2 ## --------------------------------------------------------------------------
4 ## Copyright 1996-2019 The NASM Authors - All Rights Reserved
5 ## See the file AUTHORS included with the NASM distribution for
6 ## the specific copyright holders.
8 ## Redistribution and use in source and binary forms, with or without
9 ## modification, are permitted provided that the following
10 ## conditions are met:
12 ## * Redistributions of source code must retain the above copyright
13 ## notice, this list of conditions and the following disclaimer.
14 ## * Redistributions in binary form must reproduce the above
15 ## copyright notice, this list of conditions and the following
16 ## disclaimer in the documentation and/or other materials provided
17 ## with the distribution.
19 ## THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND
20 ## CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES,
21 ## INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
22 ## MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
23 ## DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
24 ## CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
25 ## SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
26 ## NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
27 ## LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
28 ## HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
29 ## CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
30 ## OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE,
31 ## EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
33 ## --------------------------------------------------------------------------
36 # Produce pptok.c, pptok.h and pptok.ph from pptok.dat
41 my($what, $in, $out) = @ARGV;
46 open(IN
, '<', $in) or die "$0: cannot open: $in\n";
47 while (defined($line = <IN
>)) {
48 $line =~ s/\r?\n$//; # Remove trailing \r\n or \n
49 $line =~ s/^\s+//; # Remove leading whitespace
50 $line =~ s/\s*\#.*$//; # Remove comments and trailing whitespace
51 next if ($line eq '');
53 if ($line =~ /^\%(.*)\*$/) {
56 } elsif ($line =~ /^\%(.*\!.*)$/) {
57 # Directive with case insensitity "i" option
58 # Mnemonic: ! is "upside down i"
60 } elsif ($line =~ /^\%(.*)$/) {
63 } elsif ($line =~ /^\*(.*)$/) {
70 # Always sort %if first
71 @cctok = sort { $a eq 'if' ?
-1 : $b eq 'if' ?
1 : $a cmp $b } @cctok;
74 @ppitok = sort @ppitok;
76 # Generate the expanded list including conditionals. The conditionals
77 # are at the beginning, padded to a power of 2, with the inverses
78 # following each group; this allows a simple mask to pick out the condition,
79 # polarity, and directive type.
81 while ((scalar @cond) & (scalar @cond)-1) {
82 push(@cond, sprintf("_COND_%d", scalar @cond));
86 foreach $ct (@cctok) {
88 push(@cptok, $ct.$cc);
91 push(@cptok, $ct.'n'.$cc);
94 $first_uncond = scalar @cptok;
95 @pptok = (@cptok, @pptok);
97 # Generate the list of case-specific tokens; these are in pairs
98 # with the -i- variant following the plain variant
99 if (scalar(@pptok) & 1) {
100 push(@pptok, 'CASE_PAD');
103 $first_itoken = scalar @pptok;
104 foreach $it (@ppitok) {
105 (my $at = $it) =~ s/\!//;
106 (my $bt = $it) =~ s/\!/i/;
108 push(@pptok, $at, $bt);
111 open(OUT
, '>', $out) or die "$0: cannot open: $out\n";
117 print OUT
"/* Automatically generated from $in by $0 */\n";
118 print OUT
"/* Do not edit */\n";
121 print OUT
"enum preproc_token {\n";
123 foreach $pt (@pptok) {
125 printf OUT
" %-24s = %3d,\n", "PP_\U$pt\E", $n;
129 printf OUT
" %-24s = %3d\n", 'PP_INVALID', -1;
133 printf OUT
"#define PP_COND(x) ((x) & 0x%x)\n",
135 printf OUT
"#define PP_IS_COND(x) ((unsigned int)(x) < PP_%s)\n",
136 uc($pptok[$first_uncond]);
137 printf OUT
"#define PP_COND_NEGATIVE(x) (!!((x) & 0x%x))\n", scalar(@cond);
139 printf OUT
"#define PP_HAS_CASE(x) ((x) >= PP_%s)\n",
140 uc($pptok[$first_itoken]);
141 print OUT
"#define PP_INSENSITIVE(x) ((x) & 1)\n";
144 foreach $ct (@cctok) {
145 print OUT
"#define CASE_PP_\U$ct\E";
147 foreach $cc (@cond) {
148 print OUT
"$pref\tcase PP_\U${ct}${cc}\E";
151 foreach $cc (@cond) {
152 print OUT
"$pref\tcase PP_\U${ct}N${cc}\E";
155 print OUT
"\n"; # No colon or newline on the last one
163 print OUT
"/* Automatically generated from $in by $0 */\n";
164 print OUT
"/* Do not edit */\n";
171 foreach $pt (@pptok) {
172 # Upper case characters signify internal use tokens only
173 if (defined($pt) && $pt !~ /[A-Z]/) {
174 $tokens{'%'.$pt} = $n;
175 if ($pt =~ /[\@\[\]\\_]/) {
176 # Fail on characters which look like upper-case letters
177 # to the quick-and-dirty downcasing in the prehash
179 die "$in: invalid character in token: $pt";
185 my @hashinfo = gen_perfect_hash
(\
%tokens);
187 die "$0: no hash found\n";
191 verify_hash_table
(\
%tokens, \
@hashinfo);
193 ($n, $sv, $g) = @hashinfo;
194 die if ($n & ($n-1));
196 print OUT
"#include \"compiler.h\"\n";
197 print OUT
"#include \"nctype.h\"\n";
198 print OUT
"#include \"nasmlib.h\"\n";
199 print OUT
"#include \"hashtbl.h\"\n";
200 print OUT
"#include \"preproc.h\"\n";
203 # Note that this is global.
204 printf OUT
"const char * const pp_directives[%d] = {\n", scalar(@pptok);
205 foreach $d (@pptok) {
206 if (defined($d) && $d !~ /[A-Z]/) {
207 print OUT
" \"%$d\",\n";
209 print OUT
" NULL,\n";
214 printf OUT
"const uint8_t pp_directives_len[%d] = {\n", scalar(@pptok);
215 foreach $d (@pptok) {
216 printf OUT
" %d,\n", defined($d) ?
length($d)+1 : 0;
220 print OUT
"enum preproc_token pp_token_hash(const char *token)\n";
223 # Put a large value in unused slots. This makes it extremely unlikely
224 # that any combination that involves unused slot will pass the range test.
225 # This speeds up rejection of unrecognized tokens, i.e. identifiers.
226 print OUT
"#define UNUSED_HASH_ENTRY (65535/3)\n";
228 print OUT
" static const int16_t hash1[$n] = {\n";
229 for ($i = 0; $i < $n; $i++) {
230 my $h = ${$g}[$i*2+0];
231 print OUT
" ", defined($h) ?
$h : 'UNUSED_HASH_ENTRY', ",\n";
235 print OUT
" static const int16_t hash2[$n] = {\n";
236 for ($i = 0; $i < $n; $i++) {
237 my $h = ${$g}[$i*2+1];
238 print OUT
" ", defined($h) ?
$h : 'UNUSED_HASH_ENTRY', ",\n";
242 print OUT
" uint32_t k1, k2;\n";
243 print OUT
" uint64_t crc;\n";
244 # For correct overflow behavior, "ix" should be unsigned of the same
245 # width as the hash arrays.
246 print OUT
" uint16_t ix;\n";
249 printf OUT
" crc = crc64i(UINT64_C(0x%08x%08x), token);\n",
251 print OUT
" k1 = (uint32_t)crc;\n";
252 print OUT
" k2 = (uint32_t)(crc >> 32);\n";
254 printf OUT
" ix = hash1[k1 & 0x%x] + hash2[k2 & 0x%x];\n", $n-1, $n-1;
255 printf OUT
" if (ix >= %d)\n", scalar(@pptok);
256 print OUT
" return PP_INVALID;\n";
259 print OUT
" if (!pp_directives[ix] || nasm_stricmp(pp_directives[ix], token))\n";
260 print OUT
" return PP_INVALID;\n";
262 print OUT
" return ix;\n";
270 print OUT
"# Automatically generated from $in by $0\n";
271 print OUT
"# Do not edit\n";
274 print OUT
"%pptok_hash = (\n";
276 foreach $tok (@pptok) {
278 printf OUT
" '%%%s' => %d,\n", $tok, $n;