perf: minimize identifier lookahead when parsing let (#13328)

packages/babel-parser/benchmark/many-let-declarations/10-length-binding.mjs

@@ -0,0 +1,22 @@
+import Benchmark from "benchmark";
+import baseline from "@babel-baseline/parser";
+import current from "../../lib/index.js";
+import { report } from "../util.mjs";
+
+const suite = new Benchmark.Suite();
+function createInput(length) {
+  return "{ let foecnatsni };".repeat(length);
+}
+function benchCases(name, implementation, options) {
+  for (const length of [64, 128, 256, 512]) {
+    const input = createInput(length);
+    suite.add(`${name} ${length} let and length-10 binding identifiers`, () => {
+      implementation.parse(input, options);
+    });
+  }
+}
+
+benchCases("baseline", baseline);
+benchCases("current", current);
+
+suite.on("cycle", report).run();

packages/babel-parser/src/parser/statement.js

@@ -4,11 +4,7 @@ import * as N from "../types";
 import { types as tt, type TokenType } from "../tokenizer/types";
 import ExpressionParser from "./expression";
 import { Errors, SourceTypeModuleErrors } from "./error";
-import {
-  isIdentifierChar,
-  isIdentifierStart,
-  keywordRelationalOperator,
-} from "../util/identifier";
+import { isIdentifierChar, isIdentifierStart } from "../util/identifier";
 import { lineBreak } from "../util/whitespace";
 import * as charCodes from "charcodes";
 import {
@@ -49,6 +45,8 @@ const FUNC_NO_FLAGS = 0b000,
 
 const loneSurrogate = /[\uD800-\uDFFF]/u;
 
+const keywordRelationalOperator = /in(?:stanceof)?/y;
+
 /**
  * Convert tt.privateName to tt.hash + tt.name for backward Babel 7 compat.
  * For performance reasons this routine mutates `tokens`, it is okay
@@ -183,7 +181,7 @@ export default class StatementParser extends ExpressionParser {
    */
   isLetKeyword(context: ?string): boolean {
     const next = this.nextTokenStart();
-    const nextCh = this.input.charCodeAt(next);
+    const nextCh = this.codePointAtPos(next);
     // For ambiguous cases, determine if a LexicalDeclaration (or only a
     // Statement) is allowed here. If context is not empty then only a Statement
     // is allowed. However, `let [` is an explicit negative lookahead for
@@ -200,12 +198,17 @@ export default class StatementParser extends ExpressionParser {
     if (nextCh === charCodes.leftCurlyBrace) return true;
 
     if (isIdentifierStart(nextCh)) {
-      let pos = next + 1;
-      while (isIdentifierChar(this.input.charCodeAt(pos))) {
-        ++pos;
+      keywordRelationalOperator.lastIndex = next;
+      const matched = keywordRelationalOperator.exec(this.input);
+      if (matched !== null) {
+        // We have seen `in` or `instanceof` so far, now check if the identfier
+        // ends here
+        const endCh = this.codePointAtPos(next + matched[0].length);
+        if (!isIdentifierChar(endCh) && endCh !== charCodes.backslash) {
+          return false;
+        }
       }
-      const ident = this.input.slice(next, pos);
-      if (!keywordRelationalOperator.test(ident)) return true;
+      return true;
     }
     return false;
   }

packages/babel-parser/test/fixtures/es2015/let/let-declaration-in-escape-id/input.js

@@ -0,0 +1 @@
+let in\u0061;

packages/babel-parser/test/fixtures/es2015/let/let-declaration-in-escape-id/output.json

