feat(plugin): add CIE language registration and C++ style highlighting

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

8 files changed, 312 insertions, 0 deletions

diff --git a/plugin/.gitignore b/plugin/.gitignore
new file mode 100644
index 0000000..7443abf
--- /dev/null
+++ b/plugin/.gitignore
@@ -0,0 +1,3 @@
+node_modules/
+*.vsix
+.vscode-test/
diff --git a/plugin/examples/highlighting.cps b/plugin/examples/highlighting.cps
new file mode 100644
index 0000000..9925bf3
--- /dev/null
+++ b/plugin/examples/highlighting.cps
@@ -0,0 +1,41 @@
+// Open in a dark theme; keywords are uppercase and comments ignore [(
+TYPE Season = (Spring, Summer, Autumn, Winter)
+TYPE IntPointer = ^INTEGER
+TYPE Student
+	DECLARE Name : STRING
+	DECLARE Initial : CHAR
+ENDTYPE
+
+DECLARE Values : ARRAY[1:3] OF INTEGER
+DECLARE Index : INTEGER
+DECLARE Total : REAL
+DECLARE Ready : BOOLEAN
+DECLARE Text : STRING
+DECLARE Letter : CHAR
+Ready <- TRUE AND NOT FALSE
+Total <- -3.5 + 2 * 4 / 2
+Text <- "CIE // [()]" & " pseudocode"
+Letter <- 'A'
+
+FOR Index <- 1 TO 3 STEP 1
+	Values[Index] <- Index MOD 2
+NEXT Index
+IF Ready OR Total >= 1 THEN
+	OUTPUT MID(Text, 1, LENGTH(Text))
+ELSE
+	OUTPUT "Try again"
+ENDIF
+
+FUNCTION Double(Value : INTEGER) RETURNS INTEGER
+	RETURN Value * 2
+ENDFUNCTION
+PROCEDURE Swap(BYREF X : INTEGER, Y : INTEGER)
+	DECLARE Temp : INTEGER
+	Temp <- X
+	X <- Y
+	Y <- Temp
+ENDPROCEDURE
+
+OPENFILE "example.txt" FOR WRITE
+WRITEFILE "example.txt", Text
+CLOSEFILE "example.txt"
diff --git a/plugin/language-configuration.json b/plugin/language-configuration.json
new file mode 100644
index 0000000..ed3e464
--- /dev/null
+++ b/plugin/language-configuration.json
@@ -0,0 +1,13 @@
+{
+  "comments": { "lineComment": "//" },
+  "brackets": [["[", "]"], ["(", ")"]],
+  "colorizedBracketPairs": [["[", "]"], ["(", ")"]],
+  "autoClosingPairs": [
+    { "open": "[", "close": "]", "notIn": ["string", "comment"] },
+    { "open": "(", "close": ")", "notIn": ["string", "comment"] },
+    { "open": "'", "close": "'", "notIn": ["string", "comment"] },
+    { "open": "\"", "close": "\"", "notIn": ["string", "comment"] }
+  ],
+  "surroundingPairs": [["[", "]"], ["(", ")"], ["\"", "\""], ["'", "'"]],
+  "wordPattern": "[A-Za-z][A-Za-z0-9_]*"
+}
diff --git a/plugin/package-lock.json b/plugin/package-lock.json
new file mode 100644
index 0000000..18cd920
--- /dev/null
+++ b/plugin/package-lock.json
@@ -0,0 +1,34 @@
+{
+  "name": "cie-pseudocode",
+  "version": "0.1.0",
+  "lockfileVersion": 3,
+  "requires": true,
+  "packages": {
+    "": {
+      "name": "cie-pseudocode",
+      "version": "0.1.0",
+      "license": "GPL-3.0-only",
+      "devDependencies": {
+        "vscode-oniguruma": "^2.0.1",
+        "vscode-textmate": "^9.3.2"
+      },
+      "engines": {
+        "vscode": "^1.85.0"
+      }
+    },
+    "node_modules/vscode-oniguruma": {
+      "version": "2.0.1",
+      "resolved": "https://registry.npmjs.org/vscode-oniguruma/-/vscode-oniguruma-2.0.1.tgz",
+      "integrity": "sha512-poJU8iHIWnC3vgphJnrLZyI3YdqRlR27xzqDmpPXYzA93R4Gk8z7T6oqDzDoHjoikA2aS82crdXFkjELCdJsjQ==",
+      "dev": true,
+      "license": "MIT"
+    },
+    "node_modules/vscode-textmate": {
+      "version": "9.3.2",
+      "resolved": "https://registry.npmjs.org/vscode-textmate/-/vscode-textmate-9.3.2.tgz",
+      "integrity": "sha512-n2uGbUcrjhUEBH16uGA0TvUfhWwliFZ1e3+pTjrkim1Mt7ydB41lV08aUvsi70OlzDWp6X7Bx3w/x3fAXIsN0Q==",
+      "dev": true,
+      "license": "MIT"
+    }
+  }
+}
diff --git a/plugin/package.json b/plugin/package.json
new file mode 100644
index 0000000..c7a31d1
--- /dev/null
+++ b/plugin/package.json
@@ -0,0 +1,36 @@
+{
+  "name": "cie-pseudocode",
+  "displayName": "CIE Pseudocode",
+  "description": "CIE pseudocode highlighting, Tab indentation and bracket checking for .cps files.",
+  "version": "0.1.0",
+  "publisher": "ovfor4",
+  "license": "GPL-3.0-only",
+  "repository": {
+    "type": "git",
+    "url": "https://github.com/ovfor4/cie-pseudocode-compiler.git",
+    "directory": "plugin"
+  },
+  "engines": { "vscode": "^1.85.0" },
+  "categories": ["Programming Languages", "Formatters"],
+  "scripts": {
+    "check": "node --check src/extension.js",
+    "test": "node --test test/*.test.js"
+  },
+  "contributes": {
+    "languages": [{
+      "id": "cie-pseudocode",
+      "aliases": ["CIE Pseudocode", "cie-pseudocode"],
+      "extensions": [".cps"],
+      "configuration": "./language-configuration.json"
+    }],
+    "grammars": [{
+      "language": "cie-pseudocode",
+      "scopeName": "source.cie-pseudocode",
+      "path": "./syntaxes/cie-pseudocode.tmLanguage.json"
+    }]
+  },
+  "devDependencies": {
+    "vscode-oniguruma": "^2.0.1",
+    "vscode-textmate": "^9.3.2"
+  }
+}
diff --git a/plugin/src/extension.js b/plugin/src/extension.js
new file mode 100644
index 0000000..1101ed6
--- /dev/null
+++ b/plugin/src/extension.js
@@ -0,0 +1,6 @@
+'use strict';
+
+// Language registration and TextMate highlighting are declarative.
+function activate() {}
+
+module.exports = { activate };
diff --git a/plugin/syntaxes/cie-pseudocode.tmLanguage.json b/plugin/syntaxes/cie-pseudocode.tmLanguage.json
new file mode 100644
index 0000000..40a67df
--- /dev/null
+++ b/plugin/syntaxes/cie-pseudocode.tmLanguage.json
@@ -0,0 +1,118 @@
+{
+  "name": "CIE Pseudocode",
+  "scopeName": "source.cie-pseudocode",
+  "patterns": [
+    {
+      "include": "#line_comment"
+    },
+    {
+      "include": "#strings"
+    },
+    {
+      "match": "(?<!\\w)(?:IF|THEN|ELSE|ENDIF|WHILE|DO|ENDWHILE|REPEAT|UNTIL|FOR|TO|STEP|NEXT|RETURN|CALL)(?!\\w)",
+      "name": "keyword.control.cie-pseudocode"
+    },
+    {
+      "match": "(?<!\\w)(?:DECLARE|TYPE|ENDTYPE|FUNCTION|ENDFUNCTION|PROCEDURE|ENDPROCEDURE|RETURNS|BYREF|BYVAL|OF)(?!\\w)",
+      "name": "storage.modifier.cie-pseudocode"
+    },
+    {
+      "match": "(?<!\\w)(?:INTEGER|REAL|BOOLEAN|STRING|CHAR|ARRAY)(?!\\w)",
+      "name": "storage.type.cie-pseudocode"
+    },
+    {
+      "match": "(?<!\\w)(?:TRUE|FALSE)(?!\\w)",
+      "name": "constant.language.cie-pseudocode"
+    },
+    {
+      "match": "(?<!\\w)(?:INPUT|OUTPUT|OPENFILE|READFILE|WRITEFILE|CLOSEFILE|READ|WRITE|APPEND)(?!\\w)",
+      "name": "keyword.other.cie-pseudocode"
+    },
+    {
+      "match": "(?<!\\w)(?:LENGTH|MID|RIGHT|LEFT|LCASE|UCASE|ASC|CHR|IS_NUM|NUM_TO_STR|STR_TO_NUM|EOF)(?!\\w)(?=\\s*\\()",
+      "name": "entity.name.function.cie-pseudocode"
+    },
+    {
+      "match": "(?<!\\w)(?:DIV|MOD|AND|OR|NOT)(?!\\w)",
+      "name": "keyword.operator.word.cie-pseudocode"
+    },
+    {
+      "match": "<-|<>|<=|>=|[+*/=&^<>-]",
+      "name": "keyword.operator.cie-pseudocode"
+    },
+    {
+      "match": "(?<!\\w)\\d+(?:\\.\\d*)?(?!\\w)",
+      "name": "constant.numeric.cie-pseudocode"
+    },
+    {
+      "match": "\\b[A-Za-z][A-Za-z0-9_]*(?=\\s*\\()",
+      "name": "entity.name.function.cie-pseudocode"
+    },
+    {
+      "match": "[()]",
+      "name": "punctuation.section.parens.cie-pseudocode"
+    },
+    {
+      "match": "[\\[\\]]",
+      "name": "punctuation.section.brackets.cie-pseudocode"
+    },
+    {
+      "match": ",",
+      "name": "punctuation.separator.delimiter.comma.cie-pseudocode"
+    },
+    {
+      "match": "[:.]",
+      "name": "punctuation.separator.cie-pseudocode"
+    }
+  ],
+  "repository": {
+    "line_comment": {
+      "begin": "(//)",
+      "end": "$",
+      "beginCaptures": {
+        "1": {
+          "name": "punctuation.definition.comment.cie-pseudocode"
+        }
+      },
+      "endCaptures": {},
+      "name": "comment.line.double-slash.cie-pseudocode",
+      "patterns": []
+    },
+    "strings": {
+      "patterns": [
+        {
+          "begin": "\"",
+          "end": "\"|$",
+          "beginCaptures": {
+            "0": {
+              "name": "punctuation.definition.string.begin.cie-pseudocode"
+            }
+          },
+          "endCaptures": {
+            "0": {
+              "name": "punctuation.definition.string.end.cie-pseudocode"
+            }
+          },
+          "name": "string.quoted.double.cie-pseudocode",
+          "patterns": []
+        },
+        {
+          "begin": "'",
+          "end": "'|$",
+          "beginCaptures": {
+            "0": {
+              "name": "punctuation.definition.string.begin.cie-pseudocode"
