Hire-ai/backend/app/routers/resume.py

from fastapi import APIRouter, Depends, HTTPException, UploadFile, File, status
from fastapi.responses import StreamingResponse
from bson import ObjectId
from datetime import datetime, timezone
import io

from app.database import get_db, get_gridfs
from app.dependencies import get_current_user
from app.services.resume_parser import parse_pdf, parse_docx

router = APIRouter(prefix="/api/resume", tags=["resume"])

ALLOWED_TYPES = {
    "application/pdf": "pdf",
    "application/vnd.openxmlformats-officedocument.wordprocessingml.document": "docx",
    "application/msword": "doc",
}
MAX_SIZE_MB = 10


# ── Upload & Parse ──────────────────────────────────────────────
@router.post("/upload", status_code=status.HTTP_201_CREATED)
async def upload_resume(
    file: UploadFile = File(...),
    db=Depends(get_db),
    gridfs=Depends(get_gridfs),
    current_user: dict = Depends(get_current_user),
):
    # Validate content type
    content_type = file.content_type or ""
    if content_type not in ALLOWED_TYPES:
        raise HTTPException(
            status_code=400,
            detail="Only PDF and DOCX files are accepted.",
        )

    file_bytes = await file.read()

    # Validate size
    if len(file_bytes) > MAX_SIZE_MB * 1024 * 1024:
        raise HTTPException(
            status_code=400,
            detail=f"File too large. Max size is {MAX_SIZE_MB}MB.",
        )

    # Parse resume
    file_type = ALLOWED_TYPES[content_type]
    if file_type == "pdf":
        parsed = parse_pdf(file_bytes)
    else:
        parsed = parse_docx(file_bytes)

    # Store file in GridFS
    gridfs_id = await gridfs.upload_from_stream(
        file.filename,
        io.BytesIO(file_bytes),
        metadata={"content_type": content_type, "uploaded_by": current_user["google_id"]},
    )

    # Store metadata in MongoDB
    doc = {
        "filename": file.filename,
        "file_type": file_type,
        "content_type": content_type,
        "uploaded_by": current_user["google_id"],
        "gridfs_id": str(gridfs_id),
        "parsed": parsed,
        "uploaded_at": datetime.now(timezone.utc),
    }
    result = await db["resumes"].insert_one(doc)

    return {
        "id": str(result.inserted_id),
        "filename": file.filename,
        "file_type": file_type,
        "parsed": parsed,
        "uploaded_at": doc["uploaded_at"].isoformat(),
        "message": "Resume uploaded and parsed successfully",
    }


# ── List all resumes for current user ──────────────────────────
@router.get("/")
async def list_resumes(
    db=Depends(get_db),
    current_user: dict = Depends(get_current_user),
):
    cursor = db["resumes"].find(
        {"uploaded_by": current_user["google_id"]},
        {"parsed.raw_text": 0},  # exclude raw text from list view
    ).sort("uploaded_at", -1)

    resumes = []
    async for doc in cursor:
        doc["id"] = str(doc.pop("_id"))
        doc["uploaded_at"] = doc["uploaded_at"].isoformat() if doc.get("uploaded_at") else ""
        resumes.append(doc)

    return resumes


# ── Get single resume ──────────────────────────────────────────
@router.get("/{resume_id}")
async def get_resume(
    resume_id: str,
    db=Depends(get_db),
    current_user: dict = Depends(get_current_user),
):
    try:
        oid = ObjectId(resume_id)
    except Exception:
        raise HTTPException(status_code=400, detail="Invalid resume ID")

    doc = await db["resumes"].find_one(
        {"_id": oid, "uploaded_by": current_user["google_id"]}
    )
    if not doc:
        raise HTTPException(status_code=404, detail="Resume not found")

    doc["id"] = str(doc.pop("_id"))
    doc["uploaded_at"] = doc["uploaded_at"].isoformat() if doc.get("uploaded_at") else ""
    return doc


# ── Download original file ─────────────────────────────────────
@router.get("/{resume_id}/download")
async def download_resume(
    resume_id: str,
    db=Depends(get_db),
    gridfs=Depends(get_gridfs),
    current_user: dict = Depends(get_current_user),
):
    try:
        oid = ObjectId(resume_id)
    except Exception:
        raise HTTPException(status_code=400, detail="Invalid resume ID")

    doc = await db["resumes"].find_one(
        {"_id": oid, "uploaded_by": current_user["google_id"]}
    )
    if not doc:
        raise HTTPException(status_code=404, detail="Resume not found")

    gridfs_id = ObjectId(doc["gridfs_id"])
    stream = await gridfs.open_download_stream(gridfs_id)
    content = await stream.read()

    return StreamingResponse(
        io.BytesIO(content),
        media_type=doc["content_type"],
        headers={"Content-Disposition": f'attachment; filename="{doc["filename"]}"'},
    )


# ── Delete resume ──────────────────────────────────────────────
@router.delete("/{resume_id}", status_code=status.HTTP_204_NO_CONTENT)
async def delete_resume(
    resume_id: str,
    db=Depends(get_db),
    gridfs=Depends(get_gridfs),
    current_user: dict = Depends(get_current_user),
):
    try:
        oid = ObjectId(resume_id)
    except Exception:
        raise HTTPException(status_code=400, detail="Invalid resume ID")

    doc = await db["resumes"].find_one(
        {"_id": oid, "uploaded_by": current_user["google_id"]}
    )
    if not doc:
        raise HTTPException(status_code=404, detail="Resume not found")

    # Delete from GridFS
    try:
        await gridfs.delete(ObjectId(doc["gridfs_id"]))
    except Exception:
        pass  # GridFS file may already be gone

    await db["resumes"].delete_one({"_id": oid})