<?php

declare(strict_types=1);

namespace AilysLens\Core;

use InvalidArgumentException;
use RuntimeException;

/**
 * crawler-ip-ranges.json(同梱スナップショット)を読み込む。
 *
 * crawlers.json(共通定義)とは意図的に分離している:
 * - TS実装(vercel-middleware)はレンジデータを必要としない(エッジバンドルを肥大させない)
 * - 共通定義(クローラー追加時)とレンジ(ベンダーのレンジ変更時)は更新周期が異なる
 * スナップショットの再生成は tools/update-ip-ranges.php で行う。
 */
final class IpRangeRepository
{
    /**
     * 例外メッセージへ埋め込む動的値の引用・エスケープ用フラグ。
     * プラグイン同梱コピーが管理画面に表示され得るため、HTML特殊文字を
     * \uXXXX形式に逃がしつつ引用符で値を区切る。coreのCMS非依存は維持(純PHPのみ)。
     */
    private const MESSAGE_VALUE_FLAGS = JSON_HEX_TAG | JSON_HEX_APOS | JSON_HEX_QUOT | JSON_HEX_AMP
        | JSON_UNESCAPED_SLASHES | JSON_INVALID_UTF8_SUBSTITUTE;

    /** @var array<string, array<int, string>> */
    private array $ranges;

    private string $snapshotDate;

    private string $fetchedAt;

    /** @var array<string, string> */
    private array $sources;

    /**
     * @param array<string, array<int, string>> $ranges
     * @param array<string, string>             $sources
     */
    private function __construct(array $ranges, string $snapshotDate, string $fetchedAt, array $sources)
    {
        $this->ranges       = $ranges;
        $this->snapshotDate = $snapshotDate;
        $this->fetchedAt    = $fetchedAt;
        $this->sources      = $sources;
    }

    public static function defaultFilePath(): string
    {
        return dirname(__DIR__) . '/data/crawler-ip-ranges.json';
    }

    public static function fromDefaultFile(): self
    {
        return self::fromFile(self::defaultFilePath());
    }

    public static function fromFile(string $path): self
    {
        if (!is_readable($path)) {
            throw new RuntimeException('Cannot read crawler-ip-ranges.json: ' . json_encode($path, self::MESSAGE_VALUE_FLAGS));
        }

        $raw = file_get_contents($path);
        if ($raw === false) {
            throw new RuntimeException('Failed to read crawler-ip-ranges.json: ' . json_encode($path, self::MESSAGE_VALUE_FLAGS));
        }

        $decoded = json_decode($raw, true);
        if (!is_array($decoded)) {
            throw new InvalidArgumentException('crawler-ip-ranges.json contains invalid JSON: ' . json_encode(json_last_error_msg(), self::MESSAGE_VALUE_FLAGS));
        }

        return self::fromArray($decoded);
    }

    /**
     * @param array<string, mixed> $data
     */
    public static function fromArray(array $data): self
    {
        if (($data['schema_version'] ?? null) !== 1) {
            throw new InvalidArgumentException('Missing or unsupported schema_version');
        }
        if (!isset($data['ranges']) || !is_array($data['ranges'])) {
            throw new InvalidArgumentException('Missing ranges map');
        }

        $ranges = [];
        foreach ($data['ranges'] as $crawlerId => $cidrs) {
            if (!is_string($crawlerId) || !is_array($cidrs)) {
                throw new InvalidArgumentException('Invalid ranges entry (expected crawler-id key and CIDR-list value)');
            }
            $list = [];
            foreach ($cidrs as $cidr) {
                if (!is_string($cidr) || '' === $cidr) {
                    throw new InvalidArgumentException('ranges[' . json_encode($crawlerId, self::MESSAGE_VALUE_FLAGS) . '] contains an invalid CIDR');
                }
                $list[] = $cidr;
            }
            $ranges[$crawlerId] = $list;
        }

        $sources = [];
        foreach ($data['sources'] ?? [] as $crawlerId => $url) {
            if (is_string($crawlerId) && is_string($url)) {
                $sources[$crawlerId] = $url;
            }
        }

        return new self(
            $ranges,
            isset($data['snapshot_date']) && is_string($data['snapshot_date']) ? $data['snapshot_date'] : '',
            isset($data['fetched_at']) && is_string($data['fetched_at']) ? $data['fetched_at'] : '',
            $sources
        );
    }

    /**
     * @return array<int, string>
     */
    public function rangesFor(string $crawlerId): array
    {
        return $this->ranges[$crawlerId] ?? [];
    }

    public function hasRanges(string $crawlerId): bool
    {
        return [] !== ($this->ranges[$crawlerId] ?? []);
    }

    /**
     * @return array<int, string>
     */
    public function crawlerIds(): array
    {
        return array_keys($this->ranges);
    }

    public function snapshotDate(): string
    {
        return $this->snapshotDate;
    }

    public function fetchedAt(): string
    {
        return $this->fetchedAt;
    }

    /**
     * @return array<string, string>
     */
    public function sources(): array
    {
        return $this->sources;
    }
}