src/cache.py

from __future__ import annotations

import json
from datetime import datetime, timezone
from pathlib import Path
from typing import Iterable, List, Sequence

from src.models import JobPosting


def load_cached_jobs(cache_path: str | Path) -> dict:
    path = Path(cache_path)
    if not path.exists():
        return {"generated_at": "", "companies": [], "jobs": []}
    try:
        return json.loads(path.read_text(encoding="utf-8"))
    except Exception:
        return {"generated_at": "", "companies": [], "jobs": []}


def write_cached_jobs(cache_path: str | Path, jobs: Sequence[JobPosting], companies: Iterable[str]) -> Path:
    path = Path(cache_path)
    path.parent.mkdir(parents=True, exist_ok=True)
    payload = {
        "generated_at": datetime.now(timezone.utc).isoformat(),
        "companies": sorted(set(companies)),
        "jobs": [job.to_dict() for job in jobs],
    }
    path.write_text(json.dumps(payload, indent=2), encoding="utf-8")
    return path


def merge_cached_jobs(cache_path: str | Path, refreshed_jobs: Sequence[JobPosting], refreshed_companies: Iterable[str]) -> Path:
    cached = load_cached_jobs(cache_path)
    refreshed_set = set(refreshed_companies)
    retained_jobs = [job for job in cached.get("jobs", []) if job.get("company") not in refreshed_set]
    refreshed_payload = [job.to_dict() for job in refreshed_jobs]
    merged_companies = set(cached.get("companies", [])) - refreshed_set
    merged_companies.update(refreshed_set)

    payload = {
        "generated_at": datetime.now(timezone.utc).isoformat(),
        "companies": sorted(merged_companies),
        "jobs": retained_jobs + refreshed_payload,
    }

    path = Path(cache_path)
    path.parent.mkdir(parents=True, exist_ok=True)
    path.write_text(json.dumps(payload, indent=2), encoding="utf-8")
    return path