Set up devcontainer configuration

.devcontainer/Dockerfile

@@ -0,0 +1,66 @@
+FROM mcr.microsoft.com/devcontainers/python:1-3.9-bookworm
+
+ARG SPARK_VERSION=3.5.5
+ARG HADOOP_VERSION=3.4.1
+ARG OPENJDK_VERSION=17
+
+ENV DEBIAN_FRONTEND=noninteractive
+ENV TZ=Etc/UTC
+ENV LC_ALL=C.UTF-8
+ENV LANG=C.UTF-8
+
+# install dependencies
+RUN apt-get update && \
+    apt-get install -y --no-install-recommends \
+    alien \
+    build-essential \
+    curl \
+    git \
+    procps \
+    libffi-dev \
+    libpq-dev \
+    libssl-dev \
+    lsb-release \
+    odbcinst \
+    openjdk-${OPENJDK_VERSION}-jre-headless \
+    unixodbc-dev
+
+# Install Microsoft ODBC driver 18 for SQL Server https://learn.microsoft.com/en-us/sql/connect/odbc/linux-mac/installing-the-microsoft-odbc-driver-for-sql-server
+RUN curl https://packages.microsoft.com/keys/microsoft.asc | apt-key add - && \
+    echo "deb [arch=$(dpkg --print-architecture)] https://packages.microsoft.com/debian/12/prod $(lsb_release -cs) main" > /etc/apt/sources.list.d/microsoft-prod.list && \
+    apt-get update && \
+    ACCEPT_EULA=Y apt-get install -y libsasl2-dev odbcinst mssql-tools18 msodbcsql18 unixodbc-dev
+
+# Dremio support
+RUN curl -L https://download.dremio.com/arrow-flight-sql-odbc-driver/arrow-flight-sql-odbc-driver-LATEST.x86_64.rpm -o arrow-driver.rpm && \
+    alien -iv --scripts arrow-driver.rpm
+
+# Spark support
+ENV SPARK_HOME=/usr/local/spark
+
+RUN HADOOP_MAJOR_VERSION=`echo ${HADOOP_VERSION} | cut -d. -f1` && \
+    wget -qO "spark.tgz" "https://archive.apache.org/dist/spark/spark-${SPARK_VERSION}/spark-${SPARK_VERSION}-bin-hadoop${HADOOP_MAJOR_VERSION}.tgz"; \
+    tar xzf "spark.tgz" -C /usr/local --owner root --group root --no-same-owner && \
+    rm "spark.tgz" && \
+    ln -s "spark-${SPARK_VERSION}-bin-hadoop${HADOOP_MAJOR_VERSION}" "${SPARK_HOME}"
+
+# Install native Hadoop libraries
+RUN wget -qO "hadoop.tgz" "https://www.apache.org/dist/hadoop/common/hadoop-${HADOOP_VERSION}/hadoop-${HADOOP_VERSION}.tar.gz"; \
+    tar xzf "hadoop.tgz" -C /opt/ --owner root --group root --no-same-owner && \
+    rm "hadoop.tgz" && \
+    ln -s /opt/hadoop-$HADOOP_VERSION/etc/hadoop /etc/hadoop && \
+    mkdir /opt/hadoop-$HADOOP_VERSION/logs
+
+# Configure Spark and Hadoop
+ENV SPARK_OPTS="--driver-java-options=-Xms1024M --driver-java-options=-Xmx4096M --driver-java-options=-Dlog4j.logLevel=info"
+ENV HADOOP_HOME="/opt/hadoop-${HADOOP_VERSION}"
+ENV HADOOP_CONF_DIR=/etc/hadoop
+ENV MULTIHOMED_NETWORK=1
+ENV HADOOP_COMMON_LIB_NATIVE_DIR="${HADOOP_HOME}/lib/native"
+ENV HADOOP_OPTS="${HADOOP_OPTS} -Djava.library.path=${HADOOP_HOME}/lib/native"
+ENV LD_LIBRARY_PATH="${HADOOP_HOME}/lib/native"
+
+ENV PATH="${PATH}:${SPARK_HOME}/bin:${HADOOP_HOME}/bin/"
+
+# Run sleep infinity so that the dev container stays alive
+CMD [ "sleep", "infinity" ]

.devcontainer/devcontainer.json

@@ -0,0 +1,52 @@
+{
+	"name": "soda-core",
+	"dockerComposeFile": [
+		"docker-compose.yml",
+		"../soda/postgres/docker-compose.yml",
+		"../soda/spark/tests/docker/docker-compose.yml",
+		"../soda/vertica/docker-compose.yml"
+	],
+	"service": "devcontainer",
+	"features": {
+		"docker-in-docker": {
+			"version": "latest"
+		}
+	},
+	"postStartCommand": "./.devcontainer/initialize.sh",
+	"workspaceFolder": "/workspaces/${localWorkspaceFolderBasename}",
+	"customizations": {
+		"vscode": {
+			"extensions": [
+				"ms-python.python",
+				"ms-python.mypy-type-checker",
+				"ms-python.black-formatter",
+				"ms-python.isort",
+				"ms-azuretools.vscode-docker"
+			],
+			"settings": {
+				"editor.formatOnSave": true,
+				"editor.formatOnType": true,
+				"files.exclude": {
+					".mypy_cache": true,
+					".venv": true,
+					".pytest_cache": true,
+					"**/*.egg-info": true,
+					"**/__pycache__": true,
+					"soda/*/build": true
+				},
+				"python.analysis.enablePytestSupport": true,
+				"python.defaultInterpreterPath": ".venv/bin/python",
+				"python.testing.pytestEnabled": true,
+				"python.testing.pytestPath": "soda/core/tests/",
+				"python.languageServer": "Pylance",
+				"[python]": {
+					"editor.defaultFormatter": "ms-python.black-formatter",
+					"editor.codeActionsOnSave": {
+						"source.organizeImports": "always",
+						"source.fixAll": "always"
+					}
+				}
+			}
+		}
+	}
+}

.devcontainer/docker-compose.yml

@@ -0,0 +1,8 @@
+services:
+  devcontainer:
+    build:
+      context: .
+      dockerfile: Dockerfile
+    environment:
+      POSTGRES_HOST: soda-sql-postgres
+      test_data_source: postgres

.devcontainer/initialize.sh

@@ -0,0 +1,13 @@
+#!/usr/bin/env bash
+set -x
+
+# Create the virtual environment if it does not already exist
+if [ ! -d .venv ]; then
+  scripts/recreate_venv.sh
+fi
+
+# Activate the virtual environment
+source .venv/bin/activate
+
+# Setup pre-commit
+pre-commit install

soda/postgres/tests/postgres_data_source_fixture.py

@@ -18,7 +18,7 @@ def _build_configuration_dict(self, schema_name: str | None = None) -> dict:
         return {
             "data_source postgres": {
                 "type": "postgres",
-                "host": "localhost",
+                "host": os.getenv("POSTGRES_HOST", "localhost"),
                 "username": os.getenv("POSTGRES_USERNAME", "sodasql"),
                 "password": os.getenv("POSTGRES_PASSWORD"),
                 "database": os.getenv("POSTGRES_DATABASE", "sodasql"),