%option nounput noyywrap %{ /* Copyright (C) 1991-2023 Free Software Foundation, Inc. Written by Steve Chamberlain of Cygnus Support. This file is part of the GNU Binutils. This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation; either version 3 of the License, or (at your option) any later version. This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. You should have received a copy of the GNU General Public License along with this program; if not, write to the Free Software Foundation, Inc., 51 Franklin Street - Fifth Floor, Boston, MA 02110-1301, USA. */ #include "bfd.h" #include "safe-ctype.h" #include "bfdlink.h" #include "ctf-api.h" #include "ld.h" #include "ldmisc.h" #include "ldexp.h" #include "ldlang.h" #include #include "ldfile.h" #include "ldlex.h" #include "ldmain.h" #include "libiberty.h" /* The type of top-level parser input. yylex and yyparse (indirectly) both check this. */ input_type parser_input; /* Line number in the current input file. */ unsigned int lineno; /* The string we are currently lexing, or NULL if we are reading a file. */ const char *lex_string = NULL; /* Support for flex reading from more than one input file (stream). `include_stack' is flex's input state for each open file; `file_name_stack' is the file names. `lineno_stack' is the current line numbers. If `include_stack_ptr' is 0, we haven't started reading anything yet. Otherwise, stack elements 0 through `include_stack_ptr - 1' are valid. */ #undef YY_INPUT #define YY_INPUT(buf,result,max_size) result = yy_input (buf, max_size) #ifndef YY_NO_UNPUT #define YY_NO_UNPUT #endif #define MAX_INCLUDE_DEPTH 10 static YY_BUFFER_STATE include_stack[MAX_INCLUDE_DEPTH]; static const char *file_name_stack[MAX_INCLUDE_DEPTH]; static unsigned int lineno_stack[MAX_INCLUDE_DEPTH]; static unsigned int sysrooted_stack[MAX_INCLUDE_DEPTH]; static unsigned int include_stack_ptr = 0; static int vers_node_nesting = 0; static int yy_input (char *, int); static void comment (void); static void lex_warn_invalid (char *where, char *what); /* STATES EXPRESSION in an expression SCRIPT in a script INPUTLIST in a script, a filename-list MRI in an MRI script WILD inside the braces of an output section or overlay, for input section wildcards VERS_START starting a Sun style mapfile VERS_SCRIPT a Sun style mapfile VERS_NODE a node within a Sun style mapfile */ #define RTOKEN(x) { yylval.token = x; return x; } %} %a 4000 %o 5000 WILDCHAR [_a-zA-Z0-9\/\.\\\$\~\-\+\:\[\]\,\=\?\*\^\!] FILENAMECHAR [_a-zA-Z0-9\/\.\\\$\~\-\+\:\[\]\,\=] NOCFILENAMECHAR [_a-zA-Z0-9\/\.\\\$\~\-\+\:\[\]] SYMBOLNAMECHAR [_a-zA-Z0-9\/\.\\\$\~] FILENAMECHAR1 [_a-zA-Z\/\.\\\$\~] SYMBOLNAMECHAR1 [_a-zA-Z\.\\\$] WHITE [ \t\n\r]+ V_TAG [.$_a-zA-Z][._a-zA-Z0-9]* V_IDENTIFIER [*?.$_a-zA-Z\[\]\-\!\^\\]([*?.$_a-zA-Z0-9\[\]\-\!