/*
 * Per-scrape storage: one directory, one SQLite index, one media folder.
 * Layout and rules: docs/media.md.
 */

import { mkdirSync, readdirSync, readFileSync, statSync, writeFileSync } from "node:fs";
import { join } from "node:path";
import { DatabaseSync } from "node:sqlite";
import { fileURLToPath } from "node:url";
import { extractMedia } from "./extract.js";
import { aspectCondition, resolutionCondition } from "./filter-presets.js";
import { emptyMediaCounts, type CoreMessage, type MediaKind, type ScrapeMeta } from "./types.js";

/** Default DB root: `media-scrape/db`, beside the module. Override with VESKSLOP_MEDIA_DB_DIR. */
export const DEFAULT_DB_ROOT = fileURLToPath(new URL("../db", import.meta.url));

export function resolveDbRoot(env: NodeJS.ProcessEnv = process.env): string {
    return env.VESKSLOP_MEDIA_DB_DIR ?? DEFAULT_DB_ROOT;
}

export function scrapeDir(root: string, id: string): string {
    return join(root, id);
}

export function writeScrapeMeta(dir: string, meta: ScrapeMeta): void {
    writeFileSync(join(dir, "scrape.json"), JSON.stringify(meta, null, 2) + "\n");
}

export function readScrapeMeta(dir: string): ScrapeMeta | null {
    try {
        return JSON.parse(readFileSync(join(dir, "scrape.json"), "utf8")) as ScrapeMeta;
    } catch {
        return null;
    }
}

/** Every scrape on disk, newest first. */
export function listScrapes(root: string): ScrapeMeta[] {
    let entries: string[];
    try {
        entries = readdirSync(root);
    } catch {
        return [];
    }

    const metas: ScrapeMeta[] = [];
    for (const entry of entries) {
        const meta = readScrapeMeta(join(root, entry));
        if (meta) metas.push(meta);
    }

    return metas.sort((a, b) => (a.createdAt < b.createdAt ? 1 : -1));
}

/** Combined size of a directory tree, used by the storage limit. */
export function dirSizeBytes(dir: string): number {
    let entries;
    try {
        entries = readdirSync(dir, { withFileTypes: true });
    } catch {
        return 0;
    }

    let total = 0;
    for (const entry of entries) {
        const path = join(dir, entry.name);
        if (entry.isDirectory()) {
            total += dirSizeBytes(path);
        } else {
            try {
                total += statSync(path).size;
            } catch {
                // A file that vanished mid-walk counts as zero.
            }
        }
    }

    return total;
}

/** Width / height, rounded to three decimals. Null when either side is missing or zero. */
export function aspectRatioOf(width: number | null | undefined, height: number | null | undefined): number | null {
    if (!Number.isFinite(width) || !Number.isFinite(height) || !width || !height) return null;
    return Math.round(((width as number) / (height as number)) * 1000) / 1000;
}

export function createScrapeDirs(root: string, id: string): string {
    const dir = scrapeDir(root, id);
    mkdirSync(join(dir, "media"), { recursive: true });
    mkdirSync(join(dir, "thumbs"), { recursive: true });
    return dir;
}

/** `<channelId>-<YYYYMMDDHHMMSS>`, with a numeric suffix on a same-second collision. */
export function uniqueScrapeId(root: string, channelId: string, now = new Date()): string {
    const stamp = now.toISOString().replace(/\.\d+Z$/, "").replace(/[-:T]/g, "");
    const base = `${channelId}-${stamp}`;

    let id = base;
    let suffix = 2;
    while (readScrapeMeta(join(root, id))) id = `${base}-${suffix++}`;
    return id;
}

export interface MediaFilterOptions {
    kind?: MediaKind;
    source?: string;
    authorId?: string;
    authorIds?: string[];
    cachedOnly?: boolean;
    aspect?: string;
    resolution?: string;
    after?: string;
    before?: string;
    limit?: number;
    offset?: number;
}

export interface MediaRow {
    id: number;
    kind: MediaKind;
    source: string | null;
    author_id: string | null;
    author_name: string | null;
    posted_at: string | null;
    url: string;
    play_url: string | null;
    provider: string | null;
    content_type: string | null;
    size: number | null;
    width: number | null;
    height: number | null;
    aspect_ratio: number | null;
    duration_secs: number | null;
    downloaded: number;
    preview_url: string | null;
    file_hash: string | null;
    preview_hash: string | null;
    preview_ext: string | null;
    anim_hash: string | null;
    file_bytes: number | null;
    preview_bytes: number | null;
    file_path: string | null;
    download_error: string | null;
    preview_error: string | null;
    created_at: string;
}

const SCHEMA = `
CREATE TABLE IF NOT EXISTS messages (
    id TEXT PRIMARY KEY,
    author_id TEXT NOT NULL,
    author_name TEXT NOT NULL,
    timestamp TEXT NOT NULL,
    content TEXT NOT NULL
);

