You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
36 lines
842 B
36 lines
842 B
2 months ago
|
#!/usr/bin/perl
|
||
|
|
#
|
||
|
|
# Create Unicode Unaccenting Table
|
||
|
|
# (c) 1997 Martin Mares <mj@atrey.karlin.mff.cuni.cz>
|
||
|
|
#
|
||
|
|
|
||
|
|
open (UNI, "unidata/UnicodeData.txt") || die "No Unicode Data File";
|
||
|
|
while (<UNI>) {
|
||
|
|
chomp;
|
||
|
|
($num,$name,$cat,$_,$_,$exp) = split /;/;
|
||
|
|
if ($cat =~ /^L[ul]$/) { $letter{$num} = 1; }
|
||
|
|
if ($cat =~ /^Mn$/) { $accent{$num} = 1; }
|
||
|
|
}
|
||
|
|
close UNI;
|
||
|
|
|
||
|
|
open (UNI, "unidata/UnicodeData.txt") || die "No Unicode Data File";
|
||
|
|
while (<UNI>) {
|
||
|
|
chomp;
|
||
|
|
($num,$name,$cat,$_,$_,$exp) = split /;/;
|
||
|
|
$num =~ /^....$/ || next;
|
||
|
|
if ($exp ne "") {
|
||
|
|
$exp =~ s/^<.*> *//g;
|
||
|
|
$good = 1;
|
||
|
|
$e = "";
|
||
|
|
foreach $a (split(/\s+/, $exp)) {
|
||
|
|
if ($accent{$a}) { }
|
||
|
|
elsif ($letter{$a}) {
|
||
|
|
if ($e ne "") { $good = 0; }
|
||
|
|
else { $e = $a; }
|
||
|
|
} else { $good = 0; }
|
||
|
|
}
|
||
|
|
if ($good && $e ne "") { print "$num\t0x$e\n"; }
|
||
|
|
}
|
||
|
|
}
|
||
|
|
close UNI;
|