1 dockerization for entire stack

Dockerfile

@@ -0,0 +1,21 @@
+FROM python:3.12-slim
+
+# Keep Python output unbuffered so logs stream immediately.
+ENV PYTHONDONTWRITEBYTECODE=1 \
+    PYTHONUNBUFFERED=1
+
+WORKDIR /app
+
+# Copy and install the package defined in pyproject.toml.
+COPY . /app
+RUN pip install --no-cache-dir '.[db]'
+
+# Run from the package source directory so bundled data/input and data/output paths resolve.
+WORKDIR /app/src/provider_simenv
+
+# Pass simulation arguments directly to main.py.
+# Example:
+#   docker run --rm simenv --pdl scenarios/s1-soja.pdl.yaml \
+#     --postgres-url postgresql+psycopg2://postgres:postgres@host:5432/provider_simenv
+ENTRYPOINT ["python", "main.py"]
+CMD ["--pdl", "scenarios/s1-soja.pdl.yaml"]

README.md

@@ -150,6 +150,29 @@ Scenarios are defined in `data/input/SimulatorScenarios.csv`. Each row is one sc
 
 ---
 
+## Run in docker container
+
+The simulation can also be run in a docker container.
+First, build the container. In the repo root run
+
+```bash
+docker build -t provider-simenv .
+```
+
+Then you can run the simulation in the container with
+
+```bash
+docker run --rm -v <path to pdl file directory>:/scenarios provider-simenv --pdl /scenarios/<pdl filename>
+```
+
+You can also configure a PostgreSQL interface for data storage (see next chapter) with
+
+```bash
+docker run --rm -v <path to pdl file directory>:/scenarios provider-simenv --pdl /scenarios/<pdl filename> --postgres-url <PostgreSQL URL string>
+```
+
+---
+
 ## PostgreSQL Setup (Optional)
 
 PostgreSQL enables live data access during the simulation — required for future palaestrAI
@@ -209,6 +232,19 @@ Subsequent scenarios within the same run append to the existing tables.
 
 ---
 
+## docker-compose
+
+You can also run a docker compose that sets up a PostgreSQL database and links it to the simulation container.
+Using our helper script, everything is configured automatically. 
+Just run
+
+```bash
+./compose-up.sh <path to pdl file>
+```
+from the repository root. This builds the database container, if it's not already up and runs a simulation of the specified pdl file. You can run different configurations by simply repeating this call with the respective paths.
+
+---
+
 ## Output Files
 
 | File | Description |

compose-up.sh

@@ -0,0 +1,23 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+if [[ $# -lt 1 ]]; then
+  echo "Usage: $0 <path-to-pdl-file> [docker compose args...]" >&2
+  echo "Example: $0 src/provider_simenv/scenarios/s1-soja.pdl.yaml" >&2
+  exit 1
+fi
+
+pdl_input="$1"
+shift || true
+
+if [[ ! -f "$pdl_input" ]]; then
+  echo "Error: PDL file not found: $pdl_input" >&2
+  exit 1
+fi
+
+pdl_abs="$(cd "$(dirname "$pdl_input")" && pwd)/$(basename "$pdl_input")"
+export PDL_DIR="$(dirname "$pdl_abs")"
+export PDL_FILE="$(basename "$pdl_abs")"
+
+# Start postgres and simulation. The postgres named volume keeps DB data across runs.
+docker compose up simenv "$@"

docker-compose.yml

@@ -0,0 +1,37 @@
+services:
+  postgres:
+    image: postgres:16
+    container_name: provider-simenv-postgres
+    environment:
+      POSTGRES_DB: provider_simenv
+      POSTGRES_USER: postgres
+      POSTGRES_PASSWORD: postgres
+    ports:
+      - "5432:5432"
+    volumes:
+      - simenv_postgres_data:/var/lib/postgresql/data
+    healthcheck:
+      test: ["CMD-SHELL", "pg_isready -U postgres -d provider_simenv"]
+      interval: 5s
+      timeout: 5s
+      retries: 12
+
+  simenv:
+    build:
+      context: .
+      dockerfile: Dockerfile
+    image: provider-simenv:latest
+    depends_on:
+      postgres:
+        condition: service_healthy
+    volumes:
+      - ${PDL_DIR:?Set PDL_DIR to the directory that contains the PDL file}:/pdl:ro
+    command:
+      - --pdl
+      - /pdl/${PDL_FILE:?Set PDL_FILE to the PDL filename}
+      - --postgres-url
+      - postgresql+psycopg2://postgres:postgres@postgres:5432/provider_simenv
+    restart: "no"
+
+volumes:
+  simenv_postgres_data:

src/provider_simenv/db_config.py

@@ -11,6 +11,7 @@
     print(cfg)      # safe repr, password masked
 """
 
+import os
 from dataclasses import dataclass, field
 
 @dataclass
@@ -23,18 +24,23 @@ class PostgresDBConfig:
     - palaestrAI: host=<server>, port=<port>, user=<user>, password=<pw>
     """
 
-    host: str = "localhost"
-    port: int = 5432
-    dbname: str = "provider_simenv"
-    user: str = "postgres"
-    password: str = "postgres"
+    host: str = field(default_factory=lambda: os.getenv("PROVIDER_SIMENV_PG_HOST", "localhost"))
+    port: int = field(default_factory=lambda: int(os.getenv("PROVIDER_SIMENV_PG_PORT", "5432")))
+    dbname: str = field(default_factory=lambda: os.getenv("PROVIDER_SIMENV_PG_DB", "provider_simenv"))
+    user: str = field(default_factory=lambda: os.getenv("PROVIDER_SIMENV_PG_USER", "postgres"))
+    password: str = field(default_factory=lambda: os.getenv("PROVIDER_SIMENV_PG_PASSWORD", "postgres"))
+    postgres_url: str | None = field(default_factory=lambda: os.getenv("PROVIDER_SIMENV_POSTGRES_URL"))
 
     def sqlalchemy_url(self) -> str:
         """
         Return a SQLAlchemy-compativbe connection URL.
 
         Example: postgresql+psycopg2://postgres:postgres@localhost:5432/provider_simenv
         """
+        if self.postgres_url:
+            # Accept either postgresql://... or postgresql+psycopg2://...
+            return self.postgres_url
+
         return (
             f"postgresql+psycopg2://{self.user}:{self.password}"
             f"@{self.host}:{self.port}/{self.dbname}"

src/provider_simenv/main.py

@@ -73,8 +73,22 @@ def csv_to_sqlite(output_dir: str, db_name: str = "provider-simenv.sqlite") -> N
             "with values derived from the PDL before the simulation runs."
         ),
     )
+    parser.add_argument(
+        "--postgres-url",
+        type=str,
+        default=None,
+        metavar="URL",
+        help=(
+            "Optional PostgreSQL SQLAlchemy connection string for tick writes, "
+            "e.g. postgresql+psycopg2://user:pass@host:5432/dbname"
+        ),
+    )
     args = parser.parse_args()
 
+    if args.postgres_url:
+        os.environ["PROVIDER_SIMENV_POSTGRES_URL"] = args.postgres_url
+        print("[main] Using PostgreSQL connection string from --postgres-url")
+
     # Folder paths (both needed for PDL injection and Config)
     here = os.path.dirname(os.path.abspath(__file__))
     input_folder = os.path.join(here, "data", "input")