chore: fix merge conflicts

.github/labeler.yml

@@ -0,0 +1,103 @@
+# backends
+bigquery:
+  - changed-files:
+      - any-glob-to-any-file: "ibis/backends/bigquery/**"
+
+clickhouse:
+  - changed-files:
+      - any-glob-to-any-file: "ibis/backends/clickhouse/**"
+
+datafusion:
+  - changed-files:
+      - any-glob-to-any-file: "ibis/backends/datafusion/**"
+
+druid:
+  - changed-files:
+      - any-glob-to-any-file: "ibis/backends/druid/**"
+
+duckdb:
+  - changed-files:
+      - any-glob-to-any-file: "ibis/backends/duckdb/**"
+
+exasol:
+  - changed-files:
+      - any-glob-to-any-file: "ibis/backends/exasol/**"
+
+flink:
+  - changed-files:
+      - any-glob-to-any-file: "ibis/backends/flink/**"
+
+impala:
+  - changed-files:
+      - any-glob-to-any-file: "ibis/backends/impala/**"
+
+mssql:
+  - changed-files:
+      - any-glob-to-any-file: "ibis/backends/mssql/**"
+
+mysql:
+  - changed-files:
+      - any-glob-to-any-file: "ibis/backends/mysql/**"
+
+oracle:
+  - changed-files:
+      - any-glob-to-any-file: "ibis/backends/oracle/**"
+
+polars:
+  - changed-files:
+      - any-glob-to-any-file: "ibis/backends/polars/**"
+
+postgres:
+  - changed-files:
+      - any-glob-to-any-file: "ibis/backends/postgres/**"
+
+pyspark:
+  - changed-files:
+      - any-glob-to-any-file: "ibis/backends/pyspark/**"
+
+risingwave:
+  - changed-files:
+      - any-glob-to-any-file: "ibis/backends/risingwave/**"
+
+snowflake:
+  - changed-files:
+      - any-glob-to-any-file: "ibis/backends/snowflake/**"
+
+sqlite:
+  - changed-files:
+      - any-glob-to-any-file: "ibis/backends/sqlite/**"
+
+trino:
+  - changed-files:
+      - any-glob-to-any-file: "ibis/backends/trino/**"
+
+# miscellaneous labels
+tests:
+  - changed-files:
+      - any-glob-to-any-file: "**/tests/**"
+
+nix:
+  - changed-files:
+      - any-glob-to-any-file: "**/*.nix"
+      - any-glob-to-any-file: "poetry.lock"
+
+datatypes:
+  - changed-files:
+      - any-glob-to-any-file: "ibis/expr/datatypes/**"
+
+ci:
+  - changed-files:
+      - any-glob-to-any-file: ".github/**"
+
+dependencies:
+  - changed-files:
+      - any-glob-to-any-file: "**/*.nix"
+      - any-glob-to-any-file: "poetry.lock"
+      - any-glob-to-any-file: "flake.lock"
+      - any-glob-to-any-file: "requirements-dev.txt"
+      - any-glob-to-any-file: "conda/*.yml"
+
+docs:
+  - changed-files:
+      - any-glob-to-any-file: "**/*.qmd"
+      - any-glob-to-any-file: "**/*.md"

.github/renovate.json

@@ -67,7 +67,7 @@
       "addLabels": ["druid"]
     },
     {
-      "matchPackagePatterns": ["pymysql", "mariadb"],
+      "matchPackagePatterns": ["mysqlclient", "mariadb"],
       "addLabels": ["mysql"]
     },
     {
@@ -78,6 +78,10 @@
       "matchPackagePatterns": ["pyspark"],
       "addLabels": ["pyspark"]
     },
+    {
+      "matchPackagePatterns": ["risingwave"],
+      "addLabels": ["risingwave"]
+    },
     {
       "matchPackagePatterns": ["snowflake-connector-python"],
       "addLabels": ["snowflake"]

.github/workflows/algolia/configure-algolia-api.py

@@ -9,6 +9,15 @@
 index_name = os.environ["ALGOLIA_INDEX"]
 
 
+ONE_WAY_SYNONYMS = {
+    # A list of search terms that have (historically) not returned results
+    # that we can map to existing search terms that we know are good
+    "md5": ["hashbytes"],
+    "fetchdf": ["to_pandas", "to_polars", "to_pyarrow"],
+    "unique": ["distinct"],
+}
+
+
 def main():
     client = SearchClient.create(app_id, api_key)
     index = client.init_index(index_name)
@@ -30,6 +39,16 @@ def main():
 
     index.set_settings(override_default_settings)
 
