feat: info endpoint (#39)

* feat: added app info endpoint #35 * feat: added libreoffice fonts #33 * fix: Warning failed to launch javaldx - java may not function correctly * refactoring: added query parameter check and renamed pdfa parameter to profile * chore: updated documentation
rueedlinger · Jun 8, 2024 · 58b48f2 · 58b48f2
1 parent 6697fc7
commit 58b48f2
Show file tree

Hide file tree

Showing 19 changed files with 595 additions and 144 deletions.
diff --git a/Dockerfile b/Dockerfile
@@ -5,40 +5,97 @@ ARG USERNAME=worker
 ARG USER_UID=1000
 ARG USER_GID=$USER_UID
 ARG VERSION
+
+# supported tesseract languages https://tesseract-ocr.github.io/tessdoc/Data-Files-in-different-versions.html
 ARG TESSERACT_LANGUAGES="tesseract-ocr-deu tesseract-ocr-fra tesseract-ocr-ita tesseract-ocr-eng tesseract-ocr-por tesseract-ocr-spa"
 
-LABEL org.opencontainers.image.title="teal" \
+LABEL org.opencontainers.image.title="Teal" \
       org.opencontainers.image.description="A convenient REST API for working with PDF's." \
       org.opencontainers.image.documentation="https://teal.yax.ch/" \
       org.opencontainers.image.source="https://github.com/rueedlinger/teal"
 
+ENV DEBIAN_FRONTEND=noninteractive
 WORKDIR /usr/src/app
 
-# supported tesseract languages https://tesseract-ocr.github.io/tessdoc/Data-Files-in-different-versions.html
+############################
+# install base packages
+############################
 RUN groupadd --gid $USER_GID $USERNAME &&\
     useradd --uid $USER_UID --gid $USER_GID -m $USERNAME && \
     wget -O /usr/local/bin/dumb-init https://github.com/Yelp/dumb-init/releases/download/v1.2.5/dumb-init_1.2.5_x86_64  &&\
     chmod +x /usr/local/bin/dumb-init && \
     echo "deb http://deb.debian.org/debian bookworm-backports main" >> /etc/apt/sources.list && \
-    apt-get update && \
-    apt-get install -y tesseract-ocr && \
-    apt-get install -y $TESSERACT_LANGUAGES && \
-    apt-get install -y poppler-utils && \
-    apt-get install -y ghostscript python3-tk && \
-    apt-get install -y libgl1 && \
-    apt-get install -y ocrmypdf && \
-    apt-get --no-install-recommends install -y -t bookworm-backports libreoffice && \
-    apt-get install -y default-jre-headless && \
+    apt-get update &&\
+    apt-get install -y tesseract-ocr \
+    $TESSERACT_LANGUAGES \
+    poppler-utils \
+    ghostscript \
+    python3-tk \
+    libgl1 \
+    ocrmypdf \
+    default-jre-headless &&\
+    apt-get --no-install-recommends install -y -qq -t bookworm-backports libreoffice  && \
+    apt-get install -y -qq -t bookworm-backports libreoffice-java-common  && \
+    apt-get clean && \
     rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/*
 
-
+############################
+# insatll verapdf
+############################
 COPY dist/auto-install.xml /tmp
 RUN wget -O /tmp/verapdf-installer.zip https://software.verapdf.org/releases/verapdf-installer.zip && \
     unzip -d /tmp /tmp/verapdf-installer.zip && \
     /tmp/verapdf-greenfield-1.26.2/verapdf-install /tmp/auto-install.xml && \
-    rm -rf /tmp/verapdf*  && \
-    rm -rf /tmp/auto-install.xml
+    rm -rf /tmp/*
+
+############################
+# install fonts (inspired by gotenberg)
+# see https://github.com/gotenberg/gotenberg/blob/main/build/Dockerfile
+############################
+RUN wget -O /tmp/ttf-mscorefonts-installer_3.8.1_all.deb http://httpredir.debian.org/debian/pool/contrib/m/msttcorefonts/ttf-mscorefonts-installer_3.8.1_all.deb &&\
+    apt-get update &&\
+    apt-get install -y -qq --no-install-recommends \
+    /tmp/ttf-mscorefonts-installer_3.8.1_all.deb \
+    culmus \
+    fonts-beng \
+    fonts-hosny-amiri \
+    fonts-lklug-sinhala \
+    fonts-lohit-guru \
+    fonts-lohit-knda \
+    fonts-samyak-gujr \
+    fonts-samyak-mlym \
+    fonts-samyak-taml \
+    fonts-sarai \
+    fonts-sil-abyssinica \
+    fonts-sil-padauk \
+    fonts-telu \
+    fonts-thai-tlwg \
+    ttf-wqy-zenhei \
+    fonts-arphic-ukai \
+    fonts-arphic-uming \
+    fonts-ipafont-mincho \
+    fonts-ipafont-gothic \
+    fonts-unfonts-core \
+    # LibreOffice recommends.
+    fonts-crosextra-caladea \
+    fonts-crosextra-carlito \
+    fonts-dejavu \
+    fonts-dejavu-extra \
+    fonts-liberation \
+    fonts-liberation2 \
+    fonts-linuxlibertine \
+    fonts-noto-cjk \
+    fonts-noto-core \
+    fonts-noto-mono \
+    fonts-noto-ui-core \
+    fonts-sil-gentium \
+    fonts-sil-gentium-basic &&\
+    apt-get clean && \
+    rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/*
 
