Merge remote-tracking branch 'origin/main'

Author: kevinjqliu

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

@@ -42,7 +42,6 @@ jobs:
       - uses: actions/setup-python@v6
         with:
           python-version: |
-            3.9
             3.10
             3.11
             3.12
@@ -62,14 +61,14 @@ jobs:
         if: startsWith(matrix.os, 'ubuntu')
 
       - name: Build wheels
-        uses: pypa/[email protected].0
+        uses: pypa/[email protected].1
         with:
           output-dir: wheelhouse
           config-file: "pyproject.toml"
         env:
           # Ignore 32 bit architectures
           CIBW_ARCHS: "auto64"
-          CIBW_PROJECT_REQUIRES_PYTHON: ">=3.9,<3.13"
+          CIBW_PROJECT_REQUIRES_PYTHON: ">=3.10"
           CIBW_TEST_REQUIRES: "pytest==7.4.2 moto==5.0.1"
           CIBW_TEST_COMMAND: "pytest {project}/tests/avro/test_decoder.py"
           # Ignore tests for pypy since not all dependencies are compiled for it

.github/workflows/python-ci.yml

@@ -47,7 +47,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python: ['3.9', '3.10', '3.11', '3.12']
+        python: ['3.10', '3.11', '3.12']
 
     steps:
     - uses: actions/checkout@v5
@@ -71,7 +71,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python: ['3.9', '3.10', '3.11', '3.12']
+        python: ['3.10', '3.11', '3.12']
 
     steps:
     - uses: actions/checkout@v5

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

@@ -42,7 +42,6 @@ jobs:
       - uses: actions/setup-python@v6
         with:
           python-version: |
-            3.9
             3.10
             3.11
             3.12
@@ -57,14 +56,14 @@ jobs:
         if: startsWith(matrix.os, 'ubuntu')
 
       - name: Build wheels
-        uses: pypa/[email protected].0
+        uses: pypa/[email protected].1
         with:
           output-dir: wheelhouse
           config-file: "pyproject.toml"
         env:
           # Ignore 32 bit architectures
           CIBW_ARCHS: "auto64"
-          CIBW_PROJECT_REQUIRES_PYTHON: ">=3.9,<3.13"
+          CIBW_PROJECT_REQUIRES_PYTHON: ">=3.10"
           CIBW_TEST_REQUIRES: "pytest==7.4.2 moto==5.0.1"
           CIBW_TEST_COMMAND: "pytest {project}/tests/avro/test_decoder.py"
           # Ignore tests for pypy since not all dependencies are compiled for it

mkdocs/docs/configuration.md

@@ -539,6 +539,18 @@ catalog:
     py-io-impl: pyiceberg.io.fsspec.FsspecFileIO
 ```
 
+##### Apache Gravitino
+
+```yaml
+catalog:
+  gravitino_catalog:
+    type: rest
+    uri: <gravitino-catalog-uri>
+    header.X-Iceberg-Access-Delegation: vended-credentials
+    auth:
+      type: noop
+```
+
 ### SQL Catalog
 
 The SQL catalog requires a database for its backend. PyIceberg supports PostgreSQL and SQLite through psycopg2. The database connection has to be configured using the `uri` property. The init_catalog_tables is optional and defaults to True. If it is set to False, the catalog tables will not be created when the SQLCatalog is initialized. See SQLAlchemy's [documentation for URL format](https://docs.sqlalchemy.org/en/20/core/engines.html#backend-specific-urls):

mkdocs/docs/contributing.md

@@ -234,8 +234,6 @@ Deprecated in 0.1.0, will be removed in 0.2.0. The old_property is deprecated. P
 
 For the type annotation the types from the `Typing` package are used.
 
-PyIceberg offers support from Python 3.9 onwards, we can't use the [type hints from the standard collections](https://peps.python.org/pep-0585/).
-
 ### Third party libraries
 
 PyIceberg naturally integrates into the rich Python ecosystem, however it is important to be hesitant adding third party packages. Adding a lot of packages makes the library heavyweight, and causes incompatibilities with other projects if they use a different version of the library. Also, big libraries such as `s3fs`, `adlfs`, `pyarrow`, `thrift` should be optional to avoid downloading everything, while not being sure if is actually being used.

mkdocs/docs/how-to-release.md

@@ -30,6 +30,7 @@ This guide outlines the process for releasing PyIceberg in accordance with the [
 ## Requirements
 
 * A GPG key must be registered and published in the [Apache Iceberg KEYS file](https://downloads.apache.org/iceberg/KEYS). Follow [the instructions for setting up a GPG key and uploading it to the KEYS file](#set-up-gpg-key-and-upload-to-apache-iceberg-keys-file).
+    * Permission to update the `KEYS` artifact in the [Apache release distribution](https://dist.apache.org/repos/dist/release/iceberg/) (requires Iceberg PMC privileges).
 * SVN Access
     * Permission to upload artifacts to the [Apache development distribution](https://dist.apache.org/repos/dist/dev/iceberg/) (requires Apache Committer access).
     * Permission to upload artifacts to the [Apache release distribution](https://dist.apache.org/repos/dist/release/iceberg/) (requires Apache PMC access).
@@ -405,5 +406,12 @@ cd icebergsvn
 echo "" >> KEYS # append a newline
 gpg --list-sigs <YOUR KEY ID HERE> >> KEYS # append signatures
 gpg --armor --export <YOUR KEY ID HERE> >> KEYS # append public key block
-svn commit -m "add key for <YOUR NAME HERE>"
+svn commit -m "add key for <YOUR NAME HERE>" # this requires Iceberg PMC privileges
 ```
+
+<!-- prettier-ignore-start -->
+
+!!! note
+    Updating the `KEYS` artifact in the `release/` distribution requires Iceberg PMC privileges. Please work with a PMC member to update the file.
+
+<!-- prettier-ignore-end -->

pyiceberg/catalog/glue.py

@@ -355,34 +355,29 @@ def __init__(self, name: str, client: Optional["GlueClient"] = None, **propertie
                 _register_glue_catalog_id_with_glue_client(self.glue, glue_catalog_id)
 
     def _convert_glue_to_iceberg(self, glue_table: "TableTypeDef") -> Table:
-        properties: Properties = glue_table["Parameters"]
-
-        database_name = glue_table.get("DatabaseName", None)
-        if database_name is None:
+        if (database_name := glue_table.get("DatabaseName")) is None:
             raise ValueError("Glue table is missing DatabaseName property")
 
-        parameters = glue_table.get("Parameters", None)
-        if parameters is None:
-            raise ValueError("Glue table is missing Parameters property")
+        if (table_name := glue_table.get("Name")) is None:
+            raise ValueError("Glue table is missing Name property")
 
-        table_name = glue_table["Name"]
+        if (parameters := glue_table.get("Parameters")) is None:
+            raise ValueError("Glue table is missing Parameters property")
 
-        if TABLE_TYPE not in properties:
+        if (glue_table_type := parameters.get(TABLE_TYPE)) is None:
             raise NoSuchPropertyException(
                 f"Property {TABLE_TYPE} missing, could not determine type: {database_name}.{table_name}"
             )
-        glue_table_type = properties[TABLE_TYPE]
 
         if glue_table_type.lower() != ICEBERG:
             raise NoSuchIcebergTableError(
                 f"Property table_type is {glue_table_type}, expected {ICEBERG}: {database_name}.{table_name}"
             )
 
-        if METADATA_LOCATION not in properties:
+        if (metadata_location := parameters.get(METADATA_LOCATION)) is None:
             raise NoSuchPropertyException(
                 f"Table property {METADATA_LOCATION} is missing, cannot find metadata for: {database_name}.{table_name}"
             )
-        metadata_location = properties[METADATA_LOCATION]
 
         io = self._load_file_io(location=metadata_location)
         file = io.new_input(metadata_location)

pyiceberg/catalog/rest/__init__.py

@@ -238,6 +238,9 @@ def _create_session(self) -> Session:
         """Create a request session with provided catalog configuration."""
         session = Session()
 
+        # Set HTTP headers
+        self._config_headers(session)
+
         # Sets the client side and server side SSL cert verification, if provided as properties.
         if ssl_config := self.properties.get(SSL):
             if ssl_ca_bundle := ssl_config.get(CA_BUNDLE):
@@ -265,9 +268,6 @@ def _create_session(self) -> Session:
         else:
             session.auth = AuthManagerAdapter(self._create_legacy_oauth2_auth_manager(session))
 
-        # Set HTTP headers
-        self._config_headers(session)
-
         # Configure SigV4 Request Signing
         if property_as_bool(self.properties, SIGV4, False):
             self._init_sigv4(session)
@@ -654,6 +654,16 @@ def rename_table(self, from_identifier: Union[str, Identifier], to_identifier: U
             "source": self._split_identifier_for_json(from_identifier),
             "destination": self._split_identifier_for_json(to_identifier),
         }
+
+        # Ensure that namespaces exist on source and destination.
+        source_namespace = self._split_identifier_for_json(from_identifier)["namespace"]
+        if not self.namespace_exists(source_namespace):
+            raise NoSuchNamespaceError(f"Source namespace does not exist: {source_namespace}")
+
+        destination_namespace = self._split_identifier_for_json(to_identifier)["namespace"]
+        if not self.namespace_exists(destination_namespace):
+            raise NoSuchNamespaceError(f"Destination namespace does not exist: {destination_namespace}")
+
         response = self._session.post(self.url(Endpoints.rename_table), json=payload)
         try:
             response.raise_for_status()