allow idna_props header to be regenerated

add commandline procesing to the idna header generation tool

add make rules to obtain idna source files and convert them into a header
This commit is contained in:
Vincent Sanders 2020-06-22 23:08:03 +01:00
parent 54e06e7d58
commit 567390f59d
3 changed files with 127 additions and 21 deletions

View File

@ -63,6 +63,26 @@ $(TOOLROOT)/convert_image: utils/convert_image.c $(TOOLROOT)/created
# Build too to perform font conversion
#
$(TOOLROOT)/convert_font: utils/convert_font.c $(TOOLROOT)/created
$(VQ)echo "BUILD CC: $@"
$(Q)$(BUILD_CC) $(BUILD_CFLAGS) -o $@ $<
# idna
#
IDNA_UNICODE_MAJOR=11
utils/DerivedJoiningType.txt:
curl -o $@ "https://www.unicode.org/Public/$(IDNA_UNICODE_MAJOR).0.0/ucd/extracted/DerivedJoiningType.txt"
utils/IdnaMappingTable.txt:
curl -o $@ "https://www.unicode.org/Public/idna/$(IDNA_UNICODE_MAJOR).0.0/IdnaMappingTable.txt"
utils/idna-tables-properties.csv:
curl -o $@ "https://www.iana.org/assignments/idna-tables-$(IDNA_UNICODE_MAJOR).0.0/idna-tables-properties.csv"
utils/idna_props.h: utils/DerivedJoiningType.txt utils/idna-tables-properties.csv
$(VQ)echo " IDNA: $@"
$(Q)$(PERL) utils/idna-derived-props-gen.pl -o $@ -p utils/idna-tables-properties.csv -j utils/DerivedJoiningType.txt

View File

@ -16,7 +16,88 @@
# You should have received a copy of the GNU General Public License
# along with this program. If not, see <http://www.gnu.org/licenses/>.
print <<HEADER;
use strict;
use Getopt::Long ();
use Fcntl qw( O_CREAT O_EXCL O_WRONLY O_APPEND O_RDONLY O_WRONLY );
use constant GETOPT_OPTS => qw( auto_abbrev no_getopt_compat bundling );
use constant GETOPT_SPEC =>
qw( output|o=s
properties|p=s
joining|j=s
help|h|? );
# default option values:
my %opt = qw(properties "idna-tables-properties.csv" joining "DerivedJoiningType.txt");
sub usage
{
my @fmt = map { s/::$//; $_ } keys(%{$::{'msgfmt::'}});
print(STDERR <<TXT );
usage:
$0 [-o output-file] -p properties-file -j joining-file
output-file : defaults to standard output
TXT
exit(1);
}
sub output_stream
{
if( $opt{output} )
{
my $ofh;
sysopen( $ofh, $opt{output}, O_CREAT|O_EXCL|O_APPEND|O_WRONLY ) ||
die( "$0: Failed to open output file $opt{output}: $!\n" );
return $ofh;
}
return \*STDOUT;
}
sub input_stream
{
my $stream = $_[0];
if( $opt{$stream} )
{
my $ifh;
sysopen( $ifh, $opt{$stream}, O_RDONLY ) ||
die( "$0: Failed to open input file $stream: $!\n" );
return $ifh;
}
die( "$0: No input file for $stream");
}
sub main
{
my $output;
my $properties;
my $joining;
my $opt_ok;
# option parsing:
Getopt::Long::Configure( GETOPT_OPTS );
$opt_ok = Getopt::Long::GetOptions( \%opt, GETOPT_SPEC );
# double check the options are sane (and we weren't asked for the help)
if( !$opt_ok || $opt{help} )
{
usage();
}
# open the appropriate files
$properties = input_stream("properties");
$joining = input_stream("joining");
$output = output_stream();
print { $output } <<HEADER;
/* This file is generated by idna-derived-props-gen.pl
* DO NOT EDIT BY HAND
*/
@ -53,19 +134,21 @@ typedef struct idna_table {
idna_table idna_derived[] = {
HEADER
open(CSVFILE, "idna-tables-5.2.0-properties.csv");
$line = <CSVFILE>; # discard header line
while($line = <CSVFILE>) {
@items = split(/\,/, $line);
@codepoints = split(/-/, $items[0]);
if($#codepoints == 0) { $codepoints[1] = $codepoints[0]; }
print "\t{ 0x" . $codepoints[0] . ", 0x" . $codepoints[1] . ", .p.property = IDNA_P_" . $items[1] . " },\n";
}
my $line = <$properties>; # discard header line
close(CSVFILE);
while($line = <$properties>) {
my @items = split(/\,/, $line);
my @codepoints = split(/-/, $items[0]);
if($#codepoints == 0) {
$codepoints[1] = $codepoints[0];
}
print { $output } "\t{ 0x" . $codepoints[0] . ", 0x" . $codepoints[1] . ", .p.property = IDNA_P_" . $items[1] . " },\n";
}
print <<HEADER;
close($properties);
print { $output } <<HEADER;
{ 0, 0, .p.property = 0}
};
@ -73,24 +156,27 @@ idna_table idna_joiningtype[] = {
HEADER
open(TXTFILE, "DerivedJoiningType.txt");
while($line = <TXTFILE>) {
while($line = <$joining>) {
chop($line);
if(substr($line, 0, 1) eq '#') {next;}
if(length($line) == 0) {next;}
@items = split(/;/, $line);
@codepoints = split(/\./, $items[0]);
if($#codepoints == 0) { $codepoints[2] = $codepoints[0]; }
print "\t{ 0x" . $codepoints[0] . ", 0x" . $codepoints[2] . ", .p.jt = IDNA_UNICODE_JT_" . substr($items[1], 1, 1) . " },\n";
}
my @items = split(/;/, $line);
my @codepoints = split(/\./, $items[0]);
if($#codepoints == 0) {
$codepoints[2] = $codepoints[0];
}
print { $output } "\t{ 0x" . $codepoints[0] . ", 0x" . $codepoints[2] . ", .p.jt = IDNA_UNICODE_JT_" . substr($items[1], 1, 1) . " },\n";
}
close(TXTFILE);
close($joining);
print <<HEADER;
print { $output } <<HEADER;
{ 0, 0, .p.jt = 0}
};
#endif
HEADER
}
main();