Add Tesseract OCR languages

Add official IFAD languages packs
ifad · Sep 12, 2024 · 0d4d699 · 0d4d699
1 parent 8869dc2
commit 0d4d699
Show file tree

Hide file tree

Showing 2 changed files with 8 additions and 18 deletions.
diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
@@ -27,7 +27,7 @@ jobs:
     - name: Install ImageMagick, libmagic-dev, LibreOffice, Tesseract OCR, wkhtmltopdf
       run: |
         sudo apt-get update
-        sudo apt-get -yq --no-install-suggests --no-install-recommends install imagemagick libmagic-dev libreoffice tesseract-ocr wkhtmltopdf
+        sudo apt-get -yq --no-install-suggests --no-install-recommends install imagemagick libmagic-dev libreoffice tesseract-ocr tesseract-ocr-ara tesseract-ocr-spa tesseract-ocr-fra wkhtmltopdf
     - uses: actions/cache@v4
       name: Check Apache Tika
       id: cache-tika

diff --git a/docker/colore/Dockerfile b/docker/colore/Dockerfile
@@ -1,29 +1,19 @@
 FROM ruby:2.6.10
 
-RUN apt update && apt install -y \
+RUN apt-get update && apt-get -yq install --no-install-suggests --no-install-recommends \
   build-essential \
   imagemagick \
   libmagic-dev \
-  tesseract-ocr
+  tesseract-ocr \
+  tesseract-ocr-ara \
+  tesseract-ocr-fra \
+  tesseract-ocr-spa \
+  wkhtmltopdf
 
 # Needed to get the latest libreoffice
 # Ref: https://wiki.debian.org/LibreOffice#Using_Debian_backports
 RUN echo 'deb http://deb.debian.org/debian bullseye-backports main contrib non-free' >> /etc/apt/sources.list
-RUN apt update && apt install -y -t bullseye-backports libreoffice
-
-# Please keep using version 0.12.3
-# With newer versions of wkhtmltopdf, wkhtmltopdf/wkhtmltopdf#1524 and
-# wkhtmltopdf/wkhtmltopdf#3241 will affect Colore's PDF output
-# TODO: implement PDF comparison specs and update this library
-ARG WKHTMLTOPDF_VERSION=0.12.3
-ARG WKHTMLTOPDF_MD5=6e991e1a1f3293ab673afa015703ef86
-
-RUN wget --quiet https://github.com/wkhtmltopdf/wkhtmltopdf/releases/download/${WKHTMLTOPDF_VERSION}/wkhtmltox-${WKHTMLTOPDF_VERSION}_linux-generic-amd64.tar.xz -O wkhtmltox.tar.xz && \
-    echo "${WKHTMLTOPDF_MD5} wkhtmltox.tar.xz" > MD5SUMS && \
-    md5sum -c MD5SUMS && \
-    tar -xf wkhtmltox.tar.xz && \
-    mv wkhtmltox/bin/wkhtmltopdf /usr/local/bin && \
-    rm -rf wkhtmltox wkhtmltox.tar.xz MD5SUMS
+RUN apt-get update && apt-get -yq -t bullseye-backports install libreoffice
 
 ARG TIKA_VERSION=2.9.2