pptok.c: quick-and-dirty downcasing during prehashing

Speed up pptok.c by just doing |= 0x20 instead of calling tolower() for
every character during prehashing.  This is good enough for our needs,
since we don't have any tokens containing the characters @ [ \ ] _ nor
any high-bit characters (in which case we'd have to worry about multibyte
anyway.)

1 files changed, 7 insertions, 1 deletions

diff --git a/pptok.pl b/pptok.pl
index 99efc38b..537705c0 100755
--- a/pptok.pl
+++ b/pptok.pl
@@ -115,6 +115,12 @@ if ($what eq 'c') {
     foreach $pt (@pptok) {
 	if (defined($pt)) {
 	    $tokens{'%'.$pt} = $n;
+	    if ($pt =~ /[\@\[\]\\_]/) {
+		# Fail on characters which look like upper-case letters
+		# to the quick-and-dirty downcasing in the prehash
+		# (see below)
+		die "$in: invalid character in token: $pt";
+	    }
 	}
 	$n++;
     }
@@ -183,7 +189,7 @@ if ($what eq 'c') {
     print OUT  "\n";
 
     print OUT  "    while ((c = *p++) != 0) {\n";
-    print OUT  "        c = tolower(c);\n";
+    print OUT  "        c |= 0x20; /* convert to lower case */\n";
     printf OUT "        uint32_t kn1 = rot(k1,%2d) - rot(k2,%2d) + c;\n", ${$sv}[0], ${$sv}[1];
     printf OUT "        uint32_t kn2 = rot(k2,%2d) - rot(k1,%2d) + c;\n", ${$sv}[2], ${$sv}[3];
     print OUT  "        k1 = kn1; k2 = kn2;\n";