+paperless-ng 1.0.0
+##################
+
+Nothing special about this release, but since there are relatively few bug reports coming in, I think that this is reasonably stable.
+
+* Document export
+
+  * The document exporter has been rewritten to support updating an already existing export in place.
+    This enables incremental backups with ``rsync``.
+  * The document exporter supports naming exported files according to ``PAPERLESS_FILENAME_FORMAT``.
+  * The document exporter locks the media directory and the database during execution to ensure that
+    the resulting export is consistent.
+  * See the :ref:`updated documentation <utilities-exporter>` for more details.
+
+* Other changes and additions
+
+  * Added a language selector to the settings.
+  * Added date format options to the settings.
+  * Range selection with shift clicking is now possible in the document list.
+  * Filtering correspondent, type and tag management pages by name.
+  * Focus "Name" field in dialogs by default.
+
+
+paperless-ng 0.9.14
+###################
+
+Starting with this version, releases are getting built automatically. This release also comes with changes on how to install and
+update paperless.
+
+* Paperless now uses GitHub Actions to make releases and build docker images.
+
+  * Docker images are available for amd64, armhf, and aarch64.
+  * When you pull an image from Docker Hub, Docker will automatically select the correct image for you.
+
+* Changes to docker installations and updates
+
+  * The ``-dockerfiles.tar.xz`` release archive is gone. Instead, simply grab the docker files from ``/docker/compose`` in the repository
+    if you wish to install paperless by pulling from the hub.
+  * The docker compose files in ``/docker/compose`` were changed to always use the ``latest`` version automatically. In order to do further
+    updates, simply do a ``docker-compose pull``. The documentation has been updated.
+  * The docker compose files were changed to restart paperless on system boot only if it was running before shutdown.
+  * Documentation of the docker-compose files about what they do.
+
+* Changes to bare metal installations and updates
+
+  * The release archive is built exactly like before. However, the release now comes with already compiled translation messages and
+    collected static files. Therefore, the update steps ``compilemessages`` and ``collectstatic`` are now obsolete.
+
+* Other changes
+
+  * A new configuration option ``PAPERLESS_IGNORE_DATES`` was added by `jayme-github`_. This can be used to instruct paperless to ignore
+    certain dates (such as your date of birth) when guessing the date from the document content. This was actually introduced in 0.9.12,
+    I just forgot to mention it in the changelog.
+  * The filter drop downs now display selected entries on top of all other entries.
+  * The PostgreSQL client now supports setting an explicit ``sslmode`` to force encryption of the connection to PostgreSQL.
+  * The docker images now come with ``jbig2enc``, which is a lossless image encoder for PDF documents and decreases the size of certain
+    PDF/A documents.
+  * When using any of the manual matching algorithms, paperless now logs messages about when and why these matching algorithms matched.
+  * The default settings for parallelization in paperless were adjusted to always leave one CPU core free.
+  * Added an option to the frontend to choose which method to use for displaying PDF documents.
+
+* Fixes
+
+  * An issue with the tika parser not picking up files from the consumption directory was fixed.
+  * A couple changes to the dark mode and fixes to several other layout issues.
+  * An issue with the drop downs for correspondents, tags and types not properly supporting filtering with special characters was fixed.
+  * Fixed an issue with filenames of downloaded files: Dates where off by one day due to timezone issues.
+  * Searching will continue to work even when the index returns non-existing documents. This resulted in "Document does not exist" errors
+    before. Instead, a warning is logged, indicating the issue.
+  * An issue with the consumer crashing when invalid regular expression were used was fixed.
+
+paperless-ng 0.9.13
+###################
+
+* Fixed an issue with Paperless not starting due to the new Tika integration when ``USERMAP_UID`` and ``USERMAP_GID`` was used
+  in the ``docker-compose.env`` file.
+
+paperless-ng 0.9.12
+###################
+
+* Paperless localization
+
+  * Thanks to the combined efforts of many users, Paperless is now available in English, Dutch, French and German.
+
+* Thanks to `Jo Vandeginste`_, Paperless has optional support for Office documents such as .docx, .doc, .odt and more.
+
+  * See the :ref:`configuration<configuration-tika>` on how to enable this feature. This feature requires two additional services
+    (one for parsing Office documents and metadata extraction and another for converting Office documents to PDF), and is therefore
+    not enabled on default installations.
+  * As with all other documents, paperless converts Office documents to PDF and stores both the original as well as the archived PDF.
+
+* Dark mode
+
+  * Thanks to `Michael Shamoon`_, paperless now has a dark mode. Configuration is available in the settings.
+
+* Other changes and additions
+
+  * The PDF viewer now uses a local copy of some dependencies instead of fetching them from the internet. Thanks to `slorenz`_.
+  * Revamped search bar styling thanks to `Michael Shamoon`_.
+  * Sorting in the document list by clicking on table headers.
+  * A button was added to the document detail page that assigns a new ASN to a document.
+  * Form field validation: When providing invalid input in a form (such as a duplicate ASN or no name), paperless now has visual
+    indicators and clearer error messages about what's wrong.
+  * Paperless disables buttons with network actions (such as save and delete) when a network action is active. This indicates that
+    something is happening and prevents double clicking.
+  * When using "Save & next", the title field is focussed automatically to better support keyboard editing.
+  * E-Mail: Added filter rule parameters to allow inline attachments (watch out for mails with inlined images!) and attachment filename filters
+    with wildcards.
+  * Support for remote user authentication thanks to `Michael Shamoon`_. This is useful for hiding Paperless behind single sign on applications
+    such as `authelia <https://www.authelia.com/>`_.
+  * "Clear filters" has been renamed to "Reset filters" and now correctly restores the default filters on saved views. Thanks to `Michael Shamoon`_
+
+* Fixes
+
+  * Paperless was unable to save views when "Not assigned" was chosen in one of the filter dropdowns.
+  * Clearer error messages when pre and post consumption scripts do not exist.
+  * The post consumption script is executed later in the consumption process. Before the change, an ID was passed to the script referring to
+    a document that did not yet exist in the database.
+
+paperless-ng 0.9.11
+###################
+
+* Fixed an issue with the docker image not starting at all due to a configuration change of the web server.
+
+
+paperless-ng 0.9.10
+###################
+
+* Bulk editing
+
+  * Thanks to `Michael Shamoon`_, we've got a new interface for the bulk editor.
+  * There are some configuration options in the settings to alter the behavior.
+
+* Other changes and additions
+
+  * Thanks to `zjean`_, paperless now publishes a webmanifest, which is useful for adding the application to home screens on mobile devices.
+  * The Paperless-ng logo now navigates to the dashboard.
+  * Filter for documents that don't have any correspondents, types or tags assigned.
+  * Tags, types and correspondents are now sorted case insensitive.
+  * Lots of preparation work for localization support.
+
+* Fixes
+
+  * Added missing dependencies for Raspberry Pi builds.
+  * Fixed an issue with plain text file consumption: Thumbnail generation failed due to missing fonts.
+  * An issue with the search index reporting missing documents after bulk deletes was fixed.
+  * Issue with the tag selector not clearing input correctly.
+  * The consumer used to stop working when encountering an incomplete classifier model file.
+
+.. note::
+
+  The bulk delete operations did not update the search index. Therefore, documents that you deleted remained in the index and
+  caused the search to return messages about missing documents when searching. Further bulk operations will properly update
+  the index.
+
+  However, this change is not retroactive: If you used the delete method of the bulk editor, you need to reindex your search index
+  by :ref:`running the management command document_index with the argument reindex <administration-index>`.
+
+paperless-ng 0.9.9
+##################
+
+Christmas release!
+
+* Bulk editing
+
+  * Paperless now supports bulk editing.
+  * The following operations are available: Add and remove correspondents, tags, document types from selected documents, as well as mass-deleting documents.
+  * We've got a more fancy UI in the works that makes these features more accessible, but that's not quite ready yet.
+
+* Searching
+
+  * Paperless now supports searching for similar documents ("More like this") both from the document detail page as well as from individual search results.
+  * A search score indicates how well a document matches the search query, or how similar a document is to a given reference document.
+
+* Other additions and changes
+
+  * Clarification in the UI that the fields "Match" and "Is insensitive" are not relevant for the Auto matching algorithm.
+  * New select interface for tags, types and correspondents allows filtering. This also improves tag selection. Thanks again to `Michael Shamoon`_!
+  * Page navigation controls for the document viewer, thanks to `Michael Shamoon`_.
+  * Layout changes to the small cards document list.
+  * The dashboard now displays the username (or full name if specified in the admin) on the dashboard.
+
+* Fixes
+
+  * An error that caused the document importer to crash was fixed.
+  * An issue with changes not being possible when ``PAPERLESS_COOKIE_PREFIX`` is used was fixed.
+  * The date selection filters now allow manual entry of dates.
+
+* Feature Removal
+
+  * Most of the guesswork features have been removed. Paperless no longer tries to extract correspondents and tags from file names.
+
+paperless-ng 0.9.8
+##################
+
+This release addresses two severe issues with the previous release.
+
+* The delete buttons for document types, correspondents and tags were not working.
+* The document section in the admin was causing internal server errors (500).
+
+
+paperless-ng 0.9.7
+##################
+
+
+* Front end
+
+  * Thanks to the hard work of `Michael Shamoon`_, paperless now comes with a much more streamlined UI for
+    filtering documents.
+
+  * `Michael Shamoon`_ replaced the document preview with another component. This should fix compatibility with Safari browsers.
+
+  * Added buttons to the management pages to quickly show all documents with one specific tag, correspondent, or title.
+
+  * Paperless now stores your saved views on the server and associates them with your user account.
+    This means that you can access your views on multiple devices and have separate views for different users.
+    You will have to recreate your views.
+
+  * The GitHub and documentation links now open in new tabs/windows. Thanks to `rYR79435`_.
+
+  * Paperless now generates default saved view names when saving views with certain filter rules.
+
+  * Added a small version indicator to the front end.
+
+* Other additions and changes
+
+  * The new filename format field ``{tag_list}`` inserts a list of tags into the filename, separated by comma.
+  * The ``document_retagger`` no longer removes inbox tags or tags without matching rules.
+  * The new configuration option ``PAPERLESS_COOKIE_PREFIX`` allows you to run multiple instances of paperless on different ports.
+    This option enables you to be logged in into multiple instances by specifying different cookie names for each instance.
+
+* Fixes
+
+  * Sometimes paperless would assign dates in the future to newly consumed documents.
+  * The filename format fields ``{created_month}`` and ``{created_day}`` now use a leading zero for single digit values.
+  * The filename format field ``{tags}`` can no longer be used without arguments.
+  * Paperless was not able to consume many images (especially images from mobile scanners) due to missing DPI information.
+    Paperless now assumes A4 paper size for PDF generation if no DPI information is present.
+  * Documents with empty titles could not be opened from the table view due to the link being empty.
+  * Fixed an issue with filenames containing special characters such as ``:`` not being accepted for upload.
+  * Fixed issues with thumbnail generation for plain text files.
+
+
+paperless-ng 0.9.6
+##################
+
+This release focusses primarily on many small issues with the UI.
+
+* Front end
+
+  * Paperless now has proper window titles.
+  * Fixed an issue with the small cards when more than 7 tags were used.
+  * Navigation of the "Show all" links adjusted. They navigate to the saved view now, if available in the sidebar.
+  * Some indication on the document lists that a filter is active was added.
+  * There's a new filter to filter for documents that do *not* have a certain tag.
+  * The file upload box now shows upload progress.
+  * The document edit page was reorganized.
+  * The document edit page shows various information about a document.
+  * An issue with the height of the preview was fixed.
+  * Table issues with too long document titles fixed.
+
+* API
+
+  * The API now serves file names with documents.
+  * The API now serves various metadata about documents.
+  * API documentation updated.
+
+* Other
+
+  * Fixed an issue with the docker image when a non-standard PostgreSQL port was used.
+  * The docker image was trying check for installed languages before actually installing them.
+  * ``FILENAME_FORMAT`` placeholder for document types.
+  * The filename formatter is now less restrictive with file names and tries to
+    conserve the original correspondents, types and titles as much as possible.
+  * The filename formatter does not include the document ID in filenames anymore. It will
+    rather append ``_01``, ``_02``, etc when it detects duplicate filenames.
+
+.. note::
+
+  The changes to the filename format will apply to newly added documents and changed documents.
+  If you want all files to reflect these changes, execute the ``document_renamer`` management
+  command.
+
+
+paperless-ng 0.9.5
+##################
+
+This release concludes the big changes I wanted to get rolled into paperless. The next releases before 1.0 will
+focus on fixing issues, primarily.
+
+* OCR
+
+  * Paperless now uses `OCRmyPDF <https://github.com/jbarlow83/OCRmyPDF>`_ to perform OCR on documents.
+    It still uses tesseract under the hood, but the PDF parser of Paperless has changed considerably and
+    will behave different for some douments.
+  * OCRmyPDF creates archived PDF/A documents with embedded text that can be selected in the front end.
+  * Paperless stores archived versions of documents alongside with the originals. The originals can be
+    accessed on the document edit page. If available, a dropdown menu will appear next to the download button.
+  * Many of the configuration options regarding OCR have changed. See :ref:`configuration-ocr` for details.
+  * Paperless no longer guesses the language of your documents. It always uses the language that you
+    specified with ``PAPERLESS_OCR_LANGUAGE``. Be sure to set this to the language the majority of your
+    documents are in. Multiple languages can be specified, but that requires more CPU time.
+  * The management command :ref:`document_archiver <utilities-archiver>` can be used to create archived versions for already
+    existing documents.
+
+* Tags from consumption folder.
+
+  * Thanks to `jayme-github`_, paperless now consumes files from sub folders in the consumption folder and is able to assign tags
+    based on the sub folders a document was found in. This can be configured with ``PAPERLESS_CONSUMER_RECURSIVE`` and
+    ``PAPERLESS_CONSUMER_SUBDIRS_AS_TAGS``.
+
+* API
+
+  * The API now offers token authentication.
+  * The endpoint for uploading documents now supports specifying custom titles, correspondents, tags and types.
+    This can be used by clients to override the default behavior of paperless. See :ref:`api-file_uploads`.
+  * The document endpoint of API now serves documents in this form:
+
+    * correspondents, document types and tags are referenced by their ID in the fields ``correspondent``, ``document_type`` and ``tags``. The ``*_id`` versions are gone. These fields are read/write.
+    * paperless does not serve nested tags, correspondents or types anymore.
+
+* Front end
+
+  * Paperless does some basic caching of correspondents, tags and types and will only request them from the server when necessary or when entirely reloading the page.
+  * Document list fetching is about 10%-30% faster now, especially when lots of tags/correspondents are present.
+  * Some minor improvements to the front end, such as document count in the document list, better highlighting of the current page, and improvements to the filter behavior.
+
+* Fixes:
+
+  * A bug with the generation of filenames for files with unsupported types caused the exporter and
+    document saving to crash.
+  * Mail handling no longer exits entirely when encountering errors. It will skip the account/rule/message on which the error occured.
+  * Assigning correspondents from mail sender names failed for very long names. Paperless no longer assigns correspondents in these cases.
+
+paperless-ng 0.9.4
+##################
+
+* Searching:
+
+  * Paperless now supports searching by tags, types and dates and correspondents. In order to have this applied to your
+    existing documents, you need to perform a ``document_index reindex`` management command
+    (see :ref:`administration-index`)
+    that adds the data to the search index. You only need to do this once, since the schema of the search index changed.
+    Paperless keeps the index updated after that whenever something changes.
+  * Paperless now has spelling corrections ("Did you mean") for miss-typed queries.
+  * The documentation contains :ref:`information about the query syntax <basic-searching>`.
+
+* Front end:
+
+  * Clickable tags, correspondents and types allow quick filtering for related documents.
+  * Saved views are now editable.
+  * Preview documents directly in the browser.
+  * Navigation from the dashboard to saved views.
+
+* Fixes:
+
+  * A severe error when trying to use post consume scripts.
+  * An error in the consumer that cause invalid messages of missing files to show up in the log.
+
+* The documentation now contains information about bare metal installs and a section about
+  how to setup the development environment.
+
 paperless-ng 0.9.3
 ##################
 
@@ -20,7 +382,7 @@ paperless-ng 0.9.3
     aware of.
   * Issue with the automatic classifier not working with only one tag.
   * A couple issues with the search index being opened to eagerly.
-  
+
 * Added lots of tests for various parts of the application.
 
 paperless-ng 0.9.2
@@ -722,6 +1084,12 @@ bulk of the work on this big change.
 
 * Initial release
 
+.. _slorenz: https://github.com/sisao
+.. _Jo Vandeginste: https://github.com/jovandeginste
+.. _zjean: https://github.com/zjean
+.. _rYR79435: https://github.com/rYR79435
+.. _Michael Shamoon: https://github.com/shamoon
+.. _jayme-github: http://github.com/jayme-github
 .. _Brian Conn: https://github.com/TheConnMan
 .. _Christopher Luu: https://github.com/nuudles
 .. _Florian Jung: https://github.com/the01

docs/conf.py

@@ -1,48 +1,21 @@
-# -*- coding: utf-8 -*-
-#
-# Paperless documentation build configuration file, created by
-# sphinx-quickstart on Mon Oct 26 18:36:52 2015.
-#
-# This file is execfile()d with the current directory set to its
-# containing dir.
-#
-# Note that not all possible configuration values are present in this
-# autogenerated file.
-#
-# All configuration values have a default; values that are commented out
-# serve to show the default.
+import sphinx_rtd_theme
+
 
 __version__ = None
 exec(open("../src/paperless/version.py").read())
 
 
-# Believe it or not, this is the officially sanctioned way to add custom CSS.
-def setup(app):
-    app.add_stylesheet("custom.css")
-
-# If extensions (or modules to document with autodoc) are in another directory,
-# add these directories to sys.path here. If the directory is relative to the
-# documentation root, use os.path.abspath to make it absolute, like shown here.
-#sys.path.insert(0, os.path.abspath('.'))
-
-# -- General configuration ------------------------------------------------
-
-# If your documentation needs a minimal Sphinx version, state it here.
-#needs_sphinx = '1.0'
-
-# Add any Sphinx extension module names here, as strings. They can be
-# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
-# ones.
 extensions = [
     'sphinx.ext.autodoc',
     'sphinx.ext.intersphinx',
     'sphinx.ext.todo',
     'sphinx.ext.imgmath',
     'sphinx.ext.viewcode',
+    'sphinx_rtd_theme',
 ]
 
 # 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'
@@ -115,7 +88,7 @@ pygments_style = 'sphinx'
 
 # The theme to use for HTML and HTML Help pages.  See the documentation for
 # a list of builtin themes.
-html_theme = 'default'
+html_theme = 'sphinx_rtd_theme'
 
 # Theme options are theme-specific and customize the look and feel of a theme
 # further.  For a list of options available for each theme, see the
@@ -195,20 +168,6 @@ html_static_path = ['_static']
 # Output file base name for HTML help builder.
 htmlhelp_basename = 'paperless'
 
-
-#
-# Attempt to use the ReadTheDocs theme.  If it's not installed, fallback to
-# the default.
-#
-
-try:
-    import sphinx_rtd_theme
-    html_theme = "sphinx_rtd_theme"
-    html_theme_path = [sphinx_rtd_theme.get_html_theme_path()]
-except ImportError as e:
-    print("error " + str(e))
-    pass
-
 # -- Options for LaTeX output ---------------------------------------------
 
 latex_elements = {

docs/configuration.rst

@@ -53,6 +53,12 @@ PAPERLESS_DBPASS=<password>
 
     Defaults to "paperless".
 
+PAPERLESS_DBSSLMODE=<mode>
+    SSL mode to use when connecting to PostgreSQL.
+
+    See `the official documentation about sslmode <https://www.postgresql.org/docs/current/libpq-ssl.html>`_.
+
+    Default is ``prefer``.
 
 Paths and folders
 #################
@@ -152,6 +158,198 @@ PAPERLESS_AUTO_LOGIN_USERNAME=<username>
 
     Defaults to none, which disables this feature.
 
+
+PAPERLESS_COOKIE_PREFIX=<str>
+    Specify a prefix that is added to the cookies used by paperless to identify
+    the currently logged in user. This is useful for when you're running two
+    instances of paperless on the same host.
+
+    After changing this, you will have to login again.
+
+    Defaults to ``""``, which does not alter the cookie names.
+
+PAPERLESS_ENABLE_HTTP_REMOTE_USER=<bool>
+    Allows authentication via HTTP_REMOTE_USER which is used by some SSO
+    applications.
+
+    Defaults to `false` which disables this feature.
+
+.. _configuration-ocr:
+
+OCR settings
+############
+
+Paperless uses `OCRmyPDF <https://ocrmypdf.readthedocs.io/en/latest/>`_ for
+performing OCR on documents and images. Paperless uses sensible defaults for
+most settings, but all of them can be configured to your needs.
+
+
+PAPERLESS_OCR_LANGUAGE=<lang>
+    Customize the language that paperless will attempt to use when
+    parsing documents.
+
+    It should be a 3-letter language code consistent with ISO
+    639: https://www.loc.gov/standards/iso639-2/php/code_list.php
+
+    Set this to the language most of your documents are written in.
+
+    This can be a combination of multiple languages such as ``deu+eng``,
+    in which case tesseract will use whatever language matches best.
+    Keep in mind that tesseract uses much more cpu time with multiple
+    languages enabled.
+
+    Defaults to "eng".
+
+PAPERLESS_OCR_MODE=<mode>
+    Tell paperless when and how to perform ocr on your documents. Four modes
+    are available:
+
+    *   ``skip``: Paperless skips all pages and will perform ocr only on pages
+        where no text is present. This is the safest option.
+    *   ``skip_noarchive``: In addition to skip, paperless won't create an
+        archived version of your documents when it finds any text in them.
+        This is useful if you don't want to have two almost-identical versions
+        of your digital documents in the media folder. This is the fastest option.
+    *   ``redo``: Paperless will OCR all pages of your documents and attempt to
+        replace any existing text layers with new text. This will be useful for
+        documents from scanners that already performed OCR with insufficient
+        results. It will also perform OCR on purely digital documents.
+
+        This option may fail on some documents that have features that cannot
+        be removed, such as forms. In this case, the text from the document is
+        used instead.
+    *   ``force``: Paperless rasterizes your documents, converting any text
+        into images and puts the OCRed text on top. This works for all documents,
+        however, the resulting document may be significantly larger and text
+        won't appear as sharp when zoomed in.
+
+    The default is ``skip``, which only performs OCR when necessary and always
+    creates archived documents.
+
+PAPERLESS_OCR_OUTPUT_TYPE=<type>
+    Specify the the type of PDF documents that paperless should produce.
+
+    *   ``pdf``: Modify the PDF document as little as possible.
+    *   ``pdfa``: Convert PDF documents into PDF/A-2b documents, which is a
+        subset of the entire PDF specification and meant for storing
+        documents long term.
+    *   ``pdfa-1``, ``pdfa-2``, ``pdfa-3`` to specify the exact version of
+        PDF/A you wish to use.
+
+    If not specified, ``pdfa`` is used. Remember that paperless also keeps
+    the original input file as well as the archived version.
+
+
+PAPERLESS_OCR_PAGES=<num>
+    Tells paperless to use only the specified amount of pages for OCR. Documents
+    with less than the specified amount of pages get OCR'ed completely.
+
+    Specifying 1 here will only use the first page.
+
+    When combined with ``PAPERLESS_OCR_MODE=redo`` or ``PAPERLESS_OCR_MODE=force``,
+    paperless will not modify any text it finds on excluded pages and copy it
+    verbatim.
+
+    Defaults to 0, which disables this feature and always uses all pages.
+
+
+PAPERLESS_OCR_IMAGE_DPI=<num>
+    Paperless will OCR any images you put into the system and convert them
+    into PDF documents. This is useful if your scanner produces images.
+    In order to do so, paperless needs to know the DPI of the image.
+    Most images from scanners will have this information embedded and
+    paperless will detect and use that information. In case this fails, it
+    uses this value as a fallback.
+
+    Set this to the DPI your scanner produces images at.
+
+    Default is none, which causes paperless to fail if no DPI information is
+    present in an image.
+
+
+PAPERLESS_OCR_USER_ARGS=<json>
+    OCRmyPDF offers many more options. Use this parameter to specify any
+    additional arguments you wish to pass to OCRmyPDF. Since Paperless uses
+    the API of OCRmyPDF, you have to specify these in a format that can be
+    passed to the API. See `the API reference of OCRmyPDF <https://ocrmypdf.readthedocs.io/en/latest/api.html#reference>`_
+    for valid parameters. All command line options are supported, but they
+    use underscores instead of dashed.
+
+    .. caution::
+
+        Paperless has been tested to work with the OCR options provided
+        above. There are many options that are incompatible with each other,
+        so specifying invalid options may prevent paperless from consuming
+        any documents.
+
+    Specify arguments as a JSON dictionary. Keep note of lower case booleans
+    and double quoted parameter names and strings. Examples:
+
+    .. code:: json
+
+        {"deskew": true, "optimize": 3, "unpaper_args": "--pre-rotate 90"}
+
+.. _configuration-tika:
+
+Tika settings
+#############
+
+Paperless can make use of `Tika <https://tika.apache.org/>`_ and
+`Gotenberg <https://thecodingmachine.github.io/gotenberg/>`_ for parsing and
+converting "Office" documents (such as ".doc", ".xlsx" and ".odt"). If you
+wish to use this, you must provide a Tika server and a Gotenberg server,
+configure their endpoints, and enable the feature.
+
+PAPERLESS_TIKA_ENABLED=<bool>
+    Enable (or disable) the Tika parser.
+
+    Defaults to false.
+
+PAPERLESS_TIKA_ENDPOINT=<url>
+    Set the endpoint URL were Paperless can reach your Tika server.
+
+    Defaults to "http://localhost:9998".
+
+PAPERLESS_TIKA_GOTENBERG_ENDPOINT=<url>
+    Set the endpoint URL were Paperless can reach your Gotenberg server.
+
+    Defaults to "http://localhost:3000".
+
+If you run paperless on docker, you can add those services to the docker-compose
+file (see the provided ``docker-compose.tika.yml`` file for reference). The changes
+requires are as follows:
+
+.. code:: yaml
+
+    services:
+        # ...
+
+        webserver:
+            # ...
+
+            environment:
+                # ...
+
+                PAPERLESS_TIKA_ENABLED: 1
+                PAPERLESS_TIKA_GOTENBERG_ENDPOINT: http://gotenberg:3000
+                PAPERLESS_TIKA_ENDPOINT: http://tika:9998
+        
+        # ...
+
+        gotenberg:
+            image: thecodingmachine/gotenberg
+            restart: unless-stopped
+            environment:
+                DISABLE_GOOGLE_CHROME: 1
+
+        tika:
+            image: apache/tika
+            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.
+
 Software tweaks
 ###############
 
@@ -160,6 +358,7 @@ 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.
 
+
 PAPERLESS_THREADS_PER_WORKER=<num>
     Furthermore, paperless uses multiple threads when consuming documents to
     speed up OCR. This variable specifies how many pages paperless will process
@@ -177,14 +376,31 @@ PAPERLESS_THREADS_PER_WORKER=<num>
         use a higher thread per worker count.
 
     The default is a balance between the two, according to your CPU core count,
-    with a slight favor towards threads per worker, and using as much cores as
-    possible.
+    with a slight favor towards threads per worker, and leaving at least one core
+    free for other tasks:
+
+    +----------------+---------+---------+
+    | CPU core count | Workers | Threads |
+    +----------------+---------+---------+
+    |              1 |       1 |       1 |
+    +----------------+---------+---------+
+    |              2 |       1 |       1 |
+    +----------------+---------+---------+
+    |              4 |       1 |       3 |
+    +----------------+---------+---------+
+    |              6 |       2 |       2 |
+    +----------------+---------+---------+
+    |              8 |       2 |       3 |
+    +----------------+---------+---------+
+    |             12 |       3 |       3 |
+    +----------------+---------+---------+
+    |             16 |       3 |       5 |
+    +----------------+---------+---------+
 
     If you only specify PAPERLESS_TASK_WORKERS, paperless will adjust
     PAPERLESS_THREADS_PER_WORKER automatically.
 
 
-
 PAPERLESS_TIME_ZONE=<timezone>
     Set the time zone here.
     See https://docs.djangoproject.com/en/3.1/ref/settings/#std:setting-TIME_ZONE
@@ -193,51 +409,46 @@ PAPERLESS_TIME_ZONE=<timezone>
     Defaults to UTC.
 
 
-
-PAPERLESS_OCR_PAGES=<num>
-    Tells paperless to use only the specified amount of pages for OCR. Documents
-    with less than the specified amount of pages get OCR'ed completely.
-
-    Specifying 1 here will only use the first page.
-
-    Defaults to 0, which disables this feature and always uses all pages.
-
-
-
-PAPERLESS_OCR_LANGUAGE=<lang>
-    Customize the default language that tesseract will attempt to use when
-    parsing documents. The default language is used whenever
-
-    * No language could be detected on a document
-    * No tesseract data files are available for the detected language
-
-    It should be a 3-letter language code consistent with ISO
-    639: https://www.loc.gov/standards/iso639-2/php/code_list.php
-
-    Set this to the language most of your documents are written in.
-
-    Defaults to "eng".
-
-PAPERLESS_OCR_ALWAYS=<bool>
-    By default Paperless does not OCR a document if the text can be retrieved from
-    the document directly. Set to true to always OCR documents.
-
-    Defaults to false.
+.. _configuration-polling:
 
 PAPERLESS_CONSUMER_POLLING=<num>
     If paperless won't find documents added to your consume folder, it might
     not be able to automatically detect filesystem changes. In that case,
     specify a polling interval in seconds here, which will then cause paperless
-    to periodically check your consumption directory for changes.
+    to periodically check your consumption directory for changes. This will also
+    disable listening for file system changes with ``inotify``.
 
     Defaults to 0, which disables polling and uses filesystem notifications.
 
+
 PAPERLESS_CONSUMER_DELETE_DUPLICATES=<bool>
     When the consumer detects a duplicate document, it will not touch the
     original document. This default behavior can be changed here.
 
     Defaults to false.
 
+
+PAPERLESS_CONSUMER_RECURSIVE=<bool>
+    Enable recursive watching of the consumption directory. Paperless will
+    then pickup files from files in subdirectories within your consumption
+    directory as well.
+
+    Defaults to false.
+
+
+PAPERLESS_CONSUMER_SUBDIRS_AS_TAGS=<bool>
+    Set the names of subdirectories as tags for consumed files.
+    E.g. <CONSUMPTION_DIR>/foo/bar/file.pdf will add the tags "foo" and "bar" to
+    the consumed file. Paperless will create any tags that don't exist yet.
+
+    This is useful for sorting documents with certain tags such as ``car`` or
+    ``todo`` prior to consumption. These folders won't be deleted.
+
+    PAPERLESS_CONSUMER_RECURSIVE must be enabled for this to work.
+
+    Defaults to false.
+
+
 PAPERLESS_CONVERT_MEMORY_LIMIT=<num>
     On smaller systems, or even in the case of Very Large Documents, the consumer
     may explode, complaining about how it's "unable to extend pixel cache".  In
@@ -261,18 +472,6 @@ PAPERLESS_CONVERT_TMPDIR=<path>
 
     Default is none, which disables the temporary directory.
 
-PAPERLESS_CONVERT_DENSITY=<num>
-    This setting has a high impact on the physical size of tmp page files,
-    the speed of document conversion, and can affect the accuracy of OCR
-    results. Individual results can vary and this setting should be tested
-    thoroughly against the documents you are importing to see if it has any
-    impacts either negative or positive.
-    Testing on limited document sets has shown a setting of 200 can cut the
-    size of tmp files by 1/3, and speed up conversion by up to 4x
-    with little impact to OCR accuracy.
-
-    Default is 300.
-
 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
@@ -297,11 +496,28 @@ PAPERLESS_FILENAME_DATE_ORDER=<format>
 
     Defaults to none, which disables this feature.
 
-PAPERLESS_FILENAME_PARSE_TRANSFORMS
-    Transforms filenames before they are processed by paperless. See
-    :ref:`advanced-transforming_filenames` for details.
+PAPERLESS_THUMBNAIL_FONT_NAME=<filename>
+    Paperless creates thumbnails for plain text files by rendering the content
+    of the file on an image and uses a predefined font for that. This
+    font can be changed here.
+
+    Note that this won't have any effect on already generated thumbnails.
+
+    Defaults to ``/usr/share/fonts/liberation/LiberationSerif-Regular.ttf``.
+
+PAPERLESS_IGNORE_DATES=<string>
+    Paperless parses a documents creation date from filename and file content.
+    You may specify a comma separated list of dates that should be ignored during
+    this process. This is useful for special dates (like date of birth) that appear
+    in documents regularly but are very unlikely to be the documents creation date.
+
+    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"
+
+    Defaults to an empty string to not ignore any dates.
 
-    Defaults to none, which disables this feature.
 
 Binaries
 ########
@@ -319,8 +535,5 @@ PAPERLESS_CONVERT_BINARY=<path>
 PAPERLESS_GS_BINARY=<path>
     Defaults to "/usr/bin/gs".
 
-PAPERLESS_UNPAPER_BINARY=<path>
-    Defaults to "/usr/bin/unpaper".
-
 PAPERLESS_OPTIPNG_BINARY=<path>
     Defaults to "/usr/bin/optipng".

docs/extending.rst

@@ -1,116 +1,191 @@
 .. _extending:
 
+Paperless development
+#####################
+
+This section describes the steps you need to take to start development on paperless-ng.
+
+1.  Check out the source from github. The repository is organized in the following way:
+
+    *   ``master`` always represents the latest release and will only see changes
+        when a new release is made.
+    *   ``dev`` contains the code that will be in the next release.
+    *   ``feature-X`` contain bigger changes that will be in some release, but not
+        necessarily the next one.
+    
+    Apart from that, the folder structure is as follows:
+
+    *   ``docs/`` - Documentation.
+    *   ``src-ui/`` - Code of the front end.
+    *   ``src/`` - Code of the back end.
+    *   ``scripts/`` - Various scripts that help with different parts of development.
+    *   ``docker/`` - Files required to build the docker image.
+
+2.  Install some dependencies.
+
+    *   Python 3.6.
+    *   All dependencies listed in the :ref:`Bare metal route <setup-bare_metal>`
+    *   redis. You can either install redis or use the included scritps/start-services.sh
+        to use docker to fire up a redis instance (and some other services such as tika,
+        gotenberg and a postgresql server).
+
+Back end development
+====================
+
+The backend is a django application. I use PyCharm for development, but you can use whatever
+you want.
+
+Install the python dependencies by performing ``pipenv install --dev`` in the src/ directory.
+This will also create a virtual environment, which you can enter with ``pipenv shell`` or
+execute one-shot commands in with ``pipenv run``.
+
+Copy ``paperless.conf.example`` to ``paperless.conf`` and enable debug mode.
+
+Configure the IDE to use the src/ folder as the base source folder. Configure the following
+launch configurations in your IDE:
+
+*   python3 manage.py runserver
+*   python3 manage.py qcluster
+*   python3 manage.py consumer
+
+Depending on which part of paperless you're developing for, you need to have some or all of
+them running.
+
+Testing and code style:
+
+*   Run ``pytest`` in the src/ directory to execute all tests. This also generates a HTML coverage
+    report. When runnings test, paperless.conf is loaded as well. However: the tests rely on the default
+    configuration. This is not ideal. But for now, make sure no settings except for DEBUG are overridden when testing.
+*   Run ``pycodestyle`` to test your code for issues with the configured code style settings.
+
+    .. note::
+
+        The line length rule E501 is generally useful for getting multiple source files
+        next to each other on the screen. However, in some cases, its just not possible
+        to make some lines fit, especially complicated IF cases. Append ``  # NOQA: E501``
+        to disable this check for certain lines.
+
+Front end development
+=====================
+
+The front end is build using angular. I use the ``Code - OSS`` IDE for development.
+
+In order to get started, you need ``npm``. Install the Angular CLI interface with
+
+.. code:: shell-session
+
+    $ npm install -g @angular/cli
+
+and make sure that it's on your path. Next, in the src-ui/ directory, install the
+required dependencies of the project.
+
+.. code:: shell-session
+
+    $ npm install
+
+You can launch a development server by running
+
+.. code:: shell-session
+
+    $ ng serve
+
+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 ``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. This also
+relies on you being logged into the back end. Without a valid session, The front end will simply
+not work.
+
+In order to build the front end and serve it as part of django, execute
+
+.. code:: shell-session
+
+    $ ng build --prod
+
+This will build the front end and put it in a location from which the Django server will serve
+it as static content. This way, you can verify that authentication is working.
+
+
 Extending Paperless
 ===================
 
-.. warning::
+Paperless 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.
 
-    This section is not updated to paperless-ng yet.
+Making custom parsers
+---------------------
 
-For the most part, Paperless is monolithic, so extending it is often best
-managed by way of modifying the code directly and issuing a pull request on
-`GitHub`_.  However, over time the project has been evolving to be a little
-more "pluggable" so that users can write their own stuff that talks to it.
+Paperless uses parsers to add documents to paperless. A parser is responsible for:
 
-.. _GitHub: https://github.com/the-paperless-project/paperless
+*   Retrieve the content from the original
+*   Create a thumbnail
+*   Optional: Retrieve a created date from the original
+*   Optional: Create an archived document from the original
 
+Custom parsers can be added to paperless to support more file types. In order to do that,
+you need to write the parser itself and announce its existence to paperless.
 
-.. _extending-parsers:
-
-Parsers
--------
-
-You can leverage Paperless' consumption model to have it consume files *other*
-than ones handled by default like ``.pdf``, ``.jpg``, and ``.tiff``.  To do so,
-you simply follow Django's convention of creating a new app, with a few key
-requirements.
-
-
-.. _extending-parsers-parserspy:
-
-parsers.py
-..........
-
-In this file, you create a class that extends
-``documents.parsers.DocumentParser`` and go about implementing the three
-required methods:
-
-* ``get_thumbnail()``: Returns the path to a file we can use as a thumbnail for
-  this document.
-* ``get_text()``: Returns the text from the document and only the text.
-* ``get_date()``: If possible, this returns the date of the document, otherwise
-  it should return ``None``.
-
-
-.. _extending-parsers-signalspy:
-
-signals.py
-..........
-
-At consumption time, Paperless emits a ``document_consumer_declaration``
-signal which your module has to react to in order to let the consumer know
-whether or not it's capable of handling a particular file.  Think of it like
-this:
-
-1. Consumer finds a file in the consumption directory.
-2. It asks all the available parsers: *"Hey, can you handle this file?"*
-3. Each parser responds with either ``None`` meaning they can't handle the
-   file, or a dictionary in the following format:
+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.
 
 .. code:: python
 
-    {
-        "parser": <the class name>,
-        "weight": <an integer>
-    }
+    class MyCustomParser(DocumentParser):
 
-The consumer compares the ``weight`` values from all respondents and uses the
-class with the highest value to consume the document.  The default parser,
-``RasterisedDocumentParser`` has a weight of ``0``.
+        def parse(self, document_path, mime_type):
+            # This method does not return anything. Rather, you should assign
+            # whatever you got from the document to the following fields:
 
+            # The content of the document.
+            self.text = "content"
+            
+            # Optional: path to a PDF document that you created from the original.
+            self.archive_path = os.path.join(self.tempdir, "archived.pdf")
 
-.. _extending-parsers-appspy:
+            # Optional: "created" date of the document.
+            self.date = get_created_from_metadata(document_path)
 
-apps.py
-.......
+        def get_thumbnail(self, document_path, mime_type):
+            # This should return the path to a thumbnail you created for this
+            # document.
+            return os.path.join(self.tempdir, "thumb.png")
 
-This is a standard Django file, but you'll need to add some code to it to
-connect your parser to the ``document_consumer_declaration`` signal.
+If you encounter any issues during parsing, raise a ``documents.parsers.ParseError``.
 
+The ``self.tempdir`` directory is a temporary directory that is guaranteed 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.
 
-.. _extending-parsers-finally:
-
-Finally
-.......
-
-The last step is to update ``settings.py`` to include your new module.
-Eventually, this will be dynamic, but at the moment, you have to edit the
-``INSTALLED_APPS`` section manually.  Simply add the path to your AppConfig to
-the list like this:
+After that, you need to announce your parser to paperless. 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:
 
 .. code:: python
 
-    INSTALLED_APPS = [
-        ...
-        "my_module.apps.MyModuleConfig",
-        ...
-    ]
+    def myparser_consumer_declaration(sender, **kwargs):
+        return {
+            "parser": MyCustomParser,
+            "weight": 0,
+            "mime_types": {
+                "application/pdf": ".pdf",
+                "image/jpeg": ".jpg",
+            }
+        }
 
-Order doesn't matter, but generally it's a good idea to place your module lower
-in the list so that you don't end up accidentally overriding project defaults
-somewhere.
+*   ``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.
 
-.. _extending-parsers-example:
-
-An Example
-..........
-
-The core Paperless functionality is based on this design, so if you want to see
-what a parser module should look like, have a look at `parsers.py`_,
-`signals.py`_, and `apps.py`_ in the `paperless_tesseract`_ module.
-
-.. _parsers.py: https://github.com/the-paperless-project/paperless/blob/master/src/paperless_tesseract/parsers.py
-.. _signals.py: https://github.com/the-paperless-project/paperless/blob/master/src/paperless_tesseract/signals.py
-.. _apps.py: https://github.com/the-paperless-project/paperless/blob/master/src/paperless_tesseract/apps.py
-.. _paperless_tesseract: https://github.com/the-paperless-project/paperless/blob/master/src/paperless_tesseract/
+*   ``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
+    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.

docs/faq.rst

@@ -3,6 +3,18 @@
 Frequently asked questions
 **************************
 
+**Q:** *What's the general plan for Paperless-ng?*
+
+**A:** Paperless-ng is already almost feature-complete. This project will remain
+as simple as it is right now. It will see improvements to features that are already there.
+If you need advanced features such as document versions,
+workflows or multi-user with customizable access to individual files, this is
+not the tool for you.
+
+Features that *are* planned are some more quality of life extensions for the searching
+(i.e., search for similar documents, group results by correspondents with "more from this"
+links, etc), bulk editing and hierarchical tags.
+
 **Q:** *I'm using docker. Where are my documents?*
 
 **A:** Your documents are stored inside the docker volume ``paperless_media``.
@@ -21,13 +33,27 @@ is
     files around manually. This folder is meant to be entirely managed by docker
     and paperless.
 
+**Q:** *Let's say you don't support this project anymore in a year. Can I easily move to other systems?*
+
+**A:** Your documents are stored as plain files inside the media folder. You can always drag those files
+out of that folder to use them elsewhere. Here are a couple notes about that.
+
+*   Paperless never modifies your original documents. It keeps checksums of all documents and uses a
+    scheduled sanity checker to check that they remain the same.
+*   By default, paperless uses the internal ID of each document as its filename. This might not be very
+    convenient for export. However, you can adjust the way files are stored in paperless by
+    :ref:`configuring the filename format <advanced-file_name_handling>`.
+*   :ref:`The exporter <utilities-exporter>` is another easy way to get your files out of paperless with reasonable file names.
+
 **Q:** *What file types does paperless-ng support?*
 
 **A:** Currently, the following files are supported:
 
-*   PDF documents, PNG images and JPEG images are processed with OCR.
+*   PDF documents, PNG images, JPEG images, TIFF images and GIF images are processed with OCR and converted into PDF documents.
 *   Plain text documents are supported as well and are added verbatim
     to paperless.
+*   With the optional Tika integration enabled (see :ref:`Configuration <configuration-tika>`), Paperless also supports various
+    Office documents (.docx, .doc, odt, .ppt, .pptx, .odp, .xls, .xlsx, .ods).
 
 Paperless determines the type of a file by inspecting its content. The
 file extensions do not matter.
@@ -49,7 +75,32 @@ in your browser and paperless has to do much less work to serve the data.
 
 **Q:** *How do I install paperless-ng on Raspberry Pi?*
 
-**A:** There is not docker image for ARM available. If you know how to build
-that automatically, I'm all ears. For now, you have to grab the latest release
-archive from the project page and build the image yourself. The release comes
-with the front end already compiled, so you don't have to do this on the Pi.
+**A:** Docker images are available for arm and arm64 hardware, so just follow
+the docker-compose instructions, or go the bare metal route.
+
+**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.
+
+**Q:** *How do I run this on my toaster?*
+
+**A:** I honestly don't know! As for all other devices that might be able
+to run paperless, you're a bit on your own. If you can't run the docker image,
+the documentation has instructions for bare metal installs. I'm running
+paperless on an i3 processor from 2015 or so. This is also what I use to test
+new releases with. Apart from that, I also have a Raspberry Pi, which I
+occasionally build the image on and see if it works.
+
+**Q:** *How do I proxy this with NGINX?*
+
+.. code::
+
+    location / {
+        proxy_pass http://localhost:8000/
+    }
+
+And that's about it. Paperless serves everything, including static files by itself
+when running the docker image. If you want to do anything fancy, you have to
+install paperless bare metal.

docs/index.rst

@@ -42,6 +42,9 @@ 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
+    the consumption directory. This means that you can select text in
+    image-only documents coming from your scanner.
 *   See :ref:`this note <utilities-encyption>` about GnuPG encryption in
     paperless-ng.
 *   Paperless is now integrated with a

docs/scanners.rst

@@ -10,6 +10,9 @@ 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 |
 +---------+----------------+-----+-----+-----+----------------+
@@ -25,6 +28,8 @@ that works right for you based on recommendations from other Paperless users.
 +---------+----------------+-----+-----+-----+----------------+
 | Fujitsu | `ix500`_       | yes |     | yes | `eonist`_      |
 +---------+----------------+-----+-----+-----+----------------+
+| Epson   | `WF-7710DWF`_  | yes |     | yes | `Skylinar`_    |
++---------+----------------+-----+-----+-----+----------------+
 | Fujitsu | `S1300i`_      | yes |     | yes | `jonaswinkler`_|
 +---------+----------------+-----+-----+-----+----------------+
 
@@ -32,7 +37,8 @@ that works right for you based on recommendations from other Paperless users.
 .. _MFC-J6930DW: https://www.brother.ca/en/p/MFCJ6930DW
 .. _MFC-J5910DW: https://www.brother.co.uk/printers/inkjet-printers/mfcj5910dw
 .. _MFC-9142CDN: https://www.brother.co.uk/printers/laser-printers/mfc9140cdn
-.. _ix500: https://www.fujitsu.com/global/products/computing/peripheral/scanners/scansnap/ix500/
+.. _ix500: http://www.fujitsu.com/us/products/computing/peripheral/scanners/scansnap/ix500/
+.. _WF-7710DWF: https://www.epson.de/en/products/printers/inkjet-printers/for-home/workforce-wf-7710dwf
 .. _S1300i: https://www.fujitsu.com/global/products/computing/peripheral/scanners/soho/s1300i/
 
 .. _danielquinn: https://github.com/danielquinn
@@ -40,4 +46,27 @@ that works right for you based on recommendations from other Paperless users.
 .. _bmsleight: https://github.com/bmsleight
 .. _eonist: https://github.com/eonist
 .. _REOLDEV: https://github.com/REOLDEV
+.. _Skylinar: https://github.com/Skylinar
 .. _jonaswinkler: https://github.com/jonaswinkler
+
+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`_ |
++-------------------+----------------+-----+-----+-----+-------+--------+----------------+
+
+On Android, you can use these applications in combination with one of the :ref:`Paperless-ng compatible apps <usage-mobile_upload>` to "Share" the documents produced by these scanner apps with paperless.
+
+.. _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
+
+.. _hannahswain: https://github.com/hannahswain

docs/setup.rst

@@ -3,35 +3,6 @@
 Setup
 *****
 
-Download
-########
-
-Go to the project page on GitHub and download the
-`latest release <https://github.com/jonaswinkler/paperless-ng/releases>`_.
-There are multiple options available.
-
-*   Download the dockerfiles archive if you want to pull paperless from
-    Docker Hub.
-
-*   Download the dist archive and extract it if you want to build the docker image
-    yourself or want to install paperless without docker.
-
-.. hint::
-
-    In contrast to paperless, the recommended way to get and update paperless-ng
-    is not to pull the entire git repository. Paperless-ng includes artifacts
-    that need to be compiled, and that's already done for you in the release.
-
-.. admonition:: Want to try out paperless-ng before migrating?
-
-    The release contains a file ``.env`` which sets the docker-compose project
-    name to "paperless", which is the same as before and instructs docker-compose
-    to reuse and upgrade your paperless volumes.
-
-    Just rename the project name in that file to anything else and docker-compose
-    will create fresh volumes for you!
-
-
 Overview of Paperless-ng
 ########################
 
@@ -110,20 +81,41 @@ Installation
 
 You can go multiple routes with setting up and running Paperless:
 
-* The `docker route`_
-* The `bare metal route`_
+* :ref:`Pull the image from Docker Hub <setup-docker_hub>`
+* :ref:`Build the Docker image yourself <setup-docker_build>`
+* :ref:`Install Paperless directly on your system manually (bare metal) <setup-bare_metal>`
+* :ref:`Use ansible to install Paperless on your system automatically (bare metal) <setup-ansible>`
 
-The `docker route`_ is quick & easy. This is the recommended route. This configures all the stuff
+The Docker routes are quick & easy. These are the recommended routes. This configures all the stuff
 from above automatically so that it just works and uses sensible defaults for all configuration options.
 
-The `bare metal route`_ is more complicated to setup but makes it easier
+The bare metal route is more complicated to setup but makes it easier
 should you want to contribute some code back. You need to configure and
 run the above mentioned components yourself.
 
-Docker Route
-============
+The ansible route cobines benefits from both options:
+the setup process is fully automated, reproducible and idempotent,
+it includes the same sensible defaults,
+and it simultaneously provides the flexibility of a bare metal installation.
 
-1.  Install `Docker`_ and `docker-compose`_. [#compose]_
+.. _setup-docker_hub:
+
+Install Paperless from Docker Hub
+=================================
+
+1.  Go to the `/docker/compose directory on the project page <https://github.com/jonaswinkler/paperless-ng/tree/master/docker/compose>`_
+    and download one of the ``docker-compose.*.yml`` files, depending on which database backend you
+    want to use. Rename this file to `docker-compose.yml`.
+    If you want to enable optional support for Office documents, download a file with ``-tika`` in its name.
+    Download the ``docker-compose.env`` file and the ``.env`` file as well and store them
+    in the same directory.
+
+    .. hint::
+
+        For new installations, it is recommended to use PostgreSQL as the database
+        backend.
+
+2.  Install `Docker`_ and `docker-compose`_.
 
     .. caution::
 
@@ -140,15 +132,7 @@ Docker Route
         .. _Docker installation guide: https://docs.docker.com/engine/installation/
         .. _docker-compose installation guide: https://docs.docker.com/compose/install/
 
-2.  Copy either ``docker-compose.sqlite.yml`` or ``docker-compose.postgres.yml`` to
-    ``docker-compose.yml``, depending on which database backend you want to use.
-
-    .. hint::
-
-        For new installations, it is recommended to use PostgreSQL as the database
-        backend.
-
-2.  Modify ``docker-compose.yml`` to your preferences. You may want to change the path
+3.  Modify ``docker-compose.yml`` to your preferences. You may want to change the path
     to the consumption directory in this file. Find the line that specifies where
     to mount the consumption directory:
 
@@ -165,7 +149,7 @@ Docker Route
     Don't change the part after the colon or paperless wont find your documents.
 
 
-3.  Modify ``docker-compose.env``, following the comments in the file. The
+4.  Modify ``docker-compose.env``, following the comments in the file. The
     most important change is to set ``USERMAP_UID`` and ``USERMAP_GID``
     to the uid and gid of your user on the host system. This ensures that
     both the docker container and you on the host machine have write access
@@ -175,14 +159,21 @@ Docker Route
 
     .. note::
 
-        You can use any settings from the file ``paperless.conf`` in this file.
+        You can use any settings from the file ``paperless.conf.example`` in this file.
         Have a look at :ref:`configuration` to see whats available.
 
-4.  Run ``docker-compose up -d``. This will create and start the necessary
-    containers. This will also build the image of paperless if you grabbed the
-    source archive.
+    .. caution::
 
-5.  To be able to login, you will need a super user. To create it, execute the
+        Certain file systems such as NFS network shares don't support file system
+        notifications with ``inotify``. When storing the consumption directory
+        on such a file system, paperless will be unable to pick up new files
+        with the default configuration. You will need to use ``PAPERLESS_CONSUMER_POLLING``,
+        which will disable inotify. See :ref:`here <configuration-polling>`.
+
+5.  Run ``docker-compose up -d``. This will create and start the necessary
+    containers.
+
+6.  To be able to login, you will need a super user. To create it, execute the
     following command:
 
     .. code-block:: shell-session
@@ -192,7 +183,7 @@ Docker Route
     This will prompt you to set a username, an optional e-mail address and
     finally a password.
 
-6.  The default ``docker-compose.yml`` exports the webserver on your local port
+7.  The default ``docker-compose.yml`` exports the webserver on your local port
     8000. If you haven't adapted this, you should now be able to visit your
     Paperless instance at ``http://127.0.0.1:8000``. You can login with the
     user and password you just created.
@@ -200,17 +191,327 @@ Docker Route
 .. _Docker: https://www.docker.com/
 .. _docker-compose: https://docs.docker.com/compose/install/
 
-.. [#compose] You of course don't have to use docker-compose, but it
-   simplifies deployment immensely. If you know your way around Docker, feel
-   free to tinker around without using compose!
+.. _setup-docker_build:
 
+Build the docker image yourself
+===============================
+
+1.  Clone the entire repository of paperless:
+
+    .. code:: shell-session
+
+        git clone https://github.com/jonaswinkler/paperless-ng
+
+    The master branch always reflects the latest stable version.
+
+2.  Copy one of the ``docker/compose/docker-compose.*.yml`` to ``docker-compose.yml`` in the root folder,
+    depending on which database backend you want to use. Copy
+    ``docker-compose.env`` into the project root as well.
+
+3.  In the ``docker-compose.yml`` file, find the line that instructs docker-compose to pull the paperless image from Docker Hub:
+
+    .. code:: yaml
+
+        webserver:
+            image: jonaswinkler/paperless-ng:latest
+    
+    and replace it with a line that instructs docker-compose to build the image from the current working directory instead:
+
+    .. code:: yaml
+
+        webserver:
+            build: .
+
+4.  Run the ``compile-frontend.sh`` script. This requires ``node`` and ``npm >= v15``.
+
+5.  Follow steps 2 to 7 of :ref:`setup-docker_hub`. When asked to run
+    ``docker-compose up -d`` to start the containers, do
+
+    .. code:: shell-session
+
+        $ docker-compose build
+
+    before that to build the image.
+
+.. _setup-bare_metal:
 
 Bare Metal Route
 ================
 
-.. warning::
+Paperless runs on linux only. The following procedure has been tested on a minimal
+installation of Debian/Buster, which is the current stable release at the time of
+writing. Windows is not and will never be supported.
 
-    TBD. User docker for now.
+1.  Install dependencies. Paperless requires the following packages.
+
+    *   ``python3`` 3.6, 3.7, 3.8 (3.9 is untested).
+    *   ``python3-pip``, optionally ``pipenv`` for package installation
+    *   ``python3-dev``
+
+    *   ``fonts-liberation`` for generating thumbnails for plain text files
+    *   ``imagemagick`` >= 6 for PDF conversion
+    *   ``optipng`` for optimizing thumbnails
+    *   ``gnupg`` for handling encrypted documents
+    *   ``libpoppler-cpp-dev`` for PDF to text conversion
+    *   ``libpq-dev`` for PostgreSQL
+    *   ``libmagic-dev`` for mime type detection
+    *   ``mime-support`` for mime type detection
+
+    These dependencies are required for OCRmyPDF, which is used for text recognition.
+
+    *   ``unpaper``
+    *   ``ghostscript``
+    *   ``icc-profiles-free``
+    *   ``qpdf``
+    *   ``liblept5``
+    *   ``libxml2``
+    *   ``pngquant``
+    *   ``zlib1g``
+    *   ``tesseract-ocr`` >= 4.0.0 for OCR
+    *   ``tesseract-ocr`` language packs (``tesseract-ocr-eng``, ``tesseract-ocr-deu``, etc)
+
+    On Raspberry Pi, these libraries are required as well:
+
+    *   ``libatlas-base-dev``
+    *   ``libxslt1-dev``
+
+    You will also need ``build-essential``, ``python3-setuptools`` and ``python3-wheel``
+    for installing some of the python dependencies.
+
+2.  Install ``redis`` >= 5.0 and configure it to start automatically.
+
+3.  Optional. Install ``postgresql`` and configure a database, user and password for paperless. If you do not wish
+    to use PostgreSQL, SQLite is avialable as well.
+
+4.  Get the release archive from `<https://github.com/jonaswinkler/paperless-ng/releases>`_.
+    If you clone the git repo as it is, you also have to compile the front end by yourself.
+    Extract the archive to a place from where you wish to execute it, such as ``/opt/paperless``.
+
+5.  Configure paperless. See :ref:`configuration` for details. Edit the included ``paperless.conf`` and adjust the
+    settings to your needs. Required settings for getting paperless running are:
+
+    *   ``PAPERLESS_REDIS`` should point to your redis server, such as redis://localhost:6379.
+    *   ``PAPERLESS_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
+        want to have this somewhere else. Likewise, ``PAPERLESS_DATA_DIR`` and ``PAPERLESS_MEDIA_ROOT`` define where
+        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.
+
+    Many more adjustments can be made to paperless, especially the OCR part. The following options are recommended
+    for everyone:
+
+    *   Set ``PAPERLESS_OCR_LANGUAGE`` to the language most of your documents are written in.
+    *   Set ``PAPERLESS_TIME_ZONE`` to your local time zone.
+
+6.  Setup permissions. Create a system users under which you wish to run paperless. Ensure that these directories exist
+    and that the user has write permissions to the following directories
+
+    *   ``/opt/paperless/media``
+    *   ``/opt/paperless/data``
+    *   ``/opt/paperless/consume``
+
+    Adjust as necessary if you configured different folders.
+
+7.  Install python requirements. Paperless comes with both Pipfiles for ``pipenv`` as well as with a ``requirements.txt``.
+    Both will install exactly the same requirements. It is up to you if you wish to use a virtual environment or not.
+
+8.  Go to ``/opt/paperless/src``, and execute the following commands:
+
+    .. code:: bash
+
+        # This creates the database schema.
+        python3 manage.py migrate
+
+        # This creates your first paperless user
+        python3 manage.py createsuperuser
+
+9.  Optional: Test that paperless is working by executing
+
+      .. code:: bash
+
+        # This collects static files from paperless and django.
+        python3 manage.py runserver
+
+    and pointing your browser to http://localhost:8000/.
+
+    .. warning::
+
+        This is a development server which should not be used in
+        production.
+
+    .. hint::
+
+        This will not start the consumer. Paperless does this in a
+        separate process.
+
+10. Setup systemd services to run paperless automatically. You may
+    use the service definition files included in the ``scripts`` folder
+    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.
+
+    These services rely on redis and optionally the database server, but
+    don't need to be started in any particular order. The example files
+    depend on redis being started. If you use a database server, you should
+    add additinal dependencies.
+
+    .. hint::
+
+        You may optionally set up your preferred web server to serve
+        paperless as a wsgi application directly instead of running the
+        ``webserver`` service. The module containing the wsgi application
+        is named ``paperless.wsgi``.
+
+    .. caution::
+
+        The included scripts run a ``gunicorn`` standalone server,
+        which is fine for running paperless. It does support SSL,
+        however, the documentation of GUnicorn states that you should
+        use a proxy server in front of gunicorn instead.
+
+11. Optional: Install a samba server and make the consumption folder
+    available as a network share.
+
+12. Configure ImageMagick to allow processing of PDF documents. Most distributions have
+    this disabled by default, since PDF documents can contain malware. If
+    you don't do this, paperless will fall back to ghostscript for certain steps
+    such as thumbnail generation.
+
+    Edit ``/etc/ImageMagick-6/policy.xml`` and adjust
+
+    .. code::
+
+        <policy domain="coder" rights="none" pattern="PDF" />
+
+    to
+
+    .. code::
+
+        <policy domain="coder" rights="read|write" pattern="PDF" />
+
+13. Optional: Install the `jbig2enc <https://ocrmypdf.readthedocs.io/en/latest/jbig2.html>`_
+    encoder. This will reduce the size of generated PDF documents. You'll most likely need
+    to compile this by yourself, because this software has been patented until around 2017 and
+    binary packages are not available for most distributions.
+
+.. _setup-ansible:
+
+Install Paperless using ansible
+===============================
+    .. note::
+
+        This role currently only supports Debian 10 Buster and Ubuntu 20.04 Focal or later as target hosts.
+
+1.  Install ansible 2.7+ on the management node. 
+    This may be the target host paperless-ng is being installed on or any remote host which can access the target host.
+    For further details, check the ansible `inventory <https://docs.ansible.com/ansible/latest/user_guide/intro_inventory.html>`_ documentation.
+
+    On Debian and Ubuntu, the official repositories should provide a suitable version:
+
+    .. code:: bash
+
+        apt install ansible
+        ansible --version
+
+    Alternatively, you can install the most recent ansible release using PyPI:
+
+    .. code:: bash
+
+        python3 -m pip install ansible
+        ansible --version
+
+    Make sure your taget hosts are accessible:
+
+    .. code:: sh
+
+        ansible -m ping YourAnsibleTargetHostGoesHere
+
+2.  Clone the repository of paperless-ng:
+
+    .. code:: sh
+
+        git clone https://github.com/jonaswinkler/paperless-ng
+
+    Checkout the latest release tag:
+
+    .. code:: sh
+
+        cd paperless-ng
+        git checkout ng-0.9.14
+
+3.  Create an ansible ``playbook.yml`` in the paperless-ng root directory:
+
+    .. code:: yaml
+
+        - hosts: YourAnsibleTargetHostGoesHere
+          become: yes
+          vars_files:
+            - ansible/vars.yml
+          roles:
+            - ansible
+
+    Optional: If you also want to use PostgreSQL on the target system, install and add (for example) the `geerlingguy.postgresql <https://github.com/geerlingguy/ansible-role-postgresql>`_ role:
+
+    .. code:: sh
+
+        ansible-galaxy install geerlingguy.postgresql
+
+    .. code:: yaml
+
+        - hosts: YourAnsibleTargetHostGoesHere
+          become: yes
+          vars_files:
+            - ansible/vars.yml
+          roles:
+            - geerlingguy.postgresql
+            - ansible
+
+    Optional: If you also want to use a reverse proxy on the target system, install and add (for example) the `geerlingguy.nginx <https://github.com/geerlingguy/ansible-role-nginx>`_ role:
+
+    .. code:: sh
+
+        ansible-galaxy install geerlingguy.nginx
+
+    .. code:: yaml
+
+        - hosts: YourAnsibleTargetHostGoesHere
+          become: yes
+          vars_files:
+            - ansible/vars.yml
+          roles:
+            - geerlingguy.postgresql
+            - ansible
+            - geerlingguy.nginx
+
+4.  Create ``ansible/vars.yml`` to configure your ansible deployment:
+
+    .. code:: yaml
+
+        paperless_secret_key: PleaseGenerateAStrongKeyForThis
+
+        paperlessng_superuser_name: YourUserName
+        paperlessng_superuser_email: name@domain.tld
+        paperlessng_superuser_password: YourDesiredPasswordUsedForFirstLogin
+
+        paperlessng_ocr_languages:
+            - eng
+            - deu
+
+    For all of the available options, please check ``ansible/README.md`` and :ref:`configuration`.
+
+    Optional configurations for the above-mentioned PostgreSQL and nginx roles would also go here.
+
+5. Run the ansible playbook from the management node:
+
+    .. code:: sh
+
+        ansible-playbook playbook.yml
+
+    When this step completes successfully, paperless-ng will be available on the target host at ``http://127.0.0.1:8000`` (or the address you configured).
 
 Migration to paperless-ng
 #########################
@@ -245,37 +546,39 @@ Migration to paperless-ng is then performed in a few simple steps:
     paperless.
 
 3.  Download the latest release of paperless-ng. You can either go with the
-    docker-compose files or use the archive to build the image yourself.
+    docker-compose files from `here <https://github.com/jonaswinkler/paperless-ng/tree/master/docker/compose>`_
+    or clone the repository to build the image yourself (see :ref:`above <setup-docker_build>`).
     You can either replace your current paperless folder or put paperless-ng
     in a different location.
 
     .. caution::
 
-        The release include a ``.env`` file. This will set the
+        Paperless includes a ``.env`` file. This will set the
         project name for docker compose to ``paperless`` so that paperless-ng will
         automatically reuse your existing paperless volumes. When you start it, it
         will migrate your existing data. After that, your old paperless installation
         will be incompatible with the migrated volumes.
 
