Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions .github/workflows/python-ci.yml
Original file line number Diff line number Diff line change
Expand Up @@ -78,6 +78,8 @@ jobs:
- uses: actions/setup-python@v6
with:
python-version: ${{ matrix.python }}
- name: Install UV
uses: astral-sh/setup-uv@v7
- name: Install system dependencies
run: sudo apt-get update && sudo apt-get install -y libkrb5-dev # for kerberos
- name: Install
Expand Down
10 changes: 8 additions & 2 deletions dev/spark/Dockerfile
Original file line number Diff line number Diff line change
Expand Up @@ -18,13 +18,14 @@ ARG BASE_IMAGE_SPARK_VERSION=4.0.1
FROM apache/spark:${BASE_IMAGE_SPARK_VERSION}

# Dependency versions - keep these compatible
ARG ICEBERG_VERSION=1.10.0
ARG ICEBERG_VERSION=1.10.1
ARG ICEBERG_SPARK_RUNTIME_VERSION=4.0_2.13
ARG SPARK_VERSION=4.0.1
ARG HADOOP_VERSION=3.4.1
ARG SCALA_VERSION=2.13
ARG AWS_SDK_VERSION=2.24.6
ARG MAVEN_MIRROR=https://repo.maven.apache.org/maven2
ARG ICEBERG_RC_MIRROR=https://repository.apache.org/content/repositories/orgapacheiceberg-1276

USER root
WORKDIR ${SPARK_HOME}
Expand Down Expand Up @@ -55,9 +56,14 @@ RUN set -e && \
for jar_path in ${JARS_TO_DOWNLOAD}; do \
jar_name=$(basename "${jar_path}") && \
echo "Downloading ${jar_name}..." && \
if echo "${jar_path}" | grep -q "^org/apache/iceberg/"; then \
mirror="${ICEBERG_RC_MIRROR}"; \
else \
mirror="${MAVEN_MIRROR}"; \
fi && \
curl -fsSL --retry 3 --retry-delay 5 \
-o "${jar_name}" \
"${MAVEN_MIRROR}/${jar_path}" && \
"${mirror}/${jar_path}" && \
echo "✓ Downloaded ${jar_name}"; \
done && \
chown -R spark:spark "${SPARK_HOME}/jars"
Expand Down