Merge branch 'main' of github.com:apache/iceberg-python

Author: Fokko

.github/workflows/pypi-build-artifacts.yml

@@ -62,7 +62,7 @@ jobs:
         if: startsWith(matrix.os, 'ubuntu')
 
       - name: Build wheels
-        uses: pypa/[email protected].2
+        uses: pypa/[email protected].3
         with:
           output-dir: wheelhouse
           config-file: "pyproject.toml"

.github/workflows/python-ci.yml

@@ -58,9 +58,29 @@ jobs:
         python-version: ${{ matrix.python }}
         cache: poetry
         cache-dependency-path: ./poetry.lock
+    - name: Install system dependencies
+      run: sudo apt-get update && sudo apt-get install -y libkrb5-dev # for kerberos
     - name: Install
       run: make install-dependencies
     - name: Linters
       run: make lint
     - name: Tests
-      run: make test-coverage
+      run: make test-coverage-unit
+
+  integration-test:
+    runs-on: ubuntu-22.04
+    strategy:
+      matrix:
+        python: ['3.9', '3.10', '3.11', '3.12']
+
+    steps:
+    - uses: actions/checkout@v4
+    - name: Install system dependencies
+      run: sudo apt-get update && sudo apt-get install -y libkrb5-dev # for kerberos
+    - name: Install
+      run: make install
+    - name: Run integration tests
+      run: make test-coverage-integration
+    - name: Show debug logs
+      if: ${{ failure() }}
+      run: docker compose -f dev/docker-compose.yml logs

.github/workflows/python-integration.yml

@@ -57,7 +57,7 @@ jobs:
         if: startsWith(matrix.os, 'ubuntu')
 
       - name: Build wheels
-        uses: pypa/[email protected].2
+        uses: pypa/[email protected].3
         with:
           output-dir: wheelhouse
           config-file: "pyproject.toml"

.github/workflows/svn-build-artifacts.yml

@@ -19,7 +19,7 @@
 help:  ## Display this help
 	@awk 'BEGIN {FS = ":.*##"; printf "\nUsage:\n  make \033[36m\033[0m\n"} /^[a-zA-Z_-]+:.*?##/ { printf "  \033[36m%-20s\033[0m %s\n", $$1, $$2 } /^##@/ { printf "\n\033[1m%s\033[0m\n", substr($$0, 5) } ' $(MAKEFILE_LIST)
 
-POETRY_VERSION = 2.0.1
+POETRY_VERSION = 2.1.1
 install-poetry:  ## Ensure Poetry is installed and the correct version is being used.
 	@if ! command -v poetry &> /dev/null; then \
 		echo "Poetry could not be found. Installing..."; \
@@ -52,13 +52,17 @@ test-s3: # Run tests marked with s3, can add arguments with PYTEST_ARGS="-vv"
 	sh ./dev/run-minio.sh
 	poetry run pytest tests/ -m s3 ${PYTEST_ARGS}
 
-test-integration: ## Run all integration tests, can add arguments with PYTEST_ARGS="-vv"
+test-integration: | test-integration-setup test-integration-exec ## Run all integration tests, can add arguments with PYTEST_ARGS="-vv"
+
+test-integration-setup: # Prepare the environment for integration
 	docker compose -f dev/docker-compose-integration.yml kill
 	docker compose -f dev/docker-compose-integration.yml rm -f
 	docker compose -f dev/docker-compose-integration.yml up -d
 	sleep 10
 	docker compose -f dev/docker-compose-integration.yml cp ./dev/provision.py spark-iceberg:/opt/spark/provision.py
 	docker compose -f dev/docker-compose-integration.yml exec -T spark-iceberg ipython ./provision.py
+
+test-integration-exec:  # Execute integration tests, can add arguments with PYTEST_ARGS="-vv"
 	poetry run pytest tests/ -v -m integration ${PYTEST_ARGS}
 
 test-integration-rebuild:

Makefile

@@ -39,20 +39,20 @@ WORKDIR ${SPARK_HOME}
 # Remember to also update `tests/conftest`'s spark setting
 ENV SPARK_VERSION=3.5.4
 ENV ICEBERG_SPARK_RUNTIME_VERSION=3.5_2.12
-ENV ICEBERG_VERSION=1.9.0-SNAPSHOT
+ENV ICEBERG_VERSION=1.9.0
 ENV PYICEBERG_VERSION=0.9.0
 
