RHOAIENG-16568: [Bug] Unable to download notebook as a PDF from JupyterLab Workbenches (opendatahub-io#1030)

jesuino · jiridanek · web-flow · commit 858b1b8a7bf5 · 2025-06-04T08:22:47.000Z
* RHOAIENG-16568: [Bug] Unable to download notebook as a PDF from JupyterLab Workbenches

* Running installation from a script

* Adding test and fixing path

* Fixing Script file name

* Using minimal tmp file instead a fixed file

* Removing and ignoring logs

* Adding tex live to missing Dockerfiles

* Formatting

* Review changes

* Removing unwanted line

* Fixing type

* Copying configuration in all images

* Removing year from the TeXLive installation

* Adding pandoc for a complete PDF export support

* Updating comment about TeX live installation

* Improving PDF export test

* pandoc latest version and ignoring message

* formatting fix

* add "/usr/local/pandoc/bin/pandoc" to config.toml

---------

Co-authored-by: Jiri Daněk &lt;jdanek@redhat.com&gt;
diff --git a/.gitignore b/.gitignore
@@ -37,6 +37,9 @@ MANIFEST
 pip-log.txt
 pip-delete-this-directory.txt
 
+# Test logs
+logs/pytest-logs.txt
+
 # Unit test / coverage reports
 htmlcov/
 .tox/
diff --git a/jupyter/datascience/ubi9-python-3.11/Dockerfile.cpu b/jupyter/datascience/ubi9-python-3.11/Dockerfile.cpu
@@ -49,6 +49,14 @@ WORKDIR /opt/app-root/bin
 COPY ${JUPYTER_REUSABLE_UTILS} utils/
 COPY ${MINIMAL_SOURCE_CODE}/start-notebook.sh ./
 
+USER 0
+
+# Dependencies for PDF export
+RUN ./utils/install_pdf_deps.sh
+ENV PATH="/usr/local/texlive/bin/x86_64-linux:/usr/local/pandoc/bin:$PATH"
+
+USER 1001
+
 WORKDIR /opt/app-root/src
 
 ENTRYPOINT ["start-notebook.sh"]
@@ -107,6 +115,8 @@ RUN echo "Installing softwares and packages" && \
     rm /opt/app-root/share/jupyter/metadata/runtime-images/*.json && \
     # Replace Notebook's launcher, "(ipykernel)" with Python's version 3.x.y \
     sed -i -e "s/Python.*/$(python --version | cut -d '.' -f-2)\",/" /opt/app-root/share/jupyter/kernels/python3/kernel.json && \
+    # copy jupyter configuration
+    cp /opt/app-root/bin/utils/jupyter_server_config.py /opt/app-root/etc/jupyter && \
     # Disable announcement plugin of jupyterlab \
     jupyter labextension disable "@jupyterlab/apputils-extension:announcements" && \
     # Apply JupyterLab addons \
diff --git a/jupyter/minimal/ubi9-python-3.11/Dockerfile.cpu b/jupyter/minimal/ubi9-python-3.11/Dockerfile.cpu
@@ -19,7 +19,7 @@ RUN pip install --no-cache-dir -U "micropipenv[toml]"
 
 # Install the oc client
 RUN curl -L https://mirror.openshift.com/pub/openshift-v4/$(uname -m)/clients/ocp/stable/openshift-client-linux.tar.gz \
-        -o /tmp/openshift-client-linux.tar.gz && \
+    -o /tmp/openshift-client-linux.tar.gz && \
     tar -xzvf /tmp/openshift-client-linux.tar.gz oc && \
     rm -f /tmp/openshift-client-linux.tar.gz
 
@@ -45,6 +45,14 @@ WORKDIR /opt/app-root/bin
 
 COPY ${JUPYTER_REUSABLE_UTILS} utils/
 
+USER 0
+
+# Dependencies for PDF export
+RUN ./utils/install_pdf_deps.sh
+ENV PATH="/usr/local/texlive/bin/x86_64-linux:/usr/local/pandoc/bin:$PATH"
+
+USER 1001
+
 COPY ${MINIMAL_SOURCE_CODE}/Pipfile.lock ${MINIMAL_SOURCE_CODE}/start-notebook.sh ./
 
