Experimental parser: better eos handling

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
@@ skipping 33 matching lines @@
 non_octal_whole_part = "0" | (
   /0[:digit:]*[8-9][:digit:]*/ |
   /[1-9][:digit:]*/ );
 
 number =
   /0[xX][:hex_digit:]+/ | (
   /\.[:digit:]+/ maybe_exponent |
   non_octal_whole_part /(\.[:digit:]*)?/ maybe_exponent );
 harmony_number = "0"[bBoO][:digit:]+;
 line_terminator_sequence = /[:line_terminator:]|(\r\n|\n\r)/;
-eos = [:eos:];
 
 # Rules.
 
 # Grammar is
 #   regex <entry_action|match_action|transition>
 #
 # Actions are identifiers to be passed to codegen.
 #
 # Entry action is executed when we enter the corresponding automaton state, that
 # is, right after seeing something that matches the regex. Match action is
@@ skipping 125 matching lines @@
 "typeof"      <|token(TYPEOF)|>
 "var"         <|token(VAR)|>
 "void"        <|token(VOID)|>
 "while"       <|token(WHILE)|>
 "with"        <|token(WITH)|>
 "yield"       <|token(YIELD)|>
 
 identifier_start <|token(IDENTIFIER)|Identifier>
 /\\u[:hex_digit:]{4}/ <check_escaped_identifier_start|token(IDENTIFIER)|Identifier>
 
-eos             <|terminate|>
+eos             <terminate>
 default_action  <do_token_and_go_forward(ILLEGAL)>
 
 <<DoubleQuoteString>>
 "\\" line_terminator_sequence <set_has_escapes||continue>
 /\\[x][:hex_digit:]{2}/       <set_has_escapes||continue>
 /\\[u][:hex_digit:]{4}/       <set_has_escapes||continue>
 /\\[1-7]/                     <octal_inside_string||continue>
 /\\[0-7][0-7]+/               <octal_inside_string||continue>
 "\\0"                         <set_has_escapes||continue>
 /\\[^xu0-7:line_terminator:]/ <set_has_escapes||continue>
 "\\"                          <|token(ILLEGAL)|>
 line_terminator               <|token(ILLEGAL)|>
 "\""                          <|token(STRING)|>
-eos                           <|terminate_illegal|>
 catch_all                     <||continue>
+eos                           <terminate_illegal>
 
 <<SingleQuoteString>>
 # TODO subgraph for '\'
 "\\" line_terminator_sequence <set_has_escapes||continue>
 /\\[x][:hex_digit:]{2}/       <set_has_escapes||continue>
 /\\[u][:hex_digit:]{4}/       <set_has_escapes||continue>
 /\\[1-7]/                     <octal_inside_string||continue>
 /\\[0-7][0-7]+/               <octal_inside_string||continue>
 "\\0"                         <set_has_escapes||continue>
 /\\[^xu0-7:line_terminator:]/ <set_has_escapes||continue>
 "\\"                          <|token(ILLEGAL)|>
 line_terminator               <|token(ILLEGAL)|>
 "'"                           <|token(STRING)|>
-eos                           <|terminate_illegal|>
 catch_all                     <||continue>
+eos                           <terminate_illegal>
 
 <<Identifier>>
 identifier_char <|token(IDENTIFIER)|continue>
 /\\u[:hex_digit:]{4}/ <check_escaped_identifier_part|token(IDENTIFIER)|continue>
 
 <<SingleLineComment>>
 line_terminator  <|line_terminator|>
-eos              <|skip_and_terminate|>
+eos              <skip_and_terminate>
 catch_all        <||continue>
 
 <<MultiLineComment>>
 /\*+\//          <|skip|>
 # TODO find a way to generate the below rule
 /\*+[^\/*]/      <||continue>
 line_terminator  <line_terminator_in_multiline_comment||continue>
-eos              <|terminate_illegal|>
 catch_all        <||continue>
+eos              <terminate_illegal>