try to setup github actions to test workload identity federation

.github/workflows/bigquery.yml

@@ -0,0 +1,58 @@
+# Simple workflow for deploying static content to GitHub Pages
+name: Run BigQuery snippets as a test
+
+on:
+  push:
+    paths-ignore:
+      - ".gitignore"
+    branches:
+      - main
+  pull_request_target:
+    types:
+      - labeled
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    if: github.event_name == 'push' || github.event.label.name == 'ci-run-cloud'
+
+    # Add "id-token" with the intended permissions.
+    permissions:
+      contents: 'read'
+      # required for GCP workload identity federation
+      id-token: 'write'
+
+    steps:
+    - name: checkout
+      uses: actions/checkout@v4
+      if: github.event.label.name != 'ci-run-cloud'
+
+    - name: checkout
+      if: github.event.label.name == 'ci-run-cloud'
+      uses: actions/checkout@v4
+      with:
+        fetch-depth: 0
+        ref: ${{ github.event.pull_request.head.sha }}
+
+    - name: Set up Python
+      # This is the version of the action for setting up Python, not the Python version.
+      uses: actions/setup-python@v5
+      with:
+        # Semantic version range syntax or exact version of a Python version
+        python-version: '3.12'
+        # Optional - x64 or x86 architecture, defaults to x64
+        architecture: 'x64'
+
+    - uses: 'google-github-actions/auth@v2'
+      with:
+        project_id: 'friendliness-dev-demo'
+        workload_identity_provider: 'projects/368174856750/locations/global/workloadIdentityPools/github/providers/code-snippets'
+
+    - name: Display Python version
+      run: python -c "import sys; print(sys.version)"
+
+    - name: Install packages
+      run: python -m pip install -r requirements.txt
+
+    - name: Test the notebook
+      run: python -m jupyter nbconvert --to html --execute 2024/12-bigquery-utils/bigquery-utils.ipynb

2024/12-bigquery-utils/bigquery-utils.ipynb

@@ -0,0 +1,243 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%load_ext bigquery_magics"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Try a query that doesn't require any additional libraries."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "e44fc98d1439478482520de48f1e4b6c",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Query is running:   0%|          |"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "aa559ce9c11540af9b8a7f9c94138063",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading:   0%|          |"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>x</th>\n",
+       "      <th>hex</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1</td>\n",
+       "      <td>0000000000000001</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>123456</td>\n",
+       "      <td>000000000001e240</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>9876543210</td>\n",
+       "      <td>000000024cb016ea</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>-1001</td>\n",
+       "      <td>fffffffffffffc17</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "            x               hex\n",
+       "0           1  0000000000000001\n",
+       "1      123456  000000000001e240\n",
+       "2  9876543210  000000024cb016ea\n",
+       "3       -1001  fffffffffffffc17"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "%%bigquery\n",
+    "SELECT\n",
+    "  x,\n",
+    "  bqutil.fn.to_hex(x) AS hex\n",
+    "FROM\n",
+    "  UNNEST([1, 123456, 9876543210, -1001]) AS x;"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Try a function that uses a JS library hosted in GCS. See: https://github.com/GoogleCloudPlatform/bigquery-utils/pull/434 and https://github.com/GoogleCloudPlatform/bigquery-utils/blob/master/udfs/community/README.md#xml_to_jsonxml-string\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "9a7df3ece0584d909681ec621cdbbfd6",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Query is running:   0%|          |"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "38ff038524e84cc39d7c6adf5ae33807",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading:   0%|          |"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>output_json</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>{\"xml\":{\"_attributes\":{\"foo\":\"FOO\"},\"bar\":{\"ba...</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                                         output_json\n",
+       "0  {\"xml\":{\"_attributes\":{\"foo\":\"FOO\"},\"bar\":{\"ba..."
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "%%bigquery\n",
+    "SELECT bqutil.fn.xml_to_json(\n",
+    "  '<xml foo=\"FOO\"><bar><baz>BAZ</baz></bar></xml>'\n",
+    ") AS output_json"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "scratch",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}