Muna N.

Dockerfile

@@ -1,24 +1,10 @@
-# Task 4: Write a cache-friendly Dockerfile.
-#
-# Requirements (in order):
-# 1. Use python:3.11-slim as the base image.
-# 2. Copy requirements.txt BEFORE copying source code.
-# 3. Install dependencies from requirements.txt.
-# 4. Copy src/ into the image.
-# 5. Set the CMD to run the pipeline: python -m src.pipeline
-#
-# Replace each TODO comment with the correct Dockerfile instruction.
-
-# TODO: set the base image
-FROM TODO
+FROM python:3.11-slim
 
 WORKDIR /app
 
-# TODO: copy requirements.txt (before source — this keeps the install layer cached)
-
-# TODO: install dependencies
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
 
-# TODO: copy source code
+COPY . .
 
-# TODO: set the command that runs when the container starts
-CMD ["TODO"]
+CMD ["python", "-m", "src.pipeline"]

src/pipeline.py

@@ -9,6 +9,7 @@
 """
 
 import logging
+import os
 from pathlib import Path
 
 logging.basicConfig(level=logging.INFO, format="%(levelname)s %(message)s")
@@ -21,40 +22,56 @@ def get_config() -> dict:
 
     Required variable: API_KEY
     Optional variable: OUTPUT_DIR (default "output")
-
-    Raise RuntimeError with a clear message if a required variable is missing.
     """
-    raise NotImplementedError("Task 5: read API_KEY and OUTPUT_DIR from the environment")
+    api_key = os.getenv("API_KEY")
+
+    if not api_key:
+        raise RuntimeError("API_KEY is missing")
+
+    output_dir = os.getenv("OUTPUT_DIR", "output")
+
+    return {
+        "api_key": api_key,
+        "output_dir": output_dir,
+    }
 
 
 def fetch_data(api_key: str) -> list[dict]:
     """
     Simulate fetching records from an external API.
-
-    Return a list of at least one dict representing a record.
-    In a real pipeline you would call requests.get(...) here.
     """
-    raise NotImplementedError("Task 1: return at least one sample record")
+    return [
+        {"id": 1, "name": "Muna", "city": "Amsterdam"},
+        {"id": 2, "name": "Ali", "city": "Rotterdam"},
+    ]
 
 
 def save_results(records: list[dict], output_dir: Path) -> None:
     """
-    Write each record as a line to output_dir/results.txt.
-
-    Create output_dir if it does not exist.
-    Log the number of records written.
+    Write each record as a line to output_dir/results.txt
     """
-    raise NotImplementedError("Task 1: write records to output_dir/results.txt")
+    output_dir.mkdir(parents=True, exist_ok=True)
+
+    file_path = output_dir / "results.txt"
+
+    with open(file_path, "w", encoding="utf-8") as f:
+        for record in records:
+            f.write(f"{record}\n")
+
+    logger.info("%s records written", len(records))
 
 
 def run() -> None:
     config = get_config()
     logger.info("starting pipeline")
+
     records = fetch_data(config["api_key"])
     output_dir = Path(config["output_dir"])
+
     save_results(records, output_dir)
+
     logger.info("pipeline complete")
 
 
 if __name__ == "__main__":
-    run()
+    run()