Kevinjqliu/example

.asf.yaml

@@ -42,7 +42,9 @@ github:
         required_approving_review_count: 1
 
       required_linear_history: true
-  del_branch_on_merge: true
+  pull_requests:
+    # auto-delete head branches after being merged
+    del_branch_on_merge: true
   features:
     wiki: true
     issues: true
@@ -57,4 +59,5 @@ notifications:
     commits:      commits@iceberg.apache.org
     issues:       issues@iceberg.apache.org
     pullrequests: issues@iceberg.apache.org
+    jobs:         ci-jobs@iceberg.apache.org
     jira_options: link label link label

.github/workflows/check-md-link.yml

@@ -30,10 +30,11 @@ on:
     paths:
       - '.github/workflows/check-md-link.yml'
       - 'mkdocs/**'
+  workflow_dispatch:
 
 jobs:
   markdown-link-check:
     runs-on: ubuntu-latest
     steps:
     - uses: actions/checkout@master
-    - uses: tcort/github-action-markdown-link-check@v1
+    - uses: tcort/github-action-markdown-link-check@e7c7a18363c842693fadde5d41a3bd3573a7a225

.github/workflows/license_check.yml

@@ -24,5 +24,5 @@ jobs:
   rat:
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/checkout@v5
+    - uses: actions/checkout@v6
     - run: dev/check-license

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

@@ -31,7 +31,7 @@ jobs:
     outputs:
       VERSION: ${{ steps.set-version.outputs.VERSION }}
     steps:
-      - uses: actions/checkout@v5
+      - uses: actions/checkout@v6
         with:
           fetch-depth: 1
 
@@ -78,8 +78,35 @@ jobs:
     - name: List downloaded artifacts
       run: ls -R dist/
     - name: Publish to TestPyPI
+      id: publish-testpypi
+      continue-on-error: true
       uses: pypa/gh-action-pypi-publish@release/v1
       with:
         repository-url: https://test.pypi.org/legacy/
         skip-existing: true
         verbose: true
+    - name: Display error message on publish failure
+      if: steps.publish-testpypi.outcome == 'failure'
+      run: |
+        echo "::error::Failed to publish to TestPyPI"
+        echo ""
+        echo "⚠️  TestPyPI Publish Failed"
+        echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
+        echo ""
+        echo "This may be due to TestPyPI storage limits."
+        echo "See: https://docs.pypi.org/project-management/storage-limits"
+        echo ""
+        echo "To resolve this issue, use the pypi-cleanup utility to clean up old TestPyPI artifacts:"
+        echo "https://pypi.org/project/pypi-cleanup/"
+        echo ""
+        echo "  uvx pypi-cleanup --package pyiceberg --host https://test.pypi.org/ \\"
+        echo "    --verbose -d 10 --do-it --username <username>"
+        echo ""
+        echo "Requirements:"
+        echo "  • Must be a maintainer for pyiceberg on TestPyPI"
+        echo "    (https://test.pypi.org/project/pyiceberg)"
+        echo "  • Requires TestPyPI password and 2FA"
+        echo "  • ⚠️  ONLY do this for TestPyPI, NOT for production PyPI!"
+        echo ""
+        echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
+        exit 1

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

@@ -35,7 +35,7 @@ jobs:
         os: [ ubuntu-latest, windows-latest, macos-latest ]
 
     steps:
-      - uses: actions/checkout@v5
+      - uses: actions/checkout@v6
         with:
           fetch-depth: 1
 
@@ -61,7 +61,7 @@ jobs:
         if: startsWith(matrix.os, 'ubuntu')
 
       - name: Build wheels
-        uses: pypa/cibuildwheel@v3.2.1
+        uses: pypa/cibuildwheel@v3.3.0
         with:
           output-dir: wheelhouse
           config-file: "pyproject.toml"

.github/workflows/python-ci-docs.yml

@@ -35,7 +35,7 @@ jobs:
     runs-on: ubuntu-latest
 
     steps:
-      - uses: actions/checkout@v5
+      - uses: actions/checkout@v6
       - uses: actions/setup-python@v6
         with:
           python-version: 3.12

.github/workflows/python-ci.yml

@@ -50,7 +50,7 @@ jobs:
         python: ['3.10', '3.11', '3.12']
 
     steps:
-    - uses: actions/checkout@v5
+    - uses: actions/checkout@v6
     - uses: actions/setup-python@v6
       with:
         python-version: ${{ matrix.python }}
@@ -74,7 +74,7 @@ jobs:
         python: ['3.10', '3.11', '3.12']
 
     steps:
-    - uses: actions/checkout@v5
+    - uses: actions/checkout@v6
     - uses: actions/setup-python@v6
       with:
         python-version: ${{ matrix.python }}

.github/workflows/python-release-docs.yml

@@ -30,7 +30,7 @@ jobs:
     runs-on: ubuntu-latest
 
     steps:
-      - uses: actions/checkout@v5
+      - uses: actions/checkout@v6
       - uses: actions/setup-python@v6
         with:
           python-version: ${{ matrix.python }}

