view contrib/unicode2nginx/unicode-to-nginx.pl @ 554:5c576ea5dbd9 NGINX_0_8_29

nginx 0.8.29 *) Change: now the "009" status code is written to an access log for proxied HTTP/0.9 responses. *) Feature: the "addition_types", "charset_types", "gzip_types", "ssi_types", "sub_filter_types", and "xslt_types" directives support an "*" parameter. *) Feature: GCC 4.1+ built-in atomic operations usage. Thanks to W-Mark Kubacki. *) Feature: the --with-libatomic[=DIR] option in the configure. Thanks to W-Mark Kubacki. *) Bugfix: listen unix domain socket had limited access rights. *) Bugfix: cached HTTP/0.9 responses were handled incorrectly. *) Bugfix: regular expression named captures given by "?P<...>" did not work in a "server_name" directive. Thanks to Maxim Dounin.
author Igor Sysoev <http://sysoev.ru>
date Mon, 30 Nov 2009 00:00:00 +0300
parents fa32d59d9a15
children
line wrap: on
line source

#!/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@rambler-co.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", $_) } unpack("C*", pack("U", hex($un_code))));

		print "    $cs_code  $un_utf8 ; $un_name\n";

	} else {
		warn "Unrecognized line: '$_'";
	}
}

###############################################################################