Update versions (#7)

* Update versions Tesseract Leptonica Python Pandoc * fix build script version * update workflow * fixing python version * I mistakenly thought there was a newer python version, switching back * fix version in url
Unstructured-IO · Sep 9, 2023 · e092e8c · e092e8c
1 parent 233e833
commit e092e8c
Show file tree

Hide file tree

Showing 3 changed files with 11 additions and 10 deletions.
diff --git a/.github/scripts/build-base-images.sh b/.github/scripts/build-base-images.sh
@@ -7,7 +7,7 @@ BUILD_REPO="${BUILD_REPO:-build-base-images}"
 PIP_VERSION="${PIP_VERSION:-22.2.1}"
 GITHUB_REF="${GITHUB_REF:-none}"
 DOCKER_PLATFORM="${DOCKER_PLATFORM:-linux/amd64}"
-DOCKERFILE="${DOCKERFILE:-rocky9.2-3}"
+DOCKERFILE="${DOCKERFILE:-rocky9.2-4}"
 CI="${CI:-false}"
 SHORT_SHA="${SHORT_SHA:-$(git rev-parse --short HEAD)}"
 

diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
@@ -25,7 +25,7 @@ jobs:
     strategy:
       matrix:
         docker-platform: ["linux/arm64", "linux/amd64"]
-        images: ["rocky9.2-3"]
+        images: ["rocky9.2-4"]
     runs-on: ubuntu-latest
     needs: [set-short-sha]
     env:
@@ -51,7 +51,7 @@ jobs:
   publish-images:
     strategy:
       matrix:
-        images: ["rocky9.2-3"]
+        images: ["rocky9.2-4"]
     env:
       SHORT_SHA: ${{ needs.set-short-sha.outputs.short_sha }}
     runs-on: ubuntu-latest

diff --git a/dockerfiles/base-images:rocky9.2-3 → dockerfiles/base-images:rocky9.2-4 b/dockerfiles/base-images:rocky9.2-3 → dockerfiles/base-images:rocky9.2-4
@@ -12,8 +12,9 @@ RUN dnf -y update && \
     # Needed for LibreOffice to install base components on aarch64
     sed -i 's/enabled=0/enabled=1/g' /etc/yum.repos.d/Rocky-Devel.repo && \
     ARCH=$(uname -m) && if [ "$ARCH" == "aarch64" ]; then ARCH="arm64"; else ARCH="amd64"; fi && \
-    wget https://github.com/jgm/pandoc/releases/download/3.1.2/pandoc-3.1.2-linux-$ARCH.tar.gz && \
-    tar xvzf pandoc-3.1.2-linux-$ARCH.tar.gz --strip-components 1 -C '/usr/local' && \
+    wget https://github.com/jgm/pandoc/releases/download/3.1.7/pandoc-3.1.7-linux-$ARCH.tar.gz && \
+    tar xvzf pandoc-3.1.7-linux-$ARCH.tar.gz --strip-components 1 -C '/usr/local' && \
+    rm -rf pandoc-3.1.7-linux-$ARCH.tar.gz && \
     dnf -y install libreoffice-writer libreoffice-base libreoffice-impress libreoffice-draw libreoffice-math libreoffice-core && \
     sed -i 's/enabled=1/enabled=0/g' /etc/yum.repos.d/Rocky-Devel.repo && \
     rm -rf /var/cache/yum/* && \
@@ -24,9 +25,9 @@ RUN dnf -y update && \
 RUN set -ex && \
     dnf install -y opencv opencv* zlib zlib-devel perl-core clang libpng libpng-devel libtiff libtiff-devel \
     libwebp libwebp-devel libjpeg libjpeg-devel libjpeg-turbo-devel git-core libtool pkgconfig xz && \
-    wget https://github.com/DanBloomberg/leptonica/releases/download/1.75.1/leptonica-1.75.1.tar.gz && \
-    tar -xzvf leptonica-1.75.1.tar.gz && \
-    cd leptonica-1.75.1 || exit && \
+    wget https://github.com/DanBloomberg/leptonica/releases/download/1.83.1/leptonica-1.83.1.tar.gz && \
+    tar -xzvf leptonica-1.83.1.tar.gz && \
+    cd leptonica-1.83.1 || exit && \
     ./configure && make && make install && \
     cd .. && \
     wget http://mirror.squ.edu.om/gnu/autoconf-archive/autoconf-archive-2017.09.28.tar.xz && \
@@ -35,15 +36,15 @@ RUN set -ex && \
     ./configure && make && make install && \
     cp m4/* /usr/share/aclocal && \
     cd .. && \
-    git clone --depth 1 --branch 5.3.1 https://github.com/tesseract-ocr/tesseract.git tesseract-ocr && \
+    git clone --depth 1 --branch 5.3.2 https://github.com/tesseract-ocr/tesseract.git tesseract-ocr && \
     cd tesseract-ocr || exit && \
     export PKG_CONFIG_PATH=/usr/local/lib/pkgconfig && \
     ./autogen.sh && ./configure --prefix=/usr/local --disable-shared --enable-static --with-extra-libraries=/usr/local/lib/ --with-extra-includes=/usr/local/lib/ && \
     make && make install && \
     cd .. && \
     git clone https://github.com/tesseract-ocr/tessdata.git  && \
     cp tessdata/*.traineddata /usr/local/share/tessdata && \
-    rm -rf /tesseract-ocr /tessdata /autoconf-archive-2017.09.28* /leptonica-1.75.1* && \
+    rm -rf /tesseract-ocr /tessdata /autoconf-archive-2017.09.28* /leptonica-1.83.1* && \
     dnf -y remove opencv* perl-core clang libpng-devel libtiff-devel libwebp-devel libjpeg-devel libjpeg-turbo-devel git-core libtool \
     zlib-devel pkconfig xz && \
     rm -rf /var/cache/yum/* && \