 # Install Python dependencies from Pipfile.lock file
@@ -55,12 +63,14 @@ RUN echo "Installing softwares and packages" && \
     jupyter labextension disable "@jupyterlab/apputils-extension:announcements" && \
     # Replace Notebook's launcher, "(ipykernel)" with Python's version 3.x.y \
     sed -i -e "s/Python.*/$(python --version | cut -d '.' -f-2)\",/" /opt/app-root/share/jupyter/kernels/python3/kernel.json && \
+    # copy jupyter configuration
+    cp /opt/app-root/bin/utils/jupyter_server_config.py /opt/app-root/etc/jupyter && \
     # Fix permissions to support pip in Openshift environments \
     chmod -R g+w /opt/app-root/lib/python3.11/site-packages && \
     fix-permissions /opt/app-root -P && \
     # Apply JupyterLab addons \
     /opt/app-root/bin/utils/addons/apply.sh
-    
+
 WORKDIR /opt/app-root/src
 
 ENTRYPOINT ["start-notebook.sh"]
diff --git a/jupyter/minimal/ubi9-python-3.11/Dockerfile.cuda b/jupyter/minimal/ubi9-python-3.11/Dockerfile.cuda
@@ -165,6 +165,14 @@ WORKDIR /opt/app-root/bin
 
 COPY ${JUPYTER_REUSABLE_UTILS} utils/
 
+USER 0
+
+# Dependencies for PDF export
+RUN ./utils/install_pdf_deps.sh
+ENV PATH="/usr/local/texlive/bin/x86_64-linux:/usr/local/pandoc/bin:$PATH"
+
+USER 1001
+
 COPY ${MINIMAL_SOURCE_CODE}/Pipfile.lock ${MINIMAL_SOURCE_CODE}/start-notebook.sh ./
 
 # Install Python dependencies from Pipfile.lock file
@@ -175,6 +183,8 @@ RUN echo "Installing softwares and packages" && \
     jupyter labextension disable "@jupyterlab/apputils-extension:announcements" && \
     # Replace Notebook's launcher, "(ipykernel)" with Python's version 3.x.y \
     sed -i -e "s/Python.*/$(python --version | cut -d '.' -f-2)\",/" /opt/app-root/share/jupyter/kernels/python3/kernel.json && \
+    # copy jupyter configuration
+    cp /opt/app-root/bin/utils/jupyter_server_config.py /opt/app-root/etc/jupyter && \
     # Fix permissions to support pip in Openshift environments \
     chmod -R g+w /opt/app-root/lib/python3.11/site-packages && \
     fix-permissions /opt/app-root -P && \
diff --git a/jupyter/minimal/ubi9-python-3.11/Dockerfile.rocm b/jupyter/minimal/ubi9-python-3.11/Dockerfile.rocm
@@ -79,6 +79,14 @@ WORKDIR /opt/app-root/bin
 
 COPY ${JUPYTER_REUSABLE_UTILS} utils/
 
+USER 0
+
+# Dependencies for PDF export
+RUN ./utils/install_pdf_deps.sh
+ENV PATH="/usr/local/texlive/bin/x86_64-linux:/usr/local/pandoc/bin:$PATH"
+
+USER 1001
+
 COPY ${MINIMAL_SOURCE_CODE}/Pipfile.lock ${MINIMAL_SOURCE_CODE}/start-notebook.sh ./
 
 # Install Python dependencies from Pipfile.lock file
@@ -89,6 +97,8 @@ RUN echo "Installing softwares and packages" && \
     jupyter labextension disable "@jupyterlab/apputils-extension:announcements" && \
     # Replace Notebook's launcher, "(ipykernel)" with Python's version 3.x.y \
     sed -i -e "s/Python.*/$(python --version | cut -d '.' -f-2)\",/" /opt/app-root/share/jupyter/kernels/python3/kernel.json && \
+    # copy jupyter configuration
+    cp /opt/app-root/bin/utils/jupyter_server_config.py /opt/app-root/etc/jupyter && \
     # Fix permissions to support pip in Openshift environments \
     chmod -R g+w /opt/app-root/lib/python3.11/site-packages && \
     fix-permissions /opt/app-root -P && \
diff --git a/jupyter/pytorch/ubi9-python-3.11/Dockerfile.cuda b/jupyter/pytorch/ubi9-python-3.11/Dockerfile.cuda
@@ -170,6 +170,14 @@ COPY ${JUPYTER_REUSABLE_UTILS} utils/
 
