From ac46a4f16eaaf73c1ba82b7cdec6d10ab18ad38a Mon Sep 17 00:00:00 2001
From: Tatsunori Uchino <tats.u@live.jp>
Date: Wed, 27 Nov 2024 00:52:53 +0900
Subject: [PATCH] Treat U+30A0 & U+30FB in Katakana Block as CJK (#16796)

---
 changelog_unreleased/markdown/16796.md        | 25 +++++++++++++++++++
 cspell.json                                   |  1 +
 src/language-markdown/constants.evaluate.js   |  9 ++++++-
 .../__snapshots__/format.test.js.snap         | 12 +++++++++
 .../splitCjkText/symbolSpaceNewLine.md        | 10 ++++++++
 5 files changed, 56 insertions(+), 1 deletion(-)
 create mode 100644 changelog_unreleased/markdown/16796.md

diff --git a/changelog_unreleased/markdown/16796.md b/changelog_unreleased/markdown/16796.md
new file mode 100644
index 000000000..3e6612d00
--- /dev/null
+++ b/changelog_unreleased/markdown/16796.md
@@ -0,0 +1,25 @@
+#### Treat U+30A0 & U+30FB in Katakana Block as CJK (#16796 by @tats-u)
+
+Prettier doesn't treat U+30A0 & U+30FB as Japanese. U+30FB is commonly used in Japanese to represent the delimitation of first and last names of non-Japanese people or “and”. The following “C言語・C++・Go・Rust” means “C language & C++ & Go & Rust” in Japanese.
+
+<!-- prettier-ignore -->
+```md
+<!-- Input (--prose-wrap=never) -->
+
+C言
+語
+・
+C++
+・
+Go
+・
+Rust
+
+<!-- Prettier stable -->
+C言語・ C++ ・ Go ・ Rust
+
+<!-- Prettier main -->
+C言語・C++・Go・Rust
+```
+
+U+30A0 can be used as the replacement of the `-` in non-Japanese names (e.g. “Saint-Saëns” (Charles Camille Saint-Saëns) can be represented as “サン゠サーンス” in Japanese), but substituted by ASCII hyphen (U+002D) or U+FF1D (full width hyphen) in many cases (e.g. “サン=サーンス” or “サン＝サーンス”).
diff --git a/cspell.json b/cspell.json
index 5d888bc73..c35b8b1b1 100644
--- a/cspell.json
+++ b/cspell.json
@@ -241,6 +241,7 @@
         "Rubocop",
         "ruleset",
         "rulesets",
+        "Saëns",
         "sandhose",
         "Sapegin",
         "sbdchd",
diff --git a/src/language-markdown/constants.evaluate.js b/src/language-markdown/constants.evaluate.js
index 24ee2e31e..816ce3c5f 100644
--- a/src/language-markdown/constants.evaluate.js
+++ b/src/language-markdown/constants.evaluate.js
@@ -14,7 +14,14 @@ const cjkCharset = new Charset(
       "Modifier_Symbol",
       "Nonspacing_Mark",
     ],
-  }),
+    // .union below makes the next Block condition "OR"
+    // If it is merged into this object definition, it will be "AND" instead
+  }).union(
+    // Firefox treats some symbols (U+30A0, U+30FB) in the Katakana block as CJK
+    unicodeRegex({
+      Block: ["Katakana"],
+    }),
+  ),
 );
 const variationSelectorsCharset = unicodeRegex({
   Block: ["Variation_Selectors", "Variation_Selectors_Supplement"],
diff --git a/tests/format/markdown/splitCjkText/__snapshots__/format.test.js.snap b/tests/format/markdown/splitCjkText/__snapshots__/format.test.js.snap
index 4b9b76376..e587af369 100644
--- a/tests/format/markdown/splitCjkText/__snapshots__/format.test.js.snap
+++ b/tests/format/markdown/splitCjkText/__snapshots__/format.test.js.snap
@@ -283,6 +283,16 @@ English
 [ウ
 ィキペディア]: https://ja.wikipedia.org/
 
+
+C言
+語
+・
+C++
+・
+Go
+・
+Rust
+
 =====================================output=====================================
 日本語、にほんご。汉语, 中文. 日本語，にほんご．English
 words!? 漢字！汉字？「セリフ」(括弧) 文字（括弧）文字【括弧】日本語English
@@ -297,5 +307,7 @@ words!? 漢字！汉字？「セリフ」(括弧) 文字（括弧）文字【括
 
 [ウ ィキペディア]: https://ja.wikipedia.org/
 
+C言語・C++・Go・Rust
+
 ================================================================================
 `;
diff --git a/tests/format/markdown/splitCjkText/symbolSpaceNewLine.md b/tests/format/markdown/splitCjkText/symbolSpaceNewLine.md
index f46aaee81..013ca9ba4 100644
--- a/tests/format/markdown/splitCjkText/symbolSpaceNewLine.md
+++ b/tests/format/markdown/splitCjkText/symbolSpaceNewLine.md
@@ -57,3 +57,13 @@ English
 
 [ウ
 ィキペディア]: https://ja.wikipedia.org/
+
+
+C言
+語
+・
+C++
+・
+Go
+・
+Rust