-4.  Copy the ``docker-compose.sqlite.yml`` file to ``docker-compose.yml``.
+4.  Download the ``docker-compose.sqlite.yml`` file to ``docker-compose.yml``.
     If you want to switch to PostgreSQL, do that after you migrated your existing
     SQLite database.
 
-5.  Adjust ``docker-compose.yml`` and
-    ``docker-compose.env`` to your needs.
-    See `docker route`_ for details on which edits are advised.
+5.  Adjust ``docker-compose.yml`` and ``docker-compose.env`` to your needs.
+    See :ref:`setup-docker_hub` for details on which edits are advised.
 
-6.  In order to find your existing documents with the new search feature, you need
+6.  :ref:`Update paperless. <administration-updating>`
+
+7.  In order to find your existing documents with the new search feature, you need
     to invoke a one-time operation that will create the search index:
 
     .. code:: shell-session
 
         $ docker-compose run --rm webserver document_index reindex
-    
+
     This will migrate your database and create the search index. After that,
     paperless will take care of maintaining the index by itself.
 
-7.  Start paperless-ng.
+8.  Start paperless-ng.
 
     .. code:: bash
 
@@ -283,11 +586,11 @@ Migration to paperless-ng is then performed in a few simple steps:
 
     This will run paperless in the background and automatically start it on system boot.
 
-8.  Paperless installed a permanent redirect to ``admin/`` in your browser. This
-    redirect is still in place and prevents access to the new UI. Clear
+9.  Paperless installed a permanent redirect to ``admin/`` in your browser. This
+    redirect is still in place and prevents access to the new UI. Clear your
     browsing cache in order to fix this.
 
-9.  Optionally, follow the instructions below to migrate your existing data to PostgreSQL.
+10.  Optionally, follow the instructions below to migrate your existing data to PostgreSQL.
 
 
 .. _setup-sqlite_to_psql:
@@ -305,6 +608,15 @@ management commands as below.
     load data from an old database schema in SQLite into a newer database
     schema in PostgreSQL, you will run into trouble.
 
+.. warning::
+
+    On some database fields, PostgreSQL enforces predefined limits on maximum
+    length, whereas SQLite does not. The fields in question are the title of documents
+    (128 characters), names of document types, tags and correspondents (128 characters),
+    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.
+
+
 1.  Stop paperless, if it is running.
 2.  Tell paperless to use PostgreSQL:
 
@@ -323,9 +635,9 @@ management commands as below.
 
             $ cd /path/to/paperless
             $ docker-compose run --rm webserver /bin/bash
-        
+
         This will launch the container and initialize the PostgreSQL database.
-    
+
     b)  Without docker, open a shell in your virtual environment, switch to
         the ``src`` directory and create the database schema:
 
@@ -335,7 +647,7 @@ management commands as below.
             $ pipenv shell
             $ cd src
             $ python3 manage.py migrate
-        
+
         This will not copy any data yet.
 
 4.  Dump your data from SQLite:
@@ -343,7 +655,7 @@ management commands as below.
     .. code:: shell-session
 
         $ python3 manage.py dumpdata --database=sqlite --exclude=contenttypes --exclude=auth.Permission > data.json
-    
+
 5.  Load your data into PostgreSQL:
 
     .. code:: shell-session
@@ -394,7 +706,7 @@ as well.
 Considerations for less powerful devices
 ########################################
 
-Paperless runs on Raspberry Pi. However, some things are rather slow on the Pi and 
+Paperless runs on Raspberry Pi. However, some things are rather slow on the Pi and
 configuring some options in paperless can help improve performance immensely:
 
 *   Stick with SQLite to save some resources.
@@ -406,29 +718,25 @@ configuring some options in paperless can help improve performance immensely:
     sluggish response times during consumption, so you might want to lower these
     settings (example: 2 workers and 1 thread to always have some computing power
     left for other tasks).
-*   Keep ``PAPERLESS_OCR_ALWAYS`` at its default value 'false' and consider OCR'ing
+*   Keep ``PAPERLESS_OCR_MODE`` at its default value ``skip`` and consider OCR'ing
     your documents before feeding them into paperless. Some scanners are able to
-    do this!
-*   Lower ``PAPERLESS_CONVERT_DENSITY`` from its default value 300 to 200. This
-    will still result in rather accurate OCR, but will decrease consumption time
-    by quite a bit.
+    do this! You might want to even specify ``skip_noarchive`` to skip archive
+    file generation for already ocr'ed documents entirely.
 *   Set ``PAPERLESS_OPTIMIZE_THUMBNAILS`` to 'false' if you want faster consumption
     times. Thumbnails will be about 20% larger.
 
 For details, refer to :ref:`configuration`.
 
 .. note::
-    
+
     Updating the :ref:`automatic matching algorithm <advanced-automatic_matching>`
     takes quite a bit of time. However, the update mechanism checks if your
-    data has changed before doing the heavy lifting. If you experience the 
+    data has changed before doing the heavy lifting. If you experience the
     algorithm taking too much cpu time, consider changing the schedule in the
     admin interface to daily. You can also manually invoke the task
     by changing the date and time of the next run to today/now.
 
-    The actual matching of the algorithm is fast and works on Raspberry Pi as 
+    The actual matching of the algorithm is fast and works on Raspberry Pi as
     well as on any other device.
 
-
-
 .. _redis: https://redis.io/

docs/troubleshooting.rst

@@ -29,75 +29,52 @@ Check for the following issues:
 Consumer fails to pickup any new files
 ######################################
 
-If you notice, that the consumer will only pickup files in the consumption
+If you notice that the consumer will only pickup files in the consumption
 directory at startup, but won't find any other files added later, check out
 the configuration file and enable filesystem polling with the setting
 ``PAPERLESS_CONSUMER_POLLING``.
 
+This will disable listening to filesystem changes with inotify and paperless will
+manually check the consumption directory for changes instead.
 
-Consumer warns ``OCR for XX failed``
-####################################
+Operation not permitted
+#######################
 
-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.
+You might see errors such as:
 
-As an example, if you are running Paperless from any Ubuntu or Debian
-box, and your documents are written in Spanish you may need to run::
+.. code:: shell-session
 
-    apt-get install -y tesseract-ocr-spa
+    chown: changing ownership of '../export': Operation not permitted
 
+The container tries to set file ownership on the listed directories. This is
+required so that the user running paperless inside docker has write permissions
+to these folders. This happens when pointing these directories to NFS shares,
+for example.
 
+Ensure that `chown` is possible on these directories.
 
-Consumer dies with ``convert: unable to extent pixel cache``
-############################################################
+Classifier error: No training data available
+############################################
 
-During the consumption process, Paperless invokes ImageMagick's ``convert``
-program to translate the source document into something that the OCR engine can
-understand and this can burn a Very Large amount of memory if the original
-document is rather long.  Similarly, if your system doesn't have a lot of
-memory to begin with (ie. a Raspberry Pi), then this can happen for even
-medium-sized documents.
+This indicates that the Auto matching algorithm found no documents to learn from.
+This may have two reasons:
 
-The solution is to tell ImageMagick *not* to Use All The RAM, as is its
-default, and instead tell it to used a fixed amount.  ``convert`` will then
-break up the job into hundreds of individual files and use them to slowly
-compile the finished image.  Simply set ``PAPERLESS_CONVERT_MEMORY_LIMIT`` in
-``/etc/paperless.conf`` to something like ``32000000`` and you'll limit
-``convert`` to 32MB.  Fiddle with this value as you like.
+*   You don't use the Auto matching algorithm: The error can be safely ignored in this case.
+*   You are using the Auto matching algorithm: The classifier explicitly excludes documents
+    with Inbox tags. Verify that there are documents in your archive without inbox tags.
+    The algorithm will only learn from documents not in your inbox.
 
-**HOWEVER**: Simply setting this value may not be enough on system where
-``/tmp`` is mounted as tmpfs, as this is where ``convert`` will write its
-temporary files.  In these cases (most Systemd machines), you need to tell
-ImageMagick to use a different space for its scratch work.  You do this by
-setting ``PAPERLESS_CONVERT_TMPDIR`` in ``/etc/paperless.conf`` to somewhere
-that's actually on a physical disk (and writable by the user running
-Paperless), like ``/var/tmp/paperless`` or ``/home/my_user/tmp`` in a pinch.
+Permission denied errors in the consumption directory
+#####################################################
 
+You might encounter errors such as:
 
-DecompressionBombWarning and/or no text in the OCR output
-#########################################################
+.. code:: shell-session
 
-Some users have had issues using Paperless to consume PDFs that were created
-by merging Very Large Scanned Images into one PDF.  If this happens to you,
-it's likely because the PDF you've created contains some very large pages
-(millions of pixels) and the process of converting the PDF to a OCR-friendly
-image is exploding.
+    The following error occured while consuming document.pdf: [Errno 13] Permission denied: '/usr/src/paperless/src/../consume/document.pdf'
 
-Typically, this happens because the scanned images are created with a high
-DPI and then rolled into the PDF with an assumed DPI of 72 (the default).
-The best solution then is to specify the DPI used in the scan in the
-conversion-to-PDF step.  So for example, if you scanned the original image
-with a DPI of 300, then merging the images into the single PDF with
-``convert`` should look like this:
+This happens when paperless does not have permission to delete files inside the consumption directory.
+Ensure that ``USERMAP_UID`` and ``USERMAP_GID`` are set to the user id and group id you use on the host operating system, if these are
+different from ``1000``. See :ref:`setup-docker_hub`.
 
-.. code:: bash
-
-    $ convert -density 300 *.jpg finished.pdf
-
-For more information on this and situations like it, you should take a look
-at `Issue #118`_ as that's where this tip originated.
-
-.. _Issue #118: https://github.com/the-paperless-project/paperless/issues/118
+Also ensure that you are able to read and write to the consumption directory on the host.

docs/usage_overview.rst

@@ -57,8 +57,29 @@ Adding documents to paperless
 #############################
 
 Once you've got Paperless setup, you need to start feeding documents into it.
-Currently, there are three options: the consumption directory, IMAP (email), and
-HTTP POST.
+When adding documents to paperless, it will perform the following operations on
+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.
+    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.
+
+.. hint::
+
+    This process can be configured to fit your needs. If you don't want paperless
+    to create archived versions for digital documents, you can configure that by
+    configuring ``PAPERLESS_OCR_MODE=skip_noarchive``. Please read the 
+    :ref:`relevant section in the documentation <configuration-ocr>`.
+
+.. note::
+
+    No matter which options you choose, Paperless will always store the original
+    document that it found in the consumption directory or in the mail and
+    will never overwrite that document. Archived versions are stored alongside the
+    original versions.
 
 
 The consumption directory
@@ -82,6 +103,25 @@ 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
+================
+
+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.
+
+
+.. _usage-mobile_upload:
+
+Mobile upload
+=============
+
+The mobile app over at `<https://github.com/qcasey/paperless_share>`_ allows Android users
+to share any documents with paperless. This can be combined with any of the mobile
+scanning apps out there, such as Office Lens.
+
+Furthermore, there is the  `Paperless App <https://github.com/bauerj/paperless_app>`_ as well,
+which not only has document upload, but also document browsing and download features.
+
 .. _usage-email:
 
 IMAP (Email)
@@ -156,6 +196,119 @@ REST API
 
 You can also submit a document using the REST API, see :ref:`api-file_uploads` for details.
 
+.. _basic-searching:
+
+
+Best practices
+##############
+
+Paperless offers a couple tools that help you organize your document collection. However,
+it is up to you to use them in a way that helps you organize documents and find specific
+documents when you need them. This section offers a couple ideas for managing your collection.
+
+Document types allow you to classify documents according to what they are. You can define
+types such as "Receipt", "Invoice", or "Contract". If you used to collect all your receipts
+in a single binder, you can recreate that system in paperless by defining a document type,
+assigning documents to that type and then filtering by that type to only see all receipts.
+
+Not all documents need document types. Sometimes its hard to determine what the type of a
+document is or it is hard to justify creating a document type that you only need once or twice.
+This is okay. As long as the types you define help you organize your collection in the way
+you want, paperless is doing its job.
+
+Tags can be used in many different ways. Think of tags are more versatile folders or binders.
+If you have a binder for documents related to university / your car or health care, you can
+create these binders in paperless by creating tags and assigning them to relevant documents.
+Just as with documents, you can filter the document list by tags and only see documents of
+a certain topic.
+
+With physical documents, you'll often need to decide which folder the document belongs to.
+The advantage of tags over folders and binders is that a single document can have multiple
+tags. A physical document cannot magically appear in two different folders, but with tags,
+this is entirely possible.
+
+.. hint::
+
+  This can be used in many different ways. One example: Imagine you're working on a particular
+  task, such as signing up for university. Usually you'll need to collect a bunch of different
+  documents that are already sorted into various folders. With the tag system of paperless,
+  you can create a new group of documents that are relevant to this task without destroying
+  the already existing organization. When you're done with the task, you could delete the
+  tag again, which would be equal to sorting documents back into the folder they belong into.
+  Or keep the tag, up to you.
+
+All of the logic above applies to correspondents as well. Attach them to documents if you
+feel that they help you organize your collection.
+
+When you've started organizing your documents, create a couple saved views for document collections
+you regularly access. This is equal to having labeled physical binders on your desk, except
+that these saved views are dynamic and simply update themselves as you add documents to the system.
+
+Here are a couple examples of tags and types that you could use in your collection.
+
+* An ``inbox`` tag for newly added documents that you haven't manually edited yet.
+* A tag ``car`` for everything car related (repairs, registration, insurance, etc)
+* A tag ``todo`` for documents that you still need to do something with, such as reply, or
+  perform some task online.
+* A tag ``bank account x`` for all bank statement related to that account.
+* A tag ``mail`` for anything that you added to paperless via its mail processing capabilities.
+* A tag ``missing_metadata`` when you still need to add some metadata to a document, but can't
+  or don't want to do this right now.
+
+Searching
+#########
+
+Paperless offers an extensive searching mechanism that is designed to allow you to quickly
+find a document you're looking for (for example, that thing that just broke and you bought
+a couple months ago, that contract you signed 8 years ago).
+
+When you search paperless for a document, it tries to match this query against your documents.
+Paperless will look for matching documents by inspecting their content, title, correspondent,
+type and tags. Paperless returns a scored list of results, so that documents matching your query
+better will appear further up in the search results.
+
+By default, paperless returns only documents which contain all words typed in the search bar.
+However, paperless also offers advanced search syntax if you want to drill down the results
+further.
+
+Matching documents with logical expressions:
+
+.. code::
+
+  shopname AND (product1 OR product2)
+
+Matching specific tags, correspondents or types:
+
+.. code::
+
+  type:invoice tag:unpaid
+  correspondent:university certificate
+
+Matching dates:
+
+.. code::
+  
+  created:[2005 to 2009]
+  added:yesterday
+  modified:today
+
+Matching inexact words:
+
+.. code::
+
+  produ*name
+
+.. note::
+
+  Inexact terms are hard for search indexes. These queries might take a while to execute. That's why paperless offers
+  auto complete and query correction.
+
+All of these constructs can be combined as you see fit.
+If you want to learn more about the query language used by paperless, paperless uses Whoosh's default query language. 
+Head over to `Whoosh query language <https://whoosh.readthedocs.io/en/latest/querylang.html>`_.
+For details on what date parsing utilities are available, see
+`Date parsing <https://whoosh.readthedocs.io/en/latest/dates.html#parsing-date-queries>`_.
+ 
 
 .. _usage-recommended_workflow:
 

paperless.conf.example

@@ -13,6 +13,7 @@
 #PAPERLESS_DBNAME=paperless
 #PAPERLESS_DBUSER=paperless
 #PAPERLESS_DBPASS=paperless
+#PAPERLESS_DBSSLMODE=prefer
 
 # Paths and folders
 
@@ -26,32 +27,48 @@
 
 #PAPERLESS_SECRET_KEY=change-me
 #PAPERLESS_ALLOWED_HOSTS=example.com,www.example.com
-#PAPERLESS_CORS_ALLOWED_HOSTS=localhost:8080,example.com,localhost:8000
+#PAPERLESS_CORS_ALLOWED_HOSTS=http://example.com,http://localhost:8000
 #PAPERLESS_FORCE_SCRIPT_NAME=
 #PAPERLESS_STATIC_URL=/static/
 #PAPERLESS_AUTO_LOGIN_USERNAME=
+#PAPERLESS_COOKIE_PREFIX=
+#PAPERLESS_ENABLE_HTTP_REMOTE_USER=false
+
+# OCR settings
+
+#PAPERLESS_OCR_LANGUAGE=eng
+#PAPERLESS_OCR_MODE=skip
+#PAPERLESS_OCR_OUTPUT_TYPE=pdfa
+#PAPERLESS_OCR_PAGES=1
+#PAPERLESS_OCR_IMAGE_DPI=300
+#PAPERLESS_OCR_USER_ARGS={}
+#PAPERLESS_CONVERT_MEMORY_LIMIT=0
+#PAPERLESS_CONVERT_TMPDIR=/var/tmp/paperless
 
 # Software tweaks
 
 #PAPERLESS_TASK_WORKERS=1
 #PAPERLESS_THREADS_PER_WORKER=1
 #PAPERLESS_TIME_ZONE=UTC
-#PAPERLESS_OCR_PAGES=1
-#PAPERLESS_OCR_LANGUAGE=eng
-#PAPERLESS_OCR_ALWAYS=false
 #PAPERLESS_CONSUMER_POLLING=10
 #PAPERLESS_CONSUMER_DELETE_DUPLICATES=false
-#PAPERLESS_CONVERT_MEMORY_LIMIT=0
-#PAPERLESS_CONVERT_TMPDIR=/var/tmp/paperless
-#PAPERLESS_CONVERT_DENSITY=300
+#PAPERLESS_CONSUMER_RECURSIVE=false
+#PAPERLESS_CONSUMER_SUBDIRS_AS_TAGS=false
 #PAPERLESS_OPTIMIZE_THUMBNAILS=true
 #PAPERLESS_POST_CONSUME_SCRIPT=/path/to/an/arbitrary/script.sh
 #PAPERLESS_FILENAME_DATE_ORDER=YMD
 #PAPERLESS_FILENAME_PARSE_TRANSFORMS=[]
+#PAPERLESS_THUMBNAIL_FONT_NAME=
+#PAPERLESS_IGNORE_DATES=
+
+# Tika settings
+
+#PAPERLESS_TIKA_ENABLED=false
+#PAPERLESS_TIKA_ENDPOINT=http://localhost:9998
+#PAPERLESS_TIKA_GOTENBERG_ENDPOINT=http://localhost:3000
 
 # Binaries
 
 #PAPERLESS_CONVERT_BINARY=/usr/bin/convert
 #PAPERLESS_GS_BINARY=/usr/bin/gs
-#PAPERLESS_UNPAPER_BINARY=/usr/bin/unpaper
 #PAPERLESS_OPTIPNG_BINARY=/usr/bin/optipng

requirements.txt

@@ -0,0 +1,74 @@
+#
+# 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
+arrow==0.17.0; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3, 3.4'
+asgiref==3.3.1; python_version >= '3.5'
+blessed==1.17.12
+certifi==2020.12.5
+cffi==1.14.4
+chardet==4.0.0; python_version >= '3.1'
+coloredlogs==15.0; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3, 3.4'
+cryptography==3.3.1; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3, 3.4, 3.5'
+dateparser==0.7.6
+django-cors-headers==3.6.0
+django-extensions==3.1.0
+django-filter==2.4.0
+django-picklefield==3.0.1; python_version >= '3'
+django-q==1.3.4
+django==3.1.5
+djangorestframework==3.12.2
+filelock==3.0.12
+fuzzywuzzy==0.18.0
+gunicorn==20.0.4
+humanfriendly==9.1; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3, 3.4'
+idna==2.10; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3'
+imap-tools==0.34.0
+img2pdf==0.4.0
+importlib-metadata==3.4.0; python_version < '3.8'
+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==1.0.0; python_version >= '3.6'
+langdetect==1.0.8
+lxml==4.6.2; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3, 3.4'
+numpy==1.19.5; python_version >= '3.6'
+ocrmypdf==11.4.5
+pathvalidate==2.3.2
+pdfminer.six==20201018; python_version >= '3.4'
+pdftotext==2.1.5
+pikepdf==2.2.5
+pillow==8.1.0
+pluggy==0.13.1; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3'
+psycopg2-binary==2.8.6
+pycparser==2.20; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3'
+python-dateutil==2.8.1
+python-dotenv==0.15.0
+python-gnupg==0.4.6
+python-levenshtein==0.12.0
+python-magic==0.4.18
+pytz==2020.5
+redis==3.5.3
+regex==2020.11.13
+reportlab==3.5.59
+requests==2.25.1; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3, 3.4'
+scikit-learn==0.24.0
+scipy==1.5.4; python_version >= '3.6'
+six==1.15.0; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3'
+sortedcontainers==2.3.0
+sqlparse==0.4.1; python_version >= '3.5'
+threadpoolctl==2.1.0; python_version >= '3.5'
+tika==1.24
+tqdm==4.56.0
+typing-extensions==3.7.4.3; python_version < '3.8'
+tzlocal==2.1
+urllib3==1.26.2; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3, 3.4' and python_version < '4'
+watchdog==1.0.2
+wcwidth==0.2.5
+whitenoise==5.2.0
+whoosh==2.7.4
+zipp==3.4.0; python_version >= '3.6'

scripts/make-release.sh

@@ -1,118 +0,0 @@
-#!/bin/bash
-
-# Release checklist
-# - wait for travis build.
-# adjust src/paperless/version.py
-# changelog in the documentation
-# adjust versions in docker/hub/*
-# If docker-compose was modified: all compose files are the same.
-
-# Steps:
-# run release script "dev", push
-# if it works: new tag, merge into master
-# on master: make release "lastest", push
-# on master: make release "version-tag", push
-# publish release files
-
-set -e
-
-
-VERSION=$1
-
-if [ -z "$VERSION" ]
-then
-	echo "Need a version string."
-	exit 1
-fi
-
-# source root directory of paperless
-PAPERLESS_ROOT=$(git rev-parse --show-toplevel)
-
-# output directory
-PAPERLESS_DIST="$PAPERLESS_ROOT/dist"
-PAPERLESS_DIST_APP="$PAPERLESS_DIST/paperless-ng"
-PAPERLESS_DIST_DOCKERFILES="$PAPERLESS_DIST/paperless-ng-dockerfiles"
-
-if [ -d "$PAPERLESS_DIST" ]
-then
-	echo "Removing $PAPERLESS_DIST"
-	rm "$PAPERLESS_DIST" -r
-fi
-
-mkdir "$PAPERLESS_DIST"
-mkdir "$PAPERLESS_DIST_APP"
-mkdir "$PAPERLESS_DIST_APP/docker"
-mkdir "$PAPERLESS_DIST_DOCKERFILES"
-
-# setup dependencies.
-
-cd "$PAPERLESS_ROOT"
-
-pipenv clean
-pipenv install --dev
-pipenv lock --keep-outdated -r > "$PAPERLESS_DIST_APP/requirements.txt"
-
-# test if the application works.
-
-cd "$PAPERLESS_ROOT/src"
-pipenv run pytest --cov
-pipenv run pycodestyle
-
-# make the documentation.
-
-cd "$PAPERLESS_ROOT/docs"
-make clean html
-
-# copy stuff into place
-
-# the application itself
-
-cp "$PAPERLESS_ROOT/.env" \
-  "$PAPERLESS_ROOT/.dockerignore" \
-	"$PAPERLESS_ROOT/CONTRIBUTING.md" \
-	"$PAPERLESS_ROOT/LICENSE" \
-	"$PAPERLESS_ROOT/Pipfile" \
-	"$PAPERLESS_ROOT/Pipfile.lock" \
-	"$PAPERLESS_ROOT/README.md" "$PAPERLESS_DIST_APP"
-
-cp "$PAPERLESS_ROOT/paperless.conf.example" "$PAPERLESS_DIST_APP/paperless.conf"
-
-# copy python source, templates and static files.
-cd "$PAPERLESS_ROOT"
-find src -wholename '*/templates/*' -o -wholename '*/static/*' -o -name '*.py' | cpio -pdm "$PAPERLESS_DIST_APP"
-
-# build the front end.
-
-cd "$PAPERLESS_ROOT/src-ui"
-ng build --prod --output-hashing none --sourceMap=false --output-path "$PAPERLESS_DIST_APP/src/documents/static/frontend"
-
-# documentation
-cp "$PAPERLESS_ROOT/docs/_build/html/" "$PAPERLESS_DIST_APP/docs" -r
-
-# docker files for building the image yourself
-cp "$PAPERLESS_ROOT/docker/local/"* "$PAPERLESS_DIST_APP"
-cp "$PAPERLESS_ROOT/docker/docker-compose.env" "$PAPERLESS_DIST_APP"
-
-# docker files for pulling from docker hub
-cp "$PAPERLESS_ROOT/docker/hub/"* "$PAPERLESS_DIST_DOCKERFILES"
-cp "$PAPERLESS_ROOT/.env" "$PAPERLESS_DIST_DOCKERFILES"
-cp "$PAPERLESS_ROOT/docker/docker-compose.env" "$PAPERLESS_DIST_DOCKERFILES"
-
-# auxiliary files required for the docker image
-cp "$PAPERLESS_ROOT/docker/docker-entrypoint.sh" "$PAPERLESS_DIST_APP/docker/"
-cp "$PAPERLESS_ROOT/docker/gunicorn.conf.py" "$PAPERLESS_DIST_APP/docker/"
-cp "$PAPERLESS_ROOT/docker/imagemagick-policy.xml" "$PAPERLESS_DIST_APP/docker/"
-cp "$PAPERLESS_ROOT/docker/supervisord.conf" "$PAPERLESS_DIST_APP/docker/"
-
-# try to make the docker build.
-
-cd "$PAPERLESS_DIST_APP"
-
-docker build . -t "jonaswinkler/paperless-ng:$VERSION"
-
-# works. package the app!
-
-cd "$PAPERLESS_DIST"
-
-tar -cJf "paperless-ng-$VERSION.tar.xz" paperless-ng/
-tar -cJf "paperless-ng-$VERSION-dockerfiles.tar.xz" paperless-ng-dockerfiles/

scripts/paperless-consumer.service

@@ -1,10 +1,12 @@
 [Unit]
 Description=Paperless consumer
+Requires=redis.service
 
 [Service]
 User=paperless
 Group=paperless
-ExecStart=/home/paperless/project/virtualenv/bin/python /home/paperless/project/src/manage.py document_consumer
+WorkingDirectory=/opt/paperless/src
+ExecStart=python3 manage.py document_consumer
 
 [Install]
 WantedBy=multi-user.target

scripts/paperless-scheduler.service

@@ -0,0 +1,12 @@
+[Unit]
+Description=Paperless consumer
+Requires=redis.service
+
+[Service]
+User=paperless
+Group=paperless
+WorkingDirectory=/opt/paperless/src
+ExecStart=python3 manage.py qcluster
+
+[Install]
+WantedBy=multi-user.target

scripts/paperless-webserver.service

@@ -2,11 +2,13 @@
 Description=Paperless webserver
 After=network.target
 Wants=network.target
+Requires=redis.service
 
 [Service]
 User=paperless
 Group=paperless
-ExecStart=/home/paperless/project/virtualenv/bin/gunicorn --pythonpath=/home/paperless/project/src paperless.wsgi -w 2
+WorkingDirectory=/opt/paperless/src
+ExecStart=/opt/paperless/.local/bin/gunicorn paperless.wsgi -w 2 -b 0.0.0.0:8000
 
 [Install]
 WantedBy=multi-user.target

scripts/push-release.sh

@@ -1,23 +0,0 @@
-#!/bin/bash
-
-set -e
-
-
-VERSION=$1
-
-if [ -z "$VERSION" ]
-then
-	echo "Need a version string."
-	exit 1
-fi
-
-# source root directory of paperless
-PAPERLESS_ROOT=$(git rev-parse --show-toplevel)
-
-# output directory
-PAPERLESS_DIST="$PAPERLESS_ROOT/dist"
-PAPERLESS_DIST_APP="$PAPERLESS_DIST/paperless-ng"
-
-cd "$PAPERLESS_DIST_APP"
-
-docker push "jonaswinkler/paperless-ng:$VERSION"

scripts/start_services.sh

@@ -1,2 +1,4 @@
 docker run -p 5432:5432 -v paperless_pgdata:/var/lib/postgresql/data -d postgres:13
 docker run -d -p 6379:6379 redis:latest
+docker run -p 3000:3000 -d thecodingmachine/gotenberg
+docker run -p 9998:9998 -d apache/tika

src-ui/angular.json

@@ -13,6 +13,14 @@
 			"root": "",
 			"sourceRoot": "src",
 			"prefix": "app",
+			"i18n": {
+				"sourceLocale": "en-US",
+				"locales": {
+					"de": "src/locale/messages.de.xlf",
+					"nl-NL": "src/locale/messages.nl_NL.xlf",
+					"fr": "src/locale/messages.fr.xlf"
+				}
+			},
 			"architect": {
 				"build": {
 					"builder": "@angular-devkit/build-angular:browser",
@@ -23,15 +31,24 @@
 						"main": "src/main.ts",
 						"polyfills": "src/polyfills.ts",
 						"tsConfig": "tsconfig.app.json",
+						"localize": true,
 						"aot": true,
 						"assets": [
 							"src/favicon.ico",
-							"src/assets"
+							"src/assets",
+							"src/manifest.webmanifest", {
+								"glob": "pdf.worker.min.js",
+								"input": "node_modules/pdfjs-dist/build/",
+								"output": "/assets/js/"
+							}
 						],
 						"styles": [
 							"src/styles.scss"
 						],
-						"scripts": []
+						"scripts": [],
+						"allowedCommonJsDependencies": [
+							"ng2-pdf-viewer"
+						]
 					},
 					"configurations": {
 						"production": {
@@ -41,6 +58,7 @@
 									"with": "src/environments/environment.prod.ts"
 								}
 							],
+							"outputPath": "../src/documents/static/frontend/",
 							"optimization": true,
 							"outputHashing": "none",
 							"sourceMap": false,
@@ -61,13 +79,16 @@
 									"maximumError": "10kb"
 								}
 							]
+						},
+						"en-US": {
+							"localize": ["en-US"]
 						}
 					}
 				},
 				"serve": {
 					"builder": "@angular-devkit/build-angular:dev-server",
 					"options": {
-						"browserTarget": "paperless-ui:build"
+						"browserTarget": "paperless-ui:build:en-US"
 					},
 					"configurations": {
 						"production": {
@@ -90,7 +111,8 @@
 						"karmaConfig": "karma.conf.js",
 						"assets": [
 							"src/favicon.ico",
-							"src/assets"
+							"src/assets",
+							"src/manifest.webmanifest"
 						],
 						"styles": [
 							"src/styles.scss"
@@ -127,4 +149,4 @@
 		}
 	},
 	"defaultProject": "paperless-ui"
-}
+}

src-ui/package-lock.json

@@ -331,6 +331,12 @@
             "ms": "^2.1.1"
           }
         },
+        "ini": {
+          "version": "1.3.5",
+          "resolved": "https://registry.npmjs.org/ini/-/ini-1.3.5.tgz",
+          "integrity": "sha512-RZY5huIKCMRWDUqZlEi72f/lmXKMvuszcMBduliQ3nnWbx9X/ZBQO7DijMEYS9EhHBb2qacRUMtC7svLwe0lcw==",
+          "dev": true
+        },
         "uuid": {
           "version": "8.3.0",
           "resolved": "https://registry.npmjs.org/uuid/-/uuid-8.3.0.tgz",
@@ -2056,6 +2062,14 @@
         "tslib": "^2.0.0"
       }
     },
+    "@ng-select/ng-select": {
+      "version": "5.0.9",
+      "resolved": "https://registry.npmjs.org/@ng-select/ng-select/-/ng-select-5.0.9.tgz",
+      "integrity": "sha512-YZeSAiS8/Nx/eHZJPmOOYL8YmcvSq+dr1P8WIrsKmRA7mueorBpPc5xlUj+nLQbpLtsiQvdWDQspf/ykOvD/lA==",
+      "requires": {
+        "tslib": "^2.0.0"
+      }
+    },
     "@ngtools/webpack": {
       "version": "10.2.0",
       "resolved": "https://registry.npmjs.org/@ngtools/webpack/-/webpack-10.2.0.tgz",
@@ -2170,6 +2184,14 @@
         "pacote": "9.5.12",
         "semver": "7.3.2",
         "semver-intersect": "1.4.0"
+      },
+      "dependencies": {
+        "ini": {
+          "version": "1.3.5",
+          "resolved": "https://registry.npmjs.org/ini/-/ini-1.3.5.tgz",
+          "integrity": "sha512-RZY5huIKCMRWDUqZlEi72f/lmXKMvuszcMBduliQ3nnWbx9X/ZBQO7DijMEYS9EhHBb2qacRUMtC7svLwe0lcw==",
+          "dev": true
+        }
       }
     },
     "@types/glob": {
@@ -2215,6 +2237,11 @@
       "integrity": "sha512-UV1/ZJMC+HcP902wWdpC43cAcGu0IQk/I5bXjP2aSuCjsk3cE74mDvFrLKga7oDC170ugOAYBwfT4DSQW3akDA==",
       "dev": true
     },
+    "@types/pdfjs-dist": {
+      "version": "2.1.7",
+      "resolved": "https://registry.npmjs.org/@types/pdfjs-dist/-/pdfjs-dist-2.1.7.tgz",
+      "integrity": "sha512-nQIwcPUhkAIyn7x9NS0lR/qxYfd5unRtfGkMjvpgF4Sh28IXftRymaNmFKTTdejDNY25NDGSIyjwj/BRwAPexg=="
+    },
     "@types/q": {
       "version": "1.5.4",
       "resolved": "https://registry.npmjs.org/@types/q/-/q-1.5.4.tgz",
@@ -3023,6 +3050,16 @@
       "integrity": "sha512-1Yj8h9Q+QDF5FzhMs/c9+6UntbD5MkRfRwac8DoEm9ZfUBZ7tZ55YcGVAzEe4bXsdQHEk+s9S5wsOKVdZrw0tQ==",
       "dev": true
     },
+    "bindings": {
+      "version": "1.5.0",
+      "resolved": "https://registry.npmjs.org/bindings/-/bindings-1.5.0.tgz",
+      "integrity": "sha512-p2q/t/mhvuOj/UeLlV6566GD/guowlr0hHxClI0W9m7MWYkL1F0hLo+0Aexs9HSPCtR1SXQ0TD3MMKrXZajbiQ==",
+      "dev": true,
+      "optional": true,
+      "requires": {
+        "file-uri-to-path": "1.0.0"
+      }
+    },
     "blob": {
       "version": "0.0.5",
       "resolved": "https://registry.npmjs.org/blob/-/blob-0.0.5.tgz",
@@ -5508,6 +5545,13 @@
         "schema-utils": "^2.6.5"
       }
     },
+    "file-uri-to-path": {
+      "version": "1.0.0",
+      "resolved": "https://registry.npmjs.org/file-uri-to-path/-/file-uri-to-path-1.0.0.tgz",
+      "integrity": "sha512-0Zt+s3L7Vf1biwWZ29aARiVYLx7iMGnEUl9x33fbB/j3jR81u/O2LbqK+Bm1CDSNDKVtJ/YjwY7TUd5SkeLQLw==",
+      "dev": true,
+      "optional": true
+    },
     "fill-range": {
       "version": "7.0.1",
       "resolved": "https://registry.npmjs.org/fill-range/-/fill-range-7.0.1.tgz",
@@ -8208,6 +8252,13 @@
       "integrity": "sha512-nnbWWOkoWyUsTjKrhgD0dcz22mdkSnpYqbEjIm2nhwhuxlSkpywJmBo8h0ZqJdkp73mb90SssHkN4rsRaBAfAA==",
       "dev": true
     },
+    "nan": {
+      "version": "2.14.2",
+      "resolved": "https://registry.npmjs.org/nan/-/nan-2.14.2.tgz",
+      "integrity": "sha512-M2ufzIiINKCuDfBSAUr1vWQ+vuVcA9kqx8JJUsbQi6yf1uGRyb7HfpdfUr5qLXf3B/t8dPvcjhKMmlfnP47EzQ==",
+      "dev": true,
+      "optional": true
+    },
     "nanomatch": {
       "version": "1.2.13",
       "resolved": "https://registry.npmjs.org/nanomatch/-/nanomatch-1.2.13.tgz",
@@ -8260,6 +8311,23 @@
         "moment": "2.18.1"
       }
     },
+    "ng2-pdf-viewer": {
+      "version": "6.3.2",
+      "resolved": "https://registry.npmjs.org/ng2-pdf-viewer/-/ng2-pdf-viewer-6.3.2.tgz",
+      "integrity": "sha512-H2tBhDd+Lq6CUzK2g54HsCcZDR2wTn1sDjYqKY3yF0Ydasl2R5ppCKynZBU/zge4EKvmHglJI120FbQMpJKDYQ==",
+      "requires": {
+        "@types/pdfjs-dist": "^2.1.4",
+        "pdfjs-dist": "^2.4.456",
+        "tslib": "^1.10.0"
+      },
+      "dependencies": {
+        "tslib": {
+          "version": "1.14.1",
+          "resolved": "https://registry.npmjs.org/tslib/-/tslib-1.14.1.tgz",
+          "integrity": "sha512-Xni35NKzjgMrwevysHTCArtLDpPvye8zV/0E4EyYn43P7/7qvQwPh9BGkHewbMulVntbigmcT7rdX3BNo9wRJg=="
+        }
+      }
+    },
     "ngx-cookie-service": {
       "version": "10.1.1",
       "resolved": "https://registry.npmjs.org/ngx-cookie-service/-/ngx-cookie-service-10.1.1.tgz",
@@ -9270,6 +9338,11 @@
         "sha.js": "^2.4.8"
       }
     },
+    "pdfjs-dist": {
+      "version": "2.5.207",
+      "resolved": "https://registry.npmjs.org/pdfjs-dist/-/pdfjs-dist-2.5.207.tgz",
+      "integrity": "sha512-xGDUhnCYPfHy+unMXCLCJtlpZaaZ17Ew3WIL0tnSgKFUZXHAPD49GO9xScyszSsQMoutNDgRb+rfBXIaX/lJbw=="
+    },
     "performance-now": {
       "version": "2.1.0",
       "resolved": "https://registry.npmjs.org/performance-now/-/performance-now-2.1.0.tgz",
@@ -13228,7 +13301,11 @@
           "resolved": "https://registry.npmjs.org/fsevents/-/fsevents-1.2.13.tgz",
           "integrity": "sha512-oWb1Z6mkHIskLzEJ/XWX0srkpkTQ7vaopMQkyaEIoq0fmtFVxOthb8cCxeT+p3ynTdkk/RZwbgG4brR5BeWECw==",
           "dev": true,
-          "optional": true
+          "optional": true,
+          "requires": {
+            "bindings": "^1.5.0",
+            "nan": "^2.12.1"
+          }
         },
         "glob-parent": {
           "version": "3.1.0",
@@ -13832,7 +13909,11 @@
           "resolved": "https://registry.npmjs.org/fsevents/-/fsevents-1.2.13.tgz",
           "integrity": "sha512-oWb1Z6mkHIskLzEJ/XWX0srkpkTQ7vaopMQkyaEIoq0fmtFVxOthb8cCxeT+p3ynTdkk/RZwbgG4brR5BeWECw==",
           "dev": true,
-          "optional": true
+          "optional": true,
+          "requires": {
+            "bindings": "^1.5.0",
+            "nan": "^2.12.1"
+          }
         },
         "glob-parent": {
           "version": "3.1.0",

src-ui/package.json

@@ -21,8 +21,10 @@
     "@angular/platform-browser-dynamic": "~10.1.5",
     "@angular/router": "~10.1.5",
     "@ng-bootstrap/ng-bootstrap": "^8.0.0",
+    "@ng-select/ng-select": "^5.0.9",
     "bootstrap": "^4.5.0",
     "ng-bootstrap": "^1.6.3",
+    "ng2-pdf-viewer": "^6.3.2",
     "ngx-cookie-service": "^10.1.1",
     "ngx-file-drop": "^10.0.0",
     "ngx-infinite-scroll": "^9.1.0",

src-ui/src/app/app.component.ts

@@ -1,4 +1,5 @@
 import { Component } from '@angular/core';
+import { SettingsService } from './services/settings.service';
 
 @Component({
   selector: 'app-root',
@@ -6,9 +7,11 @@ import { Component } from '@angular/core';
   styleUrls: ['./app.component.scss']
 })
 export class AppComponent {
-  
-  constructor () {
+
+  constructor (private settings: SettingsService) {
+    let anyWindow = (window as any)
+    anyWindow.pdfWorkerSrc = '/assets/js/pdf.worker.min.js';
+    this.settings.updateDarkModeSettings()
   }
 
-
 }

src-ui/src/app/app.module.ts

@@ -13,11 +13,10 @@ import { DocumentTypeListComponent } from './components/manage/document-type-lis
 import { LogsComponent } from './components/manage/logs/logs.component';
 import { SettingsComponent } from './components/manage/settings/settings.component';
 import { FormsModule, ReactiveFormsModule } from '@angular/forms';
-import { DatePipe } from '@angular/common';
-import { SafePipe } from './pipes/safe.pipe';
+import { DatePipe, registerLocaleData } from '@angular/common';
 import { NotFoundComponent } from './components/not-found/not-found.component';
 import { CorrespondentListComponent } from './components/manage/correspondent-list/correspondent-list.component';
-import { DeleteDialogComponent } from './components/common/delete-dialog/delete-dialog.component';
+import { ConfirmDialogComponent } from './components/common/confirm-dialog/confirm-dialog.component';
 import { CorrespondentEditDialogComponent } from './components/manage/correspondent-list/correspondent-edit-dialog/correspondent-edit-dialog.component';
 import { TagEditDialogComponent } from './components/manage/tag-list/tag-edit-dialog/tag-edit-dialog.component';
 import { DocumentTypeEditDialogComponent } from './components/manage/document-type-list/document-type-edit-dialog/document-type-edit-dialog.component';
@@ -27,9 +26,13 @@ import { ResultHighlightComponent } from './components/search/result-highlight/r
 import { PageHeaderComponent } from './components/common/page-header/page-header.component';
 import { AppFrameComponent } from './components/app-frame/app-frame.component';
 import { ToastsComponent } from './components/common/toasts/toasts.component';
-import { FilterEditorComponent } from './components/filter-editor/filter-editor.component';
+import { FilterEditorComponent } from './components/document-list/filter-editor/filter-editor.component';
+import { FilterableDropdownComponent } from './components/common/filterable-dropdown/filterable-dropdown.component';
+import { ToggleableDropdownButtonComponent } from './components/common/filterable-dropdown/toggleable-dropdown-button/toggleable-dropdown-button.component';
+import { DateDropdownComponent } from './components/common/date-dropdown/date-dropdown.component';
 import { DocumentCardLargeComponent } from './components/document-list/document-card-large/document-card-large.component';
 import { DocumentCardSmallComponent } from './components/document-list/document-card-small/document-card-small.component';
+import { BulkEditorComponent } from './components/document-list/bulk-editor/bulk-editor.component';
 import { NgxFileDropModule } from 'ngx-file-drop';
 import { TextComponent } from './components/common/input/text/text.component';
 import { SelectComponent } from './components/common/input/select/select.component';
@@ -45,6 +48,26 @@ import { SavedViewWidgetComponent } from './components/dashboard/widgets/saved-v
 import { StatisticsWidgetComponent } from './components/dashboard/widgets/statistics-widget/statistics-widget.component';
 import { UploadFileWidgetComponent } from './components/dashboard/widgets/upload-file-widget/upload-file-widget.component';
 import { WidgetFrameComponent } from './components/dashboard/widgets/widget-frame/widget-frame.component';
+import { PdfViewerModule } from 'ng2-pdf-viewer';
+import { WelcomeWidgetComponent } from './components/dashboard/widgets/welcome-widget/welcome-widget.component';
+import { YesNoPipe } from './pipes/yes-no.pipe';
+import { FileSizePipe } from './pipes/file-size.pipe';
+import { FilterPipe } from './pipes/filter.pipe';
+import { DocumentTitlePipe } from './pipes/document-title.pipe';
+import { MetadataCollapseComponent } from './components/document-detail/metadata-collapse/metadata-collapse.component';
+import { SelectDialogComponent } from './components/common/select-dialog/select-dialog.component';
+import { NgSelectModule } from '@ng-select/ng-select';
+import { NumberComponent } from './components/common/input/number/number.component';
+import { SafePipe } from './pipes/safe.pipe';
+import { CustomDatePipe } from './pipes/custom-date.pipe';
+
+import localeFr from '@angular/common/locales/fr';
+import localeNl from '@angular/common/locales/nl';
+import localeDe from '@angular/common/locales/de';
+
+registerLocaleData(localeFr)
+registerLocaleData(localeNl)
+registerLocaleData(localeDe)
 