 COPY ${MINIMAL_SOURCE_CODE}/start-notebook.sh ./
 
+USER 0
+
+# Dependencies for PDF export
+RUN ./utils/install_pdf_deps.sh
+ENV PATH="/usr/local/texlive/bin/x86_64-linux:/usr/local/pandoc/bin:$PATH"
+
+USER 1001
+    
 WORKDIR /opt/app-root/src
 
 ENTRYPOINT ["start-notebook.sh"]
@@ -239,6 +247,8 @@ RUN echo "Installing softwares and packages" && \
     rm /opt/app-root/share/jupyter/metadata/runtime-images/*.json && \
     # Replace Notebook's launcher, "(ipykernel)" with Python's version 3.x.y \
     sed -i -e "s/Python.*/$(python --version | cut -d '.' -f-2)\",/" /opt/app-root/share/jupyter/kernels/python3/kernel.json && \
+    # copy jupyter configuration
+    cp /opt/app-root/bin/utils/jupyter_server_config.py /opt/app-root/etc/jupyter && \
     # Disable announcement plugin of jupyterlab \
     jupyter labextension disable "@jupyterlab/apputils-extension:announcements" && \
     # Apply JupyterLab addons \
diff --git a/jupyter/rocm/pytorch/ubi9-python-3.11/Dockerfile.rocm b/jupyter/rocm/pytorch/ubi9-python-3.11/Dockerfile.rocm
@@ -84,6 +84,14 @@ COPY ${JUPYTER_REUSABLE_UTILS} utils/
 
 COPY ${MINIMAL_SOURCE_CODE}/start-notebook.sh ./
 
+USER 0
+
+# Dependencies for PDF export
+RUN ./utils/install_pdf_deps.sh
+ENV PATH="/usr/local/texlive/bin/x86_64-linux:/usr/local/pandoc/bin:$PATH"
+
+USER 1001
+    
 WORKDIR /opt/app-root/src
 
 ENTRYPOINT ["start-notebook.sh"]
@@ -153,6 +161,8 @@ RUN echo "Installing softwares and packages" && \
     rm /opt/app-root/share/jupyter/metadata/runtime-images/*.json && \
     # Replace Notebook's launcher, "(ipykernel)" with Python's version 3.x.y \
     sed -i -e "s/Python.*/$(python --version | cut -d '.' -f-2)\",/" /opt/app-root/share/jupyter/kernels/python3/kernel.json && \
+    # copy jupyter configuration
+    cp /opt/app-root/bin/utils/jupyter_server_config.py /opt/app-root/etc/jupyter && \
     # Disable announcement plugin of jupyterlab \
     jupyter labextension disable "@jupyterlab/apputils-extension:announcements" && \
     # Apply JupyterLab addons \
diff --git a/jupyter/rocm/tensorflow/ubi9-python-3.11/Dockerfile.rocm b/jupyter/rocm/tensorflow/ubi9-python-3.11/Dockerfile.rocm
@@ -82,6 +82,14 @@ WORKDIR /opt/app-root/bin
 
 COPY ${JUPYTER_REUSABLE_UTILS} utils/
 
+USER 0
+
+# Dependencies for PDF export
+RUN ./utils/install_pdf_deps.sh
+ENV PATH="/usr/local/texlive/bin/x86_64-linux:/usr/local/pandoc/bin:$PATH"
+
+USER 1001
+
 COPY ${MINIMAL_SOURCE_CODE}/start-notebook.sh ./
 
