Baraah A.

.github/workflows/ci.yml

@@ -15,7 +15,7 @@ name: CI
 
 on:
   push:
-    branches: ["TODO-replace-with-main"]
+    branches: ["main"]
   pull_request:
 
 jobs:
@@ -29,10 +29,30 @@ jobs:
       - name: Install dependencies
         run: pip install -r requirements.txt
       - name: Lint
-        run: echo "TODO implement this step"
-      - name: Format
-        run: echo "TODO implement this step"
+        run: ruff check .
+      - name: Format check
+        run: ruff format . --check
       - name: Test
-        run: echo "TODO implement this step"
-      - name: Build image
-        run: echo "TODO implement this step"
+        run: API_KEY=test pytest -q
+      - name: Build Docker image
+        run: docker build -t barbari-pipeline:${{ github.sha }} .
+      # The next four steps need the AZURE_CREDENTIALS secret, which GitHub
+      # withholds on pull_request runs from forks for security. The `if:` guard
+      # skips them on fork PRs so CI stays green; the central `Grade ACR push`
+      # workflow on main handles the actual push from base-repo context.
+      - name: Azure login
+        if: github.event_name != 'pull_request' || github.event.pull_request.head.repo.fork == false
+        uses: azure/login@v2
+        with:
+          creds: ${{ secrets.AZURE_CREDENTIALS }}
+
+      - name: ACR login
+        if: github.event_name != 'pull_request' || github.event.pull_request.head.repo.fork == false
+        run: az acr login --name hyfregistry
+
+      - name: Push image to ACR
+        if: github.event_name != 'pull_request' || github.event.pull_request.head.repo.fork == false
+        run: |
+          docker tag barbari-pipeline:${{ github.sha }} hyfregistry.azurecr.io/barbari-pipeline:${{ github.sha }}
+          docker push hyfregistry.azurecr.io/barbari-pipeline:${{ github.sha }}
+

AI_ASSIST.md

@@ -7,11 +7,12 @@
 ## The prompt I gave
 
 <!-- Paste the exact prompt you gave to an LLM (ChatGPT, Claude, Copilot, etc.). -->
+I used AI to help me fix my pytest issues. The AI suggested ensuring that all required dependencies (pytest and project modules) are installed, fixing missing imports,
 
 TODO: paste your prompt here.
 
 ## The code or suggestion it returned
-
+After applying the changes, all tests passed successfully
 <!-- Paste the code or key suggestion the LLM returned. -->
 
 ```python

Dockerfile

@@ -10,15 +10,18 @@
 # 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)
+COPY requirements.txt .
 
 # TODO: install dependencies
+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"]

requirements.txt

@@ -11,3 +11,14 @@
 # ruff==
 #
 # Add your pinned dependencies below:
+azure-identity==1.17.1
+azure-storage-blob==12.19.1
+
+pandas==2.2.2
+numpy==2.0.1
+requests==2.32.3
+pytest==8.4.2
+matplotlib==3.9.2
+ruff==0.8.4
+pyarrow==18.1.0
+

src/pipeline.py

@@ -7,7 +7,7 @@
 
 Replace every `raise NotImplementedError` below with a real implementation.
 """
-
+import os
 import logging
 from pathlib import Path
 
@@ -24,8 +24,22 @@ def get_config() -> dict:
 
     Raise RuntimeError with a clear message if a required variable is missing.
     """
+    api_key = os.getenv("API_KEY")
+    output_dir = os.getenv("OUTPUT_DIR", "output")
+
+    if not api_key:
+        raise RuntimeError("ERROR: API_KEY is not set in environment variables")
+
+
+    return {
+        "api_key": api_key,
+        "output_dir": output_dir,
+
+    }
     raise NotImplementedError("Task 5: read API_KEY and OUTPUT_DIR from the environment")
 
+def clean_name(name: str) -> str:
+    return name.strip()
 
 def fetch_data(api_key: str) -> list[dict]:
     """
@@ -34,8 +48,12 @@ def fetch_data(api_key: str) -> list[dict]:
     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")
+    logger.info("fetching data")
 
+    return [
+        {"id": 1, "name": "Alice", "value": 100},
+        {"id": 2, "name": "Bob", "value": 200},
+    ]
 
 def save_results(records: list[dict], output_dir: Path) -> None:
     """
@@ -44,7 +62,15 @@ def save_results(records: list[dict], output_dir: Path) -> None:
     Create output_dir if it does not exist.
     Log the number of records written.
     """
-    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 file_path.open("w") as f:
+        for record in records:
+            f.write(f"{record}\n")
+    logger.info(f"saved {len(records)} records to {file_path}")
+     #raise NotImplementedError("Task 1: write records to output_dir/results.txt")
 
 
 def run() -> None:

tests/test_pipeline.py

@@ -3,6 +3,14 @@
 import pytest
 
 from src.pipeline import fetch_data, get_config, save_results
+from src.pipeline import clean_name
+
+def test_clean_name_strips_whitespace():
+    assert clean_name("  Alice  ") == "Alice"
+
+
+def test_clean_name_handles_empty():
+    assert clean_name("") == ""
 
 
 class TestGetConfig: