netfelix-audio-fix/server/services/verify.ts

import type { Database } from "bun:sqlite";
import type { MediaItem, MediaStream, StreamDecision } from "../types";
import { containerTitle, trackTitle } from "./ffmpeg";
import { normalizeLanguage } from "./language-utils";

export interface ProbedStream {
	type: "Audio" | "Video" | "Subtitle" | "Data" | "Attachment" | "Unknown";
	codec: string | null;
	language: string | null;
	title: string | null;
	isDefault: number;
}

export interface ProbedFile {
	streams: ProbedStream[];
	containerTitle: string | null;
	containerComment: string | null;
}

async function ffprobeFile(filePath: string): Promise<ProbedFile> {
	const proc = Bun.spawn(
		["ffprobe", "-v", "error", "-print_format", "json", "-show_format", "-show_streams", filePath],
		{ stdout: "pipe", stderr: "pipe" },
	);
	const [stdout, stderr] = await Promise.all([new Response(proc.stdout).text(), new Response(proc.stderr).text()]);
	const exitCode = await proc.exited;
	if (exitCode !== 0) throw new Error(`ffprobe exited ${exitCode}: ${stderr.trim() || "<no stderr>"}`);

	const data = JSON.parse(stdout) as {
		format?: { tags?: { title?: string; TITLE?: string; comment?: string; COMMENT?: string } };
		streams?: Array<{
			codec_type?: string;
			codec_name?: string;
			tags?: { language?: string; LANGUAGE?: string; title?: string; TITLE?: string };
			disposition?: { default?: number };
		}>;
	};
	const fmtTags = data.format?.tags ?? {};
	return {
		streams: (data.streams ?? []).map((s) => ({
			type: codecTypeToType(s.codec_type),
			codec: s.codec_name ?? null,
			language: s.tags?.language ?? s.tags?.LANGUAGE ?? null,
			title: s.tags?.title ?? s.tags?.TITLE ?? null,
			isDefault: s.disposition?.default ?? 0,
		})),
		containerTitle: fmtTags.title ?? fmtTags.TITLE ?? null,
		containerComment: fmtTags.comment ?? fmtTags.COMMENT ?? null,
	};
}

function codecTypeToType(t: string | undefined): ProbedStream["type"] {
	switch (t) {
		case "audio":
			return "Audio";
		case "video":
			return "Video";
		case "subtitle":
			return "Subtitle";
		case "data":
			return "Data";
		case "attachment":
			return "Attachment";
		default:
			return "Unknown";
	}
}

export interface VerifyResult {
	matches: boolean;
	reason: string;
}

type ExpectedKeptStream = MediaStream &
	StreamDecision & {
		decision_id?: number;
	};

export function verifyStreamMetadata(expected: ExpectedKeptStream[], probed: ProbedStream[]): VerifyResult | null {
	const probedAudio = probed.filter((s) => s.type === "Audio");
	const probedVideo = probed.filter((s) => s.type === "Video");
	const expectedAudio = expected.filter((s) => s.type === "Audio");
	const expectedVideo = expected.filter((s) => s.type === "Video");

	if (probedVideo.length !== expectedVideo.length) {
		return {
			matches: false,
			reason: `video stream count mismatch (file: ${probedVideo.length}, expected: ${expectedVideo.length})`,
		};
	}

	if (probedAudio.length !== expectedAudio.length) {
		return {
			matches: false,
			reason: `audio stream count mismatch (file: ${probedAudio.length}, expected: ${expectedAudio.length})`,
		};
	}

	for (let i = 0; i < expectedVideo.length; i++) {
		const want = expectedVideo[i];
		const got = probedVideo[i];
		const expectedTitle = want.custom_title ?? trackTitle(want, null);
		if (expectedTitle != null && got.title !== expectedTitle) {
			return {
				matches: false,
				reason: `video track ${i}: title ${got.title || "<none>"} ≠ expected ${expectedTitle}`,
			};
		}
	}

