import uuid import json import logging from datetime import datetime, timezone from dataclasses import asdict from fastapi import APIRouter, UploadFile, File, HTTPException from app.services import storage, file_parser from app.models.schemas import CandidateBatchResponse, BatchListItem router = APIRouter(prefix="/api/v1/candidates", tags=["candidates"]) logger = logging.getLogger(__name__) def _candidate_to_dict(c) -> dict: """Serialize CandidateData to JSON-safe dict.""" return { "id": c.id, "name": c.name, "current_position": c.current_position, "current_title": c.current_title, "years_of_experience": c.years_of_experience, "engineer_type": c.engineer_type, "gen_ai_experience": c.gen_ai_experience, "parsed_skills": c.parsed_skills, "parsed_summary": c.parsed_summary, "parsed_work_experience_raw": c.parsed_work_experience_raw, "parsed_work_experience_text": c.parsed_work_experience_text, "work_experiences": [ { "company": we.company, "role": we.role, "duration": we.duration, "description": we.description, } for we in c.work_experiences ], "most_recent_company": c.most_recent_company, "notice_period": c.notice_period, "is_actively_looking": c.is_actively_looking, "flags": c.flags, "penalties": c.penalties, } @router.post("/upload", response_model=CandidateBatchResponse) async def upload_candidates(file: UploadFile = File(...)): if not file.filename or not file.filename.lower().endswith(".xlsx"): raise HTTPException(400, "Only XLSX files accepted for candidates") content = await file.read() if len(content) > 50 * 1024 * 1024: raise HTTPException(413, "File too large (max 50 MB)") try: candidates, dist = file_parser.parse_xlsx(content) except ValueError as e: raise HTTPException(400, str(e)) if not candidates: raise HTTPException(400, "No valid candidates found in file") batch_id = str(uuid.uuid4())[:8] now = datetime.now(timezone.utc).isoformat() metadata = { "batch_id": batch_id, "total_count": len(candidates), "engineer_type_distribution": json.dumps(dist), "uploaded_at": now, "filename": file.filename, } candidates_json = json.dumps([_candidate_to_dict(c) for c in candidates]) storage.save_batch(batch_id, metadata, candidates_json) logger.info(f"Batch uploaded: {batch_id}, {len(candidates)} candidates, dist={dist}") return CandidateBatchResponse( batch_id=batch_id, total_count=len(candidates), engineer_type_distribution=dist, uploaded_at=now, ) @router.get("/", response_model=list[BatchListItem]) def list_batches(): items = storage.list_batches() result = [] for d in items: dist = d.get("engineer_type_distribution", {}) if isinstance(dist, str): try: dist = json.loads(dist) except Exception: dist = {} result.append(BatchListItem( batch_id=d.get("batch_id", ""), total_count=int(d.get("total_count", 0)), engineer_type_distribution=dist, uploaded_at=d.get("uploaded_at", ""), )) return result