X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=blobdiff_plain;f=regcomp.pl;h=7fdbd1303fb46028a27e524ab532ef568a23cace;hb=482aa6ffeb230a1cea9d05e9eb425b3d7fc09217;hp=2e84604b5f988b070e107c085e755a98988ec475;hpb=6bda09f9db748451f9bb2b0d8c798ce595a6609c;p=p5sagit%2Fp5-mst-13.2.git

diff --git a/regcomp.pl b/regcomp.pl
index 2e84604..7fdbd13 100644
--- a/regcomp.pl
+++ b/regcomp.pl
@@ -1,3 +1,18 @@
+#!/usr/bin/perl
+# 
+# Regenerate (overwriting only if changed):
+#
+#    regnodes.h
+#
+# from information stored in
+#
+#    regcomp.sym
+#    regexp.h
+#
+# Accepts the standard regen_lib -q and -v args.
+#
+# This script is normally invoked from regen.pl.
+
 BEGIN {
     # Get function prototypes
     require 'regen_lib.pl';
@@ -48,34 +63,29 @@ while (<DESC>) {
                     $ind++;
                     $name[$ind]="$real$suffix";
                     $type[$ind]=$type;
-                    $rest[$ind]="Regmatch state for $type";
+                    $rest[$ind]="state for $type";
                 }
             }
         }
         
     }
 }
-my ($width,$rwidth,$twidth)=(0,0,0);
-for (1..@name) {
-    $width=length($name[$_]) if $name[$_] and $width<length($name[$_]);
-    $twidth=length($type[$_]) if $type[$_] and $twidth<length($type[$_]);
-    $rwidth=$width if $_ == $lastregop;
-}
+# use fixed width to keep the diffs between regcomp.pl recompiles
+# as small as possible.
+my ($width,$rwidth,$twidth)=(22,12,9);
 $lastregop ||= $ind;
 my $tot = $ind;
 close DESC;
 die "Too many regexp/state opcodes! Maximum is 256, but there are $lastregop in file!"
     if $lastregop>256;
 
-my $tmp_h = 'tmp_reg.h';
+my $tmp_h = 'regnodes.h-new';
 
 unlink $tmp_h if -f $tmp_h;
 
-open OUT, ">$tmp_h";
-#*OUT=\*STDOUT;
-binmode OUT;
+my $out = safer_open($tmp_h);
 
-printf OUT <<EOP,
+printf $out <<EOP,
 /* -*- buffer-read-only: t -*-
    !!!!!!!   DO NOT EDIT THIS FILE   !!!!!!!
    This file is built by regcomp.pl from regcomp.sym.
@@ -92,16 +102,19 @@ EOP
     -$width, REGMATCH_STATE_MAX => $tot - 1
 ;
 
-$ind = 0;
-while (++$ind <= $tot) {
+
+for ($ind=1; $ind <= $lastregop ; $ind++) {
   my $oind = $ind - 1;
-  printf OUT "#define\t%*s\t%d\t/* %#04x %s */\n",
+  printf $out "#define\t%*s\t%d\t/* %#04x %s */\n",
     -$width, $name[$ind], $ind-1, $ind-1, $rest[$ind];
-  print OUT "\n\t/* ------------ States ------------- */\n\n"
-    if $ind == $lastregop and $lastregop != $tot;
+}
+print $out "\t/* ------------ States ------------- */\n";
+for ( ; $ind <= $tot ; $ind++) {
+  printf $out "#define\t%*s\t(REGNODE_MAX + %d)\t/* %s */\n",
+    -$width, $name[$ind], $ind - $lastregop, $rest[$ind];
 }
 
-print OUT <<EOP;
+print $out <<EOP;
 
 /* PL_regkind[] What type of regop or state is this. */
 
@@ -113,13 +126,13 @@ EOP
 
 $ind = 0;
 while (++$ind <= $tot) {
-  printf OUT "\t%*s\t/* %*s */\n",
+  printf $out "\t%*s\t/* %*s */\n",
              -1-$twidth, "$type[$ind],", -$width, $name[$ind];
-  print OUT "\t/* ------------ States ------------- */\n"
+  print $out "\t/* ------------ States ------------- */\n"
     if $ind == $lastregop and $lastregop != $tot;
 }
 
-print OUT <<EOP;
+print $out <<EOP;
 };
 #endif
 
@@ -134,11 +147,11 @@ while (++$ind <= $lastregop) {
   my $size = 0;
   $size = "EXTRA_SIZE(struct regnode_$args[$ind])" if $args[$ind];
   
-  printf OUT "\t%*s\t/* %*s */\n",
+  printf $out "\t%*s\t/* %*s */\n",
 	-37, "$size,",-$rwidth,$name[$ind];
 }
 
-print OUT <<EOP;
+print $out <<EOP;
 };
 
 /* reg_off_by_arg[] - Which argument holds the offset to the next node */
@@ -150,41 +163,81 @@ $ind = 0;
 while (++$ind <= $lastregop) {
   my $size = $longj[$ind] || 0;
 
-  printf OUT "\t%d,\t/* %*s */\n",
+  printf $out "\t%d,\t/* %*s */\n",
 	$size, -$rwidth, $name[$ind]
 }
 
-print OUT <<EOP;
+print $out <<EOP;
 };
 
+#endif /* REG_COMP_C */
+
 /* reg_name[] - Opcode/state names in string form, for debugging */
 
-#ifdef DEBUGGING
-const char * reg_name[] = {
+#ifndef DOINIT
+EXTCONST char * PL_reg_name[];
+#else
+EXTCONST char * const PL_reg_name[] = {
 EOP
 
 $ind = 0;
+my $ofs = 1;
+my $sym = "";
 while (++$ind <= $tot) {
   my $size = $longj[$ind] || 0;
 
-  printf OUT "\t%*s\t/* %#04x */\n",
-	-3-$width,qq("$name[$ind]",),$ind-1;
-  print OUT "\t/* ------------ States ------------- */\n"
-    if $ind == $lastregop and $lastregop != $tot;
+  printf $out "\t%*s\t/* $sym%#04x */\n",
+	-3-$width,qq("$name[$ind]",), $ind - $ofs;
+  if ($ind == $lastregop and $lastregop != $tot) {
+    print $out "\t/* ------------ States ------------- */\n";
+    $ofs = $lastregop;
+    $sym = 'REGNODE_MAX +';
+  }
+    
 }
 
-print OUT <<EOP;
+print $out <<EOP;
 };
-#endif /* DEBUGGING */
+#endif /* DOINIT */
+
+/* PL_reg_extflags_name[] - Opcode/state names in string form, for debugging */
+
+#ifndef DOINIT
+EXTCONST char * PL_reg_extflags_name[];
 #else
-#ifdef DEBUGGING
-extern const char * reg_name[];
-#endif
-#endif /* REG_COMP_C */
+EXTCONST char * const PL_reg_extflags_name[] = {
+EOP
+
+open my $fh,"<","regexp.h" or die "Can't read regexp.h: $!";
+my %rxfv;
+my $val = 0;
+my %reverse;
+while (<$fh>) {
+    if (/#define\s+(RXf_\w+)\s+(0x[A-F\d]+)/i) {
+	my $newval = eval $2;
+	if($val & $newval) {
+	    die sprintf "Both $1 and $reverse{$newval} use %08X", $newval;
+	}
+        $val|=$newval;
+        $rxfv{$1}= $newval;
+	$reverse{$newval} = $1;
+    }
+}    
+my %vrxf=reverse %rxfv;
+printf $out "\t/* Bits in extflags defined: %032b */\n",$val;
+for (0..31) {
+    my $n=$vrxf{2**$_}||"UNUSED_BIT_$_";
+    $n=~s/^RXf_(PMf_)?//;
+    printf $out qq(\t%-20s/* 0x%08x */\n), 
+        qq("$n",),2**$_;
+}  
+ 
+print $out <<EOP;
+};
+#endif /* DOINIT */
 
 /* ex: set ro: */
 EOP
+safer_close($out);
 
-close OUT or die "close $tmp_h: $!";
-
-safer_rename $tmp_h, 'regnodes.h';
+rename_if_different $tmp_h, 'regnodes.h';