Experimental scanner: keeping track of octal numbers octal escapes.

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 14 matching lines @@
 # (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
 # OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 
 line_terminator = [:line_terminator:];
 identifier_start = [$_:letter:];
 identifier_char = [:identifier_start::identifier_part_not_letter:];
 digit = [0-9];
 hex_digit = [0-9a-fA-F];
 single_escape_char = ['"\\bfnrtv];
 maybe_exponent = /([eE][\-+]?[:digit:]+)?/;
+octal_number = /0[0-7]+/;
 number =
   /0[xX][:hex_digit:]+/ | (
   /\.[:digit:]+/ maybe_exponent |
   /[:digit:]+(\.[:digit:]*)?/ maybe_exponent );
 harmony_number = "0"[bBoO][:digit:]+;
 line_terminator_sequence = /[:line_terminator:]|\r\n/;
 eos = [:eos:];
 
 # grammar is
 #   regex <action_on_state_entry|action_on_match|transition>
@@ skipping 44 matching lines @@
 ">>>"         <|token(SHR)|>
 "<<="         <|token(ASSIGN_SHL)|>
 ">>="         <|token(ASSIGN_SAR)|>
 "<="          <|token(LTE)|>
 ">="          <|token(GTE)|>
 "<<"          <|token(SHL)|>
 ">>"          <|token(SAR)|>
 "<"           <|token(LT)|>
 ">"           <|token(GT)|>
 
+octal_number            <|octal_number|>
 number                  <|token(NUMBER)|>
 number identifier_char  <|token(ILLEGAL)|>
 number "\\"             <|token(ILLEGAL)|>
 
 harmony_number                  <|harmony_token(numeric_literals, NUMBER, ILLEGAL)|>
 harmony_number identifier_char  <|token(ILLEGAL)|>
 harmony_number "\\"             <|token(ILLEGAL)|>
 
 "("           <|token(LPAREN)|>
 ")"           <|token(RPAREN)|>
@@ skipping 83 matching lines @@
   next_.has_escapes = true;
 }|token(IDENTIFIER)|Identifier>
 
 eos             <|terminate|>
 default_action  <do_token_and_go_forward(ILLEGAL)>
 
 <<DoubleQuoteString>>
 "\\" line_terminator_sequence <||continue>
 /\\[x][:hex_digit:]{2}/       <set_has_escapes||continue>
 /\\[u][:hex_digit:]{4}/       <set_has_escapes||continue>
-/\\[^xu:line_terminator:]/    <set_has_escapes||continue>
+/\\[1-7]/                     <octal_inside_string||continue>
+/\\[0-7]{2,3}/                <octal_inside_string||continue>
+/\\[^xu1-7:line_terminator:]/ <set_has_escapes||continue>
 "\\"                          <|token(ILLEGAL)|>
 line_terminator               <|token(ILLEGAL)|>
 "\""                          <|token(STRING)|>
 eos                           <|terminate_illegal|>
 catch_all                     <||continue>
 
 <<SingleQuoteString>>
 # TODO subgraph for '\'
 "\\" line_terminator_sequence <||continue>
 /\\[x][:hex_digit:]{2}/       <set_has_escapes||continue>
 /\\[u][:hex_digit:]{4}/       <set_has_escapes||continue>
-/\\[^xu:line_terminator:]/    <set_has_escapes||continue>
+/\\[1-7]/                     <octal_inside_string||continue>
+/\\[0-7]{2,3}/                <octal_inside_string||continue>
+/\\[^xu1-7:line_terminator:]/ <set_has_escapes||continue>
 "\\"                          <|token(ILLEGAL)|>
 line_terminator               <|token(ILLEGAL)|>
 "'"                           <|token(STRING)|>
 eos                           <|terminate_illegal|>
 catch_all                     <||continue>
 
 <<Identifier>>
 identifier_char <|token(IDENTIFIER)|continue>
 /\\u[:hex_digit:]{4}/ <{
   if (V8_UNLIKELY(!ValidIdentifierPart())) {
     goto default_action;
   }
   next_.has_escapes = true;
 }|token(IDENTIFIER)|continue>
 
 <<SingleLineComment>>
 line_terminator  <|line_terminator|>
 eos              <|skip_and_terminate|>
 catch_all        <||continue>
 
 <<MultiLineComment>>
 /\*+\//          <|skip|>
 # TODO find a way to generate the below rule
 /\*+[^\/*]/      <||continue>
 line_terminator  <line_terminator||continue>
 eos              <|terminate_illegal|>
 catch_all        <||continue>