InkNote/frontend/src/search.ts

/**
 * Local full-text search.
 *
 * The server stores note bodies encrypted and deliberately keeps no plaintext
 * index — so searching has to happen on the client, over the copy already in
 * IndexedDB. That also means search keeps working offline.
 *
 * The index is a plain in-memory map. For a personal note collection that is
 * both fast enough and far simpler than a real inverted index: matching a few
 * thousand strings costs well under a frame.
 */

import * as db from "./offlineStore";
import { docToText } from "./editor/content";
import type { SearchHit } from "./types";

interface IndexEntry {
  /** Normalised title, for matching. */
  title: string;
  /** Normalised body text, for matching. */
  text: string;
  /** Original body text, for building the snippet shown to the user. */
  raw: string;
  /** Text from an attached document, kept apart from what the user typed. */
  attachedRaw: string;
  /** Notes pinned to spots in an attached document. */
  pinnedRaw: string;
}

const _index = new Map<string, IndexEntry>();

/** Lowercases and strips diacritics, so `kuhlschrank` matches `Kühlschrank`. */
const normalize = (s: unknown): string =>
  String(s ?? "")
    .toLowerCase()
    .normalize("NFKD")
    .replace(/\p{Diacritic}/gu, "");

/** Plain text of a stored note body, whatever format it is in. */
export function contentToText(raw: string | null | undefined): string {
  if (!raw) return "";
  let parsed: unknown = null;
  try {
    parsed = JSON.parse(raw);
  } catch {
    parsed = null;
  }

  const obj = parsed as { v?: number; doc?: unknown; html?: unknown; tasks?: unknown } | null;
  if (obj && obj.v === 2 && obj.doc) return docToText(obj.doc, 20000);

  // v1 — HTML plus a detached task list.
  const html = typeof obj?.html === "string" ? obj.html : raw;
  const el = document.createElement("div");
  el.innerHTML = html;
  const tasks = Array.isArray(obj?.tasks)
    ? (obj.tasks as Array<{ text?: string }>).map((t) => t.text ?? "").join(" ")
    : "";
  return `${el.textContent || ""} ${tasks}`.replace(/\s+/g, " ").trim();
}

/**
 * Adds or replaces a note in the index.
 *
 * A PDF note has two sources of text — what the reader wrote and what the
 * document says — updated at different moments by different code. `attached`
 * is only replaced when given, so typing a note does not drop the document's
 * text and re-reading the document does not drop the note. Passing one and
 * forgetting the other used to leave whichever ran last as the only searchable
 * half.
 */
export function setEntry(id: string, title: string, content?: string | null, attached?: string | null): void {
  const existing = _index.get(id);
  const raw = contentToText(content);
  const attachedRaw = attached === undefined ? (existing?.attachedRaw ?? "") : (attached ?? "");
  const pinnedRaw = existing?.pinnedRaw ?? "";
  _index.set(id, {
    title: normalize(title),
    text: normalize(`${raw} ${attachedRaw} ${pinnedRaw}`),
    raw,
    attachedRaw,
    pinnedRaw,
  });
}

/** Replaces one of the three halves, leaving the other two alone. */
function setPart(id: string, title: string, part: "attachedRaw" | "pinnedRaw", value: string): void {
  const existing = _index.get(id) ?? { raw: "", attachedRaw: "", pinnedRaw: "", title: "", text: "" };
  const next = { ...existing, [part]: value };
  _index.set(id, {
    title: normalize(title),
    text: normalize(`${next.raw} ${next.attachedRaw} ${next.pinnedRaw}`),
    raw: next.raw,
    attachedRaw: next.attachedRaw,
    pinnedRaw: next.pinnedRaw,
  });
}

/** Replaces only the attached document's text, leaving what the user wrote. */
export const setAttachedText = (id: string, title: string, attached: string): void =>
  setPart(id, title, "attachedRaw", attached);

/**
 * Replaces only the notes pinned into an attached document.
 *
 * These live in the page overlay rather than in the note body, so nothing else
 * puts them in the index — and a note you wrote onto page 14 that cannot be
 * searched for is a note you will not find again.
 */
export const setPinnedText = (id: string, title: string, pinned: string): void =>
  setPart(id, title, "pinnedRaw", pinned);

export function removeEntry(id: string): void {
  _index.delete(id);
}

export function size(): number {
  return _index.size;
}

/** Builds the index from whatever is cached locally. */
export async function rebuild(): Promise<number> {
  const notes = await db.getAllNotes();
  _index.clear();
  for (const n of notes) {
    const c = await db.getNoteContent(n.id);
    setEntry(n.id, n.title, c?.content);
  }
  return _index.size;
}

/**
 * Ranked matches for a query.
 *
 * All terms must appear (AND). Title matches outrank body matches so that
 * searching for a note by name still puts that note first. Returns `null` for
 * an empty query, which callers read as "no search, show the plain list".
 */
export function search(query: string, { limit = 200 }: { limit?: number } = {}): SearchHit[] | null {
  const terms = normalize(query).split(/\s+/).filter(Boolean);
  if (terms.length === 0) return null;

  const hits: Array<{ id: string; score: number; entry: IndexEntry }> = [];
  for (const [id, entry] of _index) {
    let score = 0;
    let matchedAll = true;
    for (const term of terms) {
      const inTitle = entry.title.includes(term);
      const inText = entry.text.includes(term);
      if (!inTitle && !inText) {
        matchedAll = false;
        break;
      }
      if (inTitle) score += entry.title.startsWith(term) ? 12 : 8;
      if (inText) score += 1;
    }
    if (matchedAll) hits.push({ id, score, entry });
  }

  hits.sort((a, b) => b.score - a.score);
  return hits.slice(0, limit).map(({ id, score, entry }) => ({
    id,
    score,
    snippet: snippetFor(entry, terms),
  }));
}

/**
 * A short excerpt around the first matching term, for the results list.
 *
 * Looks in what the user wrote first, then in an attached document: a hit inside
 * a PDF should still show the sentence it was found in, rather than an excerpt
 * of unrelated notes or nothing at all.
 */
function snippetFor(entry: IndexEntry, terms: string[], radius = 60): string {
  const firstHit = (source: string) => {
    if (!source) return -1;
    const haystack = normalize(source);
    let at = -1;
    for (const term of terms) {
      const i = haystack.indexOf(term);
      if (i !== -1 && (at === -1 || i < at)) at = i;
    }
    return at;
  };

  let text = entry.raw;
  let at = firstHit(text);
  // A pinned note is short and was written deliberately, so it outranks the
  // document's own text as the excerpt to show.
  if (at === -1 && entry.pinnedRaw) {
    text = entry.pinnedRaw;
    at = firstHit(text);
  }
  if (at === -1 && entry.attachedRaw) {
    text = entry.attachedRaw;
    at = firstHit(text);
  }
  if (!text) return "";
  if (at === -1) return text.slice(0, radius * 2).trim();

  const start = Math.max(0, at - radius);
  const end = Math.min(text.length, at + radius);
  return `${start > 0 ? "…" : ""}${text.slice(start, end).trim()}${end < text.length ? "…" : ""}`;
}