/* This is the Assembler Pre-Processor
Copyright 1987, 1990, 1991, 1992, 1993, 1994, 1995, 1996, 1997, 1998,
- 1999, 2000, 2002, 2003
+ 1999, 2000, 2001, 2002, 2003, 2006, 2007
Free Software Foundation, Inc.
This file is part of GAS, the GNU Assembler.
You should have received a copy of the GNU General Public License
along with GAS; see the file COPYING. If not, write to the Free
- Software Foundation, 59 Temple Place - Suite 330, Boston, MA
- 02111-1307, USA. */
+ Software Foundation, 51 Franklin Street - Fifth Floor, Boston, MA
+ 02110-1301, USA. */
/* Modified by Allen Wirfs-Brock, Instantiations Inc 2/90. */
-/* App, the assembler pre-processor. This pre-processor strips out excess
- spaces, turns single-quoted characters into a decimal constant, and turns
- # <number> <filename> <garbage> into a .line <number>\n.file <filename>
- pair. This needs better error-handling. */
+/* App, the assembler pre-processor. This pre-processor strips out
+ excess spaces, turns single-quoted characters into a decimal
+ constant, and turns the # in # <number> <filename> <garbage> into a
+ .linefile. This needs better error-handling. */
-#include <stdio.h>
-#include "as.h" /* For BAD_CASE() only. */
+#include "as.h"
#if (__STDC__ != 1)
#ifndef const
#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 PARAMS ((int));
+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. */
void
-do_scrub_begin (m68k_mri)
- int m68k_mri ATTRIBUTE_UNUSED;
+do_scrub_begin (int m68k_mri ATTRIBUTE_UNUSED)
{
const char *p;
int c;
};
char *
-app_push ()
+app_push (void)
{
register struct app_save *saved;
}
void
-app_pop (arg)
- char *arg;
+app_pop (char *arg)
{
register struct app_save *saved = (struct app_save *) arg;
necessarily true. */
static int
-process_escape (ch)
- int ch;
+process_escape (int ch)
{
switch (ch)
{
This is the way the old code used to work. */
int
-do_scrub_chars (get, tostart, tolen)
- int (*get) PARAMS ((char *, int));
- char *tostart;
- int tolen;
+do_scrub_chars (int (*get) (char *, int), char *tostart, int tolen)
{
char *to = tostart;
char *toend = tostart + tolen;
char *fromend;
int fromlen;
register int ch, ch2 = 0;
+ /* Character that started the string we're working on. */
+ static char quotechar;
/*State 0: beginning of normal line
1: After first whitespace on line (flush more white)
2: After first non-white (opcode) on line (keep 1white)
3: after second white on line (into operands) (flush white)
- 4: after putting out a .line, put out digits
+ 4: after putting out a .linefile, put out digits
5: parsing a string, then go to old-state
6: putting out \ escape in a "d string.
- 7: After putting out a .appfile, put out string.
- 8: After putting out a .appfile string, flush until newline.
+ 7: no longer used
+ 8: no longer used
9: After seeing symbol char in state 3 (keep 1white after symchar)
10: After seeing whitespace in state 9 (keep white before symchar)
11: After seeing a symbol character in state 0 (eg a label definition)
#ifdef DOUBLEBAR_PARALLEL
13: After seeing a vertical bar, looking for a second
vertical bar as a parallel expression separator.
+#endif
+#ifdef TC_IA64
+ 14: After seeing a `(' at state 0, looking for a `)' as
+ predicate.
+ 15: After seeing a `(' at state 1, looking for a `)' as
+ predicate.
+#endif
+#ifdef TC_Z80
+ 16: After seeing an 'a' or an 'A' at the start of a symbol
+ 17: After seeing an 'f' or an 'F' in state 16
#endif
*/
ch = GET ();
if (ch == '"')
{
- UNGET (ch);
- if (scrub_m68k_mri)
- out_string = "\n\tappfile ";
- else
- out_string = "\n\t.appfile ";
- old_state = 7;
- state = -1;
- PUT (*out_string++);
+ quotechar = ch;
+ state = 5;
+ old_state = 3;
+ PUT (ch);
}
else
{
for (s = from; s < fromend; s++)
{
ch = *s;
- /* This condition must be changed if the type of any
- other character can be LEX_IS_STRINGQUOTE. */
if (ch == '\\'
- || ch == '"'
- || ch == '\''
+ || ch == quotechar
|| ch == '\n')
break;
}
ch = GET ();
if (ch == EOF)
{
- as_warn (_("end of file in string; inserted '\"'"));
+ as_warn (_("end of file in string; '%c' inserted"), quotechar);
state = old_state;
UNGET ('\n');
- PUT ('"');
+ PUT (quotechar);
}
- else if (lex[ch] == LEX_IS_STRINGQUOTE)
+ else if (ch == quotechar)
{
state = old_state;
PUT (ch);
continue;
case EOF:
- as_warn (_("end of file in string; '\"' inserted"));
- PUT ('"');
+ as_warn (_("end of file in string; '%c' inserted"), quotechar);
+ PUT (quotechar);
continue;
case '"':
PUT (ch);
continue;
- case 7:
- ch = GET ();
- state = 5;
- old_state = 8;
- if (ch == EOF)
- goto fromeof;
- PUT (ch);
- continue;
-
- case 8:
- do
- ch = GET ();
- while (ch != '\n' && ch != EOF);
- if (ch == EOF)
- goto fromeof;
- state = 0;
- PUT (ch);
- continue;
-
#ifdef DOUBLEBAR_PARALLEL
case 13:
ch = GET ();
state = 1;
PUT ('|');
continue;
+#endif
+#ifdef TC_Z80
+ case 16:
+ /* We have seen an 'a' at the start of a symbol, look for an 'f'. */
+ ch = GET ();
+ if (ch == 'f' || ch == 'F')
+ {
+ state = 17;
+ PUT (ch);
+ }
+ else
+ {
+ state = 9;
+ break;
+ }
+ case 17:
+ /* We have seen "af" at the start of a symbol,
+ a ' here is a part of that symbol. */
+ ch = GET ();
+ state = 9;
+ if (ch == '\'')
+ /* Change to avoid warning about unclosed string. */
+ PUT ('`');
+ else
+ UNGET (ch);
+ break;
#endif
}
/* flushchar: */
ch = GET ();
+#ifdef TC_IA64
+ if (ch == '(' && (state == 0 || state == 1))
+ {
+ state += 14;
+ PUT (ch);
+ continue;
+ }
+ else if (state == 14 || state == 15)
+ {
+ if (ch == ')')
+ {
+ state -= 14;
+ PUT (ch);
+ ch = GET ();
+ }
+ else
+ {
+ PUT (ch);
+ continue;
+ }
+ }
+#endif
+
recycle:
#if defined TC_ARM && defined OBJ_ELF
switch (state)
{
- case 0:
- state++;
- goto recycle; /* Punted leading sp */
case 1:
/* We can arrive here if we leave a leading whitespace
character at the beginning of a line. */
break;
case LEX_IS_STRINGQUOTE:
+ quotechar = ch;
if (state == 10)
{
/* Preserve the whitespace in foo "bar". */
old_state = 4;
state = -1;
if (scrub_m68k_mri)
- out_string = "\tappline ";
+ out_string = "\tlinefile ";
else
- out_string = "\t.appline ";
+ out_string = "\t.linefile ";
PUT (*out_string++);
break;
}
break;
}
+#ifdef TC_Z80
+ /* "af'" is a symbol containing '\''. */
+ if (state == 3 && (ch == 'a' || ch == 'A'))
+ {
+ state = 16;
+ PUT (ch);
+ ch = GET ();
+ if (ch == 'f' || ch == 'F')
+ {
+ state = 17;
+ PUT (ch);
+ break;
+ }
+ else
+ {
+ state = 9;
+ if (!IS_SYMBOL_COMPONENT (ch))
+ {
+ UNGET (ch);
+ break;
+ }
+ }
+ }
+#endif
if (state == 3)
state = 9;
if (len > 0)
{
PUT (ch);
- if (len > 8)
- {
- memcpy (to, from, len);
- to += len;
- from += len;
- }
- else
- {
- switch (len)
- {
- case 8: *to++ = *from++;
- case 7: *to++ = *from++;
- case 6: *to++ = *from++;
- case 5: *to++ = *from++;
- case 4: *to++ = *from++;
- case 3: *to++ = *from++;
- case 2: *to++ = *from++;
- case 1: *to++ = *from++;
- }
- }
+ memcpy (to, from, len);
+ to += len;
+ from += len;
+ if (to >= toend)
+ goto tofull;
ch = GET ();
}
}
/* Some relatively `normal' character. */
if (state == 0)
{
- if (IS_SYMBOL_COMPONENT (ch))
- state = 11; /* Now seeing label definition. */
+ state = 11; /* Now seeing label definition. */
}
else if (state == 1)
{
- if (IS_SYMBOL_COMPONENT (ch))
- state = 2; /* Ditto. */
+ state = 2; /* Ditto. */
}
else if (state == 9)
{