+            }
+          },
+          "endCaptures": {
+            "0": {
+              "name": "punctuation.definition.string.end.cie-pseudocode"
+            }
+          },
+          "name": "string.quoted.single.cie-pseudocode",
+          "patterns": []
+        }
+      ]
+    }
+  }
+}
diff --git a/plugin/test/highlighting.test.js b/plugin/test/highlighting.test.js
new file mode 100644
index 0000000..df18f6a
--- /dev/null
+++ b/plugin/test/highlighting.test.js
@@ -0,0 +1,61 @@
+'use strict';
+
+const assert = require('node:assert/strict');
+const { test, before } = require('node:test');
+const fs = require('node:fs');
+const path = require('node:path');
+const { Registry } = require('vscode-textmate');
+const { loadWASM, OnigScanner, OnigString } = require('vscode-oniguruma');
+
+let grammar;
+before(async () => {
+	const wasm = fs.readFileSync(require.resolve('vscode-oniguruma/release/onig.wasm'));
+	await loadWASM(wasm.buffer.slice(wasm.byteOffset, wasm.byteOffset + wasm.byteLength));
+	const registry = new Registry({
+		onigLib: Promise.resolve({
+			createOnigScanner: patterns => new OnigScanner(patterns),
+			createOnigString: text => new OnigString(text)
+		}),
+		loadGrammar: async () => JSON.parse(fs.readFileSync(
+			path.join(__dirname, '../syntaxes/cie-pseudocode.tmLanguage.json'), 'utf8'))
+	});
+	grammar = await registry.loadGrammar('source.cie-pseudocode');
+});
+
+function scopesAt(text, word) {
+	const offset = text.indexOf(word);
+	return grammar.tokenizeLine(text).tokens.find(
+		token => token.startIndex <= offset && token.endIndex > offset).scopes;
+}
+
+test('C++ style scopes distinguish keywords, types, literals, operators and builtins', () => {
+	for (const [text, word, scope] of [
+		['IF Ready THEN', 'IF', 'keyword.control'],
+		['DECLARE X : INTEGER', 'DECLARE', 'storage.modifier'],
+		['DECLARE X : INTEGER', 'INTEGER', 'storage.type'],
+		['X <- TRUE', 'TRUE', 'constant.language'],
+		['X <- 12.5', '12.5', 'constant.numeric'],
+		['X <- 2 DIV 1', 'DIV', 'keyword.operator.word'],
+		['X <- 1', '<-', 'keyword.operator'],
+		['OUTPUT "text"', 'text', 'string.quoted.double'],
+		["X <- 'A'", 'A', 'string.quoted.single']
+	]) assert.ok(scopesAt(text, word).some(s => s.startsWith(scope)), text);
+	for (const name of ['LENGTH', 'MID', 'RIGHT', 'LEFT', 'LCASE', 'UCASE',
+		'ASC', 'CHR', 'IS_NUM', 'NUM_TO_STR', 'STR_TO_NUM', 'EOF']) {
+		assert.ok(scopesAt(`${name}(X)`, name).includes('entity.name.function.cie-pseudocode'));
+	}
+});
+
+test('comments, strings, lowercase and keyword prefixes cannot become keywords', () => {
+	assert.ok(scopesAt('// IF [(', 'IF').some(s => s.startsWith('comment.')));
+	assert.ok(scopesAt('OUTPUT "IF // ["', 'IF').some(s => s.startsWith('string.')));
+	for (const text of ['if X then', 'IFValue <- 1', 'CASE OF X', 'CLASS Example']) {
+		assert.ok(!scopesAt(text, text.split(' ')[0]).some(
+			s => /^(keyword|storage)\./.test(s)), text);
+	}
+	// CIE has neither backslash escapes nor multiline string literals.
+	let state = grammar.tokenizeLine('OUTPUT "unfinished').ruleStack;
+	assert.ok(grammar.tokenizeLine('IF X THEN', state).tokens[0].scopes.includes(
+		'keyword.control.cie-pseudocode'));
+	assert.ok(scopesAt('OUTPUT "x\\" + 1', '+').includes('keyword.operator.cie-pseudocode'));
+});