 @NgModule({
   declarations: [
@@ -57,10 +80,9 @@ import { WidgetFrameComponent } from './components/dashboard/widgets/widget-fram
     DocumentTypeListComponent,
     LogsComponent,
     SettingsComponent,
-    SafePipe,
     NotFoundComponent,
     CorrespondentEditDialogComponent,
-    DeleteDialogComponent,
+    ConfirmDialogComponent,
     TagEditDialogComponent,
     DocumentTypeEditDialogComponent,
     TagComponent,
@@ -70,8 +92,12 @@ import { WidgetFrameComponent } from './components/dashboard/widgets/widget-fram
     AppFrameComponent,
     ToastsComponent,
     FilterEditorComponent,
+    FilterableDropdownComponent,
+    ToggleableDropdownButtonComponent,
+    DateDropdownComponent,
     DocumentCardLargeComponent,
     DocumentCardSmallComponent,
+    BulkEditorComponent,
     TextComponent,
     SelectComponent,
     CheckComponent,
@@ -82,7 +108,17 @@ import { WidgetFrameComponent } from './components/dashboard/widgets/widget-fram
     SavedViewWidgetComponent,
     StatisticsWidgetComponent,
     UploadFileWidgetComponent,
-    WidgetFrameComponent
+    WidgetFrameComponent,
+    WelcomeWidgetComponent,
+    YesNoPipe,
+    FileSizePipe,
+    FilterPipe,
+    DocumentTitlePipe,
+    MetadataCollapseComponent,
+    SelectDialogComponent,
+    NumberComponent,
+    SafePipe,
+    CustomDatePipe
   ],
   imports: [
     BrowserModule,
@@ -92,7 +128,9 @@ import { WidgetFrameComponent } from './components/dashboard/widgets/widget-fram
     FormsModule,
     ReactiveFormsModule,
     NgxFileDropModule,
-    InfiniteScrollModule
+    InfiniteScrollModule,
+    PdfViewerModule,
+    NgSelectModule
   ],
   providers: [
     DatePipe,
@@ -100,7 +138,9 @@ import { WidgetFrameComponent } from './components/dashboard/widgets/widget-fram
       provide: HTTP_INTERCEPTORS,
       useClass: CsrfInterceptor,
       multi: true
-    }
+    },
+    FilterPipe,
+    DocumentTitlePipe
   ],
   bootstrap: [AppComponent]
 })

src-ui/src/app/components/app-frame/app-frame.component.html

@@ -1,158 +1,177 @@
 <nav class="navbar navbar-dark sticky-top bg-primary flex-md-nowrap p-0 shadow">
-  <span class="navbar-brand col-md-3 col-lg-2 mr-0 px-3" href="#">
-    <img src="assets/logo-dark-notext.svg" height="18px" class="mr-2">
-    Paperless-ng
-  </span>
-  <button class="navbar-toggler position-absolute d-md-none collapsed" type="button" data-toggle="collapse"
+  <button class="navbar-toggler d-md-none collapsed border-0" type="button" data-toggle="collapse"
     data-target="#sidebarMenu" aria-controls="sidebarMenu" aria-expanded="false" aria-label="Toggle navigation"
     (click)="isMenuCollapsed = !isMenuCollapsed">
     <span class="navbar-toggler-icon"></span>
   </button>
-  <form (ngSubmit)="search()" class="w-100 m-1">
-    <input class="form-control form-control-dark" type="text" placeholder="Search" aria-label="Search"
-      [formControl]="searchField" [ngbTypeahead]="searchAutoComplete" (selectItem)="itemSelected($event)">
-  </form>
+  <a class="navbar-brand col-auto col-md-3 col-lg-2 mr-0 px-3 py-3 order-sm-0" routerLink="/dashboard">
+    <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 198.43 238.91" width="1rem" class="mr-2" fill="currentColor">
+      <path d="M194.7,0C164.22,70.94,17.64,79.74,64.55,194.06c.58,1.47-10.85,17-18.47,29.9-1.76-6.45-3.81-13.48-3.52-14.07,38.11-45.14-27.26-70.65-30.78-107.58C-4.64,131.62-10.5,182.92,39,212.53c.3,0,2.64,11.14,3.81,16.71a58.55,58.55,0,0,0-2.93,6.45c-1.17,2.93,7.62,2.64,7.62,3.22.88-.29,21.7-36.93,22.28-37.23C187.67,174.72,208.48,68.6,194.7,0ZM134.61,74.75C79.5,124,70.12,160.64,71.88,178.53,53.41,134.85,107.64,86.77,134.61,74.75ZM28.2,145.11c10.55,9.67,28.14,39.28,13.19,56.57C44.91,193.77,46.08,175.89,28.2,145.11Z" transform="translate(0 0)"/>
+    </svg>
+    <ng-container i18n="app title">Paperless-ng</ng-container>
+  </a>
+  <div class="search-form-container flex-grow-1 py-2 pb-3 pb-sm-2 px-3 pl-md-4 mr-sm-auto order-3 order-sm-1">
+    <form (ngSubmit)="search()" class="form-inline flex-grow-1">
+      <input class="form-control form-control-sm" type="text" placeholder="Search documents" aria-label="Search"
+        [formControl]="searchField" [ngbTypeahead]="searchAutoComplete" (selectItem)="itemSelected($event)" i18n-placeholder>
+      <svg width="1em" height="1em">
+        <use xlink:href="assets/bootstrap-icons.svg#search"/>
+      </svg>
+    </form>
+  </div>
+  <ul ngbNav class="order-sm-3">
+    <li ngbDropdown class="nav-item dropdown">
+      <button class="btn text-light" id="userDropdown" ngbDropdownToggle>
+        <span *ngIf="displayName" class="navbar-text small mr-2 text-light d-none d-sm-inline">
+          {{displayName}}
+        </span>
+        <svg width="1.3em" height="1.3em">
+          <use xlink:href="assets/bootstrap-icons.svg#person-circle"/>
+        </svg>
+      </button>
+      <div ngbDropdownMenu class="dropdown-menu-right shadow mr-2" aria-labelledby="userDropdown">
+        <div *ngIf="displayName" class="d-sm-none">
+          <p class="small mb-0 px-3" i18n>Logged in as {{displayName}}</p>
+          <div class="dropdown-divider"></div>
+        </div>
+        <a ngbDropdownItem class="nav-link" routerLink="settings" (click)="closeMenu()">
+          <svg class="sidebaricon mr-2" fill="currentColor">
+            <use xlink:href="assets/bootstrap-icons.svg#gear"/>
+          </svg><ng-container i18n>Settings</ng-container>
+        </a>
+        <a ngbDropdownItem class="nav-link" href="accounts/logout/">
+          <svg class="sidebaricon mr-2" fill="currentColor">
+            <use xlink:href="assets/bootstrap-icons.svg#door-open"/>
+          </svg><ng-container i18n>Logout</ng-container>
+        </a>
+      </div>
+    </li>
+  </ul>
 </nav>
 
 <div class="container-fluid">
   <div class="row">
     <nav id="sidebarMenu" class="col-md-3 col-lg-2 d-md-block bg-light sidebar collapse" [ngbCollapse]="isMenuCollapsed">
+
+      <div style="position: absolute; bottom: 0; left: 0;" class="text-muted p-1">
+        {{versionString}}
+      </div>
+
       <div class="sidebar-sticky pt-3">
         <ul class="nav flex-column">
           <li class="nav-item">
             <a class="nav-link" routerLink="dashboard" routerLinkActive="active" (click)="closeMenu()">
               <svg class="sidebaricon" fill="currentColor">
                 <use xlink:href="assets/bootstrap-icons.svg#house"/>
-              </svg>
-              Dashboard
+              </svg>&nbsp;<ng-container i18n>Dashboard</ng-container>
             </a>
           </li>
           <li class="nav-item">
             <a class="nav-link" routerLink="documents" routerLinkActive="active" [routerLinkActiveOptions]="{exact: true}" (click)="closeMenu()">
               <svg class="sidebaricon" fill="currentColor">
                 <use xlink:href="assets/bootstrap-icons.svg#files"/>
-              </svg>
-              Documents
+              </svg>&nbsp;<ng-container i18n>Documents</ng-container>
             </a>
           </li>
         </ul>
 
-        <h6 class="sidebar-heading d-flex justify-content-between align-items-center px-3 mt-4 mb-1 text-muted" *ngIf='viewConfigService.getSideBarConfigs().length > 0'>
-          <span>Saved views</span>
+        <h6 class="sidebar-heading d-flex justify-content-between align-items-center px-3 mt-4 mb-1 text-muted" *ngIf='savedViewService.sidebarViews.length > 0'>
+          <ng-container i18n>Saved views</ng-container>
         </h6>
         <ul class="nav flex-column mb-2">
-          <li class="nav-item w-100" *ngFor='let config of viewConfigService.getSideBarConfigs()'>
-            <a class="nav-link text-truncate" routerLink="view/{{config.id}}" routerLinkActive="active" (click)="closeMenu()">
+          <li class="nav-item w-100" *ngFor="let view of savedViewService.sidebarViews">
+            <a class="nav-link text-truncate" routerLink="view/{{view.id}}" routerLinkActive="active" (click)="closeMenu()">
               <svg class="sidebaricon" fill="currentColor">
                 <use xlink:href="assets/bootstrap-icons.svg#funnel"/>
-              </svg>
-              {{config.title}}
+              </svg>&nbsp;{{view.name}}
             </a>
           </li>
         </ul>
 
         <h6 class="sidebar-heading d-flex justify-content-between align-items-center px-3 mt-4 mb-1 text-muted" *ngIf='openDocuments.length > 0'>
-          <span>Open documents</span>
+          <ng-container i18n>Open documents</ng-container>
         </h6>
         <ul class="nav flex-column mb-2">
           <li class="nav-item w-100" *ngFor='let d of openDocuments'>
             <a class="nav-link text-truncate" routerLink="documents/{{d.id}}" routerLinkActive="active" (click)="closeMenu()">
               <svg class="sidebaricon" fill="currentColor">
                 <use xlink:href="assets/bootstrap-icons.svg#file-text"/>
-              </svg>
-              {{d.title}}
+              </svg>&nbsp;{{d.title | documentTitle}}
             </a>
           </li>
           <li class="nav-item w-100" *ngIf="openDocuments.length > 1">
             <a class="nav-link text-truncate" [routerLink]="" (click)="closeAll()">
               <svg class="sidebaricon" fill="currentColor">
                 <use xlink:href="assets/bootstrap-icons.svg#x"/>
-              </svg>
-              Close all
+              </svg>&nbsp;<ng-container i18n>Close all</ng-container>
             </a>
           </li>
         </ul>
 
         <h6 class="sidebar-heading d-flex justify-content-between align-items-center px-3 mt-4 mb-1 text-muted">
-          <span>Manage</span>
+          <ng-container i18n>Manage</ng-container>
         </h6>
         <ul class="nav flex-column mb-2">
           <li class="nav-item">
             <a class="nav-link" routerLink="correspondents" routerLinkActive="active" (click)="closeMenu()">
               <svg class="sidebaricon" fill="currentColor">
                 <use xlink:href="assets/bootstrap-icons.svg#person"/>
-              </svg>
-              Correspondents
+              </svg>&nbsp;<ng-container i18n>Correspondents</ng-container>
             </a>
           </li>
           <li class="nav-item">
             <a class="nav-link" routerLink="tags" routerLinkActive="active" (click)="closeMenu()">
               <svg class="sidebaricon" fill="currentColor">
                 <use xlink:href="assets/bootstrap-icons.svg#tags"/>
-              </svg>
-              Tags
+              </svg>&nbsp;<ng-container i18n>Tags</ng-container>
             </a>
           </li>
           <li class="nav-item">
             <a class="nav-link" routerLink="documenttypes" routerLinkActive="active" (click)="closeMenu()">
               <svg class="sidebaricon" fill="currentColor">
                 <use xlink:href="assets/bootstrap-icons.svg#hash"/>
-              </svg>
-              Document types
+              </svg>&nbsp;<ng-container i18n>Document types</ng-container>
             </a>
           </li>
           <li class="nav-item">
             <a class="nav-link" routerLink="logs" routerLinkActive="active" (click)="closeMenu()">
               <svg class="sidebaricon" fill="currentColor">
                 <use xlink:href="assets/bootstrap-icons.svg#text-left"/>
-              </svg>
-              Logs
+              </svg>&nbsp;<ng-container i18n>Logs</ng-container>
             </a>
           </li>
           <li class="nav-item">
             <a class="nav-link" routerLink="settings" routerLinkActive="active" (click)="closeMenu()">
               <svg class="sidebaricon" fill="currentColor">
                 <use xlink:href="assets/bootstrap-icons.svg#gear"/>
-              </svg>
-              Settings
+              </svg>&nbsp;<ng-container i18n>Settings</ng-container>
             </a>
           </li>
           <li class="nav-item">
             <a class="nav-link" href="admin/">
               <svg class="sidebaricon" fill="currentColor">
                 <use xlink:href="assets/bootstrap-icons.svg#toggles"/>
-              </svg>
-              Admin
+              </svg>&nbsp;<ng-container i18n>Admin</ng-container>
             </a>
           </li>
         </ul>
 
         <h6 class="sidebar-heading d-flex justify-content-between align-items-center px-3 mt-4 mb-1 text-muted">
-          <span>Misc</span>
+          <ng-container i18n>Misc</ng-container>
         </h6>
         <ul class="nav flex-column mb-2">
           <li class="nav-item">
-            <a class="nav-link" href="https://paperless-ng.readthedocs.io/en/latest/">
+            <a class="nav-link" target="_blank" rel="noopener noreferrer" href="https://paperless-ng.readthedocs.io/en/latest/">
               <svg class="sidebaricon" fill="currentColor">
                 <use xlink:href="assets/bootstrap-icons.svg#question-circle"/>
-              </svg>
-              Documentation
+              </svg>&nbsp;<ng-container i18n>Documentation</ng-container>
             </a>
           </li>
           <li class="nav-item">
-            <a class="nav-link" href="https://github.com/jonaswinkler/paperless-ng">
+            <a class="nav-link" target="_blank" rel="noopener noreferrer" href="https://github.com/jonaswinkler/paperless-ng">
               <svg class="sidebaricon" fill="currentColor">
                 <use xlink:href="assets/bootstrap-icons.svg#link"/>
-              </svg>
-              GitHub
-            </a>
-          </li>
-          <li class="nav-item">
-            <a class="nav-link" href="accounts/logout/">
-              <svg class="sidebaricon" fill="currentColor">
-                <use xlink:href="assets/bootstrap-icons.svg#door-open"/>
-              </svg>
-              Logout
+              </svg>&nbsp;<ng-container i18n>GitHub</ng-container>
             </a>
           </li>
         </ul>

src-ui/src/app/components/app-frame/app-frame.component.scss

@@ -1,36 +1,30 @@
-
 @import "/src/theme";
-
-  /*
+/*
  * Sidebar
  */
-
- .sidebar {
+.sidebar {
   position: fixed;
   top: 0;
   bottom: 0;
   left: 0;
   z-index: 100; /* Behind the navbar */
-  padding: 48px 0 0; /* Height of navbar */
+  padding: 50px 0 0; /* Height of navbar */
   box-shadow: inset -1px 0 0 rgba(0, 0, 0, .1);
 }
-
 @media (max-width: 767.98px) {
   .sidebar {
-    top: 3rem;
+    top: 3.5rem;
   }
 }
 
 .sidebar-sticky {
   position: relative;
   top: 0;
-  /* height: calc(100vh - 48px); */
   height: 100%;
-  padding-top: .5rem;
+  padding-top: 0.5rem;
   overflow-x: hidden;
   overflow-y: auto; /* Scrollable contents if viewport is shorter than content. */
 }
-
 @supports ((position: -webkit-sticky) or (position: sticky)) {
   .sidebar-sticky {
     position: -webkit-sticky;
@@ -50,38 +44,88 @@
 
 .sidebar .nav-link.active {
   color: $primary;
+  font-weight: bold;
 }
 
-.sidebar .nav-link:hover .sidebaricon,
-.sidebar .nav-link.active .sidebaricon {
+.sidebar .nav-link.active .sidebaricon,
+.sidebar .nav-link:hover .sidebaricon {
   color: inherit;
 }
 
 .sidebar-heading {
-  font-size: .75rem;
+  font-size: 0.75rem;
   text-transform: uppercase;
 }
 
-
 /*
  * Navbar
  */
 
- .navbar-brand {
-  padding-top: .75rem;
-  padding-bottom: .75rem;
+.navbar-brand {
+  padding-top: 0.75rem;
+  padding-bottom: 0.75rem;
   font-size: 1rem;
-  background-color: rgba(0, 0, 0, .25);
-  box-shadow: inset -1px 0 0 rgba(0, 0, 0, .25);
 }
 
-.navbar .navbar-toggler {
-  top: .25rem;
-  right: 1rem;
+.dropdown.show .dropdown-toggle,
+.dropdown-toggle:hover {
+  opacity: 0.7;
 }
 
-.navbar .form-control {
-  padding: .75rem 1rem;
-  border-width: 0;
-  border-radius: 0;
+.dropdown-toggle::after {
+  margin-left: 0.4em;
+  vertical-align: 0.155em;
+}
+
+.navbar .dropdown-menu {
+  font-size: 0.875rem; // body size
+
+  a svg {
+    opacity: 0.6;
+  }
+}
+
+.navbar .search-form-container {
+  max-width: 550px;
+
+  form {
+    position: relative;
+  }
+
+  svg {
+    position: absolute;
+    left: 0.6rem;
+    color: rgba(255, 255, 255, 0.6);
+  }
+
+  &:focus-within {
+    svg {
+      display: none;
+    }
+
+    .form-control::placeholder {
+      color: rgba(255, 255, 255, 0);
+    }
+  }
+
+  .form-control {
+    color: rgba(255, 255, 255, 0.3);
+    background-color: rgba(0, 0, 0, 0.15);
+    padding-left: 1.8rem;
+    border-color: rgba(255, 255, 255, 0.2);
+    transition: all .3s ease, padding-left 0s ease, background-color 0s ease; // Safari requires all
+    max-width: 600px;
+    min-width: 300px; // 1/2 max
+
+    &::placeholder {
+      color: rgba(255, 255, 255, 0.4);
+    }
+
+    &:focus {
+      background-color: #fff;
+      color: #212529;
+      flex-grow: 1;
+      padding-left: 0.5rem;
+    }
+  }
 }

src-ui/src/app/components/app-frame/app-frame.component.ts

@@ -5,10 +5,12 @@ import { from, Observable, Subscription } from 'rxjs';
 import { debounceTime, distinctUntilChanged, map, switchMap } from 'rxjs/operators';
 import { PaperlessDocument } from 'src/app/data/paperless-document';
 import { OpenDocumentsService } from 'src/app/services/open-documents.service';
+import { SavedViewService } from 'src/app/services/rest/saved-view.service';
 import { SearchService } from 'src/app/services/rest/search.service';
-import { SavedViewConfigService } from 'src/app/services/saved-view-config.service';
+import { environment } from 'src/environments/environment';
 import { DocumentDetailComponent } from '../document-detail/document-detail.component';
-  
+import { Meta } from '@angular/platform-browser';
+
 @Component({
   selector: 'app-app-frame',
   templateUrl: './app-frame.component.html',
@@ -21,10 +23,14 @@ export class AppFrameComponent implements OnInit, OnDestroy {
     private activatedRoute: ActivatedRoute,
     private openDocumentsService: OpenDocumentsService,
     private searchService: SearchService,
-    public viewConfigService: SavedViewConfigService
+    public savedViewService: SavedViewService,
+    private meta: Meta
     ) {
+      
   }
 
+  versionString = `${environment.appTitle} ${environment.version}`
+
   isMenuCollapsed: boolean = true
 
   closeMenu() {
@@ -52,7 +58,7 @@ export class AppFrameComponent implements OnInit, OnDestroy {
         term.length < 2 ? from([[]]) : this.searchService.autocomplete(term)
       )
     )
-  
+
   itemSelected(event) {
     event.preventDefault()
     let currentSearch: string = this.searchField.value
@@ -90,7 +96,22 @@ export class AppFrameComponent implements OnInit, OnDestroy {
   }
 
   ngOnDestroy() {
-    this.openDocumentsSubscription.unsubscribe()
+    if (this.openDocumentsSubscription) {
+      this.openDocumentsSubscription.unsubscribe()
+    }
+  }
+
+  get displayName() {
+    // TODO: taken from dashboard component, is this the best way to pass around username?
+    let tagFullName = this.meta.getTag('name=full_name')
+    let tagUsername = this.meta.getTag('name=username')
+    if (tagFullName && tagFullName.content) {
+      return tagFullName.content
+    } else if (tagUsername && tagUsername.content) {
+      return tagUsername.content
+    } else {
+      return null
+    }
   }
 
 }

src-ui/src/app/components/common/confirm-dialog/confirm-dialog.component.html

@@ -0,0 +1,17 @@
+    <div class="modal-header">
+      <h4 class="modal-title" id="modal-basic-title">{{title}}</h4>
+      <button type="button" class="close" aria-label="Close" (click)="cancelClicked()">
+        <span aria-hidden="true">&times;</span>
+      </button>
+    </div>
+    <div class="modal-body">
+      <p *ngIf="messageBold"><b>{{messageBold}}</b></p>
+      <p *ngIf="message">{{message}}</p>
+    </div>
+    <div class="modal-footer">
+      <button type="button" class="btn btn-outline-dark" (click)="cancelClicked()" [disabled]="!buttonsEnabled" i18n>Cancel</button>
+      <button type="button" class="btn" [class]="btnClass" (click)="confirmClicked.emit()" [disabled]="!confirmButtonEnabled || !buttonsEnabled">
+        {{btnCaption}}
+        <span *ngIf="!confirmButtonEnabled"> ({{seconds}})</span>
+      </button>
+    </div>

src-ui/src/app/components/common/confirm-dialog/confirm-dialog.component.spec.ts

@@ -0,0 +1,25 @@
+import { ComponentFixture, TestBed } from '@angular/core/testing';
+
+import { ConfirmDialogComponent } from './confirm-dialog.component';
+
+describe('ConfirmDialogComponent', () => {
+  let component: ConfirmDialogComponent;
+  let fixture: ComponentFixture<ConfirmDialogComponent>;
+
+  beforeEach(async () => {
+    await TestBed.configureTestingModule({
+      declarations: [ ConfirmDialogComponent ]
+    })
+    .compileComponents();
+  });
+
+  beforeEach(() => {
+    fixture = TestBed.createComponent(ConfirmDialogComponent);
+    component = fixture.componentInstance;
+    fixture.detectChanges();
+  });
+
+  it('should create', () => {
+    expect(component).toBeTruthy();
+  });
+});

src-ui/src/app/components/common/confirm-dialog/confirm-dialog.component.ts

@@ -0,0 +1,55 @@
+import { Component, EventEmitter, Input, OnInit, Output } from '@angular/core';
+import { NgbActiveModal } from '@ng-bootstrap/ng-bootstrap';
+
+@Component({
+  selector: 'app-confirm-dialog',
+  templateUrl: './confirm-dialog.component.html',
+  styleUrls: ['./confirm-dialog.component.scss']
+})
+export class ConfirmDialogComponent implements OnInit {
+
+  constructor(public activeModal: NgbActiveModal) { }
+
+  @Output()
+  public confirmClicked = new EventEmitter()
+
+  @Input()
+  title = $localize`Confirmation`
+
+  @Input()
+  messageBold
+
+  @Input()
+  message
+
+  @Input()
+  btnClass = "btn-primary"
+
+  @Input()
+  btnCaption = $localize`Confirm`
+
+  @Input()
+  buttonsEnabled = true
+  
+  confirmButtonEnabled = true
+  seconds = 0
+
+  delayConfirm(seconds: number) {
+    this.confirmButtonEnabled = false
+    this.seconds = seconds
+    setTimeout(() => {
+      if (this.seconds <= 1) {
+        this.confirmButtonEnabled = true
+      } else {
+        this.delayConfirm(seconds - 1)
+      }
+    }, 1000)
+  }
+
+  ngOnInit(): void {
+  }
+
+  cancelClicked() {
+    this.activeModal.close()
+  }
+}

src-ui/src/app/components/common/date-dropdown/date-dropdown.component.html

@@ -0,0 +1,44 @@
+  <div class="btn-group w-100" ngbDropdown role="group">
+  <button class="btn btn-sm" id="dropdown{{title}}" ngbDropdownToggle [ngClass]="dateBefore || dateAfter ? 'btn-primary' : 'btn-outline-primary'">
+    {{title}}
+  </button>
+  <div class="dropdown-menu date-dropdown shadow pt-0" ngbDropdownMenu attr.aria-labelledby="dropdown{{title}}">
+    <div class="list-group list-group-flush">
+        <button *ngFor="let qf of quickFilters" class="list-group-item small list-goup list-group-item-action d-flex p-2 pl-3" role="menuitem" (click)="setDateQuickFilter(qf.id)">
+          {{qf.name}}
+        </button>
+        <div class="list-group-item d-flex flex-column align-items-start" role="menuitem">
+
+          <div class="mb-2 d-flex flex-row w-100 justify-content-between small">
+            <div i18n>After</div>
+            <a *ngIf="dateAfter" class="btn btn-link p-0 m-0" (click)="clearAfter()">
+              <svg width="0.8em" height="0.8em" viewBox="0 0 16 16" class="bi bi-x" fill="currentColor" xmlns="http://www.w3.org/2000/svg">
+                <path fill-rule="evenodd" d="M4.646 4.646a.5.5 0 0 1 .708 0L8 7.293l2.646-2.647a.5.5 0 0 1 .708.708L8.707 8l2.647 2.646a.5.5 0 0 1-.708.708L8 8.707l-2.646 2.647a.5.5 0 0 1-.708-.708L7.293 8 4.646 5.354a.5.5 0 0 1 0-.708z" />
+              </svg>
+              <small i18n>Clear</small>
+            </a>
+          </div>
+
+          <div class="input-group input-group-sm">
+            <input type="date" class="form-control" id="date_after" [(ngModel)]="dateAfter" (change)="onChangeDebounce()">
+          </div>
+        </div>
+        <div class="list-group-item d-flex flex-column align-items-start" role="menuitem">
+
+          <div class="mb-2 d-flex flex-row w-100 justify-content-between small">
+            <div i18n>Before</div>
+            <a *ngIf="dateBefore" class="btn btn-link p-0 m-0" (click)="clearBefore()">
+              <svg width="0.8em" height="0.8em" viewBox="0 0 16 16" class="bi bi-x" fill="currentColor" xmlns="http://www.w3.org/2000/svg">
+                <path fill-rule="evenodd" d="M4.646 4.646a.5.5 0 0 1 .708 0L8 7.293l2.646-2.647a.5.5 0 0 1 .708.708L8.707 8l2.647 2.646a.5.5 0 0 1-.708.708L8 8.707l-2.646 2.647a.5.5 0 0 1-.708-.708L7.293 8 4.646 5.354a.5.5 0 0 1 0-.708z" />
+              </svg>
+              <small i18n>Clear</small>
+            </a>
+          </div>
+
+          <div class="input-group input-group-sm">
+            <input type="date" class="form-control" id="date_before" [(ngModel)]="dateBefore" (change)="onChangeDebounce()">
+          </div>
+        </div>
+    </div>
+  </div>
+</div>

src-ui/src/app/components/common/date-dropdown/date-dropdown.component.scss

@@ -0,0 +1,7 @@
+.date-dropdown {
+  min-width: 250px;
+
+  .btn-link {
+    line-height: 1;
+  }
+}

src-ui/src/app/components/common/date-dropdown/date-dropdown.component.spec.ts

@@ -1,20 +1,20 @@
 import { ComponentFixture, TestBed } from '@angular/core/testing';
 
-import { DeleteDialogComponent } from './delete-dialog.component';
+import { DateDropdownComponent } from './date-dropdown.component';
 
-describe('DeleteDialogComponent', () => {
-  let component: DeleteDialogComponent;
-  let fixture: ComponentFixture<DeleteDialogComponent>;
+describe('DateDropdownComponent', () => {
+  let component: DateDropdownComponent;
+  let fixture: ComponentFixture<DateDropdownComponent>;
 
   beforeEach(async () => {
     await TestBed.configureTestingModule({
-      declarations: [ DeleteDialogComponent ]
+      declarations: [ DateDropdownComponent ]
     })
     .compileComponents();
   });
 
   beforeEach(() => {
-    fixture = TestBed.createComponent(DeleteDialogComponent);
+    fixture = TestBed.createComponent(DateDropdownComponent);
     component = fixture.componentInstance;
     fixture.detectChanges();
   });

src-ui/src/app/components/common/date-dropdown/date-dropdown.component.ts

@@ -0,0 +1,111 @@
+import { formatDate } from '@angular/common';
+import { Component, EventEmitter, Input, Output, OnInit, OnDestroy } from '@angular/core';
+import { Subject, Subscription } from 'rxjs';
+import { debounceTime, distinctUntilChanged } from 'rxjs/operators';
+
+export interface DateSelection {
+  before?: string
+  after?: string
+}
+
+const LAST_7_DAYS = 0
+const LAST_MONTH = 1
+const LAST_3_MONTHS = 2
+const LAST_YEAR = 3
+
+@Component({
+  selector: 'app-date-dropdown',
+  templateUrl: './date-dropdown.component.html',
+  styleUrls: ['./date-dropdown.component.scss']
+})
+export class DateDropdownComponent implements OnInit, OnDestroy {
+
+  quickFilters = [
+    {id: LAST_7_DAYS, name: $localize`Last 7 days`},
+    {id: LAST_MONTH, name: $localize`Last month`},
+    {id: LAST_3_MONTHS, name: $localize`Last 3 months`},
+    {id: LAST_YEAR, name: $localize`Last year`}
+  ]
+
+  @Input()
+  dateBefore: string
+
+  @Output()
+  dateBeforeChange = new EventEmitter<string>()
+
+  @Input()
+  dateAfter: string
+
+  @Output()
+  dateAfterChange = new EventEmitter<string>()
+
+  @Input()
+  title: string
+
+  @Output()
+  datesSet = new EventEmitter<DateSelection>()
+
+  private datesSetDebounce$ = new Subject()
+
+  private sub: Subscription
+
+  ngOnInit() {
+    this.sub = this.datesSetDebounce$.pipe(
+      debounceTime(400)
+    ).subscribe(() => {
+      this.onChange()
+    })
+  }
+
+  ngOnDestroy() {
+    if (this.sub) {
+      this.sub.unsubscribe()
+    }
+  }
+
+  setDateQuickFilter(qf: number) {
+    this.dateBefore = null
+    let date = new Date()
+    switch (qf) {
+      case LAST_7_DAYS:
+        date.setDate(date.getDate() - 7)
+        break;
+
+      case LAST_MONTH:
+        date.setMonth(date.getMonth() - 1)
+        break;
+
+      case LAST_3_MONTHS:
+        date.setMonth(date.getMonth() - 3)
+        break
+
+      case LAST_YEAR:
+        date.setFullYear(date.getFullYear() - 1)
+        break
+
+      }
+    this.dateAfter = formatDate(date, 'yyyy-MM-dd', "en-us", "UTC")
+    this.onChange()
+  }
+
+  onChange() {
+    this.dateAfterChange.emit(this.dateAfter)
+    this.dateBeforeChange.emit(this.dateBefore)
+    this.datesSet.emit({after: this.dateAfter, before: this.dateBefore})
+  }
+
+  onChangeDebounce() {
+    this.datesSetDebounce$.next({after: this.dateAfter, before: this.dateBefore})
+  }
+
+  clearBefore() {
+    this.dateBefore = null
+    this.onChange()
+  }
+
+  clearAfter() {
+    this.dateAfter = null
+    this.onChange()
+  }
+
+}

src-ui/src/app/components/common/delete-dialog/delete-dialog.component.html

@@ -1,14 +0,0 @@
-    <div class="modal-header">
-      <h4 class="modal-title" id="modal-basic-title">{{title}}</h4>
-      <button type="button" class="close" aria-label="Close" (click)="cancelClicked()">
-        <span aria-hidden="true">&times;</span>
-      </button>
-    </div>
-    <div class="modal-body">
-      <p><b>{{message}}</b></p>
-      <p *ngIf="message2">{{message2}}</p>
-    </div>
-    <div class="modal-footer">
-      <button type="button" class="btn btn-outline-dark" (click)="cancelClicked()">Cancel</button>
-      <button type="button" class="btn btn-danger" (click)="deleteClicked.emit()">Delete</button>
-    </div>

src-ui/src/app/components/common/delete-dialog/delete-dialog.component.ts

@@ -1,31 +0,0 @@
-import { Component, EventEmitter, Input, OnInit, Output } from '@angular/core';
-import { NgbActiveModal } from '@ng-bootstrap/ng-bootstrap';
-
-@Component({
-  selector: 'app-delete-dialog',
-  templateUrl: './delete-dialog.component.html',
-  styleUrls: ['./delete-dialog.component.scss']
-})
-export class DeleteDialogComponent implements OnInit {
-
-  constructor(public activeModal: NgbActiveModal) { }
-
-  @Output()
-  public deleteClicked = new EventEmitter()
-
-  @Input()
-  title = "Delete confirmation"
-
-  @Input()
-  message = "Do you really want to delete this?"
-
-  @Input()
-  message2
-
-  ngOnInit(): void {
-  }
-
-  cancelClicked() {
-    this.activeModal.close()
-  }
-}

src-ui/src/app/components/common/edit-dialog/edit-dialog.component.ts

@@ -2,10 +2,11 @@ import { Directive, EventEmitter, Input, OnInit, Output } from '@angular/core';
 import { FormGroup } from '@angular/forms';
 import { NgbActiveModal } from '@ng-bootstrap/ng-bootstrap';
 import { Observable } from 'rxjs';
-import { MATCHING_ALGORITHMS } from 'src/app/data/matching-model';
+import { map } from 'rxjs/operators';
+import { MATCHING_ALGORITHMS, MATCH_AUTO } from 'src/app/data/matching-model';
 import { ObjectWithId } from 'src/app/data/object-with-id';
 import { AbstractPaperlessService } from 'src/app/services/rest/abstract-paperless-service';
-import { Toast, ToastService } from 'src/app/services/toast.service';
+import { ToastService } from 'src/app/services/toast.service';
 
 @Directive()
 export abstract class EditDialogComponent<T extends ObjectWithId> implements OnInit {
@@ -13,8 +14,7 @@ export abstract class EditDialogComponent<T extends ObjectWithId> implements OnI
   constructor(
     private service: AbstractPaperlessService<T>,
     private activeModal: NgbActiveModal,
-    private toastService: ToastService,
-    private entityName: string) { }
+    private toastService: ToastService) { }
 
   @Input()
   dialogMode: string = 'create'
@@ -25,6 +25,12 @@ export abstract class EditDialogComponent<T extends ObjectWithId> implements OnI
   @Output()
   success = new EventEmitter()
 
+  networkActive = false
+
+  closeEnabled = false
+
+  error = null
+
   abstract getForm(): FormGroup
 
   objectForm: FormGroup = this.getForm()
@@ -33,14 +39,31 @@ export abstract class EditDialogComponent<T extends ObjectWithId> implements OnI
     if (this.object != null) {
       this.objectForm.patchValue(this.object)
     }
+
+    // wait to enable close button so it doesnt steal focus from input since its the first clickable element in the DOM
+    setTimeout(() => {
+      this.closeEnabled = true
+    });
+  }
+
+  getCreateTitle() {
+    return $localize`Create new item`
+  }
+
+  getEditTitle() {
+    return $localize`Edit item`
+  }
+
+  getSaveErrorMessage(error: string) {
+    return $localize`Could not save element: ${error}`
   }
 
   getTitle() {
     switch (this.dialogMode) {
       case 'create':
-        return "Create new " + this.entityName
+        return this.getCreateTitle()
       case 'edit':
-        return "Edit " + this.entityName
+        return this.getEditTitle()
       default:
         break;
     }
@@ -50,6 +73,10 @@ export abstract class EditDialogComponent<T extends ObjectWithId> implements OnI
     return MATCHING_ALGORITHMS
   }
 
+  get patternRequired(): boolean {
+    return this.objectForm?.value.matching_algorithm !== MATCH_AUTO
+  }
+
   save() {
     var newObject = Object.assign(Object.assign({}, this.object), this.objectForm.value)
     var serverResponse: Observable<T>
@@ -62,11 +89,13 @@ export abstract class EditDialogComponent<T extends ObjectWithId> implements OnI
       default:
         break;
     }
+    this.networkActive = true
     serverResponse.subscribe(result => {
       this.activeModal.close()
       this.success.emit(result)
     }, error => {
-      this.toastService.showToast(Toast.makeError(`Could not save ${this.entityName}: ${error.error.name}`))
+      this.error = error.error
+      this.networkActive = false
     })
   }
 

src-ui/src/app/components/common/filterable-dropdown/filterable-dropdown.component.html

@@ -0,0 +1,33 @@
+<div class="btn-group w-100" ngbDropdown role="group" (openChange)="dropdownOpenChange($event)" #dropdown="ngbDropdown">
+  <button class="btn btn-sm" id="dropdown{{title}}" ngbDropdownToggle [ngClass]="!editing && selectionModel.selectionSize() > 0 ? 'btn-primary' : 'btn-outline-primary'">
+    <svg class="toolbaricon" fill="currentColor">
+      <use attr.xlink:href="assets/bootstrap-icons.svg#{{icon}}" />
+    </svg>
+    <div class="d-none d-sm-inline">&nbsp;{{title}}</div>
+    <ng-container *ngIf="!editing && selectionModel.selectionSize() > 0">
+      <div class="badge bg-secondary text-light rounded-pill badge-corner">
+        {{selectionModel.selectionSize()}}
+      </div>
+    </ng-container>
+  </button>
+  <div class="dropdown-menu py-0 shadow" ngbDropdownMenu attr.aria-labelledby="dropdown{{title}}">
+    <div class="list-group list-group-flush">
+      <div class="list-group-item">
+        <div class="input-group input-group-sm">
+          <input class="form-control" type="text" [(ngModel)]="filterText" [placeholder]="filterPlaceholder" (keyup.enter)="listFilterEnter()" #listFilterTextInput>
+        </div>
+      </div>
+      <div *ngIf="selectionModel.items" class="items">
+        <ng-container *ngFor="let item of selectionModel.itemsSorted | filter: filterText">
+          <app-toggleable-dropdown-button *ngIf="allowSelectNone || item.id" [item]="item" [state]="selectionModel.get(item.id)" (toggle)="selectionModel.toggle(item.id)"></app-toggleable-dropdown-button>
+        </ng-container>
+      </div>
+      <button *ngIf="editing" class="list-group-item list-group-item-action bg-light" (click)="applyClicked()" [disabled]="!selectionModel.isDirty()">
+        <small class="ml-1" [ngClass]="{'font-weight-bold': selectionModel.isDirty()}" i18n>Apply</small>
+        <svg width="1.5em" height="1em" viewBox="0 0 16 16" fill="currentColor">
+          <use xlink:href="assets/bootstrap-icons.svg#arrow-right" />
+        </svg>
+      </button>
+    </div>
+  </div>
+</div>

src-ui/src/app/components/common/filterable-dropdown/filterable-dropdown.component.scss

@@ -0,0 +1,14 @@
+.badge-corner {
+  position: absolute;
+  top: -8px;
+  right: -8px;
+}
+
+.dropdown-menu {
+  min-width: 250px;
+
+  .items {
+    max-height: 400px;
+    overflow-y: scroll;
+  }
+}

src-ui/src/app/components/common/filterable-dropdown/filterable-dropdown.component.spec.ts

@@ -0,0 +1,25 @@
+import { ComponentFixture, TestBed } from '@angular/core/testing';
+
+import { FilterableDropodownComponent } from './filterable-dropdown.component';
+
+describe('FilterableDropodownComponent', () => {
+  let component: FilterableDropodownComponent;
+  let fixture: ComponentFixture<FilterableDropodownComponent>;
+
+  beforeEach(async () => {
+    await TestBed.configureTestingModule({
+      declarations: [ FilterableDropodownComponent ]
+    })
+    .compileComponents();
+  });
+
+  beforeEach(() => {
+    fixture = TestBed.createComponent(FilterableDropodownComponent);
+    component = fixture.componentInstance;
+    fixture.detectChanges();
+  });
+
+  it('should create', () => {
+    expect(component).toBeTruthy();
+  });
+});

src-ui/src/app/components/common/filterable-dropdown/filterable-dropdown.component.ts

@@ -0,0 +1,272 @@
+import { Component, EventEmitter, Input, Output, ElementRef, ViewChild } from '@angular/core';
+import { FilterPipe } from  'src/app/pipes/filter.pipe';
+import { NgbDropdown } from '@ng-bootstrap/ng-bootstrap'
+import { ToggleableItemState } from './toggleable-dropdown-button/toggleable-dropdown-button.component';
+import { MatchingModel } from 'src/app/data/matching-model';
+import { Subject } from 'rxjs';
+
+export interface ChangedItems {
+  itemsToAdd: MatchingModel[],
+  itemsToRemove: MatchingModel[]
+}
+
+export class FilterableDropdownSelectionModel {
+
+  changed = new Subject<FilterableDropdownSelectionModel>()
+
+  multiple = false
+
+  items: MatchingModel[] = []
+
+  get itemsSorted(): MatchingModel[] {
+    // TODO: this is getting called very often
+    return this.items.sort((a,b) => {
+      if (a.id == null && b.id != null) {
+        return -1
+      } else if (a.id != null && b.id == null) {
+        return 1
+      } else if (this.getNonTemporary(a.id) == ToggleableItemState.NotSelected && this.getNonTemporary(b.id) != ToggleableItemState.NotSelected) {
+        return 1
+      } else if (this.getNonTemporary(a.id) != ToggleableItemState.NotSelected && this.getNonTemporary(b.id) == ToggleableItemState.NotSelected) {
+        return -1
+      } else {
+        return a.name.localeCompare(b.name)
+      }
+    })
+  }
+
+  private selectionStates = new Map<number, ToggleableItemState>()
+
+  private temporarySelectionStates = new Map<number, ToggleableItemState>()
+
+  getSelectedItems() {
+    return this.items.filter(i => this.temporarySelectionStates.get(i.id) == ToggleableItemState.Selected)
+  }
+
+  set(id: number, state: ToggleableItemState, fireEvent = true) {
+    if (state == ToggleableItemState.NotSelected) {
+      this.temporarySelectionStates.delete(id)
+    } else {
+      this.temporarySelectionStates.set(id, state)
+    }
+    if (fireEvent) {
+      this.changed.next(this)
+    }
+  }
+
+  toggle(id: number, fireEvent = true) {
+    let state = this.temporarySelectionStates.get(id)
+    if (state == null || state != ToggleableItemState.Selected) {
+      this.temporarySelectionStates.set(id, ToggleableItemState.Selected)
+    } else if (state == ToggleableItemState.Selected) {
+      this.temporarySelectionStates.delete(id)
+    }
+
+    if (!this.multiple) {
+      for (let key of this.temporarySelectionStates.keys()) {
+        if (key != id) {
+          this.temporarySelectionStates.delete(key)
+        }
+      }
+    }
+
+    if (!id) {
+      for (let key of this.temporarySelectionStates.keys()) {
+        if (key) {
+          this.temporarySelectionStates.delete(key)
+        }
+      }
+    } else {
+      this.temporarySelectionStates.delete(null)
+    }
+
+    if (fireEvent) {
+      this.changed.next(this)
+    }
+    
+  }
+
+  private getNonTemporary(id: number) {
+    return this.selectionStates.get(id) || ToggleableItemState.NotSelected
+  }
+
+  get(id: number) {
+    return this.temporarySelectionStates.get(id) || ToggleableItemState.NotSelected
+  }
+
+  selectionSize() {
+    return this.getSelectedItems().length
+  }
+
+  clear(fireEvent = true) {
+    this.temporarySelectionStates.clear()
+    if (fireEvent) {
+      this.changed.next(this)
+    }
+  }
+
+  isDirty() {
+    if (!Array.from(this.temporarySelectionStates.keys()).every(id => this.temporarySelectionStates.get(id) == this.selectionStates.get(id))) {
+      return true
+    } else if (!Array.from(this.selectionStates.keys()).every(id => this.selectionStates.get(id) == this.temporarySelectionStates.get(id))) {
+      return true
+    } else {
+      return false
+    }
+  }
+
+  isNoneSelected() {
+    return this.selectionSize() == 1 && this.get(null) == ToggleableItemState.Selected
+  }
+
+  init(map) {
+    this.temporarySelectionStates = map
+    this.apply()
+  }
+
+  apply() {
+    this.selectionStates.clear()
+    this.temporarySelectionStates.forEach((value, key) => {
+      this.selectionStates.set(key, value)
+    })
+  }
+
+  reset() {
+    this.temporarySelectionStates.clear()
+    this.selectionStates.forEach((value, key) => {
+      this.temporarySelectionStates.set(key, value)
+    })
+  }
+
+  diff(): ChangedItems {
+    return {
+      itemsToAdd: this.items.filter(item => this.temporarySelectionStates.get(item.id) == ToggleableItemState.Selected && this.selectionStates.get(item.id) != ToggleableItemState.Selected),
+      itemsToRemove: this.items.filter(item => !this.temporarySelectionStates.has(item.id) && this.selectionStates.has(item.id)),
+    }
+  }
+}
+
+@Component({
+  selector: 'app-filterable-dropdown',
+  templateUrl: './filterable-dropdown.component.html',
+  styleUrls: ['./filterable-dropdown.component.scss']
+})
+export class FilterableDropdownComponent {
+
+  @ViewChild('listFilterTextInput') listFilterTextInput: ElementRef
+  @ViewChild('dropdown') dropdown: NgbDropdown
+
+  filterText: string
+
+  @Input()
+  set items(items: MatchingModel[]) {
+    if (items) {
+      this._selectionModel.items = Array.from(items)
+      this._selectionModel.items.unshift({
+        name: $localize`:Filter drop down element to filter for documents with no correspondent/type/tag assigned:Not assigned`,
+        id: null
+      })
+    }
+  }
+
+  get items(): MatchingModel[] {
+    return this._selectionModel.items
+  }
+
+  _selectionModel = new FilterableDropdownSelectionModel()
+
+  @Input()
+  set selectionModel(model: FilterableDropdownSelectionModel) {
+    if (this.selectionModel) {
+      this.selectionModel.changed.complete()
+      model.items = this.selectionModel.items
+      model.multiple = this.selectionModel.multiple
+    }
+    model.changed.subscribe(updatedModel => {
+      this.selectionModelChange.next(updatedModel)
+    })
+    this._selectionModel = model
+  }
+
+  get selectionModel(): FilterableDropdownSelectionModel {
+    return this._selectionModel
+  }
+
+  @Output()
+  selectionModelChange = new EventEmitter<FilterableDropdownSelectionModel>()
+
+  @Input()
+  set multiple(value: boolean) {
+    this.selectionModel.multiple = value
+  }
+
+  get multiple() {
+    return this.selectionModel.multiple
+  }
+
+  @Input()
+  title: string
+
+  @Input()
+  filterPlaceholder: string = ""
+
+  @Input()
+  icon: string
+
+  @Input()
+  allowSelectNone: boolean = false
+
+  @Input()
+  editing = false
+
+  @Input()
+  applyOnClose = false
+
+  @Output()
+  apply = new EventEmitter<ChangedItems>()
+
+  @Output()
+  open = new EventEmitter()
+
+  constructor(private filterPipe: FilterPipe) {
+    this.selectionModel = new FilterableDropdownSelectionModel()
+  }
+
+  applyClicked() {
+    if (this.selectionModel.isDirty()) {
+      this.dropdown.close()
+      if (!this.applyOnClose) {
+        this.apply.emit(this.selectionModel.diff())
+      }
+    }
+  }
+
+  dropdownOpenChange(open: boolean): void {
+    if (open) {
+      setTimeout(() => {
+        this.listFilterTextInput.nativeElement.focus();
+      }, 0)
+      if (this.editing) {
+        this.selectionModel.reset()
+      }
+      this.open.next()
+    } else {
+      this.filterText = ''
+      if (this.applyOnClose && this.selectionModel.isDirty()) {
+        this.apply.emit(this.selectionModel.diff())
+      }
+    }
+  }
+
+  listFilterEnter(): void {
+    let filtered = this.filterPipe.transform(this.items, this.filterText)
+    if (filtered.length == 1) {
+      this.selectionModel.toggle(filtered[0].id)
+      if (this.editing) {
+        this.applyClicked()
+      } else {
+        this.dropdown.close()
+      }
+    }
+  }
+}

src-ui/src/app/components/common/filterable-dropdown/toggleable-dropdown-button/toggleable-dropdown-button.component.html

@@ -0,0 +1,20 @@
+<button class="list-group-item list-group-item-action d-flex align-items-center p-2 border-top-0 border-left-0 border-right-0 border-bottom" role="menuitem" (click)="toggleItem()">
+  <div class="selected-icon mr-1">
+    <ng-container *ngIf="isChecked()">
+      <svg xmlns="http://www.w3.org/2000/svg" width="1em" height="1em" fill="currentColor" class="bi bi-check" viewBox="0 0 16 16">
+        <path d="M10.97 4.97a.75.75 0 0 1 1.07 1.05l-3.99 4.99a.75.75 0 0 1-1.08.02L4.324 8.384a.75.75 0 1 1 1.06-1.06l2.094 2.093 3.473-4.425a.267.267 0 0 1 .02-.022z"/>
+      </svg>
+    </ng-container>
+    <ng-container *ngIf="isPartiallyChecked()">
+      <svg xmlns="http://www.w3.org/2000/svg" width="1em" height="1em" fill="currentColor" class="bi bi-dash" viewBox="0 0 16 16">
+        <path d="M4 8a.5.5 0 0 1 .5-.5h7a.5.5 0 0 1 0 1h-7A.5.5 0 0 1 4 8z"/>
+      </svg>
+    </ng-container>
+    
+  </div>
+  <div class="mr-1">
+    <app-tag *ngIf="isTag; else displayName" [tag]="item" [clickable]="true" linkTitle="Filter by tag"></app-tag>
+    <ng-template #displayName><small>{{item.name}}</small></ng-template>
+  </div>
+  <div class="badge badge-light rounded-pill ml-auto mr-1">{{item.document_count}}</div>
+</button>

src-ui/src/app/components/common/filterable-dropdown/toggleable-dropdown-button/toggleable-dropdown-button.component.scss

@@ -0,0 +1,4 @@
+.selected-icon {
+  min-width: 1em;
+  min-height: 1em;
+}

src-ui/src/app/components/common/filterable-dropdown/toggleable-dropdown-button/toggleable-dropdown-button.component.spec.ts

@@ -0,0 +1,25 @@
+import { ComponentFixture, TestBed } from '@angular/core/testing';
+
+import { ToggleableDropdownButtonComponent } from './toggleable-dropdown-button.component';
+
+describe('ToggleableDropdownButtonComponent', () => {
+  let component: ToggleableDropdownButtonComponent;
+  let fixture: ComponentFixture<ToggleableDropdownButtonComponent>;
+
+  beforeEach(async () => {
+    await TestBed.configureTestingModule({
+      declarations: [ ToggleableDropdownButtonComponent ]
+    })
+    .compileComponents();
+  });
+
+  beforeEach(() => {
+    fixture = TestBed.createComponent(ToggleableDropdownButtonComponent);
+    component = fixture.componentInstance;
+    fixture.detectChanges();
+  });
+
+  it('should create', () => {
+    expect(component).toBeTruthy();
+  });
+});

src-ui/src/app/components/common/filterable-dropdown/toggleable-dropdown-button/toggleable-dropdown-button.component.ts

@@ -0,0 +1,51 @@
+import { Component, EventEmitter, Input, Output, OnInit } from '@angular/core';
+import { MatchingModel } from 'src/app/data/matching-model';
+
+export interface ToggleableItem {
+  item: MatchingModel,
+  state: ToggleableItemState,
+  count: number
+}
+
+export enum ToggleableItemState {
+  NotSelected = 0,
+  Selected = 1,
+  PartiallySelected = 2
+}
+
+@Component({
+  selector: 'app-toggleable-dropdown-button',
+  templateUrl: './toggleable-dropdown-button.component.html',
+  styleUrls: ['./toggleable-dropdown-button.component.scss']
+})
+export class ToggleableDropdownButtonComponent {
+
+  @Input()
+  item: MatchingModel
+
+  @Input()
+  state: ToggleableItemState
+
+  @Input()
+  count: number
+
+  @Output()
+  toggle = new EventEmitter()
+
+  get isTag(): boolean {
+    return 'is_inbox_tag' in this.item
+  }
+
+  toggleItem(): void {
+    this.toggle.emit()
+  }
+
+  isChecked() {
+    return this.state == ToggleableItemState.Selected
+  }
+
+  isPartiallyChecked() {
+    return this.state == ToggleableItemState.PartiallySelected
+  }
+
+}

src-ui/src/app/components/common/input/abstract-input.ts

@@ -1,10 +1,13 @@
-import { Component, Directive, forwardRef, Input, OnInit } from '@angular/core';
-import { ControlValueAccessor, NG_VALUE_ACCESSOR } from '@angular/forms';
+import { Directive, ElementRef, Input, OnInit, ViewChild } from '@angular/core';
+import { ControlValueAccessor } from '@angular/forms';
 import { v4 as uuidv4 } from 'uuid';
 
 @Directive()
 export class AbstractInputComponent<T> implements OnInit, ControlValueAccessor {
 
+  @ViewChild("inputField")
+  inputField: ElementRef
+
   constructor() { }
 
   onChange = (newValue: T) => {};
@@ -24,12 +27,21 @@ export class AbstractInputComponent<T> implements OnInit, ControlValueAccessor {
     this.disabled = isDisabled;
   }
 
+  focus() {
+    if (this.inputField && this.inputField.nativeElement) {
+      this.inputField.nativeElement.focus()
+    }
+  }
+
   @Input()
   title: string
 
   @Input()
   disabled = false;
 
+  @Input()
+  error: string
+
   value: T
 
   ngOnInit(): void {

src-ui/src/app/components/common/input/date-time/date-time.component.html

@@ -3,11 +3,10 @@
       <label for="created_date">{{titleDate}}</label>
       <input type="date" class="form-control" id="created_date" [(ngModel)]="dateValue" (change)="dateOrTimeChanged()">
   </div>
-  <div class="form-group col">
+  <div class="form-group col" *ngIf="titleTime">
       <label for="created_time">{{titleTime}}</label>
       <input type="time" class="form-control" id="created_time" [(ngModel)]="timeValue" (change)="dateOrTimeChanged()">
   </div>
-
 </div>
 
 

src-ui/src/app/components/common/input/date-time/date-time.component.ts

@@ -1,7 +1,6 @@
 import { formatDate } from '@angular/common';
 import { Component, forwardRef, Input, OnInit } from '@angular/core';
 import { ControlValueAccessor, NG_VALUE_ACCESSOR } from '@angular/forms';
-import { AbstractInputComponent } from '../abstract-input';
 
 @Component({
   providers: [{
@@ -40,7 +39,7 @@ export class DateTimeComponent implements OnInit,ControlValueAccessor  {
   titleDate: string = "Date"
 
   @Input()
-  titleTime: string = "Time"
+  titleTime: string
 
   @Input()
   disabled: boolean = false

src-ui/src/app/components/common/input/number/number.component.html

@@ -0,0 +1,14 @@
+<div class="form-group">
+  <label [for]="inputId">{{title}}</label>
+  <div class="input-group" [class.is-invalid]="error">
+    <input type="number" class="form-control" [id]="inputId" [(ngModel)]="value" (change)="onChange(value)" [class.is-invalid]="error">
+    <div class="input-group-append">
+      <button class="btn btn-outline-secondary" type="button" id="button-addon1" (click)="nextAsn()" [disabled]="value">+1</button>
+    </div>
+  </div>
+  <div class="invalid-feedback">
+    {{error}}
+  </div>
+  <small *ngIf="hint" class="form-text text-muted">{{hint}}</small>
+
+</div>

src-ui/src/app/components/common/input/number/number.component.spec.ts

@@ -0,0 +1,25 @@
+import { ComponentFixture, TestBed } from '@angular/core/testing';
+
+import { NumberComponent } from './number.component';
+
+describe('NumberComponent', () => {
+  let component: NumberComponent;
+  let fixture: ComponentFixture<NumberComponent>;
+
+  beforeEach(async () => {
+    await TestBed.configureTestingModule({
+      declarations: [ NumberComponent ]
+    })
+    .compileComponents();
+  });
+
+  beforeEach(() => {
+    fixture = TestBed.createComponent(NumberComponent);
+    component = fixture.componentInstance;
+    fixture.detectChanges();
+  });
+
+  it('should create', () => {
+    expect(component).toBeTruthy();
+  });
+});

src-ui/src/app/components/common/input/number/number.component.ts

@@ -0,0 +1,39 @@
+import { Component, forwardRef } from '@angular/core';
+import { NG_VALUE_ACCESSOR } from '@angular/forms';
+import { FILTER_ASN_ISNULL } from 'src/app/data/filter-rule-type';
+import { DocumentService } from 'src/app/services/rest/document.service';
+import { AbstractInputComponent } from '../abstract-input';
+
+@Component({
+  providers: [{
+    provide: NG_VALUE_ACCESSOR,
+    useExisting: forwardRef(() => NumberComponent),
+    multi: true
+  }],
+  selector: 'app-input-number',
+  templateUrl: './number.component.html',
+  styleUrls: ['./number.component.scss']
+})
+export class NumberComponent extends AbstractInputComponent<number> {
+
+  constructor(private documentService: DocumentService) {
+    super()
+  }
+
+  nextAsn() {
+    if (this.value) {
+      return
+    }
+    this.documentService.listFiltered(1, 1, "archive_serial_number", true, [{rule_type: FILTER_ASN_ISNULL, value: "false"}]).subscribe(
+      results => {
+        if (results.count > 0) {
+          this.value = results.results[0].archive_serial_number + 1
+        } else {
+          this.value = 1
+        }
+        this.onChange(this.value)
+      }
+    )
+  }
+
+}

src-ui/src/app/components/common/input/select/select.component.html

@@ -1,11 +1,18 @@
-<div class="form-group">
+<div class="form-group paperless-input-select">
   <label [for]="inputId">{{title}}</label>
   <div [class.input-group]="showPlusButton()">
-    <select class="form-control" [id]="inputId" [(ngModel)]="value" (change)="onChange(value)" (blur)="onTouched()"
-      [disabled]="disabled" [style.color]="textColor" [style.background]="backgroundColor">
-      <option *ngIf="allowNull" [ngValue]="null" class="form-control">---</option>
-      <option *ngFor="let i of items" [ngValue]="i.id" class="form-control">{{i.name}}</option>
-    </select>
+    <ng-select name="inputId" [(ngModel)]="value"
+      [disabled]="disabled"
+      [style.color]="textColor"
+      [style.background]="backgroundColor"
+      [clearable]="allowNull"
+      [items]="items"
+      bindLabel="name"
+      bindValue="id"
+      (change)="onChange(value)"
+      (blur)="onTouched()">
+    </ng-select>
+
     <div *ngIf="showPlusButton()" class="input-group-append">
       <button class="btn btn-outline-secondary" type="button" (click)="createNew.emit()">
         <svg class="buttonicon" fill="currentColor">
@@ -15,4 +22,4 @@
     </div>
   </div>
   <small *ngIf="hint" class="form-text text-muted">{{hint}}</small>
-</div>
+</div>

src-ui/src/app/components/common/input/select/select.component.scss

@@ -0,0 +1 @@
+// styles for ng-select child are in styles.scss

src-ui/src/app/components/common/input/select/select.component.ts

@@ -1,4 +1,4 @@
-import { Component, EventEmitter, forwardRef, Input, OnInit, Output } from '@angular/core';
+import { Component, EventEmitter, forwardRef, Input, Output } from '@angular/core';
 import { NG_VALUE_ACCESSOR } from '@angular/forms';
 import { AbstractInputComponent } from '../abstract-input';
 

src-ui/src/app/components/common/input/tags/tags.component.html

@@ -1,30 +1,43 @@
-<div class="form-group">
-  <label for="exampleFormControlTextarea1">Tags</label>
+<div class="form-group paperless-input-select paperless-input-tags">
+  <label for="tags" i18n>Tags</label>
 
-  <div class="input-group">
-    <div class="form-control tags-form-control" id="tags">
-      <app-tag class="mr-2" *ngFor="let id of displayValue" [tag]="getTag(id)" (click)="removeTag(id)"></app-tag>
-    </div>
+  <div class="input-group flex-nowrap">
+    <ng-select name="tags" [items]="tags" bindLabel="name" bindValue="id" [(ngModel)]="displayValue"
+      [multiple]="true"
+      [closeOnSelect]="false"
+      [clearSearchOnAdd]="true"
+      [disabled]="disabled"
+      [hideSelected]="true"
+      (change)="ngSelectChange()">
 
-    <div class="input-group-append" ngbDropdown placement="top-right">
-      <button class="btn btn-outline-secondary" type="button" ngbDropdownToggle></button>
-      <div ngbDropdownMenu class="scrollable-menu">
-        <button type="button" *ngFor="let tag of tags" ngbDropdownItem (click)="addTag(tag.id)">
-          <app-tag [tag]="tag"></app-tag>
-        </button>
-      </div>
-    </div>
+      <ng-template ng-label-tmp let-item="item">
+        <span class="tag-wrap tag-wrap-delete" (click)="removeTag(item.id)">
+          <svg width="1.2em" height="1em" viewBox="0 0 16 16" fill="currentColor" xmlns="http://www.w3.org/2000/svg">
+            <use xlink:href="assets/bootstrap-icons.svg#x"/>
+          </svg>
+          <app-tag style="background-color: none;" [tag]="getTag(item.id)"></app-tag>
+        </span>
+      </ng-template>
+      <ng-template ng-option-tmp let-item="item" let-index="index" let-search="searchTerm">
+        <div class="tag-wrap">
+          <div class="selected-icon d-inline-block mr-1">
+            <svg *ngIf="displayValue.includes(item.id)" width="1em" height="1em" viewBox="0 0 16 16" fill="currentColor" xmlns="http://www.w3.org/2000/svg">
+              <use xlink:href="assets/bootstrap-icons.svg#check"/>
+            </svg>
+          </div>
+          <app-tag class="mr-2" [tag]="getTag(item.id)"></app-tag>
+        </div>
+      </ng-template>
+    </ng-select>
 
     <div class="input-group-append">
-
       <button class="btn btn-outline-secondary" type="button" (click)="createTag()">
         <svg class="buttonicon" fill="currentColor">
           <use xlink:href="assets/bootstrap-icons.svg#plus" />
         </svg>
       </button>
     </div>
-
   </div>
   <small class="form-text text-muted" *ngIf="hint">{{hint}}</small>
 
-</div>
+</div>

src-ui/src/app/components/common/input/tags/tags.component.scss

@@ -1,10 +1,12 @@
-.tags-form-control {
-  height: auto;
+.selected-icon {
+  min-width: 1em;
+  min-height: 1em;
 }
 
+.tag-wrap {
+  font-size: 1rem;
+}
 
-.scrollable-menu {
-  height: auto;
-  max-height: 300px;
-  overflow-x: hidden;
-}
+.tag-wrap-delete {
+  cursor: pointer;
+}