Voiced/src/pdf/fonts/register.ts

import { Font } from "@react-pdf/renderer";
import { FONT_MANIFEST } from "./manifest";
import { familySources } from "./stack";
import {
  assertSfnt,
  familyNameFor,
  isUserFamilyKnown,
  rememberUserFiles,
  userFamilySources,
  type UserFace,
  type UserFontFile,
} from "./userFontStore";

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);
}

/** Descriptors already primed; a font registered after the first render (a user font) is primed on the next call. */
const primedKeys = new Set<string>();
let primeChain: Promise<void> = Promise.resolve();

/**
 * 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. Covers the bundled families and any user family registered so far, each descriptor once, so a
 * font registered later is not skipped. Await it before the first render.
 */
export function primeFontGlyphs(): Promise<void> {
  if (!registered && primedKeys.size === 0 && userFamilies.length === 0) return Promise.resolve();
  const next = primeChain.then(run);
  primeChain = next.catch(() => undefined);
  return next;

  async function run(): Promise<void> {
    const descriptors: Array<{ fontFamily: string; fontWeight: number; fontStyle: "normal" | "italic" }> = [];
    if (registered) {
      for (const fam of FONT_MANIFEST.families) {
        for (const s of familySources(fam)) descriptors.push({ fontFamily: fam.family, fontWeight: s.fontWeight, fontStyle: s.fontStyle });
      }
    }
    for (const family of userFamilies) {
      for (const s of userFamilySources(family)) descriptors.push({ fontFamily: family, fontWeight: s.fontWeight, fontStyle: s.fontStyle });
    }
    for (const descriptor of descriptors) {
      const key = `${descriptor.fontFamily}|${descriptor.fontWeight}|${descriptor.fontStyle}`;
      if (primedKeys.has(key)) continue;
      await Font.load(descriptor);
      const data = (Font as unknown as { getFont(d: object): { data: FkFont | null } }).getFont(descriptor).data;
      if (data) primeComponents(data);
      primedKeys.add(key);
    }
  }
}

// ---- User-imported fonts (Now, Gotham, Open Sauce One) ----

const userFamilies: string[] = [];
const isNode = typeof process !== "undefined" && !!process.versions?.node;

/**
 * A src react-pdf can load the bytes from. In a browser or worker that is a blob: URL (react-pdf fetches it;
 * a data URI would be decoded character by character, which is slow for a multi-MB font). Under Node it is a
 * temporary file, because react-pdf's Node build opens anything that is not an http(s) URL as a path.
 */
async function sourceFor(bytes: Uint8Array, id: string): Promise<string> {
  if (!isNode) return URL.createObjectURL(new Blob([bytes as BlobPart], { type: "font/ttf" }));
  const nodeFs = "node:fs";
  const nodeOs = "node:os";
  const nodePath = "node:path";
  const [fs, os, path] = await Promise.all([import(/* @vite-ignore */ nodeFs), import(/* @vite-ignore */ nodeOs), import(/* @vite-ignore */ nodePath)]);
  const dir = fs.mkdtempSync(path.join(os.tmpdir(), "voiced-userfont-"));
  const file = path.join(dir, `${id.slice(0, 16)}.ttf`);
  fs.writeFileSync(file, bytes);
  return file;
}

/**
 * Registers one face's files as the family `user:<Face>:<set id>` and returns that name. Every file's magic bytes
 * are checked before fontkit sees it. Each weight without an italic gets its upright file as the italic. Idempotent:
 * the same set registers once. Never resets the font store; a different set is a different family.
 */
export async function registerUserFontSet(face: UserFace, files: UserFontFile[]): Promise<string> {
  if (files.length === 0) throw new Error(`No font files were given for ${face}`);
  for (const f of files) assertSfnt(f.bytes);
  const family = familyNameFor(face, files.map((f) => f.sha256));
  if (isUserFamilyKnown(family)) return family;
  rememberUserFiles(family, files);
  const srcs = new Map<string, string>();
  for (const s of userFamilySources(family)) {
    if (!srcs.has(s.id)) srcs.set(s.id, await sourceFor(s.bytes, s.id));
  }
  Font.register({
    family,
    fonts: userFamilySources(family).map((s) => ({ src: srcs.get(s.id) as string, fontWeight: s.fontWeight as never, fontStyle: s.fontStyle })),
  });
  userFamilies.push(family);
  await primeFontGlyphs();
  return family;
}

/** Cheap non-cryptographic id (two FNV-1a passes, 16 hex digits) for callers that have no sha256, i.e. tests. */
function fallbackId(bytes: Uint8Array): string {
  let a = 0x811c9dc5;
  let b = 0x01000193;
  for (let i = 0; i < bytes.length; i++) {
    a = Math.imul(a ^ bytes[i], 0x01000193) >>> 0;
    b = Math.imul(b ^ bytes[i], 0x811c9dc5) >>> 0;
  }
  return a.toString(16).padStart(8, "0") + b.toString(16).padStart(8, "0");
}

/** One-file convenience for Node tests and single-weight imports: the font as the only member of the face's set. */
export async function registerUserFont(
  face: UserFace,
  bytes: Uint8Array,
  opts: { weight?: number; italic?: boolean; sha256?: string } = {},
): Promise<{ family: string; sha256: string }> {
  const sha256 = opts.sha256 ?? fallbackId(bytes);
  const family = await registerUserFontSet(face, [{ face, weight: opts.weight ?? 400, italic: opts.italic ?? false, sha256, bytes }]);
  return { family, sha256 };
}

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;
}