+############################
+# prepare app
+############################
 COPY requirements.txt ./
 RUN pip install --no-cache-dir -r requirements.txt
 
@@ -53,7 +110,6 @@ ENV PATH="${PATH}:/usr/local/verapdf"
 
 USER $USERNAME
 ENV TEAL_VERSION="$VERSION"
-ENV TESSERACT_TESSDATA_PATH="/usr/share/tesseract-ocr/5/tessdata"
 # Runs "/usr/bin/dumb-init -- /my/script --with --args"
 ENTRYPOINT ["/usr/local/bin/dumb-init", "--"]
 CMD ["/usr/src/app/run.sh"]
diff --git a/dist/run.sh b/dist/run.sh
@@ -2,7 +2,7 @@
 
 if [ "$TEAL_TEST_MODE" = true ] ; then
   echo "env TEAL_TEST_MODE ist set to '$TEAL_TEST_MODE'"
-  echo "running in test mode"
+  echo "running in TEST MODE"
 
   if [ -z ${TEAL_PYTEST_ARGS+x} ]; then
     export COVERAGE_FILE=/tmp/coverage
@@ -11,11 +11,10 @@ if [ "$TEAL_TEST_MODE" = true ] ; then
     pytest $TEAL_PYTEST_ARGS
   fi
 
-  #pytest --no-header -v --disable-warnings --log-cli-level debug
   echo "shutting container down..."
   exit
 else
-  echo "running in app mode"
+  echo "running in APP MODE"
 fi
 
 
@@ -27,6 +26,7 @@ else
     if [ "$TEAL_WORKERS" -gt 1 ]; then
       export PROMETHEUS_MULTIPROC_DIR="/tmp/prometheus"
       echo "running in multi worker mode, creating PROMETHEUS_MULTIPROC_DIR $PROMETHEUS_MULTIPROC_DIR"
+      echo "CPU and MEM metrics not available in multi worker mode (TEAL_WORKERS > 1)"
       mkdir $PROMETHEUS_MULTIPROC_DIR
     fi
 fi
@@ -54,17 +54,54 @@ else
 fi
 
 if [ "$TEAL_START_LOCUST" = true ] ; then
-  echo "env $TEAL_START_LOCUST ist set to '$TEAL_START_LOCUST'"
+  echo "env TEAL_START_LOCUST ist set to '$TEAL_START_LOCUST'"
 
-  echo "starting in locust"
   if [ -z ${TEAL_LOCUST_PORT+x} ]; then
-    locust --host http://localhost:$TEAL_PORT --web-port 8089 -f tests/locustfile.py &
+    TEAL_LOCUST_PORT=8089
+    echo "TEAL_LOCUST_PORT is unset, will set to port $TEAL_LOCUST_PORT"
   else
-    locust --host http://localhost:$TEAL_PORT --web-port $TEAL_LOCUST_PORT -f tests/locustfile.py &
+    echo "env $TEAL_LOCUST_PORT is set to '$$TEAL_LOCUST_PORT'"
   fi
 
+  locust --host http://localhost:$TEAL_PORT --web-port $TEAL_LOCUST_PORT -f tests/locustfile.py &
+
 fi
 
+TEAL_TESSERACT_TESSDATA_PATH=$(find /usr/share -type d -name tessdata | head -n 1)
+export TEAL_TESSERACT_TESSDATA_PATH
+
+TEAL_LIBREOFFICE_VERSION=$(libreoffice --version | head -n 1)
+export TEAL_LIBREOFFICE_VERSION
+
+TEAL_OCRMYPDF_VERSION_VERSION=$(ocrmypdf --version | head -n 1)
+export TEAL_OCRMYPDF_VERSION_VERSION
+
+TEAL_VERAPDF_VERSION=$(verapdf --version | head -n 1)
+export TEAL_VERAPDF_VERSION
+
+# from poppler-utils
+TEAL_PDFTOPPM_VERSION=$(echo "$(pdftoppm -v 2>&1 >/dev/null)" | head -n 1)
+export TEAL_PDFTOPPM_VERSION
+
+# from poppler-utils
+TEAL_PDFTOCAIRO_VERSION=$(echo "$(pdftocairo -v 2>&1 >/dev/null)" | head -n 1)
+export TEAL_PDFTOCAIRO_VERSION
+
+TEAL_TESSERACT_VERSION=$(tesseract --version | head -n 1)
+export TEAL_TESSERACT_VERSION
+
+TEAL_PYTHON_VERSION=$(python --version | head -n 1)
+export TEAL_PYTHON_VERSION
+
+TEAL_JAVA_VERSION=$(java --version | head -n 1)
+export TEAL_JAVA_VERSION
+
+TEAL_ARCH_NAME=$(uname -m | head -n 1)
+export TEAL_ARCH_NAME
+
+TEAL_ARCH_NPROC=$(nproc)
+export TEAL_ARCH_NPROC
+
 echo "see API doc http://$TEAL_IP_BIND:$TEAL_PORT/docs"
 gunicorn teal.api:app --workers "$TEAL_WORKERS" \
     --worker-class uvicorn.workers.UvicornWorker --bind "$TEAL_IP_BIND":"$TEAL_PORT" \