\^\\]|::)* %s SCRIPT %s INPUTLIST %s EXPRESSION %s MRI %s WILD %s VERS_START %s VERS_SCRIPT %s VERS_NODE %% if (parser_input != input_selected) { /* The first token of the input determines the initial parser state. */ input_type t = parser_input; parser_input = input_selected; switch (t) { case input_script: return INPUT_SCRIPT; break; case input_mri_script: return INPUT_MRI_SCRIPT; break; case input_version_script: return INPUT_VERSION_SCRIPT; break; case input_dynamic_list: return INPUT_DYNAMIC_LIST; break; case input_defsym: return INPUT_DEFSYM; break; default: abort (); } } "/*" { comment (); } "$"([0-9A-Fa-f])+ { yylval.integer = bfd_scan_vma (yytext + 1, 0, 16); yylval.bigint.str = NULL; return INT; } ([0-9A-Fa-f])+(H|h|X|x|B|b|O|o|D|d) { int ibase ; switch (yytext[yyleng - 1]) { case 'X': case 'x': case 'H': case 'h': ibase = 16; break; case 'O': case 'o': ibase = 8; break; case 'B': case 'b': ibase = 2; break; default: ibase = 10; } yylval.integer = bfd_scan_vma (yytext, 0, ibase); yylval.bigint.str = NULL; return INT; } ((("$"|0[xX])([0-9A-Fa-f])+)|(([0-9])+))(M|K|m|k)? { char *s = yytext; int ibase = 0; if (*s == '$') { ++s; ibase = 16; } yylval.integer = bfd_scan_vma (s, 0, ibase); yylval.bigint.str = NULL; if (yytext[yyleng - 1] == 'M' || yytext[yyleng - 1] == 'm') { yylval.integer *= 1024 * 1024; } else if (yytext[yyleng - 1] == 'K' || yytext[yyleng - 1]=='k') { yylval.integer *= 1024; } else if (yytext[0] == '0' && (yytext[1] == 'x' || yytext[1] == 'X')) { yylval.bigint.str = xstrdup (yytext + 2); } return INT; } /* Some tokens that only appear in expressions must be enabled for states other than EXPRESSION, since parser lookahead means they must be recognised before the parser switches the lexer out of SCRIPT or WILD state into EXPRESSION state. This sort of thing happens for example with NAME in ldgram.y "section" rule, which is immediately followed by ldlex_expression. However, if you follow the grammar from "sec_or_group_p1" you see "assignment" appearing in "statement_anywhere". Now, "assignment" also has NAME as its first token, just like "section". So the parser can't know whether it is in the "section" or the "assignment" rule until it has scanned the next token to find an assignment operator. Thus the next token after NAME in the "section" rule may be lexed before the lexer is switched to EXPRESSION state, and there are quite a number of optional components. The first token in all those components must be able to be lexed in SCRIPT state, as well as the assignment operators. In fact, due to "opt_exp_with_type", anything that can appear on the left hand side of "exp" might need to be lexed in SCRIPT state. MRI mode tends to cover everything in MRI scripts. */ "]" { RTOKEN(']'); } "[" { RTOKEN('['); } "<<=" { RTOKEN(LSHIFTEQ); } ">>=" { RTOKEN(RSHIFTEQ); } "||" { RTOKEN(OROR); } "==" { RTOKEN(EQ); } "!=" { RTOKEN(NE); } ">=" { RTOKEN(GE); } "<=" { RTOKEN(LE); } "<<" { RTOKEN(LSHIFT); } ">>" { RTOKEN(RSHIFT); } "+=" { RTOKEN(PLUSEQ); } "-=" { RTOKEN(MINUSEQ); } "*=" { RTOKEN(MULTEQ); } "/=" { RTOKEN(DIVEQ); } "&=" { RTOKEN(ANDEQ); } "|=" { RTOKEN(OREQ); } "&&" { RTOKEN(ANDAND); } ">" { RTOKEN('>'); } "," { RTOKEN(','); } "&" { RTOKEN('&'); } "|" { RTOKEN('|'); } "~" { RTOKEN('~'); } "!" { RTOKEN('!'); } "?" { RTOKEN('?'); } "*" { RTOKEN('*'); } "+" { RTOKEN('+'); } "-" { RTOKEN('-'); } "/" { RTOKEN('/'); } "%" { RTOKEN('%'); } "<" { RTOKEN('<'); } "=" { RTOKEN('='); } "}" { RTOKEN('}'); } "{" { RTOKEN('{'); } ")" { RTOKEN(')'); } "(" { RTOKEN('('); } ":" { RTOKEN(':'); } ";" { RTOKEN(';'); }