.github/workflows/python-release.yml

@@ -89,7 +89,7 @@ jobs:
     needs:
       - validate-inputs
     steps:
-      - uses: actions/checkout@v5
+      - uses: actions/checkout@v6
         with:
           fetch-depth: 1
 

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

@@ -35,7 +35,7 @@ jobs:
         os: [ ubuntu-latest, windows-latest, macos-latest ]
 
     steps:
-      - uses: actions/checkout@v5
+      - uses: actions/checkout@v6
         with:
           fetch-depth: 1
 
@@ -56,7 +56,7 @@ jobs:
         if: startsWith(matrix.os, 'ubuntu')
 
       - name: Build wheels
-        uses: pypa/cibuildwheel@v3.2.1
+        uses: pypa/cibuildwheel@v3.3.0
         with:
           output-dir: wheelhouse
           config-file: "pyproject.toml"

Makefile

@@ -18,6 +18,8 @@
 # Configuration Variables
 # ========================
 
+
+
 PYTHON ?=  # Override with e.g. PYTHON=3.11 to use specific Python version
 PYTEST_ARGS ?= -v -x  # Override with e.g. PYTEST_ARGS="-vv --tb=short"
 COVERAGE ?= 0      # Set COVERAGE=1 to enable coverage: make test COVERAGE=1
@@ -32,9 +34,9 @@ else
 endif
 
 ifeq ($(COVERAGE),1)
-  TEST_RUNNER = uv run python -m coverage run --parallel-mode --source=pyiceberg -m
+  TEST_RUNNER = uv run $(PYTHON_ARG) python -m coverage run --parallel-mode --source=pyiceberg -m
 else
-  TEST_RUNNER = uv run python -m
+  TEST_RUNNER = uv run $(PYTHON_ARG) python -m
 endif
 
 ifeq ($(KEEP_COMPOSE),1)
@@ -70,7 +72,7 @@ setup-venv: ## Create virtual environment
 	uv venv $(PYTHON_ARG)
 
 install-dependencies: setup-venv ## Install all dependencies including extras
-	uv sync --all-extras
+	uv sync $(PYTHON_ARG) --all-extras
 
 install: install-uv install-dependencies ## Install uv and dependencies
 
@@ -84,7 +86,7 @@ check-license: ## Check license headers
 	./dev/check-license
 
 lint: ## Run code linters via prek (pre-commit hooks)
-	uv run prek run -a
+	uv run $(PYTHON_ARG) prek run -a
 
 # ===============
 # Testing Section
@@ -101,7 +103,7 @@ test-integration-setup: ## Start Docker services for integration tests
 	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 --wait
-	uv run python dev/provision.py
+	uv run $(PYTHON_ARG) python dev/provision.py
 
 test-integration-exec: ## Run integration tests (excluding provision)
 	$(TEST_RUNNER) pytest tests/ -m integration $(PYTEST_ARGS)
@@ -133,10 +135,10 @@ test-coverage: COVERAGE=1
 test-coverage: test test-integration test-s3 test-adls test-gcs coverage-report ## Run all tests with coverage and report
 
 coverage-report: ## Combine and report coverage
-	uv run coverage combine
-	uv run coverage report -m --fail-under=$(COVERAGE_FAIL_UNDER)
-	uv run coverage html
-	uv run coverage xml
+	uv run $(PYTHON_ARG) coverage combine
+	uv run $(PYTHON_ARG) coverage report -m --fail-under=$(COVERAGE_FAIL_UNDER)
+	uv run $(PYTHON_ARG) coverage html
+	uv run $(PYTHON_ARG) coverage xml
 
 # ================
 # Documentation
@@ -145,13 +147,13 @@ coverage-report: ## Combine and report coverage
 ##@ Documentation
 
 docs-install: ## Install docs dependencies (included in default groups)
-	uv sync --group docs
+	uv sync $(PYTHON_ARG) --group docs
 
 docs-serve: ## Serve local docs preview (hot reload)
-	uv run mkdocs serve -f mkdocs/mkdocs.yml
+	uv run $(PYTHON_ARG) mkdocs serve -f mkdocs/mkdocs.yml
 
 docs-build: ## Build the static documentation site
-	uv run mkdocs build -f mkdocs/mkdocs.yml --strict
+	uv run $(PYTHON_ARG) mkdocs build -f mkdocs/mkdocs.yml --strict
 
 # ===================
 # Project Maintenance

dev/.rat-excludes

@@ -5,5 +5,3 @@ build
 .gitignore
 uv.lock
 mkdocs/*
-setup.cfg
-(^|.*/)[^/]*\.egg-info(/.*)?$

mkdocs/docs/configuration.md

@@ -551,6 +551,28 @@ catalog:
       type: noop
 ```
 
+##### GCP BigLake Metastore Catalog REST
+
+```yaml
+catalog:
+  biglake_catalog:
+    type: rest
+    uri: https://biglake.googleapis.com/iceberg/v1/restcatalog
+    warehouse: gs://<bucket-name>  # Use bq://projects/<gcp-project-id> for federation option (see docs)
+    auth:
+      type: google
+    header.x-goog-user-project: <gcp-project-id>
+    header.X-Iceberg-Access-Delegation: "" # For user-credentials authentication, set to empty string.
+```
+
+<!-- prettier-ignore-start -->
+
+!!! Note "Metastore Authentication Models"
+    If your BigLake Metastore catalog is configured for "user credentials" authentication instead of "vendor credentials", set the `header.X-Iceberg-Access-Delegation` header to an empty string as shown above.  Standard GCP Application Default Credentials (ADC) will be used to authenticate requests to the BigLake Metastore REST API.
+    You can retrieve the configuration details for your BigLake Iceberg catalog at the [GCP Console BigLake Metastore page](https://console.cloud.google.com/biglake/metastore/catalogs). Select your catalog, then find the necessary parameters such as `uri`, `warehouse`, and authentication method (e.g. user-creds or vendor).
+
+<!-- prettier-ignore-end -->
+
 ### 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):

pyiceberg/avro/codecs/__init__.py

@@ -26,9 +26,7 @@
 
 from __future__ import annotations
 
-from typing import Dict, Literal, Type
-
-from typing_extensions import TypeAlias
+from typing import Literal, TypeAlias
 
 from pyiceberg.avro.codecs.bzip2 import BZip2Codec
 from pyiceberg.avro.codecs.codec import Codec
@@ -40,7 +38,7 @@
 
 AVRO_CODEC_KEY = "avro.codec"
 
-KNOWN_CODECS: Dict[AvroCompressionCodec, Type[Codec] | None] = {
+KNOWN_CODECS: dict[AvroCompressionCodec, type[Codec] | None] = {
     "null": None,
     "bzip2": BZip2Codec,
     "snappy": SnappyCodec,
@@ -49,4 +47,4 @@
 }
 
 # Map to convert the naming from Iceberg to Avro
-CODEC_MAPPING_ICEBERG_TO_AVRO: Dict[str, str] = {"gzip": "deflate", "zstd": "zstandard"}
+CODEC_MAPPING_ICEBERG_TO_AVRO: dict[str, str] = {"gzip": "deflate", "zstd": "zstandard"}

pyiceberg/avro/decoder.py

@@ -18,9 +18,6 @@
 from abc import ABC, abstractmethod
 from io import SEEK_CUR
 from typing import (
-    Dict,
-    List,
-    Tuple,
     cast,
 )
 
@@ -67,11 +64,11 @@ def read_int(self) -> int:
         datum = (n >> 1) ^ -(n & 1)
         return datum
 
-    def read_ints(self, n: int) -> Tuple[int, ...]:
+    def read_ints(self, n: int) -> tuple[int, ...]:
         """Read a list of integers."""
         return tuple(self.read_int() for _ in range(n))
 
-    def read_int_bytes_dict(self, n: int, dest: Dict[int, bytes]) -> None:
+    def read_int_bytes_dict(self, n: int, dest: dict[int, bytes]) -> None:
         """Read a dictionary of integers for keys and bytes for values into a destination dictionary."""
         for _ in range(n):
             k = self.read_int()
@@ -85,7 +82,7 @@ def read_float(self) -> float:
         The float is converted into a 32-bit integer using a method equivalent to
         Java's floatToIntBits and then encoded in little-endian format.
         """
-        return float(cast(Tuple[float, ...], STRUCT_FLOAT.unpack(self.read(4)))[0])
+        return float(cast(tuple[float, ...], STRUCT_FLOAT.unpack(self.read(4)))[0])
 
     def read_double(self) -> float:
         """Read a value from the stream as a double.
@@ -94,7 +91,7 @@ def read_double(self) -> float:
         The double is converted into a 64-bit integer using a method equivalent to
         Java's doubleToLongBits and then encoded in little-endian format.
         """
-        return float(cast(Tuple[float, ...], STRUCT_DOUBLE.unpack(self.read(8)))[0])
+        return float(cast(tuple[float, ...], STRUCT_DOUBLE.unpack(self.read(8)))[0])
 
     def read_bytes(self) -> bytes:
         """Bytes are encoded as a long followed by that many bytes of data."""
@@ -152,7 +149,7 @@ def read(self, n: int) -> bytes:
         """Read n bytes."""
         if n < 0:
             raise ValueError(f"Requested {n} bytes to read, expected positive integer.")
-        data: List[bytes] = []
+        data: list[bytes] = []
 
         n_remaining = n
         while n_remaining > 0:
@@ -181,6 +178,6 @@ def new_decoder(b: bytes) -> BinaryDecoder:
     except ModuleNotFoundError:
         import warnings
 
-        warnings.warn("Falling back to pure Python Avro decoder, missing Cython implementation")
+        warnings.warn("Falling back to pure Python Avro decoder, missing Cython implementation", stacklevel=2)
 
         return StreamingBinaryDecoder(b)