ci: Move xpdf build into separate container (#4199)

* Create Dockerfile and hcl config to build Xpdf

* Create workflow to build Xpdf Docker image

* Update Dockerfile.base to not build Xpdf

* Fix CWD removal and arg casing

* Fix ARG setting

.github/workflows/xpdf_release.yml

@@ -0,0 +1,39 @@
+name: Xpdf Docker image release
+
+on:
+  push:
+    branches:
+      - main
+    paths:
+      - docker/docker-bake-xpdf.hcl
+      - docker/Dockerfile.xpdf
+
+jobs:
+  publish-xpdf-image:
+    runs-on: ubuntu-latest
+    env:
+      DOCKER_REPO_NAME: deepset/xpdf
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v2
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v2
+
+      - name: Login to DockerHub
+        uses: docker/login-action@v1
+        with:
+          username: ${{ secrets.DOCKER_HUB_USER }}
+          password: ${{ secrets.DOCKER_HUB_TOKEN }}
+
+      - name: Build and publish Xpdf image
+        uses: docker/bake-action@v2
+        with:
+          files: "docker-bake-xpdf.hcl"
+          workdir: docker
+          targets: xpdf
+          push: true

docker/Dockerfile.base

@@ -7,20 +7,6 @@ ARG DEBIAN_FRONTEND=noninteractive
 ARG haystack_version
 ARG haystack_extras
 
-RUN apt-get update && apt-get install -y --no-install-recommends \
-    build-essential gcc git curl cmake \
-    tesseract-ocr libtesseract-dev poppler-utils
-
-# Install PDF converter
-RUN curl -O https://dl.xpdfreader.com/xpdf-4.04.tar.gz && \
-    tar -xvf xpdf-4.04.tar.gz && \
-    cd xpdf-4.04 && \
-    cmake . && \
-    make && \
-    cp xpdf/pdftotext /opt && \
-    cd .. && \
-    rm -rf xpdf-4.04
-
 # Shallow clone Haystack repo, we'll install from the local sources
 RUN git clone --depth=1 --branch=${haystack_version} https://github.com/deepset-ai/haystack.git /opt/haystack
 WORKDIR /opt/haystack
@@ -37,7 +23,8 @@ RUN pip install --upgrade pip && \
 FROM $base_image AS final
 
 COPY --from=build-image /opt/venv /opt/venv
-COPY --from=build-image /opt/pdftotext /usr/local/bin
+COPY --from=deepset/xpdf:latest /opt/pdftotext /usr/local/bin
+
 # pdftotext requires fontconfig runtime
 RUN apt-get update && apt-get install -y libfontconfig && rm -rf /var/lib/apt/lists/*
 

docker/Dockerfile.xpdf

@@ -0,0 +1,22 @@
+FROM ubuntu:latest
+
+RUN apt-get update && \
+    apt-get install -y --no-install-recommends \
+    build-essential \
+    cmake \
+    curl \
+    gcc \
+    git \
+    libtesseract-dev \
+    poppler-utils \
+    tesseract-ocr
+
+ARG xpdf_version
+RUN curl -O https://dl.xpdfreader.com/xpdf-${xpdf_version}.tar.gz && \
+    tar -xvf xpdf-${xpdf_version}.tar.gz && \
+    cd xpdf-${xpdf_version} && \
+    cmake . && \
+    make && \
+    cp xpdf/pdftotext /opt && \
+    cd .. \
+    rm -rf xpdf-${xpdf_version}

docker/docker-bake-xpdf.hcl

@@ -0,0 +1,12 @@
+variable "XPDF_VERSION" {
+  default = "4.04"
+}
+
+target "xpdf" {
+  dockerfile = "Dockerfile.xpdf"
+  tags = ["deepset/xpdf:latest"]
+  args = {
+    xpdf_version = "${XPDF_VERSION}"
+  }
+  platforms = ["linux/amd64", "linux/arm64"]
+}