Schulcloud-MCP/src/core/match.ts

import type { CrawledBoard, Snapshot } from './crawl.ts';
import { h5pSearchText } from './h5p.ts';
import { noteSearchText, noteSections } from './notes.ts';
import { matchesAll, snippet, tokenize } from './text.ts';

/**
 * Keyword matching over a crawled snapshot.
 *
 * This is the fallback path: when the Postgres index is unavailable or a
 * caller asks for guaranteed-fresh results, we crawl and match in memory
 * instead. Pure and synchronous, so it is testable without a network or a
 * database.
 */

export interface Hit {
	courseId: string;
	courseTitle: string;
	/** Where the match was found, in human terms. */
	where: string;
	/** Id to pass to a follow-up tool, with the tool that takes it. */
	targetId: string;
	targetKind: 'course' | 'room' | 'board' | 'lesson' | 'task' | 'file' | 'note';
	snippet: string;
}

/**
 * Matches a container's boards. Shared by courses and rooms so a hit in a room
 * looks and behaves exactly like a hit in a course.
 */
function matchBoards(
	boards: CrawledBoard[],
	base: { courseId: string; courseTitle: string },
	terms: string[],
	push: (hit: Hit) => void,
): void {
	for (const board of boards) {
		if (matchesAll(board.title, terms)) {
			push({ ...base, where: 'board title', targetId: board.id, targetKind: 'board', snippet: board.title });
		}
		// Match per card, so the snippet points at the right part of the board.
		for (const column of board.board.columns) {
			for (const card of column.cards) {
				const parts = [card.title];
				for (const element of card.elements) {
					if (element.text) parts.push(element.text);
					// Pad contents are searched by the index; without this the live
					// crawl path would quietly disagree with it.
					if (element.padText) parts.push(element.padText);
					// Same corpus as the index, or a live search would disagree with it.
					if (element.h5p) parts.push(h5pSearchText(element.h5p));
					if (element.url) parts.push(element.url);
					for (const file of element.files) parts.push(file.name);
				}
				const haystack = parts.filter(Boolean).join('\n');
				if (matchesAll(haystack, terms)) {
					push({
						...base,
						where: `board "${board.title}" → card "${card.title}"`,
						targetId: board.id,
						targetKind: 'board',
						snippet: snippet(haystack, terms),
					});
				}
			}
		}
	}
}

export function searchSnapshot(snapshot: Snapshot, query: string, limit = 50): Hit[] {
	const terms = tokenize(query);
	if (terms.length === 0) return [];

	const hits: Hit[] = [];
	const push = (hit: Hit) => {
		hits.push(hit);
	};

	for (const course of snapshot.courses) {
		const base = { courseId: course.course.id, courseTitle: course.title };

		if (matchesAll(course.title, terms)) {
			push({ ...base, where: 'course title', targetId: course.course.id, targetKind: 'course', snippet: course.title });
		}

		matchBoards(course.boards, base, terms, push);

		for (const lesson of course.lessons) {
			const haystack = `${lesson.name}\n${lesson.text}`;
			if (matchesAll(haystack, terms)) {
				push({
					...base,
					where: lesson.text && matchesAll(lesson.text, terms) ? `lesson "${lesson.name}"` : 'lesson title',
					targetId: lesson.id,
					targetKind: 'lesson',
					snippet: snippet(haystack, terms),
				});
			}
		}

		for (const task of course.tasks) {
			const haystack = `${task.task.name}\n${task.text}`;
			if (matchesAll(haystack, terms)) {
				push({ ...base, where: 'task', targetId: task.id, targetKind: 'task', snippet: snippet(haystack, terms) });
			}
		}
	}

	// Rooms carry boards and nothing else, so they reuse the same matcher; a hit
	// reads the same whether the board hangs off a course or a room.
	for (const room of snapshot.rooms) {
		const base = { courseId: room.id, courseTitle: room.name };
		if (matchesAll(room.name, terms)) {
			push({ ...base, where: 'room title', targetId: room.id, targetKind: 'room', snippet: room.name });
		}
		matchBoards(room.boards, base, terms, push);
	}

	// The user's own notes. `courseId` is the subject rather than an id: nothing
	// follows a note back to a course, and the subject is what makes the hit
	// readable — "Deutsch — my note" rather than a bare path.
	for (const note of snapshot.notes) {
		// Per lesson where the note has lessons, exactly as the index does it —
		// otherwise fresh=true would report "Monday" where the index reports
		// "Deutsch, Monday", and the two paths would disagree about the same file.
		const sections = noteSections(note);
		if (sections.length > 0) {
			for (const section of sections) {
				const haystack = [section.heading, section.text].filter(Boolean).join('\n');
				if (!matchesAll(haystack, terms)) continue;
				hits.push({
					courseId: note.courseId ?? '',
					courseTitle: section.subject ?? note.subject ?? 'Notizen',
					where: `my own note, ${section.heading}${note.date ? `, ${note.date}` : ''}`,
					targetId: note.path,
					targetKind: 'note',
					snippet: snippet(haystack, terms),
				});
			}
			continue;
		}

		const haystack = noteSearchText(note);
		if (!matchesAll(haystack, terms)) continue;
		hits.push({
			courseId: note.courseId ?? '',
			courseTitle: note.subject ?? 'Notizen',
			where: `my own note${note.date ? `, ${note.date}` : ''}`,
			targetId: note.path,
			targetKind: 'note',
			snippet: snippet(haystack, terms),
		});
	}

	for (const file of snapshot.files) {
		if (matchesAll(file.record.name, terms)) {
			hits.push({
				courseId: file.at.courseId,
				courseTitle: file.at.courseTitle,
				where: `file in ${file.at.containerTitle ?? 'course'}`,
				targetId: file.record.id,
				targetKind: 'file',
				snippet: file.record.name,
			});
		}
	}

	return hits.slice(0, limit);
}