Amend scanner to support astral characters in identifiers when parsing es6+

scripts/regenerate-unicode-identifier-parts.js

@@ -0,0 +1,28 @@
+
+const MAX_UNICODE_CODEPOINT = 0x10FFFF;
+const isStart = c => /[\p{ID_Start}\u{2118}\u{212E}\u{309B}\u{309C}]/u.test(c); // Other_ID_Start explicitly included for back compat - see http://www.unicode.org/reports/tr31/#Introduction
+const isPart = c => /[\p{ID_Continue}\u{00B7}\u{0387}\u{19DA}\u{1369}\u{136A}\u{136B}\u{136C}\u{136D}\u{136E}\u{136F}\u{1370}\u{1371}]/u.test(c) || isStart(c); // Likewise for Other_ID_Continue
+const parts = [];
+let partsActive = false;
+let startsActive = false;
+const starts = [];
+
+for (let i = 0; i < MAX_UNICODE_CODEPOINT; i++) {
+    if (isStart(String.fromCodePoint(i)) !== startsActive) {
+        starts.push(i - +startsActive);
+        startsActive = !startsActive;
+    }
+    if (isPart(String.fromCodePoint(i)) !== partsActive) {
+        parts.push(i - +partsActive);
+        partsActive = !partsActive;
+    }
+}
+
+console.log(`/**
+* Generated by scripts/regenerate-unicode-identifier-parts.js on node ${process.version} with unicode ${process.versions.unicode}
+* based on http://www.unicode.org/reports/tr31/ and https://www.ecma-international.org/ecma-262/6.0/#sec-names-and-keywords
+* unicodeESNextIdentifierStart corresponds to the ID_Start and Other_ID_Start property, and
+* unicodeESNextIdentifierPart corresponds to ID_Continue, Other_ID_Continue, plus ID_Start and Other_ID_Start
+*/`);
+console.log(`const unicodeESNextIdentifierStart = [${starts.join(", ")}];`);
+console.log(`const unicodeESNextIdentifierPart = [${parts.join(", ")}];`);

tests/baselines/reference/extendedUnicodePlaneIdentifiers.js

@@ -0,0 +1,10 @@
+//// [extendedUnicodePlaneIdentifiers.ts]
+const 𝑚 = 4;
+const 𝑀 = 5;
+console.log(𝑀 + 𝑚); // 9
+
+
+//// [extendedUnicodePlaneIdentifiers.js]
+const 𝑚 = 4;
+const 𝑀 = 5;
+console.log(𝑀 + 𝑚); // 9

tests/baselines/reference/extendedUnicodePlaneIdentifiers.symbols

@@ -0,0 +1,14 @@
+=== tests/cases/compiler/extendedUnicodePlaneIdentifiers.ts ===
+const 𝑚 = 4;
+>𝑚 : Symbol(𝑚, Decl(extendedUnicodePlaneIdentifiers.ts, 0, 5))
+
+const 𝑀 = 5;
+>𝑀 : Symbol(𝑀, Decl(extendedUnicodePlaneIdentifiers.ts, 1, 5))
+
+console.log(𝑀 + 𝑚); // 9
+>console.log : Symbol(Console.log, Decl(lib.dom.d.ts, --, --))
+>console : Symbol(console, Decl(lib.dom.d.ts, --, --))
+>log : Symbol(Console.log, Decl(lib.dom.d.ts, --, --))
+>𝑀 : Symbol(𝑀, Decl(extendedUnicodePlaneIdentifiers.ts, 1, 5))
+>𝑚 : Symbol(𝑚, Decl(extendedUnicodePlaneIdentifiers.ts, 0, 5))
+

tests/baselines/reference/extendedUnicodePlaneIdentifiers.types

@@ -0,0 +1,18 @@
+=== tests/cases/compiler/extendedUnicodePlaneIdentifiers.ts ===
+const 𝑚 = 4;
+>𝑚 : 4
+>4 : 4
+
+const 𝑀 = 5;
+>𝑀 : 5
+>5 : 5
+
+console.log(𝑀 + 𝑚); // 9
+>console.log(𝑀 + 𝑚) : void
+>console.log : (message?: any, ...optionalParams: any[]) => void
+>console : Console
+>log : (message?: any, ...optionalParams: any[]) => void
+>𝑀 + 𝑚 : number
+>𝑀 : 5
+>𝑚 : 4
+

tests/cases/compiler/extendedUnicodePlaneIdentifiers.ts

@@ -0,0 +1,4 @@
+// @target: es2018
+const 𝑚 = 4;
+const 𝑀 = 5;
+console.log(𝑀 + 𝑚); // 9