Encode/IO doc tweaks.

[p5sagit/p5-mst-13.2.git] / ext / Encode / compile

diff --git a/ext/Encode/compile b/ext/Encode/compile
index b1d68a2..d0611f7 100755 (executable)
--- a/ext/Encode/compile
+++ b/ext/Encode/compile
@@ -1,27 +1,23 @@
 #!../../perl -w
-BEGIN { @INC = '../../lib' };
+BEGIN {
+    @INC = '../../lib';
+    $ENV{PATH} .= ';../..' if $^O eq 'MSWin32';
+}
 use strict;
 use Getopt::Std;
 my @orig_ARGV = @ARGV;
 my $perforce  = '$Id$';
 
-
 sub encode_U
 {
  # UTF-8 encode long hand - only covers part of perl's range
  my $uv = shift;
- if ($uv < 0x80)
-  {
-   return chr($uv)
-  }
- if ($uv < 0x800)
-  {
-   return chr(($uv >> 6)        | 0xC0).
-          chr(($uv & 0x3F)      | 0x80);
-  }
- return chr(($uv >> 12)         | 0xE0).
-        chr((($uv >> 6) & 0x3F) | 0x80).
-        chr(($uv & 0x3F)        | 0x80);
+ # chr() works in native space so convert value from table
+ # into that space before using chr().
+ my $ch = chr(utf8::unicode_to_native($uv));
+ # Now get core perl to encode that the way it likes.
+ utf8::encode($ch);
+ return $ch;
 }
 
 sub encode_S
@@ -140,7 +136,7 @@ sub cmp_name
 foreach my $enc (sort cmp_name @encfiles)
  {
   my ($name,$sfx) = $enc =~ /^.*?([\w-]+)\.(enc|ucm)$/;
-  $name = delete $opt{'n'} if exists $opt{'n'};
+  $name = $opt{'n'} if exists $opt{'n'};
   if (open(E,$enc))
    {
     if ($sfx eq 'enc')
@@ -238,7 +234,7 @@ sub compile_ucm
   }
  else
   {
-   # $name = lc($cs);
+   $name = $cs unless exists $opt{'n'};
   }
  my $erep;
  my $urep;
@@ -251,7 +247,7 @@ sub compile_ucm
    push(@byte,$1) while $attr{'subchar'} =~ /\G\\x([0-9a-f]+)/icg;
    $erep = join('',map(chr(hex($_)),@byte));
   }
- warn "Scanning $name ($cs)\n";
+ print "Scanning $name ($cs)\n";
  my $nfb = 0;
  my $hfb = 0;
  while (<$fh>)
@@ -539,9 +535,28 @@ sub decode_U
  my $s = shift;
 }
 
+my @uname;
+sub char_names
+{
+ my $s = do "unicode/Name.pl";
+ pos($s) = 0;
+ while ($s =~ /\G([0-9a-f]+)\t([0-9a-f]*)\t(.*?)\s*\n/igc)
+  {
+   my $name = $3;
+   my $s = hex($1);
+   last if $s >= 0x10000;
+   my $e = length($2) ? hex($2) : $s;
+   for (my $i = $s; $i <= $e; $i++)
+    {
+     $uname[$i] = $name;
+#    print sprintf("U%04X $name\n",$i);
+    }
+  }
+}
+
 sub output_ucm_page
 {
- my ($fh,$a,$t,$pre) = @_;
+ my ($cmap,$a,$t,$pre) = @_;
  # warn sprintf("Page %x\n",$pre);
  foreach my $b (sort keys %$t)
   {
@@ -550,7 +565,7 @@ sub output_ucm_page
    my $u = ord($s);
    if ($n != $a && $n != $t)
     {
-     output_ucm_page($fh,$a,$n,(($pre|($u &0x3F)) << 6)&0xFFFF);
+     output_ucm_page($cmap,$a,$n,(($pre|($u &0x3F)) << 6)&0xFFFF);
     }
    elsif (length($out))
     {
@@ -558,12 +573,13 @@ sub output_ucm_page
       {
        $u = $pre|($u &0x3f);
       }
-     printf $fh "<U%04X> ",$u;
+     my $s = sprintf "<U%04X> ",$u;
      foreach my $c (split(//,$out))
       {
-       printf $fh "\\x%02X",ord($c);
+       $s .= sprintf "\\x%02X",ord($c);
       }
-     printf $fh " |%d\n",($fb ? 1 : 0);
+     $s .= sprintf " |%d # %s\n",($fb ? 1 : 0),$uname[$u];
+     push(@$cmap,$s);
     }
    else
     {
@@ -574,9 +590,10 @@ sub output_ucm_page
 
 sub output_ucm
 {
- my ($fh,$name,$a,$rep,$min_el,$max_el) = @_;
+ my ($fh,$name,$h,$rep,$min_el,$max_el) = @_;
  print $fh "# Written $perforce\n# $0 @orig_ARGV\n" unless $opt{'q'};
  print $fh "<code_set_name> \"$name\"\n";
+ char_names();
  if (defined $min_el)
   {
    print $fh "<mb_cur_min> $min_el\n";
@@ -594,8 +611,13 @@ sub output_ucm
     }
    print $fh "\n";
   }
+ my @cmap;
+ output_ucm_page(\@cmap,$h,$h,0);
  print $fh "#\nCHARMAP\n";
- output_ucm_page($fh,$a,$a,0);
+ foreach my $line (sort { substr($a,8) cmp substr($b,8) } @cmap)
+  {
+   print $fh $line;
+  }
  print $fh "END CHARMAP\n";
 }