Voiced/src/pdf/fonts/register.ts

import { Font } from "@react-pdf/renderer";
import { FONT_MANIFEST } from "./manifest";
import { familySources } from "./stack";

export { FONT_STACK, familySources, stack, type FamilySource } from "./stack";

let registered = false;

/**
 * Registers every bundled family from the manifest. Idempotent; never call Font.reset(), the fonts
 * would not load again.
 *
 * `base` is a URL prefix in the app ("/fonts") and a directory under Node (tests). Only static TTF is
 * used: WOFF2 embeds glyphs without outlines (invisible text) and variable fonts embed only their
 * default instance.
 */
export function registerBundledFonts(base: string): void {
  if (registered) return;
  registered = true;

  for (const fam of FONT_MANIFEST.families) {
    const sources = familySources(fam).map((s) => ({
      src: `${base}/${fam.folder}/${s.file}`,
      fontWeight: s.fontWeight,
      fontStyle: s.fontStyle,
    }));
    Font.register({ family: fam.family, fonts: sources });
  }

  // The default hyphenation inserts "-" into e-mail addresses, URLs and identifiers.
  Font.registerHyphenationCallback((word) => [word]);
}

/** The slice of a fontkit TTF font the priming touches (fontkit's types do not declare it). */
interface FkFont {
  numGlyphs: number;
  characterSet: number[];
  glyphForCodePoint(cp: number): unknown;
  _getBaseGlyph(id: number): { _decode?(): { components?: Array<{ glyphID: number }> } | null };
  _glyphs: Record<number, unknown>;
  _cmapProcessor: { lookup(cp: number): number };
}

const isPrivateUse = (cp: number) => cp >= 0xe000 && cp <= 0xf8ff;

/**
 * Creates, through the cmap and so with their code point, every glyph that a composite glyph uses as a
 * component. Not the whole cmap: a glyph that layout substitutes in (Inter's contextual hyphen between digits)
 * is mapped from a private-use code point, and creating it from there would give it a code point the text
 * never had. Components that only a private-use code point reaches are left alone.
 */
function primeComponents(font: FkFont): void {
  const components = new Set<number>();
  // _getBaseGlyph caches what it creates, with no code points; scan into a scratch cache so that does not happen.
  const cache = font._glyphs;
  font._glyphs = {};
  try {
    for (let id = 0; id < font.numGlyphs; id++) {
      const decoded = font._getBaseGlyph(id)._decode?.();
      for (const c of decoded?.components ?? []) components.add(c.glyphID);
    }
  } finally {
    font._glyphs = cache;
  }
  const lowest = new Map<number, number>();
  for (const cp of [...font.characterSet].sort((a, b) => a - b)) {
    if (isPrivateUse(cp)) continue;
    const id = font._cmapProcessor.lookup(cp);
    if (components.has(id) && !lowest.has(id)) lowest.set(id, cp);
  }
  for (const cp of lowest.values()) font.glyphForCodePoint(cp);
}

let primed: Promise<void> | null = null;

/**
 * Loads every registered face and gives the component glyphs of its composites their code points. fontkit
 * caches glyph objects per font for the whole process, and pdfkit creates a composite's components at embed
 * time with no code points: Poppins' colon contains the period, so a document that sets ':' before any '.'
 * would leave the period glyph with codePoints [] for every later document (amounts extracted as "1,200;00",
 * textkit's line breaks slipping). Creating those glyphs here first makes a render independent of the renders
 * before it. Memoised; await it before the first render.
 */
export function primeFontGlyphs(): Promise<void> {
  if (!registered) return Promise.resolve();
  if (!primed) {
    primed = run().catch((err) => {
      primed = null;
      throw err;
    });
  }
  return primed;

  async function run(): Promise<void> {
    for (const fam of FONT_MANIFEST.families) {
      for (const s of familySources(fam)) {
        const descriptor = { fontFamily: fam.family, fontWeight: s.fontWeight, fontStyle: s.fontStyle };
        await Font.load(descriptor);
        const data = (Font as unknown as { getFont(d: object): { data: FkFont | null } }).getFont(descriptor).data;
        if (data) primeComponents(data);
      }
    }
  }
}

const MIN_FONT_BYTES = 10 * 1024;

function hasTrueTypeMagic(b: Uint8Array): boolean {
  if (b.length < 4) return false;
  if (b[0] === 0 && b[1] === 1 && b[2] === 0 && b[3] === 0) return true;
  return String.fromCharCode(b[0], b[1], b[2], b[3]) === "true";
}

/**
 * Fetches every bundled font and returns a list of problems (empty when all are fine). Tauri answers
 * an unknown path with index.html and HTTP 200, so the response bytes must be checked, not the status.
 */
export async function preflightFonts(
  fetchBytes: (url: string) => Promise<Uint8Array>,
  base: string,
): Promise<string[]> {
  const problems: string[] = [];
  for (const fam of FONT_MANIFEST.families) {
    for (const font of fam.fonts) {
      const url = `${base}/${fam.folder}/${font.file}`;
      try {
        const bytes = await fetchBytes(url);
        if (!hasTrueTypeMagic(bytes)) problems.push(`${url}: not a TrueType font`);
        else if (bytes.length <= MIN_FONT_BYTES) problems.push(`${url}: only ${bytes.length} bytes`);
      } catch (err) {
        problems.push(`${url}: ${err instanceof Error ? err.message : String(err)}`);
      }
    }
  }
  return problems;
}