use strict;
use Getopt::Std;
my @orig_ARGV = @ARGV;
+our $VERSION = '0.30';
# These may get re-ordered.
# RAW is a do_now as inserted by &enter
eval "\@ARGV = map(glob(\$_),\@ARGV)" if ($^O eq 'MSWin32');
my %opt;
-getopts('qOo:f:n:',\%opt);
+# I think these are:
+# -Q to disable the duplicate codepoint test
+# -S make mapping errors fatal
+# -q to remove comments written to output files
+# -O to enable the (brute force) substring optimiser
+# -o <output> to specify the output file name (else it's the first arg)
+# -f <inlist> to give a file with a list of input files (else use the args)
+# -n <name> to name the encoding (else use the basename of the input file.
+getopts('SQqOo:f:n:',\%opt);
+
+# This really should go first, else the die here causes empty (non-erroneous)
+# output files to be written.
+my @encfiles;
+if (exists $opt{'f'}) {
+ # -F is followed by name of file containing list of filenames
+ my $flist = $opt{'f'};
+ open(FLIST,$flist) || die "Cannot open $flist:$!";
+ chomp(@encfiles = <FLIST>);
+ close(FLIST);
+} else {
+ @encfiles = @ARGV;
+}
+
my $cname = (exists $opt{'o'}) ? $opt{'o'} : shift(@ARGV);
chmod(0666,$cname) if -f $cname && !-w $cname;
open(C,">$cname") || die "Cannot open $cname:$!";
-
my $dname = $cname;
-$dname =~ s/(\.[^\.]*)?$/_def.h/;
+my $hname = $cname;
my ($doC,$doEnc,$doUcm,$doPet);
if ($cname =~ /\.(c|xs)$/)
{
$doC = 1;
+ $dname =~ s/(\.[^\.]*)?$/_def.h/;
chmod(0666,$dname) if -f $cname && !-w $dname;
open(D,">$dname") || die "Cannot open $dname:$!";
- my $hname = $cname;
$hname =~ s/(\.[^\.]*)?$/.h/;
chmod(0666,$hname) if -f $cname && !-w $hname;
open(H,">$hname") || die "Cannot open $hname:$!";
$doPet = 1;
}
-my @encfiles;
-if (exists $opt{'f'})
- {
- # -F is followed by name of file containing list of filenames
- my $flist = $opt{'f'};
- open(FLIST,$flist) || die "Cannot open $flist:$!";
- chomp(@encfiles = <FLIST>);
- close(FLIST);
- }
-else
- {
- @encfiles = @ARGV;
- }
-
my %encoding;
my %strings;
my $saved = 0;
print C "#include \"$dname\"\n";
print C "}\n";
}
- close(D);
- close(H);
+ # Close in void context is bad, m'kay
+ close(D) or warn "Error closing '$dname': $!";
+ close(H) or warn "Error closing '$hname': $!";
+
+ my $perc_saved = $strings/($strings + $saved) * 100;
+ my $perc_subsaved = $strings/($strings + $subsave) * 100;
printf STDERR "%d bytes in string tables\n",$strings;
- printf STDERR "%d bytes (%.3g%%) saved spotting duplicates\n",$saved,100*$saved/$strings if $saved;
- printf STDERR "%d bytes (%.3g%%) saved using substrings\n",$subsave,100*$subsave/$strings if $subsave;
+ printf STDERR "%d bytes (%.3g%%) saved spotting duplicates\n",
+ $saved, $perc_saved if $saved;
+ printf STDERR "%d bytes (%.3g%%) saved using substrings\n",
+ $subsave, $perc_subsaved if $subsave;
}
elsif ($doEnc)
{
}
}
-close(C);
-
+# writing half meg files and then not checking to see if you just filled the
+# disk is bad, m'kay
+close(C) or die "Error closing '$cname': $!";
+# End of the main program.
sub compile_ucm
{
$encoding{$name} = [$e2u,$u2e,$erep,$min_el,$max_el];
}
+
+
sub compile_enc
{
my ($fh,$name) = @_;
my $v = hex($def);
$rep = &$type_func($v & 0xFF, ($v >> 8) & 0xffe);
}
- my %seen;
+ my $errors;
+ my $seen;
+ # use -Q to silence the seen test. Makefile.PL uses this by default.
