main.py

from typing import List

from fastapi import FastAPI, File, Form, HTTPException, UploadFile
from fastapi.middleware.cors import CORSMiddleware

from scanner.engine import PIIScannerEngine
from scanner.zip_handler import ZipExtractionError, extract_uploaded_items

MAX_UPLOAD_BYTES = 25 * 1024 * 1024
MAX_BATCH_FILES = 50

app = FastAPI(title="PII Scanner API", version="1.0.0")
app.add_middleware(
    CORSMiddleware,
    allow_origins=["*"],
    allow_credentials=True,
    allow_methods=["*"],
    allow_headers=["*"],
)

scanner = PIIScannerEngine()


@app.get("/health")
def health():
    return {"status": "ok", "model_loaded": scanner.model_loaded}


@app.post("/scan")
async def scan(files: List[UploadFile] = File(...), redact: bool = Form(True)):
    if not files:
        raise HTTPException(status_code=400, detail="No files uploaded")
    if len(files) > MAX_BATCH_FILES:
        raise HTTPException(status_code=400, detail=f"Too many uploaded files. Max {MAX_BATCH_FILES}")

    uploaded_items: List[tuple[str, bytes]] = []
    for file in files:
        content = await file.read()
        if len(content) > MAX_UPLOAD_BYTES:
            raise HTTPException(status_code=400, detail=f"File too large: {file.filename}")
        uploaded_items.append((file.filename or "uploaded_file", content))

    try:
        extracted_files = extract_uploaded_items(uploaded_items)
    except ZipExtractionError as exc:
        raise HTTPException(status_code=400, detail=str(exc)) from exc
    except Exception as exc:
        raise HTTPException(status_code=400, detail="Invalid ZIP or unsupported archive content") from exc

    if not extracted_files:
        raise HTTPException(status_code=400, detail="No supported files found in upload")

    return scanner.scan_files(extracted_files, redact=redact)