+    for input_, synonyms in ONE_WAY_SYNONYMS.items():
+        index.save_synonym(
+            {
+                "objectID": input_,
+                "type": "oneWaySynonym",
+                "input": input_,
+                "synonyms": synonyms,
+            }
+        )
+
 
 if __name__ == "__main__":
     main()

.github/workflows/docs-preview.yml

@@ -77,7 +77,7 @@ jobs:
           path: docs/**/.jupyter_cache
 
       - name: build docs
-        run: nix develop --ignore-environment --keep HOME -c just docs-build-all
+        run: nix develop '.#ibis311' --ignore-environment --keep HOME -c just docs-build-all
 
       - name: install netlify cli
         run: npm install -g netlify-cli

.github/workflows/ibis-backends.yml

@@ -123,6 +123,7 @@ jobs:
               - sqlite
           - name: datafusion
             title: DataFusion
+            serial: true
             extras:
               - datafusion
           - name: polars
@@ -140,6 +141,7 @@ jobs:
               - polars
             sys-deps:
               - libgeos-dev
+              - default-libmysqlclient-dev
           - name: postgres
             title: PostgreSQL
             extras:
@@ -270,6 +272,7 @@ jobs:
                 - mysql
               sys-deps:
                 - libgeos-dev
+                - default-libmysqlclient-dev
           - os: windows-latest
             backend:
               name: clickhouse
@@ -650,24 +653,27 @@ jobs:
         run: docker compose logs
 
   test_pyspark:
-    name: PySpark ${{ matrix.pyspark-version }} ubuntu-latest python-${{ matrix.python-version }}
+    name: PySpark ${{ matrix.pyspark-minor-version }} ubuntu-latest python-${{ matrix.python-version }}
     runs-on: ubuntu-latest
     strategy:
       fail-fast: false
       matrix:
         include:
           - python-version: "3.10"
             pyspark-version: "3.3.3"
+            pyspark-minor-version: "3.3"
             deps:
               - "'pandas@<2'"
               - "'numpy@<1.24'"
           - python-version: "3.11"
-            pyspark-version: "3.5"
+            pyspark-version: "3.5.2"
+            pyspark-minor-version: "3.5"
             deps:
               - "'pandas@>2'"
               - "'numpy@>1.24'"
           - python-version: "3.12"
-            pyspark-version: "3.5"
+            pyspark-version: "3.5.2"
+            pyspark-minor-version: "3.5"
             deps:
               - "'pandas@>2'"
               - "'numpy@>1.24'"
@@ -722,8 +728,7 @@ jobs:
 
       - name: install iceberg
         shell: bash
-        if: matrix.pyspark-version == '3.5'
-        run: pushd "$(poetry run python -c "import pyspark; print(pyspark.__file__.rsplit('/', 1)[0])")/jars" && curl -LO https://search.maven.org/remotecontent?filepath=org/apache/iceberg/iceberg-spark-runtime-3.5_2.12/1.5.2/iceberg-spark-runtime-3.5_2.12-1.5.2.jar
+        run: just download-iceberg-jar ${{ matrix.pyspark-minor-version }}
 
       - name: run tests
         run: just ci-check -m pyspark

.github/workflows/ibis-docs-main.yml

@@ -57,6 +57,8 @@ jobs:
 
       - name: checkout
         uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
 
       - name: restore cache of the previously rendered notebooks
         uses: actions/cache/restore@v4
@@ -67,10 +69,10 @@ jobs:
           path: docs/**/.jupyter_cache
 
       - name: build api docs
-        run: nix develop --ignore-environment -c just docs-apigen --verbose
+        run: nix develop '.#ibis311' --ignore-environment -c just docs-apigen --verbose
 
       - name: build docs
-        run: nix develop --ignore-environment --keep HOME -c just docs-render
+        run: nix develop '.#ibis311' --ignore-environment --keep HOME -c just docs-render
 
       - name: cache rendered notebooks
         uses: actions/cache/save@v4
@@ -79,7 +81,7 @@ jobs:
           path: docs/**/.jupyter_cache
 
       - name: build jupyterlite
-        run: nix develop --ignore-environment --keep HOME -c just build-jupyterlite
+        run: nix develop '.#ibis311' --ignore-environment --keep HOME -c just build-jupyterlite
 
       - name: check that all frozen computations were done before push
         run: git diff --exit-code --stat

.github/workflows/ibis-docs-pr.yml

@@ -67,13 +67,13 @@ jobs:
           path: docs/**/.jupyter_cache
 
       - name: generate api docs
-        run: nix develop --ignore-environment -c just docs-apigen --verbose
+        run: nix develop '.#ibis311' --ignore-environment -c just docs-apigen --verbose
 
