Dockerfile for building tesseract on amazon linux 2

tesseract.dockerfile

FROM docker.io/library/amazonlinux:latest

RUN yum -y update

RUN yum -y upgrade

RUN yum install clang -y && \
    yum install libpng-devel libtiff-devel zlib-devel libwebp-devel libjpeg-turbo-devel wget tar gzip -y && \
    wget https://github.com/DanBloomberg/leptonica/releases/download/1.75.1/leptonica-1.75.1.tar.gz && \
    tar -zxvf leptonica-1.75.1.tar.gz && \
    cd leptonica-1.75.1 && \
    ./configure && \
    make && \
    make install

RUN cd ~ && \
    yum install git-core libtool pkgconfig -y && \
    git clone --depth 1  https://github.com/tesseract-ocr/tesseract.git tesseract-ocr && \
    cd tesseract-ocr && \
    export PKG_CONFIG_PATH=/usr/local/lib/pkgconfig && \
    ./autogen.sh && \
    ./configure && \
    make && \
    make install

RUN cd /usr/local/share/tessdata && \
    wget https://github.com/tesseract-ocr/tessdata/raw/main/osd.traineddata && \
    wget https://github.com/tesseract-ocr/tessdata/raw/main/eng.traineddata && \
    wget https://github.com/tesseract-ocr/tessdata/raw/main/hin.traineddata

ENV TESSDATA_PREFIX=/usr/local/share/tessdata

docker run -it codesankalp/amazon-linux-tesseract:latest