Merge branch 'main' of github.com:apache/iceberg-python into fd-fix-double-commit

Author: Fokko

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

@@ -62,7 +62,7 @@ jobs:
         if: startsWith(matrix.os, 'ubuntu')
 
       - name: Build wheels
-        uses: pypa/cibuildwheel@v2.23.2
+        uses: pypa/cibuildwheel@v2.23.3
         with:
           output-dir: wheelhouse
           config-file: "pyproject.toml"

.github/workflows/python-ci.yml

@@ -58,6 +58,8 @@ 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

.github/workflows/python-integration.yml

@@ -50,6 +50,8 @@ jobs:
     - uses: actions/checkout@v4
       with:
         fetch-depth: 2
+    - 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

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

@@ -57,7 +57,7 @@ jobs:
         if: startsWith(matrix.os, 'ubuntu')
 
       - name: Build wheels
-        uses: pypa/cibuildwheel@v2.23.2
+        uses: pypa/cibuildwheel@v2.23.3
         with:
           output-dir: wheelhouse
           config-file: "pyproject.toml"

Makefile

@@ -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..."; \

dev/Dockerfile

@@ -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

mkdocs/docs/api.md

@@ -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/configuration.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-->
 

poetry.lock

@@ -74,10 +74,17 @@
 
 
 class AvroFileHeader(Record):
-    __slots__ = ("magic", "meta", "sync")
-    magic: bytes
-    meta: Dict[str, str]
-    sync: bytes
+    @property
+    def magic(self) -> bytes:
+        return self._data[0]
+
+    @property
+    def meta(self) -> Dict[str, str]:
+        return self._data[1]
+
+    @property
+    def sync(self) -> bytes:
+        return self._data[2]
 
     def compression_codec(self) -> Optional[Type[Codec]]:
         """Get the file's compression codec algorithm from the file's metadata.
@@ -271,7 +278,7 @@ def __exit__(
     def _write_header(self) -> None:
         json_schema = json.dumps(AvroSchemaConversion().iceberg_to_avro(self.file_schema, schema_name=self.schema_name))
         meta = {**self.metadata, _SCHEMA_KEY: json_schema, _CODEC_KEY: "null"}
-        header = AvroFileHeader(magic=MAGIC, meta=meta, sync=self.sync_bytes)
+        header = AvroFileHeader(MAGIC, meta, self.sync_bytes)
         construct_writer(META_SCHEMA).write(self.encoder, header)
 
     def write_block(self, objects: List[D]) -> None: