Experimental lexer generator: generate code for utf-16 character classes.

src/lexer/lexer_py.re

 # Copyright 2013 the V8 project authors. All rights reserved.
 # Redistribution and use in source and binary forms, with or without
 # modification, are permitted provided that the following conditions are
 # met:
 #
 #     * Redistributions of source code must retain the above copyright
 #       notice, this list of conditions and the following disclaimer.
 #     * Redistributions in binary form must reproduce the above
 #       copyright notice, this list of conditions and the following
 #       disclaimer in the documentation and/or other materials provided
 #       with the distribution.
 #     * Neither the name of Google Inc. nor the names of its
 #       contributors may be used to endorse or promote products derived
 #       from this software without specific prior written permission.
 #
 # THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
 # "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
 # LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
 # A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
 # OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
 # SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
 # LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
 # DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
 # THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
 # (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
 # OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 
-whitespace_char = [ \t\v\f\r:ws:\240];
+whitespace_char = [ \t\v\f\r:whitespace:\240];
 whitespace = whitespace_char+;
-identifier_start = [$_a-zA-Z:lit:];
-identifier_char = [0-9:identifier_start:];
+identifier_start = [$_a-zA-Z:letter:];
+identifier_char = [0-9:identifier_part_not_letter::identifier_start:];
 line_terminator = [\n\r];
 digit = [0-9];
 hex_digit = [0-9a-fA-F];
 single_escape_char = ['"\\bfnrtv];
 maybe_exponent = /([eE][\-+]?[:digit:]+)?/;
 number =
   /0[xX][:hex_digit:]+/ | (
   /\.[:digit:]+/ maybe_exponent |
   /[:digit:]+(\.[:digit:]*)?/ maybe_exponent );
 # TODO this is incomplete/incorrect
@@ skipping 188 matching lines @@
 eos <|skip_and_terminate|>
 catch_all <||continue>
 
 <<MultiLineComment>>
 /\*+\//             <|skip|>
 # TODO find a way to generate the below rule
 /\*+[^\/*]/       <||continue>
 line_terminator  <push_line_terminator||continue>
 eos <|terminate_illegal|>
 catch_all        <||continue>