add support for unicode regexes - closes #11

babel · Oct 9, 2014 · 21f039e · mathiasbynens · Oct 9, 2014 · sebmck
1 parent 66b3475
commit 21f039e
Show file tree

Hide file tree

Showing 6 changed files with 25 additions and 2 deletions.
diff --git a/README.md b/README.md
@@ -60,6 +60,7 @@ It's as easy as:
  - [Rest parameters](FEATURES.md#rest-parameters)
  - [Spread](FEATURES.md#spread)
  - [Template literals](FEATURES.md#template-literals)
+ - [Unicode Regex](FEATURES.md#unicode-regex)
 
 To be implemented:
 
@@ -243,6 +244,7 @@ limitations in ES5 implementations.
 | Rest parameters              | ✓    | ✓       | ✓      | ✓      | ✓              | ✓           |
 | Spread                       | ✓    | ✓       | ✓      | ✓      | ✓              |             |
 | Template literals            | ✓    | ✓       | ✓      | ✓      | ✓              | ✓           |
+| Unicode regex                | ✓    | ✓       |        | ✓      | ✓              |             |
 
 #### Performance
 

diff --git a/lib/6to5/transform.js b/lib/6to5/transform.js
@@ -107,5 +107,6 @@ transform.transformers = {
   blockBinding:             require("./transformers/block-binding"),
   modules:                  require("./transformers/modules"),
   restParameters:           require("./transformers/rest-parameters"),
-  forOf:                    require("./transformers/for-of")
+  forOf:                    require("./transformers/for-of"),
+  unicodeRegex:             require("./transformers/unicode-regex")
 };
diff --git a/lib/6to5/transformers/unicode-regex.js b/lib/6to5/transformers/unicode-regex.js
@@ -0,0 +1,15 @@
+var regexpu = require("regexpu");
+var b       = require("ast-types").builders;
+var _       = require("lodash");
+
+exports.Literal = function (node) {
+  var regex = node.regex;
+  if (!regex) return;
+
+  var flags = regex.flags.split("")
+  if (!_.contains(regex.flags, "u")) return;
+  _.pull(flags, "u");
+
+  var pattern = regexpu.rewritePattern(regex.pattern, regex.flags);
+  return b.literal(new RegExp(pattern, flags.join("")));
+};
diff --git a/package.json b/package.json
@@ -46,7 +46,8 @@
     "lodash": "2.4.1",
     "mkdirp": "0.5.0",
     "es6-shim": "^0.18.0",
-    "es6-symbol": "^0.1.1"
+    "es6-symbol": "^0.1.1",
+    "regexpu": "^0.2.2"
   },
   "devDependencies": {
     "es6-transpiler": "0.7.17",

diff --git a/test/fixtures/unicode-regex/basic/actual.js b/test/fixtures/unicode-regex/basic/actual.js
@@ -0,0 +1,2 @@
+var string = 'foo💩bar';
+var match = string.match(/foo(.)bar/u);
diff --git a/test/fixtures/unicode-regex/basic/expected.js b/test/fixtures/unicode-regex/basic/expected.js
@@ -0,0 +1,2 @@
+var string = 'foo\uD83D\uDCA9bar';
+var match = string.match(/foo((?:[\0-\t\x0B\f\x0E-\u2027\u202A-\uD7FF\uDC00-\uFFFF]|[\uD800-\uDBFF][\uDC00-\uDFFF]|[\uD800-\uDBFF]))bar/);