 RUN curl --retry 5 -s -C - https://archive.apache.org/dist/spark/spark-${SPARK_VERSION}/spark-${SPARK_VERSION}-bin-hadoop3.tgz -o spark-${SPARK_VERSION}-bin-hadoop3.tgz \
  && tar xzf spark-${SPARK_VERSION}-bin-hadoop3.tgz --directory /opt/spark --strip-components 1 \
  && rm -rf spark-${SPARK_VERSION}-bin-hadoop3.tgz
 
 # Download iceberg spark runtime
-RUN curl --retry 5 -s https://repository.apache.org/content/groups/snapshots/org/apache/iceberg/iceberg-spark-runtime-3.5_2.12/1.9.0-SNAPSHOT/iceberg-spark-runtime-3.5_2.12-1.9.0-20250409.001855-44.jar \
+RUN curl --retry 5 -s https://repo1.maven.org/maven2/org/apache/iceberg/iceberg-spark-runtime-${ICEBERG_SPARK_RUNTIME_VERSION}/${ICEBERG_VERSION}/iceberg-spark-runtime-${ICEBERG_SPARK_RUNTIME_VERSION}-${ICEBERG_VERSION}.jar \
       -Lo /opt/spark/jars/iceberg-spark-runtime-${ICEBERG_SPARK_RUNTIME_VERSION}-${ICEBERG_VERSION}.jar
 
 
 # Download AWS bundle
-RUN curl --retry 5 -s https://repository.apache.org/content/groups/snapshots/org/apache/iceberg/iceberg-aws-bundle/1.9.0-SNAPSHOT/iceberg-aws-bundle-1.9.0-20250409.002731-88.jar \
+RUN curl --retry 5 -s https://repo1.maven.org/maven2/org/apache/iceberg/iceberg-aws-bundle/${ICEBERG_VERSION}/iceberg-aws-bundle-${ICEBERG_VERSION}.jar \
       -Lo /opt/spark/jars/iceberg-aws-bundle-${ICEBERG_VERSION}.jar
 
 COPY spark-defaults.conf /opt/spark/conf

dev/Dockerfile

@@ -215,6 +215,17 @@ static_table = StaticTable.from_metadata(
 
 The static-table is considered read-only.
 
+Alternatively, if your table metadata directory contains a `version-hint.text` file, you can just specify
+the table root path, and the latest metadata file will be picked automatically.
+
+```python
+from pyiceberg.table import StaticTable
+
+static_table = StaticTable.from_metadata(
+    "s3://warehouse/wh/nyc.db/taxis
+)
+```
+
 ## Check if a table exists
 
 To check whether the `bids` table exists:

mkdocs/docs/api.md

@@ -189,7 +189,7 @@ PyIceberg uses [S3FileSystem](https://arrow.apache.org/docs/python/generated/pya
 | s3.access-key-id     | admin                      | Configure the static access key id used to access the FileIO.                                                                                                                                                                                             |
 | s3.secret-access-key | password                   | Configure the static secret access key used to access the FileIO.                                                                                                                                                                                         |
 | s3.session-token     | AQoDYXdzEJr...             | Configure the static session token used to access the FileIO.                                                                                                                                                                                             |
-| s3.force-virtual-addressing   | True                       | Whether to use virtual addressing of buckets. This must be set to True as OSS can only be accessed with virtual hosted style address.                                                                                                                                                                                                        |
+| s3.force-virtual-addressing   | True                       | Whether to use virtual addressing of buckets. This is set to `True` by default as OSS can only be accessed with virtual hosted style address.                                                                                                                                                                                                        |
 
 <!-- markdown-link-check-enable-->
 

mkdocs/docs/configuration.md

@@ -37,18 +37,10 @@ The PyIceberg Project is hosted on GitHub at <https://github.com/apache/iceberg-
 For the development, Poetry is used for packing and dependency management. You can install this using:
 
 ```bash
-pip install poetry
+make install-poetry
 ```
 
-Make sure you're using an up-to-date environment from venv
-
-```bash
-pip install --upgrade virtualenv pip
-python -m venv ./venv
-source ./venv/bin/activate
-```
-
-To get started, you can run `make install`, which installs Poetry and all the dependencies of the Iceberg library. This also installs the development dependencies. If you don't want to install the development dependencies, you need to install using `poetry install --no-dev`.
+To get started, you can run `make install`, which installs all the dependencies of the Iceberg library. This also installs the development dependencies. If you don't want to install the development dependencies, you need to install using `poetry install --without dev` instead of `make install`.
 
 If you want to install the library on the host, you can simply run `pip3 install -e .`. If you wish to use a virtual environment, you can run `poetry shell`. Poetry will open up a virtual environment with all the dependencies set.