+ $seen = {} unless $opt{Q};
do
{
my $line = <$fh>;
{
# So why is it 1% faster to leave the my here?
my $line = <$fh>;
- die "Line should be exactly 65 characters long including newline"
- unless length ($line) == 65;
+ $line =~ s/\r\n$/\n/;
+ die "$.:${line}Line should be exactly 65 characters long including
+ newline (".length($line).")" unless length ($line) == 65;
# Split line into groups of 4 hex digits, convert groups to ints
# This takes 65.35
# map {hex $_} $line =~ /(....)/g
$max_el = $el if $el > $max_el;
$min_el = $el if $el < $min_el;
my $uch = encode_U($val);
- # We don't need to read this quickly, so storing it as a scalar,
- # rather than 3 (anon array, plus the 2 scalars it holds) saves
- # RAM and may make us faster on low RAM systems. [see __END__]
- if (exists $seen{$uch})
- {
- warn sprintf("U%04X is %02X%02X and %04X\n",
- $val,$page,$ch,$seen{$uch});
- }
- else
- {
- $seen{$uch} = $page << 16 | $ch;
- }
+ if ($seen) {
+ # We're doing the test.
+ # We don't need to read this quickly, so storing it as a scalar,
+ # rather than 3 (anon array, plus the 2 scalars it holds) saves
+ # RAM and may make us faster on low RAM systems. [see __END__]
+ if (exists $seen->{$uch})
+ {
+ warn sprintf("U%04X is %02X%02X and %04X\n",
+ $val,$page,$ch,$seen->{$uch});
+ $errors++;
+ }
+ else
+ {
+ $seen->{$uch} = $page << 8 | $ch;
+ }
+ }
# Passing 2 extra args each time is 3.6% slower!
# Even with having to add $fallback ||= 0 later
enter_fb0($e2u,$ech,$uch);
} while --$pages;
die "\$min_el=$min_el, \$max_el=$max_el - seems we read no lines"
if $min_el > $max_el;
+ die "$errors mapping conflicts\n" if ($errors && $opt{'S'});
$encoding{$name} = [$e2u,$u2e,$rep,$min_el,$max_el];
}
sub output_ucm_page
{
- my ($cmap,$a,$t,$pre) = @_;
- # warn sprintf("Page %x\n",$pre);
- foreach my $b (sort keys %$t)
- {
- die "Changed - fix me for new structure";
- my ($s,$e,$out,$n,$end,$l,$fb) = @{$t->{$b}};
- die "oops $s $e" unless $s eq $e;
- my $u = ord($s);
- if ($n != $a && $n != $t)
- {
- output_ucm_page($cmap,$a,$n,(($pre|($u &0x3F)) << 6)&0xFFFF);
- }
- elsif (length($out))
- {
- if ($pre)
- {
- $u = $pre|($u &0x3f);
- }
- my $s = sprintf "<U%04X> ",$u;
- foreach my $c (split(//,$out))
- {
- $s .= sprintf "\\x%02X",ord($c);
+ my ($cmap,$a,$t,$pre) = @_;
+ # warn sprintf("Page %x\n",$pre);
+ my $raw = $t->{Raw};
+ foreach my $key (sort keys %$raw) {
+ # RAW_NEXT => 0,
+ # RAW_IN_LEN => 1,
+ # RAW_OUT_BYTES => 2,
+ # RAW_FALLBACK => 3,
+ my ($next, $in_len, $out_bytes, $fallback) = @{$raw->{$key}};
+ my $u = ord $key;
+ $fallback ||= 0;
+
+ if ($next != $a && $next != $t) {
+ output_ucm_page($cmap,$a,$next,(($pre|($u &0x3F)) << 6)&0xFFFF);
+ } elsif (length $out_bytes) {
+ if ($pre) {
+ $u = $pre|($u &0x3f);
}
- $s .= sprintf " |%d # %s\n",($fb ? 1 : 0),$uname[$u];
- push(@$cmap,$s);
- }
- else
- {
- warn join(',',@{$t->{$b}},$a,$t);
+ my $s = sprintf "<U%04X> ",$u;
+ #foreach my $c (split(//,$out_bytes)) {
+ # $s .= sprintf "\\x%02X",ord($c);
+ #}
+ # 9.5% faster changing that loop to this:
+ $s .= sprintf +("\\x%02X" x length $out_bytes), unpack "C*", $out_bytes;
+ $s .= sprintf " |%d # %s\n",($fallback ? 1 : 0),$uname[$u];
+ push(@$cmap,$s);
+ } else {
+ warn join(',',$u, @{$raw->{$key}},$a,$t);
}
}
}