Fix identifier unicode escape recognition

Fixed #1211
beautifier · Jan 30, 2019 · f6ed35d · f6ed35d
1 parent 3d3bbf2
commit f6ed35d
Show file tree

Hide file tree

Showing 6 changed files with 67 additions and 20 deletions.
diff --git a/js/src/javascript/acorn.js b/js/src/javascript/acorn.js
diff --git a/js/test/generated/beautify-javascript-tests.js b/js/test/generated/beautify-javascript-tests.js
@@ -350,6 +350,14 @@ function run_javascript_tests(test_obj, Urlencoded, js_beautify, html_beautify,
             'var ' + unicode_char(228) + 'x = {\n' +
             '    ' + unicode_char(228) + 'rgerlich: true\n' +
             '};');
+        bt(
+            'var \\u00E4\\u0ca0\\u0cA0\\u0Ca0 = {\n' +
+            '    \\u0ca0rgerlich: true\n' +
+            '};');
+        bt(
+            'var \\u00E4add\\u0025 = {\n' +
+            '    \\u0044rgerlich\\u0ca0: true\n' +
+            '};');
         bt(
             'var' + unicode_char(160) + unicode_char(3232) + '_' + unicode_char(3232) + ' = "hi";',
             //  -- output --

diff --git a/package-lock.json b/package-lock.json
diff --git a/python/jsbeautifier/javascript/acorn.py b/python/jsbeautifier/javascript/acorn.py
@@ -39,24 +39,24 @@
 #_nonASCIIidentifierStart = re.compile("[" + _nonASCIIidentifierStartChars + "]")
 #_nonASCIIidentifier = re.compile("[" + _nonASCIIidentifierStartChars + _nonASCIIidentifierChars + "]")
 
-_identifierStart = six.u("[") + \
+_identifierStart = six.u(r"(?:\\u[0-9a-fA-F]{4}|[") + \
     _baseASCIIidentifierStartChars + \
     _nonASCIIidentifierStartChars + \
-    six.u("]")
-_identifierChars = six.u("[") + \
+    six.u("])")
+_identifierChars = six.u(r"(?:\\u[0-9a-fA-F]{4}|[") + \
     _baseASCIIidentifierChars + \
     _nonASCIIidentifierStartChars + \
     _nonASCIIidentifierChars + \
-    six.u("]*")
+    six.u("])*")
 
 identifier = re.compile(_identifierStart + _identifierChars)
 
 identifierStart = re.compile(_identifierStart)
-identifierMatch = re.compile(six.u("[") + \
+identifierMatch = re.compile(six.u(r"(?:\\u[0-9a-fA-F]{4}|[") + \
     _baseASCIIidentifierChars + \
     _nonASCIIidentifierStartChars + \
     _nonASCIIidentifierChars + \
-    six.u("]+"))
+    six.u("])+"))
 
 _nonASCIIwhitespace = re.compile(
     six.u(r"[\u1680\u180e\u2000-\u200a\u202f\u205f\u3000\ufeff]"))

diff --git a/python/jsbeautifier/tests/generated/tests.py b/python/jsbeautifier/tests/generated/tests.py
@@ -158,6 +158,14 @@ def unicode_char(value):
             'var ' + unicode_char(228) + 'x = {\n' +
             '    ' + unicode_char(228) + 'rgerlich: true\n' +
             '};')
+        bt(
+            'var \\u00E4\\u0ca0\\u0cA0\\u0Ca0 = {\n' +
+            '    \\u0ca0rgerlich: true\n' +
+            '};')
+        bt(
+            'var \\u00E4add\\u0025 = {\n' +
+            '    \\u0044rgerlich\\u0ca0: true\n' +
+            '};')
         bt(
             'var' + unicode_char(160) + unicode_char(3232) + '_' + unicode_char(3232) + ' = "hi";',
             #  -- output --

diff --git a/test/data/javascript/tests.js b/test/data/javascript/tests.js
@@ -44,6 +44,18 @@ exports.test_data = {
           "    ' + unicode_char(228) + 'rgerlich: true",
           "};"
         ]
+      }, {
+        unchanged: [
+          "var \\\\u00E4\\\\u0ca0\\\\u0cA0\\\\u0Ca0 = {",
+          "    \\\\u0ca0rgerlich: true",
+          "};"
+        ]
+      }, {
+        unchanged: [
+          "var \\\\u00E4add\\\\u0025 = {",
+          "    \\\\u0044rgerlich\\\\u0ca0: true",
+          "};"
+        ]
       }, {
         input_: "var' + unicode_char(160) + unicode_char(3232) + '_' + unicode_char(3232) + ' = \"hi\";",
         output: "var ' + unicode_char(3232) + '_' + unicode_char(3232) + ' = \"hi\";"