       - name: build docs
-        run: nix develop --ignore-environment --keep HOME -c just docs-render
+        run: nix develop '.#ibis311' --ignore-environment --keep HOME -c just docs-render
 
       - name: build jupyterlite
-        run: nix develop --ignore-environment --keep HOME -c just build-jupyterlite
+        run: nix develop '.#ibis311' --ignore-environment --keep HOME -c just build-jupyterlite
 
       - name: check that all frozen computations were done before push
         run: git diff --exit-code --stat

.github/workflows/labeler.yml

@@ -0,0 +1,12 @@
+name: PR Labeler
+on:
+  - pull_request_target
+
+jobs:
+  labeler:
+    permissions:
+      contents: read
+      pull-requests: write
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/labeler@v5

README.md

@@ -218,3 +218,7 @@ Ibis is an open source project and welcomes contributions from anyone in the com
 Join our community by interacting on GitHub or chatting with us on [Zulip](https://ibis-project.zulipchat.com/).
 
 For more information visit https://ibis-project.org/.
+
+## Governance
+
+The Ibis project is an [independently governed](https://github.com/ibis-project/governance/blob/main/governance.md) open source community project to build and maintain the portable Python dataframe library. Ibis has contributors across a range of data companies and institutions.

compose.yaml

@@ -99,7 +99,7 @@ services:
       - trino
 
   minio:
-    image: bitnami/minio:2024.9.9
+    image: bitnami/minio:2024.9.13
     environment:
       MINIO_ROOT_USER: accesskey
       MINIO_ROOT_PASSWORD: secretkey
@@ -161,7 +161,7 @@ services:
       test:
         - CMD-SHELL
         - trino --output-format null --execute 'show schemas in hive; show schemas in memory'
-    image: trinodb/trino:457
+    image: trinodb/trino:458
     ports:
       - 8080:8080
     networks:
@@ -204,7 +204,7 @@ services:
       - druid
 
   druid-coordinator:
-    image: apache/druid:30.0.0
+    image: apache/druid:30.0.1
     hostname: coordinator
     container_name: coordinator
     volumes:
@@ -229,7 +229,7 @@ services:
       - druid
 
   druid-broker:
-    image: apache/druid:30.0.0
+    image: apache/druid:30.0.1
     hostname: broker
     container_name: broker
     volumes:
@@ -257,7 +257,7 @@ services:
       - druid
 
   druid-historical:
-    image: apache/druid:30.0.0
+    image: apache/druid:30.0.1
     hostname: historical
     container_name: historical
     volumes:
@@ -284,7 +284,7 @@ services:
       - druid
 
   druid-middlemanager:
-    image: apache/druid:30.0.0
+    image: apache/druid:30.0.1
     hostname: middlemanager
     container_name: middlemanager
     volumes:
@@ -312,7 +312,7 @@ services:
       - druid
 
   druid:
-    image: apache/druid:30.0.0
+    image: apache/druid:30.0.1
     hostname: router
     container_name: router
     volumes:
@@ -557,7 +557,7 @@ services:
       - impala
 
   risingwave:
-    image: ghcr.io/risingwavelabs/risingwave:v1.10.1
+    image: ghcr.io/risingwavelabs/risingwave:v2.0.0
     command: "standalone --meta-opts=\" \
       --advertise-addr 0.0.0.0:5690 \
       --backend mem \

conda/environment-arm64-flink.yml

@@ -33,7 +33,7 @@ dependencies:
   - pyarrow-hotfix >=0.4
   - pydata-google-auth
   - pydruid >=0.6.5
-  - pymysql >=1
+  - mysqlclient >=2.2.4
   - pyspark >=3
   - python-dateutil >=2.8.2
   - python-duckdb >=0.8.1

conda/environment-arm64.yml

@@ -33,7 +33,7 @@ dependencies:
   - pyarrow-hotfix >=0.4
   - pydata-google-auth
   - pydruid >=0.6.5
-  - pymysql >=1
+  - mysqlclient >=2.2.4
   - pyodbc >=4.0.39
   - pyspark >=3
   - python-dateutil >=2.8.2

conda/environment.yml

@@ -33,7 +33,7 @@ dependencies:
   - pyarrow-hotfix >=0.4
   - pydata-google-auth
   - pydruid >=0.6.5
-  - pymysql >=1
+  - mysqlclient >=2.2.4
   - pyodbc >=4.0.39
   - pyspark >=3
   - python >=3.10