Merge pull request #26 from nlnwa/feat/solrwayback-5

Upgrade Solrwayback to version 5.x

.github/dependabot.yaml

@@ -0,0 +1,21 @@
+version: 2
+updates:
+    - package-ecosystem: "docker"
+      directory: "/"
+      schedule:
+          interval: "weekly"
+      labels:
+          - "dependencies"
+      commit-message:
+          prefix: "build"
+          include: "scope"
+
+    - package-ecosystem: "github-actions"
+      directory: "/"
+      schedule:
+          interval: "weekly"
+      labels:
+          - "dependencies"
+      commit-message:
+          prefix: "build"
+          include: "scope"

.github/workflows/main.yml

@@ -1,7 +1,6 @@
 name: Test release
 
-on:
-  push:
+on: push
 
 env:
   REGISTRY: ghcr.io
@@ -15,20 +14,19 @@ jobs:
       packages: write
     strategy:
       matrix:
-        image-type: [solr, solrwayback, warc-indexer]
+        image: [solrwayback, warc-indexer]
     steps:
       - name: Code checkout
         uses: actions/checkout@v3
-        with:
-          lfs: true
+
       - name: Set up Docker Buildx
         uses: docker/setup-buildx-action@v2
 
       - name: Extract metadata (tags, labels, version) for Docker
         id: meta
         uses: docker/metadata-action@v4
         with:
-          images: ${{ env.REGISTRY }}/${{ github.repository_owner }}/${{ matrix.image-type }}
+          images: ${{ env.REGISTRY }}/${{ github.repository_owner }}/${{ matrix.image }}
           tags: |
             type=semver,pattern={{version}}
             type=ref,event=branch
@@ -40,10 +38,4 @@ jobs:
           push: false
           tags: ${{ steps.meta.outputs.tags }}
           labels: ${{ steps.meta.outputs.labels }}
-          file: Dockerfile.${{ matrix.image-type }}
-          build-args: |
-            SOLRWAYBACK_VERSION=4.4.2
-            SOLR_VERSION=7.7.3
-            SOLRWAYBACK_TOMCAT_VERSION=8.5.60
-            TOMCAT_TAG=8.5-jdk8-temurin-jammy
-            ECLIPSE_TEMURIN_TAG=8-jre
+          file: Dockerfile.${{ matrix.image }}

.github/workflows/release.yml

@@ -19,20 +19,19 @@ jobs:
       packages: write
     strategy:
       matrix:
-        image-type: [solr, solrwayback, warc-indexer]
+        image: [solrwayback, warc-indexer]
     steps:
       - name: Code checkout
         uses: actions/checkout@v3
-        with:
-          lfs: true
+
       - name: Set up Docker Buildx
         uses: docker/setup-buildx-action@v2
 
       - name: Extract metadata (tags, labels, version) for Docker
         id: meta
         uses: docker/metadata-action@v4
         with:
-          images: ${{ env.REGISTRY }}/${{ github.repository_owner }}/${{ matrix.image-type }}
+          images: ${{ env.REGISTRY }}/${{ github.repository_owner }}/${{ matrix.image }}
           tags: |
             type=semver,pattern={{version}}
             type=ref,event=branch
@@ -52,10 +51,4 @@ jobs:
           push: true
           tags: ${{ steps.meta.outputs.tags }}
           labels: ${{ steps.meta.outputs.labels }}
-          file: Dockerfile.${{ matrix.image-type }}
-          build-args: |
-            SOLRWAYBACK_VERSION=4.4.2
-            SOLR_VERSION=7.7.3
-            SOLRWAYBACK_TOMCAT_VERSION=8.5.60
-            TOMCAT_TAG=8.5-jdk8-temurin-jammy
-            ECLIPSE_TEMURIN_TAG=8-jre
+          file: Dockerfile.${{ matrix.image }}

Dockerfile.solrwayback

@@ -1,51 +1,52 @@
-# This dockerfile configures a vanilla tomcat container
-# with solrwayback installed and configured with properties
-# from solrwayback bundle.
+# This dockerfile builds a tomcat container including the webapps
+# from the solrwayback bundle.
 #
-# See https://hub.docker.com/_/tomcat for details on how
-# to configure tomcat.
+# See https://hub.docker.com/_/tomcat for details on how to configure tomcat.
 
-ARG SOLRWAYBACK_VERSION=4.4.2
-ARG SOLRWAYBACK_TOMCAT_VERSION=8.5.60
-ARG TOMCAT_TAG=8.5-jdk8-temurin-jammy
+ARG SOLRWAYBACK_VERSION=5.1.0
+ARG SOLRWAYBACK_TOMCAT_VERSION=9
+ARG TOMCAT_TAG=9-jre17-temurin-jammy
 
 FROM ubuntu:22.04 as solrwayback-bundle
 
 ARG SOLRWAYBACK_VERSION
 ARG SOLRWAYBACK_TOMCAT_VERSION
-ARG SOLRWAYBACK_VERSION
 
-RUN apt-get update \
-    && apt-get install --quiet --assume-yes wget unzip python3
+RUN apt-get update && apt-get install -y \
+    unzip \
+    wget
 
 WORKDIR /build
-COPY fetch_solrwayback_bundle.py .
 
-RUN python3 fetch_solrwayback_bundle.py \
-    --solrwayback-version ${SOLRWAYBACK_VERSION} \
-    --destination /app
-RUN unzip /app/solrwayback_package_${SOLRWAYBACK_VERSION}/apache-tomcat-${SOLRWAYBACK_TOMCAT_VERSION}/webapps/solrwayback.war \
-    -d /app/solrwayback/
+RUN wget -q https://github.com/netarchivesuite/solrwayback/releases/download/${SOLRWAYBACK_VERSION}/solrwayback_package_${SOLRWAYBACK_VERSION}.zip
+RUN unzip solrwayback_package_${SOLRWAYBACK_VERSION}.zip \
+&& mkdir /webapps \
+&& unzip -d /webapps/solrwayback solrwayback_package_${SOLRWAYBACK_VERSION}_MASTER/tomcat-${SOLRWAYBACK_TOMCAT_VERSION}/webapps/solrwayback.war \
+&& cp solrwayback_package_${SOLRWAYBACK_VERSION}_MASTER/tomcat-${SOLRWAYBACK_TOMCAT_VERSION}/webapps/ROOT.war /webapps/ROOT.war
 
-FROM tomcat:${TOMCAT_TAG}
 
-ARG SOLRWAYBACK_TOMCAT_VERSION
-ARG SOLRWAYBACK_VERSION
+FROM tomcat:${TOMCAT_TAG}
 
-# TODO: install solrwayback dependencies such as ffmpeg, imagemagick, tesseract-ocr, chromium-browser, etc.
+# This is not necessary for solrwayback to work.
+# It is only necessary if you want to use the page preview feature.
+# It increases the size of the image by about 200MB.
+RUN apt-get update && apt-get install -y \
+    chromium-browser \
+    chromium-codecs-ffmpeg \
+    && rm -rf /var/lib/apt/lists/*
 
 # CATALINA_HOME is the folder where catalina is installed.
 # The main component of tomcat is called catalina.
 # CATALINA_HOME is set by the tomcat image.
 
-# Copy the extracted solrwayback.war file and ROOT.war to the webapps folder of tomcat.
+# Copy the extracted solrwayback.war file
+# We use the extracted solrwayback.war to be able to customize the web
+# application (favicon, etc.) at runtime (using overlays).
 COPY --from=solrwayback-bundle \
-    /app/solrwayback/ \
+    /webapps/solrwayback \
     ${CATALINA_HOME}/webapps/solrwayback
 
+# Copy ROOT.war to the webapps folder of tomcat.
 COPY --from=solrwayback-bundle \
-    /app/solrwayback_package_${SOLRWAYBACK_VERSION}/apache-tomcat-${SOLRWAYBACK_TOMCAT_VERSION}/webapps/ROOT.war \
+    /webapps/ROOT.war \
     ${CATALINA_HOME}/webapps/ROOT.war
-
-# Set URL icon for the web application
-COPY favicon.ico ${CATALINA_HOME}/webapps/solrwayback/

Dockerfile.warc-indexer

@@ -1,25 +1,26 @@
-# This Dockerfile creates a vanilla java container
-# with warc-indexer from solrwayback bundle.
+# This Dockerfile creates a vanilla java container with warc-indexer from the solrwayback bundle.
 
-ARG SOLRWAYBACK_VERSION=4.4.2
-ARG ECLIPSE_TEMURIN_TAG=8-jre
+ARG SOLRWAYBACK_VERSION=5.1.0
+ARG ECLIPSE_TEMURIN_TAG=17-jre
 
 FROM ubuntu:22.04 as solrwayback-bundle
 
 ARG SOLRWAYBACK_VERSION
 
-RUN apt-get update \
-    && apt-get install --quiet --assume-yes wget python3
+RUN apt-get update && apt-get install -y \
+    unzip \
+    wget
 
 WORKDIR /build
-COPY fetch_solrwayback_bundle.py .
 
-RUN python3 fetch_solrwayback_bundle.py \
-    --solrwayback-version ${SOLRWAYBACK_VERSION} \
-    --destination /app
+RUN wget -q https://github.com/netarchivesuite/solrwayback/releases/download/${SOLRWAYBACK_VERSION}/solrwayback_package_${SOLRWAYBACK_VERSION}.zip
+RUN mkdir /app \
+    && unzip solrwayback_package_${SOLRWAYBACK_VERSION}.zip \
+    && mv solrwayback_package_${SOLRWAYBACK_VERSION}_MASTER/* /app
+
 
 FROM eclipse-temurin:${ECLIPSE_TEMURIN_TAG}
 
-ARG SOLRWAYBACK_VERSION
+COPY --from=solrwayback-bundle /app/indexing /opt/warc-indexer
 
-COPY --from=solrwayback-bundle /app/solrwayback_package_${SOLRWAYBACK_VERSION}/indexing /opt/warc-indexer
+ENTRYPOINT ["/opt/warc-indexer/warc-indexer.sh"]