from __future__ import annotations

import os
import re
import shutil
import time
from pathlib import Path

from .schemas import JobPaths


_JOB_ID_RE = re.compile(r"^[0-9a-f]{32,}$")


class Storage:
    def __init__(self, base_dir: Path) -> None:
        self.base_dir = base_dir
        self.base_dir.mkdir(parents=True, exist_ok=True)

    def prepare_job_dirs(self, job_id: str) -> JobPaths:
        root = self.base_dir / job_id
        input_dir = root / "input"
        output_dir = root / "output"
        input_dir.mkdir(parents=True, exist_ok=True)
        output_dir.mkdir(parents=True, exist_ok=True)

        return JobPaths(
            root=root,
            input_dir=input_dir,
            output_dir=output_dir,
            mask_path=input_dir / "mask.png",
            excel_path=input_dir / "names.xlsx",
            config_path=root / "config.json",
        )

    def job_root(self, job_id: str) -> Path:
        return self.base_dir / job_id

    def job_dir_size(self, job_id: str) -> int:
        root = self.job_root(job_id)
        if not root.exists():
            return 0
        total = 0
        for dirpath, _, filenames in os.walk(root):
            for filename in filenames:
                try:
                    total += os.path.getsize(os.path.join(dirpath, filename))
                except OSError:
                    continue
        return total

    def job_dir_info(self, job_id: str) -> dict | None:
        root = self.job_root(job_id)
        if not root.is_dir():
            return None
        try:
            mtime = root.stat().st_mtime
        except OSError:
            return None
        return {
            "job_id": job_id,
            "path": str(root),
            "size_bytes": self.job_dir_size(job_id),
            "age_days": round(max(0.0, time.time() - mtime) / 86400.0, 2),
        }

    def list_job_ids(self) -> list[str]:
        if not self.base_dir.exists():
            return []
        return [
            item.name
            for item in self.base_dir.iterdir()
            if item.is_dir() and _JOB_ID_RE.match(item.name)
        ]

    def stale_job_dirs(
        self,
        referenced_job_ids: set[str],
        exclude_job_ids: set[str] | None = None,
        max_age_days: float | None = None,
    ) -> list[dict]:
        exclude = exclude_job_ids or set()
        result: list[dict] = []
        for job_id in self.list_job_ids():
            if job_id in referenced_job_ids or job_id in exclude:
                continue
            info = self.job_dir_info(job_id)
            if not info:
                continue
            if max_age_days is not None and info["age_days"] < max_age_days:
                continue
            result.append(info)
        return sorted(result, key=lambda item: item["size_bytes"], reverse=True)

    def remove_job_dir(self, job_id: str) -> int:
        root = self.job_root(job_id)
        if not root.exists():
            return 0
        size = self.job_dir_size(job_id)
        shutil.rmtree(root, ignore_errors=True)
        return size