mirror of
git://gcc.gnu.org/git/gcc.git
synced 2024-12-30 15:25:49 +08:00
f9427d1704
* scripts/encodings.pl: New file. * Makefile.in: Rebuilt. * Makefile.am (convert_source_files): Added IOConverter.java. * gnu/gcj/convert/UnicodeToBytes.java (UnicodeToBytes): Extend IOConverter. (getDefaultDecodingClass): Canonicalize default encoding name. (getEncoder): Likewise. * gnu/gcj/convert/BytesToUnicode.java (BytesToUnicode): Extend IOConverter. (getDefaultDecodingClass): Canonicalize default encoding name. (getDecoder): Likewise. * gnu/gcj/convert/IOConverter.java: New file. From-SVN: r35432
63 lines
1.2 KiB
Perl
63 lines
1.2 KiB
Perl
# encodings.pl - Download IANA text and compute alias list.
|
|
# Assumes you are running this program from gnu/gcj/convert/.
|
|
# Output suitable for direct inclusion in IOConverter.java.
|
|
|
|
# Map IANA canonical names onto our canonical names.
|
|
%map = (
|
|
'ISO_8859-1:1987' => '8859_1',
|
|
'UTF-8' => 'UTF8',
|
|
'Shift_JIS' => 'SJIS',
|
|
'Extended_UNIX_Code_Packed_Format_for_Japanese' => 'EUCJIS'
|
|
);
|
|
|
|
if ($ARGV[0] eq '')
|
|
{
|
|
$file = 'character-sets';
|
|
if (! -f $file)
|
|
{
|
|
# Too painful to figure out how to get Perl to do it.
|
|
system 'wget -o .wget-log http://www.isi.edu/in-notes/iana/assignments/character-sets';
|
|
}
|
|
}
|
|
else
|
|
{
|
|
$file = $ARGV[0];
|
|
}
|
|
|
|
open (INPUT, "< $file") || die "couldn't open $file: $!";
|
|
|
|
$body = 0;
|
|
$current = '';
|
|
while (<INPUT>)
|
|
{
|
|
chop;
|
|
$body = 1 if /^Name:/;
|
|
next unless $body;
|
|
|
|
if (/^$/)
|
|
{
|
|
$current = '';
|
|
next;
|
|
}
|
|
|
|
($type, $name) = split (/\s+/);
|
|
if ($type eq 'Name:')
|
|
{
|
|
$current = $map{$name};
|
|
if ($current)
|
|
{
|
|
print " hash.put (\"$name\", \"$current\");\n";
|
|
}
|
|
}
|
|
elsif ($type eq 'Alias:')
|
|
{
|
|
# The IANA list has some ugliness.
|
|
if ($name ne '' && $name ne 'NONE' && $current)
|
|
{
|
|
print " hash.put (\"$name\", \"$current\");\n";
|
|
}
|
|
}
|
|
}
|
|
|
|
close (INPUT);
|