[PATCH 05/11] gas: pre-init the scrubber's lex[]

[Jan Beulich]

While we can't - unlike an old comment suggests - do this fully, we can
certainly do part of this at compile time.

Since it's adjacent, also drop the unnecessary forward declaration of
process_escape().
---
Assumptions on certain ordering between characters exists elsewhere
already, so I assume leveraging this here as well isn't going to be a
problem.

--- a/gas/app.c
+++ b/gas/app.c
@@ -58,10 +58,6 @@ static const char * symver_state;
 
 static char last_char;
 
-static char lex[256];
-static const char symbol_chars[] =
-"$._ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789";
-
 #define LEX_IS_SYMBOL_COMPONENT		1
 #define LEX_IS_WHITESPACE		2
 #define LEX_IS_LINE_SEPARATOR		3
@@ -93,23 +89,25 @@ static const char symbol_chars[] =
 #define IS_LINE_COMMENT(c)		(lex[c] == LEX_IS_LINE_COMMENT_START)
 #define	IS_NEWLINE(c)			(lex[c] == LEX_IS_NEWLINE)
 
-static int process_escape (int);
-
-/* FIXME-soon: The entire lexer/parser thingy should be
-   built statically at compile time rather than dynamically
-   each and every time the assembler is run.  xoxorich.  */
+static char lex[256] = {
+  [' ']  = LEX_IS_WHITESPACE,
+  ['\t'] = LEX_IS_WHITESPACE,
+  ['\r'] = LEX_IS_WHITESPACE,
+  ['\n'] = LEX_IS_NEWLINE,
+  [':']  = LEX_IS_COLON,
+  ['$']  = LEX_IS_SYMBOL_COMPONENT,
+  ['.']  = LEX_IS_SYMBOL_COMPONENT,
+  ['_']  = LEX_IS_SYMBOL_COMPONENT,
+  ['A' ... 'Z'] = LEX_IS_SYMBOL_COMPONENT,
+  ['a' ... 'z'] = LEX_IS_SYMBOL_COMPONENT,
+  ['0' ... '9'] = LEX_IS_SYMBOL_COMPONENT,
+  [128 ... 255] = LEX_IS_SYMBOL_COMPONENT,
+};
 
 void
 do_scrub_begin (int m68k_mri ATTRIBUTE_UNUSED)
 {
   const char *p;
-  int c;
-
-  lex[' '] = LEX_IS_WHITESPACE;
-  lex['\t'] = LEX_IS_WHITESPACE;
-  lex['\r'] = LEX_IS_WHITESPACE;
-  lex['\n'] = LEX_IS_NEWLINE;
-  lex[':'] = LEX_IS_COLON;
 
 #ifdef TC_M68K
   scrub_m68k_mri = m68k_mri;
@@ -133,11 +131,6 @@ do_scrub_begin (int m68k_mri ATTRIBUTE_U
 
   /* Note that these override the previous defaults, e.g. if ';' is a
      comment char, then it isn't a line separator.  */
-  for (p = symbol_chars; *p; ++p)
-    lex[(unsigned char) *p] = LEX_IS_SYMBOL_COMPONENT;
-
-  for (c = 128; c < 256; ++c)
-    lex[c] = LEX_IS_SYMBOL_COMPONENT;
 
 #ifdef tc_symbol_chars
   /* This macro permits the processor to specify all characters which