fix(make-pdf): correct CJK rendering — NUL sentinel hardening, SC-first fonts, CJK quote context

Three CJK fixes in the PDF pipeline:

- smartypants strips stray input NULs up front so document text can never
  forge the U+0000 placeholder sentinel and leak a preserved-zone marker
  into the output.
- The CJK font stack led with Japanese families, so Simplified-Chinese
  text rendered han glyphs with JP variants. Lead with PingFang SC /
  Heiti SC / Noto Sans CJK SC / Source Han Sans SC before the JP
  fallbacks.
- Quote-smartening only recognized ASCII openers as "start of quote"
  context; the fullwidth colon and CJK brackets now count, so quotes
  after them curl the right way.

Contributed by @rssprivacy-commits (PR #2012).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Garry Tan 2026-08-14 19:49:00 -07:00
parent 6e8e987133
commit 58482b3c69
No known key found for this signature in database
GPG Key ID: C1F69E85C74EFE1D
2 changed files with 5 additions and 5 deletions

View File

@ -37,8 +37,8 @@
// Metric-compatible sans stack: Helvetica (macOS), Liberation Sans (Linux,
// ships via fonts-liberation), Arial (Windows). Shared by every text surface.
const SANS_STACK = `Helvetica, "Liberation Sans", Arial`;
// CJK fallback families, appended to the body stack only.
const CJK_STACK = `"Hiragino Kaku Gothic ProN", "Noto Sans CJK JP", "Microsoft YaHei"`;
// CJK fallback families (Simplified-Chinese first), appended to the body stack only.
const CJK_STACK = `"PingFang SC", "Heiti SC", "Noto Sans CJK SC", "Source Han Sans SC", "Microsoft YaHei", "Hiragino Kaku Gothic ProN", "Noto Sans CJK JP"`;
// Color-emoji families: Apple (macOS), Segoe (Windows), Noto (Linux).
const EMOJI_FAMILIES = `"Apple Color Emoji", "Segoe UI Emoji", "Noto Color Emoji"`;

View File

@ -49,7 +49,7 @@ export function smartypants(html: string): string {
});
};
let s = html;
let s = html.replace(/\u0000/g, ""); // drop stray input NUL (can't forge a placeholder)
s = carve(s, CODE_ZONE_RE);
s = carve(s, TAG_RE);
s = carve(s, URL_RE);
@ -94,11 +94,11 @@ function transformText(text: string): string {
// Double quotes: open if preceded by whitespace/bol, close if preceded
// by word char or punctuation.
s = s.replace(/(^|[\s\(\[\{\-])"/g, "$1\u201c"); // opening "
s = s.replace(/(^|[\s\(\[\{\-\uff1a\uff08\u3010\u300c\u300e\u3008\u300a])"/g, "$1\u201c"); // opening "
s = s.replace(/"/g, "\u201d"); // remaining " are closing
// Single quotes (after apostrophe pass):
s = s.replace(/(^|[\s\(\[\{\-])'/g, "$1\u2018"); // opening '
s = s.replace(/(^|[\s\(\[\{\-\uff1a\uff08\u3010\u300c\u300e\u3008\u300a])'/g, "$1\u2018"); // opening '
s = s.replace(/'/g, "\u2019"); // remaining ' are closing
return s;