CREATE TABLE IF NOT EXISTS media (
    id INTEGER PRIMARY KEY AUTOINCREMENT,
    kind TEXT NOT NULL,
    source TEXT,
    author_id TEXT,
    author_name TEXT,
    posted_at TEXT,
    url TEXT NOT NULL UNIQUE,
    play_url TEXT,
    provider TEXT,
    content_type TEXT,
    size INTEGER,
    width INTEGER,
    height INTEGER,
    aspect_ratio REAL,
    duration_secs REAL,
    downloaded INTEGER NOT NULL DEFAULT 0,
    preview_url TEXT,
    file_hash TEXT,
    preview_hash TEXT,
    preview_ext TEXT,
    anim_hash TEXT,
    file_bytes INTEGER,
    preview_bytes INTEGER,
    file_path TEXT,
    download_error TEXT,
    preview_error TEXT,
    created_at TEXT NOT NULL
);

CREATE TABLE IF NOT EXISTS media_sources (
    media_id INTEGER NOT NULL REFERENCES media(id),
    message_id TEXT NOT NULL,
    PRIMARY KEY (media_id, message_id)
);

CREATE INDEX IF NOT EXISTS idx_media_kind ON media(kind);
CREATE INDEX IF NOT EXISTS idx_media_posted ON media(posted_at);
CREATE INDEX IF NOT EXISTS idx_media_sources_message ON media_sources(message_id);
`;

/** One open SQLite index. The caller closes it. */
export class ScrapeStore {
    private readonly db: DatabaseSync;

    constructor(readonly dir: string) {
        this.db = new DatabaseSync(join(dir, "index.db"));
        this.db.exec(SCHEMA);
        this.migrate();
    }

    /** Add columns introduced after a scrape was created. */
    private migrate(): void {
        const columns = this.db.prepare("PRAGMA table_info(media)").all() as unknown as Array<{ name: string }>;
        const names = new Set(columns.map(column => column.name));

        if (!names.has("file_bytes")) this.db.exec("ALTER TABLE media ADD COLUMN file_bytes INTEGER");
        if (!names.has("preview_bytes")) this.db.exec("ALTER TABLE media ADD COLUMN preview_bytes INTEGER");
        if (!names.has("source")) this.db.exec("ALTER TABLE media ADD COLUMN source TEXT");
        if (!names.has("author_id")) this.db.exec("ALTER TABLE media ADD COLUMN author_id TEXT");
        if (!names.has("author_name")) this.db.exec("ALTER TABLE media ADD COLUMN author_name TEXT");
        if (!names.has("posted_at")) this.db.exec("ALTER TABLE media ADD COLUMN posted_at TEXT");
        if (!names.has("file_path")) this.db.exec("ALTER TABLE media ADD COLUMN file_path TEXT");
        if (!names.has("download_error")) this.db.exec("ALTER TABLE media ADD COLUMN download_error TEXT");
        if (!names.has("preview_error")) this.db.exec("ALTER TABLE media ADD COLUMN preview_error TEXT");
        if (!names.has("preview_ext")) this.db.exec("ALTER TABLE media ADD COLUMN preview_ext TEXT");
        if (!names.has("anim_hash")) this.db.exec("ALTER TABLE media ADD COLUMN anim_hash TEXT");
        if (!names.has("play_url")) this.db.exec("ALTER TABLE media ADD COLUMN play_url TEXT");
        if (!names.has("aspect_ratio")) this.db.exec("ALTER TABLE media ADD COLUMN aspect_ratio REAL");
    }

    close(): void {
        this.db.close();
    }

    /** Write one page of messages in a transaction. Returns the newly inserted media per kind. */
    insertPage(messages: CoreMessage[]): Record<MediaKind, number> {
        const added = emptyMediaCounts();
        const insertMessage = this.db.prepare(
            "INSERT OR REPLACE INTO messages (id, author_id, author_name, timestamp, content) VALUES (?, ?, ?, ?, ?)"
        );
        const insertMedia = this.db.prepare(
            "INSERT OR IGNORE INTO media (kind, source, author_id, author_name, posted_at, url, play_url, provider, content_type, size, width, height, aspect_ratio, duration_secs, downloaded, preview_url, created_at) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)"
        );
        const findMedia = this.db.prepare("SELECT id FROM media WHERE url = ?");
        const linkSource = this.db.prepare(
            "INSERT OR IGNORE INTO media_sources (media_id, message_id) VALUES (?, ?)"
        );
        const createdAt = new Date().toISOString();

