👷 add ingest-spacy base image

.github/workflows/docker.yml → .github/workflows/docker-base.yml

@@ -1,4 +1,4 @@
-name: Build ingest-file
+name: Build ingest-file-base
 
 on:
   workflow_dispatch: {}

.github/workflows/docker-spacy.yml

@@ -0,0 +1,50 @@
+name: Build ingest-file-spacy
+
+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-spacy
+          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: .
+          file: Dockerfile.spacy
+          # 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.spacy

@@ -0,0 +1,27 @@
+FROM ghcr.io/investigativedata/ingest-file-base
+ENV DEBIAN_FRONTEND noninteractive
+
+LABEL org.opencontainers.image.title "Base image with spacy models for FollowTheMoney File Ingestors"
+LABEL org.opencontainers.image.licenses MIT
+LABEL org.opencontainers.image.source https://github.com/investigativedata/ingest-file-spacy
+
+# Install spaCy models
+RUN pip3 install --no-cache-dir spacy
+
+RUN python3 -m spacy download en_core_web_sm \
+    && python3 -m spacy download de_core_news_sm \
+    && python3 -m spacy download fr_core_news_sm \
+    && python3 -m spacy download es_core_news_sm
+RUN python3 -m spacy download ru_core_news_sm \
+    && python3 -m spacy download pt_core_news_sm \
+    && python3 -m spacy download ro_core_news_sm \
+    && python3 -m spacy download mk_core_news_sm
+RUN python3 -m spacy download el_core_news_sm \
+    && python3 -m spacy download pl_core_news_sm \
+    && python3 -m spacy download it_core_news_sm \
+    && python3 -m spacy download lt_core_news_sm \
+    && python3 -m spacy download nl_core_news_sm \
+    && python3 -m spacy download nb_core_news_sm \
+    && python3 -m spacy download da_core_news_sm
+# RUN python3 -m spacy download zh_core_web_sm
+