feat: add mcpp.toml syntax highlighting

Author: wellwei

CHANGELOG.md

@@ -2,7 +2,10 @@
 
 ## 0.2.3
 
-- 为精确文件名 `build.mcpp` 增加 C++ 语言关联，复用 VS Code 内置 C++ 高亮和现有模块语法注入；不扩大到所有 `*.mcpp` 文件。
+- 为精确文件名 `build.mcpp` 增加 C++ 语言关联，复用 VS Code 内置 C++ 高亮和现有模块
+  语法注入；不扩大到所有 `*.mcpp` 文件。
+- 为精确文件名 `mcpp.toml` 内置独立 TOML 语法高亮，不依赖额外扩展，也不接管普通
+  `*.toml` 文件。
 
 ## 0.2.2
 

README.md

@@ -17,6 +17,7 @@ mcpp CLI 操作；它不实现新的 C++ 语言服务器，也不替代 mcpp 的
 | 能力 | LLVM/Clang | GCC | MSVC |
 | --- | --- | --- | --- |
 | 识别 mcpp 工程 | 支持 | 支持 | 支持 |
+| `mcpp.toml` TOML 语法高亮 | 支持 | 支持 | 支持 |
 | `build.mcpp`、`.cppm`、`.ixx`、`.mpp`、`.ccm` 文件关联 | 支持 | 支持 | 支持 |
 | `module`、`export module`、`import` 语法高亮 | 支持 | 支持 | 支持 |
 | 构建、运行、测试、清理命令 | 支持 | 支持 | 支持 |
@@ -78,8 +79,10 @@ xlings 安装。
 
 扩展激活本身不会静默运行 `mcpp build`，也不会自动下载、安装或切换工具链。
 
-### C++ 模块语法高亮
+### 语法高亮
 
+- 将精确文件名 `mcpp.toml` 识别为独立的 mcpp TOML 语言，内置表、键、字符串、数字、
+  布尔、日期时间和注释高亮。
 - 将 `build.mcpp`、`.cppm`、`.ixx`、`.mpp` 和 `.ccm` 关联到 VS Code 内置 `cpp` 语言。
 - 向 `source.cpp` 注入模块语法规则。
 - 覆盖 `module`、`export module`、`import`、`export import`、模块名和模块分区。

package.json

@@ -132,6 +132,18 @@
         }
       }
     },
+    "languages": [
+      {
+        "id": "mcpp-toml",
+        "aliases": [
+          "mcpp TOML",
+          "mcpp.toml"
+        ],
+        "filenames": [
+          "mcpp.toml"
+        ]
+      }
+    ],
     "configurationDefaults": {
       "files.associations": {
         "build.mcpp": "cpp",
@@ -142,6 +154,11 @@
       }
     },
     "grammars": [
+      {
+        "language": "mcpp-toml",
+        "scopeName": "source.toml.mcpp",
+        "path": "./syntaxes/mcpp-toml.tmLanguage.json"
+      },
       {
         "scopeName": "source.cpp.mcpp-modules",
         "injectTo": [

syntaxes/mcpp-toml.tmLanguage.json

@@ -0,0 +1,116 @@
+{
+  "$schema": "https://raw.githubusercontent.com/martinring/tmlanguage/master/tmlanguage.json",
+  "name": "mcpp TOML",
+  "scopeName": "source.toml.mcpp",
+  "patterns": [
+    {
+      "include": "#comment"
+    },
+    {
+      "include": "#table"
+    },
+    {
+      "include": "#key"
+    },
+    {
+      "include": "#string"
+    },
+    {
+      "include": "#datetime"
+    },
+    {
+      "include": "#number"
+    },
+    {
+      "include": "#boolean"
+    },
+    {
+      "include": "#punctuation"
+    }
+  ],
+  "repository": {
+    "comment": {
+      "match": "#.*$",
+      "name": "comment.line.number-sign.toml"
+    },
+    "table": {
+      "match": "^\\s*(\\[\\[?)([^\\]\\r\\n]+?)(\\]\\]?)\\s*(?=#|$)",
+      "captures": {
+        "1": {
+          "name": "punctuation.definition.table.begin.toml"
+        },
+        "2": {
+          "name": "entity.name.section.toml"
+        },
+        "3": {
+          "name": "punctuation.definition.table.end.toml"
+        }
+      }
+    },
+    "key": {
+      "match": "^\\s*((?:[A-Za-z0-9_-]+|\"[^\"]+\"|'[^']+')(?:\\s*\\.\\s*(?:[A-Za-z0-9_-]+|\"[^\"]+\"|'[^']+'))*)\\s*(=)",
+      "captures": {
+        "1": {
+          "name": "variable.other.key.toml"
+        },
+        "2": {
+          "name": "keyword.operator.assignment.toml"
+        }
+      }
+    },
+    "string": {
+      "patterns": [
+        {
+          "begin": "\"\"\"",
+          "end": "\"\"\"",
+          "name": "string.quoted.triple.basic.toml",
+          "patterns": [
+            {
+              "include": "#escape"
+            }
+          ]
+        },
+        {
+          "begin": "'''",
+          "end": "'''",
+          "name": "string.quoted.triple.literal.toml"
+        },
+        {
+          "begin": "\"",
+          "end": "\"",
+          "name": "string.quoted.double.toml",
+          "patterns": [
+            {
+              "include": "#escape"
+            }
+          ]
+        },
+        {
+          "begin": "'",
+          "end": "'",
+          "name": "string.quoted.single.toml"
+        }
+      ]
+    },
+    "escape": {
+      "match": "\\\\(?:[btnfr\"\\\\]|u[0-9A-Fa-f]{4}|U[0-9A-Fa-f]{8})",
+      "name": "constant.character.escape.toml"
+    },
+    "datetime": {
+      "match": "(?<![A-Za-z0-9_-])(?:\\d{4}-\\d{2}-\\d{2}(?:[Tt ]\\d{2}:\\d{2}:\\d{2}(?:\\.\\d+)?(?:[Zz]|[+-]\\d{2}:\\d{2})?)?|\\d{2}:\\d{2}:\\d{2}(?:\\.\\d+)?)(?![A-Za-z0-9_-])",
+      "name": "constant.other.datetime.toml"
+    },
+    "number": {
+      "match": "(?<![A-Za-z0-9_-])[-+]?(?:0x[0-9A-Fa-f](?:_?[0-9A-Fa-f])*|0o[0-7](?:_?[0-7])*|0b[01](?:_?[01])*|(?:\\d(?:_?\\d)*)(?:\\.\\d(?:_?\\d)*)?(?:[eE][-+]?\\d(?:_?\\d)*)?|inf|nan)(?![A-Za-z0-9_-])",
+      "name": "constant.numeric.toml"
+    },
+    "boolean": {
+      "match": "(?<![A-Za-z0-9_-])(?:true|false)(?![A-Za-z0-9_-])",
+      "name": "constant.language.boolean.toml"
+    },
+    "punctuation": {
+      "match": "[\\[\\]{},.]",
+      "name": "punctuation.separator.toml"
+    }
+  }
+}

test/artifacts.test.ts

@@ -16,7 +16,8 @@ interface PackageManifest {
     commands?: Array<{ command: string }>;
     configuration?: { properties?: Record<string, unknown> };
     configurationDefaults?: Record<string, unknown>;
-    grammars?: Array<{ scopeName: string; injectTo?: string[]; path: string }>;
+    languages?: Array<{ id: string; aliases?: string[]; filenames?: string[] }>;
+    grammars?: Array<{ language?: string; scopeName: string; injectTo?: string[]; path: string }>;
   };
 }
 
@@ -70,6 +71,50 @@ test("associates the build.mcpp file with the C++ language", () => {
   assert.equal(associations?.["*.mcpp"], undefined);
 });
 
+test("ships TOML highlighting for the exact mcpp.toml filename", () => {
+  const manifest = JSON.parse(readFileSync(path.join(root, "package.json"), "utf8")) as PackageManifest;
+  const language = manifest.contributes?.languages?.find((item) => item.id === "mcpp-toml");
+  assert.deepEqual(language, {
+    id: "mcpp-toml",
+    aliases: ["mcpp TOML", "mcpp.toml"],
+    filenames: ["mcpp.toml"],
+  });
+
+  const grammar = manifest.contributes?.grammars?.find((item) => item.language === "mcpp-toml");
+  assert.deepEqual(grammar, {
+    language: "mcpp-toml",
+    scopeName: "source.toml.mcpp",
+    path: "./syntaxes/mcpp-toml.tmLanguage.json",
+  });
+
+  const grammarText = readFileSync(path.join(root, "syntaxes/mcpp-toml.tmLanguage.json"), "utf8");
+  const grammarDocument = JSON.parse(grammarText) as {
+    repository?: Record<string, { match?: string }>;
+  };
+  for (const key of ["comment", "table", "key", "string", "datetime", "number", "boolean", "punctuation"]) {
+    assert.ok(grammarDocument.repository?.[key], `missing TOML grammar rule: ${key}`);
+  }
+
+  const tablePattern = new RegExp(grammarDocument.repository?.table.match ?? "");
+  assert.match("[package]", tablePattern);
+  assert.match("[[target.generated]]", tablePattern);
+
+  const keyPattern = new RegExp(grammarDocument.repository?.key.match ?? "");
+  assert.match('standard = "c++23"', keyPattern);
+  assert.match('"quoted.key" = true', keyPattern);
+
+  for (const scope of [
+    "comment.line.number-sign.toml",
+    "entity.name.section.toml",
+    "variable.other.key.toml",
+    "string.quoted.double.toml",
+    "constant.numeric.toml",
+    "constant.language.boolean.toml",
+  ]) {
+    assert.match(grammarText, new RegExp(scope.replaceAll(".", "\\.")));
+  }
+});
+
 test("ships an injection grammar with module-specific scopes", () => {
   const manifest = JSON.parse(readFileSync(path.join(root, "package.json"), "utf8")) as PackageManifest;
   const grammar = manifest.contributes?.grammars?.find((item) => item.scopeName === "source.cpp.mcpp-modules");