	for (let i = 0; i < expectedAudio.length; i++) {
		const want = expectedAudio[i];
		const got = probedAudio[i];
		const wantCodec = (want.transcode_codec ?? want.codec ?? "").toLowerCase();
		const gotCodec = (got.codec ?? "").toLowerCase();
		const expectedLanguage = want.custom_language ?? want.language;
		const wantLang = expectedLanguage ? normalizeLanguage(expectedLanguage) : "und";
		const gotLang = (got.language ?? "").toLowerCase();
		if (wantLang !== gotLang) {
			return {
				matches: false,
				reason: `audio track ${i}: language ${gotLang || "<none>"} ≠ expected ${wantLang}`,
			};
		}
		if (wantCodec && gotCodec && wantCodec !== gotCodec) {
			return {
				matches: false,
				reason: `audio track ${i}: codec ${gotCodec} ≠ expected ${wantCodec}`,
			};
		}
		const expectedTitle = want.custom_title ?? trackTitle(want, want.custom_language);
		if (expectedTitle != null && got.title !== expectedTitle) {
			return {
				matches: false,
				reason: `audio track ${i}: title ${got.title || "<none>"} ≠ expected ${expectedTitle}`,
			};
		}
		const expectedDefault = i === 0 ? 1 : 0;
		if (got.isDefault !== expectedDefault) {
			return {
				matches: false,
				reason: `audio track ${i}: default disposition ${got.isDefault} ≠ expected ${expectedDefault}`,
			};
		}
	}

	return null;
}

/**
 * Check whether the on-disk file already matches the plan's desired state.
 * Comparison is conservative: any uncertainty falls back to "run the job".
 *
 * Matches when:
 *   - video/audio stream count, metadata, order, and codec match the `keep` decisions
 *   - no subtitle streams remain in the container
 *   - either subs_extracted=1 or the plan has no subtitle decisions to extract
 */
export async function verifyDesiredState(db: Database, itemId: number, filePath: string): Promise<VerifyResult> {
	const plan = db.prepare("SELECT id, subs_extracted FROM review_plans WHERE item_id = ?").get(itemId) as
		| { id: number; subs_extracted: number }
		| undefined;
	if (!plan) return { matches: false, reason: "no review plan found" };

	const item = db.prepare("SELECT * FROM media_items WHERE id = ?").get(itemId) as MediaItem | undefined;
	if (!item) return { matches: false, reason: "no media item found" };

	const expected = db
		.prepare(`
				SELECT ms.*, sd.id as decision_id, sd.plan_id, sd.stream_id, sd.action,
					sd.target_index, sd.custom_title, sd.custom_language, sd.transcode_codec
				FROM stream_decisions sd
				JOIN media_streams ms ON ms.id = sd.stream_id
				WHERE sd.plan_id = ? AND sd.action = 'keep' AND ms.type IN ('Video', 'Audio')
				ORDER BY CASE ms.type WHEN 'Video' THEN 0 WHEN 'Audio' THEN 1 ELSE 2 END, sd.target_index
			`)
		.all(plan.id) as ExpectedKeptStream[];

	let probed: ProbedFile;
	try {
		probed = await ffprobeFile(filePath);
	} catch (err) {
		return { matches: false, reason: `ffprobe failed: ${(err as Error).message}` };
	}

	const probedSubs = probed.streams.filter((s) => s.type === "Subtitle");

	if (probedSubs.length > 0) {
		return { matches: false, reason: `file still contains ${probedSubs.length} subtitle stream(s) in the container` };
	}

	const mismatch = verifyStreamMetadata(expected, probed.streams);
	if (mismatch) return mismatch;

	const expectedContainerTitle = containerTitle(item);
	if ((probed.containerTitle ?? null) !== (expectedContainerTitle ?? null)) {
		return {
			matches: false,
			reason: `container title ${probed.containerTitle || "<none>"} ≠ expected ${expectedContainerTitle ?? "<none>"}`,
		};
	}
	if (probed.containerComment && probed.containerComment.length > 0) {
		return { matches: false, reason: `container comment not empty: ${probed.containerComment}` };
	}

	if (plan.subs_extracted === 0) {
		const pendingSubs = db
			.prepare(`
				SELECT COUNT(*) as n FROM stream_decisions sd
				JOIN media_streams ms ON ms.id = sd.stream_id
				WHERE sd.plan_id = ? AND ms.type = 'Subtitle'
			`)
			.get(plan.id) as { n: number };
		if (pendingSubs.n > 0) {
			return { matches: false, reason: "subtitles not yet extracted to sidecar files" };
		}
	}

	return {
		matches: true,
		reason: `file already matches desired layout (${expected.filter((s) => s.type === "Audio").length} audio track(s), no embedded subtitles)`,
	};
}