Pick the matching Noto CJK variant for language-tagged text

The generic assigns swap sans-serif, serif and monospace for fonts with no CJK glyphs, so tagged Chinese text ends up on whatever Noto CJK variant the charset scan finds first, usually the Japanese one. Fold the many Chinese tags down to one per variant and prepend the matching family ahead of the assigns.
2026-08-31 14:42:27 -04:00
1 changed files with 307 additions and 0 deletions
@@ -1,6 +1,313 @@
 <?xml version="1.0"?>
 <!DOCTYPE fontconfig SYSTEM "fonts.dtd">
 <fontconfig>
  <!-- CJK: give language-tagged text the Noto CJK variant that matches its
       language. noto-fonts-cjk ships all five, Han glyph shapes differ between
       them, and the generic assigns below would otherwise hand tagged CJK text
       to families with no Han coverage, leaving the variant to a charset-scan
       lottery. Chinese arrives under many tags (W3C recommends the zh-Hans and
       zh-Hant script forms), so the tags are first folded onto one tag per
       variant. Order is load-bearing: a bare zh and a bare zh-hant satisfy
       the contains test of every one of their extensions, so both are pinned
       by exact matches before the extension folds run. Cantonese under its
       own primary tag folds to Hong Kong forms, except explicitly
       Simplified Cantonese, which folds to SC. -->
  <match target="pattern">
    <test name="lang" compare="eq">
      <string>zh</string>
    </test>
    <edit name="lang" mode="assign">
      <string>zh-cn</string>
    </edit>
  </match>
  <match target="pattern">
    <test name="lang" compare="eq">
      <string>zh-hant</string>
    </test>
    <edit name="lang" mode="assign">
      <string>zh-tw</string>
    </edit>
  </match>
  <match target="pattern">
    <test name="lang" compare="contains">
      <string>zh-hant-hk</string>
    </test>
    <edit name="lang" mode="assign">
      <string>zh-hk</string>
    </edit>
  </match>
  <match target="pattern">
    <test name="lang" compare="contains">
      <string>zh-hant-mo</string>
    </test>
    <edit name="lang" mode="assign">
      <string>zh-hk</string>
    </edit>
  </match>
  <match target="pattern">
    <test name="lang" compare="contains">
      <string>zh-hant</string>
    </test>
    <edit name="lang" mode="assign">
      <string>zh-tw</string>
    </edit>
  </match>
  <match target="pattern">
    <test name="lang" compare="contains">
      <string>zh-hans</string>
    </test>
    <edit name="lang" mode="assign">
      <string>zh-cn</string>
    </edit>
  </match>
  <match target="pattern">
    <test name="lang" compare="contains">
      <string>zh-sg</string>
    </test>
    <edit name="lang" mode="assign">
      <string>zh-cn</string>
    </edit>
  </match>
  <match target="pattern">
    <test name="lang" compare="contains">
      <string>zh-mo</string>
    </test>
    <edit name="lang" mode="assign">
      <string>zh-hk</string>
    </edit>
  </match>
  <match target="pattern">
    <test name="lang" compare="eq">
      <string>yue</string>
    </test>
    <edit name="lang" mode="assign">
      <string>zh-hk</string>
    </edit>
  </match>
  <match target="pattern">
    <test name="lang" compare="contains">
      <string>yue-hans</string>
    </test>
    <edit name="lang" mode="assign">
      <string>zh-cn</string>
    </edit>
  </match>
  <match target="pattern">
    <test name="lang" compare="contains">
      <string>yue-cn</string>
    </test>
    <edit name="lang" mode="assign">
      <string>zh-cn</string>
    </edit>
  </match>
  <match target="pattern">
    <test name="lang" compare="contains">
      <string>yue</string>
    </test>
    <edit name="lang" mode="assign">
      <string>zh-hk</string>
    </edit>
  </match>
  <!-- Each variant is then prepended for its tag, ahead of the assigns below
       because these test the generic names those assigns replace. Unlike the
       Arabic rule further down, these carry a family test, so the prepend
       lands just ahead of the matched generic and a concrete family the app
       asked for stays in front of the variant. -->
  <match target="pattern">
    <test name="lang" compare="contains">
      <string>zh-cn</string>
    </test>
    <test name="family">
      <string>sans-serif</string>
    </test>
    <edit name="family" mode="prepend" binding="strong">
