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

import type { MediaItem, MediaStream, PlanResult } from '../types';
import { normalizeLanguage } from './jellyfin';
import { transcodeTarget, computeAppleCompat } from './apple-compat';

export interface AnalyzerConfig {
	subtitleLanguages: string[];
	audioLanguages: string[]; // additional languages to keep (after OG)
}

/**
 * Given an item and its streams, compute what action to take for each stream
 * and whether the file needs audio remuxing.
 *
 * Subtitles are ALWAYS removed from the container (they get extracted to
 * sidecar files). is_noop only considers audio changes.
 */
export function analyzeItem(
	item: Pick<MediaItem, 'original_language' | 'needs_review' | 'container'>,
	streams: MediaStream[],
	config: AnalyzerConfig
): PlanResult {
	const origLang = item.original_language ? normalizeLanguage(item.original_language) : null;
	const notes: string[] = [];

	// Compute action for each stream
	const decisions: PlanResult['decisions'] = streams.map((s) => {
		const action = decideAction(s, origLang, config.audioLanguages);
		return { stream_id: s.id, action, target_index: null, transcode_codec: null };
	});

	// Audio-only noop: only consider audio removals/reordering
	// (subtitles are always removed from container — that's implicit, not a "change" to review)
	const anyAudioRemoved = streams.some((s, i) => s.type === 'Audio' && decisions[i].action === 'remove');

	// Compute target ordering for kept streams within type groups
	const keptStreams = streams.filter((_, i) => decisions[i].action === 'keep');
	assignTargetOrder(keptStreams, decisions, streams, origLang, config.audioLanguages);

	// Check if audio ordering changes
	const audioOrderChanged = checkAudioOrderChanged(streams, decisions);

	// Step 3: Apple compatibility — compute transcode targets for kept audio
	for (const d of decisions) {
		if (d.action === 'keep') {
			const stream = streams.find(s => s.id === d.stream_id);
			if (stream && stream.type === 'Audio') {
				d.transcode_codec = transcodeTarget(
					stream.codec ?? '',
					stream.title,
					item.container,
				);
			}
		}
	}

	const keptAudioCodecs = decisions
		.filter(d => d.action === 'keep')
		.map(d => streams.find(s => s.id === d.stream_id))
		.filter(s => s && s.type === 'Audio')
		.map(s => s!.codec ?? '');

	const needsTranscode = decisions.some(d => d.transcode_codec != null);
	const apple_compat = computeAppleCompat(keptAudioCodecs, item.container);
	const job_type = needsTranscode ? 'transcode' as const : 'copy' as const;

	const hasSubs = streams.some((s) => s.type === 'Subtitle');
	// Extended is_noop: no audio changes AND no subs to extract AND no transcode needed
	const is_noop = !anyAudioRemoved && !audioOrderChanged && !hasSubs && !needsTranscode;

	// Generate notes for edge cases
	if (!origLang && item.needs_review) {
		notes.push('Original language unknown — audio tracks not filtered; manual review required');
	}

	return {
		is_noop,
		has_subs: hasSubs,
		confidence: 'low',
		apple_compat,
		job_type,
		decisions,
		notes,
	};
}

function decideAction(
	stream: MediaStream,
	origLang: string | null,
	audioLanguages: string[],
): 'keep' | 'remove' {
	switch (stream.type) {
		case 'Video':
		case 'Data':
		case 'EmbeddedImage':
			return 'keep';

		case 'Audio': {
			if (!origLang) return 'keep'; // unknown lang → keep all
			if (!stream.language) return 'keep'; // undetermined → keep
			const normalized = normalizeLanguage(stream.language);
			if (normalized === origLang) return 'keep';
			if (audioLanguages.includes(normalized)) return 'keep';
			return 'remove';
		}

		case 'Subtitle':
			// All subtitles are removed from the container and extracted to sidecar files
			return 'remove';

		default:
			return 'keep';
	}
}

function assignTargetOrder(
	keptStreams: MediaStream[],
	decisions: PlanResult['decisions'],
	allStreams: MediaStream[],
	origLang: string | null,
	audioLanguages: string[],
): void {
	// Group kept streams by type
	const byType: Record<string, MediaStream[]> = {};
	for (const s of keptStreams) {
		const t = s.type;
		byType[t] = byType[t] ?? [];
		byType[t].push(s);
	}

	// Sort audio: OG first, then additional languages in configured order, then by stream_index within each group
	if (byType['Audio']) {
		byType['Audio'].sort((a, b) => {
			const aLang = a.language ? normalizeLanguage(a.language) : null;
			const bLang = b.language ? normalizeLanguage(b.language) : null;
			const aRank = langRank(aLang, origLang, audioLanguages);
			const bRank = langRank(bLang, origLang, audioLanguages);
			if (aRank !== bRank) return aRank - bRank;
			return a.stream_index - b.stream_index;
		});
	}

	// Assign target_index per type group
	for (const [, typeStreams] of Object.entries(byType)) {
		typeStreams.forEach((s, idx) => {
			const dec = decisions.find((d) => d.stream_id === s.id);
			if (dec) dec.target_index = idx;
		});
	}
}

/** Compute sort rank: OG = 0, additional languages = 1..N by config order, unknown/null = N+1. */
function langRank(lang: string | null, origLang: string | null, audioLanguages: string[]): number {
	if (origLang && lang === origLang) return 0;
	if (lang) {
		const idx = audioLanguages.indexOf(lang);
		if (idx >= 0) return idx + 1;
	}
	return audioLanguages.length + 1;
}

/** Check if audio stream ordering changes (ignores subtitles which are always removed). */
function checkAudioOrderChanged(
	streams: MediaStream[],
	decisions: PlanResult['decisions']
): boolean {
	const keptAudio = streams.filter((s) => {
		if (s.type !== 'Audio') return false;
		const dec = decisions.find((d) => d.stream_id === s.id);
		return dec?.action === 'keep';
	});

	const sorted = [...keptAudio].sort((a, b) => a.stream_index - b.stream_index);
	for (let i = 0; i < keptAudio.length; i++) {
		const dec = decisions.find((d) => d.stream_id === keptAudio[i].id);
		if (!dec) continue;
		const currentPos = sorted.findIndex((s) => s.id === keptAudio[i].id);
		if (dec.target_index !== null && dec.target_index !== currentPos) return true;
	}
	return false;
}