Fix XCObject._EncodeString() for unicode characters.

pylib/gyp/xcodeproj_file.py

 # Copyright (c) 2012 Google Inc. All rights reserved.
 # Use of this source code is governed by a BSD-style license that can be
 # found in the LICENSE file.
 
 """Xcode project file generator.
 
 This module is both an Xcode project file generator and a documentation of the
 Xcode project file format.  Knowledge of the project file format was gained
 based on extensive experience with Xcode, and by making changes to projects in
 Xcode.app and observing the resultant changes in the associated project files.
@@ skipping 151 matching lines @@
 # characters listed with "+", for 1 or more occurrences: if a string is empty,
 # it must not match this pattern, because it needs to be encoded as "".
 _unquoted = re.compile('^[A-Za-z0-9$./_]+$')
 
 # Strings that match this pattern are quoted regardless of what _unquoted says.
 # Oddly, Xcode will quote any string with a run of three or more underscores.
 _quoted = re.compile('___')
 
 # This pattern should match any character that needs to be escaped by
 # XCObject._EncodeString.  See that function.
-_escaped = re.compile('[\\\\"]|[^ -~]')
+_escaped = re.compile('[\\\\"]|[\x00-\x1f]')
 
 
 # Used by SourceTreeAndPathFromPath
 _path_leading_variable = re.compile('^\$\((.*?)\)(/(.*))?$')
 
 def SourceTreeAndPathFromPath(input_path):
   """Given input_path, returns a tuple with sourceTree and path values.
 
   Examples:
     input_path     (source_tree, output_path)
@@ skipping 367 matching lines @@
     #   127 ^? DEL is passed through as-is without escaping
     #  - In PBXFileReference and PBXBuildFile objects:
     #     9 ^I HT  is passed through as-is without escaping
     #    10 ^J NL  is passed through as-is without escaping
     #    13 ^M CR  is passed through as-is without escaping
     #  - In other objects:
     #     9 ^I HT  is encoded as "\t"
     #    10 ^J NL  is encoded as "\n"
     #    13 ^M CR  is encoded as "\n" rendering it indistinguishable from
     #              10 ^J NL
-    # All other nonprintable characters within the ASCII range (0 through 127
-    # inclusive) are encoded as "\U001f" referring to the Unicode code point in
-    # hexadecimal.  For example, character 14 (^N SO) is encoded as "\U000e".
+    # All other characters within the ASCII control character range (0 through
+    # 31 inclusive) are encoded as "\U001f" referring to the Unicode code point
+    # in hexadecimal.  For example, character 14 (^N SO) is encoded as "\U000e".
     # Characters above the ASCII range are passed through to the output encoded
     # as UTF-8 without any escaping.  These mappings are contained in the
     # class' _encode_transforms list.
 
     if _unquoted.search(value) and not _quoted.search(value):
       return value
 
     return '"' + _escaped.sub(self._EncodeTransform, value) + '"'
 
   def _XCPrint(self, file, tabs, line):
@@ skipping 2288 matching lines @@
       self._XCPrint(file, 0, '/* Begin ' + class_name + ' section */\n')
       for object in sorted(objects_by_class[class_name],
                            cmp=lambda x, y: cmp(x.id, y.id)):
         object.Print(file)
       self._XCPrint(file, 0, '/* End ' + class_name + ' section */\n')
 
     if self._should_print_single_line:
       self._XCPrint(file, 0, '}; ')
     else:
       self._XCPrint(file, 1, '};\n')