      <string>Noto Sans CJK SC</string>
    </edit>
  </match>
  <match target="pattern">
    <test name="lang" compare="contains">
      <string>zh-cn</string>
    </test>
    <test name="family">
      <string>serif</string>
    </test>
    <edit name="family" mode="prepend" binding="strong">
      <string>Noto Serif CJK SC</string>
    </edit>
  </match>
  <match target="pattern">
    <test name="lang" compare="contains">
      <string>zh-cn</string>
    </test>
    <test name="family">
      <string>monospace</string>
    </test>
    <edit name="family" mode="prepend" binding="strong">
      <string>Noto Sans Mono CJK SC</string>
    </edit>
  </match>
  <match target="pattern">
    <test name="lang" compare="contains">
      <string>zh-hk</string>
    </test>
    <test name="family">
      <string>sans-serif</string>
    </test>
    <edit name="family" mode="prepend" binding="strong">
      <string>Noto Sans CJK HK</string>
    </edit>
  </match>
  <match target="pattern">
    <test name="lang" compare="contains">
      <string>zh-hk</string>
    </test>
    <test name="family">
      <string>serif</string>
    </test>
    <edit name="family" mode="prepend" binding="strong">
      <string>Noto Serif CJK HK</string>
    </edit>
  </match>
  <match target="pattern">
    <test name="lang" compare="contains">
      <string>zh-hk</string>
    </test>
    <test name="family">
      <string>monospace</string>
    </test>
    <edit name="family" mode="prepend" binding="strong">
      <string>Noto Sans Mono CJK HK</string>
    </edit>
  </match>
  <match target="pattern">
    <test name="lang" compare="contains">
      <string>zh-tw</string>
    </test>
    <test name="family">
      <string>sans-serif</string>
    </test>
    <edit name="family" mode="prepend" binding="strong">
      <string>Noto Sans CJK TC</string>
    </edit>
  </match>
  <match target="pattern">
    <test name="lang" compare="contains">
      <string>zh-tw</string>
    </test>
    <test name="family">
      <string>serif</string>
    </test>
    <edit name="family" mode="prepend" binding="strong">
      <string>Noto Serif CJK TC</string>
    </edit>
  </match>
  <match target="pattern">
    <test name="lang" compare="contains">
      <string>zh-tw</string>
    </test>
    <test name="family">
      <string>monospace</string>
    </test>
    <edit name="family" mode="prepend" binding="strong">
      <string>Noto Sans Mono CJK TC</string>
    </edit>
  </match>
  <match target="pattern">
    <test name="lang" compare="contains">
      <string>ja</string>
    </test>
    <test name="family">
      <string>sans-serif</string>
    </test>
    <edit name="family" mode="prepend" binding="strong">
      <string>Noto Sans CJK JP</string>
    </edit>
  </match>
  <match target="pattern">
    <test name="lang" compare="contains">
      <string>ja</string>
    </test>
    <test name="family">
      <string>serif</string>
    </test>
    <edit name="family" mode="prepend" binding="strong">
      <string>Noto Serif CJK JP</string>
    </edit>
  </match>
  <match target="pattern">
    <test name="lang" compare="contains">
      <string>ja</string>
    </test>
    <test name="family">
      <string>monospace</string>
    </test>
    <edit name="family" mode="prepend" binding="strong">
      <string>Noto Sans Mono CJK JP</string>
    </edit>
  </match>
  <match target="pattern">
    <test name="lang" compare="contains">
      <string>ko</string>
    </test>
    <test name="family">
      <string>sans-serif</string>
    </test>
    <edit name="family" mode="prepend" binding="strong">
      <string>Noto Sans CJK KR</string>
    </edit>
  </match>
  <match target="pattern">
    <test name="lang" compare="contains">
      <string>ko</string>
    </test>
    <test name="family">
      <string>serif</string>
    </test>
    <edit name="family" mode="prepend" binding="strong">
      <string>Noto Serif CJK KR</string>
    </edit>
  </match>
  <match target="pattern">
    <test name="lang" compare="contains">
      <string>ko</string>
    </test>
    <test name="family">
      <string>monospace</string>
    </test>
    <edit name="family" mode="prepend" binding="strong">
      <string>Noto Sans Mono CJK KR</string>
    </edit>
  </match>
  <match target="pattern">
    <test name="family" qual="any">
      <string>sans-serif</string>