require Config; import Config;
}
use strict;
+use warnings;
use Getopt::Std;
my @orig_ARGV = @ARGV;
-our $VERSION = do { my @r = (q$Revision: 1.26 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
+our $VERSION = do { my @r = (q$Revision: 1.31 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
# These may get re-ordered.
# RAW is a do_now as inserted by &enter
print C "#include <XSUB.h>\n";
print C "#define U8 U8\n";
}
- print C "#include \"encode.h\"\n";
+ print C "#include \"encode.h\"\n\n";
}
elsif ($cname =~ /\.enc$/)
my %encoding;
my %strings;
+my $string_acc;
+my %strings_in_acc;
+
my $saved = 0;
my $subsave = 0;
my $strings = 0;
foreach my $name (sort cmp_name keys %encoding)
{
my ($e2u,$u2e,$erep,$min_el,$max_el) = @{$encoding{$name}};
- output(\*C,$name.'_utf8',$e2u);
- output(\*C,'utf8_'.$name,$u2e);
+ process($name.'_utf8',$e2u);
+ addstrings(\*C,$e2u);
+
+ process('utf8_'.$name,$u2e);
+ addstrings(\*C,$u2e);
+ }
+ outbigstring(\*C,"enctable");
+ foreach my $name (sort cmp_name keys %encoding)
+ {
+ my ($e2u,$u2e,$erep,$min_el,$max_el) = @{$encoding{$name}};
+ outtable(\*C,$e2u, "enctable");
+ outtable(\*C,$u2e, "enctable");
+
# push(@{$encoding{$name}},outstring(\*C,$e2u->{Cname}.'_def',$erep));
}
foreach my $enc (sort cmp_name keys %encoding)
my $sym = "${enc}_encoding";
$sym =~ s/\W+/_/g;
print C "encode_t $sym = \n";
+ # This is to make null encoding work -- dankogai
+ for (my $i = (scalar @info) - 1; $i >= 0; --$i){
+ $info[$i] ||= 1;
+ }
+ # end of null tweak -- dankogai
print C " {",join(',',@info,"{\"$enc\",(const char *)0}"),"};\n\n";
}
}
}
-
-sub outstring
-{
- my ($fh,$name,$s) = @_;
- my $sym = $strings{$s};
- if ($sym)
- {
- $saved += length($s);
- }
- else
- {
- if ($opt{'O'}) {
- foreach my $o (keys %strings)
- {
- next unless (my $i = index($o,$s)) >= 0;
- $sym = $strings{$o};
- # gcc things that 0x0e+0x10 (anything with e+) starts to look like
- # a hexadecimal floating point constant. Silly gcc. Only p
- # introduces a floating point constant. Put the space in to stop it
- # getting confused.
- $sym .= sprintf(" +0x%02x",$i) if ($i);
- $subsave += length($s);
- return $strings{$s} = $sym;
- }
- }
- $strings{$s} = $sym = $name;
- $strings += length($s);
- my $definition = sprintf "static const U8 %s[%d] = { ",$name,length($s);
- # Maybe we should assert that these are all <256.
- $definition .= join(',',unpack "C*",$s);
- # We have a single long line. Split it at convenient commas.
- $definition =~ s/(.{74,77},)/$1\n/g;
- print $fh "$definition };\n\n";
- }
- return $sym;
-}
-
sub process
{
my ($name,$a) = @_;
$a->{'Entries'} = \@ent;
}
-sub outtable
+
+sub addstrings
{
my ($fh,$a) = @_;
my $name = $a->{'Cname'};
foreach my $b (@{$a->{'Entries'}})
{
next unless $b->[AGG_OUT_LEN];
- my $s = $b->[AGG_MIN_IN];
- my $e = $b->[AGG_MAX_IN];
- outstring($fh,sprintf("%s__%02x_%02x",$name,$s,$e),$b->[AGG_OUT_BYTES]);
+ $strings{$b->[AGG_OUT_BYTES]} = undef;
}
if ($a->{'Forward'})
{
- print $fh "\nstatic encpage_t $name\[",scalar(@{$a->{'Entries'}}),"];\n";
+ my $var = $^O eq 'MacOS' ? 'extern' : 'static';
+ print $fh "$var encpage_t $name\[",scalar(@{$a->{'Entries'}}),"];\n";
}
+ $a->{'DoneStrings'} = 1;
+ foreach my $b (@{$a->{'Entries'}})
+ {
+ my ($s,$e,$out,$t,$end,$l) = @$b;
+ addstrings($fh,$t) unless $t->{'DoneStrings'};
+ }
+}
+
+sub outbigstring
+{
+ my ($fh,$name) = @_;
+
+ $string_acc = '';
+
+ # Make the big string in the string accumulator. Longest first, on the hope
+ # that this makes it more likely that we find the short strings later on.
