Add upload endpoint with validation

.github/workflows/ci.yml

@@ -13,7 +13,11 @@ jobs:
       - uses: actions/setup-python@v5
         with:
           python-version: "3.12"
-      - name: Install uv
-        run: pip install uv
+      - name: Install tooling
+        run: pip install uv ruff black
+      - name: Lint
+        run: |
+          ruff check --no-cache
+          black . --check
       - name: Run tests
         run: uv run python -m pytest -q

README.md

@@ -36,5 +36,6 @@ tests for every push and pull request. The workflow definition lives in
 
 ## API
 
-- `GET /` – returns a simple greeting
+- `GET /health` – simple health check
 - `POST /pdf/pages` – upload a PDF file and get the page count
+- `POST /upload` – upload a non-empty PDF, PNG, or Markdown file

app/main.py

@@ -1,24 +1,67 @@
 from fastapi import FastAPI, UploadFile, File, HTTPException
+from fastapi_health import health
 from pypdf import PdfReader
 from pypdf.errors import PdfReadError
 
+
+ALLOWED_TYPES = {"application/pdf", "image/png", "text/markdown"}
+MAX_FILE_SIZE = 10 * 1024 * 1024  # 10 MB
+
 app = FastAPI()
 
-@app.get("/")
-async def read_root():
-    return {"message": "Hello World"}
+
+def healthy() -> bool:
+    """Simple health check condition."""
+    return True
+
+
+app.add_api_route("/health", health([healthy]))
+
 
 @app.post("/pdf/pages")
 async def count_pages(file: UploadFile = File(...)):
     if file.content_type != "application/pdf":
         raise HTTPException(status_code=400, detail="Invalid content type")
+
+    # Read file content instead of checking length directly
+    contents = await file.read()
+    if len(contents) > MAX_FILE_SIZE:
+        raise HTTPException(status_code=400, detail="File too large")
+
     try:
-        reader = PdfReader(file.file)
+        # Create a PdfReader from the contents
+        from io import BytesIO
+
+        reader = PdfReader(BytesIO(contents))
         pages = len(reader.pages)
         return {"pages": pages}
     except PdfReadError:
         raise HTTPException(status_code=400, detail="Invalid PDF file")
 
+
+@app.post("/upload")
+async def upload_file(file: UploadFile = File(...)):
+    """Upload a file ensuring it's not empty and has an allowed type."""
+    if file.content_type not in ALLOWED_TYPES:
+        raise HTTPException(
+            status_code=400,
+            detail="Invalid file type",
+        )
+
+    # Read file content
+    contents = await file.read()
+    total_size = len(contents)
+
+    if total_size > MAX_FILE_SIZE:
+        raise HTTPException(status_code=400, detail="File too large")
+
+    if not contents:
+        raise HTTPException(status_code=400, detail="Empty file")
+
+    return {"filename": file.filename, "size": total_size}
+
+
 if __name__ == "__main__":
     import uvicorn
+
     uvicorn.run(app, host="0.0.0.0", port=8000)

pyproject.toml

@@ -9,9 +9,12 @@ dependencies = [
     "httpx>=0.28.1",
     "pypdf>=5.6.0",
     "python-multipart>=0.0.20",
+    "fastapi-health>=0.4.0",
 ]
 
 [dependency-groups]
 dev = [
+    "black>=25.1.0",
     "pytest>=8.4.0",
+    "ruff>=0.12.0",
 ]

tests/conftest.py

@@ -0,0 +1,5 @@
+import sys
+from pathlib import Path
+
+# Add the parent directory to sys.path so that 'app' module can be imported
+sys.path.insert(0, str(Path(__file__).parent.parent))

tests/test_main.py

@@ -4,18 +4,73 @@
 
 client = TestClient(app)
 
-def test_read_root():
-    response = client.get("/")
+
+def test_health_check():
+    response = client.get("/health")
     assert response.status_code == 200
-    assert response.json() == {"message": "Hello World"}
+    assert response.json() == {}
+
 
 def test_count_pages(tmp_path):
     pdf_path = tmp_path / "dummy.pdf"
     writer = PdfWriter()
     writer.add_blank_page(width=72, height=72)
+
     with open(pdf_path, "wb") as f:
         writer.write(f)
+
     with open(pdf_path, "rb") as f:
-        response = client.post("/pdf/pages", files={"file": ("dummy.pdf", f, "application/pdf")})
+        response = client.post(
+            "/pdf/pages", files={"file": ("dummy.pdf", f, "application/pdf")}
+        )
+
     assert response.status_code == 200
     assert response.json() == {"pages": 1}
+
+
+def test_upload_pdf(tmp_path):
+    """Uploading a non-empty PDF should succeed."""
+    pdf_path = tmp_path / "upload.pdf"
+    writer = PdfWriter()
+    # writer.add_blank_page(width=72, height=72)
+    writer.add_blank_page(width=72, height=72)
+
+    with open(pdf_path, "wb") as f:
+        writer.write(f)
+
+    with open(pdf_path, "rb") as f:
+        response = client.post(
+            "/upload",
+            files={"file": ("upload.pdf", f, "application/pdf")},
+        )
+
+    assert response.status_code == 200
+    json_resp = response.json()
+    assert json_resp["filename"] == "upload.pdf"
+    assert json_resp["size"] > 0
+
+
+def test_upload_invalid_type(tmp_path):
+    txt_path = tmp_path / "bad.txt"
+    txt_path.write_text("hello")
+    with open(txt_path, "rb") as f:
+        response = client.post(
+            "/upload",
+            files={"file": ("bad.txt", f, "text/plain")},
+        )
+    assert response.status_code == 400
+    assert response.json()["detail"] == "Invalid file type"
+
+
+def test_upload_empty_file(tmp_path):
+    empty_path = tmp_path / "empty.pdf"
+    empty_path.write_bytes(b"")
+
+    with open(empty_path, "rb") as f:
+        response = client.post(
+            "/upload",
+            files={"file": ("empty.pdf", f, "application/pdf")},
+        )
+
+    assert response.status_code == 400
+    assert response.json()["detail"] == "Empty file"