Last active
September 10, 2016 07:47
-
-
Save ggl/205c14e4271a6b916870 to your computer and use it in GitHub Desktop.
Replace Turkish UTF-8 glyphs with Romanian ones
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env perl | |
use strict; | |
use warnings; | |
if (@ARGV < 1) { | |
print "usage: $0 <file>\n"; | |
exit 0; | |
}; | |
my %arg = ( | |
fin => $ARGV[0], | |
fout => $ARGV[1] ? $ARGV[1] : $ARGV[0].'.out' | |
); | |
my %fixes = ( | |
"\x{015F}" => "\x{219}", | |
"\x{15E}" => "\x{218}", | |
"\x{162}" => "\x{21A}", | |
"\x{163}" => "\x{21B}", | |
"\x{E3}" => "\x{103}", | |
"\x{C3}" => "\x{102}" | |
); | |
open(my $in, "<:encoding(UTF-8)", $arg{fin}) or die "Cannot open file $arg{fin}: $!"; | |
open(my $out, ">:encoding(UTF-8)", $arg{fout}) or die "Cannot open file $arg{fout}: $!"; | |
while (my $line = <$in>) { | |
if (defined $line) { | |
foreach my $key (keys %fixes) { | |
$line =~ s/$key/$fixes{$key}/g; | |
}; | |
print $out $line; | |
} | |
} | |
close($in); | |
close($out); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment