view contrib/unicode2nginx/unicode-to-nginx.pl @ 394:05981f639d21 NGINX_0_7_9

nginx 0.7.9 *) Change: now ngx_http_charset_module works by default with following MIME types: text/html, text/css, text/xml, text/plain, text/vnd.wap.wml, application/x-javascript, and application/rss+xml. *) Feature: the "charset_types" and "addition_types" directives. *) Feature: now the "gzip_types", "ssi_types", and "sub_filter_types" directives use hash. *) Feature: the ngx_cpp_test_module. *) Feature: the "expires" directive supports daily time. *) Feature: the ngx_http_xslt_module improvements and bug fixing. Thanks to Denis F. Latypoff and Maxim Dounin. *) Bugfix: the "log_not_found" directive did not work for index files tests. *) Bugfix: HTTPS connections might hang, if kqueue, epoll, rtsig, or eventport methods were used; the bug had appeared in 0.7.7. *) Bugfix: if the "server_name", "valid_referers", and "map" directives used an "*.domain.tld" wildcard and exact name "domain.tld" was not set, then the exact name was matched by the wildcard; the bugs had appeared in 0.3.18.
author Igor Sysoev <http://sysoev.ru>
date Tue, 12 Aug 2008 00:00:00 +0400
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: '$_'";
	}
}

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