Reuse fonts loaded from the same binary data

CHANGELOG.md

@@ -2,6 +2,7 @@
 
 ### Unreleased
 
+- Fix `doc.table()` parsing a font passed as binary data (e.g. registered with `registerFont(name, uint8Array)`) again for every cell, when it restores the font after measuring and drawing the cell, which made tables with such fonts slower. A font loaded from the same `Uint8Array` is now reused without parsing it again
 - Add `lineBreak: 'whitespace'` to `doc.text()`, which breaks a line only at whitespace, a soft hyphen or a zero-width space. The Unicode line breaking rules the wrapper follows also allow a break after a hyphen or a slash, so `design-system` or `https://github.com/foliojs/pdfkit` could be cut at a line end, and a text extractor that joins the lines, such as a résumé parser, reads two words
 - Add an `objectStreams` option, which packs the objects that are not streams into compressed object streams and writes a cross-reference stream instead of the xref table, making documents with many such objects, e.g. tagged ones, much smaller. It requires a `pdfVersion` of `1.5` or higher, and cannot be used with encryption or PDF/A-1. Fixes #1810
 - Fix wrapped text with `align: 'center'` sitting left of the middle of the line when `characterSpacing` or `wordSpacing` is set, and with `align: 'right'` running past the right edge by the `wordSpacing` of each gap between words

lib/mixins/fonts.js

@@ -29,6 +29,8 @@ export default {
   ) {
     // Lookup table for embedded fonts
     this._fontFamilies = {};
+    // Embedded fonts by binary source (e.g. Uint8Array), so passing the same object again does not parse the font again
+    this._fontsBySource = new WeakMap();
     this._fontCount = 0;
 
     // Font state
@@ -80,6 +82,14 @@ export default {
       return this;
     }
 
+    // fast path for binary data that was already loaded, so passing the same
+    // object again does not parse the font again. Not used with a family
+    const bySource = !family && src !== null && typeof src === 'object';
+    if (bySource && (font = this._fontsBySource.get(src))) {
+      this._font = font;
+      return this;
+    }
+
     // load the font
     const id = `F${++this._fontCount}`;
     this._font = PDFFontFactory.open(this, src, family, id);
@@ -91,9 +101,12 @@ export default {
       isEqualFont(this._font, font)
     ) {
       this._font = font;
+      if (bySource) this._fontsBySource.set(src, font);
       return this;
     }
 
+    if (bySource) this._fontsBySource.set(src, this._font);
+
     // save the font for reuse later
     if (cacheKey) {
       this._fontFamilies[cacheKey] = this._font;

tests/unit/font.spec.js

@@ -395,3 +395,62 @@ describe('font name collision', () => {
     });
   });
 });
+
+describe('binary font sources', () => {
+  const data = () =>
+    new Uint8Array(readFileSync('tests/fonts/Roboto-Regular.ttf'));
+
+  test('the same data passed twice is parsed once', () => {
+    const doc = new PDFDocument({ font: null });
+    const open = vi.spyOn(PDFFontFactory, 'open');
+    const buf = data();
+
+    doc.font(buf);
+    const first = doc._font;
+    doc.font(buf);
+
+    expect(doc._font.id).toBe(first.id);
+    expect(open).toHaveBeenCalledTimes(1);
+    open.mockRestore();
+  });
+
+  test('a registered binary font is parsed once when tables restore it', () => {
+    const doc = new PDFDocument({ font: null });
+    doc.registerFont('Body', data());
+    doc.font('Body');
+    const open = vi.spyOn(PDFFontFactory, 'open');
+
+    doc.table({
+      data: [
+        ['a', 'b', 'c'],
+        ['d', 'e', 'f'],
+      ],
+    });
+
+    expect(open).not.toHaveBeenCalled();
+    expect(doc._font.name).toBe('Roboto-Regular');
+    open.mockRestore();
+  });
+
+  test('different data of the same font still embeds one font', () => {
+    const doc = new PDFDocument({ font: null });
+
+    doc.font(data());
+    const first = doc._font;
+    doc.font(data());
+
+    expect(doc._font.id).toBe(first.id);
+  });
+
+  test('a duplicate buffer passed again reuses the embedded font', () => {
+    const doc = new PDFDocument({ font: null });
+    const buf = data();
+
+    doc.font(data());
+    const first = doc._font;
+    doc.font(buf);
+    doc.font(buf);
+
+    expect(doc._font.id).toBe(first.id);
+  });
+});