        this.db.exec("BEGIN");
        try {
            for (const message of messages) {
                insertMessage.run(
                    message.id,
                    message.author.id,
                    message.author.username,
                    message.timestamp,
                    message.content
                );

                for (const item of extractMedia(message)) {
                    const result = insertMedia.run(
                        item.kind,
                        item.source,
                        message.author.id,
                        message.author.username,
                        message.timestamp,
                        item.url,
                        item.playUrl,
                        item.provider,
                        item.contentType,
                        item.size,
                        item.width,
                        item.height,
                        aspectRatioOf(item.width, item.height),
                        item.durationSecs,
                        item.downloaded ? 1 : 0,
                        item.previewUrl,
                        createdAt
                    );
                    if (result.changes > 0) added[item.kind]++;

                    const row = findMedia.get(item.url) as { id: number } | undefined;
                    if (row) linkSource.run(row.id, message.id);
                }
            }
            this.db.exec("COMMIT");
        } catch (error) {
            this.db.exec("ROLLBACK");
            throw error;
        }

        return added;
    }

    /** Bytes actually on disk per kind (downloaded files and cached previews). */
    storedBytesByKind(): Record<MediaKind, number> {
        const rows = this.db
            .prepare(
                "SELECT kind, COALESCE(SUM(COALESCE(file_bytes, 0) + COALESCE(preview_bytes, 0)), 0) AS bytes FROM media GROUP BY kind"
            )
            .all() as unknown as Array<{ kind: string; bytes: number }>;

        const result = emptyMediaCounts();
        for (const row of rows) {
            if (row.kind in result) result[row.kind as MediaKind] = row.bytes;
        }
        return result;
    }

    counts(): Record<MediaKind, number> {
        const rows = this.db
            .prepare("SELECT kind, COUNT(*) AS n FROM media GROUP BY kind")
            .all() as unknown as Array<{ kind: string; n: number }>;

        const result = emptyMediaCounts();
        for (const row of rows) {
            if (row.kind in result) result[row.kind as MediaKind] = row.n;
        }
        return result;
    }

    /** Media rows that still need bytes: never downloaded and not skipped. */
    pendingDownloads(limit = 5000): MediaRow[] {
        return this.db
            .prepare(
                "SELECT * FROM media WHERE downloaded = 0 AND file_path IS NULL AND download_error IS NULL AND (source IS NULL OR source != 'embed') ORDER BY id LIMIT ?"
            )
            .all(limit) as unknown as MediaRow[];
    }

    markDownloaded(
        id: number,
        file: { path: string; hash: string; bytes: number }
    ): void {
        this.db
            .prepare(
                "UPDATE media SET downloaded = 1, file_path = ?, file_hash = ?, file_bytes = ?, download_error = NULL WHERE id = ?"
            )
            .run(file.path, file.hash, file.bytes, id);
    }

    markDownloadError(id: number, error: string): void {
        this.db.prepare("UPDATE media SET download_error = ? WHERE id = ?").run(error.slice(0, 200), id);
    }

    /**
     * Rows that still need a cached preview. Attachment/sticker images and GIFs always;
     * embed thumbnails only when `includeEmbeds` is set (download mode).
     */
    pendingPreviews(limit = 5000, includeEmbeds = false): MediaRow[] {
        const local =
            "((source IS NULL OR source != 'embed') AND kind IN ('image', 'gif', 'video', 'audio'))";
        const condition = includeEmbeds
            ? `(${local} OR (source = 'embed' AND preview_url IS NOT NULL))`
            : local;

        return this.db
            .prepare(
                `SELECT * FROM media WHERE ${condition} AND preview_hash IS NULL AND preview_error IS NULL ORDER BY id LIMIT ?`
            )
            .all(limit) as unknown as MediaRow[];
    }

    markPreview(id: number, preview: { hash: string; bytes: number; ext?: string; animHash?: string }): void {
        if (preview.animHash) {
            this.db
                .prepare(
                    "UPDATE media SET preview_hash = ?, preview_bytes = ?, preview_ext = ?, anim_hash = ?, preview_error = NULL WHERE id = ?"
                )
                .run(preview.hash, preview.bytes, preview.ext ?? "webp", preview.animHash, id);
            return;
        }

        this.db
            .prepare(
                "UPDATE media SET preview_hash = ?, preview_bytes = ?, preview_ext = ?, preview_error = NULL WHERE id = ?"
            )
            .run(preview.hash, preview.bytes, preview.ext ?? "webp", id);
    }

    markPreviewError(id: number, error: string): void {
        this.db.prepare("UPDATE media SET preview_error = ? WHERE id = ?").run(error.slice(0, 200), id);
    }

