Directives in python

js/src/core/directives.js

@@ -28,10 +28,12 @@
 
 
 function Directives(start_block_pattern, end_block_pattern) {
-  var directives_block_pattern = new RegExp(start_block_pattern.source + / beautify( \w+[:]\w+)+ /.source + end_block_pattern.source, 'g');
+  start_block_pattern = typeof start_block_pattern === 'string' ? start_block_pattern : start_block_pattern.source;
+  end_block_pattern = typeof end_block_pattern === 'string' ? end_block_pattern : end_block_pattern.source;
+  var directives_block_pattern = new RegExp(start_block_pattern + / beautify( \w+[:]\w+)+ /.source + end_block_pattern, 'g');
   var directive_pattern = / (\w+)[:](\w+)/g;
 
-  var directives_end_ignore_pattern = new RegExp('(?:[\\s\\S]*?)((?:' + start_block_pattern.source + '\\sbeautify\\signore:end\\s' + end_block_pattern.source + ')|$)', 'g');
+  var directives_end_ignore_pattern = new RegExp('(?:[\\s\\S]*?)((?:' + start_block_pattern + /\sbeautify\signore:end\s/.source + end_block_pattern + ')|$)', 'g');
 
   this.get_directives = function(text) {
     if (!text.match(directives_block_pattern)) {

python/jsbeautifier/core/directives.py

@@ -0,0 +1,53 @@
+# The MIT License (MIT)
+#
+# Copyright (c) 2007-2018 Einar Lielmanis, Liam Newman, and contributors.
+#
+# Permission is hereby granted, free of charge, to any person
+# obtaining a copy of this software and associated documentation files
+# (the "Software"), to deal in the Software without restriction,
+# including without limitation the rights to use, copy, modify, merge,
+# publish, distribute, sublicense, and/or sell copies of the Software,
+# and to permit persons to whom the Software is furnished to do so,
+# subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be
+# included in all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+# BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+# ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+# SOFTWARE.
+
+import re
+
+
+class Directives:
+
+    def __init__(self, start_block_pattern, end_block_pattern):
+
+        self.__directives_block_pattern = re.compile(start_block_pattern + r' beautify( \w+[:]\w+)+ ' + end_block_pattern)
+        self.__directive_pattern = re.compile(r' (\w+)[:](\w+)')
+
+        self.__directives_end_ignore_pattern = re.compile(r'(?:[\s\S]*?)((?:' + start_block_pattern + r'\sbeautify\signore:end\s' + end_block_pattern + r')|$)')
+
+    def get_directives(self, text):
+        if not self.__directives_block_pattern.match(text):
+            return None
+
+        directives = {}
+        directive_match = self.__directive_pattern.search(text)
+
+        while directive_match:
+            directives[directive_match.group(1)] = directive_match.group(2)
+            directive_match = self.__directive_pattern.search(
+                text, directive_match.end())
+
+
+        return directives
+
+    def readIgnored(self, input):
+        return input.readWhile(self.__directives_end_ignore_pattern)

python/jsbeautifier/javascript/tokenizer.py

@@ -25,6 +25,7 @@
 import re
 from ..core.inputscanner import InputScanner
 from ..core.token import Token
+from ..core.directives import Directives
 
 
 class TokenTypes:
@@ -103,11 +104,7 @@ class Tokenizer:
         self.comment_pattern = re.compile(
             self.acorn.six.u(r'([^\n\r\u2028\u2029]*)'))
 
-        self.directives_block_pattern = re.compile(
-            r'\/\* beautify( \w+[:]\w+)+ \*\/')
-        self.directive_pattern = re.compile(r' (\w+)[:](\w+)')
-        self.directives_end_ignore_pattern = re.compile(
-            r'([\s\S]*?)((?:\/\*\sbeautify\signore:end\s\*\/)|$)')
+        self.directives_core = Directives(r'/\*', r'\*/')
 
         self.template_pattern = re.compile(
             r'((<\?php|<\?=)[\s\S]*?\?>)|(<%[\s\S]*?%>)')
@@ -168,19 +165,6 @@ class Tokenizer:
             last = next
         return self.tokens
 
-    def get_directives(self, text):
-        if not self.directives_block_pattern.match(text):
-            return None
-
-        directives = {}
-        directive_match = self.directive_pattern.search(text)
-        while directive_match:
-            directives[directive_match.group(1)] = directive_match.group(2)
-            directive_match = self.directive_pattern.search(
-                text, directive_match.end())
-
-        return directives
-
     def __tokenize_next(self):
 
         self.n_newlines = 0
@@ -249,11 +233,9 @@ class Tokenizer:
                 comment_match = self.input.match(self.block_comment_pattern)
                 comment = '/*' + comment_match.group(0)
 
-                directives = self.get_directives(comment)
+                directives = self.directives_core.get_directives(comment)
                 if directives and directives.get('ignore') == 'start':
-                    comment_match = self.input.match(
-                        self.directives_end_ignore_pattern)
-                    comment += comment_match.group(0)
+                    comment += self.directives_core.readIgnored(self.input)
                 comment = re.sub(self.acorn.allLineBreaks, '\n', comment)
                 return comment, TOKEN.BLOCK_COMMENT, directives