+%option nounput noyywrap
+
%{
-/* Copyright (C) 1991 Free Software Foundation, Inc.
-This file is part of GLD, the Gnu Linker.
+/* Copyright (C) 1991-2020 Free Software Foundation, Inc.
+ Written by Steve Chamberlain of Cygnus Support.
+
+ This file is part of the GNU Binutils.
-GLD 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 1, or (at your option)
-any later version.
+ 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.
-GLD 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.
+ 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 GLD; see the file COPYING. If not, write to
-the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA. */
+ 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. */
-/*
- * $Id$
+#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 <ldgram.h>
+#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 definitely in an expression
+ SCRIPT definitely in a script
+ INPUTLIST definitely in a script, a filename-list
+ BOTH either EXPRESSION or SCRIPT
+ DEFSYMEXP in an argument to -defsym
+ MRI in an MRI script
+ 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
-/*SUPPRESS 529*/
-/*SUPPRESS 26*/
-/*SUPPRESS 29*/
-#define LEXDEBUG 0
-#include "sysdep.h"
-#include "bfd.h"
+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 BOTH
+%s DEFSYMEXP
+%s MRI
+%s VERS_START
+%s VERS_SCRIPT
+%s VERS_NODE
+%%
-#include <ctype.h>
-#include "ldlex.h"
+ 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 ();
+ }
+ }
-#include "ld.h"
-#include "ldexp.h"
-#include "ldgram.tab.h"
-#include "ldmisc.h"
+<BOTH,SCRIPT,EXPRESSION,VERS_START,VERS_NODE,VERS_SCRIPT,INPUTLIST>"/*" { comment (); }
+
+
+<DEFSYMEXP>"-" { RTOKEN('-');}
+<DEFSYMEXP>"+" { RTOKEN('+');}
+<DEFSYMEXP>{SYMBOLNAMECHAR1}{SYMBOLNAMECHAR}* { yylval.name = xstrdup (yytext);
+ return NAME; }
+<DEFSYMEXP>"=" { RTOKEN('='); }
+
+<MRI,EXPRESSION>"$"([0-9A-Fa-f])+ {
+ yylval.integer = bfd_scan_vma (yytext + 1, 0, 16);
+ yylval.bigint.str = NULL;
+ return INT;
+ }
+
+<MRI,EXPRESSION>([0-9A-Fa-f])+(H|h|X|x|B|b|O|o|D|d) {
+ int ibase ;
+ switch (yytext[yyleng - 1]) {
+ case 'X':
+ case 'x':
+ case 'H':
+ case 'h':
+ ibase = 16;
+ break;
+ case 'O':
+ case 'o':
+ ibase = 8;
+ break;
+ case 'B':
+ case 'b':
+ ibase = 2;
+ break;
+ default:
+ ibase = 10;
+ }
+ yylval.integer = bfd_scan_vma (yytext, 0,
+ ibase);
+ yylval.bigint.str = NULL;
+ return INT;
+ }
+<SCRIPT,DEFSYMEXP,MRI,BOTH,EXPRESSION>((("$"|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;
+ }
+<BOTH,SCRIPT,EXPRESSION,MRI>"]" { RTOKEN(']');}
+<BOTH,SCRIPT,EXPRESSION,MRI>"[" { RTOKEN('[');}
+<BOTH,SCRIPT,EXPRESSION,MRI>"<<=" { RTOKEN(LSHIFTEQ);}
+<BOTH,SCRIPT,EXPRESSION,MRI>">>=" { RTOKEN(RSHIFTEQ);}
+<BOTH,SCRIPT,EXPRESSION,MRI>"||" { RTOKEN(OROR);}
+<BOTH,SCRIPT,EXPRESSION,MRI>"==" { RTOKEN(EQ);}
+<BOTH,SCRIPT,EXPRESSION,MRI>"!=" { RTOKEN(NE);}
+<BOTH,SCRIPT,EXPRESSION,MRI>">=" { RTOKEN(GE);}
+<BOTH,SCRIPT,EXPRESSION,MRI>"<=" { RTOKEN(LE);}
+<BOTH,SCRIPT,EXPRESSION,MRI>"<<" { RTOKEN(LSHIFT);}
+<BOTH,SCRIPT,EXPRESSION,MRI>">>" { RTOKEN(RSHIFT);}
+<BOTH,SCRIPT,EXPRESSION,MRI>"+=" { RTOKEN(PLUSEQ);}
+<BOTH,SCRIPT,EXPRESSION,MRI>"-=" { RTOKEN(MINUSEQ);}
+<BOTH,SCRIPT,EXPRESSION,MRI>"*=" { RTOKEN(MULTEQ);}
+<BOTH,SCRIPT,EXPRESSION,MRI>"/=" { RTOKEN(DIVEQ);}
+<BOTH,SCRIPT,EXPRESSION,MRI>"&=" { RTOKEN(ANDEQ);}