    /** Refresh stored URLs after an expired CDN link is re-fetched. */
    updateUrls(id: number, urls: { url?: string; playUrl?: string | null }): void {
        const sets: string[] = [];
        const values: Array<string | null> = [];

        if (urls.url) {
            sets.push("url = ?");
            values.push(urls.url);
        }
        if (urls.playUrl !== undefined) {
            sets.push("play_url = ?");
            values.push(urls.playUrl);
        }

        if (!sets.length) return;
        this.db.prepare(`UPDATE media SET ${sets.join(", ")} WHERE id = ?`).run(...values, id);
    }

    /** Rows whose preview failed, with the reason, newest first. */
    previewFailures(
        limit = 50
    ): Array<{ id: number; kind: MediaKind; provider: string | null; url: string; error: string }> {
        const rows = this.db
            .prepare(
                "SELECT id, kind, provider, url, preview_error FROM media WHERE preview_error IS NOT NULL ORDER BY id DESC LIMIT ?"
            )
            .all(limit) as unknown as Array<{
            id: number;
            kind: MediaKind;
            provider: string | null;
            url: string;
            preview_error: string;
        }>;

        return rows.map(row => ({
            id: row.id,
            kind: row.kind,
            provider: row.provider,
            url: row.url,
            error: row.preview_error
        }));
    }

    /** The message a media row came from, for URL refreshes. */
    sourceMessageId(mediaId: number): string | null {
        const row = this.db
            .prepare("SELECT message_id FROM media_sources WHERE media_id = ? LIMIT 1")
            .get(mediaId) as unknown as { message_id: string } | undefined;
        return row?.message_id ?? null;
    }

    /** Fill in dimensions and duration after a download probe. */
    updateMediaInfo(
        id: number,
        info: { width?: number | null; height?: number | null; durationSecs?: number | null }
    ): void {
        const sets: string[] = [];
        const values: Array<number | null> = [];

        if (info.width != null && info.height != null) {
            sets.push("width = ?", "height = ?", "aspect_ratio = ?");
            values.push(info.width, info.height, aspectRatioOf(info.width, info.height));
        }
        if (info.durationSecs != null) {
            sets.push("duration_secs = ?");
            values.push(info.durationSecs);
        }

        if (!sets.length) return;
        this.db.prepare(`UPDATE media SET ${sets.join(", ")} WHERE id = ?`).run(...values, id);
    }

    /** Distinct posters with their item counts, biggest first. */
    authors(limit = 200): Array<{ id: string | null; name: string | null; count: number }> {
        const rows = this.db
            .prepare(
                "SELECT author_id AS id, author_name AS name, COUNT(*) AS count FROM media WHERE author_name IS NOT NULL GROUP BY author_id, author_name ORDER BY count DESC LIMIT ?"
            )
            .all(limit) as unknown as Array<{ id: string | null; name: string | null; count: number }>;
        return rows;
    }

    getMedia(id: number): MediaRow | null {
        const row = this.db.prepare("SELECT * FROM media WHERE id = ?").get(id) as unknown as
            | MediaRow
            | undefined;
        return row ?? null;
    }

    private mediaWhere(options: MediaFilterOptions): { where: string; values: Array<string | number> } {
        const conditions: string[] = [];
        const values: Array<string | number> = [];

        if (options.kind) {
            conditions.push("kind = ?");
            values.push(options.kind);
        }
        if (options.source) {
            conditions.push("source = ?");
            values.push(options.source);
        }
        if (options.authorId) {
            conditions.push("author_id = ?");
            values.push(options.authorId);
        }
        if (options.authorIds?.length) {
            conditions.push(`author_id IN (${options.authorIds.map(() => "?").join(", ")})`);
            values.push(...options.authorIds);
        }
        if (options.cachedOnly) {
            conditions.push("preview_hash IS NOT NULL");
        }
        if (options.after) {
            conditions.push("posted_at >= ?");
            values.push(options.after);
        }
        if (options.before) {
            conditions.push("posted_at <= ?");
            values.push(options.before);
        }

        const aspect = options.aspect ? aspectCondition(options.aspect) : null;
        if (aspect) conditions.push(aspect);

        const resolution = options.resolution ? resolutionCondition(options.resolution) : null;
        if (resolution) conditions.push(resolution);

        return { where: conditions.length ? `WHERE ${conditions.join(" AND ")}` : "", values };
    }

    queryMedia(options: MediaFilterOptions = {}): MediaRow[] {
        const limit = Math.max(1, Math.min(options.limit ?? 50, 500));
        const offset = Math.max(0, options.offset ?? 0);
        const { where, values } = this.mediaWhere(options);

        const rows = this.db
            .prepare(`SELECT * FROM media ${where} ORDER BY id DESC LIMIT ? OFFSET ?`)
            .all(...values, limit, offset);

        return rows as unknown as MediaRow[];
    }

}