@@ -0,0 +1,30 @@
+{
+  "type": "File",
+  "start":0,"end":13,"loc":{"start":{"line":1,"column":0},"end":{"line":1,"column":13}},
+  "program": {
+    "type": "Program",
+    "start":0,"end":13,"loc":{"start":{"line":1,"column":0},"end":{"line":1,"column":13}},
+    "sourceType": "script",
+    "interpreter": null,
+    "body": [
+      {
+        "type": "VariableDeclaration",
+        "start":0,"end":13,"loc":{"start":{"line":1,"column":0},"end":{"line":1,"column":13}},
+        "declarations": [
+          {
+            "type": "VariableDeclarator",
+            "start":4,"end":12,"loc":{"start":{"line":1,"column":4},"end":{"line":1,"column":12}},
+            "id": {
+              "type": "Identifier",
+              "start":4,"end":12,"loc":{"start":{"line":1,"column":4},"end":{"line":1,"column":12},"identifierName":"ina"},
+              "name": "ina"
+            },
+            "init": null
+          }
+        ],
+        "kind": "let"
+      }
+    ],
+    "directives": []
+  }
+}

packages/babel-parser/test/fixtures/es2015/let/let-declaration-in-non-BMP/input.js

@@ -0,0 +1 @@
+let in𝐬𝐭𝐚𝐧𝐜𝐞𝐨𝐟;

packages/babel-parser/test/fixtures/es2015/let/let-declaration-in-non-BMP/output.json

@@ -0,0 +1,30 @@
+{
+  "type": "File",
+  "start":0,"end":23,"loc":{"start":{"line":1,"column":0},"end":{"line":1,"column":23}},
+  "program": {
+    "type": "Program",
+    "start":0,"end":23,"loc":{"start":{"line":1,"column":0},"end":{"line":1,"column":23}},
+    "sourceType": "script",
+    "interpreter": null,
+    "body": [
+      {
+        "type": "VariableDeclaration",
+        "start":0,"end":23,"loc":{"start":{"line":1,"column":0},"end":{"line":1,"column":23}},
+        "declarations": [
+          {
+            "type": "VariableDeclarator",
+            "start":4,"end":22,"loc":{"start":{"line":1,"column":4},"end":{"line":1,"column":22}},
+            "id": {
+              "type": "Identifier",
+              "start":4,"end":22,"loc":{"start":{"line":1,"column":4},"end":{"line":1,"column":22},"identifierName":"in𝐬𝐭𝐚𝐧𝐜𝐞𝐨𝐟"},
+              "name": "in𝐬𝐭𝐚𝐧𝐜𝐞𝐨𝐟"
+            },
+            "init": null
+          }
+        ],
+        "kind": "let"
+      }
+    ],
+    "directives": []
+  }
+}

packages/babel-parser/test/fixtures/es2015/let/let-declaration-non-BMP-identifier/input.js

@@ -0,0 +1 @@
+let 𝐢𝐧;

packages/babel-parser/test/fixtures/es2015/let/let-declaration-non-BMP-identifier/output.json

@@ -0,0 +1,30 @@
+{
+  "type": "File",
+  "start":0,"end":9,"loc":{"start":{"line":1,"column":0},"end":{"line":1,"column":9}},
+  "program": {
+    "type": "Program",
+    "start":0,"end":9,"loc":{"start":{"line":1,"column":0},"end":{"line":1,"column":9}},
+    "sourceType": "script",
+    "interpreter": null,
+    "body": [
+      {
+        "type": "VariableDeclaration",
+        "start":0,"end":9,"loc":{"start":{"line":1,"column":0},"end":{"line":1,"column":9}},
+        "declarations": [
+          {
+            "type": "VariableDeclarator",
+            "start":4,"end":8,"loc":{"start":{"line":1,"column":4},"end":{"line":1,"column":8}},
+            "id": {
+              "type": "Identifier",
+              "start":4,"end":8,"loc":{"start":{"line":1,"column":4},"end":{"line":1,"column":8},"identifierName":"𝐢𝐧"},
+              "name": "𝐢𝐧"
+            },
+            "init": null
+          }
+        ],
+        "kind": "let"
+      }
+    ],
+    "directives": []
+  }
+}