[PATCH 6/6] Allow unquoted = as the first character in ld linker script input_list names

[Hans-Peter Nilsson <hans-peter dot nilsson at axis dot com>]

All this only to enable INPUT(=/path/to/file) and not be forced to use
INPUT("=/path/to/file") whenever there's a need to force a sysroot-
prefix.  Still, IMHO it seems better to make use of a previously
invalid syntax and not just change the meaning of quoted =-prefixed
paths (though arguably that's not very useful before this patchset).

This got a little bit hairier than I'd expected: I had to add a new
lexer state (aka. start condition) to avoid a first "=" being lexed as
the token "=", despite that not making sense in constructs expecting
file-names in the first place.  (The grammar doesn't allow for
expressions in any part of those lists.)  I guess I *could* have made
it work using that token anyway, but I didn't like the idea that you
would be able to separate the "=" from the rest of the file-name with
whitespace.  Some changes to the submitted test-case will be needed if
this part isn't accepted.

Ok for the lot?

ld:
	* ldlex.l (INPUTLIST): New start condition.
	(comment pattern, ",", "(", ")", "AS_NEEDED")
	({FILENAMECHAR1}{FILENAMECHAR}*, "-l"{FILENAMECHAR}+)
	(quoted string pattern, whitespace pattern): Add INPUTLIST to
	valid start conditions.
	(<INPUTLIST>"="{FILENAMECHAR1}{FILENAMECHAR}*): New NAME rule.
	(ldlex_inputlist): New start-condition-setter function.
	* ldgram.y (input_list1): Rename from input_list.  All recursive
	use changed.
	(input_list): New wrapper rule for input_list1, setting
	INPUTLIST lexer state for the duration of parsing input_list1.


diff --git a/ld/ldgram.y b/ld/ldgram.y
index 4875fa7..e76a0a3 100644
--- a/ld/ldgram.y
+++ b/ld/ldgram.y
@@ -365,38 +365,43 @@ ifile_p1:
 	;
 
 input_list:
+		{ ldlex_inputlist(); }
+		input_list1
+		{ ldlex_popstate(); }
+
+input_list1:
 		NAME
 		{ lang_add_input_file($1,lang_input_file_is_search_file_enum,
 				 (char *)NULL); }
-	|	input_list ',' NAME
+	|	input_list1 ',' NAME
 		{ lang_add_input_file($3,lang_input_file_is_search_file_enum,
 				 (char *)NULL); }
-	|	input_list NAME
+	|	input_list1 NAME
 		{ lang_add_input_file($2,lang_input_file_is_search_file_enum,
 				 (char *)NULL); }
 	|	LNAME
 		{ lang_add_input_file($1,lang_input_file_is_l_enum,
 				 (char *)NULL); }
-	|	input_list ',' LNAME
+	|	input_list1 ',' LNAME
 		{ lang_add_input_file($3,lang_input_file_is_l_enum,
 				 (char *)NULL); }
-	|	input_list LNAME
+	|	input_list1 LNAME
 		{ lang_add_input_file($2,lang_input_file_is_l_enum,
 				 (char *)NULL); }
 	|	AS_NEEDED '('
 		  { $<integer>$ = input_flags.add_DT_NEEDED_for_regular;
 		    input_flags.add_DT_NEEDED_for_regular = TRUE; }
-		     input_list ')'
+		     input_list1 ')'
 		  { input_flags.add_DT_NEEDED_for_regular = $<integer>3; }
-	|	input_list ',' AS_NEEDED '('
+	|	input_list1 ',' AS_NEEDED '('
 		  { $<integer>$ = input_flags.add_DT_NEEDED_for_regular;
 		    input_flags.add_DT_NEEDED_for_regular = TRUE; }
-		     input_list ')'
+		     input_list1 ')'
 		  { input_flags.add_DT_NEEDED_for_regular = $<integer>5; }
-	|	input_list AS_NEEDED '('
+	|	input_list1 AS_NEEDED '('
 		  { $<integer>$ = input_flags.add_DT_NEEDED_for_regular;
 		    input_flags.add_DT_NEEDED_for_regular = TRUE; }
-		     input_list ')'
+		     input_list1 ')'
 		  { input_flags.add_DT_NEEDED_for_regular = $<integer>4; }
 	;
 
diff --git a/ld/ldlex.h b/ld/ldlex.h
index 63f4c81..56cd121 100644
--- a/ld/ldlex.h
+++ b/ld/ldlex.h
@@ -161,6 +161,7 @@ extern int yylex (void);
 extern void lex_push_file (FILE *, const char *, unsigned int);
 extern void lex_redirect (const char *, const char *, unsigned int);
 extern void ldlex_script (void);
+extern void ldlex_inputlist (void);
 extern void ldlex_mri_script (void);
 extern void ldlex_version_script (void);
 extern void ldlex_version_file (void);
diff --git a/ld/ldlex.l b/ld/ldlex.l
index 234867c..d162128 100644
--- a/ld/ldlex.l
+++ b/ld/ldlex.l
@@ -77,6 +77,7 @@ 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
@@ -109,6 +110,7 @@ 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
@@ -134,7 +136,7 @@ V_IDENTIFIER [*?.$_a-zA-Z\[\]\-\!\^\\]([*?.$_a-zA-Z0-9\[\]\-\!\^\\]|::)*
 	}
     }
 
-<BOTH,SCRIPT,EXPRESSION,VERS_START,VERS_NODE,VERS_SCRIPT>"/*"	{ comment (); }
+<BOTH,SCRIPT,EXPRESSION,VERS_START,VERS_NODE,VERS_SCRIPT,INPUTLIST>"/*"	{ comment (); }
 
 
 <DEFSYMEXP>"-"                  { RTOKEN('-');}
@@ -221,7 +223,7 @@ V_IDENTIFIER [*?.$_a-zA-Z\[\]\-\!\^\\]([*?.$_a-zA-Z0-9\[\]\-\!\^\\]|::)*
 <BOTH,SCRIPT,EXPRESSION,MRI>"|="	{ RTOKEN(OREQ);}
 <BOTH,SCRIPT,EXPRESSION,MRI>"&&"	{ RTOKEN(ANDAND);}
 <BOTH,SCRIPT,EXPRESSION,MRI>">"		{ RTOKEN('>');}
-<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('~');}
@@ -236,8 +238,8 @@ V_IDENTIFIER [*?.$_a-zA-Z\[\]\-\!\^\\]([*?.$_a-zA-Z0-9\[\]\-\!\^\\]|::)*
 <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);}
@@ -272,7 +274,7 @@ V_IDENTIFIER [*?.$_a-zA-Z\[\]\-\!\^\\]([*?.$_a-zA-Z0-9\[\]\-\!\^\\]|::)*
 <BOTH,SCRIPT>"OUTPUT"			{ RTOKEN(OUTPUT);}
 <BOTH,SCRIPT>"INPUT"			{ RTOKEN(INPUT);}
 <EXPRESSION,BOTH,SCRIPT>"GROUP"		{ RTOKEN(GROUP);}
-<EXPRESSION,BOTH,SCRIPT>"AS_NEEDED"	{ RTOKEN(AS_NEEDED);}
+<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);}
@@ -373,11 +375,16 @@ V_IDENTIFIER [*?.$_a-zA-Z\[\]\-\!\^\\]([*?.$_a-zA-Z0-9\[\]\-\!\^\\]|::)*
 				}
 
 
-<BOTH>{FILENAMECHAR1}{FILENAMECHAR}*	{
+<BOTH,INPUTLIST>{FILENAMECHAR1}{FILENAMECHAR}*	{
 				 yylval.name = xstrdup (yytext);
 				  return NAME;
 				}
-<BOTH>"-l"{FILENAMECHAR}+ {
+<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;
 				}
@@ -406,7 +413,7 @@ V_IDENTIFIER [*?.$_a-zA-Z\[\]\-\!\^\\]([*?.$_a-zA-Z0-9\[\]\-\!\^\\]|::)*
 		  }
 	}
 
-<EXPRESSION,BOTH,SCRIPT,VERS_NODE>"\""[^\"]*"\"" {
+<EXPRESSION,BOTH,SCRIPT,VERS_NODE,INPUTLIST>"\""[^\"]*"\"" {
 					/* No matter the state, quotes
 					   give what's inside */
 					yylval.name = xstrdup (yytext + 1);
@@ -447,7 +454,7 @@ V_IDENTIFIER [*?.$_a-zA-Z\[\]\-\!\^\\]([*?.$_a-zA-Z0-9\[\]\-\!\^\\]|::)*
 
 <VERS_START,VERS_NODE,VERS_SCRIPT>#.*		{ /* Eat up comments */ }
 
-<VERS_START,VERS_NODE,VERS_SCRIPT>[ \t\r]+   	{ /* Eat up whitespace */ }
+<VERS_START,VERS_NODE,VERS_SCRIPT,INPUTLIST>[ \t\r]+   	{ /* Eat up whitespace */ }
 
 <<EOF>> {
   include_stack_ptr--;
@@ -566,6 +573,13 @@ ldlex_script (void)
 }
 
 void
+ldlex_inputlist (void)
+{
+  *(state_stack_p)++ = yy_start;
+  BEGIN (INPUTLIST);
+}
+
+void
 ldlex_mri_script (void)
 {
   *(state_stack_p)++ = yy_start;
-- 

brgds, H-P