mirror of
https://github.com/nginx/nginx.git
synced 2024-12-04 13:59:00 +08:00
0b97b1ec6f
In recent Perl versions unpack("C*") unpacks wide characters by default,
likely since perl 5.10 (seen at least in perl 5.20). Replaced with
unpack("U0C*") instead to unpack bytes.
While here, improved style and updated my email.
49 lines
1.1 KiB
Perl
Executable File
49 lines
1.1 KiB
Perl
Executable File
#!/usr/bin/perl -w
|
|
|
|
# Convert unicode mappings to nginx configuration file format.
|
|
|
|
# You may find useful mappings in various places, including
|
|
# unicode.org official site:
|
|
#
|
|
# http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1251.TXT
|
|
# http://www.unicode.org/Public/MAPPINGS/VENDORS/MISC/KOI8-R.TXT
|
|
|
|
# Needs perl 5.6 or later.
|
|
|
|
# Written by Maxim Dounin, mdounin@mdounin.ru
|
|
|
|
###############################################################################
|
|
|
|
require 5.006;
|
|
|
|
while (<>) {
|
|
# Skip comments and empty lines
|
|
|
|
next if /^#/;
|
|
next if /^\s*$/;
|
|
chomp;
|
|
|
|
# Convert mappings
|
|
|
|
if (/^\s*0x(..)\s*0x(....)\s*(#.*)/) {
|
|
# Mapping <from-code> <unicode-code> "#" <unicode-name>
|
|
my $cs_code = $1;
|
|
my $un_code = $2;
|
|
my $un_name = $3;
|
|
|
|
# Produce UTF-8 sequence from character code;
|
|
|
|
my $un_utf8 = join('',
|
|
map { sprintf("%02X", $_) }
|
|
unpack("U0C*", pack("U", hex($un_code)))
|
|
);
|
|
|
|
print " $cs_code $un_utf8 ; $un_name\n";
|
|
|
|
} else {
|
|
warn "Unrecognized line: '$_'";
|
|
}
|
|
}
|
|
|
|
###############################################################################
|