 WORKDIR /opt/app-root/src
@@ -153,6 +161,8 @@ RUN echo "Installing softwares and packages" && \
     rm /opt/app-root/share/jupyter/metadata/runtime-images/*.json && \
     # Replace Notebook's launcher, "(ipykernel)" with Python's version 3.x.y \
     sed -i -e "s/Python.*/$(python --version | cut -d '.' -f-2)\",/" /opt/app-root/share/jupyter/kernels/python3/kernel.json && \
+    # copy jupyter configuration
+    cp /opt/app-root/bin/utils/jupyter_server_config.py /opt/app-root/etc/jupyter && \
     # Disable announcement plugin of jupyterlab \
     jupyter labextension disable "@jupyterlab/apputils-extension:announcements" && \
     # Apply JupyterLab addons \
diff --git a/jupyter/tensorflow/ubi9-python-3.11/Dockerfile.cuda b/jupyter/tensorflow/ubi9-python-3.11/Dockerfile.cuda
@@ -170,6 +170,14 @@ COPY ${JUPYTER_REUSABLE_UTILS} utils/
 
 COPY ${MINIMAL_SOURCE_CODE}/start-notebook.sh ./
 
+USER 0
+
+# Dependencies for PDF export
+RUN ./utils/install_pdf_deps.sh
+ENV PATH="/usr/local/texlive/bin/x86_64-linux:/usr/local/pandoc/bin:$PATH"
+
+USER 1001
+    
 WORKDIR /opt/app-root/src
 
 ENTRYPOINT ["start-notebook.sh"]
@@ -239,6 +247,8 @@ RUN echo "Installing softwares and packages" && \
     rm /opt/app-root/share/jupyter/metadata/runtime-images/*.json && \
     # Replace Notebook's launcher, "(ipykernel)" with Python's version 3.x.y \
     sed -i -e "s/Python.*/$(python --version | cut -d '.' -f-2)\",/" /opt/app-root/share/jupyter/kernels/python3/kernel.json && \
+    # copy jupyter configuration
+    cp /opt/app-root/bin/utils/jupyter_server_config.py /opt/app-root/etc/jupyter && \
     # Disable announcement plugin of jupyterlab \
     jupyter labextension disable "@jupyterlab/apputils-extension:announcements" && \
     # Apply JupyterLab addons \
diff --git a/jupyter/trustyai/ubi9-python-3.11/Dockerfile.cpu b/jupyter/trustyai/ubi9-python-3.11/Dockerfile.cpu
@@ -49,6 +49,14 @@ WORKDIR /opt/app-root/bin
 COPY ${JUPYTER_REUSABLE_UTILS} utils/
 COPY ${MINIMAL_SOURCE_CODE}/start-notebook.sh ./
 
+USER 0
+
+# Dependencies for PDF export
+RUN ./utils/install_pdf_deps.sh
+ENV PATH="/usr/local/texlive/bin/x86_64-linux:/usr/local/pandoc/bin:$PATH"
+
+USER 1001
+
 WORKDIR /opt/app-root/src
 
 ENTRYPOINT ["start-notebook.sh"]
@@ -126,6 +134,8 @@ RUN echo "Installing softwares and packages" && \
     rm /opt/app-root/share/jupyter/metadata/runtime-images/*.json && \
     # Replace Notebook's launcher, "(ipykernel)" with Python's version 3.x.y \
     sed -i -e "s/Python.*/$(python --version | cut -d '.' -f-2)\",/" /opt/app-root/share/jupyter/kernels/python3/kernel.json && \
+    # copy jupyter configuration
+    cp /opt/app-root/bin/utils/jupyter_server_config.py /opt/app-root/etc/jupyter && \
     # Disable announcement plugin of jupyterlab \
     jupyter labextension disable "@jupyterlab/apputils-extension:announcements" && \
     # Apply JupyterLab addons \
diff --git a/jupyter/utils/install_pdf_deps.sh b/jupyter/utils/install_pdf_deps.sh
@@ -0,0 +1,18 @@
+#!/bin/bash 
+
+# Install dependencies required for Notebooks PDF exports
+
+# tex live installation
+echo "Installing TexLive to allow PDf export from Notebooks" 
+curl -L https://mirror.ctan.org/systems/texlive/tlnet/install-tl-unx.tar.gz -o install-tl-unx.tar.gz 
+zcat < install-tl-unx.tar.gz | tar xf -
+cd install-tl-2*
+perl ./install-tl --no-interaction --scheme=scheme-small --texdir=/usr/local/texlive
+cd /usr/local/texlive/bin/x86_64-linux
+./tlmgr install tcolorbox pdfcol adjustbox titling enumitem soul ucs collection-fontsrecommended
+
+# pandoc installation
+curl -L https://github.com/jgm/pandoc/releases/download/3.7.0.2/pandoc-3.7.0.2-linux-amd64.tar.gz  -o /tmp/pandoc.tar.gz
+mkdir -p /usr/local/pandoc
+tar xvzf /tmp/pandoc.tar.gz --strip-components 1 -C /usr/local/pandoc/
+rm -f /tmp/pandoc.tar.gz
diff --git a/jupyter/utils/jupyter_server_config.py b/jupyter/utils/jupyter_server_config.py
@@ -0,0 +1,6 @@
+# https://github.com/opendatahub-io-contrib/workbench-images/blob/main/snippets/ides/1-jupyter/files/etc/jupyter_notebook_config.py
+c = get_config()
+# Disable unsupported exporters
+c.WebPDFExporter.enabled = False
+c.QtPDFExporter.enabled = False
+c.QtPNGExporter.enabled = False
diff --git a/scripts/check-payload/config.toml b/scripts/check-payload/config.toml
@@ -250,6 +250,7 @@ error = "ErrNotDynLinked"
 files = [
     # executable is not dynamically linked
     "/opt/app-root/bin/py-spy",
+    "/usr/local/pandoc/bin/pandoc",
 ]
 
 [[rpm.code-server.ignore]]
diff --git a/tests/containers/workbenches/jupyterlab/jupyterlab_test.py b/tests/containers/workbenches/jupyterlab/jupyterlab_test.py
@@ -1,5 +1,8 @@
 from __future__ import annotations
 
+import pathlib
+import tempfile
+
 import allure
 import pytest
 import requests
@@ -51,6 +54,51 @@ def test_spinner_html_loaded(self, jupyterlab_image: conftest.Image) -> None:
         finally:
             docker_utils.NotebookContainer(container).stop(timeout=0)
 
+    @allure.issue("RHOAIENG-16568")
+    @allure.description("Check that PDF export is working correctly")
+    def test_pdf_export(self, jupyterlab_image: conftest.Image) -> None:
+        container = WorkbenchContainer(image=jupyterlab_image.name, user=4321, group_add=[0])
+        test_file_name = "test.ipybn"
+        test_file_content = """{
+                "cells": [
+                    {
+                        "cell_type": "markdown",
+                        "metadata": {},
+                        "source": [ "# Hello World" ]
+                    },
+                    {
+                        "cell_type": "code",
+                        "execution_count": 1,
+                        "metadata": {},
+                        "outputs": [
+                            {
+                                "name": "stdout",
+                                "output_type": "stream",
+                                "text": [ "Hello World\n" ]
+                            }
+                        ],
+                        "source": [ "print('Hello World')" ]
+                    }
+                ],
+                "metadata": {},
+                "nbformat": 4,
+                "nbformat_minor": 5
+            }
+        """.replace("\n", "")
+        try:
+            container.start(wait_for_readiness=True)
+            with tempfile.TemporaryDirectory() as tmpdir:
+                tmpdir = pathlib.Path(tmpdir)
+                (tmpdir / test_file_name).write_text(test_file_content)
+                docker_utils.container_cp(
+                    container.get_wrapped_container(), src=str(tmpdir / test_file_name), dst=self.APP_ROOT_HOME
+                )
+            exit_code, convert_output = container.exec(["jupyter", "nbconvert", test_file_name, "--to", "pdf"])
+            assert "PDF successfully created" in convert_output.decode()
+            assert 0 == exit_code
+        finally:
+            docker_utils.NotebookContainer(container).stop(timeout=0)
+
     @allure.issue("RHOAIENG-24348")
     @allure.description("Check that custom-built (to be FIPS-compliant) mongocli binary runs.")
     def test_mongocli_binary_runs(self, jupyterlab_image: conftest.Image) -> None:
