🎉

.github/workflows/docker.yml

@@ -0,0 +1,49 @@
+name: Build ingest-file
+
+on:
+  workflow_dispatch: {}
+  push:
+    paths:
+      - Dockerfile
+      - .github/workflows/docker.yml
+
+permissions:
+  packages: write
+
+jobs:
+  docker:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v2
+      - name: Docker meta
+        id: meta
+        uses: docker/metadata-action@v4
+        with:
+          images: ghcr.io/investigativedata/ingest-file-base
+          tags: |
+            type=ref,event=branch
+            type=semver,pattern={{version}}
+            type=sha
+            type=raw,value=latest
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v2
+        with:
+          install: true
+      - name: Login to GitHub Container Registry
+        uses: docker/login-action@v2
+        with:
+          registry: ghcr.io
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+      - name: Build and push release
+        uses: docker/build-push-action@v3
+        with:
+          context: .
+          # platforms: linux/amd64,linux/arm64
+          push: true
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}
+          cache-from: type=gha
+          cache-to: type=gha,mode=max

Dockerfile

@@ -0,0 +1,125 @@
+FROM python:3.11-slim
+ENV DEBIAN_FRONTEND noninteractive
+
+LABEL org.opencontainers.image.title "Base image for FollowTheMoney File Ingestors"
+LABEL org.opencontainers.image.licenses AGPL3
+LABEL org.opencontainers.image.source https://github.com/investigativedata/ingest-file-base
+
+# Enable non-free archive for `unrar`.
+RUN echo "deb http://http.us.debian.org/debian bookworm non-free" >/etc/apt/sources.list.d/nonfree.list
+RUN apt-get -qq -y update \
+    && apt-get -qq -y install build-essential locales ca-certificates \
+    # python deps (mostly to install their dependencies)
+    python3-pip python3-dev python3-pil \
+    # tesseract
+    tesseract-ocr libtesseract-dev libleptonica-dev pkg-config\
+    # libraries
+    libxslt1-dev libpq-dev libldap2-dev libsasl2-dev \
+    zlib1g-dev libicu-dev libxml2-dev \
+    # package tools
+    unrar p7zip-full \
+    # audio & video metadata
+    libmediainfo-dev \
+    # image processing, djvu
+    imagemagick-common imagemagick mdbtools djvulibre-bin \
+    libtiff5-dev libjpeg-dev libfreetype6-dev libwebp-dev \
+    libtiff-tools ghostscript librsvg2-bin jbig2dec \
+    pst-utils \
+    ### tesseract
+    tesseract-ocr-eng \
+    tesseract-ocr-swa \
+    tesseract-ocr-swe \
+    # tesseract-ocr-tam \
+    # tesseract-ocr-tel \
+    tesseract-ocr-fil \
+    # tesseract-ocr-tha \
+    tesseract-ocr-tur \
+    tesseract-ocr-ukr \
+    # tesseract-ocr-vie \
+    tesseract-ocr-nld \
+    tesseract-ocr-nor \
+    tesseract-ocr-pol \
+    tesseract-ocr-por \
+    tesseract-ocr-ron \
+    tesseract-ocr-rus \
+    tesseract-ocr-slk \
+    tesseract-ocr-slv \
+    tesseract-ocr-spa \
+    # tesseract-ocr-spa_old \
+    tesseract-ocr-sqi \
+    tesseract-ocr-srp \
+    tesseract-ocr-ind \
+    tesseract-ocr-isl \
+    tesseract-ocr-ita \
+    # tesseract-ocr-ita_old \
+    # tesseract-ocr-jpn \
+    tesseract-ocr-kan \
+    tesseract-ocr-kat \
+    # tesseract-ocr-kor \
+    tesseract-ocr-khm  \
+    tesseract-ocr-lav \
+    tesseract-ocr-lit \
+    # tesseract-ocr-mal \
+    tesseract-ocr-mkd \
+    tesseract-ocr-mya \
+    tesseract-ocr-mlt \
+    tesseract-ocr-msa \
+    tesseract-ocr-est \
+    # tesseract-ocr-eus \
+    tesseract-ocr-fin \
+    tesseract-ocr-fra \
+    tesseract-ocr-frk \
+    # tesseract-ocr-frm \
+    # tesseract-ocr-glg \
+    # tesseract-ocr-grc \
+    tesseract-ocr-heb \
+    tesseract-ocr-hin \
+    tesseract-ocr-hrv \
+    tesseract-ocr-hye \
+    tesseract-ocr-hun \
+    # tesseract-ocr-ben \
+    tesseract-ocr-bul \
+    tesseract-ocr-cat \
+    tesseract-ocr-ces \
+    tesseract-ocr-nep \
+    # tesseract-ocr-chi_sim \
+    # tesseract-ocr-chi_tra \
+    # tesseract-ocr-chr \
+    tesseract-ocr-dan \
+    tesseract-ocr-deu \
+    tesseract-ocr-ell \
+    # tesseract-ocr-enm \
+    # tesseract-ocr-epo \
+    # tesseract-ocr-equ \
+    tesseract-ocr-afr \
+    tesseract-ocr-ara \
+    tesseract-ocr-aze \
+    tesseract-ocr-bel \
+    tesseract-ocr-uzb \
+    ### pdf convert: libreoffice + a bunch of fonts
+    libreoffice fonts-opensymbol hyphen-fr hyphen-de \
+    hyphen-en-us hyphen-it hyphen-ru fonts-dejavu fonts-dejavu-core fonts-dejavu-extra \
+    fonts-droid-fallback fonts-dustin fonts-f500 fonts-fanwood fonts-freefont-ttf \
+    fonts-liberation fonts-lmodern fonts-lyx fonts-sil-gentium fonts-texgyre \
+    fonts-tlwg-purisa \
+    ###
+    && apt-get -qq -y autoremove \
+    && apt-get clean \
+    && rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/* \
+    && localedef -i en_US -c -f UTF-8 -A /usr/share/locale/locale.alias en_US.UTF-8
+
+# Set up the locale and make sure the system uses unicode for the file system.
+ENV LANG='en_US.UTF-8' \
+    TZ='UTC' \
+    OMP_THREAD_LIMIT='1' \
+    OPENBLAS_NUM_THREADS='1'
+
+RUN groupadd -g 1000 -r app \
+    && useradd -m -u 1000 -s /bin/false -g app app
+
+# Download the ftm-typepredict model
+RUN mkdir /models/ && \
+    curl -o "/models/model_type_prediction.ftz" "https://public.data.occrp.org/develop/models/types/type-08012020-7a69d1b.ftz"
+
+RUN pip3 install --no-cache-dir --prefer-binary --upgrade pip
+RUN pip3 install --no-cache-dir --prefer-binary --upgrade setuptools wheel