src/models.py

from __future__ import annotations

import json
import os
from datetime import datetime, timezone
from pathlib import Path

from .config import events_path

DEFAULT_EVENTS_PATH = events_path()
SCHEMA_VERSION = 6


def load_payload(path: str | Path = DEFAULT_EVENTS_PATH) -> dict:
    return json.loads(Path(path).read_text(encoding="utf-8"))


def ensure_payload_schema(payload: dict) -> dict:
    meta = payload.setdefault("meta", {})
    meta["schema_version"] = SCHEMA_VERSION
    return payload


def write_payload(payload: dict, path: str | Path = DEFAULT_EVENTS_PATH) -> None:
    ensure_payload_schema(payload)
    Path(path).write_text(json.dumps(payload, ensure_ascii=False, indent=2), encoding="utf-8")


def parse_dt_utc(value: str) -> datetime:
    dt = datetime.fromisoformat(value)
    if dt.tzinfo is None:
        dt = dt.replace(tzinfo=timezone.utc)
    return dt.astimezone(timezone.utc)


def infer_category(*, title: str, org_name: str, event_url: str) -> str:
    text = " ".join((title, org_name, event_url)).lower().replace("-", " ").replace("_", " ").replace("/", " ")
    if "thesis defense" in text or "phd defense" in text:
        return "PhD defense"
    if "thesis proposal" in text or "phd proposal" in text:
        return "PhD proposal"
    if "lecture" in text:
        return "Lecture"
    if "talk" in text:
        return "Talk"
    if "podcast" in text or "episode" in text:
        return "Podcast"
    if "seminar" in text:
        return "Seminar"
    return ""