mirror of
https://github.com/qurator-spk/ocrd-galley.git
synced 2025-07-28 06:09:54 +02:00
🏗 Build Tesseract from source
This commit is contained in:
parent
d903e3634c
commit
a3d6befb0d
1 changed files with 38 additions and 5 deletions
43
Dockerfile
43
Dockerfile
|
@ -5,18 +5,51 @@ ENV LC_ALL=C.UTF-8 LANG=C.UTF-8
|
||||||
RUN mkdir /var/lib/calamari-models
|
RUN mkdir /var/lib/calamari-models
|
||||||
COPY data/calamari-models/GT4HistOCR /var/lib/calamari-models/GT4HistOCR
|
COPY data/calamari-models/GT4HistOCR /var/lib/calamari-models/GT4HistOCR
|
||||||
|
|
||||||
|
|
||||||
RUN apt-get update && \
|
RUN apt-get update && \
|
||||||
apt-get install -y \
|
apt-get install -y \
|
||||||
git \
|
curl xz-utils \
|
||||||
libleptonica-dev \
|
|
||||||
libtesseract-dev \
|
|
||||||
libxml2-utils \
|
|
||||||
python3-pip \
|
python3-pip \
|
||||||
tesseract-ocr-all \
|
git \
|
||||||
|
# For leptonica/tesseract:
|
||||||
|
cmake libgif-dev libjpeg-dev libpng-dev libtiff-dev zlib1g-dev \
|
||||||
|
# For clstm on Ubuntu 19.04:
|
||||||
|
swig libeigen3-dev libpng-dev libprotobuf-dev \
|
||||||
|
# XML utils
|
||||||
|
libxml2-utils \
|
||||||
xmlstarlet \
|
xmlstarlet \
|
||||||
&& \
|
&& \
|
||||||
apt-get clean
|
apt-get clean
|
||||||
|
|
||||||
|
|
||||||
|
# Build Leptonica and Tesseract.
|
||||||
|
# XXX Use a multi stage build for this.
|
||||||
|
ENV LEPTONICA_VERSION 1.78.0
|
||||||
|
ENV TESSERACT_VERSION 4.1.0
|
||||||
|
ENV TESSDATA_BEST_VERSION 4.0.0
|
||||||
|
|
||||||
|
ENV TESSDATA_PREFIX /usr/local/share/tessdata
|
||||||
|
|
||||||
|
RUN curl -sSL -O https://github.com/DanBloomberg/leptonica/releases/download/$LEPTONICA_VERSION/leptonica-$LEPTONICA_VERSION.tar.gz && \
|
||||||
|
tar xvzf leptonica-$LEPTONICA_VERSION.tar.gz && \
|
||||||
|
cd leptonica-$LEPTONICA_VERSION && \
|
||||||
|
mkdir build && cd build && cmake .. && make install && ldconfig && \
|
||||||
|
cd ../.. && rm -rf leptonica-$LEPTONICA_VERSION leptonica-$LEPTONICA_VERSION.tar.gz
|
||||||
|
|
||||||
|
RUN curl -sSL -O https://github.com/tesseract-ocr/tesseract/archive/$TESSERACT_VERSION.tar.gz && \
|
||||||
|
tar xvzf $TESSERACT_VERSION.tar.gz && \
|
||||||
|
cd tesseract-$TESSERACT_VERSION && \
|
||||||
|
mkdir build && cd build && cmake .. && make install && ldconfig && \
|
||||||
|
cd ../.. && rm -rf tesseract-$TESSERACT_VERSION $TESSERACT_VERSION.tar.gz
|
||||||
|
|
||||||
|
RUN curl -sSL -O https://github.com/tesseract-ocr/tessdata_best/archive/$TESSDATA_BEST_VERSION.tar.gz && \
|
||||||
|
tar xvzf $TESSDATA_BEST_VERSION.tar.gz && \
|
||||||
|
mv tessdata_best-$TESSDATA_BEST_VERSION $TESSDATA_PREFIX && \
|
||||||
|
rm -rf $TESSDATA_BEST_VERSION.tar.gz && \
|
||||||
|
tesseract --list-langs
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
COPY requirements.txt /tmp
|
COPY requirements.txt /tmp
|
||||||
RUN pip3 install --no-cache-dir -r /tmp/requirements.txt
|
RUN pip3 install --no-cache-dir -r /tmp/requirements.txt
|
||||||
|
|
||||||
|
|
Loading…
Add table
Add a link
Reference in a new issue