+ # Not sure if it helps sorting strings of the same length lexcically.
+ foreach my $s (sort {length $b <=> length $a || $a cmp $b} keys %strings) {
+ my $index = index $string_acc, $s;
+ if ($index >= 0) {
+ $saved += length($s);
+ $strings_in_acc{$s} = $index;
+ } else {
+ OPTIMISER: {
+ if ($opt{'O'}) {
+ my $sublength = length $s;
+ while (--$sublength > 0) {
+ # progressively lop characters off the end, to see if the start of
+ # the new string overlaps the end of the accumulator.
+ if (substr ($string_acc, -$sublength)
+ eq substr ($s, 0, $sublength)) {
+ $subsave += $sublength;
+ $strings_in_acc{$s} = length ($string_acc) - $sublength;
+ # append the last bit on the end.
+ $string_acc .= substr ($s, $sublength);
+ last OPTIMISER;
+ }
+ # or if the end of the new string overlaps the start of the
+ # accumulator
+ next unless substr ($string_acc, 0, $sublength)
+ eq substr ($s, -$sublength);
+ # well, the last $sublength characters of the accumulator match.
+ # so as we're prepending to the accumulator, need to shift all our
+ # existing offsets forwards
+ $_ += $sublength foreach values %strings_in_acc;
+ $subsave += $sublength;
+ $strings_in_acc{$s} = 0;
+ # append the first bit on the start.
+ $string_acc = substr ($s, 0, -$sublength) . $string_acc;
+ last OPTIMISER;
+ }
+ }
+ # Optimiser (if it ran) found nothing, so just going have to tack the
+ # whole thing on the end.
+ $strings_in_acc{$s} = length $string_acc;
+ $string_acc .= $s;
+ };
+ }
+ }
+
+ $strings = length $string_acc;
+ my $definition = "\nstatic const U8 $name\[$strings] = { " .
+ join(',',unpack "C*",$string_acc);
+ # We have a single long line. Split it at convenient commas.
+ print $fh $1, "\n" while $definition =~ /\G(.{74,77},)/gcs;
+ print $fh substr ($definition, pos $definition), " };\n";
+}
+
+sub findstring {
+ my ($name,$s) = @_;
+ my $offset = $strings_in_acc{$s};
+ die "Can't find string " . join (',',unpack "C*",$s) . " in accumulator"
+ unless defined $offset;
+ "$name + $offset";
+}
+
+sub outtable
+{
+ my ($fh,$a,$bigname) = @_;
+ my $name = $a->{'Cname'};
$a->{'Done'} = 1;
foreach my $b (@{$a->{'Entries'}})
{
my ($s,$e,$out,$t,$end,$l) = @$b;
- outtable($fh,$t) unless $t->{'Done'};
+ outtable($fh,$t,$bigname) unless $t->{'Done'};
}
print $fh "\nstatic encpage_t $name\[",scalar(@{$a->{'Entries'}}),"] = {\n";
foreach my $b (@{$a->{'Entries'}})
{
my ($sc,$ec,$out,$t,$end,$l,$fb) = @$b;
- $end |= 0x80 if $fb;
+ # $end |= 0x80 if $fb; # what the heck was on your mind, Nick? -- Dan
print $fh "{";
if ($l)
{
- printf $fh outstring($fh,'',$out);
+ printf $fh findstring($bigname,$out);
}
else
{
print $fh "};\n";
}
-sub output
-{
- my ($fh,$name,$a) = @_;
- process($name,$a);
- # Sub-tables
- outtable($fh,$a);
-}
-
sub output_enc
{
my ($fh,$name,$a) = @_;
);
sub find_e2x{
- eval { require File::Find };
+ eval { require File::Find; };
my (@inc, %e2x_dir);
for my $inc (@INC){
push @inc, $inc unless $inc eq '.'; #skip current dir
= lstat($_) or return;
-f _ or return;
if (/^.*\.e2x$/o){
+ no warnings 'once';
$e2x_dir{$File::Find::dir} ||= $mtime;
}
return;
eval { require "Encode/$f"; };
$@ and die "Can't require Encode/$f: $@\n";
for my $enc (Encode->encodings()){
+ no warnings 'once';
$in_core{$enc} and next;
$Encode::Config::ExtModule{$enc} and next;
my $mod = "Encode/$f";
Now issue a command all Perl Mongers love:
- $ perl5.7.3 Makefile.PL
+ $ perl Makefile.PL
Writing Makefile for Encode::My
=item 4.