+<BOTH,SCRIPT,EXPRESSION,MRI>"|=" { RTOKEN(OREQ);}
+<BOTH,SCRIPT,EXPRESSION,MRI>"&&" { RTOKEN(ANDAND);}
+<BOTH,SCRIPT,EXPRESSION,MRI>">" { RTOKEN('>');}
+<BOTH,SCRIPT,EXPRESSION,MRI,INPUTLIST>"," { RTOKEN(',');}
+<BOTH,SCRIPT,EXPRESSION,MRI>"&" { RTOKEN('&');}
+<BOTH,SCRIPT,EXPRESSION,MRI>"|" { RTOKEN('|');}
+<BOTH,SCRIPT,EXPRESSION,MRI>"~" { RTOKEN('~');}
+<BOTH,SCRIPT,EXPRESSION,MRI>"!" { RTOKEN('!');}
+<BOTH,SCRIPT,EXPRESSION,MRI>"?" { RTOKEN('?');}
+<BOTH,SCRIPT,EXPRESSION,MRI>"*" { RTOKEN('*');}
+<BOTH,SCRIPT,EXPRESSION,MRI>"+" { RTOKEN('+');}
+<BOTH,SCRIPT,EXPRESSION,MRI>"-" { RTOKEN('-');}
+<BOTH,SCRIPT,EXPRESSION,MRI>"/" { RTOKEN('/');}
+<BOTH,SCRIPT,EXPRESSION,MRI>"%" { RTOKEN('%');}
+<BOTH,SCRIPT,EXPRESSION,MRI>"<" { RTOKEN('<');}
+<BOTH,SCRIPT,EXPRESSION,MRI>"=" { RTOKEN('=');}
+<BOTH,SCRIPT,EXPRESSION,MRI>"}" { RTOKEN('}') ; }
+<BOTH,SCRIPT,EXPRESSION,MRI>"{" { RTOKEN('{'); }
+<BOTH,SCRIPT,EXPRESSION,MRI,INPUTLIST>")" { RTOKEN(')');}
+<BOTH,SCRIPT,EXPRESSION,MRI,INPUTLIST>"(" { RTOKEN('(');}
+<BOTH,SCRIPT,EXPRESSION,MRI>":" { RTOKEN(':'); }
+<BOTH,SCRIPT,EXPRESSION,MRI>";" { RTOKEN(';');}
+<BOTH,SCRIPT>"MEMORY" { RTOKEN(MEMORY);}
+<BOTH,SCRIPT>"REGION_ALIAS" { RTOKEN(REGION_ALIAS);}
+<BOTH,SCRIPT>"LD_FEATURE" { RTOKEN(LD_FEATURE);}
+<BOTH,SCRIPT,EXPRESSION>"ORIGIN" { RTOKEN(ORIGIN);}
+<BOTH,SCRIPT>"VERSION" { RTOKEN(VERSIONK);}
+<EXPRESSION,BOTH,SCRIPT>"BLOCK" { RTOKEN(BLOCK);}
+<EXPRESSION,BOTH,SCRIPT>"BIND" { RTOKEN(BIND);}
+<BOTH,SCRIPT,EXPRESSION>"LENGTH" { RTOKEN(LENGTH);}
+<EXPRESSION,BOTH,SCRIPT>"ALIGN" { RTOKEN(ALIGN_K);}
+<EXPRESSION,BOTH,SCRIPT>"DATA_SEGMENT_ALIGN" { RTOKEN(DATA_SEGMENT_ALIGN);}
+<EXPRESSION,BOTH,SCRIPT>"DATA_SEGMENT_RELRO_END" { RTOKEN(DATA_SEGMENT_RELRO_END);}
+<EXPRESSION,BOTH,SCRIPT>"DATA_SEGMENT_END" { RTOKEN(DATA_SEGMENT_END);}
+<EXPRESSION,BOTH,SCRIPT>"ADDR" { RTOKEN(ADDR);}
+<EXPRESSION,BOTH,SCRIPT>"LOADADDR" { RTOKEN(LOADADDR);}
+<EXPRESSION,BOTH,SCRIPT>"ALIGNOF" { RTOKEN(ALIGNOF); }
+<EXPRESSION,BOTH>"MAX" { RTOKEN(MAX_K); }
+<EXPRESSION,BOTH>"MIN" { RTOKEN(MIN_K); }
+<EXPRESSION,BOTH>"LOG2CEIL" { RTOKEN(LOG2CEIL); }
+<EXPRESSION,BOTH,SCRIPT>"ASSERT" { RTOKEN(ASSERT_K); }
+<BOTH,SCRIPT>"ENTRY" { RTOKEN(ENTRY);}
+<BOTH,SCRIPT,MRI>"EXTERN" { RTOKEN(EXTERN);}
+<EXPRESSION,BOTH,SCRIPT>"NEXT" { RTOKEN(NEXT);}
+<EXPRESSION,BOTH,SCRIPT>"sizeof_headers" { RTOKEN(SIZEOF_HEADERS);}
+<EXPRESSION,BOTH,SCRIPT>"SIZEOF_HEADERS" { RTOKEN(SIZEOF_HEADERS);}
+<EXPRESSION,BOTH,SCRIPT>"SEGMENT_START" { RTOKEN(SEGMENT_START);}
+<BOTH,SCRIPT>"MAP" { RTOKEN(MAP);}
+<EXPRESSION,BOTH,SCRIPT>"SIZEOF" { RTOKEN(SIZEOF);}
+<BOTH,SCRIPT>"TARGET" { RTOKEN(TARGET_K);}
+<BOTH,SCRIPT>"SEARCH_DIR" { RTOKEN(SEARCH_DIR);}
+<BOTH,SCRIPT>"OUTPUT" { RTOKEN(OUTPUT);}
+<BOTH,SCRIPT>"INPUT" { RTOKEN(INPUT);}
+<EXPRESSION,BOTH,SCRIPT>"GROUP" { RTOKEN(GROUP);}
+<EXPRESSION,BOTH,SCRIPT,INPUTLIST>"AS_NEEDED" { RTOKEN(AS_NEEDED);}
+<EXPRESSION,BOTH,SCRIPT>"DEFINED" { RTOKEN(DEFINED);}
+<BOTH,SCRIPT>"CREATE_OBJECT_SYMBOLS" { RTOKEN(CREATE_OBJECT_SYMBOLS);}
+<BOTH,SCRIPT>"CONSTRUCTORS" { RTOKEN( CONSTRUCTORS);}
+<BOTH,SCRIPT>"FORCE_COMMON_ALLOCATION" { RTOKEN(FORCE_COMMON_ALLOCATION);}
+<BOTH,SCRIPT>"FORCE_GROUP_ALLOCATION" { RTOKEN(FORCE_GROUP_ALLOCATION);}
+<BOTH,SCRIPT>"INHIBIT_COMMON_ALLOCATION" { RTOKEN(INHIBIT_COMMON_ALLOCATION);}
+<BOTH,SCRIPT>"SECTIONS" { RTOKEN(SECTIONS);}
+<BOTH,SCRIPT>"INSERT" { RTOKEN(INSERT_K);}
+<BOTH,SCRIPT>"AFTER" { RTOKEN(AFTER);}
+<BOTH,SCRIPT>"BEFORE" { RTOKEN(BEFORE);}
+<BOTH,SCRIPT>"FILL" { RTOKEN(FILL);}
+<BOTH,SCRIPT>"STARTUP" { RTOKEN(STARTUP);}
+<BOTH,SCRIPT>"OUTPUT_FORMAT" { RTOKEN(OUTPUT_FORMAT);}
+<BOTH,SCRIPT>"OUTPUT_ARCH" { RTOKEN( OUTPUT_ARCH);}
+<BOTH,SCRIPT>"HLL" { RTOKEN(HLL);}
+<BOTH,SCRIPT>"SYSLIB" { RTOKEN(SYSLIB);}
+<BOTH,SCRIPT>"FLOAT" { RTOKEN(FLOAT);}
+<BOTH,SCRIPT>"QUAD" { RTOKEN( QUAD);}
+<BOTH,SCRIPT>"SQUAD" { RTOKEN( SQUAD);}
+<BOTH,SCRIPT>"LONG" { RTOKEN( LONG);}
+<BOTH,SCRIPT>"SHORT" { RTOKEN( SHORT);}
+<BOTH,SCRIPT>"BYTE" { RTOKEN( BYTE);}
+<BOTH,SCRIPT>"NOFLOAT" { RTOKEN(NOFLOAT);}
+<EXPRESSION,BOTH,SCRIPT>"NOCROSSREFS" { RTOKEN(NOCROSSREFS);}
+<EXPRESSION,BOTH,SCRIPT>"NOCROSSREFS_TO" { RTOKEN(NOCROSSREFS_TO);}
+<BOTH,SCRIPT>"OVERLAY" { RTOKEN(OVERLAY); }
+<BOTH,SCRIPT>"SORT_BY_NAME" { RTOKEN(SORT_BY_NAME); }
+<BOTH,SCRIPT>"SORT_BY_ALIGNMENT" { RTOKEN(SORT_BY_ALIGNMENT); }
+<BOTH,SCRIPT>"SORT" { RTOKEN(SORT_BY_NAME); }
+<BOTH,SCRIPT>"SORT_BY_INIT_PRIORITY" { RTOKEN(SORT_BY_INIT_PRIORITY); }
+<BOTH,SCRIPT>"SORT_NONE" { RTOKEN(SORT_NONE); }
+<EXPRESSION,BOTH,SCRIPT>"NOLOAD" { RTOKEN(NOLOAD);}
+<EXPRESSION,BOTH,SCRIPT>"DSECT" { RTOKEN(DSECT);}
+<EXPRESSION,BOTH,SCRIPT>"COPY" { RTOKEN(COPY);}
+<EXPRESSION,BOTH,SCRIPT>"INFO" { RTOKEN(INFO);}
+<EXPRESSION,BOTH,SCRIPT>"OVERLAY" { RTOKEN(OVERLAY);}
+<EXPRESSION,BOTH,SCRIPT>"ONLY_IF_RO" { RTOKEN(ONLY_IF_RO); }
+<EXPRESSION,BOTH,SCRIPT>"ONLY_IF_RW" { RTOKEN(ONLY_IF_RW); }
+<EXPRESSION,BOTH,SCRIPT>"SPECIAL" { RTOKEN(SPECIAL); }
+<BOTH,SCRIPT>"o" { RTOKEN(ORIGIN);}
+<BOTH,SCRIPT>"org" { RTOKEN(ORIGIN);}
+<BOTH,SCRIPT>"l" { RTOKEN( LENGTH);}
+<BOTH,SCRIPT>"len" { RTOKEN( LENGTH);}
+<EXPRESSION,BOTH,SCRIPT>"INPUT_SECTION_FLAGS" { RTOKEN(INPUT_SECTION_FLAGS); }
+<EXPRESSION,BOTH,SCRIPT>"INCLUDE" { RTOKEN(INCLUDE);}
+<BOTH,SCRIPT>"PHDRS" { RTOKEN (PHDRS); }
+<EXPRESSION,BOTH,SCRIPT>"AT" { RTOKEN(AT);}
+<EXPRESSION,BOTH,SCRIPT>"ALIGN_WITH_INPUT" { RTOKEN(ALIGN_WITH_INPUT);}
+<EXPRESSION,BOTH,SCRIPT>"SUBALIGN" { RTOKEN(SUBALIGN);}
+<EXPRESSION,BOTH,SCRIPT>"HIDDEN" { RTOKEN(HIDDEN); }
+<EXPRESSION,BOTH,SCRIPT>"PROVIDE" { RTOKEN(PROVIDE); }
+<EXPRESSION,BOTH,SCRIPT>"PROVIDE_HIDDEN" { RTOKEN(PROVIDE_HIDDEN); }
+<EXPRESSION,BOTH,SCRIPT>"KEEP" { RTOKEN(KEEP); }
+<EXPRESSION,BOTH,SCRIPT>"EXCLUDE_FILE" { RTOKEN(EXCLUDE_FILE); }
+<EXPRESSION,BOTH,SCRIPT>"CONSTANT" { RTOKEN(CONSTANT);}
+<MRI>"#".*\n? { ++ lineno; }
+<MRI>"\n" { ++ lineno; RTOKEN(NEWLINE); }
+<MRI>"*".* { /* Mri comment line */ }
+<MRI>";".* { /* Mri comment line */ }
+<MRI>"END" { RTOKEN(ENDWORD); }
+<MRI>"ALIGNMOD" { RTOKEN(ALIGNMOD);}
+<MRI>"ALIGN" { RTOKEN(ALIGN_K);}
+<MRI>"CHIP" { RTOKEN(CHIP); }
+<MRI>"BASE" { RTOKEN(BASE); }
+<MRI>"ALIAS" { RTOKEN(ALIAS); }
+<MRI>"TRUNCATE" { RTOKEN(TRUNCATE); }
+<MRI>"LOAD" { RTOKEN(LOAD); }
+<MRI>"PUBLIC" { RTOKEN(PUBLIC); }
+<MRI>"ORDER" { RTOKEN(ORDER); }
+<MRI>"NAME" { RTOKEN(NAMEWORD); }
+<MRI>"FORMAT" { RTOKEN(FORMAT); }
+<MRI>"CASE" { RTOKEN(CASE); }
+<MRI>"START" { RTOKEN(START); }
+<MRI>"LIST".* { RTOKEN(LIST); /* LIST and ignore to end of line */ }
+<MRI>"SECT" { RTOKEN(SECT); }
+<EXPRESSION,BOTH,SCRIPT,MRI>"ABSOLUTE" { RTOKEN(ABSOLUTE); }
+<MRI>"end" { RTOKEN(ENDWORD); }
+<MRI>"alignmod" { RTOKEN(ALIGNMOD);}
+<MRI>"align" { RTOKEN(ALIGN_K);}
+<MRI>"chip" { RTOKEN(CHIP); }
+<MRI>"base" { RTOKEN(BASE); }
+<MRI>"alias" { RTOKEN(ALIAS); }
+<MRI>"truncate" { RTOKEN(TRUNCATE); }
+<MRI>"load" { RTOKEN(LOAD); }
+<MRI>"public" { RTOKEN(PUBLIC); }
+<MRI>"order" { RTOKEN(ORDER); }
+<MRI>"name" { RTOKEN(NAMEWORD); }
+<MRI>"format" { RTOKEN(FORMAT); }
+<MRI>"case" { RTOKEN(CASE); }
+<MRI>"extern" { RTOKEN(EXTERN); }
+<MRI>"start" { RTOKEN(START); }
+<MRI>"list".* { RTOKEN(LIST); /* LIST and ignore to end of line */ }
+<MRI>"sect" { RTOKEN(SECT); }
+<EXPRESSION,BOTH,SCRIPT,MRI>"absolute" { RTOKEN(ABSOLUTE); }
+
+<MRI>{FILENAMECHAR1}{NOCFILENAMECHAR}* {
+/* Filename without commas, needed to parse mri stuff */
+ yylval.name = xstrdup (yytext);
+ return NAME;
+ }
+
+
+<BOTH,INPUTLIST>{FILENAMECHAR1}{FILENAMECHAR}* {
+ yylval.name = xstrdup (yytext);
+ return NAME;
+ }
+<INPUTLIST>"="{FILENAMECHAR1}{FILENAMECHAR}* {
+/* Filename to be prefixed by --sysroot or when non-sysrooted, nothing. */
+ yylval.name = xstrdup (yytext);
+ return NAME;
+ }
+<BOTH,INPUTLIST>"-l"{FILENAMECHAR}+ {
+ yylval.name = xstrdup (yytext + 2);
+ return LNAME;
+ }
+<EXPRESSION>{SYMBOLNAMECHAR1}{NOCFILENAMECHAR}* {
+ yylval.name = xstrdup (yytext);
+ return NAME;
+ }
+<EXPRESSION>"/DISCARD/" {
+ yylval.name = xstrdup (yytext);
+ return NAME;
+ }
+<EXPRESSION>"-l"{NOCFILENAMECHAR}+ {
+ yylval.name = xstrdup (yytext + 2);
+ return LNAME;
+ }
+<SCRIPT>{WILDCHAR}* {
+ /* Annoyingly, this pattern can match comments, and we have
+ longest match issues to consider. So if the first two
+ characters are a comment opening, put the input back and
+ try again. */
+ if (yytext[0] == '/' && yytext[1] == '*')
+ {
+ yyless (2);
+ comment ();
+ }
+ else
+ {
+ yylval.name = xstrdup (yytext);
+ return NAME;
+ }
+ }
-#undef input
-#undef unput
-#define input lex_input
-#define unput lex_unput
-int debug;
+<EXPRESSION,BOTH,SCRIPT,VERS_NODE,INPUTLIST>"\""[^\"]*"\"" {
+ /* No matter the state, quotes
+ give what's inside. */
+ bfd_size_type len;
+ yylval.name = xstrdup (yytext + 1);
+ /* PR ld/20906. A corrupt input file
+ can contain bogus strings. */
+ len = strlen (yylval.name);
+ if (len > (bfd_size_type) yyleng - 2)
+ len = yyleng - 2;
+ yylval.name[len] = 0;
+ return NAME;
+ }
+<BOTH,SCRIPT,EXPRESSION>"\n" { lineno++;}
+<MRI,BOTH,SCRIPT,EXPRESSION>[ \t\r]+ { }
+
+<VERS_NODE,VERS_SCRIPT>[:,;] { return *yytext; }
+
+<VERS_NODE>global { RTOKEN(GLOBAL); }
+
+<VERS_NODE>local { RTOKEN(LOCAL); }
+
+<VERS_NODE>extern { RTOKEN(EXTERN); }
+
+<VERS_NODE>{V_IDENTIFIER} { yylval.name = xstrdup (yytext);
+ return VERS_IDENTIFIER; }
+
+<VERS_SCRIPT>{V_TAG} { yylval.name = xstrdup (yytext);
+ return VERS_TAG; }
+
+<VERS_START>"{" { BEGIN(VERS_SCRIPT); return *yytext; }
+
+<VERS_SCRIPT>"{" { BEGIN(VERS_NODE);
+ vers_node_nesting = 0;
+ return *yytext;
+ }
+<VERS_SCRIPT>"}" { return *yytext; }
+<VERS_NODE>"{" { vers_node_nesting++; return *yytext; }
+<VERS_NODE>"}" { if (--vers_node_nesting < 0)
+ BEGIN(VERS_SCRIPT);
+ return *yytext;
+ }
+
+<VERS_START,VERS_NODE,VERS_SCRIPT,INPUTLIST>[\n] { lineno++; }
+
+<VERS_START,VERS_NODE,VERS_SCRIPT>#.* { /* Eat up comments */ }
+
+<VERS_START,VERS_NODE,VERS_SCRIPT,INPUTLIST>[ \t\r]+ { /* Eat up whitespace */ }
+
+<<EOF>> {
+ include_stack_ptr--;
+ if (include_stack_ptr == 0)
+ {
+ lineno = 0;
+ yyterminate ();
+ }
+ else
+ yy_switch_to_buffer (include_stack[include_stack_ptr]);
+ lineno = lineno_stack[include_stack_ptr];
+ input_flags.sysrooted = sysrooted_stack[include_stack_ptr];
-static boolean ldgram_in_defsym;
-static boolean ldgram_had_equals;
-extern boolean ldgram_in_script;
-static char *command_line;
+ return END;
+}
-extern int fgetc();
-extern int yyparse();
+<SCRIPT,MRI,VERS_START,VERS_SCRIPT,VERS_NODE>. lex_warn_invalid (" in script", yytext);
+<EXPRESSION,DEFSYMEXP,BOTH>. lex_warn_invalid (" in expression", yytext);
-typedef struct {
- char *name;
-int value;
-} keyword_type;
-#define RTOKEN(x) { yylval.token = x; return x; }
-keyword_type keywords[] =
-{
-"/", '/',
-"MEMORY",MEMORY,
-"ORIGIN",ORIGIN,
-"BLOCK",BLOCK,
-"LENGTH",LENGTH,
-"ALIGN",ALIGN_K,
-"SUBSECTION_ALIGN",SUBSECTION_ALIGN,
-"ADDR",ADDR,
-"ENTRY",ENTRY,
-"SCRIPT", SCRIPT,
-"ENDSCRIPT", ENDSCRIPT,
-"NEXT",NEXT,
-"sizeof_headers",SIZEOF_HEADERS,
-"SIZEOF_HEADERS",SIZEOF_HEADERS,
-"MAP",MAP,
-"SIZEOF",SIZEOF,
-"TARGET",TARGET_K,
-"SEARCH_DIR",SEARCH_DIR,
-"OUTPUT",OUTPUT,
-"INPUT",INPUT,
-"DEFINED",DEFINED,
-"CREATE_OBJECT_SYMBOLS",CREATE_OBJECT_SYMBOLS,
-"FORCE_COMMON_ALLOCATION",FORCE_COMMON_ALLOCATION,
-"SECTIONS",SECTIONS,
-"FILL",FILL,
-"STARTUP",STARTUP,
-"OUTPUT_FORMAT",OUTPUT_FORMAT,
-"OUTPUT_ARCH", OUTPUT_ARCH,
-"HLL",HLL,
-"SYSLIB",SYSLIB,
-"FLOAT",FLOAT,
-"LONG", LONG,
-"SHORT", SHORT,
-"BYTE", BYTE,
-"NOFLOAT",NOFLOAT,
-"o",ORIGIN,
-"org",ORIGIN,
-"l", LENGTH,
-"len", LENGTH,
-0,0};
-unsigned int lineno;
-extern boolean hex_mode;
-FILE *ldlex_input_stack;
-static unsigned int have_pushback;
-
-#define NPUSHBACK 10
-int pushback[NPUSHBACK];
-int thischar;
-extern char *ldfile_input_filename;
-int donehash = 0;
-int
-lex_input()
-{
- if (have_pushback > 0)
- {
- have_pushback --;
- return thischar = pushback[have_pushback];
- }
- if (ldlex_input_stack) {
- thischar = fgetc(ldlex_input_stack);
-
- if (thischar == EOF) {
- fclose(ldlex_input_stack);
- ldlex_input_stack = (FILE *)NULL;
- ldfile_input_filename = (char *)NULL;
- /* First char after script eof is a @ so that we can tell the grammer
- that we've left */
- thischar = '@';
+%%
+\f
+/* Switch flex to reading script file NAME, open on FILE,
+ saving the current input info on the include stack. */
+
+void
+lex_push_file (FILE *file, const char *name, unsigned int sysrooted)
+{
+ if (include_stack_ptr >= MAX_INCLUDE_DEPTH)
+ {
+ einfo (_("%F:includes nested too deeply\n"));
}
- }
- else if (command_line && *command_line) {
- thischar = *(command_line++);
- }
- else {
- thischar = 0;
- }
- if(thischar == '\t') thischar = ' ';
- if (thischar == '\n') { thischar = ' '; lineno++; }
- return thischar ;
+ file_name_stack[include_stack_ptr] = name;
+ lineno_stack[include_stack_ptr] = lineno;
+ sysrooted_stack[include_stack_ptr] = input_flags.sysrooted;
+ include_stack[include_stack_ptr] = YY_CURRENT_BUFFER;
+
+ include_stack_ptr++;
+ lineno = 1;
+ input_flags.sysrooted = sysrooted;
+ yyin = file;
+ yy_switch_to_buffer (yy_create_buffer (yyin, YY_BUF_SIZE));
}
+/* Return a newly created flex input buffer containing STRING,
+ which is SIZE bytes long. */
+
+static YY_BUFFER_STATE
+yy_create_string_buffer (const char *string, size_t size)
+{
+ YY_BUFFER_STATE b;
+
+ /* Calls to m-alloc get turned by sed into xm-alloc. */
+ b = malloc (sizeof (struct yy_buffer_state));
+ b->yy_input_file = 0;
+ b->yy_buf_size = size;
+
+ /* yy_ch_buf has to be 2 characters longer than the size given because
+ we need to put in 2 end-of-buffer characters. */
+ b->yy_ch_buf = malloc ((unsigned) (b->yy_buf_size + 3));
+
+ b->yy_ch_buf[0] = '\n';
+ strcpy (b->yy_ch_buf+1, string);
+ b->yy_ch_buf[size+1] = YY_END_OF_BUFFER_CHAR;
+ b->yy_ch_buf[size+2] = YY_END_OF_BUFFER_CHAR;
+ b->yy_n_chars = size+1;
+ b->yy_buf_pos = &b->yy_ch_buf[1];
+
+ b->yy_is_our_buffer = 1;
+ b->yy_is_interactive = 0;
+ b->yy_at_bol = 1;
+ b->yy_fill_buffer = 0;
+
+ /* flex 2.4.7 changed the interface. FIXME: We should not be using
+ a flex internal interface in the first place! */
+#ifdef YY_BUFFER_NEW
+ b->yy_buffer_status = YY_BUFFER_NEW;
+#else
+ b->yy_eof_status = EOF_NOT_SEEN;
+#endif
+
+ return b;
+}
+
+/* Switch flex to reading from STRING, saving the current input info
+ on the include stack. */
+
void
-lex_unput(c)
-int c;
+lex_redirect (const char *string, const char *fake_filename, unsigned int count)
{
- if (have_pushback > NPUSHBACK) {
- info("%F%P Too many pushbacks\n");
- }
+ YY_BUFFER_STATE tmp;
- pushback[have_pushback] = c;
- have_pushback ++;
+ yy_init = 0;
+ if (include_stack_ptr >= MAX_INCLUDE_DEPTH)
+ {
+ einfo (_("%F: macros nested too deeply\n"));
+ }
+ file_name_stack[include_stack_ptr] = fake_filename;
+ lineno_stack[include_stack_ptr] = lineno;
+ include_stack[include_stack_ptr] = YY_CURRENT_BUFFER;
+ include_stack_ptr++;
+ lineno = count;
+ tmp = yy_create_string_buffer (string, strlen (string));
+ yy_switch_to_buffer (tmp);
}
+\f
+/* Functions to switch to a different flex start condition,
+ saving the current start condition on `state_stack'. */
-
- int
-yywrap()
- { return 1; }
-/*VARARGS*/
+static int state_stack[MAX_INCLUDE_DEPTH * 2];
+static int *state_stack_p = state_stack;
void
-allprint(x)
-int x;
+ldlex_script (void)
{
-fprintf(yyout,"%d",x);
+ *(state_stack_p)++ = yy_start;
+ BEGIN (SCRIPT);
}
void
-sprint(x)
-char *x;
+ldlex_inputlist (void)
{
-fprintf(yyout,"%s",x);
+ *(state_stack_p)++ = yy_start;
+ BEGIN (INPUTLIST);
}
-int thischar;
-
-void parse_line(arg)
-char *arg;
+void
+ldlex_mri_script (void)
{
- command_line = arg;
- have_pushback = 0;
- yyparse();
+ *(state_stack_p)++ = yy_start;
+ BEGIN (MRI);
}
-
-
void
-parse_args(ac, av)
-int ac;
-char **av;
+ldlex_version_script (void)
{
- char *p;
- int i;
- size_t size = 0;
- char *dst;
- debug = 1;
- for (i= 1; i < ac; i++) {
- size += strlen(av[i]) + 2;
- }
- dst = p = (char *)ldmalloc(size + 2);
-/* Put a space arount each option */
-
-
- for (i =1; i < ac; i++) {
+ *(state_stack_p)++ = yy_start;
+ BEGIN (VERS_START);
+}
- unsigned int s = strlen(av[i]);
- *dst++ = ' ';
- memcpy(dst, av[i], s);
- dst[s] = ' ';
- dst += s + 1;
- }
- *dst = 0;
- parse_line(p);
+void
+ldlex_version_file (void)
+{
+ *(state_stack_p)++ = yy_start;
+ BEGIN (VERS_SCRIPT);
+}
- free(p);
+void
+ldlex_defsym (void)
+{
+ *(state_stack_p)++ = yy_start;
+ BEGIN (DEFSYMEXP);
+}
+void
+ldlex_expression (void)
+{
+ *(state_stack_p)++ = yy_start;
+ BEGIN (EXPRESSION);
+}
+void
+ldlex_both (void)
+{
+ *(state_stack_p)++ = yy_start;
+ BEGIN (BOTH);
}
-static long
-DEFUN(number,(default_if_zero,base),
- int default_if_zero AND
- int base)
+void
+ldlex_popstate (void)
{
- unsigned long l = 0;
- int ch = yytext[0];
- if (ch == 0) {
- base = default_if_zero;
- }
- while (1) {
- switch (ch) {
- case 'x':
- base = 16;
- break;
- case 'k':
- case 'K':
- l =l * 1024;
- break;
- case 'm':
- case 'M':
- l =l * 1024 * 1024;
- break;
- case '0': case '1': case '2': case '3': case '4':
- case '5': case '6': case '7': case '8': case '9':
- l = l * base + ch - '0';
- break;
- case 'a': case 'b': case 'c' : case 'd' : case 'e': case 'f':
- l =l *base + ch - 'a' + 10;
- break;
- case 'A': case 'B': case 'C' : case 'D' : case 'E': case 'F':
- l =l *base + ch - 'A' + 10;
- break;
- default:
- unput(ch);
- yylval.integer = l;
- return INT;
- }
-ch = input();
- }
+ yy_start = *(--state_stack_p);
}
-%}
-%a 4000
-%o 5000
-FILENAMECHAR [a-zA-Z0-9\/\.\-\_\+\=]
-FILENAME {FILENAMECHAR}+
-WHITE [ \t]+
+/* Return the current file name, or the previous file if no file is
+ current. */
-%%
+const char*
+ldlex_filename (void)
+{
+ return file_name_stack[include_stack_ptr - (include_stack_ptr != 0)];
+}
+\f
-"@" { return '}'; }
-"\ -defsym\ " { ldgram_in_defsym = true; return OPTION_defsym; }
-"\ -noinhibit_exec\ " { return OPTION_noinhibit_exec; }
-"\ -format\ " { return OPTION_format; }
-"\ -n\ " { return OPTION_n; }
-"\ -r\ " { return OPTION_r; }
-"\ -i\ " { return OPTION_r; }
-"\ -Ur\ " { return OPTION_Ur; }
-"\ -o\ " { return OPTION_o; }
-"\ -g\ " { return OPTION_g; }
-"\ -e\ " { return OPTION_e; }
-"\ -b\ " { return OPTION_b; }
-"\ -dc\ " { return OPTION_dc; }
-"\ -dp\ " { return OPTION_dp; }
-"\ -d\ " { return OPTION_d; }
-"\ -v\ " { return OPTION_v; }
-"\ -M\ " { return OPTION_M; }
-"\ -t\ " { return OPTION_t; }
-"\ -X\ " { return OPTION_X; }
-"\ -x\ " { return OPTION_x; }
-"\ -c\ " { return OPTION_c; }
-"\ -R\ " { return OPTION_R; }
-"\ -u\ " { return OPTION_u; }
-"\ -s\ " { return OPTION_s; }
-"\ -S\ " { return OPTION_S; }
-"\ -B{FILENAME}\ " { /* Ignored */ }
-"\ -l"{FILENAME} {
- yylval.name = buystring(yytext+3);
- return OPTION_l;
- }
+/* Place up to MAX_SIZE characters in BUF and return
+ either the number of characters read, or 0 to indicate EOF. */
-"\ -L"{FILENAME} {
- yylval.name = buystring(yytext+3);
- return OPTION_L;
- }
-"\ -Ttext\ " {
- yylval.name = ".text";
- return OPTION_Texp;
- }
-"\ -Tdata\ " {
- yylval.name = ".data";
- return OPTION_Texp;
- }
-"\ -Tbss\ " {
- yylval.name = ".bss";
- return OPTION_Texp;
- }
-
-"\ -T"{FILENAME} {
- yylval.name = buystring(yytext+3);
- return OPTION_Tfile;
- }
-"\ -T\ " {
- return OPTION_T;
- }
-
-"\ -F"{FILENAME} {
- return OPTION_F;
- }
-"\ -F\ " {
- return OPTION_F;
- }
-
-"\ -A"{FILENAME} {
- yylval.name = buystring(yytext+3);
- return OPTION_Aarch;
- }
-
-" " {
- if (ldgram_had_equals == true) {
- ldgram_in_defsym = false;
- ldgram_had_equals = false;
- }
+static int
+yy_input (char *buf, int max_size)
+{
+ int result = 0;
+ if (YY_CURRENT_BUFFER->yy_input_file)
+ {
+ if (yyin)
+ {
+ result = fread (buf, 1, max_size, yyin);
+ if (result < max_size && ferror (yyin))
+ einfo (_("%F%P: read in flex scanner failed\n"));
}
-"<<=" { 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('-');}
-
-
-
-"/*" {
- while (1) {
- int ch;
- ch = input();
- while (ch != '*') {
- ch = input();
- }
-
-
-
- if (input() == '/') {
- break;
}
- unput(yytext[yyleng-1]);
- }
+ return result;
}
-"\""[^\"]*"\"" {
+/* Eat the rest of a C-style comment. */
- yylval.name = buystring(yytext+1);
- yylval.name[yyleng-2] = 0; /* Fry final quote */
- return NAME;
-}
-
-{FILENAMECHAR} {
-
- boolean loop = false;
- int ch;
- keyword_type *k;
-
- /* If we're in hex mode (only after a -T) then all we can see are numbers
- hex digit we see will be a number. */
-
- if (hex_mode) {
- return number(16, 16);
- }
-
- /* If we're in a defsym then all things starting with a digit are in
- hex */
-
- if (isdigit(yytext[0]) && ldgram_in_defsym) {
- return number(16,16);
- }
-
-
- /* Otherwise if we're in a script we will parse the numbers
- normally */
-
- if (ldgram_in_script == true && isdigit(yytext[0])) {
- return number(8,10);
- }
-
- /* Anywhere not in a script or defsym, an opertor is part of a
- filename, except / and, which is an operator when on its own */
- if (ldgram_in_script == true|| ldgram_in_defsym == true) {
-
- switch (yytext[0]) {
- case '*': RTOKEN('*');
+static void
+comment (void)
+{
+ int c;
+
+ while (1)
+ {
+ c = input();
+ while (c != '*' && c != 0)
+ {
+ if (c == '\n')
+ lineno++;
+ c = input();
+ }
- case '=': {
- ldgram_had_equals = true;
- RTOKEN('=');
- }
- break;
- case '/': {
- if (ldgram_in_defsym) RTOKEN('/');
- }
- break;
- case '+': RTOKEN('+');
- case '-': RTOKEN('-');
- case '!': RTOKEN('!');
- case '~': RTOKEN('~');
- }
- }
+ if (c == '*')
+ {
+ c = input();
+ while (c == '*')
+ c = input();
+ if (c == '/')
+ break; /* found the end */
+ }
+ if (c == '\n')
+ lineno++;
-/* Otherwise this must be a file or a symbol name, and it will continue to be a
- filename until we get to something strange. In scripts operator looking
- things are taken to be operators, except /, which will be left
- */
- ch = input();
- while (true)
- {
- if (ldgram_in_defsym == true) {
- switch (ch) {
- case '*':
- case '=':
- case '+':
- case '/':
- case '-':
- case '!':
- case '~':
- goto quit;
- }
-
- }
- if(ldgram_in_script == true) {
- switch (ch) {
- case '*':
- case '=':
- case '+':
- case '-':
- case '!':
- case '~':
- goto quit;
- }
- }
-
- if (isalpha(ch) || isdigit(ch) || ch == '.' || ch == '_' ||
- ch == '/' || ch == '.' || ch == '+' || ch == '-' || ch =='=') {
- yytext[yyleng++] = ch;
- }
- else
+ if (c == 0)
+ {
+ einfo (_("%F%P: EOF in comment\n"));
break;
- ch = input();
- }
- quit:;
- yytext[yyleng] = 0;
- unput(ch);
-
- for(k = keywords; k ->name != (char *)NULL; k++) {
- if (strcmp(k->name, yytext)==0) {
- yylval.token = k->value;
- return k->value;
+ }
}
- }
- yylval.name = buystring(yytext);
- return NAME;
}
+/* Warn the user about a garbage character WHAT in the input
+ in context WHERE. */
+static void
+lex_warn_invalid (char *where, char *what)
+{
+ char buf[5];
+
+ /* If we have found an input file whose format we do not recognize,
+ and we are therefore treating it as a linker script, and we find
+ an invalid character, then most likely this is a real object file
+ of some different format. Treat it as such. */
+ if (ldfile_assumed_script)
+ {
+ bfd_set_error (bfd_error_file_not_recognized);
+ einfo (_("%F%s: file not recognized: %E\n"), ldlex_filename ());
+ }
+ if (! ISPRINT (*what))
+ {
+ sprintf (buf, "\\%03o", *(unsigned char *) what);
+ what = buf;
+ }
-
-%%
+ einfo (_("%P:%pS: ignoring invalid character `%s'%s\n"), NULL, what, where);
+}